Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "The rest of MM"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (101 commits)
  mm, compaction: simplify contended compaction handling
  mm, compaction: introduce direct compaction priority
  mm, thp: remove __GFP_NORETRY from khugepaged and madvised allocations
  mm, page_alloc: make THP-specific decisions more generic
  mm, page_alloc: restructure direct compaction handling in slowpath
  mm, page_alloc: don't retry initial attempt in slowpath
  mm, page_alloc: set alloc_flags only once in slowpath
  lib/stackdepot.c: use __GFP_NOWARN for stack allocations
  mm, kasan: switch SLUB to stackdepot, enable memory quarantine for SLUB
  mm, kasan: account for object redzone in SLUB's nearest_obj()
  mm: fix use-after-free if memory allocation failed in vma_adjust()
  zsmalloc: Delete an unnecessary check before the function call "iput"
  mm/memblock.c: fix index adjustment error in __next_mem_range_rev()
  mem-hotplug: alloc new page from a nearest neighbor node when mem-offline
  mm: optimize copy_page_to/from_iter_iovec
  mm: add cond_resched() to generic_swapfile_activate()
  Revert "mm, mempool: only set __GFP_NOMEMALLOC if there are free elements"
  mm, compaction: don't isolate PageWriteback pages in MIGRATE_SYNC_LIGHT mode
  mm: hwpoison: remove incorrect comments
  make __section_nr() more efficient
  ...

Documentation/cgroup-v1/memcg_test.txt

@@ -107,9 +107,9 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 
 8. LRU
         Each memcg has its own private LRU. Now, its handling is under global
-	VM's control (means that it's handled under global zone->lru_lock).
+	VM's control (means that it's handled under global zone_lru_lock).
 	Almost all routines around memcg's LRU is called by global LRU's
-	list management functions under zone->lru_lock().
+	list management functions under zone_lru_lock().
 
 	A special function is mem_cgroup_isolate_pages(). This scans
 	memcg's private LRU and call __isolate_lru_page() to extract a page

Documentation/cgroup-v1/memory.txt

@@ -267,11 +267,11 @@ When oom event notifier is registered, event will be delivered.
    Other lock order is following:
    PG_locked.
    mm->page_table_lock
-       zone->lru_lock
+       zone_lru_lock
 	  lock_page_cgroup.
   In many cases, just lock_page_cgroup() is called.
   per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
-  zone->lru_lock, it has no lock of its own.
+  zone_lru_lock, it has no lock of its own.
 
 2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)
 

arch/arm64/mm/init.c

@@ -224,7 +224,7 @@ void __init arm64_memblock_init(void)
 	 * via the linear mapping.
 	 */
 	if (memory_limit != (phys_addr_t)ULLONG_MAX) {
-		memblock_enforce_memory_limit(memory_limit);
+		memblock_mem_limit_remove_map(memory_limit);
 		memblock_add(__pa(_text), (u64)(_end - _text));
 	}
 

arch/s390/appldata/appldata_mem.c

@@ -102,7 +102,7 @@ static void appldata_get_mem_data(void *data)
 	mem_data->totalhigh = P2K(val.totalhigh);
 	mem_data->freehigh  = P2K(val.freehigh);
 	mem_data->bufferram = P2K(val.bufferram);
-	mem_data->cached    = P2K(global_page_state(NR_FILE_PAGES)
+	mem_data->cached    = P2K(global_node_page_state(NR_FILE_PAGES)
 				- val.bufferram);
 
 	si_swapinfo(&val);

arch/tile/mm/pgtable.c

@@ -45,20 +45,20 @@ void show_mem(unsigned int filter)
 	struct zone *zone;
 
 	pr_err("Active:%lu inactive:%lu dirty:%lu writeback:%lu unstable:%lu free:%lu\n slab:%lu mapped:%lu pagetables:%lu bounce:%lu pagecache:%lu swap:%lu\n",
-	       (global_page_state(NR_ACTIVE_ANON) +
-		global_page_state(NR_ACTIVE_FILE)),
-	       (global_page_state(NR_INACTIVE_ANON) +
-		global_page_state(NR_INACTIVE_FILE)),
-	       global_page_state(NR_FILE_DIRTY),
-	       global_page_state(NR_WRITEBACK),
-	       global_page_state(NR_UNSTABLE_NFS),
+	       (global_node_page_state(NR_ACTIVE_ANON) +
+		global_node_page_state(NR_ACTIVE_FILE)),
+	       (global_node_page_state(NR_INACTIVE_ANON) +
+		global_node_page_state(NR_INACTIVE_FILE)),
+	       global_node_page_state(NR_FILE_DIRTY),
+	       global_node_page_state(NR_WRITEBACK),
+	       global_node_page_state(NR_UNSTABLE_NFS),
 	       global_page_state(NR_FREE_PAGES),
 	       (global_page_state(NR_SLAB_RECLAIMABLE) +
 		global_page_state(NR_SLAB_UNRECLAIMABLE)),
-	       global_page_state(NR_FILE_MAPPED),
+	       global_node_page_state(NR_FILE_MAPPED),
 	       global_page_state(NR_PAGETABLE),
 	       global_page_state(NR_BOUNCE),
-	       global_page_state(NR_FILE_PAGES),
+	       global_node_page_state(NR_FILE_PAGES),
 	       get_nr_swap_pages());
 
 	for_each_zone(zone) {

drivers/base/node.c

@@ -56,6 +56,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 {
 	int n;
 	int nid = dev->id;
+	struct pglist_data *pgdat = NODE_DATA(nid);
 	struct sysinfo i;
 
 	si_meminfo_node(&i, nid);
@@ -74,16 +75,16 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(i.totalram),
 		       nid, K(i.freeram),
 		       nid, K(i.totalram - i.freeram),
-		       nid, K(node_page_state(nid, NR_ACTIVE_ANON) +
-				node_page_state(nid, NR_ACTIVE_FILE)),
-		       nid, K(node_page_state(nid, NR_INACTIVE_ANON) +
-				node_page_state(nid, NR_INACTIVE_FILE)),
-		       nid, K(node_page_state(nid, NR_ACTIVE_ANON)),
-		       nid, K(node_page_state(nid, NR_INACTIVE_ANON)),
-		       nid, K(node_page_state(nid, NR_ACTIVE_FILE)),
-		       nid, K(node_page_state(nid, NR_INACTIVE_FILE)),
-		       nid, K(node_page_state(nid, NR_UNEVICTABLE)),
-		       nid, K(node_page_state(nid, NR_MLOCK)));
+		       nid, K(node_page_state(pgdat, NR_ACTIVE_ANON) +
+				node_page_state(pgdat, NR_ACTIVE_FILE)),
+		       nid, K(node_page_state(pgdat, NR_INACTIVE_ANON) +
+				node_page_state(pgdat, NR_INACTIVE_FILE)),
+		       nid, K(node_page_state(pgdat, NR_ACTIVE_ANON)),
+		       nid, K(node_page_state(pgdat, NR_INACTIVE_ANON)),
+		       nid, K(node_page_state(pgdat, NR_ACTIVE_FILE)),
+		       nid, K(node_page_state(pgdat, NR_INACTIVE_FILE)),
+		       nid, K(node_page_state(pgdat, NR_UNEVICTABLE)),
+		       nid, K(sum_zone_node_page_state(nid, NR_MLOCK)));
 
 #ifdef CONFIG_HIGHMEM
 	n += sprintf(buf + n,
@@ -117,31 +118,30 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       "Node %d ShmemPmdMapped: %8lu kB\n"
 #endif
 			,
-		       nid, K(node_page_state(nid, NR_FILE_DIRTY)),
-		       nid, K(node_page_state(nid, NR_WRITEBACK)),
-		       nid, K(node_page_state(nid, NR_FILE_PAGES)),
-		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
-		       nid, K(node_page_state(nid, NR_ANON_PAGES)),
+		       nid, K(node_page_state(pgdat, NR_FILE_DIRTY)),
+		       nid, K(node_page_state(pgdat, NR_WRITEBACK)),
+		       nid, K(node_page_state(pgdat, NR_FILE_PAGES)),
+		       nid, K(node_page_state(pgdat, NR_FILE_MAPPED)),
+		       nid, K(node_page_state(pgdat, NR_ANON_MAPPED)),
 		       nid, K(i.sharedram),
-		       nid, node_page_state(nid, NR_KERNEL_STACK) *
-				THREAD_SIZE / 1024,
-		       nid, K(node_page_state(nid, NR_PAGETABLE)),
-		       nid, K(node_page_state(nid, NR_UNSTABLE_NFS)),
-		       nid, K(node_page_state(nid, NR_BOUNCE)),
-		       nid, K(node_page_state(nid, NR_WRITEBACK_TEMP)),
-		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE) +
-				node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
-		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE)),
+		       nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK_KB),
+		       nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)),
+		       nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
+		       nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
+		       nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
+		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE) +
+				sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
+		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE)),
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
-		       nid, K(node_page_state(nid, NR_ANON_THPS) *
+		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
+		       nid, K(node_page_state(pgdat, NR_ANON_THPS) *
 				       HPAGE_PMD_NR),
-		       nid, K(node_page_state(nid, NR_SHMEM_THPS) *
+		       nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
 				       HPAGE_PMD_NR),
-		       nid, K(node_page_state(nid, NR_SHMEM_PMDMAPPED) *
+		       nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
 				       HPAGE_PMD_NR));
 #else
-		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
+		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
 #endif
 	n += hugetlb_report_node_meminfo(nid, buf + n);
 	return n;
@@ -160,12 +160,12 @@ static ssize_t node_read_numastat(struct device *dev,
 		       "interleave_hit %lu\n"
 		       "local_node %lu\n"
 		       "other_node %lu\n",
-		       node_page_state(dev->id, NUMA_HIT),
-		       node_page_state(dev->id, NUMA_MISS),
-		       node_page_state(dev->id, NUMA_FOREIGN),
-		       node_page_state(dev->id, NUMA_INTERLEAVE_HIT),
-		       node_page_state(dev->id, NUMA_LOCAL),
-		       node_page_state(dev->id, NUMA_OTHER));
+		       sum_zone_node_page_state(dev->id, NUMA_HIT),
+		       sum_zone_node_page_state(dev->id, NUMA_MISS),
+		       sum_zone_node_page_state(dev->id, NUMA_FOREIGN),
+		       sum_zone_node_page_state(dev->id, NUMA_INTERLEAVE_HIT),
+		       sum_zone_node_page_state(dev->id, NUMA_LOCAL),
+		       sum_zone_node_page_state(dev->id, NUMA_OTHER));
 }
 static DEVICE_ATTR(numastat, S_IRUGO, node_read_numastat, NULL);
 
@@ -173,12 +173,18 @@ static ssize_t node_read_vmstat(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	int nid = dev->id;
+	struct pglist_data *pgdat = NODE_DATA(nid);
 	int i;
 	int n = 0;
 
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
 		n += sprintf(buf+n, "%s %lu\n", vmstat_text[i],
-			     node_page_state(nid, i));
+			     sum_zone_node_page_state(nid, i));
+
+	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+		n += sprintf(buf+n, "%s %lu\n",
+			     vmstat_text[i + NR_VM_ZONE_STAT_ITEMS],
+			     node_page_state(pgdat, i));
 
 	return n;
 }

drivers/staging/android/lowmemorykiller.c

@@ -72,10 +72,10 @@ static unsigned long lowmem_deathpending_timeout;
 static unsigned long lowmem_count(struct shrinker *s,
 				  struct shrink_control *sc)
 {
-	return global_page_state(NR_ACTIVE_ANON) +
-		global_page_state(NR_ACTIVE_FILE) +
-		global_page_state(NR_INACTIVE_ANON) +
-		global_page_state(NR_INACTIVE_FILE);
+	return global_node_page_state(NR_ACTIVE_ANON) +
+		global_node_page_state(NR_ACTIVE_FILE) +
+		global_node_page_state(NR_INACTIVE_ANON) +
+		global_node_page_state(NR_INACTIVE_FILE);
 }
 
 static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
@@ -91,8 +91,8 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
 	short selected_oom_score_adj;
 	int array_size = ARRAY_SIZE(lowmem_adj);
 	int other_free = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
-	int other_file = global_page_state(NR_FILE_PAGES) -
-						global_page_state(NR_SHMEM) -
+	int other_file = global_node_page_state(NR_FILE_PAGES) -
+						global_node_page_state(NR_SHMEM) -
 						total_swapcache_pages();
 
 	if (lowmem_adj_size < array_size)

drivers/staging/lustre/lustre/osc/osc_cache.c

@@ -1864,7 +1864,8 @@ void osc_dec_unstable_pages(struct ptlrpc_request *req)
 	LASSERT(page_count >= 0);
 
 	for (i = 0; i < page_count; i++)
-		dec_zone_page_state(desc->bd_iov[i].kiov_page, NR_UNSTABLE_NFS);
+		dec_node_page_state(desc->bd_iov[i].kiov_page,
+							NR_UNSTABLE_NFS);
 
 	atomic_sub(page_count, &cli->cl_cache->ccc_unstable_nr);
 	LASSERT(atomic_read(&cli->cl_cache->ccc_unstable_nr) >= 0);
@@ -1898,7 +1899,8 @@ void osc_inc_unstable_pages(struct ptlrpc_request *req)
 	LASSERT(page_count >= 0);
 
 	for (i = 0; i < page_count; i++)
-		inc_zone_page_state(desc->bd_iov[i].kiov_page, NR_UNSTABLE_NFS);
+		inc_node_page_state(desc->bd_iov[i].kiov_page,
+							NR_UNSTABLE_NFS);
 
 	LASSERT(atomic_read(&cli->cl_cache->ccc_unstable_nr) >= 0);
 	atomic_add(page_count, &cli->cl_cache->ccc_unstable_nr);

fs/fs-writeback.c

@@ -1807,8 +1807,8 @@ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
  */
 static unsigned long get_nr_dirty_pages(void)
 {
-	return global_page_state(NR_FILE_DIRTY) +
-		global_page_state(NR_UNSTABLE_NFS) +
+	return global_node_page_state(NR_FILE_DIRTY) +
+		global_node_page_state(NR_UNSTABLE_NFS) +
 		get_nr_dirty_inodes();
 }
 

fs/fuse/file.c

@@ -1452,7 +1452,7 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
 	list_del(&req->writepages_entry);
 	for (i = 0; i < req->num_pages; i++) {
 		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
-		dec_zone_page_state(req->pages[i], NR_WRITEBACK_TEMP);
+		dec_node_page_state(req->pages[i], NR_WRITEBACK_TEMP);
 		wb_writeout_inc(&bdi->wb);
 	}
 	wake_up(&fi->page_waitq);
@@ -1642,7 +1642,7 @@ static int fuse_writepage_locked(struct page *page)
 	req->inode = inode;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
-	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
+	inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	spin_lock(&fc->lock);
 	list_add(&req->writepages_entry, &fi->writepages);
@@ -1756,7 +1756,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
 		spin_unlock(&fc->lock);
 
 		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
-		dec_zone_page_state(page, NR_WRITEBACK_TEMP);
+		dec_node_page_state(page, NR_WRITEBACK_TEMP);
 		wb_writeout_inc(&bdi->wb);
 		fuse_writepage_free(fc, new_req);
 		fuse_request_free(new_req);
@@ -1855,7 +1855,7 @@ static int fuse_writepages_fill(struct page *page,
 	req->page_descs[req->num_pages].length = PAGE_SIZE;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
-	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
+	inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;
 	if (is_writeback && fuse_writepage_in_flight(req, page)) {

fs/nfs/internal.h

@@ -623,7 +623,7 @@ void nfs_mark_page_unstable(struct page *page, struct nfs_commit_info *cinfo)
 	if (!cinfo->dreq) {
 		struct inode *inode = page_file_mapping(page)->host;
 
-		inc_zone_page_state(page, NR_UNSTABLE_NFS);
+		inc_node_page_state(page, NR_UNSTABLE_NFS);
 		inc_wb_stat(&inode_to_bdi(inode)->wb, WB_RECLAIMABLE);
 		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 	}

fs/nfs/write.c

@@ -898,7 +898,7 @@ nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
 static void
 nfs_clear_page_commit(struct page *page)
 {
-	dec_zone_page_state(page, NR_UNSTABLE_NFS);
+	dec_node_page_state(page, NR_UNSTABLE_NFS);
 	dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb,
 		    WB_RECLAIMABLE);
 }

fs/proc/base.c

@@ -1024,23 +1024,107 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
 	char buffer[PROC_NUMBUF];
 	int oom_adj = OOM_ADJUST_MIN;
 	size_t len;
-	unsigned long flags;
 
 	if (!task)
 		return -ESRCH;
-	if (lock_task_sighand(task, &flags)) {
-		if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
-			oom_adj = OOM_ADJUST_MAX;
-		else
-			oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
-				  OOM_SCORE_ADJ_MAX;
-		unlock_task_sighand(task, &flags);
-	}
+	if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
+		oom_adj = OOM_ADJUST_MAX;
+	else
+		oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
+			  OOM_SCORE_ADJ_MAX;
 	put_task_struct(task);
 	len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
 	return simple_read_from_buffer(buf, count, ppos, buffer, len);
 }
 
+static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
+{
+	static DEFINE_MUTEX(oom_adj_mutex);
+	struct mm_struct *mm = NULL;
+	struct task_struct *task;
+	int err = 0;
+
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		return -ESRCH;
+
+	mutex_lock(&oom_adj_mutex);
+	if (legacy) {
+		if (oom_adj < task->signal->oom_score_adj &&
+				!capable(CAP_SYS_RESOURCE)) {
+			err = -EACCES;
+			goto err_unlock;
+		}
+		/*
+		 * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
+		 * /proc/pid/oom_score_adj instead.
+		 */
+		pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+			  current->comm, task_pid_nr(current), task_pid_nr(task),
+			  task_pid_nr(task));
+	} else {
+		if ((short)oom_adj < task->signal->oom_score_adj_min &&
+				!capable(CAP_SYS_RESOURCE)) {
+			err = -EACCES;
+			goto err_unlock;
+		}
+	}
+
+	/*
+	 * Make sure we will check other processes sharing the mm if this is
+	 * not vfrok which wants its own oom_score_adj.
+	 * pin the mm so it doesn't go away and get reused after task_unlock
+	 */
+	if (!task->vfork_done) {
+		struct task_struct *p = find_lock_task_mm(task);
+
+		if (p) {
+			if (atomic_read(&p->mm->mm_users) > 1) {
+				mm = p->mm;
+				atomic_inc(&mm->mm_count);
+			}
+			task_unlock(p);
+		}
+	}
+
+	task->signal->oom_score_adj = oom_adj;
+	if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
+		task->signal->oom_score_adj_min = (short)oom_adj;
+	trace_oom_score_adj_update(task);
+
+	if (mm) {
+		struct task_struct *p;
+
+		rcu_read_lock();
+		for_each_process(p) {
+			if (same_thread_group(task, p))
+				continue;
+
+			/* do not touch kernel threads or the global init */
+			if (p->flags & PF_KTHREAD || is_global_init(p))
+				continue;
+
+			task_lock(p);
+			if (!p->vfork_done && process_shares_mm(p, mm)) {
+				pr_info("updating oom_score_adj for %d (%s) from %d to %d because it shares mm with %d (%s). Report if this is unexpected.\n",
+						task_pid_nr(p), p->comm,
+						p->signal->oom_score_adj, oom_adj,
+						task_pid_nr(task), task->comm);
+				p->signal->oom_score_adj = oom_adj;
+				if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
+					p->signal->oom_score_adj_min = (short)oom_adj;
+			}
+			task_unlock(p);
+		}
+		rcu_read_unlock();
+		mmdrop(mm);
+	}
+err_unlock:
+	mutex_unlock(&oom_adj_mutex);
+	put_task_struct(task);
+	return err;
+}
+
 /*
  * /proc/pid/oom_adj exists solely for backwards compatibility with previous
  * kernels.  The effective policy is defined by oom_score_adj, which has a
@@ -1054,10 +1138,8 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
 static ssize_t oom_adj_write(struct file *file, const char __user *buf,
 			     size_t count, loff_t *ppos)
 {
-	struct task_struct *task;
 	char buffer[PROC_NUMBUF];
 	int oom_adj;
-	unsigned long flags;
 	int err;
 
 	memset(buffer, 0, sizeof(buffer));
@@ -1077,23 +1159,6 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	task = get_proc_task(file_inode(file));
-	if (!task) {
-		err = -ESRCH;
-		goto out;
-	}
-
-	task_lock(task);
-	if (!task->mm) {
-		err = -EINVAL;
-		goto err_task_lock;
-	}
-
-	if (!lock_task_sighand(task, &flags)) {
-		err = -ESRCH;
-		goto err_task_lock;
-	}
-
 	/*
 	 * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
 	 * value is always attainable.
@@ -1103,27 +1168,7 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf,
 	else
 		oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
 
-	if (oom_adj < task->signal->oom_score_adj &&
-	    !capable(CAP_SYS_RESOURCE)) {
-		err = -EACCES;
-		goto err_sighand;
-	}
-
-	/*
-	 * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
-	 * /proc/pid/oom_score_adj instead.
-	 */
-	pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
-		  current->comm, task_pid_nr(current), task_pid_nr(task),
-		  task_pid_nr(task));
-
-	task->signal->oom_score_adj = oom_adj;
-	trace_oom_score_adj_update(task);
-err_sighand:
-	unlock_task_sighand(task, &flags);
-err_task_lock:
-	task_unlock(task);
-	put_task_struct(task);
+	err = __set_oom_adj(file, oom_adj, true);
 out:
 	return err < 0 ? err : count;
 }
@@ -1140,15 +1185,11 @@ static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
 	struct task_struct *task = get_proc_task(file_inode(file));
 	char buffer[PROC_NUMBUF];
 	short oom_score_adj = OOM_SCORE_ADJ_MIN;
-	unsigned long flags;
 	size_t len;
 
 	if (!task)
 		return -ESRCH;
-	if (lock_task_sighand(task, &flags)) {
-		oom_score_adj = task->signal->oom_score_adj;
-		unlock_task_sighand(task, &flags);
-	}
+	oom_score_adj = task->signal->oom_score_adj;
 	put_task_struct(task);
 	len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj);
 	return simple_read_from_buffer(buf, count, ppos, buffer, len);
@@ -1157,9 +1198,7 @@ static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
 static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 					size_t count, loff_t *ppos)
 {
-	struct task_struct *task;
 	char buffer[PROC_NUMBUF];
-	unsigned long flags;
 	int oom_score_adj;
 	int err;
 
@@ -1180,39 +1219,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	task = get_proc_task(file_inode(file));
-	if (!task) {
-		err = -ESRCH;
-		goto out;
-	}
-
-	task_lock(task);
-	if (!task->mm) {
-		err = -EINVAL;
-		goto err_task_lock;
-	}
-
-	if (!lock_task_sighand(task, &flags)) {
-		err = -ESRCH;
-		goto err_task_lock;
-	}
-
-	if ((short)oom_score_adj < task->signal->oom_score_adj_min &&
-			!capable(CAP_SYS_RESOURCE)) {
-		err = -EACCES;
-		goto err_sighand;
-	}
-
-	task->signal->oom_score_adj = (short)oom_score_adj;
-	if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
-		task->signal->oom_score_adj_min = (short)oom_score_adj;
-	trace_oom_score_adj_update(task);
-
-err_sighand:
-	unlock_task_sighand(task, &flags);
-err_task_lock:
-	task_unlock(task);
-	put_task_struct(task);
+	err = __set_oom_adj(file, oom_score_adj, false);
 out:
 	return err < 0 ? err : count;
 }

fs/proc/meminfo.c

@@ -40,7 +40,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	si_swapinfo(&i);
 	committed = percpu_counter_read_positive(&vm_committed_as);
 
-	cached = global_page_state(NR_FILE_PAGES) -
+	cached = global_node_page_state(NR_FILE_PAGES) -
 			total_swapcache_pages() - i.bufferram;
 	if (cached < 0)
 		cached = 0;
@@ -138,23 +138,23 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #endif
 		K(i.totalswap),
 		K(i.freeswap),
-		K(global_page_state(NR_FILE_DIRTY)),
-		K(global_page_state(NR_WRITEBACK)),
-		K(global_page_state(NR_ANON_PAGES)),
-		K(global_page_state(NR_FILE_MAPPED)),
+		K(global_node_page_state(NR_FILE_DIRTY)),
+		K(global_node_page_state(NR_WRITEBACK)),
+		K(global_node_page_state(NR_ANON_MAPPED)),
+		K(global_node_page_state(NR_FILE_MAPPED)),
 		K(i.sharedram),
 		K(global_page_state(NR_SLAB_RECLAIMABLE) +
 				global_page_state(NR_SLAB_UNRECLAIMABLE)),
 		K(global_page_state(NR_SLAB_RECLAIMABLE)),
 		K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
-		global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024,
+		global_page_state(NR_KERNEL_STACK_KB),
 		K(global_page_state(NR_PAGETABLE)),
 #ifdef CONFIG_QUICKLIST
 		K(quicklist_total_size()),
 #endif
-		K(global_page_state(NR_UNSTABLE_NFS)),
+		K(global_node_page_state(NR_UNSTABLE_NFS)),
 		K(global_page_state(NR_BOUNCE)),
-		K(global_page_state(NR_WRITEBACK_TEMP)),
+		K(global_node_page_state(NR_WRITEBACK_TEMP)),
 		K(vm_commit_limit()),
 		K(committed),
 		(unsigned long)VMALLOC_TOTAL >> 10,
@@ -164,9 +164,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		, K(global_page_state(NR_ANON_THPS) * HPAGE_PMD_NR)
-		, K(global_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR)
-		, K(global_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)
+		, K(global_node_page_state(NR_ANON_THPS) * HPAGE_PMD_NR)
+		, K(global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR)
+		, K(global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)
 #endif
 #ifdef CONFIG_CMA
 		, K(totalcma_pages)

include/linux/backing-dev.h

@@ -197,7 +197,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 }
 
 long congestion_wait(int sync, long timeout);
-long wait_iff_congested(struct zone *zone, int sync, long timeout);
+long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout);
 int pdflush_proc_obsolete(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp, loff_t *ppos);
 

include/linux/compaction.h

@@ -1,6 +1,18 @@
 #ifndef _LINUX_COMPACTION_H
 #define _LINUX_COMPACTION_H
 
+/*
+ * Determines how hard direct compaction should try to succeed.
+ * Lower value means higher priority, analogically to reclaim priority.
+ */
+enum compact_priority {
+	COMPACT_PRIO_SYNC_LIGHT,
+	MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT,
+	DEF_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT,
+	COMPACT_PRIO_ASYNC,
+	INIT_COMPACT_PRIORITY = COMPACT_PRIO_ASYNC
+};
+
 /* Return values for compact_zone() and try_to_compact_pages() */
 /* When adding new states, please adjust include/trace/events/compaction.h */
 enum compact_result {
@@ -43,14 +55,6 @@ enum compact_result {
 	COMPACT_PARTIAL,
 };
 
-/* Used to signal whether compaction detected need_sched() or lock contention */
-/* No contention detected */
-#define COMPACT_CONTENDED_NONE	0
-/* Either need_sched() was true or fatal signal pending */
-#define COMPACT_CONTENDED_SCHED	1
-/* Zone lock or lru_lock was contended in async compaction */
-#define COMPACT_CONTENDED_LOCK	2
-
 struct alloc_context; /* in mm/internal.h */
 
 #ifdef CONFIG_COMPACTION
@@ -64,9 +68,8 @@ extern int sysctl_compact_unevictable_allowed;
 
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
-			unsigned int order,
-		unsigned int alloc_flags, const struct alloc_context *ac,
-		enum migrate_mode mode, int *contended);
+		unsigned int order, unsigned int alloc_flags,
+		const struct alloc_context *ac, enum compact_priority prio);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern enum compact_result compaction_suitable(struct zone *zone, int order,
@@ -151,14 +154,6 @@ extern void kcompactd_stop(int nid);
 extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx);
 
 #else
-static inline enum compact_result try_to_compact_pages(gfp_t gfp_mask,
-			unsigned int order, int alloc_flags,
-			const struct alloc_context *ac,
-			enum migrate_mode mode, int *contended)
-{
-	return COMPACT_CONTINUE;
-}
-
 static inline void compact_pgdat(pg_data_t *pgdat, int order)
 {
 }

include/linux/gfp.h

@@ -237,9 +237,11 @@ struct vm_area_struct;
  *   are expected to be movable via page reclaim or page migration. Typically,
  *   pages on the LRU would also be allocated with GFP_HIGHUSER_MOVABLE.
  *
- * GFP_TRANSHUGE is used for THP allocations. They are compound allocations
- *   that will fail quickly if memory is not available and will not wake
- *   kswapd on failure.
+ * GFP_TRANSHUGE and GFP_TRANSHUGE_LIGHT are used for THP allocations. They are
+ *   compound allocations that will generally fail quickly if memory is not
+ *   available and will not wake kswapd/kcompactd on failure. The _LIGHT
+ *   version does not attempt reclaim/compaction at all and is by default used
+ *   in page fault path, while the non-light is used by khugepaged.
  */
 #define GFP_ATOMIC	(__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
 #define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
@@ -254,9 +256,9 @@ struct vm_area_struct;
 #define GFP_DMA32	__GFP_DMA32
 #define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
 #define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE)
-#define GFP_TRANSHUGE	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
-			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \
-			 ~__GFP_RECLAIM)
+#define GFP_TRANSHUGE_LIGHT	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
+			 __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
+#define GFP_TRANSHUGE	(GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
 
 /* Convert GFP flags to their corresponding migrate type */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)

include/linux/huge_mm.h

@@ -11,7 +11,7 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  unsigned long addr,
 					  pmd_t *pmd,
 					  unsigned int flags);
-extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
+extern bool madvise_free_huge_pmd(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pmd_t *pmd, unsigned long addr, unsigned long next);
 extern int zap_huge_pmd(struct mmu_gather *tlb,

include/linux/kasan.h

@@ -77,6 +77,7 @@ void kasan_free_shadow(const struct vm_struct *vm);
 
 size_t ksize(const void *);
 static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); }
+size_t kasan_metadata_size(struct kmem_cache *cache);
 
 #else /* CONFIG_KASAN */
 
@@ -121,6 +122,7 @@ static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
 static inline void kasan_free_shadow(const struct vm_struct *vm) {}
 
 static inline void kasan_unpoison_slab(const void *ptr) { }
+static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
 
 #endif /* CONFIG_KASAN */
 

include/linux/kdb.h

@@ -177,7 +177,7 @@ extern int kdb_get_kbd_char(void);
 static inline
 int kdb_process_cpu(const struct task_struct *p)
 {
-	unsigned int cpu = task_thread_info(p)->cpu;
+	unsigned int cpu = task_cpu(p);
 	if (cpu > num_possible_cpus())
 		cpu = 0;
 	return cpu;

include/linux/memblock.h

@@ -332,6 +332,7 @@ phys_addr_t memblock_mem_size(unsigned long limit_pfn);
 phys_addr_t memblock_start_of_DRAM(void);
 phys_addr_t memblock_end_of_DRAM(void);
 void memblock_enforce_memory_limit(phys_addr_t memory_limit);
+void memblock_mem_limit_remove_map(phys_addr_t limit);
 bool memblock_is_memory(phys_addr_t addr);
 int memblock_is_map_memory(phys_addr_t addr);
 int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);

include/linux/memcontrol.h

@@ -52,7 +52,7 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
 	/* default hierarchy stats */
-	MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS,
+	MEMCG_KERNEL_STACK_KB = MEM_CGROUP_STAT_NSTATS,
 	MEMCG_SLAB_RECLAIMABLE,
 	MEMCG_SLAB_UNRECLAIMABLE,
 	MEMCG_SOCK,
@@ -60,7 +60,7 @@ enum mem_cgroup_stat_index {
 };
 
 struct mem_cgroup_reclaim_cookie {
-	struct zone *zone;
+	pg_data_t *pgdat;
 	int priority;
 	unsigned int generation;
 };
@@ -118,7 +118,7 @@ struct mem_cgroup_reclaim_iter {
 /*
  * per-zone information in memory controller.
  */
-struct mem_cgroup_per_zone {
+struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
 	unsigned long		lru_size[NR_LRU_LISTS];
 
@@ -132,10 +132,6 @@ struct mem_cgroup_per_zone {
 						/* use container_of	   */
 };
 
-struct mem_cgroup_per_node {
-	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
-};
-
 struct mem_cgroup_threshold {
 	struct eventfd_ctx *eventfd;
 	unsigned long threshold;
@@ -314,8 +310,46 @@ void mem_cgroup_uncharge_list(struct list_head *page_list);
 
 void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
 
-struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
-struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
+static struct mem_cgroup_per_node *
+mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
+{
+	return memcg->nodeinfo[nid];
+}
+
+/**
+ * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
+ * @node: node of the wanted lruvec
+ * @memcg: memcg of the wanted lruvec
+ *
+ * Returns the lru list vector holding pages for a given @node or a given
+ * @memcg and @zone. This can be the node lruvec, if the memory controller
+ * is disabled.
+ */
+static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
+				struct mem_cgroup *memcg)
+{
+	struct mem_cgroup_per_node *mz;
+	struct lruvec *lruvec;
+
+	if (mem_cgroup_disabled()) {
+		lruvec = node_lruvec(pgdat);
+		goto out;
+	}
+
+	mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
+	lruvec = &mz->lruvec;
+out:
+	/*
+	 * Since a node can be onlined after the mem_cgroup was created,
+	 * we have to be prepared to initialize lruvec->pgdat here;
+	 * and if offlined then reonlined, we need to reinitialize it.
+	 */
+	if (unlikely(lruvec->pgdat != pgdat))
+		lruvec->pgdat = pgdat;
+	return lruvec;
+}
+
+struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
 
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
@@ -404,9 +438,9 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 static inline
 unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	return mz->lru_size[lru];
 }
 
@@ -477,7 +511,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 	mem_cgroup_update_page_stat(page, idx, -1);
 }
 
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
@@ -568,16 +602,16 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new)
 {
 }
 
-static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
-						    struct mem_cgroup *memcg)
+static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
+				struct mem_cgroup *memcg)
 {
-	return &zone->lruvec;
+	return node_lruvec(pgdat);
 }
 
 static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
-						    struct zone *zone)
+						    struct pglist_data *pgdat)
 {
-	return &zone->lruvec;
+	return &pgdat->lruvec;
 }
 
 static inline bool mm_match_cgroup(struct mm_struct *mm,
@@ -681,7 +715,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 }
 
 static inline
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 					    gfp_t gfp_mask,
 					    unsigned long *total_scanned)
 {

include/linux/memremap.h

@@ -26,7 +26,7 @@ struct vmem_altmap {
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
 void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
 
-#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_ZONE_DEVICE)
+#ifdef CONFIG_ZONE_DEVICE
 struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start);
 #else
 static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)

include/linux/mm.h

@@ -933,6 +933,11 @@ static inline struct zone *page_zone(const struct page *page)
 	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
 }
 
+static inline pg_data_t *page_pgdat(const struct page *page)
+{
+	return NODE_DATA(page_to_nid(page));
+}
+
 #ifdef SECTION_IN_PAGE_FLAGS
 static inline void set_page_section(struct page *page, unsigned long section)
 {
@@ -973,11 +978,21 @@ static inline struct mem_cgroup *page_memcg(struct page *page)
 {
 	return page->mem_cgroup;
 }
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return READ_ONCE(page->mem_cgroup);
+}
 #else
 static inline struct mem_cgroup *page_memcg(struct page *page)
 {
 	return NULL;
 }
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return NULL;
+}
 #endif
 
 /*
@@ -2284,6 +2299,8 @@ static inline int in_gate_area(struct mm_struct *mm, unsigned long addr)
 }
 #endif	/* __HAVE_ARCH_GATE_AREA */
 
+extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm);
+
 #ifdef CONFIG_SYSCTL
 extern int sysctl_drop_caches;
 int drop_caches_sysctl_handler(struct ctl_table *, int,

include/linux/mm_inline.h

@@ -23,25 +23,30 @@ static inline int page_is_file_cache(struct page *page)
 }
 
 static __always_inline void __update_lru_size(struct lruvec *lruvec,
-				enum lru_list lru, int nr_pages)
+				enum lru_list lru, enum zone_type zid,
+				int nr_pages)
 {
-	__mod_zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru, nr_pages);
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
+	__mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages);
+	__mod_zone_page_state(&pgdat->node_zones[zid],
+				NR_ZONE_LRU_BASE + lru, nr_pages);
 }
 
 static __always_inline void update_lru_size(struct lruvec *lruvec,
-				enum lru_list lru, int nr_pages)
+				enum lru_list lru, enum zone_type zid,
+				int nr_pages)
 {
+	__update_lru_size(lruvec, lru, zid, nr_pages);
 #ifdef CONFIG_MEMCG
 	mem_cgroup_update_lru_size(lruvec, lru, nr_pages);
-#else
-	__update_lru_size(lruvec, lru, nr_pages);
 #endif
 }
 
 static __always_inline void add_page_to_lru_list(struct page *page,
 				struct lruvec *lruvec, enum lru_list lru)
 {
-	update_lru_size(lruvec, lru, hpage_nr_pages(page));
+	update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page));
 	list_add(&page->lru, &lruvec->lists[lru]);
 }
 
@@ -49,7 +54,7 @@ static __always_inline void del_page_from_lru_list(struct page *page,
 				struct lruvec *lruvec, enum lru_list lru)
 {
 	list_del(&page->lru);
-	update_lru_size(lruvec, lru, -hpage_nr_pages(page));
+	update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page));
 }
 
 /**

include/linux/mm_types.h

@@ -118,7 +118,7 @@ struct page {
 	 */
 	union {
 		struct list_head lru;	/* Pageout list, eg. active_list
-					 * protected by zone->lru_lock !
+					 * protected by zone_lru_lock !
 					 * Can be used as a generic list
 					 * by the page owner.
 					 */

include/linux/mmzone.h

@@ -93,7 +93,7 @@ struct free_area {
 struct pglist_data;
 
 /*
- * zone->lock and zone->lru_lock are two of the hottest locks in the kernel.
+ * zone->lock and the zone lru_lock are two of the hottest locks in the kernel.
  * So add a wild amount of padding here to ensure that they fall into separate
  * cachelines.  There are very few zone structures in the machine, so space
  * consumption is not a concern here.
@@ -110,36 +110,20 @@ struct zone_padding {
 enum zone_stat_item {
 	/* First 128 byte cacheline (assuming 64 bit words) */
 	NR_FREE_PAGES,
-	NR_ALLOC_BATCH,
-	NR_LRU_BASE,
-	NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
-	NR_ACTIVE_ANON,		/*  "     "     "   "       "         */
-	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
-	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
-	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
+	NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
+	NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE,
+	NR_ZONE_ACTIVE_ANON,
+	NR_ZONE_INACTIVE_FILE,
+	NR_ZONE_ACTIVE_FILE,
+	NR_ZONE_UNEVICTABLE,
+	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
-	NR_ANON_PAGES,	/* Mapped anonymous pages */
-	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
-			   only modified from process context */
-	NR_FILE_PAGES,
-	NR_FILE_DIRTY,
-	NR_WRITEBACK,
 	NR_SLAB_RECLAIMABLE,
 	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
-	NR_KERNEL_STACK,
+	NR_KERNEL_STACK_KB,	/* measured in KiB */
 	/* Second 128 byte cacheline */
-	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_BOUNCE,
-	NR_VMSCAN_WRITE,
-	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */
-	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
-	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
-	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
-	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
-	NR_DIRTIED,		/* page dirtyings since bootup */
-	NR_WRITTEN,		/* page writings since bootup */
-	NR_PAGES_SCANNED,	/* pages scanned since last reclaim */
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	NR_ZSPAGES,		/* allocated in zsmalloc */
 #endif
@@ -151,14 +135,40 @@ enum zone_stat_item {
 	NUMA_LOCAL,		/* allocation from local node */
 	NUMA_OTHER,		/* allocation from other node */
 #endif
+	NR_FREE_CMA_PAGES,
+	NR_VM_ZONE_STAT_ITEMS };
+
+enum node_stat_item {
+	NR_LRU_BASE,
+	NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
+	NR_ACTIVE_ANON,		/*  "     "     "   "       "         */
+	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
+	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
+	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
+	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
+	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
+	NR_PAGES_SCANNED,	/* pages scanned since last reclaim */
 	WORKINGSET_REFAULT,
 	WORKINGSET_ACTIVATE,
 	WORKINGSET_NODERECLAIM,
-	NR_ANON_THPS,
+	NR_ANON_MAPPED,	/* Mapped anonymous pages */
+	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
+			   only modified from process context */
+	NR_FILE_PAGES,
+	NR_FILE_DIRTY,
+	NR_WRITEBACK,
+	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
+	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
 	NR_SHMEM_THPS,
 	NR_SHMEM_PMDMAPPED,
-	NR_FREE_CMA_PAGES,
-	NR_VM_ZONE_STAT_ITEMS };
+	NR_ANON_THPS,
+	NR_UNSTABLE_NFS,	/* NFS unstable pages */
+	NR_VMSCAN_WRITE,
+	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */
+	NR_DIRTIED,		/* page dirtyings since bootup */
+	NR_WRITTEN,		/* page writings since bootup */
+	NR_VM_NODE_STAT_ITEMS
+};
 
 /*
  * We do arithmetic on the LRU lists in various places in the code,
@@ -215,7 +225,7 @@ struct lruvec {
 	/* Evictions & activations on the inactive file list */
 	atomic_long_t			inactive_age;
 #ifdef CONFIG_MEMCG
-	struct zone			*zone;
+	struct pglist_data *pgdat;
 #endif
 };
 
@@ -267,6 +277,11 @@ struct per_cpu_pageset {
 #endif
 };
 
+struct per_cpu_nodestat {
+	s8 stat_threshold;
+	s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
+};
+
 #endif /* !__GENERATING_BOUNDS.H */
 
 enum zone_type {
@@ -348,22 +363,9 @@ struct zone {
 #ifdef CONFIG_NUMA
 	int node;
 #endif
-
-	/*
-	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
-	 * this zone's LRU.  Maintained by the pageout code.
-	 */
-	unsigned int inactive_ratio;
-
 	struct pglist_data	*zone_pgdat;
 	struct per_cpu_pageset __percpu *pageset;
 
-	/*
-	 * This is a per-zone reserve of pages that are not available
-	 * to userspace allocations.
-	 */
-	unsigned long		totalreserve_pages;
-
 #ifndef CONFIG_SPARSEMEM
 	/*
 	 * Flags for a pageblock_nr_pages block. See pageblock-flags.h.
@@ -372,14 +374,6 @@ struct zone {
 	unsigned long		*pageblock_flags;
 #endif /* CONFIG_SPARSEMEM */
 
-#ifdef CONFIG_NUMA
-	/*
-	 * zone reclaim becomes active if more unmapped pages exist.
-	 */
-	unsigned long		min_unmapped_pages;
-	unsigned long		min_slab_pages;
-#endif /* CONFIG_NUMA */
-
 	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
 	unsigned long		zone_start_pfn;
 
@@ -472,24 +466,21 @@ struct zone {
 	unsigned long		wait_table_hash_nr_entries;
 	unsigned long		wait_table_bits;
 
+	/* Write-intensive fields used from the page allocator */
 	ZONE_PADDING(_pad1_)
+
 	/* free areas of different sizes */
 	struct free_area	free_area[MAX_ORDER];
 
 	/* zone flags, see below */
 	unsigned long		flags;
 
-	/* Write-intensive fields used from the page allocator */
+	/* Primarily protects free_area */
 	spinlock_t		lock;
 
+	/* Write-intensive fields used by compaction and vmstats. */
 	ZONE_PADDING(_pad2_)
 
-	/* Write-intensive fields used by page reclaim */
-
-	/* Fields commonly accessed by the page reclaim scanner */
-	spinlock_t		lru_lock;
-	struct lruvec		lruvec;
-
 	/*
 	 * When free pages are below this point, additional steps are taken
 	 * when reading the number of free pages to avoid per-cpu counter
@@ -527,19 +518,18 @@ struct zone {
 	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
 } ____cacheline_internodealigned_in_smp;
 
-enum zone_flags {
-	ZONE_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
-	ZONE_CONGESTED,			/* zone has many dirty pages backed by
+enum pgdat_flags {
+	PGDAT_CONGESTED,		/* pgdat has many dirty pages backed by
 					 * a congested BDI
 					 */
-	ZONE_DIRTY,			/* reclaim scanning has recently found
+	PGDAT_DIRTY,			/* reclaim scanning has recently found
 					 * many dirty file pages at the tail
 					 * of the LRU.
 					 */
-	ZONE_WRITEBACK,			/* reclaim scanning has recently found
+	PGDAT_WRITEBACK,		/* reclaim scanning has recently found
 					 * many pages under writeback
 					 */
-	ZONE_FAIR_DEPLETED,		/* fair zone policy batch depleted */
+	PGDAT_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
 };
 
 static inline unsigned long zone_end_pfn(const struct zone *zone)
@@ -663,8 +653,9 @@ typedef struct pglist_data {
 	wait_queue_head_t pfmemalloc_wait;
 	struct task_struct *kswapd;	/* Protected by
 					   mem_hotplug_begin/end() */
-	int kswapd_max_order;
-	enum zone_type classzone_idx;
+	int kswapd_order;
+	enum zone_type kswapd_classzone_idx;
+
 #ifdef CONFIG_COMPACTION
 	int kcompactd_max_order;
 	enum zone_type kcompactd_classzone_idx;
@@ -681,6 +672,23 @@ typedef struct pglist_data {
 	/* Number of pages migrated during the rate limiting time interval */
 	unsigned long numabalancing_migrate_nr_pages;
 #endif
+	/*
+	 * This is a per-node reserve of pages that are not available
+	 * to userspace allocations.
+	 */
+	unsigned long		totalreserve_pages;
+
+#ifdef CONFIG_NUMA
+	/*
+	 * zone reclaim becomes active if more unmapped pages exist.
+	 */
+	unsigned long		min_unmapped_pages;
+	unsigned long		min_slab_pages;
+#endif /* CONFIG_NUMA */
+
+	/* Write-intensive fields used by page reclaim */
+	ZONE_PADDING(_pad1_)
+	spinlock_t		lru_lock;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 	/*
@@ -695,6 +703,23 @@ typedef struct pglist_data {
 	struct list_head split_queue;
 	unsigned long split_queue_len;
 #endif
+
+	/* Fields commonly accessed by the page reclaim scanner */
+	struct lruvec		lruvec;
+
+	/*
+	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
+	 * this node's LRU.  Maintained by the pageout code.
+	 */
+	unsigned int inactive_ratio;
+
+	unsigned long		flags;
+
+	ZONE_PADDING(_pad2_)
+
+	/* Per-node vmstats */
+	struct per_cpu_nodestat __percpu *per_cpu_nodestats;
+	atomic_long_t		vm_stat[NR_VM_NODE_STAT_ITEMS];
 } pg_data_t;
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
@@ -708,6 +733,15 @@ typedef struct pglist_data {
 
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
 #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
+static inline spinlock_t *zone_lru_lock(struct zone *zone)
+{
+	return &zone->zone_pgdat->lru_lock;
+}
+
+static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
+{
+	return &pgdat->lruvec;
+}
 
 static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
 {
@@ -760,12 +794,12 @@ extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
 
 extern void lruvec_init(struct lruvec *lruvec);
 
-static inline struct zone *lruvec_zone(struct lruvec *lruvec)
+static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
 {
 #ifdef CONFIG_MEMCG
-	return lruvec->zone;
+	return lruvec->pgdat;
 #else
-	return container_of(lruvec, struct zone, lruvec);
+	return container_of(lruvec, struct pglist_data, lruvec);
 #endif
 }
 

include/linux/oom.h

@@ -73,9 +73,9 @@ static inline bool oom_task_origin(const struct task_struct *p)
 extern void mark_oom_victim(struct task_struct *tsk);
 
 #ifdef CONFIG_MMU
-extern void try_oom_reaper(struct task_struct *tsk);
+extern void wake_oom_reaper(struct task_struct *tsk);
 #else
-static inline void try_oom_reaper(struct task_struct *tsk)
+static inline void wake_oom_reaper(struct task_struct *tsk)
 {
 }
 #endif
@@ -107,27 +107,7 @@ extern void oom_killer_enable(void);
 
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
-static inline bool task_will_free_mem(struct task_struct *task)
-{
-	struct signal_struct *sig = task->signal;
-
-	/*
-	 * A coredumping process may sleep for an extended period in exit_mm(),
-	 * so the oom killer cannot assume that the process will promptly exit
-	 * and release memory.
-	 */
-	if (sig->flags & SIGNAL_GROUP_COREDUMP)
-		return false;
-
-	if (!(task->flags & PF_EXITING))
-		return false;
-
-	/* Make sure that the whole thread group is going down */
-	if (!thread_group_empty(task) && !(sig->flags & SIGNAL_GROUP_EXIT))
-		return false;
-
-	return true;
-}
+bool task_will_free_mem(struct task_struct *task);
 
 /* sysctls */
 extern int sysctl_oom_dump_tasks;

include/linux/sched.h

@@ -523,6 +523,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_HAS_UPROBES		19	/* has uprobes */
 #define MMF_RECALC_UPROBES	20	/* MMF_HAS_UPROBES can be wrong */
 #define MMF_OOM_REAPED		21	/* mm has been already reaped */
+#define MMF_OOM_NOT_REAPABLE	22	/* mm couldn't be reaped */
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
 
@@ -1949,6 +1950,32 @@ static inline int tsk_nr_cpus_allowed(struct task_struct *p)
 #define TNF_FAULT_LOCAL	0x08
 #define TNF_MIGRATE_FAIL 0x10
 
+static inline bool in_vfork(struct task_struct *tsk)
+{
+	bool ret;
+
+	/*
+	 * need RCU to access ->real_parent if CLONE_VM was used along with
+	 * CLONE_PARENT.
+	 *
+	 * We check real_parent->mm == tsk->mm because CLONE_VFORK does not
+	 * imply CLONE_VM
+	 *
+	 * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus
+	 * ->real_parent is not necessarily the task doing vfork(), so in
+	 * theory we can't rely on task_lock() if we want to dereference it.
+	 *
+	 * And in this case we can't trust the real_parent->mm == tsk->mm
+	 * check, it can be false negative. But we do not care, if init or
+	 * another oom-unkillable task does this it should blame itself.
+	 */
+	rcu_read_lock();
+	ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm;
+	rcu_read_unlock();
+
+	return ret;
+}
+
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, int flags);
 extern pid_t task_numa_group_id(struct task_struct *p);

include/linux/slab_def.h

@@ -88,7 +88,8 @@ struct kmem_cache {
 };
 
 static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
-				void *x) {
+				void *x)
+{
 	void *object = x - (x - page->s_mem) % cache->size;
 	void *last_object = page->s_mem + (cache->num - 1) * cache->size;
 

include/linux/slub_def.h

@@ -104,6 +104,10 @@ struct kmem_cache {
 	unsigned int *random_seq;
 #endif
 
+#ifdef CONFIG_KASAN
+	struct kasan_cache kasan_info;
+#endif
+
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };
 
@@ -119,15 +123,17 @@ static inline void sysfs_slab_remove(struct kmem_cache *s)
 void object_err(struct kmem_cache *s, struct page *page,
 		u8 *object, char *reason);
 
+void *fixup_red_left(struct kmem_cache *s, void *p);
+
 static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
 				void *x) {
 	void *object = x - (x - page_address(page)) % cache->size;
 	void *last_object = page_address(page) +
 		(page->objects - 1) * cache->size;
-	if (unlikely(object > last_object))
-		return last_object;
-	else
-		return object;
+	void *result = (unlikely(object > last_object)) ? last_object : object;
+
+	result = fixup_red_left(cache, result);
+	return result;
 }
 
 #endif /* _LINUX_SLUB_DEF_H */

include/linux/swap.h

@@ -157,15 +157,6 @@ enum {
 #define SWAP_CLUSTER_MAX 32UL
 #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
 
-/*
- * Ratio between zone->managed_pages and the "gap" that above the per-zone
- * "high_wmark". While balancing nodes, We allow kswapd to shrink zones that
- * do not meet the (high_wmark + gap) watermark, even which already met the
- * high_wmark, in order to provide better per-zone lru behavior. We are ok to
- * spend not more than 1% of the memory for this zone balancing "gap".
- */
-#define KSWAPD_ZONE_BALANCE_GAP_RATIO 100
-
 #define SWAP_MAP_MAX	0x3e	/* Max duplication count, in first swap_map */
 #define SWAP_MAP_BAD	0x3f	/* Note pageblock is bad, in first swap_map */
 #define SWAP_HAS_CACHE	0x40	/* Flag page is cached, in first swap_map */
@@ -317,6 +308,7 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
 
 /* linux/mm/vmscan.c */
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
+extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat);
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
 extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
@@ -324,9 +316,9 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 						  unsigned long nr_pages,
 						  gfp_t gfp_mask,
 						  bool may_swap);
-extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
 						gfp_t gfp_mask, bool noswap,
-						struct zone *zone,
+						pg_data_t *pgdat,
 						unsigned long *nr_scanned);
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
@@ -334,13 +326,14 @@ extern int remove_mapping(struct address_space *mapping, struct page *page);
 extern unsigned long vm_total_pages;
 
 #ifdef CONFIG_NUMA
-extern int zone_reclaim_mode;
+extern int node_reclaim_mode;
 extern int sysctl_min_unmapped_ratio;
 extern int sysctl_min_slab_ratio;
-extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
+extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
 #else
-#define zone_reclaim_mode 0
-static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
+#define node_reclaim_mode 0
+static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
+				unsigned int order)
 {
 	return 0;
 }

include/linux/topology.h

@@ -54,7 +54,7 @@ int arch_update_cpu_topology(void);
 /*
  * If the distance between nodes in a system is larger than RECLAIM_DISTANCE
  * (in whatever arch specific measurement units returned by node_distance())
- * and zone_reclaim_mode is enabled then the VM will only call zone_reclaim()
+ * and node_reclaim_mode is enabled then the VM will only call node_reclaim()
  * on nodes within this distance.
  */
 #define RECLAIM_DISTANCE 30

include/linux/vm_event_item.h

@@ -23,21 +23,23 @@
 
 enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGALLOC),
+		FOR_ALL_ZONES(ALLOCSTALL),
+		FOR_ALL_ZONES(PGSCAN_SKIP),
 		PGFREE, PGACTIVATE, PGDEACTIVATE,
 		PGFAULT, PGMAJFAULT,
 		PGLAZYFREED,
-		FOR_ALL_ZONES(PGREFILL),
-		FOR_ALL_ZONES(PGSTEAL_KSWAPD),
-		FOR_ALL_ZONES(PGSTEAL_DIRECT),
-		FOR_ALL_ZONES(PGSCAN_KSWAPD),
-		FOR_ALL_ZONES(PGSCAN_DIRECT),
+		PGREFILL,
+		PGSTEAL_KSWAPD,
+		PGSTEAL_DIRECT,
+		PGSCAN_KSWAPD,
+		PGSCAN_DIRECT,
 		PGSCAN_DIRECT_THROTTLE,
 #ifdef CONFIG_NUMA
 		PGSCAN_ZONE_RECLAIM_FAILED,
 #endif
 		PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
-		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+		PAGEOUTRUN, PGROTATED,
 		DROP_PAGECACHE, DROP_SLAB,
 #ifdef CONFIG_NUMA_BALANCING
 		NUMA_PTE_UPDATES,

include/linux/vmstat.h

@@ -101,25 +101,42 @@ static inline void vm_events_fold_cpu(int cpu)
 #define count_vm_vmacache_event(x) do {} while (0)
 #endif
 
-#define __count_zone_vm_events(item, zone, delta) \
-		__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
-		zone_idx(zone), delta)
+#define __count_zid_vm_events(item, zid, delta) \
+	__count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
 
 /*
- * Zone based page accounting with per cpu differentials.
+ * Zone and node-based page accounting with per cpu differentials.
  */
-extern atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
+extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS];
+extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS];
 
 static inline void zone_page_state_add(long x, struct zone *zone,
 				 enum zone_stat_item item)
 {
 	atomic_long_add(x, &zone->vm_stat[item]);
-	atomic_long_add(x, &vm_stat[item]);
+	atomic_long_add(x, &vm_zone_stat[item]);
+}
+
+static inline void node_page_state_add(long x, struct pglist_data *pgdat,
+				 enum node_stat_item item)
+{
+	atomic_long_add(x, &pgdat->vm_stat[item]);
+	atomic_long_add(x, &vm_node_stat[item]);
 }
 
 static inline unsigned long global_page_state(enum zone_stat_item item)
 {
-	long x = atomic_long_read(&vm_stat[item]);
+	long x = atomic_long_read(&vm_zone_stat[item]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
+}
+
+static inline unsigned long global_node_page_state(enum node_stat_item item)
+{
+	long x = atomic_long_read(&vm_node_stat[item]);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -160,32 +177,61 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
 	return x;
 }
 
-#ifdef CONFIG_NUMA
+static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat,
+					enum node_stat_item item)
+{
+	long x = atomic_long_read(&pgdat->vm_stat[item]);
 
-extern unsigned long node_page_state(int node, enum zone_stat_item item);
+#ifdef CONFIG_SMP
+	int cpu;
+	for_each_online_cpu(cpu)
+		x += per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->vm_node_stat_diff[item];
 
-#else
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
+}
 
-#define node_page_state(node, item) global_page_state(item)
 
+#ifdef CONFIG_NUMA
+extern unsigned long sum_zone_node_page_state(int node,
+						enum zone_stat_item item);
+extern unsigned long node_page_state(struct pglist_data *pgdat,
+						enum node_stat_item item);
+#else
+#define sum_zone_node_page_state(node, item) global_page_state(item)
+#define node_page_state(node, item) global_node_page_state(item)
 #endif /* CONFIG_NUMA */
 
 #define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
 #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
+#define add_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, __d)
+#define sub_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, -(__d))
 
 #ifdef CONFIG_SMP
 void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long);
 void __inc_zone_page_state(struct page *, enum zone_stat_item);
 void __dec_zone_page_state(struct page *, enum zone_stat_item);
 
+void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long);
+void __inc_node_page_state(struct page *, enum node_stat_item);
+void __dec_node_page_state(struct page *, enum node_stat_item);
+
 void mod_zone_page_state(struct zone *, enum zone_stat_item, long);
 void inc_zone_page_state(struct page *, enum zone_stat_item);
 void dec_zone_page_state(struct page *, enum zone_stat_item);
 
-extern void inc_zone_state(struct zone *, enum zone_stat_item);
+void mod_node_page_state(struct pglist_data *, enum node_stat_item, long);
+void inc_node_page_state(struct page *, enum node_stat_item);
+void dec_node_page_state(struct page *, enum node_stat_item);
+
+extern void inc_node_state(struct pglist_data *, enum node_stat_item);
 extern void __inc_zone_state(struct zone *, enum zone_stat_item);
+extern void __inc_node_state(struct pglist_data *, enum node_stat_item);
 extern void dec_zone_state(struct zone *, enum zone_stat_item);
 extern void __dec_zone_state(struct zone *, enum zone_stat_item);
+extern void __dec_node_state(struct pglist_data *, enum node_stat_item);
 
 void quiet_vmstat(void);
 void cpu_vm_stats_fold(int cpu);
@@ -213,16 +259,34 @@ static inline void __mod_zone_page_state(struct zone *zone,
 	zone_page_state_add(delta, zone, item);
 }
 
+static inline void __mod_node_page_state(struct pglist_data *pgdat,
+			enum node_stat_item item, int delta)
+{
+	node_page_state_add(delta, pgdat, item);
+}
+
 static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
 	atomic_long_inc(&zone->vm_stat[item]);
-	atomic_long_inc(&vm_stat[item]);
+	atomic_long_inc(&vm_zone_stat[item]);
+}
+
+static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+	atomic_long_inc(&pgdat->vm_stat[item]);
+	atomic_long_inc(&vm_node_stat[item]);
 }
 
 static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 {
 	atomic_long_dec(&zone->vm_stat[item]);
-	atomic_long_dec(&vm_stat[item]);
+	atomic_long_dec(&vm_zone_stat[item]);
+}
+
+static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+	atomic_long_dec(&pgdat->vm_stat[item]);
+	atomic_long_dec(&vm_node_stat[item]);
 }
 
 static inline void __inc_zone_page_state(struct page *page,
@@ -231,12 +295,26 @@ static inline void __inc_zone_page_state(struct page *page,
 	__inc_zone_state(page_zone(page), item);
 }
 
+static inline void __inc_node_page_state(struct page *page,
+			enum node_stat_item item)
+{
+	__inc_node_state(page_pgdat(page), item);
+}
+
+
 static inline void __dec_zone_page_state(struct page *page,
 			enum zone_stat_item item)
 {
 	__dec_zone_state(page_zone(page), item);
 }
 
+static inline void __dec_node_page_state(struct page *page,
+			enum node_stat_item item)
+{
+	__dec_node_state(page_pgdat(page), item);
+}
+
+
 /*
  * We only use atomic operations to update counters. So there is no need to
  * disable interrupts.
@@ -245,7 +323,12 @@ static inline void __dec_zone_page_state(struct page *page,
 #define dec_zone_page_state __dec_zone_page_state
 #define mod_zone_page_state __mod_zone_page_state
 
+#define inc_node_page_state __inc_node_page_state
+#define dec_node_page_state __dec_node_page_state
+#define mod_node_page_state __mod_node_page_state
+
 #define inc_zone_state __inc_zone_state
+#define inc_node_state __inc_node_state
 #define dec_zone_state __dec_zone_state
 
 #define set_pgdat_percpu_threshold(pgdat, callback) { }

include/linux/writeback.h

@@ -320,7 +320,7 @@ void laptop_mode_timer_fn(unsigned long data);
 static inline void laptop_sync_completion(void) { }
 #endif
 void throttle_vm_writeout(gfp_t gfp_mask);
-bool zone_dirty_ok(struct zone *zone);
+bool node_dirty_ok(struct pglist_data *pgdat);
 int wb_domain_init(struct wb_domain *dom, gfp_t gfp);
 #ifdef CONFIG_CGROUP_WRITEBACK
 void wb_domain_exit(struct wb_domain *dom);

include/trace/events/compaction.h

@@ -226,26 +226,26 @@ TRACE_EVENT(mm_compaction_try_to_compact_pages,
 	TP_PROTO(
 		int order,
 		gfp_t gfp_mask,
-		enum migrate_mode mode),
+		int prio),
 
-	TP_ARGS(order, gfp_mask, mode),
+	TP_ARGS(order, gfp_mask, prio),
 
 	TP_STRUCT__entry(
 		__field(int, order)
 		__field(gfp_t, gfp_mask)
-		__field(enum migrate_mode, mode)
+		__field(int, prio)
 	),
 
 	TP_fast_assign(
 		__entry->order = order;
 		__entry->gfp_mask = gfp_mask;
-		__entry->mode = mode;
+		__entry->prio = prio;
 	),
 
-	TP_printk("order=%d gfp_mask=0x%x mode=%d",
+	TP_printk("order=%d gfp_mask=0x%x priority=%d",
 		__entry->order,
 		__entry->gfp_mask,
-		(int)__entry->mode)
+		__entry->prio)
 );
 
 DECLARE_EVENT_CLASS(mm_compaction_suitable_template,

include/trace/events/mmflags.h

@@ -11,6 +11,7 @@
 
 #define __def_gfpflag_names						\
 	{(unsigned long)GFP_TRANSHUGE,		"GFP_TRANSHUGE"},	\
+	{(unsigned long)GFP_TRANSHUGE_LIGHT,	"GFP_TRANSHUGE_LIGHT"}, \
 	{(unsigned long)GFP_HIGHUSER_MOVABLE,	"GFP_HIGHUSER_MOVABLE"},\
 	{(unsigned long)GFP_HIGHUSER,		"GFP_HIGHUSER"},	\
 	{(unsigned long)GFP_USER,		"GFP_USER"},		\

include/trace/events/vmscan.h

@@ -55,21 +55,23 @@ TRACE_EVENT(mm_vmscan_kswapd_sleep,
 
 TRACE_EVENT(mm_vmscan_kswapd_wake,
 
-	TP_PROTO(int nid, int order),
+	TP_PROTO(int nid, int zid, int order),
 
-	TP_ARGS(nid, order),
+	TP_ARGS(nid, zid, order),
 
 	TP_STRUCT__entry(
 		__field(	int,	nid	)
+		__field(	int,	zid	)
 		__field(	int,	order	)
 	),
 
 	TP_fast_assign(
 		__entry->nid	= nid;
+		__entry->zid    = zid;
 		__entry->order	= order;
 	),
 
-	TP_printk("nid=%d order=%d", __entry->nid, __entry->order)
+	TP_printk("nid=%d zid=%d order=%d", __entry->nid, __entry->zid, __entry->order)
 );
 
 TRACE_EVENT(mm_vmscan_wakeup_kswapd,
@@ -98,47 +100,50 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd,
 
 DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
 
-	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
 
-	TP_ARGS(order, may_writepage, gfp_flags),
+	TP_ARGS(order, may_writepage, gfp_flags, classzone_idx),
 
 	TP_STRUCT__entry(
 		__field(	int,	order		)
 		__field(	int,	may_writepage	)
 		__field(	gfp_t,	gfp_flags	)
+		__field(	int,	classzone_idx	)
 	),
 
 	TP_fast_assign(
 		__entry->order		= order;
 		__entry->may_writepage	= may_writepage;
 		__entry->gfp_flags	= gfp_flags;
+		__entry->classzone_idx	= classzone_idx;
 	),
 
-	TP_printk("order=%d may_writepage=%d gfp_flags=%s",
+	TP_printk("order=%d may_writepage=%d gfp_flags=%s classzone_idx=%d",
 		__entry->order,
 		__entry->may_writepage,
-		show_gfp_flags(__entry->gfp_flags))
+		show_gfp_flags(__entry->gfp_flags),
+		__entry->classzone_idx)
 );
 
 DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
 
-	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
 
-	TP_ARGS(order, may_writepage, gfp_flags)
+	TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
 );
 
 DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
 
-	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
 
-	TP_ARGS(order, may_writepage, gfp_flags)
+	TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
 );
 
 DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin,
 
-	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
 
-	TP_ARGS(order, may_writepage, gfp_flags)
+	TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
 );
 
 DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template,
@@ -266,16 +271,18 @@ TRACE_EVENT(mm_shrink_slab_end,
 
 DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 
-	TP_PROTO(int order,
+	TP_PROTO(int classzone_idx,
+		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
+	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
 
 	TP_STRUCT__entry(
+		__field(int, classzone_idx)
 		__field(int, order)
 		__field(unsigned long, nr_requested)
 		__field(unsigned long, nr_scanned)
@@ -285,6 +292,7 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 	),
 
 	TP_fast_assign(
+		__entry->classzone_idx = classzone_idx;
 		__entry->order = order;
 		__entry->nr_requested = nr_requested;
 		__entry->nr_scanned = nr_scanned;
@@ -293,8 +301,9 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 		__entry->file = file;
 	),
 
-	TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
+	TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
 		__entry->isolate_mode,
+		__entry->classzone_idx,
 		__entry->order,
 		__entry->nr_requested,
 		__entry->nr_scanned,
@@ -304,27 +313,29 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 
 DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate,
 
-	TP_PROTO(int order,
+	TP_PROTO(int classzone_idx,
+		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
+	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
 
 );
 
 DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate,
 
-	TP_PROTO(int order,
+	TP_PROTO(int classzone_idx,
+		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
+	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
 
 );
 
@@ -352,15 +363,14 @@ TRACE_EVENT(mm_vmscan_writepage,
 
 TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 
-	TP_PROTO(struct zone *zone,
+	TP_PROTO(int nid,
 		unsigned long nr_scanned, unsigned long nr_reclaimed,
 		int priority, int file),
 
-	TP_ARGS(zone, nr_scanned, nr_reclaimed, priority, file),
+	TP_ARGS(nid, nr_scanned, nr_reclaimed, priority, file),
 
 	TP_STRUCT__entry(
 		__field(int, nid)
-		__field(int, zid)
 		__field(unsigned long, nr_scanned)
 		__field(unsigned long, nr_reclaimed)
 		__field(int, priority)
@@ -368,16 +378,15 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 	),
 
 	TP_fast_assign(
-		__entry->nid = zone_to_nid(zone);
-		__entry->zid = zone_idx(zone);
+		__entry->nid = nid;
 		__entry->nr_scanned = nr_scanned;
 		__entry->nr_reclaimed = nr_reclaimed;
 		__entry->priority = priority;
 		__entry->reclaim_flags = trace_shrink_flags(file);
 	),
 
-	TP_printk("nid=%d zid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s",
-		__entry->nid, __entry->zid,
+	TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s",
+		__entry->nid,
 		__entry->nr_scanned, __entry->nr_reclaimed,
 		__entry->priority,
 		show_reclaim_flags(__entry->reclaim_flags))

include/trace/events/writeback.h

@@ -412,11 +412,11 @@ TRACE_EVENT(global_dirty_state,
 	),
 
 	TP_fast_assign(
-		__entry->nr_dirty	= global_page_state(NR_FILE_DIRTY);
-		__entry->nr_writeback	= global_page_state(NR_WRITEBACK);
-		__entry->nr_unstable	= global_page_state(NR_UNSTABLE_NFS);
-		__entry->nr_dirtied	= global_page_state(NR_DIRTIED);
-		__entry->nr_written	= global_page_state(NR_WRITTEN);
+		__entry->nr_dirty	= global_node_page_state(NR_FILE_DIRTY);
+		__entry->nr_writeback	= global_node_page_state(NR_WRITEBACK);
+		__entry->nr_unstable	= global_node_page_state(NR_UNSTABLE_NFS);
+		__entry->nr_dirtied	= global_node_page_state(NR_DIRTIED);
+		__entry->nr_written	= global_node_page_state(NR_WRITTEN);
 		__entry->background_thresh = background_thresh;
 		__entry->dirty_thresh	= dirty_thresh;
 		__entry->dirty_limit	= global_wb_domain.dirty_limit;

kernel/cpuset.c

@@ -1034,15 +1034,6 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 {
 	bool need_loop;
 
-	/*
-	 * Allow tasks that have access to memory reserves because they have
-	 * been OOM killed to get memory anywhere.
-	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE)))
-		return;
-	if (current->flags & PF_EXITING) /* Let dying task have memory */
-		return;
-
 	task_lock(tsk);
 	/*
 	 * Determine if a loop is necessary if another thread is doing

kernel/fork.c

@@ -165,20 +165,12 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
 					     THREAD_SIZE_ORDER);
 
-	if (page)
-		memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-					    1 << THREAD_SIZE_ORDER);
-
 	return page ? page_address(page) : NULL;
 }
 
 static inline void free_thread_stack(unsigned long *stack)
 {
-	struct page *page = virt_to_page(stack);
-
-	memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-				    -(1 << THREAD_SIZE_ORDER));
-	__free_pages(page, THREAD_SIZE_ORDER);
+	__free_pages(virt_to_page(stack), THREAD_SIZE_ORDER);
 }
 # else
 static struct kmem_cache *thread_stack_cache;
@@ -223,9 +215,15 @@ static struct kmem_cache *mm_cachep;
 
 static void account_kernel_stack(unsigned long *stack, int account)
 {
-	struct zone *zone = page_zone(virt_to_page(stack));
+	/* All stack pages are in the same zone and belong to the same memcg. */
+	struct page *first_page = virt_to_page(stack);
+
+	mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
+			    THREAD_SIZE / 1024 * account);
 
-	mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+	memcg_kmem_update_page_stat(
+		first_page, MEMCG_KERNEL_STACK_KB,
+		account * (THREAD_SIZE / 1024));
 }
 
 void free_task(struct task_struct *tsk)

kernel/freezer.c

@@ -42,7 +42,7 @@ bool freezing_slow_path(struct task_struct *p)
 	if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK))
 		return false;
 
-	if (test_thread_flag(TIF_MEMDIE))
+	if (test_tsk_thread_flag(p, TIF_MEMDIE))
 		return false;
 
 	if (pm_nosig_freezing || cgroup_freezing(p))

kernel/memremap.c

@@ -308,12 +308,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (is_ram == REGION_INTERSECTS)
 		return __va(res->start);
 
-	if (altmap && !IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) {
-		dev_err(dev, "%s: altmap requires CONFIG_SPARSEMEM_VMEMMAP=y\n",
-				__func__);
-		return ERR_PTR(-ENXIO);
-	}
-
 	if (!ref)
 		return ERR_PTR(-EINVAL);
 
@@ -401,7 +395,6 @@ void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
 	altmap->alloc -= nr_pfns;
 }
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
 struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
 {
 	/*
@@ -427,5 +420,4 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
 
 	return pgmap ? pgmap->altmap : NULL;
 }
-#endif /* CONFIG_SPARSEMEM_VMEMMAP */
 #endif /* CONFIG_ZONE_DEVICE */

kernel/power/snapshot.c

@@ -1627,11 +1627,11 @@ static unsigned long minimum_image_size(unsigned long saveable)
 	unsigned long size;
 
 	size = global_page_state(NR_SLAB_RECLAIMABLE)
-		+ global_page_state(NR_ACTIVE_ANON)
-		+ global_page_state(NR_INACTIVE_ANON)
-		+ global_page_state(NR_ACTIVE_FILE)
-		+ global_page_state(NR_INACTIVE_FILE)
-		- global_page_state(NR_FILE_MAPPED);
+		+ global_node_page_state(NR_ACTIVE_ANON)
+		+ global_node_page_state(NR_INACTIVE_ANON)
+		+ global_node_page_state(NR_ACTIVE_FILE)
+		+ global_node_page_state(NR_INACTIVE_FILE)
+		- global_node_page_state(NR_FILE_MAPPED);
 
 	return saveable <= size ? 0 : saveable - size;
 }

kernel/printk/printk.c

@@ -3177,9 +3177,8 @@ void show_regs_print_info(const char *log_lvl)
 {
 	dump_stack_print_info(log_lvl);
 
-	printk("%stask: %p ti: %p task.ti: %p\n",
-	       log_lvl, current, current_thread_info(),
-	       task_thread_info(current));
+	printk("%stask: %p task.stack: %p\n",
+	       log_lvl, current, task_stack_page(current));
 }
 
 #endif

kernel/sysctl.c

@@ -1508,8 +1508,8 @@ static struct ctl_table vm_table[] = {
 #ifdef CONFIG_NUMA
 	{
 		.procname	= "zone_reclaim_mode",
-		.data		= &zone_reclaim_mode,
-		.maxlen		= sizeof(zone_reclaim_mode),
+		.data		= &node_reclaim_mode,
+		.maxlen		= sizeof(node_reclaim_mode),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 		.extra1		= &zero,

lib/Kconfig.kasan

@@ -5,9 +5,9 @@ if HAVE_ARCH_KASAN
 
 config KASAN
 	bool "KASan: runtime memory debugger"
-	depends on SLUB_DEBUG || (SLAB && !DEBUG_SLAB)
+	depends on SLUB || (SLAB && !DEBUG_SLAB)
 	select CONSTRUCTORS
-	select STACKDEPOT if SLAB
+	select STACKDEPOT
 	help
 	  Enables kernel address sanitizer - runtime memory debugger,
 	  designed to find out-of-bounds accesses and use-after-free bugs.

lib/iov_iter.c

@@ -144,7 +144,7 @@ static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t b
 	buf = iov->iov_base + skip;
 	copy = min(bytes, iov->iov_len - skip);
 
-	if (!fault_in_pages_writeable(buf, copy)) {
+	if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_writeable(buf, copy)) {
 		kaddr = kmap_atomic(page);
 		from = kaddr + offset;
 
@@ -175,6 +175,7 @@ static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t b
 		copy = min(bytes, iov->iov_len - skip);
 	}
 	/* Too bad - revert to non-atomic kmap */
+
 	kaddr = kmap(page);
 	from = kaddr + offset;
 	left = __copy_to_user(buf, from, copy);
@@ -193,6 +194,7 @@ static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t b
 		bytes -= copy;
 	}
 	kunmap(page);
+
 done:
 	if (skip == iov->iov_len) {
 		iov++;
@@ -225,7 +227,7 @@ static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t
 	buf = iov->iov_base + skip;
 	copy = min(bytes, iov->iov_len - skip);
 
-	if (!fault_in_pages_readable(buf, copy)) {
+	if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_readable(buf, copy)) {
 		kaddr = kmap_atomic(page);
 		to = kaddr + offset;
 
@@ -256,6 +258,7 @@ static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t
 		copy = min(bytes, iov->iov_len - skip);
 	}
 	/* Too bad - revert to non-atomic kmap */
+
 	kaddr = kmap(page);
 	to = kaddr + offset;
 	left = __copy_from_user(to, buf, copy);
@@ -274,6 +277,7 @@ static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t
 		bytes -= copy;
 	}
 	kunmap(page);
+
 done:
 	if (skip == iov->iov_len) {
 		iov++;

lib/stackdepot.c

@@ -242,6 +242,7 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
 		 */
 		alloc_flags &= ~GFP_ZONEMASK;
 		alloc_flags &= (GFP_ATOMIC | GFP_KERNEL);
+		alloc_flags |= __GFP_NOWARN;
 		page = alloc_pages(alloc_flags, STACK_ALLOC_ORDER);
 		if (page)
 			prealloc = page_address(page);

mm/Kconfig

@@ -681,7 +681,7 @@ config IDLE_PAGE_TRACKING
 	  See Documentation/vm/idle_page_tracking.txt for more details.
 
 config ZONE_DEVICE
-	bool "Device memory (pmem, etc...) hotplug support" if EXPERT
+	bool "Device memory (pmem, etc...) hotplug support"
 	depends on MEMORY_HOTPLUG
 	depends on MEMORY_HOTREMOVE
 	depends on SPARSEMEM_VMEMMAP

mm/backing-dev.c

@@ -947,24 +947,24 @@ long congestion_wait(int sync, long timeout)
 EXPORT_SYMBOL(congestion_wait);
 
 /**
- * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes
- * @zone: A zone to check if it is heavily congested
+ * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes
+ * @pgdat: A pgdat to check if it is heavily congested
  * @sync: SYNC or ASYNC IO
  * @timeout: timeout in jiffies
  *
  * In the event of a congested backing_dev (any backing_dev) and the given
- * @zone has experienced recent congestion, this waits for up to @timeout
+ * @pgdat has experienced recent congestion, this waits for up to @timeout
  * jiffies for either a BDI to exit congestion of the given @sync queue
  * or a write to complete.
  *
- * In the absence of zone congestion, cond_resched() is called to yield
+ * In the absence of pgdat congestion, cond_resched() is called to yield
  * the processor if necessary but otherwise does not sleep.
  *
  * The return value is 0 if the sleep is for the full timeout. Otherwise,
  * it is the number of jiffies that were still remaining when the function
  * returned. return_value == timeout implies the function did not sleep.
  */
-long wait_iff_congested(struct zone *zone, int sync, long timeout)
+long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout)
 {
 	long ret;
 	unsigned long start = jiffies;
@@ -973,12 +973,13 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout)
 
 	/*
 	 * If there is no congestion, or heavy congestion is not being
-	 * encountered in the current zone, yield if necessary instead
+	 * encountered in the current pgdat, yield if necessary instead
 	 * of sleeping on the congestion queue
 	 */
 	if (atomic_read(&nr_wb_congested[sync]) == 0 ||
-	    !test_bit(ZONE_CONGESTED, &zone->flags)) {
+	    !test_bit(PGDAT_CONGESTED, &pgdat->flags)) {
 		cond_resched();
+
 		/* In case we scheduled, work out time remaining */
 		ret = timeout - (jiffies - start);
 		if (ret < 0)

mm/compaction.c

@@ -331,7 +331,7 @@ static bool compact_trylock_irqsave(spinlock_t *lock, unsigned long *flags,
 {
 	if (cc->mode == MIGRATE_ASYNC) {
 		if (!spin_trylock_irqsave(lock, *flags)) {
-			cc->contended = COMPACT_CONTENDED_LOCK;
+			cc->contended = true;
 			return false;
 		}
 	} else {
@@ -365,13 +365,13 @@ static bool compact_unlock_should_abort(spinlock_t *lock,
 	}
 
 	if (fatal_signal_pending(current)) {
-		cc->contended = COMPACT_CONTENDED_SCHED;
+		cc->contended = true;
 		return true;
 	}
 
 	if (need_resched()) {
 		if (cc->mode == MIGRATE_ASYNC) {
-			cc->contended = COMPACT_CONTENDED_SCHED;
+			cc->contended = true;
 			return true;
 		}
 		cond_resched();
@@ -394,7 +394,7 @@ static inline bool compact_should_abort(struct compact_control *cc)
 	/* async compaction aborts if contended */
 	if (need_resched()) {
 		if (cc->mode == MIGRATE_ASYNC) {
-			cc->contended = COMPACT_CONTENDED_SCHED;
+			cc->contended = true;
 			return true;
 		}
 
@@ -646,8 +646,8 @@ static void acct_isolated(struct zone *zone, struct compact_control *cc)
 	list_for_each_entry(page, &cc->migratepages, lru)
 		count[!!page_is_file_cache(page)]++;
 
-	mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
-	mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, count[0]);
+	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, count[1]);
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */
@@ -655,12 +655,12 @@ static bool too_many_isolated(struct zone *zone)
 {
 	unsigned long active, inactive, isolated;
 
-	inactive = zone_page_state(zone, NR_INACTIVE_FILE) +
-					zone_page_state(zone, NR_INACTIVE_ANON);
-	active = zone_page_state(zone, NR_ACTIVE_FILE) +
-					zone_page_state(zone, NR_ACTIVE_ANON);
-	isolated = zone_page_state(zone, NR_ISOLATED_FILE) +
-					zone_page_state(zone, NR_ISOLATED_ANON);
+	inactive = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) +
+			node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON);
+	active = node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE) +
+			node_page_state(zone->zone_pgdat, NR_ACTIVE_ANON);
+	isolated = node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE) +
+			node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON);
 
 	return isolated > (inactive + active) / 2;
 }
@@ -752,7 +752,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 * if contended.
 		 */
 		if (!(low_pfn % SWAP_CLUSTER_MAX)
-		    && compact_unlock_should_abort(&zone->lru_lock, flags,
+		    && compact_unlock_should_abort(zone_lru_lock(zone), flags,
 								&locked, cc))
 			break;
 
@@ -813,7 +813,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			if (unlikely(__PageMovable(page)) &&
 					!PageIsolated(page)) {
 				if (locked) {
-					spin_unlock_irqrestore(&zone->lru_lock,
+					spin_unlock_irqrestore(zone_lru_lock(zone),
 									flags);
 					locked = false;
 				}
@@ -836,7 +836,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 		/* If we already hold the lock, we can skip some rechecking */
 		if (!locked) {
-			locked = compact_trylock_irqsave(&zone->lru_lock,
+			locked = compact_trylock_irqsave(zone_lru_lock(zone),
 								&flags, cc);
 			if (!locked)
 				break;
@@ -856,7 +856,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			}
 		}
 
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
 
 		/* Try isolate the page */
 		if (__isolate_lru_page(page, isolate_mode) != 0)
@@ -899,7 +899,7 @@ isolate_fail:
 		 */
 		if (nr_isolated) {
 			if (locked) {
-				spin_unlock_irqrestore(&zone->lru_lock,	flags);
+				spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 				locked = false;
 			}
 			acct_isolated(zone, cc);
@@ -927,7 +927,7 @@ isolate_fail:
 		low_pfn = end_pfn;
 
 	if (locked)
-		spin_unlock_irqrestore(&zone->lru_lock, flags);
+		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 
 	/*
 	 * Update the pageblock-skip information and cached scanner pfn,
@@ -1200,7 +1200,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	struct page *page;
 	const isolate_mode_t isolate_mode =
 		(sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) |
-		(cc->mode == MIGRATE_ASYNC ? ISOLATE_ASYNC_MIGRATE : 0);
+		(cc->mode != MIGRATE_SYNC ? ISOLATE_ASYNC_MIGRATE : 0);
 
 	/*
 	 * Start at where we last stopped, or beginning of the zone as
@@ -1619,14 +1619,11 @@ out:
 	trace_mm_compaction_end(start_pfn, cc->migrate_pfn,
 				cc->free_pfn, end_pfn, sync, ret);
 
-	if (ret == COMPACT_CONTENDED)
-		ret = COMPACT_PARTIAL;
-
 	return ret;
 }
 
 static enum compact_result compact_zone_order(struct zone *zone, int order,
-		gfp_t gfp_mask, enum migrate_mode mode, int *contended,
+		gfp_t gfp_mask, enum compact_priority prio,
 		unsigned int alloc_flags, int classzone_idx)
 {
 	enum compact_result ret;
@@ -1636,7 +1633,8 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 		.order = order,
 		.gfp_mask = gfp_mask,
 		.zone = zone,
-		.mode = mode,
+		.mode = (prio == COMPACT_PRIO_ASYNC) ?
+					MIGRATE_ASYNC :	MIGRATE_SYNC_LIGHT,
 		.alloc_flags = alloc_flags,
 		.classzone_idx = classzone_idx,
 		.direct_compaction = true,
@@ -1649,7 +1647,6 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 	VM_BUG_ON(!list_empty(&cc.freepages));
 	VM_BUG_ON(!list_empty(&cc.migratepages));
 
-	*contended = cc.contended;
 	return ret;
 }
 
@@ -1662,50 +1659,38 @@ int sysctl_extfrag_threshold = 500;
  * @alloc_flags: The allocation flags of the current allocation
  * @ac: The context of current allocation
  * @mode: The migration mode for async, sync light, or sync migration
- * @contended: Return value that determines if compaction was aborted due to
- *	       need_resched() or lock contention
  *
  * This is the main entry point for direct page compaction.
  */
 enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 		unsigned int alloc_flags, const struct alloc_context *ac,
-		enum migrate_mode mode, int *contended)
+		enum compact_priority prio)
 {
 	int may_enter_fs = gfp_mask & __GFP_FS;
 	int may_perform_io = gfp_mask & __GFP_IO;
 	struct zoneref *z;
 	struct zone *zone;
 	enum compact_result rc = COMPACT_SKIPPED;
-	int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */
-
-	*contended = COMPACT_CONTENDED_NONE;
 
 	/* Check if the GFP flags allow compaction */
-	if (!order || !may_enter_fs || !may_perform_io)
+	if (!may_enter_fs || !may_perform_io)
 		return COMPACT_SKIPPED;
 
-	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, mode);
+	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio);
 
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
 								ac->nodemask) {
 		enum compact_result status;
-		int zone_contended;
 
 		if (compaction_deferred(zone, order)) {
 			rc = max_t(enum compact_result, COMPACT_DEFERRED, rc);
 			continue;
 		}
 
-		status = compact_zone_order(zone, order, gfp_mask, mode,
-				&zone_contended, alloc_flags,
-				ac_classzone_idx(ac));
+		status = compact_zone_order(zone, order, gfp_mask, prio,
+					alloc_flags, ac_classzone_idx(ac));
 		rc = max(status, rc);
-		/*
-		 * It takes at least one zone that wasn't lock contended
-		 * to clear all_zones_contended.
-		 */
-		all_zones_contended &= zone_contended;
 
 		/* If a normal allocation would succeed, stop compacting */
 		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
@@ -1717,59 +1702,29 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 			 * succeeds in this zone.
 			 */
 			compaction_defer_reset(zone, order, false);
-			/*
-			 * It is possible that async compaction aborted due to
-			 * need_resched() and the watermarks were ok thanks to
-			 * somebody else freeing memory. The allocation can
-			 * however still fail so we better signal the
-			 * need_resched() contention anyway (this will not
-			 * prevent the allocation attempt).
-			 */
-			if (zone_contended == COMPACT_CONTENDED_SCHED)
-				*contended = COMPACT_CONTENDED_SCHED;
 
-			goto break_loop;
+			break;
 		}
 
-		if (mode != MIGRATE_ASYNC && (status == COMPACT_COMPLETE ||
-					status == COMPACT_PARTIAL_SKIPPED)) {
+		if (prio != COMPACT_PRIO_ASYNC && (status == COMPACT_COMPLETE ||
+					status == COMPACT_PARTIAL_SKIPPED))
 			/*
 			 * We think that allocation won't succeed in this zone
 			 * so we defer compaction there. If it ends up
 			 * succeeding after all, it will be reset.
 			 */
 			defer_compaction(zone, order);
-		}
 
 		/*
 		 * We might have stopped compacting due to need_resched() in
 		 * async compaction, or due to a fatal signal detected. In that
-		 * case do not try further zones and signal need_resched()
-		 * contention.
-		 */
-		if ((zone_contended == COMPACT_CONTENDED_SCHED)
-					|| fatal_signal_pending(current)) {
-			*contended = COMPACT_CONTENDED_SCHED;
-			goto break_loop;
-		}
-
-		continue;
-break_loop:
-		/*
-		 * We might not have tried all the zones, so  be conservative
-		 * and assume they are not all lock contended.
+		 * case do not try further zones
 		 */
-		all_zones_contended = 0;
-		break;
+		if ((prio == COMPACT_PRIO_ASYNC && need_resched())
+					|| fatal_signal_pending(current))
+			break;
 	}
 
-	/*
-	 * If at least one zone wasn't deferred or skipped, we report if all
-	 * zones that were tried were lock contended.
-	 */
-	if (rc > COMPACT_INACTIVE && all_zones_contended)
-		*contended = COMPACT_CONTENDED_LOCK;
-
 	return rc;
 }
 

mm/filemap.c

@@ -95,8 +95,8 @@
  *    ->swap_lock		(try_to_unmap_one)
  *    ->private_lock		(try_to_unmap_one)
  *    ->tree_lock		(try_to_unmap_one)
- *    ->zone.lru_lock		(follow_page->mark_page_accessed)
- *    ->zone.lru_lock		(check_pte_range->isolate_lru_page)
+ *    ->zone_lru_lock(zone)	(follow_page->mark_page_accessed)
+ *    ->zone_lru_lock(zone)	(check_pte_range->isolate_lru_page)
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->tree_lock		(page_remove_rmap->set_page_dirty)
  *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
@@ -218,11 +218,11 @@ void __delete_from_page_cache(struct page *page, void *shadow)
 
 	/* hugetlb pages do not participate in page cache accounting. */
 	if (!PageHuge(page))
-		__mod_zone_page_state(page_zone(page), NR_FILE_PAGES, -nr);
+		__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
 	if (PageSwapBacked(page)) {
-		__mod_zone_page_state(page_zone(page), NR_SHMEM, -nr);
+		__mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr);
 		if (PageTransHuge(page))
-			__dec_zone_page_state(page, NR_SHMEM_THPS);
+			__dec_node_page_state(page, NR_SHMEM_THPS);
 	} else {
 		VM_BUG_ON_PAGE(PageTransHuge(page) && !PageHuge(page), page);
 	}
@@ -568,9 +568,9 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		 * hugetlb pages do not participate in page cache accounting.
 		 */
 		if (!PageHuge(new))
-			__inc_zone_page_state(new, NR_FILE_PAGES);
+			__inc_node_page_state(new, NR_FILE_PAGES);
 		if (PageSwapBacked(new))
-			__inc_zone_page_state(new, NR_SHMEM);
+			__inc_node_page_state(new, NR_SHMEM);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		mem_cgroup_migrate(old, new);
 		radix_tree_preload_end();
@@ -677,7 +677,7 @@ static int __add_to_page_cache_locked(struct page *page,
 
 	/* hugetlb pages do not participate in page cache accounting. */
 	if (!huge)
-		__inc_zone_page_state(page, NR_FILE_PAGES);
+		__inc_node_page_state(page, NR_FILE_PAGES);
 	spin_unlock_irq(&mapping->tree_lock);
 	if (!huge)
 		mem_cgroup_commit_charge(page, memcg, false, false);

mm/huge_memory.c

@@ -539,23 +539,26 @@ static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page,
 }
 
 /*
- * If THP is set to always then directly reclaim/compact as necessary
- * If set to defer then do no reclaim and defer to khugepaged
+ * If THP defrag is set to always then directly reclaim/compact as necessary
+ * If set to defer then do only background reclaim/compact and defer to khugepaged
  * If set to madvise and the VMA is flagged then directly reclaim/compact
+ * When direct reclaim/compact is allowed, don't retry except for flagged VMA's
  */
 static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
 {
-	gfp_t reclaim_flags = 0;
-
-	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags) &&
-	    (vma->vm_flags & VM_HUGEPAGE))
-		reclaim_flags = __GFP_DIRECT_RECLAIM;
-	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
-		reclaim_flags = __GFP_KSWAPD_RECLAIM;
-	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
-		reclaim_flags = __GFP_DIRECT_RECLAIM;
-
-	return GFP_TRANSHUGE | reclaim_flags;
+	bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
+				&transparent_hugepage_flags) && vma_madvised)
+		return GFP_TRANSHUGE;
+	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
+						&transparent_hugepage_flags))
+		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
+						&transparent_hugepage_flags))
+		return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
+
+	return GFP_TRANSHUGE_LIGHT;
 }
 
 /* Caller must hold page table lock. */
@@ -1249,25 +1252,26 @@ out:
 	return 0;
 }
 
-int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+/*
+ * Return true if we do MADV_FREE successfully on entire pmd page.
+ * Otherwise, return false.
+ */
+bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		pmd_t *pmd, unsigned long addr, unsigned long next)
-
 {
 	spinlock_t *ptl;
 	pmd_t orig_pmd;
 	struct page *page;
 	struct mm_struct *mm = tlb->mm;
-	int ret = 0;
+	bool ret = false;
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
 		goto out_unlocked;
 
 	orig_pmd = *pmd;
-	if (is_huge_zero_pmd(orig_pmd)) {
-		ret = 1;
+	if (is_huge_zero_pmd(orig_pmd))
 		goto out;
-	}
 
 	page = pmd_page(orig_pmd);
 	/*
@@ -1309,7 +1313,7 @@ int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		set_pmd_at(mm, addr, pmd, orig_pmd);
 		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 	}
-	ret = 1;
+	ret = true;
 out:
 	spin_unlock(ptl);
 out_unlocked:
@@ -1586,7 +1590,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 
 	if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
 		/* Last compound_mapcount is gone. */
-		__dec_zone_page_state(page, NR_ANON_THPS);
+		__dec_node_page_state(page, NR_ANON_THPS);
 		if (TestClearPageDoubleMap(page)) {
 			/* No need in mapcount reference anymore */
 			for (i = 0; i < HPAGE_PMD_NR; i++)
@@ -1818,7 +1822,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	pgoff_t end = -1;
 	int i;
 
-	lruvec = mem_cgroup_page_lruvec(head, zone);
+	lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);
 
 	/* complete memcg works before add pages to LRU */
 	mem_cgroup_split_huge_fixup(head);
@@ -1848,7 +1852,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		spin_unlock(&head->mapping->tree_lock);
 	}
 
-	spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags);
+	spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 
 	unfreeze_page(head);
 
@@ -2034,7 +2038,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		lru_add_drain();
 
 	/* prevent PageLRU to go away from under us, and freeze lru stats */
-	spin_lock_irqsave(&page_zone(head)->lru_lock, flags);
+	spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags);
 
 	if (mapping) {
 		void **pslot;
@@ -2061,7 +2065,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			list_del(page_deferred_list(head));
 		}
 		if (mapping)
-			__dec_zone_page_state(page, NR_SHMEM_THPS);
+			__dec_node_page_state(page, NR_SHMEM_THPS);
 		spin_unlock(&pgdata->split_queue_lock);
 		__split_huge_page(page, list, flags);
 		ret = 0;
@@ -2077,7 +2081,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		spin_unlock(&pgdata->split_queue_lock);
 fail:		if (mapping)
 			spin_unlock(&mapping->tree_lock);
-		spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags);
+		spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 		unfreeze_page(head);
 		ret = -EBUSY;
 	}

mm/hugetlb.c

@@ -4391,7 +4391,6 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
 
 /*
  * This function is called from memory failure code.
- * Assume the caller holds page lock of the head page.
  */
 int dequeue_hwpoisoned_huge_page(struct page *hpage)
 {

mm/internal.h

@@ -78,7 +78,7 @@ extern unsigned long highest_memmap_pfn;
  */
 extern int isolate_lru_page(struct page *page);
 extern void putback_lru_page(struct page *page);
-extern bool zone_reclaimable(struct zone *zone);
+extern bool pgdat_reclaimable(struct pglist_data *pgdat);
 
 /*
  * in mm/rmap.c:
@@ -185,10 +185,7 @@ struct compact_control {
 	const unsigned int alloc_flags;	/* alloc flags of a direct compactor */
 	const int classzone_idx;	/* zone index of a direct compactor */
 	struct zone *zone;
-	int contended;			/* Signal need_sched() or lock
-					 * contention detected during
-					 * compaction
-					 */
+	bool contended;			/* Signal lock or sched contention */
 };
 
 unsigned long
@@ -433,10 +430,10 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
 }
 #endif /* CONFIG_SPARSEMEM */
 
-#define ZONE_RECLAIM_NOSCAN	-2
-#define ZONE_RECLAIM_FULL	-1
-#define ZONE_RECLAIM_SOME	0
-#define ZONE_RECLAIM_SUCCESS	1
+#define NODE_RECLAIM_NOSCAN	-2
+#define NODE_RECLAIM_FULL	-1
+#define NODE_RECLAIM_SOME	0
+#define NODE_RECLAIM_SUCCESS	1
 
 extern int hwpoison_filter(struct page *p);
 
@@ -467,7 +464,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
 #define ALLOC_CPUSET		0x40 /* check for correct cpuset */
 #define ALLOC_CMA		0x80 /* allow allocations from CMA areas */
-#define ALLOC_FAIR		0x100 /* fair zone allocation */
 
 enum ttu_flags;
 struct tlbflush_unmap_batch;

mm/kasan/Makefile

@@ -7,5 +7,4 @@ CFLAGS_REMOVE_kasan.o = -pg
 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
 CFLAGS_kasan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 
-obj-y := kasan.o report.o kasan_init.o
-obj-$(CONFIG_SLAB) += quarantine.o
+obj-y := kasan.o report.o kasan_init.o quarantine.o

mm/kasan/kasan.c

@@ -351,7 +351,6 @@ void kasan_free_pages(struct page *page, unsigned int order)
 				KASAN_FREE_PAGE);
 }
 
-#ifdef CONFIG_SLAB
 /*
  * Adaptive redzone policy taken from the userspace AddressSanitizer runtime.
  * For larger allocations larger redzones are used.
@@ -373,16 +372,8 @@ void kasan_cache_create(struct kmem_cache *cache, size_t *size,
 			unsigned long *flags)
 {
 	int redzone_adjust;
-	/* Make sure the adjusted size is still less than
-	 * KMALLOC_MAX_CACHE_SIZE.
-	 * TODO: this check is only useful for SLAB, but not SLUB. We'll need
-	 * to skip it for SLUB when it starts using kasan_cache_create().
-	 */
-	if (*size > KMALLOC_MAX_CACHE_SIZE -
-	    sizeof(struct kasan_alloc_meta) -
-	    sizeof(struct kasan_free_meta))
-		return;
-	*flags |= SLAB_KASAN;
+	int orig_size = *size;
+
 	/* Add alloc meta. */
 	cache->kasan_info.alloc_meta_offset = *size;
 	*size += sizeof(struct kasan_alloc_meta);
@@ -395,14 +386,26 @@ void kasan_cache_create(struct kmem_cache *cache, size_t *size,
 	}
 	redzone_adjust = optimal_redzone(cache->object_size) -
 		(*size - cache->object_size);
+
 	if (redzone_adjust > 0)
 		*size += redzone_adjust;
-	*size = min(KMALLOC_MAX_CACHE_SIZE,
-		    max(*size,
-			cache->object_size +
-			optimal_redzone(cache->object_size)));
+
+	*size = min(KMALLOC_MAX_SIZE, max(*size, cache->object_size +
+					optimal_redzone(cache->object_size)));
+
+	/*
+	 * If the metadata doesn't fit, don't enable KASAN at all.
+	 */
+	if (*size <= cache->kasan_info.alloc_meta_offset ||
+			*size <= cache->kasan_info.free_meta_offset) {
+		cache->kasan_info.alloc_meta_offset = 0;
+		cache->kasan_info.free_meta_offset = 0;
+		*size = orig_size;
+		return;
+	}
+
+	*flags |= SLAB_KASAN;
 }
-#endif
 
 void kasan_cache_shrink(struct kmem_cache *cache)
 {
@@ -414,6 +417,14 @@ void kasan_cache_destroy(struct kmem_cache *cache)
 	quarantine_remove_cache(cache);
 }
 
+size_t kasan_metadata_size(struct kmem_cache *cache)
+{
+	return (cache->kasan_info.alloc_meta_offset ?
+		sizeof(struct kasan_alloc_meta) : 0) +
+		(cache->kasan_info.free_meta_offset ?
+		sizeof(struct kasan_free_meta) : 0);
+}
+
 void kasan_poison_slab(struct page *page)
 {
 	kasan_poison_shadow(page_address(page),
@@ -431,16 +442,13 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object)
 	kasan_poison_shadow(object,
 			round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE),
 			KASAN_KMALLOC_REDZONE);
-#ifdef CONFIG_SLAB
 	if (cache->flags & SLAB_KASAN) {
 		struct kasan_alloc_meta *alloc_info =
 			get_alloc_info(cache, object);
 		alloc_info->state = KASAN_STATE_INIT;
 	}
-#endif
 }
 
-#ifdef CONFIG_SLAB
 static inline int in_irqentry_text(unsigned long ptr)
 {
 	return (ptr >= (unsigned long)&__irqentry_text_start &&
@@ -501,7 +509,6 @@ struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
 	BUILD_BUG_ON(sizeof(struct kasan_free_meta) > 32);
 	return (void *)object + cache->kasan_info.free_meta_offset;
 }
-#endif
 
 void kasan_slab_alloc(struct kmem_cache *cache, void *object, gfp_t flags)
 {
@@ -522,16 +529,16 @@ static void kasan_poison_slab_free(struct kmem_cache *cache, void *object)
 
 bool kasan_slab_free(struct kmem_cache *cache, void *object)
 {
-#ifdef CONFIG_SLAB
 	/* RCU slabs could be legally used after free within the RCU period */
 	if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU))
 		return false;
 
 	if (likely(cache->flags & SLAB_KASAN)) {
-		struct kasan_alloc_meta *alloc_info =
-			get_alloc_info(cache, object);
-		struct kasan_free_meta *free_info =
-			get_free_info(cache, object);
+		struct kasan_alloc_meta *alloc_info;
+		struct kasan_free_meta *free_info;
+
+		alloc_info = get_alloc_info(cache, object);
+		free_info = get_free_info(cache, object);
 
 		switch (alloc_info->state) {
 		case KASAN_STATE_ALLOC:
@@ -550,10 +557,6 @@ bool kasan_slab_free(struct kmem_cache *cache, void *object)
 		}
 	}
 	return false;
-#else
-	kasan_poison_slab_free(cache, object);
-	return false;
-#endif
 }
 
 void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
@@ -576,7 +579,6 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
 	kasan_unpoison_shadow(object, size);
 	kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
 		KASAN_KMALLOC_REDZONE);
-#ifdef CONFIG_SLAB
 	if (cache->flags & SLAB_KASAN) {
 		struct kasan_alloc_meta *alloc_info =
 			get_alloc_info(cache, object);
@@ -585,7 +587,6 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
 		alloc_info->alloc_size = size;
 		set_track(&alloc_info->track, flags);
 	}
-#endif
 }
 EXPORT_SYMBOL(kasan_kmalloc);
 

mm/kasan/kasan.h

@@ -95,7 +95,6 @@ struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
 struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
 					const void *object);
 
-
 static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
 {
 	return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET)
@@ -110,7 +109,7 @@ static inline bool kasan_report_enabled(void)
 void kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip);
 
-#ifdef CONFIG_SLAB
+#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB)
 void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache);
 void quarantine_reduce(void);
 void quarantine_remove_cache(struct kmem_cache *cache);

mm/kasan/report.c

@@ -116,7 +116,6 @@ static inline bool init_task_stack_addr(const void *addr)
 			sizeof(init_thread_union.stack));
 }
 
-#ifdef CONFIG_SLAB
 static void print_track(struct kasan_track *track)
 {
 	pr_err("PID = %u\n", track->pid);
@@ -130,8 +129,8 @@ static void print_track(struct kasan_track *track)
 	}
 }
 
-static void object_err(struct kmem_cache *cache, struct page *page,
-			void *object, char *unused_reason)
+static void kasan_object_err(struct kmem_cache *cache, struct page *page,
+				void *object, char *unused_reason)
 {
 	struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object);
 	struct kasan_free_meta *free_info;
@@ -162,7 +161,6 @@ static void object_err(struct kmem_cache *cache, struct page *page,
 		break;
 	}
 }
-#endif
 
 static void print_address_description(struct kasan_access_info *info)
 {
@@ -177,7 +175,7 @@ static void print_address_description(struct kasan_access_info *info)
 			struct kmem_cache *cache = page->slab_cache;
 			object = nearest_obj(cache, page,
 						(void *)info->access_addr);
-			object_err(cache, page, object,
+			kasan_object_err(cache, page, object,
 					"kasan: bad access detected");
 			return;
 		}

mm/khugepaged.c

@@ -480,7 +480,7 @@ void __khugepaged_exit(struct mm_struct *mm)
 static void release_pte_page(struct page *page)
 {
 	/* 0 stands for page_is_file_cache(page) == false */
-	dec_zone_page_state(page, NR_ISOLATED_ANON + 0);
+	dec_node_page_state(page, NR_ISOLATED_ANON + 0);
 	unlock_page(page);
 	putback_lru_page(page);
 }
@@ -576,7 +576,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 			goto out;
 		}
 		/* 0 stands for page_is_file_cache(page) == false */
-		inc_zone_page_state(page, NR_ISOLATED_ANON + 0);
+		inc_node_page_state(page, NR_ISOLATED_ANON + 0);
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 
@@ -672,10 +672,10 @@ static bool khugepaged_scan_abort(int nid)
 	int i;
 
 	/*
-	 * If zone_reclaim_mode is disabled, then no extra effort is made to
+	 * If node_reclaim_mode is disabled, then no extra effort is made to
 	 * allocate memory locally.
 	 */
-	if (!zone_reclaim_mode)
+	if (!node_reclaim_mode)
 		return false;
 
 	/* If there is a count for this node already, it must be acceptable */
@@ -694,7 +694,7 @@ static bool khugepaged_scan_abort(int nid)
 /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */
 static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void)
 {
-	return GFP_TRANSHUGE | (khugepaged_defrag() ? __GFP_DIRECT_RECLAIM : 0);
+	return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT;
 }
 
 #ifdef CONFIG_NUMA
@@ -1483,10 +1483,10 @@ tree_unlocked:
 		}
 
 		local_irq_save(flags);
-		__inc_zone_page_state(new_page, NR_SHMEM_THPS);
+		__inc_node_page_state(new_page, NR_SHMEM_THPS);
 		if (nr_none) {
-			__mod_zone_page_state(zone, NR_FILE_PAGES, nr_none);
-			__mod_zone_page_state(zone, NR_SHMEM, nr_none);
+			__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
+			__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
 		}
 		local_irq_restore(flags);
 

mm/kmemleak.c

@@ -1485,8 +1485,10 @@ static int kmemleak_scan_thread(void *arg)
 	 * Wait before the first scan to allow the system to fully initialize.
 	 */
 	if (first_run) {
+		signed long timeout = msecs_to_jiffies(SECS_FIRST_SCAN * 1000);
 		first_run = 0;
-		ssleep(SECS_FIRST_SCAN);
+		while (timeout && !kthread_should_stop())
+			timeout = schedule_timeout_interruptible(timeout);
 	}
 
 	while (!kthread_should_stop()) {

mm/memblock.c

@@ -20,7 +20,7 @@
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
 
-#include <asm-generic/sections.h>
+#include <asm/sections.h>
 #include <linux/io.h>
 
 #include "internal.h"
@@ -1027,7 +1027,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags,
 				*out_end = m_end;
 			if (out_nid)
 				*out_nid = m_nid;
-			idx_a++;
+			idx_a--;
 			*idx = (u32)idx_a | (u64)idx_b << 32;
 			return;
 		}
@@ -1465,15 +1465,16 @@ phys_addr_t __init_memblock memblock_end_of_DRAM(void)
 	return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
 }
 
-void __init memblock_enforce_memory_limit(phys_addr_t limit)
+static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit)
 {
 	phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX;
 	struct memblock_region *r;
 
-	if (!limit)
-		return;
-
-	/* find out max address */
+	/*
+	 * translate the memory @limit size into the max address within one of
+	 * the memory memblock regions, if the @limit exceeds the total size
+	 * of those regions, max_addr will keep original value ULLONG_MAX
+	 */
 	for_each_memblock(memory, r) {
 		if (limit <= r->size) {
 			max_addr = r->base + limit;
@@ -1482,6 +1483,22 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit)
 		limit -= r->size;
 	}
 
+	return max_addr;
+}
+
+void __init memblock_enforce_memory_limit(phys_addr_t limit)
+{
+	phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX;
+
+	if (!limit)
+		return;
+
+	max_addr = __find_max_addr(limit);
+
+	/* @limit exceeds the total size of the memory, do nothing */
+	if (max_addr == (phys_addr_t)ULLONG_MAX)
+		return;
+
 	/* truncate both memory and reserved regions */
 	memblock_remove_range(&memblock.memory, max_addr,
 			      (phys_addr_t)ULLONG_MAX);
@@ -1489,6 +1506,36 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit)
 			      (phys_addr_t)ULLONG_MAX);
 }
 
+void __init memblock_mem_limit_remove_map(phys_addr_t limit)
+{
+	struct memblock_type *type = &memblock.memory;
+	phys_addr_t max_addr;
+	int i, ret, start_rgn, end_rgn;
+
+	if (!limit)
+		return;
+
+	max_addr = __find_max_addr(limit);
+
+	/* @limit exceeds the total size of the memory, do nothing */
+	if (max_addr == (phys_addr_t)ULLONG_MAX)
+		return;
+
+	ret = memblock_isolate_range(type, max_addr, (phys_addr_t)ULLONG_MAX,
+				&start_rgn, &end_rgn);
+	if (ret)
+		return;
+
+	/* remove all the MAP regions above the limit */
+	for (i = end_rgn - 1; i >= start_rgn; i--) {
+		if (!memblock_is_nomap(&type->regions[i]))
+			memblock_remove_region(type, i);
+	}
+	/* truncate the reserved regions */
+	memblock_remove_range(&memblock.reserved, max_addr,
+			      (phys_addr_t)ULLONG_MAX);
+}
+
 static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
 {
 	unsigned int left = 0, right = type->cnt;

mm/memcontrol.c

@@ -132,15 +132,11 @@ static const char * const mem_cgroup_lru_names[] = {
  * their hierarchy representation
  */
 
-struct mem_cgroup_tree_per_zone {
+struct mem_cgroup_tree_per_node {
 	struct rb_root rb_root;
 	spinlock_t lock;
 };
 
-struct mem_cgroup_tree_per_node {
-	struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES];
-};
-
 struct mem_cgroup_tree {
 	struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
 };
@@ -323,15 +319,6 @@ EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
 #endif /* !CONFIG_SLOB */
 
-static struct mem_cgroup_per_zone *
-mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
-{
-	int nid = zone_to_nid(zone);
-	int zid = zone_idx(zone);
-
-	return &memcg->nodeinfo[nid]->zoneinfo[zid];
-}
-
 /**
  * mem_cgroup_css_from_page - css of the memcg associated with a page
  * @page: page of interest
@@ -383,37 +370,35 @@ ino_t page_cgroup_ino(struct page *page)
 	return ino;
 }
 
-static struct mem_cgroup_per_zone *
-mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
+static struct mem_cgroup_per_node *
+mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page)
 {
 	int nid = page_to_nid(page);
-	int zid = page_zonenum(page);
 
-	return &memcg->nodeinfo[nid]->zoneinfo[zid];
+	return memcg->nodeinfo[nid];
 }
 
-static struct mem_cgroup_tree_per_zone *
-soft_limit_tree_node_zone(int nid, int zid)
+static struct mem_cgroup_tree_per_node *
+soft_limit_tree_node(int nid)
 {
-	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+	return soft_limit_tree.rb_tree_per_node[nid];
 }
 
-static struct mem_cgroup_tree_per_zone *
+static struct mem_cgroup_tree_per_node *
 soft_limit_tree_from_page(struct page *page)
 {
 	int nid = page_to_nid(page);
-	int zid = page_zonenum(page);
 
-	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+	return soft_limit_tree.rb_tree_per_node[nid];
 }
 
-static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
-					 struct mem_cgroup_tree_per_zone *mctz,
+static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
+					 struct mem_cgroup_tree_per_node *mctz,
 					 unsigned long new_usage_in_excess)
 {
 	struct rb_node **p = &mctz->rb_root.rb_node;
 	struct rb_node *parent = NULL;
-	struct mem_cgroup_per_zone *mz_node;
+	struct mem_cgroup_per_node *mz_node;
 
 	if (mz->on_tree)
 		return;
@@ -423,7 +408,7 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
 		return;
 	while (*p) {
 		parent = *p;
-		mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
+		mz_node = rb_entry(parent, struct mem_cgroup_per_node,
 					tree_node);
 		if (mz->usage_in_excess < mz_node->usage_in_excess)
 			p = &(*p)->rb_left;
@@ -439,8 +424,8 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
 	mz->on_tree = true;
 }
 
-static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
-					 struct mem_cgroup_tree_per_zone *mctz)
+static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
+					 struct mem_cgroup_tree_per_node *mctz)
 {
 	if (!mz->on_tree)
 		return;
@@ -448,8 +433,8 @@ static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
 	mz->on_tree = false;
 }
 
-static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
-				       struct mem_cgroup_tree_per_zone *mctz)
+static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
+				       struct mem_cgroup_tree_per_node *mctz)
 {
 	unsigned long flags;
 
@@ -473,8 +458,8 @@ static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
 static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 {
 	unsigned long excess;
-	struct mem_cgroup_per_zone *mz;
-	struct mem_cgroup_tree_per_zone *mctz;
+	struct mem_cgroup_per_node *mz;
+	struct mem_cgroup_tree_per_node *mctz;
 
 	mctz = soft_limit_tree_from_page(page);
 	/*
@@ -482,7 +467,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 	 * because their event counter is not touched.
 	 */
 	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
-		mz = mem_cgroup_page_zoneinfo(memcg, page);
+		mz = mem_cgroup_page_nodeinfo(memcg, page);
 		excess = soft_limit_excess(memcg);
 		/*
 		 * We have to update the tree if mz is on RB-tree or
@@ -507,24 +492,22 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 
 static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
 {
-	struct mem_cgroup_tree_per_zone *mctz;
-	struct mem_cgroup_per_zone *mz;
-	int nid, zid;
+	struct mem_cgroup_tree_per_node *mctz;
+	struct mem_cgroup_per_node *mz;
+	int nid;
 
 	for_each_node(nid) {
-		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-			mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
-			mctz = soft_limit_tree_node_zone(nid, zid);
-			mem_cgroup_remove_exceeded(mz, mctz);
-		}
+		mz = mem_cgroup_nodeinfo(memcg, nid);
+		mctz = soft_limit_tree_node(nid);
+		mem_cgroup_remove_exceeded(mz, mctz);
 	}
 }
 
-static struct mem_cgroup_per_zone *
-__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+static struct mem_cgroup_per_node *
+__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
 {
 	struct rb_node *rightmost = NULL;
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 
 retry:
 	mz = NULL;
@@ -532,7 +515,7 @@ retry:
 	if (!rightmost)
 		goto done;		/* Nothing to reclaim from */
 
-	mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node);
+	mz = rb_entry(rightmost, struct mem_cgroup_per_node, tree_node);
 	/*
 	 * Remove the node now but someone else can add it back,
 	 * we will to add it back at the end of reclaim to its correct
@@ -546,10 +529,10 @@ done:
 	return mz;
 }
 
-static struct mem_cgroup_per_zone *
-mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+static struct mem_cgroup_per_node *
+mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
 {
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 
 	spin_lock_irq(&mctz->lock);
 	mz = __mem_cgroup_largest_soft_limit_node(mctz);
@@ -643,20 +626,16 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 					   int nid, unsigned int lru_mask)
 {
 	unsigned long nr = 0;
-	int zid;
+	struct mem_cgroup_per_node *mz;
+	enum lru_list lru;
 
 	VM_BUG_ON((unsigned)nid >= nr_node_ids);
 
-	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-		struct mem_cgroup_per_zone *mz;
-		enum lru_list lru;
-
-		for_each_lru(lru) {
-			if (!(BIT(lru) & lru_mask))
-				continue;
-			mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
-			nr += mz->lru_size[lru];
-		}
+	for_each_lru(lru) {
+		if (!(BIT(lru) & lru_mask))
+			continue;
+		mz = mem_cgroup_nodeinfo(memcg, nid);
+		nr += mz->lru_size[lru];
 	}
 	return nr;
 }
@@ -809,9 +788,9 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 	rcu_read_lock();
 
 	if (reclaim) {
-		struct mem_cgroup_per_zone *mz;
+		struct mem_cgroup_per_node *mz;
 
-		mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone);
+		mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id);
 		iter = &mz->iter[reclaim->priority];
 
 		if (prev && reclaim->generation != iter->generation)
@@ -910,19 +889,17 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
 {
 	struct mem_cgroup *memcg = dead_memcg;
 	struct mem_cgroup_reclaim_iter *iter;
-	struct mem_cgroup_per_zone *mz;
-	int nid, zid;
+	struct mem_cgroup_per_node *mz;
+	int nid;
 	int i;
 
 	while ((memcg = parent_mem_cgroup(memcg))) {
 		for_each_node(nid) {
-			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-				mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
-				for (i = 0; i <= DEF_PRIORITY; i++) {
-					iter = &mz->iter[i];
-					cmpxchg(&iter->position,
-						dead_memcg, NULL);
-				}
+			mz = mem_cgroup_nodeinfo(memcg, nid);
+			for (i = 0; i <= DEF_PRIORITY; i++) {
+				iter = &mz->iter[i];
+				cmpxchg(&iter->position,
+					dead_memcg, NULL);
 			}
 		}
 	}
@@ -943,39 +920,6 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
 	     iter != NULL;				\
 	     iter = mem_cgroup_iter(NULL, iter, NULL))
 
-/**
- * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
- * @zone: zone of the wanted lruvec
- * @memcg: memcg of the wanted lruvec
- *
- * Returns the lru list vector holding pages for the given @zone and
- * @mem.  This can be the global zone lruvec, if the memory controller
- * is disabled.
- */
-struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
-				      struct mem_cgroup *memcg)
-{
-	struct mem_cgroup_per_zone *mz;
-	struct lruvec *lruvec;
-
-	if (mem_cgroup_disabled()) {
-		lruvec = &zone->lruvec;
-		goto out;
-	}
-
-	mz = mem_cgroup_zone_zoneinfo(memcg, zone);
-	lruvec = &mz->lruvec;
-out:
-	/*
-	 * Since a node can be onlined after the mem_cgroup was created,
-	 * we have to be prepared to initialize lruvec->zone here;
-	 * and if offlined then reonlined, we need to reinitialize it.
-	 */
-	if (unlikely(lruvec->zone != zone))
-		lruvec->zone = zone;
-	return lruvec;
-}
-
 /**
  * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
  * @page: the page
@@ -985,14 +929,14 @@ out:
  * and putback protocol: the LRU lock must be held, and the page must
  * either be PageLRU() or the caller must have isolated/allocated it.
  */
-struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
+struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat)
 {
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 
 	if (mem_cgroup_disabled()) {
-		lruvec = &zone->lruvec;
+		lruvec = &pgdat->lruvec;
 		goto out;
 	}
 
@@ -1004,7 +948,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 	if (!memcg)
 		memcg = root_mem_cgroup;
 
-	mz = mem_cgroup_page_zoneinfo(memcg, page);
+	mz = mem_cgroup_page_nodeinfo(memcg, page);
 	lruvec = &mz->lruvec;
 out:
 	/*
@@ -1012,8 +956,8 @@ out:
 	 * we have to be prepared to initialize lruvec->zone here;
 	 * and if offlined then reonlined, we need to reinitialize it.
 	 */
-	if (unlikely(lruvec->zone != zone))
-		lruvec->zone = zone;
+	if (unlikely(lruvec->pgdat != pgdat))
+		lruvec->pgdat = pgdat;
 	return lruvec;
 }
 
@@ -1030,17 +974,15 @@ out:
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 				int nr_pages)
 {
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 	unsigned long *lru_size;
 	long size;
 	bool empty;
 
-	__update_lru_size(lruvec, lru, nr_pages);
-
 	if (mem_cgroup_disabled())
 		return;
 
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	lru_size = mz->lru_size + lru;
 	empty = list_empty(lruvec->lists + lru);
 
@@ -1276,9 +1218,9 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	 * select it.  The goal is to allow it to allocate so that it may
 	 * quickly exit and free its memory.
 	 */
-	if (fatal_signal_pending(current) || task_will_free_mem(current)) {
+	if (task_will_free_mem(current)) {
 		mark_oom_victim(current);
-		try_oom_reaper(current);
+		wake_oom_reaper(current);
 		goto unlock;
 	}
 
@@ -1433,7 +1375,7 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 #endif
 
 static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
-				   struct zone *zone,
+				   pg_data_t *pgdat,
 				   gfp_t gfp_mask,
 				   unsigned long *total_scanned)
 {
@@ -1443,7 +1385,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 	unsigned long excess;
 	unsigned long nr_scanned;
 	struct mem_cgroup_reclaim_cookie reclaim = {
-		.zone = zone,
+		.pgdat = pgdat,
 		.priority = 0,
 	};
 
@@ -1473,8 +1415,8 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 			}
 			continue;
 		}
-		total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
-						     zone, &nr_scanned);
+		total += mem_cgroup_shrink_node(victim, gfp_mask, false,
+					pgdat, &nr_scanned);
 		*total_scanned += nr_scanned;
 		if (!soft_limit_excess(root_memcg))
 			break;
@@ -2107,11 +2049,11 @@ static void lock_page_lru(struct page *page, int *isolated)
 {
 	struct zone *zone = page_zone(page);
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	if (PageLRU(page)) {
 		struct lruvec *lruvec;
 
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
 		ClearPageLRU(page);
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		*isolated = 1;
@@ -2126,12 +2068,12 @@ static void unlock_page_lru(struct page *page, int isolated)
 	if (isolated) {
 		struct lruvec *lruvec;
 
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		SetPageLRU(page);
 		add_page_to_lru_list(page, lruvec, page_lru(page));
 	}
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 }
 
 static void commit_charge(struct page *page, struct mem_cgroup *memcg,
@@ -2431,7 +2373,7 @@ void memcg_kmem_uncharge(struct page *page, int order)
 
 /*
  * Because tail pages are not marked as "used", set it. We're under
- * zone->lru_lock and migration entries setup in all page mappings.
+ * zone_lru_lock and migration entries setup in all page mappings.
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
@@ -2601,22 +2543,22 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 	return ret;
 }
 
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 					    gfp_t gfp_mask,
 					    unsigned long *total_scanned)
 {
 	unsigned long nr_reclaimed = 0;
-	struct mem_cgroup_per_zone *mz, *next_mz = NULL;
+	struct mem_cgroup_per_node *mz, *next_mz = NULL;
 	unsigned long reclaimed;
 	int loop = 0;
-	struct mem_cgroup_tree_per_zone *mctz;
+	struct mem_cgroup_tree_per_node *mctz;
 	unsigned long excess;
 	unsigned long nr_scanned;
 
 	if (order > 0)
 		return 0;
 
-	mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
+	mctz = soft_limit_tree_node(pgdat->node_id);
 	/*
 	 * This loop can run a while, specially if mem_cgroup's continuously
 	 * keep exceeding their soft limit and putting the system under
@@ -2631,7 +2573,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 			break;
 
 		nr_scanned = 0;
-		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone,
+		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat,
 						    gfp_mask, &nr_scanned);
 		nr_reclaimed += reclaimed;
 		*total_scanned += nr_scanned;
@@ -3252,22 +3194,21 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 
 #ifdef CONFIG_DEBUG_VM
 	{
-		int nid, zid;
-		struct mem_cgroup_per_zone *mz;
+		pg_data_t *pgdat;
+		struct mem_cgroup_per_node *mz;
 		struct zone_reclaim_stat *rstat;
 		unsigned long recent_rotated[2] = {0, 0};
 		unsigned long recent_scanned[2] = {0, 0};
 
-		for_each_online_node(nid)
-			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-				mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
-				rstat = &mz->lruvec.reclaim_stat;
+		for_each_online_pgdat(pgdat) {
+			mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
+			rstat = &mz->lruvec.reclaim_stat;
 
-				recent_rotated[0] += rstat->recent_rotated[0];
-				recent_rotated[1] += rstat->recent_rotated[1];
-				recent_scanned[0] += rstat->recent_scanned[0];
-				recent_scanned[1] += rstat->recent_scanned[1];
-			}
+			recent_rotated[0] += rstat->recent_rotated[0];
+			recent_rotated[1] += rstat->recent_rotated[1];
+			recent_scanned[0] += rstat->recent_scanned[0];
+			recent_scanned[1] += rstat->recent_scanned[1];
+		}
 		seq_printf(m, "recent_rotated_anon %lu\n", recent_rotated[0]);
 		seq_printf(m, "recent_rotated_file %lu\n", recent_rotated[1]);
 		seq_printf(m, "recent_scanned_anon %lu\n", recent_scanned[0]);
@@ -4147,11 +4088,10 @@ struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
 	return idr_find(&mem_cgroup_idr, id);
 }
 
-static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
+static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
-	struct mem_cgroup_per_zone *mz;
-	int zone, tmp = node;
+	int tmp = node;
 	/*
 	 * This routine is called against possible nodes.
 	 * But it's BUG to call kmalloc() against offline node.
@@ -4166,18 +4106,16 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return 1;
 
-	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
-		mz = &pn->zoneinfo[zone];
-		lruvec_init(&mz->lruvec);
-		mz->usage_in_excess = 0;
-		mz->on_tree = false;
-		mz->memcg = memcg;
-	}
+	lruvec_init(&pn->lruvec);
+	pn->usage_in_excess = 0;
+	pn->on_tree = false;
+	pn->memcg = memcg;
+
 	memcg->nodeinfo[node] = pn;
 	return 0;
 }
 
-static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
+static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 {
 	kfree(memcg->nodeinfo[node]);
 }
@@ -4188,7 +4126,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 
 	memcg_wb_domain_exit(memcg);
 	for_each_node(node)
-		free_mem_cgroup_per_zone_info(memcg, node);
+		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->stat);
 	kfree(memcg);
 }
@@ -4217,7 +4155,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 		goto fail;
 
 	for_each_node(node)
-		if (alloc_mem_cgroup_per_zone_info(memcg, node))
+		if (alloc_mem_cgroup_per_node_info(memcg, node))
 			goto fail;
 
 	if (memcg_wb_domain_init(memcg, GFP_KERNEL))
@@ -5233,7 +5171,7 @@ static int memory_stat_show(struct seq_file *m, void *v)
 	seq_printf(m, "file %llu\n",
 		   (u64)stat[MEM_CGROUP_STAT_CACHE] * PAGE_SIZE);
 	seq_printf(m, "kernel_stack %llu\n",
-		   (u64)stat[MEMCG_KERNEL_STACK] * PAGE_SIZE);
+		   (u64)stat[MEMCG_KERNEL_STACK_KB] * 1024);
 	seq_printf(m, "slab %llu\n",
 		   (u64)(stat[MEMCG_SLAB_RECLAIMABLE] +
 			 stat[MEMCG_SLAB_UNRECLAIMABLE]) * PAGE_SIZE);
@@ -5820,18 +5758,12 @@ static int __init mem_cgroup_init(void)
 
 	for_each_node(node) {
 		struct mem_cgroup_tree_per_node *rtpn;
-		int zone;
 
 		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL,
 				    node_online(node) ? node : NUMA_NO_NODE);
 
-		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
-			struct mem_cgroup_tree_per_zone *rtpz;
-
-			rtpz = &rtpn->rb_tree_per_zone[zone];
-			rtpz->rb_root = RB_ROOT;
-			spin_lock_init(&rtpz->lock);
-		}
+		rtpn->rb_root = RB_ROOT;
+		spin_lock_init(&rtpn->lock);
 		soft_limit_tree.rb_tree_per_node[node] = rtpn;
 	}
 

mm/memory-failure.c

@@ -741,8 +741,6 @@ static int me_huge_page(struct page *p, unsigned long pfn)
 	 * page->lru because it can be used in other hugepage operations,
 	 * such as __unmap_hugepage_range() and gather_surplus_pages().
 	 * So instead we use page_mapping() and PageAnon().
-	 * We assume that this function is called with page lock held,
-	 * so there is no race between isolation and mapping/unmapping.
 	 */
 	if (!(page_mapping(hpage) || PageAnon(hpage))) {
 		res = dequeue_hwpoisoned_huge_page(hpage);
@@ -1663,7 +1661,7 @@ static int __soft_offline_page(struct page *page, int flags)
 	put_hwpoison_page(page);
 	if (!ret) {
 		LIST_HEAD(pagelist);
-		inc_zone_page_state(page, NR_ISOLATED_ANON +
+		inc_node_page_state(page, NR_ISOLATED_ANON +
 					page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
@@ -1671,7 +1669,7 @@ static int __soft_offline_page(struct page *page, int flags)
 		if (ret) {
 			if (!list_empty(&pagelist)) {
 				list_del(&page->lru);
-				dec_zone_page_state(page, NR_ISOLATED_ANON +
+				dec_node_page_state(page, NR_ISOLATED_ANON +
 						page_is_file_cache(page));
 				putback_lru_page(page);
 			}

mm/memory_hotplug.c

@@ -1209,9 +1209,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 
 		arch_refresh_nodedata(nid, pgdat);
 	} else {
-		/* Reset the nr_zones and classzone_idx to 0 before reuse */
+		/* Reset the nr_zones, order and classzone_idx before reuse */
 		pgdat->nr_zones = 0;
-		pgdat->classzone_idx = 0;
+		pgdat->kswapd_order = 0;
+		pgdat->kswapd_classzone_idx = 0;
 	}
 
 	/* we can use NODE_DATA(nid) from here */
@@ -1547,6 +1548,37 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 	return 0;
 }
 
+static struct page *new_node_page(struct page *page, unsigned long private,
+		int **result)
+{
+	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
+	int nid = page_to_nid(page);
+	nodemask_t nmask = node_online_map;
+	struct page *new_page;
+
+	/*
+	 * TODO: allocate a destination hugepage from a nearest neighbor node,
+	 * accordance with memory policy of the user process if possible. For
+	 * now as a simple work-around, we use the next node for destination.
+	 */
+	if (PageHuge(page))
+		return alloc_huge_page_node(page_hstate(compound_head(page)),
+					next_node_in(nid, nmask));
+
+	node_clear(nid, nmask);
+	if (PageHighMem(page)
+	    || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
+		gfp_mask |= __GFP_HIGHMEM;
+
+	new_page = __alloc_pages_nodemask(gfp_mask, 0,
+					node_zonelist(nid, gfp_mask), &nmask);
+	if (!new_page)
+		new_page = __alloc_pages(gfp_mask, 0,
+					node_zonelist(nid, gfp_mask));
+
+	return new_page;
+}
+
 #define NR_OFFLINE_AT_ONCE_PAGES	(256)
 static int
 do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
@@ -1586,7 +1618,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			put_page(page);
 			list_add_tail(&page->lru, &source);
 			move_pages--;
-			inc_zone_page_state(page, NR_ISOLATED_ANON +
+			inc_node_page_state(page, NR_ISOLATED_ANON +
 					    page_is_file_cache(page));
 
 		} else {
@@ -1610,11 +1642,8 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			goto out;
 		}
 
-		/*
-		 * alloc_migrate_target should be improooooved!!
-		 * migrate_pages returns # of failed pages.
-		 */
-		ret = migrate_pages(&source, alloc_migrate_target, NULL, 0,
+		/* Allocate a new page from the nearest neighbor node */
+		ret = migrate_pages(&source, new_node_page, NULL, 0,
 					MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
 		if (ret)
 			putback_movable_pages(&source);

mm/mempolicy.c

@@ -962,7 +962,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
 	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
 		if (!isolate_lru_page(page)) {
 			list_add_tail(&page->lru, pagelist);
-			inc_zone_page_state(page, NR_ISOLATED_ANON +
+			inc_node_page_state(page, NR_ISOLATED_ANON +
 					    page_is_file_cache(page));
 		}
 	}

mm/mempool.c

@@ -306,7 +306,7 @@ EXPORT_SYMBOL(mempool_resize);
  * returns NULL. Note that due to preallocation, this function
  * *never* fails when called from process contexts. (it might
  * fail if called from an IRQ context.)
- * Note: neither __GFP_NOMEMALLOC nor __GFP_ZERO are supported.
+ * Note: using __GFP_ZERO is not supported.
  */
 void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
 {
@@ -315,27 +315,16 @@ void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
 	wait_queue_t wait;
 	gfp_t gfp_temp;
 
-	/* If oom killed, memory reserves are essential to prevent livelock */
-	VM_WARN_ON_ONCE(gfp_mask & __GFP_NOMEMALLOC);
-	/* No element size to zero on allocation */
 	VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO);
-
 	might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
 
+	gfp_mask |= __GFP_NOMEMALLOC;	/* don't allocate emergency reserves */
 	gfp_mask |= __GFP_NORETRY;	/* don't loop in __alloc_pages */
 	gfp_mask |= __GFP_NOWARN;	/* failures are OK */
 
 	gfp_temp = gfp_mask & ~(__GFP_DIRECT_RECLAIM|__GFP_IO);
 
 repeat_alloc:
-	if (likely(pool->curr_nr)) {
-		/*
-		 * Don't allocate from emergency reserves if there are
-		 * elements available.  This check is racy, but it will
-		 * be rechecked each loop.
-		 */
-		gfp_temp |= __GFP_NOMEMALLOC;
-	}
 
 	element = pool->alloc(gfp_temp, pool->pool_data);
 	if (likely(element != NULL))
@@ -359,12 +348,11 @@ repeat_alloc:
 	 * We use gfp mask w/o direct reclaim or IO for the first round.  If
 	 * alloc failed with that and @pool was empty, retry immediately.
 	 */
-	if ((gfp_temp & ~__GFP_NOMEMALLOC) != gfp_mask) {
+	if (gfp_temp != gfp_mask) {
 		spin_unlock_irqrestore(&pool->lock, flags);
 		gfp_temp = gfp_mask;
 		goto repeat_alloc;
 	}
-	gfp_temp = gfp_mask;
 
 	/* We must not sleep if !__GFP_DIRECT_RECLAIM */
 	if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) {

mm/migrate.c

@@ -168,7 +168,7 @@ void putback_movable_pages(struct list_head *l)
 			continue;
 		}
 		list_del(&page->lru);
-		dec_zone_page_state(page, NR_ISOLATED_ANON +
+		dec_node_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
 		/*
 		 * We isolated non-lru movable page so here we can use
@@ -501,19 +501,21 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 * new page and drop references to the old page.
 	 *
 	 * Note that anonymous pages are accounted for
-	 * via NR_FILE_PAGES and NR_ANON_PAGES if they
+	 * via NR_FILE_PAGES and NR_ANON_MAPPED if they
 	 * are mapped to swap space.
 	 */
 	if (newzone != oldzone) {
-		__dec_zone_state(oldzone, NR_FILE_PAGES);
-		__inc_zone_state(newzone, NR_FILE_PAGES);
+		__dec_node_state(oldzone->zone_pgdat, NR_FILE_PAGES);
+		__inc_node_state(newzone->zone_pgdat, NR_FILE_PAGES);
 		if (PageSwapBacked(page) && !PageSwapCache(page)) {
-			__dec_zone_state(oldzone, NR_SHMEM);
-			__inc_zone_state(newzone, NR_SHMEM);
+			__dec_node_state(oldzone->zone_pgdat, NR_SHMEM);
+			__inc_node_state(newzone->zone_pgdat, NR_SHMEM);
 		}
 		if (dirty && mapping_cap_account_dirty(mapping)) {
-			__dec_zone_state(oldzone, NR_FILE_DIRTY);
-			__inc_zone_state(newzone, NR_FILE_DIRTY);
+			__dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);
+			__dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);
+			__inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);
+			__inc_zone_state(newzone, NR_ZONE_WRITE_PENDING);
 		}
 	}
 	local_irq_enable();
@@ -1119,7 +1121,7 @@ out:
 		 * restored.
 		 */
 		list_del(&page->lru);
-		dec_zone_page_state(page, NR_ISOLATED_ANON +
+		dec_node_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
 	}
 
@@ -1460,7 +1462,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 		err = isolate_lru_page(page);
 		if (!err) {
 			list_add_tail(&page->lru, &pagelist);
-			inc_zone_page_state(page, NR_ISOLATED_ANON +
+			inc_node_page_state(page, NR_ISOLATED_ANON +
 					    page_is_file_cache(page));
 		}
 put_and_set:
@@ -1726,15 +1728,16 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
 				   unsigned long nr_migrate_pages)
 {
 	int z;
+
+	if (!pgdat_reclaimable(pgdat))
+		return false;
+
 	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
 		struct zone *zone = pgdat->node_zones + z;
 
 		if (!populated_zone(zone))
 			continue;
 
-		if (!zone_reclaimable(zone))
-			continue;
-
 		/* Avoid waking kswapd by allocating pages_to_migrate pages. */
 		if (!zone_watermark_ok(zone, 0,
 				       high_wmark_pages(zone) +
@@ -1828,7 +1831,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 	}
 
 	page_lru = page_is_file_cache(page);
-	mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru,
+	mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru,
 				hpage_nr_pages(page));
 
 	/*
@@ -1886,7 +1889,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 	if (nr_remaining) {
 		if (!list_empty(&migratepages)) {
 			list_del(&page->lru);
-			dec_zone_page_state(page, NR_ISOLATED_ANON +
+			dec_node_page_state(page, NR_ISOLATED_ANON +
 					page_is_file_cache(page));
 			putback_lru_page(page);
 		}
@@ -1931,7 +1934,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		goto out_dropref;
 
 	new_page = alloc_pages_node(node,
-		(GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_RECLAIM,
+		(GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
 		HPAGE_PMD_ORDER);
 	if (!new_page)
 		goto out_fail;
@@ -1979,7 +1982,7 @@ fail_putback:
 		/* Retake the callers reference and putback on LRU */
 		get_page(page);
 		putback_lru_page(page);
-		mod_zone_page_state(page_zone(page),
+		mod_node_page_state(page_pgdat(page),
 			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
 
 		goto out_unlock;
@@ -2030,7 +2033,7 @@ fail_putback:
 	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
 	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
 
-	mod_zone_page_state(page_zone(page),
+	mod_node_page_state(page_pgdat(page),
 			NR_ISOLATED_ANON + page_lru,
 			-HPAGE_PMD_NR);
 	return isolated;

mm/mlock.c

@@ -103,7 +103,7 @@ static bool __munlock_isolate_lru_page(struct page *page, bool getpage)
 	if (PageLRU(page)) {
 		struct lruvec *lruvec;
 
-		lruvec = mem_cgroup_page_lruvec(page, page_zone(page));
+		lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
 		if (getpage)
 			get_page(page);
 		ClearPageLRU(page);
@@ -188,7 +188,7 @@ unsigned int munlock_vma_page(struct page *page)
 	 * might otherwise copy PageMlocked to part of the tail pages before
 	 * we clear it in the head page. It also stabilizes hpage_nr_pages().
 	 */
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 
 	nr_pages = hpage_nr_pages(page);
 	if (!TestClearPageMlocked(page))
@@ -197,14 +197,14 @@ unsigned int munlock_vma_page(struct page *page)
 	__mod_zone_page_state(zone, NR_MLOCK, -nr_pages);
 
 	if (__munlock_isolate_lru_page(page, true)) {
-		spin_unlock_irq(&zone->lru_lock);
+		spin_unlock_irq(zone_lru_lock(zone));
 		__munlock_isolated_page(page);
 		goto out;
 	}
 	__munlock_isolation_failed(page);
 
 unlock_out:
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 
 out:
 	return nr_pages - 1;
@@ -289,7 +289,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 	pagevec_init(&pvec_putback, 0);
 
 	/* Phase 1: page isolation */
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	for (i = 0; i < nr; i++) {
 		struct page *page = pvec->pages[i];
 
@@ -315,7 +315,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 	}
 	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 
 	/* Now we can release pins of pages that we are not munlocking */
 	pagevec_release(&pvec_putback);

mm/mmap.c

@@ -621,7 +621,6 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *next = vma->vm_next;
-	struct vm_area_struct *importer = NULL;
 	struct address_space *mapping = NULL;
 	struct rb_root *root = NULL;
 	struct anon_vma *anon_vma = NULL;
@@ -631,17 +630,25 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	int remove_next = 0;
 
 	if (next && !insert) {
-		struct vm_area_struct *exporter = NULL;
+		struct vm_area_struct *exporter = NULL, *importer = NULL;
 
 		if (end >= next->vm_end) {
 			/*
 			 * vma expands, overlapping all the next, and
 			 * perhaps the one after too (mprotect case 6).
 			 */
-again:			remove_next = 1 + (end > next->vm_end);
+			remove_next = 1 + (end > next->vm_end);
 			end = next->vm_end;
 			exporter = next;
 			importer = vma;
+
+			/*
+			 * If next doesn't have anon_vma, import from vma after
+			 * next, if the vma overlaps with it.
+			 */
+			if (remove_next == 2 && next && !next->anon_vma)
+				exporter = next->vm_next;
+
 		} else if (end > next->vm_start) {
 			/*
 			 * vma expands, overlapping part of the next:
@@ -675,7 +682,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 				return error;
 		}
 	}
-
+again:
 	vma_adjust_trans_huge(vma, start, end, adjust_next);
 
 	if (file) {
@@ -796,8 +803,11 @@ again:			remove_next = 1 + (end > next->vm_end);
 		 * up the code too much to do both in one go.
 		 */
 		next = vma->vm_next;
-		if (remove_next == 2)
+		if (remove_next == 2) {
+			remove_next = 1;
+			end = next->vm_end;
 			goto again;
+		}
 		else if (next)
 			vma_gap_update(next);
 		else

mm/oom_kill.c

@@ -176,11 +176,13 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 
 	/*
 	 * Do not even consider tasks which are explicitly marked oom
-	 * unkillable or have been already oom reaped.
+	 * unkillable or have been already oom reaped or the are in
+	 * the middle of vfork
 	 */
 	adj = (long)p->signal->oom_score_adj;
 	if (adj == OOM_SCORE_ADJ_MIN ||
-			test_bit(MMF_OOM_REAPED, &p->mm->flags)) {
+			test_bit(MMF_OOM_REAPED, &p->mm->flags) ||
+			in_vfork(p)) {
 		task_unlock(p);
 		return 0;
 	}
@@ -281,10 +283,22 @@ enum oom_scan_t oom_scan_process_thread(struct oom_control *oc,
 
 	/*
 	 * This task already has access to memory reserves and is being killed.
-	 * Don't allow any other task to have access to the reserves.
+	 * Don't allow any other task to have access to the reserves unless
+	 * the task has MMF_OOM_REAPED because chances that it would release
+	 * any memory is quite low.
 	 */
-	if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims))
-		return OOM_SCAN_ABORT;
+	if (!is_sysrq_oom(oc) && atomic_read(&task->signal->oom_victims)) {
+		struct task_struct *p = find_lock_task_mm(task);
+		enum oom_scan_t ret = OOM_SCAN_ABORT;
+
+		if (p) {
+			if (test_bit(MMF_OOM_REAPED, &p->mm->flags))
+				ret = OOM_SCAN_CONTINUE;
+			task_unlock(p);
+		}
+
+		return ret;
+	}
 
 	/*
 	 * If task is allocating a lot of memory and has been marked to be
@@ -415,7 +429,7 @@ bool oom_killer_disabled __read_mostly;
  * task's threads: if one of those is using this mm then this task was also
  * using it.
  */
-static bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
+bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
 {
 	struct task_struct *t;
 
@@ -554,8 +568,27 @@ static void oom_reap_task(struct task_struct *tsk)
 		schedule_timeout_idle(HZ/10);
 
 	if (attempts > MAX_OOM_REAP_RETRIES) {
+		struct task_struct *p;
+
 		pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
 				task_pid_nr(tsk), tsk->comm);
+
+		/*
+		 * If we've already tried to reap this task in the past and
+		 * failed it probably doesn't make much sense to try yet again
+		 * so hide the mm from the oom killer so that it can move on
+		 * to another task with a different mm struct.
+		 */
+		p = find_lock_task_mm(tsk);
+		if (p) {
+			if (test_and_set_bit(MMF_OOM_NOT_REAPABLE, &p->mm->flags)) {
+				pr_info("oom_reaper: giving up pid:%d (%s)\n",
+						task_pid_nr(tsk), tsk->comm);
+				set_bit(MMF_OOM_REAPED, &p->mm->flags);
+			}
+			task_unlock(p);
+		}
+
 		debug_show_all_locks();
 	}
 
@@ -594,7 +627,7 @@ static int oom_reaper(void *unused)
 	return 0;
 }
 
-static void wake_oom_reaper(struct task_struct *tsk)
+void wake_oom_reaper(struct task_struct *tsk)
 {
 	if (!oom_reaper_th)
 		return;
@@ -612,46 +645,6 @@ static void wake_oom_reaper(struct task_struct *tsk)
 	wake_up(&oom_reaper_wait);
 }
 
-/* Check if we can reap the given task. This has to be called with stable
- * tsk->mm
- */
-void try_oom_reaper(struct task_struct *tsk)
-{
-	struct mm_struct *mm = tsk->mm;
-	struct task_struct *p;
-
-	if (!mm)
-		return;
-
-	/*
-	 * There might be other threads/processes which are either not
-	 * dying or even not killable.
-	 */
-	if (atomic_read(&mm->mm_users) > 1) {
-		rcu_read_lock();
-		for_each_process(p) {
-			if (!process_shares_mm(p, mm))
-				continue;
-			if (fatal_signal_pending(p))
-				continue;
-
-			/*
-			 * If the task is exiting make sure the whole thread group
-			 * is exiting and cannot acces mm anymore.
-			 */
-			if (signal_group_exit(p->signal))
-				continue;
-
-			/* Give up */
-			rcu_read_unlock();
-			return;
-		}
-		rcu_read_unlock();
-	}
-
-	wake_oom_reaper(tsk);
-}
-
 static int __init oom_init(void)
 {
 	oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
@@ -663,10 +656,6 @@ static int __init oom_init(void)
 	return 0;
 }
 subsys_initcall(oom_init)
-#else
-static void wake_oom_reaper(struct task_struct *tsk)
-{
-}
 #endif
 
 /**
@@ -743,6 +732,80 @@ void oom_killer_enable(void)
 	oom_killer_disabled = false;
 }
 
+static inline bool __task_will_free_mem(struct task_struct *task)
+{
+	struct signal_struct *sig = task->signal;
+
+	/*
+	 * A coredumping process may sleep for an extended period in exit_mm(),
+	 * so the oom killer cannot assume that the process will promptly exit
+	 * and release memory.
+	 */
+	if (sig->flags & SIGNAL_GROUP_COREDUMP)
+		return false;
+
+	if (sig->flags & SIGNAL_GROUP_EXIT)
+		return true;
+
+	if (thread_group_empty(task) && (task->flags & PF_EXITING))
+		return true;
+
+	return false;
+}
+
+/*
+ * Checks whether the given task is dying or exiting and likely to
+ * release its address space. This means that all threads and processes
+ * sharing the same mm have to be killed or exiting.
+ * Caller has to make sure that task->mm is stable (hold task_lock or
+ * it operates on the current).
+ */
+bool task_will_free_mem(struct task_struct *task)
+{
+	struct mm_struct *mm = task->mm;
+	struct task_struct *p;
+	bool ret;
+
+	/*
+	 * Skip tasks without mm because it might have passed its exit_mm and
+	 * exit_oom_victim. oom_reaper could have rescued that but do not rely
+	 * on that for now. We can consider find_lock_task_mm in future.
+	 */
+	if (!mm)
+		return false;
+
+	if (!__task_will_free_mem(task))
+		return false;
+
+	/*
+	 * This task has already been drained by the oom reaper so there are
+	 * only small chances it will free some more
+	 */
+	if (test_bit(MMF_OOM_REAPED, &mm->flags))
+		return false;
+
+	if (atomic_read(&mm->mm_users) <= 1)
+		return true;
+
+	/*
+	 * This is really pessimistic but we do not have any reliable way
+	 * to check that external processes share with our mm
+	 */
+	rcu_read_lock();
+	for_each_process(p) {
+		if (!process_shares_mm(p, mm))
+			continue;
+		if (same_thread_group(task, p))
+			continue;
+		ret = __task_will_free_mem(p);
+		if (!ret)
+			break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 /*
  * Must be called while holding a reference to p, which will be released upon
  * returning.
@@ -765,9 +828,9 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 	 * its children or threads, just set TIF_MEMDIE so it can die quickly
 	 */
 	task_lock(p);
-	if (p->mm && task_will_free_mem(p)) {
+	if (task_will_free_mem(p)) {
 		mark_oom_victim(p);
-		try_oom_reaper(p);
+		wake_oom_reaper(p);
 		task_unlock(p);
 		put_task_struct(p);
 		return;
@@ -850,14 +913,18 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 			continue;
 		if (same_thread_group(p, victim))
 			continue;
-		if (unlikely(p->flags & PF_KTHREAD) || is_global_init(p) ||
-		    p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+		if (unlikely(p->flags & PF_KTHREAD) || is_global_init(p)) {
 			/*
 			 * We cannot use oom_reaper for the mm shared by this
 			 * process because it wouldn't get killed and so the
-			 * memory might be still used.
+			 * memory might be still used. Hide the mm from the oom
+			 * killer to guarantee OOM forward progress.
 			 */
 			can_oom_reap = false;
+			set_bit(MMF_OOM_REAPED, &mm->flags);
+			pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n",
+					task_pid_nr(victim), victim->comm,
+					task_pid_nr(p), p->comm);
 			continue;
 		}
 		do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
@@ -939,14 +1006,10 @@ bool out_of_memory(struct oom_control *oc)
 	 * If current has a pending SIGKILL or is exiting, then automatically
 	 * select it.  The goal is to allow it to allocate so that it may
 	 * quickly exit and free its memory.
-	 *
-	 * But don't select if current has already released its mm and cleared
-	 * TIF_MEMDIE flag at exit_mm(), otherwise an OOM livelock may occur.
 	 */
-	if (current->mm &&
-	    (fatal_signal_pending(current) || task_will_free_mem(current))) {
+	if (task_will_free_mem(current)) {
 		mark_oom_victim(current);
-		try_oom_reaper(current);
+		wake_oom_reaper(current);
 		return true;
 	}
 

mm/page-writeback.c

@@ -267,26 +267,35 @@ static void wb_min_max_ratio(struct bdi_writeback *wb,
  */
 
 /**
- * zone_dirtyable_memory - number of dirtyable pages in a zone
- * @zone: the zone
+ * node_dirtyable_memory - number of dirtyable pages in a node
+ * @pgdat: the node
  *
- * Returns the zone's number of pages potentially available for dirty
- * page cache.  This is the base value for the per-zone dirty limits.
+ * Returns the node's number of pages potentially available for dirty
+ * page cache.  This is the base value for the per-node dirty limits.
  */
-static unsigned long zone_dirtyable_memory(struct zone *zone)
+static unsigned long node_dirtyable_memory(struct pglist_data *pgdat)
 {
-	unsigned long nr_pages;
+	unsigned long nr_pages = 0;
+	int z;
+
+	for (z = 0; z < MAX_NR_ZONES; z++) {
+		struct zone *zone = pgdat->node_zones + z;
+
+		if (!populated_zone(zone))
+			continue;
+
+		nr_pages += zone_page_state(zone, NR_FREE_PAGES);
+	}
 
-	nr_pages = zone_page_state(zone, NR_FREE_PAGES);
 	/*
 	 * Pages reserved for the kernel should not be considered
 	 * dirtyable, to prevent a situation where reclaim has to
 	 * clean pages in order to balance the zones.
 	 */
-	nr_pages -= min(nr_pages, zone->totalreserve_pages);
+	nr_pages -= min(nr_pages, pgdat->totalreserve_pages);
 
-	nr_pages += zone_page_state(zone, NR_INACTIVE_FILE);
-	nr_pages += zone_page_state(zone, NR_ACTIVE_FILE);
+	nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE);
+	nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE);
 
 	return nr_pages;
 }
@@ -299,13 +308,26 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
 	int i;
 
 	for_each_node_state(node, N_HIGH_MEMORY) {
-		for (i = 0; i < MAX_NR_ZONES; i++) {
-			struct zone *z = &NODE_DATA(node)->node_zones[i];
+		for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) {
+			struct zone *z;
+			unsigned long nr_pages;
+
+			if (!is_highmem_idx(i))
+				continue;
+
+			z = &NODE_DATA(node)->node_zones[i];
+			if (!populated_zone(z))
+				continue;
 
-			if (is_highmem(z))
-				x += zone_dirtyable_memory(z);
+			nr_pages = zone_page_state(z, NR_FREE_PAGES);
+			/* watch for underflows */
+			nr_pages -= min(nr_pages, high_wmark_pages(z));
+			nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE);
+			nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE);
+			x += nr_pages;
 		}
 	}
+
 	/*
 	 * Unreclaimable memory (kernel memory or anonymous memory
 	 * without swap) can bring down the dirtyable pages below
@@ -348,8 +370,8 @@ static unsigned long global_dirtyable_memory(void)
 	 */
 	x -= min(x, totalreserve_pages);
 
-	x += global_page_state(NR_INACTIVE_FILE);
-	x += global_page_state(NR_ACTIVE_FILE);
+	x += global_node_page_state(NR_INACTIVE_FILE);
+	x += global_node_page_state(NR_ACTIVE_FILE);
 
 	if (!vm_highmem_is_dirtyable)
 		x -= highmem_dirtyable_memory(x);
@@ -445,23 +467,23 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
 }
 
 /**
- * zone_dirty_limit - maximum number of dirty pages allowed in a zone
- * @zone: the zone
+ * node_dirty_limit - maximum number of dirty pages allowed in a node
+ * @pgdat: the node
  *
- * Returns the maximum number of dirty pages allowed in a zone, based
- * on the zone's dirtyable memory.
+ * Returns the maximum number of dirty pages allowed in a node, based
+ * on the node's dirtyable memory.
  */
-static unsigned long zone_dirty_limit(struct zone *zone)
+static unsigned long node_dirty_limit(struct pglist_data *pgdat)
 {
-	unsigned long zone_memory = zone_dirtyable_memory(zone);
+	unsigned long node_memory = node_dirtyable_memory(pgdat);
 	struct task_struct *tsk = current;
 	unsigned long dirty;
 
 	if (vm_dirty_bytes)
 		dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) *
-			zone_memory / global_dirtyable_memory();
+			node_memory / global_dirtyable_memory();
 	else
-		dirty = vm_dirty_ratio * zone_memory / 100;
+		dirty = vm_dirty_ratio * node_memory / 100;
 
 	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk))
 		dirty += dirty / 4;
@@ -470,19 +492,22 @@ static unsigned long zone_dirty_limit(struct zone *zone)
 }
 
 /**
- * zone_dirty_ok - tells whether a zone is within its dirty limits
- * @zone: the zone to check
+ * node_dirty_ok - tells whether a node is within its dirty limits
+ * @pgdat: the node to check
  *
- * Returns %true when the dirty pages in @zone are within the zone's
+ * Returns %true when the dirty pages in @pgdat are within the node's
  * dirty limit, %false if the limit is exceeded.
  */
-bool zone_dirty_ok(struct zone *zone)
+bool node_dirty_ok(struct pglist_data *pgdat)
 {
-	unsigned long limit = zone_dirty_limit(zone);
+	unsigned long limit = node_dirty_limit(pgdat);
+	unsigned long nr_pages = 0;
+
+	nr_pages += node_page_state(pgdat, NR_FILE_DIRTY);
+	nr_pages += node_page_state(pgdat, NR_UNSTABLE_NFS);
+	nr_pages += node_page_state(pgdat, NR_WRITEBACK);
 
-	return zone_page_state(zone, NR_FILE_DIRTY) +
-	       zone_page_state(zone, NR_UNSTABLE_NFS) +
-	       zone_page_state(zone, NR_WRITEBACK) <= limit;
+	return nr_pages <= limit;
 }
 
 int dirty_background_ratio_handler(struct ctl_table *table, int write,
@@ -1570,10 +1595,10 @@ static void balance_dirty_pages(struct address_space *mapping,
 		 * written to the server's write cache, but has not yet
 		 * been flushed to permanent storage.
 		 */
-		nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
-					global_page_state(NR_UNSTABLE_NFS);
+		nr_reclaimable = global_node_page_state(NR_FILE_DIRTY) +
+					global_node_page_state(NR_UNSTABLE_NFS);
 		gdtc->avail = global_dirtyable_memory();
-		gdtc->dirty = nr_reclaimable + global_page_state(NR_WRITEBACK);
+		gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK);
 
 		domain_dirty_limits(gdtc);
 
@@ -1910,8 +1935,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 	 * as we're trying to decide whether to put more under writeback.
 	 */
 	gdtc->avail = global_dirtyable_memory();
-	gdtc->dirty = global_page_state(NR_FILE_DIRTY) +
-		      global_page_state(NR_UNSTABLE_NFS);
+	gdtc->dirty = global_node_page_state(NR_FILE_DIRTY) +
+		      global_node_page_state(NR_UNSTABLE_NFS);
 	domain_dirty_limits(gdtc);
 
 	if (gdtc->dirty > gdtc->bg_thresh)
@@ -1955,8 +1980,8 @@ void throttle_vm_writeout(gfp_t gfp_mask)
                  */
                 dirty_thresh += dirty_thresh / 10;      /* wheeee... */
 
-                if (global_page_state(NR_UNSTABLE_NFS) +
-			global_page_state(NR_WRITEBACK) <= dirty_thresh)
+                if (global_node_page_state(NR_UNSTABLE_NFS) +
+			global_node_page_state(NR_WRITEBACK) <= dirty_thresh)
                         	break;
                 congestion_wait(BLK_RW_ASYNC, HZ/10);
 
@@ -1984,8 +2009,8 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write,
 void laptop_mode_timer_fn(unsigned long data)
 {
 	struct request_queue *q = (struct request_queue *)data;
-	int nr_pages = global_page_state(NR_FILE_DIRTY) +
-		global_page_state(NR_UNSTABLE_NFS);
+	int nr_pages = global_node_page_state(NR_FILE_DIRTY) +
+		global_node_page_state(NR_UNSTABLE_NFS);
 	struct bdi_writeback *wb;
 
 	/*
@@ -2436,8 +2461,9 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		wb = inode_to_wb(inode);
 
 		mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY);
-		__inc_zone_page_state(page, NR_FILE_DIRTY);
-		__inc_zone_page_state(page, NR_DIRTIED);
+		__inc_node_page_state(page, NR_FILE_DIRTY);
+		__inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
+		__inc_node_page_state(page, NR_DIRTIED);
 		__inc_wb_stat(wb, WB_RECLAIMABLE);
 		__inc_wb_stat(wb, WB_DIRTIED);
 		task_io_account_write(PAGE_SIZE);
@@ -2457,7 +2483,8 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
 {
 	if (mapping_cap_account_dirty(mapping)) {
 		mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
-		dec_zone_page_state(page, NR_FILE_DIRTY);
+		dec_node_page_state(page, NR_FILE_DIRTY);
+		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		dec_wb_stat(wb, WB_RECLAIMABLE);
 		task_io_account_cancelled_write(PAGE_SIZE);
 	}
@@ -2525,7 +2552,7 @@ void account_page_redirty(struct page *page)
 
 		wb = unlocked_inode_to_wb_begin(inode, &locked);
 		current->nr_dirtied--;
-		dec_zone_page_state(page, NR_DIRTIED);
+		dec_node_page_state(page, NR_DIRTIED);
 		dec_wb_stat(wb, WB_DIRTIED);
 		unlocked_inode_to_wb_end(inode, locked);
 	}
@@ -2713,7 +2740,8 @@ int clear_page_dirty_for_io(struct page *page)
 		wb = unlocked_inode_to_wb_begin(inode, &locked);
 		if (TestClearPageDirty(page)) {
 			mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
-			dec_zone_page_state(page, NR_FILE_DIRTY);
+			dec_node_page_state(page, NR_FILE_DIRTY);
+			dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 			dec_wb_stat(wb, WB_RECLAIMABLE);
 			ret = 1;
 		}
@@ -2759,8 +2787,9 @@ int test_clear_page_writeback(struct page *page)
 	}
 	if (ret) {
 		mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
-		dec_zone_page_state(page, NR_WRITEBACK);
-		inc_zone_page_state(page, NR_WRITTEN);
+		dec_node_page_state(page, NR_WRITEBACK);
+		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
+		inc_node_page_state(page, NR_WRITTEN);
 	}
 	unlock_page_memcg(page);
 	return ret;
@@ -2813,7 +2842,8 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 	}
 	if (!ret) {
 		mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
-		inc_zone_page_state(page, NR_WRITEBACK);
+		inc_node_page_state(page, NR_WRITEBACK);
+		inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 	}
 	unlock_page_memcg(page);
 	return ret;

mm/page_alloc.c

@@ -295,14 +295,6 @@ static inline bool __meminit early_page_uninitialised(unsigned long pfn)
 	return false;
 }
 
-static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid)
-{
-	if (pfn >= NODE_DATA(nid)->first_deferred_pfn)
-		return true;
-
-	return false;
-}
-
 /*
  * Returns false when the remaining initialisation should be deferred until
  * later in the boot cycle when it can be parallelised.
@@ -342,11 +334,6 @@ static inline bool early_page_uninitialised(unsigned long pfn)
 	return false;
 }
 
-static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid)
-{
-	return false;
-}
-
 static inline bool update_defer_init(pg_data_t *pgdat,
 				unsigned long pfn, unsigned long zone_end,
 				unsigned long *nr_initialised)
@@ -1091,9 +1078,9 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 
 	spin_lock(&zone->lock);
 	isolated_pageblocks = has_isolate_pageblock(zone);
-	nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
+	nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
 	if (nr_scanned)
-		__mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
+		__mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned);
 
 	while (count) {
 		struct page *page;
@@ -1148,9 +1135,9 @@ static void free_one_page(struct zone *zone,
 {
 	unsigned long nr_scanned;
 	spin_lock(&zone->lock);
-	nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
+	nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
 	if (nr_scanned)
-		__mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
+		__mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned);
 
 	if (unlikely(has_isolate_pageblock(zone) ||
 		is_migrate_isolate(migratetype))) {
@@ -2517,7 +2504,10 @@ int __isolate_free_page(struct page *page, unsigned int order)
 	zone->free_area[order].nr_free--;
 	rmv_page_order(page);
 
-	/* Set the pageblock if the isolated page is at least a pageblock */
+	/*
+	 * Set the pageblock if the isolated page is at least half of a
+	 * pageblock
+	 */
 	if (order >= pageblock_order - 1) {
 		struct page *endpage = page + (1 << order) - 1;
 		for (; page < endpage; page += pageblock_nr_pages) {
@@ -2597,7 +2587,6 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 			else
 				page = list_first_entry(list, struct page, lru);
 
-			__dec_zone_state(zone, NR_ALLOC_BATCH);
 			list_del(&page->lru);
 			pcp->count--;
 
@@ -2623,16 +2612,11 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 		spin_unlock(&zone->lock);
 		if (!page)
 			goto failed;
-		__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
 		__mod_zone_freepage_state(zone, -(1 << order),
 					  get_pcppage_migratetype(page));
 	}
 
-	if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 &&
-	    !test_bit(ZONE_FAIR_DEPLETED, &zone->flags))
-		set_bit(ZONE_FAIR_DEPLETED, &zone->flags);
-
-	__count_zone_vm_events(PGALLOC, zone, 1 << order);
+	__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
 	local_irq_restore(flags);
 
@@ -2842,40 +2826,18 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
 }
 
 #ifdef CONFIG_NUMA
-static bool zone_local(struct zone *local_zone, struct zone *zone)
-{
-	return local_zone->node == zone->node;
-}
-
 static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 {
 	return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
 				RECLAIM_DISTANCE;
 }
 #else	/* CONFIG_NUMA */
-static bool zone_local(struct zone *local_zone, struct zone *zone)
-{
-	return true;
-}
-
 static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 {
 	return true;
 }
 #endif	/* CONFIG_NUMA */
 
-static void reset_alloc_batches(struct zone *preferred_zone)
-{
-	struct zone *zone = preferred_zone->zone_pgdat->node_zones;
-
-	do {
-		mod_zone_page_state(zone, NR_ALLOC_BATCH,
-			high_wmark_pages(zone) - low_wmark_pages(zone) -
-			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
-		clear_bit(ZONE_FAIR_DEPLETED, &zone->flags);
-	} while (zone++ != preferred_zone);
-}
-
 /*
  * get_page_from_freelist goes through the zonelist trying to allocate
  * a page.
@@ -2886,10 +2848,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 {
 	struct zoneref *z = ac->preferred_zoneref;
 	struct zone *zone;
-	bool fair_skipped = false;
-	bool apply_fair = (alloc_flags & ALLOC_FAIR);
+	struct pglist_data *last_pgdat_dirty_limit = NULL;
 
-zonelist_scan:
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
@@ -2903,51 +2863,34 @@ zonelist_scan:
 			(alloc_flags & ALLOC_CPUSET) &&
 			!__cpuset_zone_allowed(zone, gfp_mask))
 				continue;
-		/*
-		 * Distribute pages in proportion to the individual
-		 * zone size to ensure fair page aging.  The zone a
-		 * page was allocated in should have no effect on the
-		 * time the page has in memory before being reclaimed.
-		 */
-		if (apply_fair) {
-			if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) {
-				fair_skipped = true;
-				continue;
-			}
-			if (!zone_local(ac->preferred_zoneref->zone, zone)) {
-				if (fair_skipped)
-					goto reset_fair;
-				apply_fair = false;
-			}
-		}
 		/*
 		 * When allocating a page cache page for writing, we
-		 * want to get it from a zone that is within its dirty
-		 * limit, such that no single zone holds more than its
+		 * want to get it from a node that is within its dirty
+		 * limit, such that no single node holds more than its
 		 * proportional share of globally allowed dirty pages.
-		 * The dirty limits take into account the zone's
+		 * The dirty limits take into account the node's
 		 * lowmem reserves and high watermark so that kswapd
 		 * should be able to balance it without having to
 		 * write pages from its LRU list.
 		 *
-		 * This may look like it could increase pressure on
-		 * lower zones by failing allocations in higher zones
-		 * before they are full.  But the pages that do spill
-		 * over are limited as the lower zones are protected
-		 * by this very same mechanism.  It should not become
-		 * a practical burden to them.
-		 *
 		 * XXX: For now, allow allocations to potentially
-		 * exceed the per-zone dirty limit in the slowpath
+		 * exceed the per-node dirty limit in the slowpath
 		 * (spread_dirty_pages unset) before going into reclaim,
 		 * which is important when on a NUMA setup the allowed
-		 * zones are together not big enough to reach the
+		 * nodes are together not big enough to reach the
 		 * global limit.  The proper fix for these situations
-		 * will require awareness of zones in the
+		 * will require awareness of nodes in the
 		 * dirty-throttling and the flusher threads.
 		 */
-		if (ac->spread_dirty_pages && !zone_dirty_ok(zone))
-			continue;
+		if (ac->spread_dirty_pages) {
+			if (last_pgdat_dirty_limit == zone->zone_pgdat)
+				continue;
+
+			if (!node_dirty_ok(zone->zone_pgdat)) {
+				last_pgdat_dirty_limit = zone->zone_pgdat;
+				continue;
+			}
+		}
 
 		mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
 		if (!zone_watermark_fast(zone, order, mark,
@@ -2959,16 +2902,16 @@ zonelist_scan:
 			if (alloc_flags & ALLOC_NO_WATERMARKS)
 				goto try_this_zone;
 
-			if (zone_reclaim_mode == 0 ||
+			if (node_reclaim_mode == 0 ||
 			    !zone_allows_reclaim(ac->preferred_zoneref->zone, zone))
 				continue;
 
-			ret = zone_reclaim(zone, gfp_mask, order);
+			ret = node_reclaim(zone->zone_pgdat, gfp_mask, order);
 			switch (ret) {
-			case ZONE_RECLAIM_NOSCAN:
+			case NODE_RECLAIM_NOSCAN:
 				/* did not scan */
 				continue;
-			case ZONE_RECLAIM_FULL:
+			case NODE_RECLAIM_FULL:
 				/* scanned but unreclaimable */
 				continue;
 			default:
@@ -2998,23 +2941,6 @@ try_this_zone:
 		}
 	}
 
-	/*
-	 * The first pass makes sure allocations are spread fairly within the
-	 * local node.  However, the local node might have free pages left
-	 * after the fairness batches are exhausted, and remote zones haven't
-	 * even been considered yet.  Try once more without fairness, and
-	 * include remote zones now, before entering the slowpath and waking
-	 * kswapd: prefer spilling to a remote zone over swapping locally.
-	 */
-	if (fair_skipped) {
-reset_fair:
-		apply_fair = false;
-		fair_skipped = false;
-		reset_alloc_batches(ac->preferred_zoneref->zone);
-		z = ac->preferred_zoneref;
-		goto zonelist_scan;
-	}
-
 	return NULL;
 }
 
@@ -3159,7 +3085,6 @@ out:
 	return page;
 }
 
-
 /*
  * Maximum number of compaction retries wit a progress before OOM
  * killer is consider as the only way to move forward.
@@ -3171,17 +3096,16 @@ out:
 static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		unsigned int alloc_flags, const struct alloc_context *ac,
-		enum migrate_mode mode, enum compact_result *compact_result)
+		enum compact_priority prio, enum compact_result *compact_result)
 {
 	struct page *page;
-	int contended_compaction;
 
 	if (!order)
 		return NULL;
 
 	current->flags |= PF_MEMALLOC;
 	*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
-						mode, &contended_compaction);
+									prio);
 	current->flags &= ~PF_MEMALLOC;
 
 	if (*compact_result <= COMPACT_INACTIVE)
@@ -3193,8 +3117,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	 */
 	count_vm_event(COMPACTSTALL);
 
-	page = get_page_from_freelist(gfp_mask, order,
-					alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
+	page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
 
 	if (page) {
 		struct zone *zone = page_zone(page);
@@ -3211,24 +3134,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	 */
 	count_vm_event(COMPACTFAIL);
 
-	/*
-	 * In all zones where compaction was attempted (and not
-	 * deferred or skipped), lock contention has been detected.
-	 * For THP allocation we do not want to disrupt the others
-	 * so we fallback to base pages instead.
-	 */
-	if (contended_compaction == COMPACT_CONTENDED_LOCK)
-		*compact_result = COMPACT_CONTENDED;
-
-	/*
-	 * If compaction was aborted due to need_resched(), we do not
-	 * want to further increase allocation latency, unless it is
-	 * khugepaged trying to collapse.
-	 */
-	if (contended_compaction == COMPACT_CONTENDED_SCHED
-		&& !(current->flags & PF_KTHREAD))
-		*compact_result = COMPACT_CONTENDED;
-
 	cond_resched();
 
 	return NULL;
@@ -3236,7 +3141,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 
 static inline bool
 should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
-		     enum compact_result compact_result, enum migrate_mode *migrate_mode,
+		     enum compact_result compact_result,
+		     enum compact_priority *compact_priority,
 		     int compaction_retries)
 {
 	int max_retries = MAX_COMPACT_RETRIES;
@@ -3247,11 +3153,11 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
 	/*
 	 * compaction considers all the zone as desperately out of memory
 	 * so it doesn't really make much sense to retry except when the
-	 * failure could be caused by weak migration mode.
+	 * failure could be caused by insufficient priority
 	 */
 	if (compaction_failed(compact_result)) {
-		if (*migrate_mode == MIGRATE_ASYNC) {
-			*migrate_mode = MIGRATE_SYNC_LIGHT;
+		if (*compact_priority > MIN_COMPACT_PRIORITY) {
+			(*compact_priority)--;
 			return true;
 		}
 		return false;
@@ -3285,7 +3191,7 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
 static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		unsigned int alloc_flags, const struct alloc_context *ac,
-		enum migrate_mode mode, enum compact_result *compact_result)
+		enum compact_priority prio, enum compact_result *compact_result)
 {
 	*compact_result = COMPACT_SKIPPED;
 	return NULL;
@@ -3294,7 +3200,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 static inline bool
 should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags,
 		     enum compact_result compact_result,
-		     enum migrate_mode *migrate_mode,
+		     enum compact_priority *compact_priority,
 		     int compaction_retries)
 {
 	struct zone *zone;
@@ -3362,8 +3268,7 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 retry:
-	page = get_page_from_freelist(gfp_mask, order,
-					alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
+	page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
 
 	/*
 	 * If an allocation failed after direct reclaim, it could be because
@@ -3384,10 +3289,14 @@ static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac)
 {
 	struct zoneref *z;
 	struct zone *zone;
+	pg_data_t *last_pgdat = NULL;
 
 	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
-						ac->high_zoneidx, ac->nodemask)
-		wakeup_kswapd(zone, order, ac_classzone_idx(ac));
+					ac->high_zoneidx, ac->nodemask) {
+		if (last_pgdat != zone->zone_pgdat)
+			wakeup_kswapd(zone, order, ac->high_zoneidx);
+		last_pgdat = zone->zone_pgdat;
+	}
 }
 
 static inline unsigned int
@@ -3421,16 +3330,6 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
-	if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
-		if (gfp_mask & __GFP_MEMALLOC)
-			alloc_flags |= ALLOC_NO_WATERMARKS;
-		else if (in_serving_softirq() && (current->flags & PF_MEMALLOC))
-			alloc_flags |= ALLOC_NO_WATERMARKS;
-		else if (!in_interrupt() &&
-				((current->flags & PF_MEMALLOC) ||
-				 unlikely(test_thread_flag(TIF_MEMDIE))))
-			alloc_flags |= ALLOC_NO_WATERMARKS;
-	}
 #ifdef CONFIG_CMA
 	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
@@ -3440,12 +3339,19 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 
 bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
 {
-	return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS);
-}
+	if (unlikely(gfp_mask & __GFP_NOMEMALLOC))
+		return false;
 
-static inline bool is_thp_gfp_mask(gfp_t gfp_mask)
-{
-	return (gfp_mask & (GFP_TRANSHUGE | __GFP_KSWAPD_RECLAIM)) == GFP_TRANSHUGE;
+	if (gfp_mask & __GFP_MEMALLOC)
+		return true;
+	if (in_serving_softirq() && (current->flags & PF_MEMALLOC))
+		return true;
+	if (!in_interrupt() &&
+			((current->flags & PF_MEMALLOC) ||
+			 unlikely(test_thread_flag(TIF_MEMDIE))))
+		return true;
+
+	return false;
 }
 
 /*
@@ -3481,10 +3387,10 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
 		return false;
 
 	/*
-	 * Keep reclaiming pages while there is a chance this will lead somewhere.
-	 * If none of the target zones can satisfy our allocation request even
-	 * if all reclaimable pages are considered then we are screwed and have
-	 * to go OOM.
+	 * Keep reclaiming pages while there is a chance this will lead
+	 * somewhere.  If none of the target zones can satisfy our allocation
+	 * request even if all reclaimable pages are considered then we are
+	 * screwed and have to go OOM.
 	 */
 	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
 					ac->nodemask) {
@@ -3509,14 +3415,12 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
 			 * prevent from pre mature OOM
 			 */
 			if (!did_some_progress) {
-				unsigned long writeback;
-				unsigned long dirty;
+				unsigned long write_pending;
 
-				writeback = zone_page_state_snapshot(zone,
-								     NR_WRITEBACK);
-				dirty = zone_page_state_snapshot(zone, NR_FILE_DIRTY);
+				write_pending = zone_page_state_snapshot(zone,
+							NR_ZONE_WRITE_PENDING);
 
-				if (2*(writeback + dirty) > reclaimable) {
+				if (2 * write_pending > reclaimable) {
 					congestion_wait(BLK_RW_ASYNC, HZ/10);
 					return true;
 				}
@@ -3551,7 +3455,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	struct page *page = NULL;
 	unsigned int alloc_flags;
 	unsigned long did_some_progress;
-	enum migrate_mode migration_mode = MIGRATE_ASYNC;
+	enum compact_priority compact_priority = DEF_COMPACT_PRIORITY;
 	enum compact_result compact_result;
 	int compaction_retries = 0;
 	int no_progress_loops = 0;
@@ -3575,42 +3479,88 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 				(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
 		gfp_mask &= ~__GFP_ATOMIC;
 
-retry:
+	/*
+	 * The fast path uses conservative alloc_flags to succeed only until
+	 * kswapd needs to be woken up, and to avoid the cost of setting up
+	 * alloc_flags precisely. So we do that now.
+	 */
+	alloc_flags = gfp_to_alloc_flags(gfp_mask);
+
 	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
 		wake_all_kswapds(order, ac);
 
 	/*
-	 * OK, we're below the kswapd watermark and have kicked background
-	 * reclaim. Now things get more complex, so set up alloc_flags according
-	 * to how we want to proceed.
+	 * The adjusted alloc_flags might result in immediate success, so try
+	 * that first
 	 */
-	alloc_flags = gfp_to_alloc_flags(gfp_mask);
+	page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
+	if (page)
+		goto got_pg;
+
+	/*
+	 * For costly allocations, try direct compaction first, as it's likely
+	 * that we have enough base pages and don't need to reclaim. Don't try
+	 * that for allocations that are allowed to ignore watermarks, as the
+	 * ALLOC_NO_WATERMARKS attempt didn't yet happen.
+	 */
+	if (can_direct_reclaim && order > PAGE_ALLOC_COSTLY_ORDER &&
+		!gfp_pfmemalloc_allowed(gfp_mask)) {
+		page = __alloc_pages_direct_compact(gfp_mask, order,
+						alloc_flags, ac,
+						INIT_COMPACT_PRIORITY,
+						&compact_result);
+		if (page)
+			goto got_pg;
+
+		/*
+		 * Checks for costly allocations with __GFP_NORETRY, which
+		 * includes THP page fault allocations
+		 */
+		if (gfp_mask & __GFP_NORETRY) {
+			/*
+			 * If compaction is deferred for high-order allocations,
+			 * it is because sync compaction recently failed. If
+			 * this is the case and the caller requested a THP
+			 * allocation, we do not want to heavily disrupt the
+			 * system, so we fail the allocation instead of entering
+			 * direct reclaim.
+			 */
+			if (compact_result == COMPACT_DEFERRED)
+				goto nopage;
+
+			/*
+			 * Looks like reclaim/compaction is worth trying, but
+			 * sync compaction could be very expensive, so keep
+			 * using async compaction.
+			 */
+			compact_priority = INIT_COMPACT_PRIORITY;
+		}
+	}
+
+retry:
+	/* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
+	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+		wake_all_kswapds(order, ac);
+
+	if (gfp_pfmemalloc_allowed(gfp_mask))
+		alloc_flags = ALLOC_NO_WATERMARKS;
 
 	/*
 	 * Reset the zonelist iterators if memory policies can be ignored.
 	 * These allocations are high priority and system rather than user
 	 * orientated.
 	 */
-	if ((alloc_flags & ALLOC_NO_WATERMARKS) || !(alloc_flags & ALLOC_CPUSET)) {
+	if (!(alloc_flags & ALLOC_CPUSET) || (alloc_flags & ALLOC_NO_WATERMARKS)) {
 		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
 		ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
 					ac->high_zoneidx, ac->nodemask);
 	}
 
-	/* This is the last chance, in general, before the goto nopage. */
-	page = get_page_from_freelist(gfp_mask, order,
-				alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
+	/* Attempt with potentially adjusted zonelist and alloc_flags */
+	page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
 	if (page)
 		goto got_pg;
 
-	/* Allocate without watermarks if the context allows */
-	if (alloc_flags & ALLOC_NO_WATERMARKS) {
-		page = get_page_from_freelist(gfp_mask, order,
-						ALLOC_NO_WATERMARKS, ac);
-		if (page)
-			goto got_pg;
-	}
-
 	/* Caller is not willing to reclaim, we can't balance anything */
 	if (!can_direct_reclaim) {
 		/*
@@ -3640,38 +3590,6 @@ retry:
 	if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
 		goto nopage;
 
-	/*
-	 * Try direct compaction. The first pass is asynchronous. Subsequent
-	 * attempts after direct reclaim are synchronous
-	 */
-	page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac,
-					migration_mode,
-					&compact_result);
-	if (page)
-		goto got_pg;
-
-	/* Checks for THP-specific high-order allocations */
-	if (is_thp_gfp_mask(gfp_mask)) {
-		/*
-		 * If compaction is deferred for high-order allocations, it is
-		 * because sync compaction recently failed. If this is the case
-		 * and the caller requested a THP allocation, we do not want
-		 * to heavily disrupt the system, so we fail the allocation
-		 * instead of entering direct reclaim.
-		 */
-		if (compact_result == COMPACT_DEFERRED)
-			goto nopage;
-
-		/*
-		 * Compaction is contended so rather back off than cause
-		 * excessive stalls.
-		 */
-		if(compact_result == COMPACT_CONTENDED)
-			goto nopage;
-	}
-
-	if (order && compaction_made_progress(compact_result))
-		compaction_retries++;
 
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac,
@@ -3679,16 +3597,25 @@ retry:
 	if (page)
 		goto got_pg;
 
+	/* Try direct compaction and then allocating */
+	page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac,
+					compact_priority, &compact_result);
+	if (page)
+		goto got_pg;
+
+	if (order && compaction_made_progress(compact_result))
+		compaction_retries++;
+
 	/* Do not loop if specifically requested */
 	if (gfp_mask & __GFP_NORETRY)
-		goto noretry;
+		goto nopage;
 
 	/*
 	 * Do not retry costly high order allocations unless they are
 	 * __GFP_REPEAT
 	 */
 	if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT))
-		goto noretry;
+		goto nopage;
 
 	/*
 	 * Costly allocations might have made a progress but this doesn't mean
@@ -3712,7 +3639,7 @@ retry:
 	 */
 	if (did_some_progress > 0 &&
 			should_compact_retry(ac, order, alloc_flags,
-				compact_result, &migration_mode,
+				compact_result, &compact_priority,
 				compaction_retries))
 		goto retry;
 
@@ -3727,25 +3654,6 @@ retry:
 		goto retry;
 	}
 
-noretry:
-	/*
-	 * High-order allocations do not necessarily loop after direct reclaim
-	 * and reclaim/compaction depends on compaction being called after
-	 * reclaim so call directly if necessary.
-	 * It can become very expensive to allocate transparent hugepages at
-	 * fault, so use asynchronous memory compaction for THP unless it is
-	 * khugepaged trying to collapse. All other requests should tolerate
-	 * at least light sync migration.
-	 */
-	if (is_thp_gfp_mask(gfp_mask) && !(current->flags & PF_KTHREAD))
-		migration_mode = MIGRATE_ASYNC;
-	else
-		migration_mode = MIGRATE_SYNC_LIGHT;
-	page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags,
-					    ac, migration_mode,
-					    &compact_result);
-	if (page)
-		goto got_pg;
 nopage:
 	warn_alloc_failed(gfp_mask, order, NULL);
 got_pg:
@@ -3761,7 +3669,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 {
 	struct page *page;
 	unsigned int cpuset_mems_cookie;
-	unsigned int alloc_flags = ALLOC_WMARK_LOW|ALLOC_FAIR;
+	unsigned int alloc_flags = ALLOC_WMARK_LOW;
 	gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
 	struct alloc_context ac = {
 		.high_zoneidx = gfp_zone(gfp_mask),
@@ -4192,7 +4100,7 @@ EXPORT_SYMBOL_GPL(si_mem_available);
 void si_meminfo(struct sysinfo *val)
 {
 	val->totalram = totalram_pages;
-	val->sharedram = global_page_state(NR_SHMEM);
+	val->sharedram = global_node_page_state(NR_SHMEM);
 	val->freeram = global_page_state(NR_FREE_PAGES);
 	val->bufferram = nr_blockdev_pages();
 	val->totalhigh = totalhigh_pages;
@@ -4214,8 +4122,8 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
 		managed_pages += pgdat->node_zones[zone_type].managed_pages;
 	val->totalram = managed_pages;
-	val->sharedram = node_page_state(nid, NR_SHMEM);
-	val->freeram = node_page_state(nid, NR_FREE_PAGES);
+	val->sharedram = node_page_state(pgdat, NR_SHMEM);
+	val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES);
 #ifdef CONFIG_HIGHMEM
 	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
 		struct zone *zone = &pgdat->node_zones[zone_type];
@@ -4298,6 +4206,7 @@ void show_free_areas(unsigned int filter)
 	unsigned long free_pcp = 0;
 	int cpu;
 	struct zone *zone;
+	pg_data_t *pgdat;
 
 	for_each_populated_zone(zone) {
 		if (skip_free_areas_node(filter, zone_to_nid(zone)))
@@ -4312,35 +4221,74 @@ void show_free_areas(unsigned int filter)
 		" unevictable:%lu dirty:%lu writeback:%lu unstable:%lu\n"
 		" slab_reclaimable:%lu slab_unreclaimable:%lu\n"
 		" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		" anon_thp: %lu shmem_thp: %lu shmem_pmdmapped: %lu\n"
-#endif
 		" free:%lu free_pcp:%lu free_cma:%lu\n",
-		global_page_state(NR_ACTIVE_ANON),
-		global_page_state(NR_INACTIVE_ANON),
-		global_page_state(NR_ISOLATED_ANON),
-		global_page_state(NR_ACTIVE_FILE),
-		global_page_state(NR_INACTIVE_FILE),
-		global_page_state(NR_ISOLATED_FILE),
-		global_page_state(NR_UNEVICTABLE),
-		global_page_state(NR_FILE_DIRTY),
-		global_page_state(NR_WRITEBACK),
-		global_page_state(NR_UNSTABLE_NFS),
+		global_node_page_state(NR_ACTIVE_ANON),
+		global_node_page_state(NR_INACTIVE_ANON),
+		global_node_page_state(NR_ISOLATED_ANON),
+		global_node_page_state(NR_ACTIVE_FILE),
+		global_node_page_state(NR_INACTIVE_FILE),
+		global_node_page_state(NR_ISOLATED_FILE),
+		global_node_page_state(NR_UNEVICTABLE),
+		global_node_page_state(NR_FILE_DIRTY),
+		global_node_page_state(NR_WRITEBACK),
+		global_node_page_state(NR_UNSTABLE_NFS),
 		global_page_state(NR_SLAB_RECLAIMABLE),
 		global_page_state(NR_SLAB_UNRECLAIMABLE),
-		global_page_state(NR_FILE_MAPPED),
-		global_page_state(NR_SHMEM),
+		global_node_page_state(NR_FILE_MAPPED),
+		global_node_page_state(NR_SHMEM),
 		global_page_state(NR_PAGETABLE),
 		global_page_state(NR_BOUNCE),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		global_page_state(NR_ANON_THPS) * HPAGE_PMD_NR,
-		global_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR,
-		global_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR,
-#endif
 		global_page_state(NR_FREE_PAGES),
 		free_pcp,
 		global_page_state(NR_FREE_CMA_PAGES));
 
+	for_each_online_pgdat(pgdat) {
+		printk("Node %d"
+			" active_anon:%lukB"
+			" inactive_anon:%lukB"
+			" active_file:%lukB"
+			" inactive_file:%lukB"
+			" unevictable:%lukB"
+			" isolated(anon):%lukB"
+			" isolated(file):%lukB"
+			" mapped:%lukB"
+			" dirty:%lukB"
+			" writeback:%lukB"
+			" shmem:%lukB"
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+			" shmem_thp: %lukB"
+			" shmem_pmdmapped: %lukB"
+			" anon_thp: %lukB"
+#endif
+			" writeback_tmp:%lukB"
+			" unstable:%lukB"
+			" pages_scanned:%lu"
+			" all_unreclaimable? %s"
+			"\n",
+			pgdat->node_id,
+			K(node_page_state(pgdat, NR_ACTIVE_ANON)),
+			K(node_page_state(pgdat, NR_INACTIVE_ANON)),
+			K(node_page_state(pgdat, NR_ACTIVE_FILE)),
+			K(node_page_state(pgdat, NR_INACTIVE_FILE)),
+			K(node_page_state(pgdat, NR_UNEVICTABLE)),
+			K(node_page_state(pgdat, NR_ISOLATED_ANON)),
+			K(node_page_state(pgdat, NR_ISOLATED_FILE)),
+			K(node_page_state(pgdat, NR_FILE_MAPPED)),
+			K(node_page_state(pgdat, NR_FILE_DIRTY)),
+			K(node_page_state(pgdat, NR_WRITEBACK)),
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+			K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
+			K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
+					* HPAGE_PMD_NR),
+			K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
+#endif
+			K(node_page_state(pgdat, NR_SHMEM)),
+			K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
+			K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
+			node_page_state(pgdat, NR_PAGES_SCANNED),
+			!pgdat_reclaimable(pgdat) ? "yes" : "no");
+	}
+
 	for_each_populated_zone(zone) {
 		int i;
 
@@ -4362,72 +4310,41 @@ void show_free_areas(unsigned int filter)
 			" active_file:%lukB"
 			" inactive_file:%lukB"
 			" unevictable:%lukB"
-			" isolated(anon):%lukB"
-			" isolated(file):%lukB"
+			" writepending:%lukB"
 			" present:%lukB"
 			" managed:%lukB"
 			" mlocked:%lukB"
-			" dirty:%lukB"
-			" writeback:%lukB"
-			" mapped:%lukB"
-			" shmem:%lukB"
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			" shmem_thp: %lukB"
-			" shmem_pmdmapped: %lukB"
-			" anon_thp: %lukB"
-#endif
 			" slab_reclaimable:%lukB"
 			" slab_unreclaimable:%lukB"
 			" kernel_stack:%lukB"
 			" pagetables:%lukB"
-			" unstable:%lukB"
 			" bounce:%lukB"
 			" free_pcp:%lukB"
 			" local_pcp:%ukB"
 			" free_cma:%lukB"
-			" writeback_tmp:%lukB"
-			" pages_scanned:%lu"
-			" all_unreclaimable? %s"
 			"\n",
 			zone->name,
 			K(zone_page_state(zone, NR_FREE_PAGES)),
 			K(min_wmark_pages(zone)),
 			K(low_wmark_pages(zone)),
 			K(high_wmark_pages(zone)),
-			K(zone_page_state(zone, NR_ACTIVE_ANON)),
-			K(zone_page_state(zone, NR_INACTIVE_ANON)),
-			K(zone_page_state(zone, NR_ACTIVE_FILE)),
-			K(zone_page_state(zone, NR_INACTIVE_FILE)),
-			K(zone_page_state(zone, NR_UNEVICTABLE)),
-			K(zone_page_state(zone, NR_ISOLATED_ANON)),
-			K(zone_page_state(zone, NR_ISOLATED_FILE)),
+			K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)),
+			K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)),
+			K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)),
+			K(zone_page_state(zone, NR_ZONE_INACTIVE_FILE)),
+			K(zone_page_state(zone, NR_ZONE_UNEVICTABLE)),
+			K(zone_page_state(zone, NR_ZONE_WRITE_PENDING)),
 			K(zone->present_pages),
 			K(zone->managed_pages),
 			K(zone_page_state(zone, NR_MLOCK)),
-			K(zone_page_state(zone, NR_FILE_DIRTY)),
-			K(zone_page_state(zone, NR_WRITEBACK)),
-			K(zone_page_state(zone, NR_FILE_MAPPED)),
-			K(zone_page_state(zone, NR_SHMEM)),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			K(zone_page_state(zone, NR_SHMEM_THPS) * HPAGE_PMD_NR),
-			K(zone_page_state(zone, NR_SHMEM_PMDMAPPED)
-					* HPAGE_PMD_NR),
-			K(zone_page_state(zone, NR_ANON_THPS) * HPAGE_PMD_NR),
-#endif
 			K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
 			K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
-			zone_page_state(zone, NR_KERNEL_STACK) *
-				THREAD_SIZE / 1024,
+			zone_page_state(zone, NR_KERNEL_STACK_KB),
 			K(zone_page_state(zone, NR_PAGETABLE)),
-			K(zone_page_state(zone, NR_UNSTABLE_NFS)),
 			K(zone_page_state(zone, NR_BOUNCE)),
 			K(free_pcp),
 			K(this_cpu_read(zone->pageset->pcp.count)),
-			K(zone_page_state(zone, NR_FREE_CMA_PAGES)),
-			K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
-			K(zone_page_state(zone, NR_PAGES_SCANNED)),
-			(!zone_reclaimable(zone) ? "yes" : "no")
-			);
+			K(zone_page_state(zone, NR_FREE_CMA_PAGES)));
 		printk("lowmem_reserve[]:");
 		for (i = 0; i < MAX_NR_ZONES; i++)
 			printk(" %ld", zone->lowmem_reserve[i]);
@@ -4469,7 +4386,7 @@ void show_free_areas(unsigned int filter)
 
 	hugetlb_show_meminfo();
 
-	printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES));
+	printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES));
 
 	show_swap_cache_info();
 }
@@ -5340,6 +5257,11 @@ static void __meminit setup_zone_pageset(struct zone *zone)
 	zone->pageset = alloc_percpu(struct per_cpu_pageset);
 	for_each_possible_cpu(cpu)
 		zone_pageset_init(zone, cpu);
+
+	if (!zone->zone_pgdat->per_cpu_nodestats) {
+		zone->zone_pgdat->per_cpu_nodestats =
+			alloc_percpu(struct per_cpu_nodestat);
+	}
 }
 
 /*
@@ -5909,6 +5831,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 	init_waitqueue_head(&pgdat->kcompactd_wait);
 #endif
 	pgdat_page_ext_init(pgdat);
+	spin_lock_init(&pgdat->lru_lock);
+	lruvec_init(node_lruvec(pgdat));
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
@@ -5958,21 +5882,16 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
 #ifdef CONFIG_NUMA
 		zone->node = nid;
-		zone->min_unmapped_pages = (freesize*sysctl_min_unmapped_ratio)
+		pgdat->min_unmapped_pages += (freesize*sysctl_min_unmapped_ratio)
 						/ 100;
-		zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100;
+		pgdat->min_slab_pages += (freesize * sysctl_min_slab_ratio) / 100;
 #endif
 		zone->name = zone_names[j];
+		zone->zone_pgdat = pgdat;
 		spin_lock_init(&zone->lock);
-		spin_lock_init(&zone->lru_lock);
 		zone_seqlock_init(zone);
-		zone->zone_pgdat = pgdat;
 		zone_pcp_init(zone);
 
-		/* For bootup, initialized properly in watermark setup */
-		mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);
-
-		lruvec_init(&zone->lruvec);
 		if (!size)
 			continue;
 
@@ -6038,11 +5957,12 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	unsigned long end_pfn = 0;
 
 	/* pg_data_t should be reset to zero when it's allocated */
-	WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
+	WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
 
 	reset_deferred_meminit(pgdat);
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
+	pgdat->per_cpu_nodestats = NULL;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 	pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
@@ -6699,6 +6619,9 @@ static void calculate_totalreserve_pages(void)
 	enum zone_type i, j;
 
 	for_each_online_pgdat(pgdat) {
+
+		pgdat->totalreserve_pages = 0;
+
 		for (i = 0; i < MAX_NR_ZONES; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 			long max = 0;
@@ -6715,7 +6638,7 @@ static void calculate_totalreserve_pages(void)
 			if (max > zone->managed_pages)
 				max = zone->managed_pages;
 
-			zone->totalreserve_pages = max;
+			pgdat->totalreserve_pages += max;
 
 			reserve_pages += max;
 		}
@@ -6816,10 +6739,6 @@ static void __setup_per_zone_wmarks(void)
 		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + tmp;
 		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
 
-		__mod_zone_page_state(zone, NR_ALLOC_BATCH,
-			high_wmark_pages(zone) - low_wmark_pages(zone) -
-			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
-
 		spin_unlock_irqrestore(&zone->lock, flags);
 	}
 
@@ -6930,6 +6849,7 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
 int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
+	struct pglist_data *pgdat;
 	struct zone *zone;
 	int rc;
 
@@ -6937,8 +6857,11 @@ int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
 	if (rc)
 		return rc;
 
+	for_each_online_pgdat(pgdat)
+		pgdat->min_slab_pages = 0;
+
 	for_each_zone(zone)
-		zone->min_unmapped_pages = (zone->managed_pages *
+		zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
 				sysctl_min_unmapped_ratio) / 100;
 	return 0;
 }
@@ -6946,6 +6869,7 @@ int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
 int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
+	struct pglist_data *pgdat;
 	struct zone *zone;
 	int rc;
 
@@ -6953,8 +6877,11 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
 	if (rc)
 		return rc;
 
+	for_each_online_pgdat(pgdat)
+		pgdat->min_slab_pages = 0;
+
 	for_each_zone(zone)
-		zone->min_slab_pages = (zone->managed_pages *
+		zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
 				sysctl_min_slab_ratio) / 100;
 	return 0;
 }

mm/page_idle.c

@@ -41,12 +41,12 @@ static struct page *page_idle_get_page(unsigned long pfn)
 		return NULL;
 
 	zone = page_zone(page);
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	if (unlikely(!PageLRU(page))) {
 		put_page(page);
 		page = NULL;
 	}
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 	return page;
 }
 

mm/page_io.c

@@ -166,6 +166,8 @@ int generic_swapfile_activate(struct swap_info_struct *sis,
 		unsigned block_in_page;
 		sector_t first_block;
 
+		cond_resched();
+
 		first_block = bmap(inode, probe_block);
 		if (first_block == 0)
 			goto bad_bmap;

mm/rmap.c

@@ -27,7 +27,7 @@
  *         mapping->i_mmap_rwsem
  *           anon_vma->rwsem
  *             mm->page_table_lock or pte_lock
- *               zone->lru_lock (in mark_page_accessed, isolate_lru_page)
+ *               zone_lru_lock (in mark_page_accessed, isolate_lru_page)
  *               swap_lock (in swap_duplicate, swap_info_get)
  *                 mmlist_lock (in mmput, drain_mmlist and others)
  *                 mapping->private_lock (in __set_page_dirty_buffers)
@@ -1213,8 +1213,8 @@ void do_page_add_anon_rmap(struct page *page,
 		 * disabled.
 		 */
 		if (compound)
-			__inc_zone_page_state(page, NR_ANON_THPS);
-		__mod_zone_page_state(page_zone(page), NR_ANON_PAGES, nr);
+			__inc_node_page_state(page, NR_ANON_THPS);
+		__mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr);
 	}
 	if (unlikely(PageKsm(page)))
 		return;
@@ -1251,14 +1251,14 @@ void page_add_new_anon_rmap(struct page *page,
 		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
 		/* increment count (starts at -1) */
 		atomic_set(compound_mapcount_ptr(page), 0);
-		__inc_zone_page_state(page, NR_ANON_THPS);
+		__inc_node_page_state(page, NR_ANON_THPS);
 	} else {
 		/* Anon THP always mapped first with PMD */
 		VM_BUG_ON_PAGE(PageTransCompound(page), page);
 		/* increment count (starts at -1) */
 		atomic_set(&page->_mapcount, 0);
 	}
-	__mod_zone_page_state(page_zone(page), NR_ANON_PAGES, nr);
+	__mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr);
 	__page_set_anon_rmap(page, vma, address, 1);
 }
 
@@ -1282,7 +1282,7 @@ void page_add_file_rmap(struct page *page, bool compound)
 		if (!atomic_inc_and_test(compound_mapcount_ptr(page)))
 			goto out;
 		VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
-		__inc_zone_page_state(page, NR_SHMEM_PMDMAPPED);
+		__inc_node_page_state(page, NR_SHMEM_PMDMAPPED);
 	} else {
 		if (PageTransCompound(page)) {
 			VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -1293,7 +1293,7 @@ void page_add_file_rmap(struct page *page, bool compound)
 		if (!atomic_inc_and_test(&page->_mapcount))
 			goto out;
 	}
-	__mod_zone_page_state(page_zone(page), NR_FILE_MAPPED, nr);
+	__mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, nr);
 	mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
 out:
 	unlock_page_memcg(page);
@@ -1322,18 +1322,18 @@ static void page_remove_file_rmap(struct page *page, bool compound)
 		if (!atomic_add_negative(-1, compound_mapcount_ptr(page)))
 			goto out;
 		VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
-		__dec_zone_page_state(page, NR_SHMEM_PMDMAPPED);
+		__dec_node_page_state(page, NR_SHMEM_PMDMAPPED);
 	} else {
 		if (!atomic_add_negative(-1, &page->_mapcount))
 			goto out;
 	}
 
 	/*
-	 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
+	 * We use the irq-unsafe __{inc|mod}_zone_page_state because
 	 * these counters are not modified in interrupt context, and
 	 * pte lock(a spinlock) is held, which implies preemption disabled.
 	 */
-	__mod_zone_page_state(page_zone(page), NR_FILE_MAPPED, -nr);
+	__mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, -nr);
 	mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
 
 	if (unlikely(PageMlocked(page)))
@@ -1356,7 +1356,7 @@ static void page_remove_anon_compound_rmap(struct page *page)
 	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
 		return;
 
-	__dec_zone_page_state(page, NR_ANON_THPS);
+	__dec_node_page_state(page, NR_ANON_THPS);
 
 	if (TestClearPageDoubleMap(page)) {
 		/*
@@ -1375,7 +1375,7 @@ static void page_remove_anon_compound_rmap(struct page *page)
 		clear_page_mlock(page);
 
 	if (nr) {
-		__mod_zone_page_state(page_zone(page), NR_ANON_PAGES, -nr);
+		__mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, -nr);
 		deferred_split_huge_page(page);
 	}
 }
@@ -1404,7 +1404,7 @@ void page_remove_rmap(struct page *page, bool compound)
 	 * these counters are not modified in interrupt context, and
 	 * pte lock(a spinlock) is held, which implies preemption disabled.
 	 */
-	__dec_zone_page_state(page, NR_ANON_PAGES);
+	__dec_node_page_state(page, NR_ANON_MAPPED);
 
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);

mm/shmem.c

@@ -575,9 +575,9 @@ static int shmem_add_to_page_cache(struct page *page,
 	if (!error) {
 		mapping->nrpages += nr;
 		if (PageTransHuge(page))
-			__inc_zone_page_state(page, NR_SHMEM_THPS);
-		__mod_zone_page_state(page_zone(page), NR_FILE_PAGES, nr);
-		__mod_zone_page_state(page_zone(page), NR_SHMEM, nr);
+			__inc_node_page_state(page, NR_SHMEM_THPS);
+		__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
+		__mod_node_page_state(page_pgdat(page), NR_SHMEM, nr);
 		spin_unlock_irq(&mapping->tree_lock);
 	} else {
 		page->mapping = NULL;
@@ -601,8 +601,8 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap)
 	error = shmem_radix_tree_replace(mapping, page->index, page, radswap);
 	page->mapping = NULL;
 	mapping->nrpages--;
-	__dec_zone_page_state(page, NR_FILE_PAGES);
-	__dec_zone_page_state(page, NR_SHMEM);
+	__dec_node_page_state(page, NR_FILE_PAGES);
+	__dec_node_page_state(page, NR_SHMEM);
 	spin_unlock_irq(&mapping->tree_lock);
 	put_page(page);
 	BUG_ON(error);
@@ -1493,8 +1493,8 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 	error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
 								   newpage);
 	if (!error) {
-		__inc_zone_page_state(newpage, NR_FILE_PAGES);
-		__dec_zone_page_state(oldpage, NR_FILE_PAGES);
+		__inc_node_page_state(newpage, NR_FILE_PAGES);
+		__dec_node_page_state(oldpage, NR_FILE_PAGES);
 	}
 	spin_unlock_irq(&swap_mapping->tree_lock);
 

mm/slab.h

@@ -369,6 +369,8 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
 	if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
 		return s->object_size;
 # endif
+	if (s->flags & SLAB_KASAN)
+		return s->object_size;
 	/*
 	 * If we have the need to store the freelist pointer
 	 * back there or track user information then we can

mm/slub.c

@@ -124,7 +124,7 @@ static inline int kmem_cache_debug(struct kmem_cache *s)
 #endif
 }
 
-static inline void *fixup_red_left(struct kmem_cache *s, void *p)
+inline void *fixup_red_left(struct kmem_cache *s, void *p)
 {
 	if (kmem_cache_debug(s) && s->flags & SLAB_RED_ZONE)
 		p += s->red_left_pad;
@@ -454,8 +454,6 @@ static inline void *restore_red_left(struct kmem_cache *s, void *p)
  */
 #if defined(CONFIG_SLUB_DEBUG_ON)
 static int slub_debug = DEBUG_DEFAULT_FLAGS;
-#elif defined(CONFIG_KASAN)
-static int slub_debug = SLAB_STORE_USER;
 #else
 static int slub_debug;
 #endif
@@ -660,6 +658,8 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 	if (s->flags & SLAB_STORE_USER)
 		off += 2 * sizeof(struct track);
 
+	off += kasan_metadata_size(s);
+
 	if (off != size_from_object(s))
 		/* Beginning of the filler is the free pointer */
 		print_section("Padding ", p + off, size_from_object(s) - off);
@@ -787,6 +787,8 @@ static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p)
 		/* We also have user information there */
 		off += 2 * sizeof(struct track);
 
+	off += kasan_metadata_size(s);
+
 	if (size_from_object(s) == off)
 		return 1;
 
@@ -1322,8 +1324,10 @@ static inline void kfree_hook(const void *x)
 	kasan_kfree_large(x);
 }
 
-static inline void slab_free_hook(struct kmem_cache *s, void *x)
+static inline void *slab_free_hook(struct kmem_cache *s, void *x)
 {
+	void *freeptr;
+
 	kmemleak_free_recursive(x, s->flags);
 
 	/*
@@ -1344,7 +1348,13 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x)
 	if (!(s->flags & SLAB_DEBUG_OBJECTS))
 		debug_check_no_obj_freed(x, s->object_size);
 
+	freeptr = get_freepointer(s, x);
+	/*
+	 * kasan_slab_free() may put x into memory quarantine, delaying its
+	 * reuse. In this case the object's freelist pointer is changed.
+	 */
 	kasan_slab_free(s, x);
+	return freeptr;
 }
 
 static inline void slab_free_freelist_hook(struct kmem_cache *s,
@@ -1362,11 +1372,11 @@ static inline void slab_free_freelist_hook(struct kmem_cache *s,
 
 	void *object = head;
 	void *tail_obj = tail ? : head;
+	void *freeptr;
 
 	do {
-		slab_free_hook(s, object);
-	} while ((object != tail_obj) &&
-		 (object = get_freepointer(s, object)));
+		freeptr = slab_free_hook(s, object);
+	} while ((object != tail_obj) && (object = freeptr));
 #endif
 }
 
@@ -2878,16 +2888,13 @@ slab_empty:
  * same page) possible by specifying head and tail ptr, plus objects
  * count (cnt). Bulk free indicated by tail pointer being set.
  */
-static __always_inline void slab_free(struct kmem_cache *s, struct page *page,
-				      void *head, void *tail, int cnt,
-				      unsigned long addr)
+static __always_inline void do_slab_free(struct kmem_cache *s,
+				struct page *page, void *head, void *tail,
+				int cnt, unsigned long addr)
 {
 	void *tail_obj = tail ? : head;
 	struct kmem_cache_cpu *c;
 	unsigned long tid;
-
-	slab_free_freelist_hook(s, head, tail);
-
 redo:
 	/*
 	 * Determine the currently cpus per cpu slab.
@@ -2921,6 +2928,27 @@ redo:
 
 }
 
+static __always_inline void slab_free(struct kmem_cache *s, struct page *page,
+				      void *head, void *tail, int cnt,
+				      unsigned long addr)
+{
+	slab_free_freelist_hook(s, head, tail);
+	/*
+	 * slab_free_freelist_hook() could have put the items into quarantine.
+	 * If so, no need to free them.
+	 */
+	if (s->flags & SLAB_KASAN && !(s->flags & SLAB_DESTROY_BY_RCU))
+		return;
+	do_slab_free(s, page, head, tail, cnt, addr);
+}
+
+#ifdef CONFIG_KASAN
+void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr)
+{
+	do_slab_free(cache, virt_to_head_page(x), x, NULL, 1, addr);
+}
+#endif
+
 void kmem_cache_free(struct kmem_cache *s, void *x)
 {
 	s = cache_from_obj(s, x);
@@ -3363,7 +3391,7 @@ static void set_min_partial(struct kmem_cache *s, unsigned long min)
 static int calculate_sizes(struct kmem_cache *s, int forced_order)
 {
 	unsigned long flags = s->flags;
-	unsigned long size = s->object_size;
+	size_t size = s->object_size;
 	int order;
 
 	/*
@@ -3422,7 +3450,10 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 		 * the object.
 		 */
 		size += 2 * sizeof(struct track);
+#endif
 
+	kasan_cache_create(s, &size, &s->flags);
+#ifdef CONFIG_SLUB_DEBUG
 	if (flags & SLAB_RED_ZONE) {
 		/*
 		 * Add some empty padding so that we can catch

mm/sparse.c

@@ -100,11 +100,7 @@ static inline int sparse_index_init(unsigned long section_nr, int nid)
 }
 #endif
 
-/*
- * Although written for the SPARSEMEM_EXTREME case, this happens
- * to also work for the flat array case because
- * NR_SECTION_ROOTS==NR_MEM_SECTIONS.
- */
+#ifdef CONFIG_SPARSEMEM_EXTREME
 int __section_nr(struct mem_section* ms)
 {
 	unsigned long root_nr;
@@ -123,6 +119,12 @@ int __section_nr(struct mem_section* ms)
 
 	return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
 }
+#else
+int __section_nr(struct mem_section* ms)
+{
+	return (int)(ms - mem_section[0]);
+}
+#endif
 
 /*
  * During early boot, before section_mem_map is used for an actual

mm/swap.c

@@ -62,12 +62,12 @@ static void __page_cache_release(struct page *page)
 		struct lruvec *lruvec;
 		unsigned long flags;
 
-		spin_lock_irqsave(&zone->lru_lock, flags);
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		spin_lock_irqsave(zone_lru_lock(zone), flags);
+		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
 		VM_BUG_ON_PAGE(!PageLRU(page), page);
 		__ClearPageLRU(page);
 		del_page_from_lru_list(page, lruvec, page_off_lru(page));
-		spin_unlock_irqrestore(&zone->lru_lock, flags);
+		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 	}
 	mem_cgroup_uncharge(page);
 }
@@ -179,26 +179,26 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 	void *arg)
 {
 	int i;
-	struct zone *zone = NULL;
+	struct pglist_data *pgdat = NULL;
 	struct lruvec *lruvec;
 	unsigned long flags = 0;
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		struct zone *pagezone = page_zone(page);
+		struct pglist_data *pagepgdat = page_pgdat(page);
 
-		if (pagezone != zone) {
-			if (zone)
-				spin_unlock_irqrestore(&zone->lru_lock, flags);
-			zone = pagezone;
-			spin_lock_irqsave(&zone->lru_lock, flags);
+		if (pagepgdat != pgdat) {
+			if (pgdat)
+				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+			pgdat = pagepgdat;
+			spin_lock_irqsave(&pgdat->lru_lock, flags);
 		}
 
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		(*move_fn)(page, lruvec, arg);
 	}
-	if (zone)
-		spin_unlock_irqrestore(&zone->lru_lock, flags);
+	if (pgdat)
+		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
 	release_pages(pvec->pages, pvec->nr, pvec->cold);
 	pagevec_reinit(pvec);
 }
@@ -318,9 +318,9 @@ void activate_page(struct page *page)
 	struct zone *zone = page_zone(page);
 
 	page = compound_head(page);
-	spin_lock_irq(&zone->lru_lock);
-	__activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL);
-	spin_unlock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
+	__activate_page(page, mem_cgroup_page_lruvec(page, zone->zone_pgdat), NULL);
+	spin_unlock_irq(zone_lru_lock(zone));
 }
 #endif
 
@@ -445,16 +445,16 @@ void lru_cache_add(struct page *page)
  */
 void add_page_to_unevictable_list(struct page *page)
 {
-	struct zone *zone = page_zone(page);
+	struct pglist_data *pgdat = page_pgdat(page);
 	struct lruvec *lruvec;
 
-	spin_lock_irq(&zone->lru_lock);
-	lruvec = mem_cgroup_page_lruvec(page, zone);
+	spin_lock_irq(&pgdat->lru_lock);
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
 	ClearPageActive(page);
 	SetPageUnevictable(page);
 	SetPageLRU(page);
 	add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE);
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(&pgdat->lru_lock);
 }
 
 /**
@@ -730,7 +730,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 {
 	int i;
 	LIST_HEAD(pages_to_free);
-	struct zone *zone = NULL;
+	struct pglist_data *locked_pgdat = NULL;
 	struct lruvec *lruvec;
 	unsigned long uninitialized_var(flags);
 	unsigned int uninitialized_var(lock_batch);
@@ -741,11 +741,11 @@ void release_pages(struct page **pages, int nr, bool cold)
 		/*
 		 * Make sure the IRQ-safe lock-holding time does not get
 		 * excessive with a continuous string of pages from the
-		 * same zone. The lock is held only if zone != NULL.
+		 * same pgdat. The lock is held only if pgdat != NULL.
 		 */
-		if (zone && ++lock_batch == SWAP_CLUSTER_MAX) {
-			spin_unlock_irqrestore(&zone->lru_lock, flags);
-			zone = NULL;
+		if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) {
+			spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
+			locked_pgdat = NULL;
 		}
 
 		if (is_huge_zero_page(page)) {
@@ -758,27 +758,27 @@ void release_pages(struct page **pages, int nr, bool cold)
 			continue;
 
 		if (PageCompound(page)) {
-			if (zone) {
-				spin_unlock_irqrestore(&zone->lru_lock, flags);
-				zone = NULL;
+			if (locked_pgdat) {
+				spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
+				locked_pgdat = NULL;
 			}
 			__put_compound_page(page);
 			continue;
 		}
 
 		if (PageLRU(page)) {
-			struct zone *pagezone = page_zone(page);
+			struct pglist_data *pgdat = page_pgdat(page);
 
-			if (pagezone != zone) {
-				if (zone)
-					spin_unlock_irqrestore(&zone->lru_lock,
+			if (pgdat != locked_pgdat) {
+				if (locked_pgdat)
+					spin_unlock_irqrestore(&locked_pgdat->lru_lock,
 									flags);
 				lock_batch = 0;
-				zone = pagezone;
-				spin_lock_irqsave(&zone->lru_lock, flags);
+				locked_pgdat = pgdat;
+				spin_lock_irqsave(&locked_pgdat->lru_lock, flags);
 			}
 
-			lruvec = mem_cgroup_page_lruvec(page, zone);
+			lruvec = mem_cgroup_page_lruvec(page, locked_pgdat);
 			VM_BUG_ON_PAGE(!PageLRU(page), page);
 			__ClearPageLRU(page);
 			del_page_from_lru_list(page, lruvec, page_off_lru(page));
@@ -789,8 +789,8 @@ void release_pages(struct page **pages, int nr, bool cold)
 
 		list_add(&page->lru, &pages_to_free);
 	}
-	if (zone)
-		spin_unlock_irqrestore(&zone->lru_lock, flags);
+	if (locked_pgdat)
+		spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
 
 	mem_cgroup_uncharge_list(&pages_to_free);
 	free_hot_cold_page_list(&pages_to_free, cold);
@@ -826,7 +826,7 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
 	VM_BUG_ON_PAGE(PageCompound(page_tail), page);
 	VM_BUG_ON_PAGE(PageLRU(page_tail), page);
 	VM_BUG_ON(NR_CPUS != 1 &&
-		  !spin_is_locked(&lruvec_zone(lruvec)->lru_lock));
+		  !spin_is_locked(&lruvec_pgdat(lruvec)->lru_lock));
 
 	if (!list)
 		SetPageLRU(page_tail);

mm/swap_state.c

@@ -95,7 +95,7 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry)
 					entry.val, page);
 	if (likely(!error)) {
 		address_space->nrpages++;
-		__inc_zone_page_state(page, NR_FILE_PAGES);
+		__inc_node_page_state(page, NR_FILE_PAGES);
 		INC_CACHE_INFO(add_total);
 	}
 	spin_unlock_irq(&address_space->tree_lock);
@@ -147,7 +147,7 @@ void __delete_from_swap_cache(struct page *page)
 	set_page_private(page, 0);
 	ClearPageSwapCache(page);
 	address_space->nrpages--;
-	__dec_zone_page_state(page, NR_FILE_PAGES);
+	__dec_node_page_state(page, NR_FILE_PAGES);
 	INC_CACHE_INFO(del_total);
 }
 

mm/util.c

@@ -528,7 +528,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 
 	if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
 		free = global_page_state(NR_FREE_PAGES);
-		free += global_page_state(NR_FILE_PAGES);
+		free += global_node_page_state(NR_FILE_PAGES);
 
 		/*
 		 * shmem pages shouldn't be counted as free in this
@@ -536,7 +536,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		 * that won't affect the overall amount of available
 		 * memory in the system.
 		 */
-		free -= global_page_state(NR_SHMEM);
+		free -= global_node_page_state(NR_SHMEM);
 
 		free += get_nr_swap_pages();
 

mm/vmscan.c

@@ -84,6 +84,9 @@ struct scan_control {
 	/* Scan (total_size >> priority) pages at once */
 	int priority;
 
+	/* The highest zone to isolate pages for reclaim from */
+	enum zone_type reclaim_idx;
+
 	unsigned int may_writepage:1;
 
 	/* Can mapped pages be reclaimed? */
@@ -191,26 +194,44 @@ static bool sane_reclaim(struct scan_control *sc)
 }
 #endif
 
+/*
+ * This misses isolated pages which are not accounted for to save counters.
+ * As the data only determines if reclaim or compaction continues, it is
+ * not expected that isolated pages will be a dominating factor.
+ */
 unsigned long zone_reclaimable_pages(struct zone *zone)
 {
 	unsigned long nr;
 
-	nr = zone_page_state_snapshot(zone, NR_ACTIVE_FILE) +
-	     zone_page_state_snapshot(zone, NR_INACTIVE_FILE) +
-	     zone_page_state_snapshot(zone, NR_ISOLATED_FILE);
+	nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
+		zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
+	if (get_nr_swap_pages() > 0)
+		nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
+			zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);
+
+	return nr;
+}
+
+unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat)
+{
+	unsigned long nr;
+
+	nr = node_page_state_snapshot(pgdat, NR_ACTIVE_FILE) +
+	     node_page_state_snapshot(pgdat, NR_INACTIVE_FILE) +
+	     node_page_state_snapshot(pgdat, NR_ISOLATED_FILE);
 
 	if (get_nr_swap_pages() > 0)
-		nr += zone_page_state_snapshot(zone, NR_ACTIVE_ANON) +
-		      zone_page_state_snapshot(zone, NR_INACTIVE_ANON) +
-		      zone_page_state_snapshot(zone, NR_ISOLATED_ANON);
+		nr += node_page_state_snapshot(pgdat, NR_ACTIVE_ANON) +
+		      node_page_state_snapshot(pgdat, NR_INACTIVE_ANON) +
+		      node_page_state_snapshot(pgdat, NR_ISOLATED_ANON);
 
 	return nr;
 }
 
-bool zone_reclaimable(struct zone *zone)
+bool pgdat_reclaimable(struct pglist_data *pgdat)
 {
-	return zone_page_state_snapshot(zone, NR_PAGES_SCANNED) <
-		zone_reclaimable_pages(zone) * 6;
+	return node_page_state_snapshot(pgdat, NR_PAGES_SCANNED) <
+		pgdat_reclaimable_pages(pgdat) * 6;
 }
 
 unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
@@ -218,7 +239,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
 	if (!mem_cgroup_disabled())
 		return mem_cgroup_get_lru_size(lruvec, lru);
 
-	return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru);
+	return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
 }
 
 /*
@@ -593,7 +614,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 			ClearPageReclaim(page);
 		}
 		trace_mm_vmscan_writepage(page);
-		inc_zone_page_state(page, NR_VMSCAN_WRITE);
+		inc_node_page_state(page, NR_VMSCAN_WRITE);
 		return PAGE_SUCCESS;
 	}
 
@@ -877,7 +898,7 @@ static void page_check_dirty_writeback(struct page *page,
  * shrink_page_list() returns the number of reclaimed pages
  */
 static unsigned long shrink_page_list(struct list_head *page_list,
-				      struct zone *zone,
+				      struct pglist_data *pgdat,
 				      struct scan_control *sc,
 				      enum ttu_flags ttu_flags,
 				      unsigned long *ret_nr_dirty,
@@ -917,7 +938,6 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			goto keep;
 
 		VM_BUG_ON_PAGE(PageActive(page), page);
-		VM_BUG_ON_PAGE(page_zone(page) != zone, page);
 
 		sc->nr_scanned++;
 
@@ -996,7 +1016,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			/* Case 1 above */
 			if (current_is_kswapd() &&
 			    PageReclaim(page) &&
-			    test_bit(ZONE_WRITEBACK, &zone->flags)) {
+			    test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
 				nr_immediate++;
 				goto keep_locked;
 
@@ -1092,14 +1112,14 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			 */
 			if (page_is_file_cache(page) &&
 					(!current_is_kswapd() ||
-					 !test_bit(ZONE_DIRTY, &zone->flags))) {
+					 !test_bit(PGDAT_DIRTY, &pgdat->flags))) {
 				/*
 				 * Immediately reclaim when written back.
 				 * Similar in principal to deactivate_page()
 				 * except we already have the page isolated
 				 * and know it's dirty
 				 */
-				inc_zone_page_state(page, NR_VMSCAN_IMMEDIATE);
+				inc_node_page_state(page, NR_VMSCAN_IMMEDIATE);
 				SetPageReclaim(page);
 
 				goto keep_locked;
@@ -1266,11 +1286,11 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 		}
 	}
 
-	ret = shrink_page_list(&clean_pages, zone, &sc,
+	ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
 			TTU_UNMAP|TTU_IGNORE_ACCESS,
 			&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
 	list_splice(&clean_pages, page_list);
-	mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
+	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret);
 	return ret;
 }
 
@@ -1348,8 +1368,31 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 	return ret;
 }
 
+
 /*
- * zone->lru_lock is heavily contended.  Some of the functions that
+ * Update LRU sizes after isolating pages. The LRU size updates must
+ * be complete before mem_cgroup_update_lru_size due to a santity check.
+ */
+static __always_inline void update_lru_sizes(struct lruvec *lruvec,
+			enum lru_list lru, unsigned long *nr_zone_taken,
+			unsigned long nr_taken)
+{
+	int zid;
+
+	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+		if (!nr_zone_taken[zid])
+			continue;
+
+		__update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
+	}
+
+#ifdef CONFIG_MEMCG
+	mem_cgroup_update_lru_size(lruvec, lru, -nr_taken);
+#endif
+}
+
+/*
+ * zone_lru_lock is heavily contended.  Some of the functions that
  * shrink the lists perform better by taking out a batch of pages
  * and working on them outside the LRU lock.
  *
@@ -1375,10 +1418,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 {
 	struct list_head *src = &lruvec->lists[lru];
 	unsigned long nr_taken = 0;
-	unsigned long scan;
+	unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
+	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
+	unsigned long scan, nr_pages;
+	LIST_HEAD(pages_skipped);
 
 	for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
-					!list_empty(src); scan++) {
+					!list_empty(src);) {
 		struct page *page;
 
 		page = lru_to_page(src);
@@ -1386,9 +1432,23 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 		VM_BUG_ON_PAGE(!PageLRU(page), page);
 
+		if (page_zonenum(page) > sc->reclaim_idx) {
+			list_move(&page->lru, &pages_skipped);
+			nr_skipped[page_zonenum(page)]++;
+			continue;
+		}
+
+		/*
+		 * Account for scanned and skipped separetly to avoid the pgdat
+		 * being prematurely marked unreclaimable by pgdat_reclaimable.
+		 */
+		scan++;
+
 		switch (__isolate_lru_page(page, mode)) {
 		case 0:
-			nr_taken += hpage_nr_pages(page);
+			nr_pages = hpage_nr_pages(page);
+			nr_taken += nr_pages;
+			nr_zone_taken[page_zonenum(page)] += nr_pages;
 			list_move(&page->lru, dst);
 			break;
 
@@ -1402,9 +1462,38 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		}
 	}
 
+	/*
+	 * Splice any skipped pages to the start of the LRU list. Note that
+	 * this disrupts the LRU order when reclaiming for lower zones but
+	 * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX
+	 * scanning would soon rescan the same pages to skip and put the
+	 * system at risk of premature OOM.
+	 */
+	if (!list_empty(&pages_skipped)) {
+		int zid;
+		unsigned long total_skipped = 0;
+
+		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+			if (!nr_skipped[zid])
+				continue;
+
+			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
+			total_skipped += nr_skipped[zid];
+		}
+
+		/*
+		 * Account skipped pages as a partial scan as the pgdat may be
+		 * close to unreclaimable. If the LRU list is empty, account
+		 * skipped pages as a full scan.
+		 */
+		scan += list_empty(src) ? total_skipped : total_skipped >> 2;
+
+		list_splice(&pages_skipped, src);
+	}
 	*nr_scanned = scan;
-	trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
+	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
 				    nr_taken, mode, is_file_lru(lru));
+	update_lru_sizes(lruvec, lru, nr_zone_taken, nr_taken);
 	return nr_taken;
 }
 
@@ -1444,8 +1533,8 @@ int isolate_lru_page(struct page *page)
 		struct zone *zone = page_zone(page);
 		struct lruvec *lruvec;
 
-		spin_lock_irq(&zone->lru_lock);
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		spin_lock_irq(zone_lru_lock(zone));
+		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
 		if (PageLRU(page)) {
 			int lru = page_lru(page);
 			get_page(page);
@@ -1453,7 +1542,7 @@ int isolate_lru_page(struct page *page)
 			del_page_from_lru_list(page, lruvec, lru);
 			ret = 0;
 		}
-		spin_unlock_irq(&zone->lru_lock);
+		spin_unlock_irq(zone_lru_lock(zone));
 	}
 	return ret;
 }
@@ -1465,7 +1554,7 @@ int isolate_lru_page(struct page *page)
  * the LRU list will go small and be scanned faster than necessary, leading to
  * unnecessary swapping, thrashing and OOM.
  */
-static int too_many_isolated(struct zone *zone, int file,
+static int too_many_isolated(struct pglist_data *pgdat, int file,
 		struct scan_control *sc)
 {
 	unsigned long inactive, isolated;
@@ -1477,11 +1566,11 @@ static int too_many_isolated(struct zone *zone, int file,
 		return 0;
 
 	if (file) {
-		inactive = zone_page_state(zone, NR_INACTIVE_FILE);
-		isolated = zone_page_state(zone, NR_ISOLATED_FILE);
+		inactive = node_page_state(pgdat, NR_INACTIVE_FILE);
+		isolated = node_page_state(pgdat, NR_ISOLATED_FILE);
 	} else {
-		inactive = zone_page_state(zone, NR_INACTIVE_ANON);
-		isolated = zone_page_state(zone, NR_ISOLATED_ANON);
+		inactive = node_page_state(pgdat, NR_INACTIVE_ANON);
+		isolated = node_page_state(pgdat, NR_ISOLATED_ANON);
 	}
 
 	/*
@@ -1499,7 +1588,7 @@ static noinline_for_stack void
 putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
 {
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
-	struct zone *zone = lruvec_zone(lruvec);
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	LIST_HEAD(pages_to_free);
 
 	/*
@@ -1512,13 +1601,13 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		list_del(&page->lru);
 		if (unlikely(!page_evictable(page))) {
-			spin_unlock_irq(&zone->lru_lock);
+			spin_unlock_irq(&pgdat->lru_lock);
 			putback_lru_page(page);
-			spin_lock_irq(&zone->lru_lock);
+			spin_lock_irq(&pgdat->lru_lock);
 			continue;
 		}
 
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 		SetPageLRU(page);
 		lru = page_lru(page);
@@ -1535,10 +1624,10 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
 			del_page_from_lru_list(page, lruvec, lru);
 
 			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&zone->lru_lock);
+				spin_unlock_irq(&pgdat->lru_lock);
 				mem_cgroup_uncharge(page);
 				(*get_compound_page_dtor(page))(page);
-				spin_lock_irq(&zone->lru_lock);
+				spin_lock_irq(&pgdat->lru_lock);
 			} else
 				list_add(&page->lru, &pages_to_free);
 		}
@@ -1563,8 +1652,32 @@ static int current_may_throttle(void)
 		bdi_write_congested(current->backing_dev_info);
 }
 
+static bool inactive_reclaimable_pages(struct lruvec *lruvec,
+				struct scan_control *sc, enum lru_list lru)
+{
+	int zid;
+	struct zone *zone;
+	int file = is_file_lru(lru);
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
+	if (!global_reclaim(sc))
+		return true;
+
+	for (zid = sc->reclaim_idx; zid >= 0; zid--) {
+		zone = &pgdat->node_zones[zid];
+		if (!populated_zone(zone))
+			continue;
+
+		if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +
+				LRU_FILE * file) >= SWAP_CLUSTER_MAX)
+			return true;
+	}
+
+	return false;
+}
+
 /*
- * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
+ * shrink_inactive_list() is a helper for shrink_node().  It returns the number
  * of reclaimed pages
  */
 static noinline_for_stack unsigned long
@@ -1582,10 +1695,13 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	unsigned long nr_immediate = 0;
 	isolate_mode_t isolate_mode = 0;
 	int file = is_file_lru(lru);
-	struct zone *zone = lruvec_zone(lruvec);
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
 
-	while (unlikely(too_many_isolated(zone, file, sc))) {
+	if (!inactive_reclaimable_pages(lruvec, sc, lru))
+		return 0;
+
+	while (unlikely(too_many_isolated(pgdat, file, sc))) {
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		/* We are about to die and free our memory. Return now. */
@@ -1600,48 +1716,45 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	if (!sc->may_writepage)
 		isolate_mode |= ISOLATE_CLEAN;
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(&pgdat->lru_lock);
 
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
 				     &nr_scanned, sc, isolate_mode, lru);
 
-	update_lru_size(lruvec, lru, -nr_taken);
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
+	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
 	reclaim_stat->recent_scanned[file] += nr_taken;
 
 	if (global_reclaim(sc)) {
-		__mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
+		__mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned);
 		if (current_is_kswapd())
-			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned);
+			__count_vm_events(PGSCAN_KSWAPD, nr_scanned);
 		else
-			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned);
+			__count_vm_events(PGSCAN_DIRECT, nr_scanned);
 	}
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(&pgdat->lru_lock);
 
 	if (nr_taken == 0)
 		return 0;
 
-	nr_reclaimed = shrink_page_list(&page_list, zone, sc, TTU_UNMAP,
+	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, TTU_UNMAP,
 				&nr_dirty, &nr_unqueued_dirty, &nr_congested,
 				&nr_writeback, &nr_immediate,
 				false);
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(&pgdat->lru_lock);
 
 	if (global_reclaim(sc)) {
 		if (current_is_kswapd())
-			__count_zone_vm_events(PGSTEAL_KSWAPD, zone,
-					       nr_reclaimed);
+			__count_vm_events(PGSTEAL_KSWAPD, nr_reclaimed);
 		else
-			__count_zone_vm_events(PGSTEAL_DIRECT, zone,
-					       nr_reclaimed);
+			__count_vm_events(PGSTEAL_DIRECT, nr_reclaimed);
 	}
 
 	putback_inactive_pages(lruvec, &page_list);
 
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
+	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
 
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(&pgdat->lru_lock);
 
 	mem_cgroup_uncharge_list(&page_list);
 	free_hot_cold_page_list(&page_list, true);
@@ -1661,7 +1774,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	 * are encountered in the nr_immediate check below.
 	 */
 	if (nr_writeback && nr_writeback == nr_taken)
-		set_bit(ZONE_WRITEBACK, &zone->flags);
+		set_bit(PGDAT_WRITEBACK, &pgdat->flags);
 
 	/*
 	 * Legacy memcg will stall in page writeback so avoid forcibly
@@ -1673,16 +1786,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * backed by a congested BDI and wait_iff_congested will stall.
 		 */
 		if (nr_dirty && nr_dirty == nr_congested)
-			set_bit(ZONE_CONGESTED, &zone->flags);
+			set_bit(PGDAT_CONGESTED, &pgdat->flags);
 
 		/*
 		 * If dirty pages are scanned that are not queued for IO, it
 		 * implies that flushers are not keeping up. In this case, flag
-		 * the zone ZONE_DIRTY and kswapd will start writing pages from
+		 * the pgdat PGDAT_DIRTY and kswapd will start writing pages from
 		 * reclaim context.
 		 */
 		if (nr_unqueued_dirty == nr_taken)
-			set_bit(ZONE_DIRTY, &zone->flags);
+			set_bit(PGDAT_DIRTY, &pgdat->flags);
 
 		/*
 		 * If kswapd scans pages marked marked for immediate
@@ -1701,9 +1814,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	 */
 	if (!sc->hibernation_mode && !current_is_kswapd() &&
 	    current_may_throttle())
-		wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10);
+		wait_iff_congested(pgdat, BLK_RW_ASYNC, HZ/10);
 
-	trace_mm_vmscan_lru_shrink_inactive(zone, nr_scanned, nr_reclaimed,
+	trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
+			nr_scanned, nr_reclaimed,
 			sc->priority, file);
 	return nr_reclaimed;
 }
@@ -1715,9 +1829,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
  * processes, from rmap.
  *
  * If the pages are mostly unmapped, the processing is fast and it is
- * appropriate to hold zone->lru_lock across the whole operation.  But if
+ * appropriate to hold zone_lru_lock across the whole operation.  But if
  * the pages are mapped, the processing is slow (page_referenced()) so we
- * should drop zone->lru_lock around each page.  It's impossible to balance
+ * should drop zone_lru_lock around each page.  It's impossible to balance
  * this, so instead we remove the pages from the LRU while processing them.
  * It is safe to rely on PG_active against the non-LRU pages in here because
  * nobody will play with that bit on a non-LRU page.
@@ -1731,20 +1845,20 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
 				     struct list_head *pages_to_free,
 				     enum lru_list lru)
 {
-	struct zone *zone = lruvec_zone(lruvec);
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	unsigned long pgmoved = 0;
 	struct page *page;
 	int nr_pages;
 
 	while (!list_empty(list)) {
 		page = lru_to_page(list);
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		SetPageLRU(page);
 
 		nr_pages = hpage_nr_pages(page);
-		update_lru_size(lruvec, lru, nr_pages);
+		update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
 		list_move(&page->lru, &lruvec->lists[lru]);
 		pgmoved += nr_pages;
 
@@ -1754,10 +1868,10 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
 			del_page_from_lru_list(page, lruvec, lru);
 
 			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&zone->lru_lock);
+				spin_unlock_irq(&pgdat->lru_lock);
 				mem_cgroup_uncharge(page);
 				(*get_compound_page_dtor(page))(page);
-				spin_lock_irq(&zone->lru_lock);
+				spin_lock_irq(&pgdat->lru_lock);
 			} else
 				list_add(&page->lru, pages_to_free);
 		}
@@ -1783,7 +1897,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	unsigned long nr_rotated = 0;
 	isolate_mode_t isolate_mode = 0;
 	int file = is_file_lru(lru);
-	struct zone *zone = lruvec_zone(lruvec);
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
 	lru_add_drain();
 
@@ -1792,20 +1906,19 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	if (!sc->may_writepage)
 		isolate_mode |= ISOLATE_CLEAN;
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(&pgdat->lru_lock);
 
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
 				     &nr_scanned, sc, isolate_mode, lru);
 
-	update_lru_size(lruvec, lru, -nr_taken);
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
+	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
 	reclaim_stat->recent_scanned[file] += nr_taken;
 
 	if (global_reclaim(sc))
-		__mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
-	__count_zone_vm_events(PGREFILL, zone, nr_scanned);
+		__mod_node_page_state(pgdat, NR_PAGES_SCANNED, nr_scanned);
+	__count_vm_events(PGREFILL, nr_scanned);
 
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(&pgdat->lru_lock);
 
 	while (!list_empty(&l_hold)) {
 		cond_resched();
@@ -1850,7 +1963,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	/*
 	 * Move pages back to the lru list.
 	 */
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(&pgdat->lru_lock);
 	/*
 	 * Count referenced pages from currently used mappings as rotated,
 	 * even though only some of them are actually re-activated.  This
@@ -1861,8 +1974,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
 
 	move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
 	move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
-	spin_unlock_irq(&zone->lru_lock);
+	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
+	spin_unlock_irq(&pgdat->lru_lock);
 
 	mem_cgroup_uncharge_list(&l_hold);
 	free_hot_cold_page_list(&l_hold, true);
@@ -1894,12 +2007,15 @@ static void shrink_active_list(unsigned long nr_to_scan,
  *    1TB     101        10GB
  *   10TB     320        32GB
  */
-static bool inactive_list_is_low(struct lruvec *lruvec, bool file)
+static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
+						struct scan_control *sc)
 {
 	unsigned long inactive_ratio;
 	unsigned long inactive;
 	unsigned long active;
 	unsigned long gb;
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+	int zid;
 
 	/*
 	 * If we don't have swap space, anonymous page deactivation
@@ -1911,6 +2027,27 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file)
 	inactive = lruvec_lru_size(lruvec, file * LRU_FILE);
 	active = lruvec_lru_size(lruvec, file * LRU_FILE + LRU_ACTIVE);
 
+	/*
+	 * For zone-constrained allocations, it is necessary to check if
+	 * deactivations are required for lowmem to be reclaimed. This
+	 * calculates the inactive/active pages available in eligible zones.
+	 */
+	for (zid = sc->reclaim_idx + 1; zid < MAX_NR_ZONES; zid++) {
+		struct zone *zone = &pgdat->node_zones[zid];
+		unsigned long inactive_zone, active_zone;
+
+		if (!populated_zone(zone))
+			continue;
+
+		inactive_zone = zone_page_state(zone,
+				NR_ZONE_LRU_BASE + (file * LRU_FILE));
+		active_zone = zone_page_state(zone,
+				NR_ZONE_LRU_BASE + (file * LRU_FILE) + LRU_ACTIVE);
+
+		inactive -= min(inactive, inactive_zone);
+		active -= min(active, active_zone);
+	}
+
 	gb = (inactive + active) >> (30 - PAGE_SHIFT);
 	if (gb)
 		inactive_ratio = int_sqrt(10 * gb);
@@ -1924,7 +2061,7 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 				 struct lruvec *lruvec, struct scan_control *sc)
 {
 	if (is_active_lru(lru)) {
-		if (inactive_list_is_low(lruvec, is_file_lru(lru)))
+		if (inactive_list_is_low(lruvec, is_file_lru(lru), sc))
 			shrink_active_list(nr_to_scan, lruvec, sc, lru);
 		return 0;
 	}
@@ -1956,7 +2093,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
 	u64 fraction[2];
 	u64 denominator = 0;	/* gcc */
-	struct zone *zone = lruvec_zone(lruvec);
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	unsigned long anon_prio, file_prio;
 	enum scan_balance scan_balance;
 	unsigned long anon, file;
@@ -1977,7 +2114,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * well.
 	 */
 	if (current_is_kswapd()) {
-		if (!zone_reclaimable(zone))
+		if (!pgdat_reclaimable(pgdat))
 			force_scan = true;
 		if (!mem_cgroup_online(memcg))
 			force_scan = true;
@@ -2023,14 +2160,24 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * anon pages.  Try to detect this based on file LRU size.
 	 */
 	if (global_reclaim(sc)) {
-		unsigned long zonefile;
-		unsigned long zonefree;
+		unsigned long pgdatfile;
+		unsigned long pgdatfree;
+		int z;
+		unsigned long total_high_wmark = 0;
 
-		zonefree = zone_page_state(zone, NR_FREE_PAGES);
-		zonefile = zone_page_state(zone, NR_ACTIVE_FILE) +
-			   zone_page_state(zone, NR_INACTIVE_FILE);
+		pgdatfree = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
+		pgdatfile = node_page_state(pgdat, NR_ACTIVE_FILE) +
+			   node_page_state(pgdat, NR_INACTIVE_FILE);
 
-		if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) {
+		for (z = 0; z < MAX_NR_ZONES; z++) {
+			struct zone *zone = &pgdat->node_zones[z];
+			if (!populated_zone(zone))
+				continue;
+
+			total_high_wmark += high_wmark_pages(zone);
+		}
+
+		if (unlikely(pgdatfile + pgdatfree <= total_high_wmark)) {
 			scan_balance = SCAN_ANON;
 			goto out;
 		}
@@ -2045,7 +2192,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * lruvec even if it has plenty of old anonymous pages unless the
 	 * system is under heavy pressure.
 	 */
-	if (!inactive_list_is_low(lruvec, true) &&
+	if (!inactive_list_is_low(lruvec, true, sc) &&
 	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
 		scan_balance = SCAN_FILE;
 		goto out;
@@ -2077,7 +2224,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
 		lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(&pgdat->lru_lock);
 	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
 		reclaim_stat->recent_scanned[0] /= 2;
 		reclaim_stat->recent_rotated[0] /= 2;
@@ -2098,7 +2245,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 
 	fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
 	fp /= reclaim_stat->recent_rotated[1] + 1;
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(&pgdat->lru_lock);
 
 	fraction[0] = ap;
 	fraction[1] = fp;
@@ -2174,12 +2321,12 @@ static inline void init_tlb_ubc(void)
 #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
 
 /*
- * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
+ * This is a basic per-node page freer.  Used by both kswapd and direct reclaim.
  */
-static void shrink_zone_memcg(struct zone *zone, struct mem_cgroup *memcg,
+static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg,
 			      struct scan_control *sc, unsigned long *lru_pages)
 {
-	struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+	struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
 	unsigned long nr[NR_LRU_LISTS];
 	unsigned long targets[NR_LRU_LISTS];
 	unsigned long nr_to_scan;
@@ -2287,7 +2434,7 @@ static void shrink_zone_memcg(struct zone *zone, struct mem_cgroup *memcg,
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (inactive_list_is_low(lruvec, false))
+	if (inactive_list_is_low(lruvec, false, sc))
 		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 				   sc, LRU_ACTIVE_ANON);
 
@@ -2312,13 +2459,14 @@ static bool in_reclaim_compaction(struct scan_control *sc)
  * calls try_to_compact_zone() that it will have enough free pages to succeed.
  * It will give up earlier than that if there is difficulty reclaiming pages.
  */
-static inline bool should_continue_reclaim(struct zone *zone,
+static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 					unsigned long nr_reclaimed,
 					unsigned long nr_scanned,
 					struct scan_control *sc)
 {
 	unsigned long pages_for_compaction;
 	unsigned long inactive_lru_pages;
+	int z;
 
 	/* If not in reclaim/compaction mode, stop */
 	if (!in_reclaim_compaction(sc))
@@ -2352,25 +2500,32 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	 * inactive lists are large enough, continue reclaiming
 	 */
 	pages_for_compaction = (2UL << sc->order);
-	inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE);
+	inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
 	if (get_nr_swap_pages() > 0)
-		inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON);
+		inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
 	if (sc->nr_reclaimed < pages_for_compaction &&
 			inactive_lru_pages > pages_for_compaction)
 		return true;
 
 	/* If compaction would go ahead or the allocation would succeed, stop */
-	switch (compaction_suitable(zone, sc->order, 0, 0)) {
-	case COMPACT_PARTIAL:
-	case COMPACT_CONTINUE:
-		return false;
-	default:
-		return true;
+	for (z = 0; z <= sc->reclaim_idx; z++) {
+		struct zone *zone = &pgdat->node_zones[z];
+		if (!populated_zone(zone))
+			continue;
+
+		switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {
+		case COMPACT_PARTIAL:
+		case COMPACT_CONTINUE:
+			return false;
+		default:
+			/* check next zone */
+			;
+		}
 	}
+	return true;
 }
 
-static bool shrink_zone(struct zone *zone, struct scan_control *sc,
-			bool is_classzone)
+static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 {
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long nr_reclaimed, nr_scanned;
@@ -2379,10 +2534,10 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 	do {
 		struct mem_cgroup *root = sc->target_mem_cgroup;
 		struct mem_cgroup_reclaim_cookie reclaim = {
-			.zone = zone,
+			.pgdat = pgdat,
 			.priority = sc->priority,
 		};
-		unsigned long zone_lru_pages = 0;
+		unsigned long node_lru_pages = 0;
 		struct mem_cgroup *memcg;
 
 		nr_reclaimed = sc->nr_reclaimed;
@@ -2403,11 +2558,11 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 			reclaimed = sc->nr_reclaimed;
 			scanned = sc->nr_scanned;
 
-			shrink_zone_memcg(zone, memcg, sc, &lru_pages);
-			zone_lru_pages += lru_pages;
+			shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
+			node_lru_pages += lru_pages;
 
-			if (memcg && is_classzone)
-				shrink_slab(sc->gfp_mask, zone_to_nid(zone),
+			if (!global_reclaim(sc))
+				shrink_slab(sc->gfp_mask, pgdat->node_id,
 					    memcg, sc->nr_scanned - scanned,
 					    lru_pages);
 
@@ -2419,7 +2574,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 			/*
 			 * Direct reclaim and kswapd have to scan all memory
 			 * cgroups to fulfill the overall scan target for the
-			 * zone.
+			 * node.
 			 *
 			 * Limit reclaim, on the other hand, only cares about
 			 * nr_to_reclaim pages to be reclaimed and it will
@@ -2437,10 +2592,10 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 		 * Shrink the slab caches in the same proportion that
 		 * the eligible LRU pages were scanned.
 		 */
-		if (global_reclaim(sc) && is_classzone)
-			shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL,
+		if (global_reclaim(sc))
+			shrink_slab(sc->gfp_mask, pgdat->node_id, NULL,
 				    sc->nr_scanned - nr_scanned,
-				    zone_lru_pages);
+				    node_lru_pages);
 
 		if (reclaim_state) {
 			sc->nr_reclaimed += reclaim_state->reclaimed_slab;
@@ -2455,7 +2610,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 		if (sc->nr_reclaimed - nr_reclaimed)
 			reclaimable = true;
 
-	} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
+	} while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
 					 sc->nr_scanned - nr_scanned, sc));
 
 	return reclaimable;
@@ -2465,9 +2620,9 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
  * Returns true if compaction should go ahead for a high-order request, or
  * the high-order allocation would succeed without compaction.
  */
-static inline bool compaction_ready(struct zone *zone, int order, int classzone_idx)
+static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
 {
-	unsigned long balance_gap, watermark;
+	unsigned long watermark;
 	bool watermark_ok;
 
 	/*
@@ -2476,23 +2631,21 @@ static inline bool compaction_ready(struct zone *zone, int order, int classzone_
 	 * there is a buffer of free pages available to give compaction
 	 * a reasonable chance of completing and allocating the page
 	 */
-	balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP(
-			zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO));
-	watermark = high_wmark_pages(zone) + balance_gap + (2UL << order);
-	watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, classzone_idx);
+	watermark = high_wmark_pages(zone) + (2UL << sc->order);
+	watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx);
 
 	/*
 	 * If compaction is deferred, reclaim up to a point where
 	 * compaction will have a chance of success when re-enabled
 	 */
-	if (compaction_deferred(zone, order))
+	if (compaction_deferred(zone, sc->order))
 		return watermark_ok;
 
 	/*
 	 * If compaction is not ready to start and allocation is not likely
 	 * to succeed without it, then keep reclaiming.
 	 */
-	if (compaction_suitable(zone, order, 0, classzone_idx) == COMPACT_SKIPPED)
+	if (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx) == COMPACT_SKIPPED)
 		return false;
 
 	return watermark_ok;
@@ -2503,14 +2656,6 @@ static inline bool compaction_ready(struct zone *zone, int order, int classzone_
  * try to reclaim pages from zones which will satisfy the caller's allocation
  * request.
  *
- * We reclaim from a zone even if that zone is over high_wmark_pages(zone).
- * Because:
- * a) The caller may be trying to free *extra* pages to satisfy a higher-order
- *    allocation or
- * b) The target zone may be at high_wmark_pages(zone) but the lower zones
- *    must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
- *    zone defense algorithm.
- *
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
@@ -2521,7 +2666,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
 	gfp_t orig_mask;
-	enum zone_type requested_highidx = gfp_zone(sc->gfp_mask);
+	pg_data_t *last_pgdat = NULL;
 
 	/*
 	 * If the number of buffer_heads in the machine exceeds the maximum
@@ -2529,21 +2674,13 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	 * highmem pages could be pinning lowmem pages storing buffer_heads
 	 */
 	orig_mask = sc->gfp_mask;
-	if (buffer_heads_over_limit)
+	if (buffer_heads_over_limit) {
 		sc->gfp_mask |= __GFP_HIGHMEM;
+		sc->reclaim_idx = gfp_zone(sc->gfp_mask);
+	}
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-					gfp_zone(sc->gfp_mask), sc->nodemask) {
-		enum zone_type classzone_idx;
-
-		if (!populated_zone(zone))
-			continue;
-
-		classzone_idx = requested_highidx;
-		while (!populated_zone(zone->zone_pgdat->node_zones +
-							classzone_idx))
-			classzone_idx--;
-
+					sc->reclaim_idx, sc->nodemask) {
 		/*
 		 * Take care memory controller reclaiming has small influence
 		 * to global LRU.
@@ -2554,7 +2691,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 				continue;
 
 			if (sc->priority != DEF_PRIORITY &&
-			    !zone_reclaimable(zone))
+			    !pgdat_reclaimable(zone->zone_pgdat))
 				continue;	/* Let kswapd poll it */
 
 			/*
@@ -2568,12 +2705,20 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			 */
 			if (IS_ENABLED(CONFIG_COMPACTION) &&
 			    sc->order > PAGE_ALLOC_COSTLY_ORDER &&
-			    zonelist_zone_idx(z) <= requested_highidx &&
-			    compaction_ready(zone, sc->order, requested_highidx)) {
+			    compaction_ready(zone, sc)) {
 				sc->compaction_ready = true;
 				continue;
 			}
 
+			/*
+			 * Shrink each node in the zonelist once. If the
+			 * zonelist is ordered by zone (not the default) then a
+			 * node may be shrunk multiple times but in that case
+			 * the user prefers lower zones being preserved.
+			 */
+			if (zone->zone_pgdat == last_pgdat)
+				continue;
+
 			/*
 			 * This steals pages from memory cgroups over softlimit
 			 * and returns the number of reclaimed pages and
@@ -2581,7 +2726,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			 * and balancing, not for a memcg's limit.
 			 */
 			nr_soft_scanned = 0;
-			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat,
 						sc->order, sc->gfp_mask,
 						&nr_soft_scanned);
 			sc->nr_reclaimed += nr_soft_reclaimed;
@@ -2589,7 +2734,11 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			/* need some check for avoid more shrink_zone() */
 		}
 
-		shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
+		/* See comment about same check for global reclaim above */
+		if (zone->zone_pgdat == last_pgdat)
+			continue;
+		last_pgdat = zone->zone_pgdat;
+		shrink_node(zone->zone_pgdat, sc);
 	}
 
 	/*
@@ -2625,7 +2774,7 @@ retry:
 	delayacct_freepages_start();
 
 	if (global_reclaim(sc))
-		count_vm_event(ALLOCSTALL);
+		__count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1);
 
 	do {
 		vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
@@ -2692,7 +2841,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
 		if (!populated_zone(zone) ||
-		    zone_reclaimable_pages(zone) == 0)
+		    pgdat_reclaimable_pages(pgdat) == 0)
 			continue;
 
 		pfmemalloc_reserve += min_wmark_pages(zone);
@@ -2707,7 +2856,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	/* kswapd must be awake if processes are being throttled */
 	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
-		pgdat->classzone_idx = min(pgdat->classzone_idx,
+		pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
 						(enum zone_type)ZONE_NORMAL);
 		wake_up_interruptible(&pgdat->kswapd_wait);
 	}
@@ -2815,6 +2964,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	struct scan_control sc = {
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
+		.reclaim_idx = gfp_zone(gfp_mask),
 		.order = order,
 		.nodemask = nodemask,
 		.priority = DEF_PRIORITY,
@@ -2833,7 +2983,8 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 
 	trace_mm_vmscan_direct_reclaim_begin(order,
 				sc.may_writepage,
-				gfp_mask);
+				gfp_mask,
+				sc.reclaim_idx);
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
@@ -2844,9 +2995,9 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 
 #ifdef CONFIG_MEMCG
 
-unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
+unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 						gfp_t gfp_mask, bool noswap,
-						struct zone *zone,
+						pg_data_t *pgdat,
 						unsigned long *nr_scanned)
 {
 	struct scan_control sc = {
@@ -2854,6 +3005,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 		.target_mem_cgroup = memcg,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
+		.reclaim_idx = MAX_NR_ZONES - 1,
 		.may_swap = !noswap,
 	};
 	unsigned long lru_pages;
@@ -2863,16 +3015,17 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
 						      sc.may_writepage,
-						      sc.gfp_mask);
+						      sc.gfp_mask,
+						      sc.reclaim_idx);
 
 	/*
 	 * NOTE: Although we can get the priority field, using it
 	 * here is not a good idea, since it limits the pages we can scan.
-	 * if we don't reclaim here, the shrink_zone from balance_pgdat
+	 * if we don't reclaim here, the shrink_node from balance_pgdat
 	 * will pick up pages from other mem cgroup's as well. We hack
 	 * the priority and make it zero.
 	 */
-	shrink_zone_memcg(zone, memcg, &sc, &lru_pages);
+	shrink_node_memcg(pgdat, memcg, &sc, &lru_pages);
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
 
@@ -2892,6 +3045,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
 		.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 				(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
+		.reclaim_idx = MAX_NR_ZONES - 1,
 		.target_mem_cgroup = memcg,
 		.priority = DEF_PRIORITY,
 		.may_writepage = !laptop_mode,
@@ -2910,7 +3064,8 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 
 	trace_mm_vmscan_memcg_reclaim_begin(0,
 					    sc.may_writepage,
-					    sc.gfp_mask);
+					    sc.gfp_mask,
+					    sc.reclaim_idx);
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
@@ -2920,7 +3075,8 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 }
 #endif
 
-static void age_active_anon(struct zone *zone, struct scan_control *sc)
+static void age_active_anon(struct pglist_data *pgdat,
+				struct scan_control *sc)
 {
 	struct mem_cgroup *memcg;
 
@@ -2929,9 +3085,9 @@ static void age_active_anon(struct zone *zone, struct scan_control *sc)
 
 	memcg = mem_cgroup_iter(NULL, NULL, NULL);
 	do {
-		struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+		struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
 
-		if (inactive_list_is_low(lruvec, false))
+		if (inactive_list_is_low(lruvec, false, sc))
 			shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 					   sc, LRU_ACTIVE_ANON);
 
@@ -2939,82 +3095,21 @@ static void age_active_anon(struct zone *zone, struct scan_control *sc)
 	} while (memcg);
 }
 
-static bool zone_balanced(struct zone *zone, int order, bool highorder,
-			unsigned long balance_gap, int classzone_idx)
+static bool zone_balanced(struct zone *zone, int order, int classzone_idx)
 {
-	unsigned long mark = high_wmark_pages(zone) + balance_gap;
+	unsigned long mark = high_wmark_pages(zone);
+
+	if (!zone_watermark_ok_safe(zone, order, mark, classzone_idx))
+		return false;
 
 	/*
-	 * When checking from pgdat_balanced(), kswapd should stop and sleep
-	 * when it reaches the high order-0 watermark and let kcompactd take
-	 * over. Other callers such as wakeup_kswapd() want to determine the
-	 * true high-order watermark.
+	 * If any eligible zone is balanced then the node is not considered
+	 * to be congested or dirty
 	 */
-	if (IS_ENABLED(CONFIG_COMPACTION) && !highorder) {
-		mark += (1UL << order);
-		order = 0;
-	}
-
-	return zone_watermark_ok_safe(zone, order, mark, classzone_idx);
-}
-
-/*
- * pgdat_balanced() is used when checking if a node is balanced.
- *
- * For order-0, all zones must be balanced!
- *
- * For high-order allocations only zones that meet watermarks and are in a
- * zone allowed by the callers classzone_idx are added to balanced_pages. The
- * total of balanced pages must be at least 25% of the zones allowed by
- * classzone_idx for the node to be considered balanced. Forcing all zones to
- * be balanced for high orders can cause excessive reclaim when there are
- * imbalanced zones.
- * The choice of 25% is due to
- *   o a 16M DMA zone that is balanced will not balance a zone on any
- *     reasonable sized machine
- *   o On all other machines, the top zone must be at least a reasonable
- *     percentage of the middle zones. For example, on 32-bit x86, highmem
- *     would need to be at least 256M for it to be balance a whole node.
- *     Similarly, on x86-64 the Normal zone would need to be at least 1G
- *     to balance a node on its own. These seemed like reasonable ratios.
- */
-static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
-{
-	unsigned long managed_pages = 0;
-	unsigned long balanced_pages = 0;
-	int i;
-
-	/* Check the watermark levels */
-	for (i = 0; i <= classzone_idx; i++) {
-		struct zone *zone = pgdat->node_zones + i;
-
-		if (!populated_zone(zone))
-			continue;
-
-		managed_pages += zone->managed_pages;
-
-		/*
-		 * A special case here:
-		 *
-		 * balance_pgdat() skips over all_unreclaimable after
-		 * DEF_PRIORITY. Effectively, it considers them balanced so
-		 * they must be considered balanced here as well!
-		 */
-		if (!zone_reclaimable(zone)) {
-			balanced_pages += zone->managed_pages;
-			continue;
-		}
+	clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags);
+	clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags);
 
-		if (zone_balanced(zone, order, false, 0, i))
-			balanced_pages += zone->managed_pages;
-		else if (!order)
-			return false;
-	}
-
-	if (order)
-		return balanced_pages >= (managed_pages >> 2);
-	else
-		return true;
+	return true;
 }
 
 /*
@@ -3023,12 +3118,9 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
  *
  * Returns true if kswapd is ready to sleep
  */
-static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
-					int classzone_idx)
+static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 {
-	/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
-	if (remaining)
-		return false;
+	int i;
 
 	/*
 	 * The throttled processes are normally woken up in balance_pgdat() as
@@ -3046,91 +3138,81 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 	if (waitqueue_active(&pgdat->pfmemalloc_wait))
 		wake_up_all(&pgdat->pfmemalloc_wait);
 
-	return pgdat_balanced(pgdat, order, classzone_idx);
+	for (i = 0; i <= classzone_idx; i++) {
+		struct zone *zone = pgdat->node_zones + i;
+
+		if (!populated_zone(zone))
+			continue;
+
+		if (!zone_balanced(zone, order, classzone_idx))
+			return false;
+	}
+
+	return true;
 }
 
 /*
- * kswapd shrinks the zone by the number of pages required to reach
- * the high watermark.
+ * kswapd shrinks a node of pages that are at or below the highest usable
+ * zone that is currently unbalanced.
  *
  * Returns true if kswapd scanned at least the requested number of pages to
  * reclaim or if the lack of progress was due to pages under writeback.
  * This is used to determine if the scanning priority needs to be raised.
  */
-static bool kswapd_shrink_zone(struct zone *zone,
-			       int classzone_idx,
+static bool kswapd_shrink_node(pg_data_t *pgdat,
 			       struct scan_control *sc)
 {
-	unsigned long balance_gap;
-	bool lowmem_pressure;
+	struct zone *zone;
+	int z;
 
-	/* Reclaim above the high watermark. */
-	sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone));
+	/* Reclaim a number of pages proportional to the number of zones */
+	sc->nr_to_reclaim = 0;
+	for (z = 0; z <= sc->reclaim_idx; z++) {
+		zone = pgdat->node_zones + z;
+		if (!populated_zone(zone))
+			continue;
 
-	/*
-	 * We put equal pressure on every zone, unless one zone has way too
-	 * many pages free already. The "too many pages" is defined as the
-	 * high wmark plus a "gap" where the gap is either the low
-	 * watermark or 1% of the zone, whichever is smaller.
-	 */
-	balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP(
-			zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO));
+		sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
+	}
 
 	/*
-	 * If there is no low memory pressure or the zone is balanced then no
-	 * reclaim is necessary
+	 * Historically care was taken to put equal pressure on all zones but
+	 * now pressure is applied based on node LRU order.
 	 */
-	lowmem_pressure = (buffer_heads_over_limit && is_highmem(zone));
-	if (!lowmem_pressure && zone_balanced(zone, sc->order, false,
-						balance_gap, classzone_idx))
-		return true;
-
-	shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
-
-	clear_bit(ZONE_WRITEBACK, &zone->flags);
+	shrink_node(pgdat, sc);
 
 	/*
-	 * If a zone reaches its high watermark, consider it to be no longer
-	 * congested. It's possible there are dirty pages backed by congested
-	 * BDIs but as pressure is relieved, speculatively avoid congestion
-	 * waits.
+	 * Fragmentation may mean that the system cannot be rebalanced for
+	 * high-order allocations. If twice the allocation size has been
+	 * reclaimed then recheck watermarks only at order-0 to prevent
+	 * excessive reclaim. Assume that a process requested a high-order
+	 * can direct reclaim/compact.
 	 */
-	if (zone_reclaimable(zone) &&
-	    zone_balanced(zone, sc->order, false, 0, classzone_idx)) {
-		clear_bit(ZONE_CONGESTED, &zone->flags);
-		clear_bit(ZONE_DIRTY, &zone->flags);
-	}
+	if (sc->order && sc->nr_reclaimed >= 2UL << sc->order)
+		sc->order = 0;
 
 	return sc->nr_scanned >= sc->nr_to_reclaim;
 }
 
 /*
- * For kswapd, balance_pgdat() will work across all this node's zones until
- * they are all at high_wmark_pages(zone).
+ * For kswapd, balance_pgdat() will reclaim pages across a node from zones
+ * that are eligible for use by the caller until at least one zone is
+ * balanced.
  *
- * Returns the highest zone idx kswapd was reclaiming at
- *
- * There is special handling here for zones which are full of pinned pages.
- * This can happen if the pages are all mlocked, or if they are all used by
- * device drivers (say, ZONE_DMA).  Or if they are all in use by hugetlb.
- * What we do is to detect the case where all pages in the zone have been
- * scanned twice and there has been zero successful reclaim.  Mark the zone as
- * dead and from now on, only perform a short scan.  Basically we're polling
- * the zone for when the problem goes away.
+ * Returns the order kswapd finished reclaiming at.
  *
  * kswapd scans the zones in the highmem->normal->dma direction.  It skips
  * zones which have free_pages > high_wmark_pages(zone), but once a zone is
- * found to have free_pages <= high_wmark_pages(zone), we scan that zone and the
- * lower zones regardless of the number of free pages in the lower zones. This
- * interoperates with the page allocator fallback scheme to ensure that aging
- * of pages is balanced across the zones.
+ * found to have free_pages <= high_wmark_pages(zone), any page is that zone
+ * or lower is eligible for reclaim until at least one usable zone is
+ * balanced.
  */
 static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 {
 	int i;
-	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
+	struct zone *zone;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.order = order,
@@ -3145,100 +3227,77 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		bool raise_priority = true;
 
 		sc.nr_reclaimed = 0;
+		sc.reclaim_idx = classzone_idx;
 
 		/*
-		 * Scan in the highmem->dma direction for the highest
-		 * zone which needs scanning
+		 * If the number of buffer_heads exceeds the maximum allowed
+		 * then consider reclaiming from all zones. This has a dual
+		 * purpose -- on 64-bit systems it is expected that
+		 * buffer_heads are stripped during active rotation. On 32-bit
+		 * systems, highmem pages can pin lowmem memory and shrinking
+		 * buffers can relieve lowmem pressure. Reclaim may still not
+		 * go ahead if all eligible zones for the original allocation
+		 * request are balanced to avoid excessive reclaim from kswapd.
 		 */
-		for (i = pgdat->nr_zones - 1; i >= 0; i--) {
-			struct zone *zone = pgdat->node_zones + i;
-
-			if (!populated_zone(zone))
-				continue;
-
-			if (sc.priority != DEF_PRIORITY &&
-			    !zone_reclaimable(zone))
-				continue;
-
-			/*
-			 * Do some background aging of the anon list, to give
-			 * pages a chance to be referenced before reclaiming.
-			 */
-			age_active_anon(zone, &sc);
+		if (buffer_heads_over_limit) {
+			for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
+				zone = pgdat->node_zones + i;
+				if (!populated_zone(zone))
+					continue;
 
-			/*
-			 * If the number of buffer_heads in the machine
-			 * exceeds the maximum allowed level and this node
-			 * has a highmem zone, force kswapd to reclaim from
-			 * it to relieve lowmem pressure.
-			 */
-			if (buffer_heads_over_limit && is_highmem_idx(i)) {
-				end_zone = i;
+				sc.reclaim_idx = i;
 				break;
 			}
+		}
 
-			if (!zone_balanced(zone, order, false, 0, 0)) {
-				end_zone = i;
-				break;
-			} else {
-				/*
-				 * If balanced, clear the dirty and congested
-				 * flags
-				 */
-				clear_bit(ZONE_CONGESTED, &zone->flags);
-				clear_bit(ZONE_DIRTY, &zone->flags);
-			}
+		/*
+		 * Only reclaim if there are no eligible zones. Check from
+		 * high to low zone as allocations prefer higher zones.
+		 * Scanning from low to high zone would allow congestion to be
+		 * cleared during a very small window when a small low
+		 * zone was balanced even under extreme pressure when the
+		 * overall node may be congested. Note that sc.reclaim_idx
+		 * is not used as buffer_heads_over_limit may have adjusted
+		 * it.
+		 */
+		for (i = classzone_idx; i >= 0; i--) {
+			zone = pgdat->node_zones + i;
+			if (!populated_zone(zone))
+				continue;
+
+			if (zone_balanced(zone, sc.order, classzone_idx))
+				goto out;
 		}
 
-		if (i < 0)
-			goto out;
+		/*
+		 * Do some background aging of the anon list, to give
+		 * pages a chance to be referenced before reclaiming. All
+		 * pages are rotated regardless of classzone as this is
+		 * about consistent aging.
+		 */
+		age_active_anon(pgdat, &sc);
 
 		/*
 		 * If we're getting trouble reclaiming, start doing writepage
 		 * even in laptop mode.
 		 */
-		if (sc.priority < DEF_PRIORITY - 2)
+		if (sc.priority < DEF_PRIORITY - 2 || !pgdat_reclaimable(pgdat))
 			sc.may_writepage = 1;
 
+		/* Call soft limit reclaim before calling shrink_node. */
+		sc.nr_scanned = 0;
+		nr_soft_scanned = 0;
+		nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order,
+						sc.gfp_mask, &nr_soft_scanned);
+		sc.nr_reclaimed += nr_soft_reclaimed;
+
 		/*
-		 * Now scan the zone in the dma->highmem direction, stopping
-		 * at the last zone which needs scanning.
-		 *
-		 * We do this because the page allocator works in the opposite
-		 * direction.  This prevents the page allocator from allocating
-		 * pages behind kswapd's direction of progress, which would
-		 * cause too much scanning of the lower zones.
+		 * There should be no need to raise the scanning priority if
+		 * enough pages are already being scanned that that high
+		 * watermark would be met at 100% efficiency.
 		 */
-		for (i = 0; i <= end_zone; i++) {
-			struct zone *zone = pgdat->node_zones + i;
-
-			if (!populated_zone(zone))
-				continue;
-
-			if (sc.priority != DEF_PRIORITY &&
-			    !zone_reclaimable(zone))
-				continue;
-
-			sc.nr_scanned = 0;
-
-			nr_soft_scanned = 0;
-			/*
-			 * Call soft limit reclaim before calling shrink_zone.
-			 */
-			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
-							order, sc.gfp_mask,
-							&nr_soft_scanned);
-			sc.nr_reclaimed += nr_soft_reclaimed;
-
-			/*
-			 * There should be no need to raise the scanning
-			 * priority if enough pages are already being scanned
-			 * that that high watermark would be met at 100%
-			 * efficiency.
-			 */
-			if (kswapd_shrink_zone(zone, end_zone, &sc))
-				raise_priority = false;
-		}
+		if (kswapd_shrink_node(pgdat, &sc))
+			raise_priority = false;
 
 		/*
 		 * If the low watermark is met there is no need for processes
@@ -3259,19 +3318,20 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		 */
 		if (raise_priority || !sc.nr_reclaimed)
 			sc.priority--;
-	} while (sc.priority >= 1 &&
-			!pgdat_balanced(pgdat, order, classzone_idx));
+	} while (sc.priority >= 1);
 
 out:
 	/*
-	 * Return the highest zone idx we were reclaiming at so
-	 * prepare_kswapd_sleep() makes the same decisions as here.
+	 * Return the order kswapd stopped reclaiming at as
+	 * prepare_kswapd_sleep() takes it into account. If another caller
+	 * entered the allocator slow path while kswapd was awake, order will
+	 * remain at the higher level.
 	 */
-	return end_zone;
+	return sc.order;
 }
 
-static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
-				int classzone_idx, int balanced_classzone_idx)
+static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
+				unsigned int classzone_idx)
 {
 	long remaining = 0;
 	DEFINE_WAIT(wait);
@@ -3282,8 +3342,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
 	prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 
 	/* Try to sleep for a short interval */
-	if (prepare_kswapd_sleep(pgdat, order, remaining,
-						balanced_classzone_idx)) {
+	if (prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) {
 		/*
 		 * Compaction records what page blocks it recently failed to
 		 * isolate pages from and skips them in the future scanning.
@@ -3296,9 +3355,20 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
 		 * We have freed the memory, now we should compact it to make
 		 * allocation of the requested order possible.
 		 */
-		wakeup_kcompactd(pgdat, order, classzone_idx);
+		wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
 
 		remaining = schedule_timeout(HZ/10);
+
+		/*
+		 * If woken prematurely then reset kswapd_classzone_idx and
+		 * order. The values will either be from a wakeup request or
+		 * the previous request that slept prematurely.
+		 */
+		if (remaining) {
+			pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
+			pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order);
+		}
+
 		finish_wait(&pgdat->kswapd_wait, &wait);
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 	}
@@ -3307,8 +3377,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
 	 * After a short sleep, check if it was a premature sleep. If not, then
 	 * go fully to sleep until explicitly woken up.
 	 */
-	if (prepare_kswapd_sleep(pgdat, order, remaining,
-						balanced_classzone_idx)) {
+	if (!remaining &&
+	    prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) {
 		trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
 
 		/*
@@ -3349,9 +3419,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
  */
 static int kswapd(void *p)
 {
-	unsigned long order, new_order;
-	int classzone_idx, new_classzone_idx;
-	int balanced_classzone_idx;
+	unsigned int alloc_order, reclaim_order, classzone_idx;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
 
@@ -3381,38 +3449,20 @@ static int kswapd(void *p)
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 	set_freezable();
 
-	order = new_order = 0;
-	classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
-	balanced_classzone_idx = classzone_idx;
+	pgdat->kswapd_order = alloc_order = reclaim_order = 0;
+	pgdat->kswapd_classzone_idx = classzone_idx = 0;
 	for ( ; ; ) {
 		bool ret;
 
-		/*
-		 * While we were reclaiming, there might have been another
-		 * wakeup, so check the values.
-		 */
-		new_order = pgdat->kswapd_max_order;
-		new_classzone_idx = pgdat->classzone_idx;
-		pgdat->kswapd_max_order =  0;
-		pgdat->classzone_idx = pgdat->nr_zones - 1;
+kswapd_try_sleep:
+		kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
+					classzone_idx);
 
-		if (order < new_order || classzone_idx > new_classzone_idx) {
-			/*
-			 * Don't sleep if someone wants a larger 'order'
-			 * allocation or has tigher zone constraints
-			 */
-			order = new_order;
-			classzone_idx = new_classzone_idx;
-		} else {
-			kswapd_try_to_sleep(pgdat, order, classzone_idx,
-						balanced_classzone_idx);
-			order = pgdat->kswapd_max_order;
-			classzone_idx = pgdat->classzone_idx;
-			new_order = order;
-			new_classzone_idx = classzone_idx;
-			pgdat->kswapd_max_order = 0;
-			pgdat->classzone_idx = pgdat->nr_zones - 1;
-		}
+		/* Read the new order and classzone_idx */
+		alloc_order = reclaim_order = pgdat->kswapd_order;
+		classzone_idx = pgdat->kswapd_classzone_idx;
+		pgdat->kswapd_order = 0;
+		pgdat->kswapd_classzone_idx = 0;
 
 		ret = try_to_freeze();
 		if (kthread_should_stop())
@@ -3422,11 +3472,25 @@ static int kswapd(void *p)
 		 * We can speed up thawing tasks if we don't call balance_pgdat
 		 * after returning from the refrigerator
 		 */
-		if (!ret) {
-			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
-			balanced_classzone_idx = balance_pgdat(pgdat, order,
-								classzone_idx);
-		}
+		if (ret)
+			continue;
+
+		/*
+		 * Reclaim begins at the requested order but if a high-order
+		 * reclaim fails then kswapd falls back to reclaiming for
+		 * order-0. If that happens, kswapd will consider sleeping
+		 * for the order it finished reclaiming at (reclaim_order)
+		 * but kcompactd is woken to compact for the original
+		 * request (alloc_order).
+		 */
+		trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx,
+						alloc_order);
+		reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
+		if (reclaim_order < alloc_order)
+			goto kswapd_try_sleep;
+
+		alloc_order = reclaim_order = pgdat->kswapd_order;
+		classzone_idx = pgdat->kswapd_classzone_idx;
 	}
 
 	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
@@ -3442,6 +3506,7 @@ static int kswapd(void *p)
 void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
+	int z;
 
 	if (!populated_zone(zone))
 		return;
@@ -3449,14 +3514,20 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
 		return;
 	pgdat = zone->zone_pgdat;
-	if (pgdat->kswapd_max_order < order) {
-		pgdat->kswapd_max_order = order;
-		pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
-	}
+	pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
+	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
-	if (zone_balanced(zone, order, true, 0, 0))
-		return;
+
+	/* Only wake kswapd if all zones are unbalanced */
+	for (z = 0; z <= classzone_idx; z++) {
+		zone = pgdat->node_zones + z;
+		if (!populated_zone(zone))
+			continue;
+
+		if (zone_balanced(zone, order, classzone_idx))
+			return;
+	}
 
 	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
 	wake_up_interruptible(&pgdat->kswapd_wait);
@@ -3477,6 +3548,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 	struct scan_control sc = {
 		.nr_to_reclaim = nr_to_reclaim,
 		.gfp_mask = GFP_HIGHUSER_MOVABLE,
+		.reclaim_idx = MAX_NR_ZONES - 1,
 		.priority = DEF_PRIORITY,
 		.may_writepage = 1,
 		.may_unmap = 1,
@@ -3578,12 +3650,12 @@ module_init(kswapd_init)
 
 #ifdef CONFIG_NUMA
 /*
- * Zone reclaim mode
+ * Node reclaim mode
  *
- * If non-zero call zone_reclaim when the number of free pages falls below
+ * If non-zero call node_reclaim when the number of free pages falls below
  * the watermarks.
  */
-int zone_reclaim_mode __read_mostly;
+int node_reclaim_mode __read_mostly;
 
 #define RECLAIM_OFF 0
 #define RECLAIM_ZONE (1<<0)	/* Run shrink_inactive_list on the zone */
@@ -3591,14 +3663,14 @@ int zone_reclaim_mode __read_mostly;
 #define RECLAIM_UNMAP (1<<2)	/* Unmap pages during reclaim */
 
 /*
- * Priority for ZONE_RECLAIM. This determines the fraction of pages
+ * Priority for NODE_RECLAIM. This determines the fraction of pages
  * of a node considered for each zone_reclaim. 4 scans 1/16th of
  * a zone.
  */
-#define ZONE_RECLAIM_PRIORITY 4
+#define NODE_RECLAIM_PRIORITY 4
 
 /*
- * Percentage of pages in a zone that must be unmapped for zone_reclaim to
+ * Percentage of pages in a zone that must be unmapped for node_reclaim to
  * occur.
  */
 int sysctl_min_unmapped_ratio = 1;
@@ -3609,11 +3681,11 @@ int sysctl_min_unmapped_ratio = 1;
  */
 int sysctl_min_slab_ratio = 5;
 
-static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
+static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat)
 {
-	unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED);
-	unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) +
-		zone_page_state(zone, NR_ACTIVE_FILE);
+	unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED);
+	unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) +
+		node_page_state(pgdat, NR_ACTIVE_FILE);
 
 	/*
 	 * It's possible for there to be more file mapped pages than
@@ -3624,7 +3696,7 @@ static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
 }
 
 /* Work out how many page cache pages we can reclaim in this reclaim_mode */
-static unsigned long zone_pagecache_reclaimable(struct zone *zone)
+static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat)
 {
 	unsigned long nr_pagecache_reclaimable;
 	unsigned long delta = 0;
@@ -3632,17 +3704,17 @@ static unsigned long zone_pagecache_reclaimable(struct zone *zone)
 	/*
 	 * If RECLAIM_UNMAP is set, then all file pages are considered
 	 * potentially reclaimable. Otherwise, we have to worry about
-	 * pages like swapcache and zone_unmapped_file_pages() provides
+	 * pages like swapcache and node_unmapped_file_pages() provides
 	 * a better estimate
 	 */
-	if (zone_reclaim_mode & RECLAIM_UNMAP)
-		nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES);
+	if (node_reclaim_mode & RECLAIM_UNMAP)
+		nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES);
 	else
-		nr_pagecache_reclaimable = zone_unmapped_file_pages(zone);
+		nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat);
 
 	/* If we can't clean pages, remove dirty pages from consideration */
-	if (!(zone_reclaim_mode & RECLAIM_WRITE))
-		delta += zone_page_state(zone, NR_FILE_DIRTY);
+	if (!(node_reclaim_mode & RECLAIM_WRITE))
+		delta += node_page_state(pgdat, NR_FILE_DIRTY);
 
 	/* Watch for any possible underflows due to delta */
 	if (unlikely(delta > nr_pagecache_reclaimable))
@@ -3652,22 +3724,24 @@ static unsigned long zone_pagecache_reclaimable(struct zone *zone)
 }
 
 /*
- * Try to free up some pages from this zone through reclaim.
+ * Try to free up some pages from this node through reclaim.
  */
-static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 {
 	/* Minimum pages needed in order to stay on node */
 	const unsigned long nr_pages = 1 << order;
 	struct task_struct *p = current;
 	struct reclaim_state reclaim_state;
+	int classzone_idx = gfp_zone(gfp_mask);
 	struct scan_control sc = {
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
 		.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
 		.order = order,
-		.priority = ZONE_RECLAIM_PRIORITY,
-		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
-		.may_unmap = !!(zone_reclaim_mode & RECLAIM_UNMAP),
+		.priority = NODE_RECLAIM_PRIORITY,
+		.may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
+		.may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
 		.may_swap = 1,
+		.reclaim_idx = classzone_idx,
 	};
 
 	cond_resched();
@@ -3681,13 +3755,13 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) {
+	if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) {
 		/*
 		 * Free memory by calling shrink zone with increasing
 		 * priorities until we have enough memory freed.
 		 */
 		do {
-			shrink_zone(zone, &sc, true);
+			shrink_node(pgdat, &sc);
 		} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
 	}
 
@@ -3697,49 +3771,47 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	return sc.nr_reclaimed >= nr_pages;
 }
 
-int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 {
-	int node_id;
 	int ret;
 
 	/*
-	 * Zone reclaim reclaims unmapped file backed pages and
+	 * Node reclaim reclaims unmapped file backed pages and
 	 * slab pages if we are over the defined limits.
 	 *
 	 * A small portion of unmapped file backed pages is needed for
 	 * file I/O otherwise pages read by file I/O will be immediately
-	 * thrown out if the zone is overallocated. So we do not reclaim
-	 * if less than a specified percentage of the zone is used by
+	 * thrown out if the node is overallocated. So we do not reclaim
+	 * if less than a specified percentage of the node is used by
 	 * unmapped file backed pages.
 	 */
-	if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
-	    zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
-		return ZONE_RECLAIM_FULL;
+	if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
+	    sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
+		return NODE_RECLAIM_FULL;
 
-	if (!zone_reclaimable(zone))
-		return ZONE_RECLAIM_FULL;
+	if (!pgdat_reclaimable(pgdat))
+		return NODE_RECLAIM_FULL;
 
 	/*
 	 * Do not scan if the allocation should not be delayed.
 	 */
 	if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC))
-		return ZONE_RECLAIM_NOSCAN;
+		return NODE_RECLAIM_NOSCAN;
 
 	/*
-	 * Only run zone reclaim on the local zone or on zones that do not
+	 * Only run node reclaim on the local node or on nodes that do not
 	 * have associated processors. This will favor the local processor
 	 * over remote processors and spread off node memory allocations
 	 * as wide as possible.
 	 */
-	node_id = zone_to_nid(zone);
-	if (node_state(node_id, N_CPU) && node_id != numa_node_id())
-		return ZONE_RECLAIM_NOSCAN;
+	if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id())
+		return NODE_RECLAIM_NOSCAN;
 
-	if (test_and_set_bit(ZONE_RECLAIM_LOCKED, &zone->flags))
-		return ZONE_RECLAIM_NOSCAN;
+	if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags))
+		return NODE_RECLAIM_NOSCAN;
 
-	ret = __zone_reclaim(zone, gfp_mask, order);
-	clear_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
+	ret = __node_reclaim(pgdat, gfp_mask, order);
+	clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags);
 
 	if (!ret)
 		count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
@@ -3778,24 +3850,23 @@ int page_evictable(struct page *page)
 void check_move_unevictable_pages(struct page **pages, int nr_pages)
 {
 	struct lruvec *lruvec;
-	struct zone *zone = NULL;
+	struct pglist_data *pgdat = NULL;
 	int pgscanned = 0;
 	int pgrescued = 0;
 	int i;
 
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page = pages[i];
-		struct zone *pagezone;
+		struct pglist_data *pagepgdat = page_pgdat(page);
 
 		pgscanned++;
-		pagezone = page_zone(page);
-		if (pagezone != zone) {
-			if (zone)
-				spin_unlock_irq(&zone->lru_lock);
-			zone = pagezone;
-			spin_lock_irq(&zone->lru_lock);
+		if (pagepgdat != pgdat) {
+			if (pgdat)
+				spin_unlock_irq(&pgdat->lru_lock);
+			pgdat = pagepgdat;
+			spin_lock_irq(&pgdat->lru_lock);
 		}
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 		if (!PageLRU(page) || !PageUnevictable(page))
 			continue;
@@ -3811,10 +3882,10 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages)
 		}
 	}
 
-	if (zone) {
+	if (pgdat) {
 		__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
 		__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
-		spin_unlock_irq(&zone->lru_lock);
+		spin_unlock_irq(&pgdat->lru_lock);
 	}
 }
 #endif /* CONFIG_SHMEM */

mm/vmstat.c

@@ -86,8 +86,10 @@ void vm_events_fold_cpu(int cpu)
  *
  * vm_stat contains the global counters
  */
-atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
-EXPORT_SYMBOL(vm_stat);
+atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
+atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp;
+EXPORT_SYMBOL(vm_zone_stat);
+EXPORT_SYMBOL(vm_node_stat);
 
 #ifdef CONFIG_SMP
 
@@ -167,19 +169,36 @@ int calculate_normal_threshold(struct zone *zone)
  */
 void refresh_zone_stat_thresholds(void)
 {
+	struct pglist_data *pgdat;
 	struct zone *zone;
 	int cpu;
 	int threshold;
 
+	/* Zero current pgdat thresholds */
+	for_each_online_pgdat(pgdat) {
+		for_each_online_cpu(cpu) {
+			per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold = 0;
+		}
+	}
+
 	for_each_populated_zone(zone) {
+		struct pglist_data *pgdat = zone->zone_pgdat;
 		unsigned long max_drift, tolerate_drift;
 
 		threshold = calculate_normal_threshold(zone);
 
-		for_each_online_cpu(cpu)
+		for_each_online_cpu(cpu) {
+			int pgdat_threshold;
+
 			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
 							= threshold;
 
+			/* Base nodestat threshold on the largest populated zone. */
+			pgdat_threshold = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold;
+			per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold
+				= max(threshold, pgdat_threshold);
+		}
+
 		/*
 		 * Only set percpu_drift_mark if there is a danger that
 		 * NR_FREE_PAGES reports the low watermark is ok when in fact
@@ -238,6 +257,26 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
 }
 EXPORT_SYMBOL(__mod_zone_page_state);
 
+void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
+				long delta)
+{
+	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+	s8 __percpu *p = pcp->vm_node_stat_diff + item;
+	long x;
+	long t;
+
+	x = delta + __this_cpu_read(*p);
+
+	t = __this_cpu_read(pcp->stat_threshold);
+
+	if (unlikely(x > t || x < -t)) {
+		node_page_state_add(x, pgdat, item);
+		x = 0;
+	}
+	__this_cpu_write(*p, x);
+}
+EXPORT_SYMBOL(__mod_node_page_state);
+
 /*
  * Optimized increment and decrement functions.
  *
@@ -277,12 +316,34 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 	}
 }
 
+void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+	s8 __percpu *p = pcp->vm_node_stat_diff + item;
+	s8 v, t;
+
+	v = __this_cpu_inc_return(*p);
+	t = __this_cpu_read(pcp->stat_threshold);
+	if (unlikely(v > t)) {
+		s8 overstep = t >> 1;
+
+		node_page_state_add(v + overstep, pgdat, item);
+		__this_cpu_write(*p, -overstep);
+	}
+}
+
 void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
 {
 	__inc_zone_state(page_zone(page), item);
 }
 EXPORT_SYMBOL(__inc_zone_page_state);
 
+void __inc_node_page_state(struct page *page, enum node_stat_item item)
+{
+	__inc_node_state(page_pgdat(page), item);
+}
+EXPORT_SYMBOL(__inc_node_page_state);
+
 void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 {
 	struct per_cpu_pageset __percpu *pcp = zone->pageset;
@@ -299,12 +360,34 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 	}
 }
 
+void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+	s8 __percpu *p = pcp->vm_node_stat_diff + item;
+	s8 v, t;
+
+	v = __this_cpu_dec_return(*p);
+	t = __this_cpu_read(pcp->stat_threshold);
+	if (unlikely(v < - t)) {
+		s8 overstep = t >> 1;
+
+		node_page_state_add(v - overstep, pgdat, item);
+		__this_cpu_write(*p, overstep);
+	}
+}
+
 void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
 {
 	__dec_zone_state(page_zone(page), item);
 }
 EXPORT_SYMBOL(__dec_zone_page_state);
 
+void __dec_node_page_state(struct page *page, enum node_stat_item item)
+{
+	__dec_node_state(page_pgdat(page), item);
+}
+EXPORT_SYMBOL(__dec_node_page_state);
+
 #ifdef CONFIG_HAVE_CMPXCHG_LOCAL
 /*
  * If we have cmpxchg_local support then we do not need to incur the overhead
@@ -318,8 +401,8 @@ EXPORT_SYMBOL(__dec_zone_page_state);
  *     1       Overstepping half of threshold
  *     -1      Overstepping minus half of threshold
 */
-static inline void mod_state(struct zone *zone, enum zone_stat_item item,
-			     long delta, int overstep_mode)
+static inline void mod_zone_state(struct zone *zone,
+       enum zone_stat_item item, long delta, int overstep_mode)
 {
 	struct per_cpu_pageset __percpu *pcp = zone->pageset;
 	s8 __percpu *p = pcp->vm_stat_diff + item;
@@ -359,26 +442,83 @@ static inline void mod_state(struct zone *zone, enum zone_stat_item item,
 void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
 			 long delta)
 {
-	mod_state(zone, item, delta, 0);
+	mod_zone_state(zone, item, delta, 0);
 }
 EXPORT_SYMBOL(mod_zone_page_state);
 
-void inc_zone_state(struct zone *zone, enum zone_stat_item item)
-{
-	mod_state(zone, item, 1, 1);
-}
-
 void inc_zone_page_state(struct page *page, enum zone_stat_item item)
 {
-	mod_state(page_zone(page), item, 1, 1);
+	mod_zone_state(page_zone(page), item, 1, 1);
 }
 EXPORT_SYMBOL(inc_zone_page_state);
 
 void dec_zone_page_state(struct page *page, enum zone_stat_item item)
 {
-	mod_state(page_zone(page), item, -1, -1);
+	mod_zone_state(page_zone(page), item, -1, -1);
 }
 EXPORT_SYMBOL(dec_zone_page_state);
+
+static inline void mod_node_state(struct pglist_data *pgdat,
+       enum node_stat_item item, int delta, int overstep_mode)
+{
+	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+	s8 __percpu *p = pcp->vm_node_stat_diff + item;
+	long o, n, t, z;
+
+	do {
+		z = 0;  /* overflow to node counters */
+
+		/*
+		 * The fetching of the stat_threshold is racy. We may apply
+		 * a counter threshold to the wrong the cpu if we get
+		 * rescheduled while executing here. However, the next
+		 * counter update will apply the threshold again and
+		 * therefore bring the counter under the threshold again.
+		 *
+		 * Most of the time the thresholds are the same anyways
+		 * for all cpus in a node.
+		 */
+		t = this_cpu_read(pcp->stat_threshold);
+
+		o = this_cpu_read(*p);
+		n = delta + o;
+
+		if (n > t || n < -t) {
+			int os = overstep_mode * (t >> 1) ;
+
+			/* Overflow must be added to node counters */
+			z = n + os;
+			n = -os;
+		}
+	} while (this_cpu_cmpxchg(*p, o, n) != o);
+
+	if (z)
+		node_page_state_add(z, pgdat, item);
+}
+
+void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
+					long delta)
+{
+	mod_node_state(pgdat, item, delta, 0);
+}
+EXPORT_SYMBOL(mod_node_page_state);
+
+void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+	mod_node_state(pgdat, item, 1, 1);
+}
+
+void inc_node_page_state(struct page *page, enum node_stat_item item)
+{
+	mod_node_state(page_pgdat(page), item, 1, 1);
+}
+EXPORT_SYMBOL(inc_node_page_state);
+
+void dec_node_page_state(struct page *page, enum node_stat_item item)
+{
+	mod_node_state(page_pgdat(page), item, -1, -1);
+}
+EXPORT_SYMBOL(dec_node_page_state);
 #else
 /*
  * Use interrupt disable to serialize counter updates
@@ -394,15 +534,6 @@ void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
 }
 EXPORT_SYMBOL(mod_zone_page_state);
 
-void inc_zone_state(struct zone *zone, enum zone_stat_item item)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__inc_zone_state(zone, item);
-	local_irq_restore(flags);
-}
-
 void inc_zone_page_state(struct page *page, enum zone_stat_item item)
 {
 	unsigned long flags;
@@ -424,21 +555,69 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item)
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(dec_zone_page_state);
-#endif
 
+void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__inc_node_state(pgdat, item);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(inc_node_state);
+
+void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
+					long delta)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_node_page_state(pgdat, item, delta);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(mod_node_page_state);
+
+void inc_node_page_state(struct page *page, enum node_stat_item item)
+{
+	unsigned long flags;
+	struct pglist_data *pgdat;
+
+	pgdat = page_pgdat(page);
+	local_irq_save(flags);
+	__inc_node_state(pgdat, item);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(inc_node_page_state);
+
+void dec_node_page_state(struct page *page, enum node_stat_item item)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__dec_node_page_state(page, item);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(dec_node_page_state);
+#endif
 
 /*
  * Fold a differential into the global counters.
  * Returns the number of counters updated.
  */
-static int fold_diff(int *diff)
+static int fold_diff(int *zone_diff, int *node_diff)
 {
 	int i;
 	int changes = 0;
 
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		if (diff[i]) {
-			atomic_long_add(diff[i], &vm_stat[i]);
+		if (zone_diff[i]) {
+			atomic_long_add(zone_diff[i], &vm_zone_stat[i]);
+			changes++;
+	}
+
+	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+		if (node_diff[i]) {
+			atomic_long_add(node_diff[i], &vm_node_stat[i]);
 			changes++;
 	}
 	return changes;
@@ -462,9 +641,11 @@ static int fold_diff(int *diff)
  */
 static int refresh_cpu_vm_stats(bool do_pagesets)
 {
+	struct pglist_data *pgdat;
 	struct zone *zone;
 	int i;
-	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+	int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+	int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
 	int changes = 0;
 
 	for_each_populated_zone(zone) {
@@ -477,7 +658,7 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
 			if (v) {
 
 				atomic_long_add(v, &zone->vm_stat[i]);
-				global_diff[i] += v;
+				global_zone_diff[i] += v;
 #ifdef CONFIG_NUMA
 				/* 3 seconds idle till flush */
 				__this_cpu_write(p->expire, 3);
@@ -516,7 +697,22 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
 		}
 #endif
 	}
-	changes += fold_diff(global_diff);
+
+	for_each_online_pgdat(pgdat) {
+		struct per_cpu_nodestat __percpu *p = pgdat->per_cpu_nodestats;
+
+		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+			int v;
+
+			v = this_cpu_xchg(p->vm_node_stat_diff[i], 0);
+			if (v) {
+				atomic_long_add(v, &pgdat->vm_stat[i]);
+				global_node_diff[i] += v;
+			}
+		}
+	}
+
+	changes += fold_diff(global_zone_diff, global_node_diff);
 	return changes;
 }
 
@@ -527,9 +723,11 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
  */
 void cpu_vm_stats_fold(int cpu)
 {
+	struct pglist_data *pgdat;
 	struct zone *zone;
 	int i;
-	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+	int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+	int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
 
 	for_each_populated_zone(zone) {
 		struct per_cpu_pageset *p;
@@ -543,11 +741,27 @@ void cpu_vm_stats_fold(int cpu)
 				v = p->vm_stat_diff[i];
 				p->vm_stat_diff[i] = 0;
 				atomic_long_add(v, &zone->vm_stat[i]);
-				global_diff[i] += v;
+				global_zone_diff[i] += v;
 			}
 	}
 
-	fold_diff(global_diff);
+	for_each_online_pgdat(pgdat) {
+		struct per_cpu_nodestat *p;
+
+		p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu);
+
+		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+			if (p->vm_node_stat_diff[i]) {
+				int v;
+
+				v = p->vm_node_stat_diff[i];
+				p->vm_node_stat_diff[i] = 0;
+				atomic_long_add(v, &pgdat->vm_stat[i]);
+				global_node_diff[i] += v;
+			}
+	}
+
+	fold_diff(global_zone_diff, global_node_diff);
 }
 
 /*
@@ -563,16 +777,19 @@ void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset)
 			int v = pset->vm_stat_diff[i];
 			pset->vm_stat_diff[i] = 0;
 			atomic_long_add(v, &zone->vm_stat[i]);
-			atomic_long_add(v, &vm_stat[i]);
+			atomic_long_add(v, &vm_zone_stat[i]);
 		}
 }
 #endif
 
 #ifdef CONFIG_NUMA
 /*
- * Determine the per node value of a stat item.
+ * Determine the per node value of a stat item. This function
+ * is called frequently in a NUMA machine, so try to be as
+ * frugal as possible.
  */
-unsigned long node_page_state(int node, enum zone_stat_item item)
+unsigned long sum_zone_node_page_state(int node,
+				 enum zone_stat_item item)
 {
 	struct zone *zones = NODE_DATA(node)->node_zones;
 	int i;
@@ -584,6 +801,19 @@ unsigned long node_page_state(int node, enum zone_stat_item item)
 	return count;
 }
 
+/*
+ * Determine the per node value of a stat item.
+ */
+unsigned long node_page_state(struct pglist_data *pgdat,
+				enum node_stat_item item)
+{
+	long x = atomic_long_read(&pgdat->vm_stat[item]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
+}
 #endif
 
 #ifdef CONFIG_COMPACTION
@@ -691,33 +921,18 @@ int fragmentation_index(struct zone *zone, unsigned int order)
 const char * const vmstat_text[] = {
 	/* enum zone_stat_item countes */
 	"nr_free_pages",
-	"nr_alloc_batch",
-	"nr_inactive_anon",
-	"nr_active_anon",
-	"nr_inactive_file",
-	"nr_active_file",
-	"nr_unevictable",
+	"nr_zone_inactive_anon",
+	"nr_zone_active_anon",
+	"nr_zone_inactive_file",
+	"nr_zone_active_file",
+	"nr_zone_unevictable",
+	"nr_zone_write_pending",
 	"nr_mlock",
-	"nr_anon_pages",
-	"nr_mapped",
-	"nr_file_pages",
-	"nr_dirty",
-	"nr_writeback",
 	"nr_slab_reclaimable",
 	"nr_slab_unreclaimable",
 	"nr_page_table_pages",
 	"nr_kernel_stack",
-	"nr_unstable",
 	"nr_bounce",
-	"nr_vmscan_write",
-	"nr_vmscan_immediate_reclaim",
-	"nr_writeback_temp",
-	"nr_isolated_anon",
-	"nr_isolated_file",
-	"nr_shmem",
-	"nr_dirtied",
-	"nr_written",
-	"nr_pages_scanned",
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	"nr_zspages",
 #endif
@@ -729,13 +944,35 @@ const char * const vmstat_text[] = {
 	"numa_local",
 	"numa_other",
 #endif
+	"nr_free_cma",
+
+	/* Node-based counters */
+	"nr_inactive_anon",
+	"nr_active_anon",
+	"nr_inactive_file",
+	"nr_active_file",
+	"nr_unevictable",
+	"nr_isolated_anon",
+	"nr_isolated_file",
+	"nr_pages_scanned",
 	"workingset_refault",
 	"workingset_activate",
 	"workingset_nodereclaim",
-	"nr_anon_transparent_hugepages",
+	"nr_anon_pages",
+	"nr_mapped",
+	"nr_file_pages",
+	"nr_dirty",
+	"nr_writeback",
+	"nr_writeback_temp",
+	"nr_shmem",
 	"nr_shmem_hugepages",
 	"nr_shmem_pmdmapped",
-	"nr_free_cma",
+	"nr_anon_transparent_hugepages",
+	"nr_unstable",
+	"nr_vmscan_write",
+	"nr_vmscan_immediate_reclaim",
+	"nr_dirtied",
+	"nr_written",
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
@@ -749,6 +986,8 @@ const char * const vmstat_text[] = {
 	"pswpout",
 
 	TEXTS_FOR_ZONES("pgalloc")
+	TEXTS_FOR_ZONES("allocstall")
+	TEXTS_FOR_ZONES("pgskip")
 
 	"pgfree",
 	"pgactivate",
@@ -758,11 +997,11 @@ const char * const vmstat_text[] = {
 	"pgmajfault",
 	"pglazyfreed",
 
-	TEXTS_FOR_ZONES("pgrefill")
-	TEXTS_FOR_ZONES("pgsteal_kswapd")
-	TEXTS_FOR_ZONES("pgsteal_direct")
-	TEXTS_FOR_ZONES("pgscan_kswapd")
-	TEXTS_FOR_ZONES("pgscan_direct")
+	"pgrefill",
+	"pgsteal_kswapd",
+	"pgsteal_direct",
+	"pgscan_kswapd",
+	"pgscan_direct",
 	"pgscan_direct_throttle",
 
 #ifdef CONFIG_NUMA
@@ -774,7 +1013,6 @@ const char * const vmstat_text[] = {
 	"kswapd_low_wmark_hit_quickly",
 	"kswapd_high_wmark_hit_quickly",
 	"pageoutrun",
-	"allocstall",
 
 	"pgrotated",
 
@@ -1180,17 +1418,41 @@ static const struct file_operations pagetypeinfo_file_ops = {
 	.release	= seq_release,
 };
 
+static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone)
+{
+	int zid;
+
+	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+		struct zone *compare = &pgdat->node_zones[zid];
+
+		if (populated_zone(compare))
+			return zone == compare;
+	}
+
+	/* The zone must be somewhere! */
+	WARN_ON_ONCE(1);
+	return false;
+}
+
 static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 							struct zone *zone)
 {
 	int i;
 	seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
+	if (is_zone_first_populated(pgdat, zone)) {
+		seq_printf(m, "\n  per-node stats");
+		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+			seq_printf(m, "\n      %-12s %lu",
+				vmstat_text[i + NR_VM_ZONE_STAT_ITEMS],
+				node_page_state(pgdat, i));
+		}
+	}
 	seq_printf(m,
 		   "\n  pages free     %lu"
 		   "\n        min      %lu"
 		   "\n        low      %lu"
 		   "\n        high     %lu"
-		   "\n        scanned  %lu"
+		   "\n   node_scanned  %lu"
 		   "\n        spanned  %lu"
 		   "\n        present  %lu"
 		   "\n        managed  %lu",
@@ -1198,13 +1460,13 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   min_wmark_pages(zone),
 		   low_wmark_pages(zone),
 		   high_wmark_pages(zone),
-		   zone_page_state(zone, NR_PAGES_SCANNED),
+		   node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED),
 		   zone->spanned_pages,
 		   zone->present_pages,
 		   zone->managed_pages);
 
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		seq_printf(m, "\n    %-12s %lu", vmstat_text[i],
+		seq_printf(m, "\n      %-12s %lu", vmstat_text[i],
 				zone_page_state(zone, i));
 
 	seq_printf(m,
@@ -1234,12 +1496,12 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 #endif
 	}
 	seq_printf(m,
-		   "\n  all_unreclaimable: %u"
-		   "\n  start_pfn:         %lu"
-		   "\n  inactive_ratio:    %u",
-		   !zone_reclaimable(zone),
+		   "\n  node_unreclaimable:  %u"
+		   "\n  start_pfn:           %lu"
+		   "\n  node_inactive_ratio: %u",
+		   !pgdat_reclaimable(zone->zone_pgdat),
 		   zone->zone_start_pfn,
-		   zone->inactive_ratio);
+		   zone->zone_pgdat->inactive_ratio);
 	seq_putc(m, '\n');
 }
 
@@ -1287,6 +1549,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
 	if (*pos >= ARRAY_SIZE(vmstat_text))
 		return NULL;
 	stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) +
+			  NR_VM_NODE_STAT_ITEMS * sizeof(unsigned long) +
 			  NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long);
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
@@ -1301,6 +1564,10 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
 		v[i] = global_page_state(i);
 	v += NR_VM_ZONE_STAT_ITEMS;
 
+	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+		v[i] = global_node_page_state(i);
+	v += NR_VM_NODE_STAT_ITEMS;
+
 	global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,
 			    v + NR_DIRTY_THRESHOLD);
 	v += NR_VM_WRITEBACK_STAT_ITEMS;
@@ -1325,7 +1592,6 @@ static int vmstat_show(struct seq_file *m, void *arg)
 {
 	unsigned long *l = arg;
 	unsigned long off = l - (unsigned long *)m->private;
-
 	seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
 	return 0;
 }
@@ -1390,13 +1656,12 @@ int vmstat_refresh(struct ctl_table *table, int write,
 	if (err)
 		return err;
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
-		val = atomic_long_read(&vm_stat[i]);
+		val = atomic_long_read(&vm_zone_stat[i]);
 		if (val < 0) {
 			switch (i) {
-			case NR_ALLOC_BATCH:
 			case NR_PAGES_SCANNED:
 				/*
-				 * These are often seen to go negative in
+				 * This is often seen to go negative in
 				 * recent kernels, but not to go permanently
 				 * negative.  Whilst it would be nicer not to
 				 * have exceptions, rooting them out would be

mm/workingset.c

@@ -16,7 +16,7 @@
 /*
  *		Double CLOCK lists
  *
- * Per zone, two clock lists are maintained for file pages: the
+ * Per node, two clock lists are maintained for file pages: the
  * inactive and the active list.  Freshly faulted pages start out at
  * the head of the inactive list and page reclaim scans pages from the
  * tail.  Pages that are accessed multiple times on the inactive list
@@ -141,11 +141,11 @@
  *
  *		Implementation
  *
- * For each zone's file LRU lists, a counter for inactive evictions
- * and activations is maintained (zone->inactive_age).
+ * For each node's file LRU lists, a counter for inactive evictions
+ * and activations is maintained (node->inactive_age).
  *
  * On eviction, a snapshot of this counter (along with some bits to
- * identify the zone) is stored in the now empty page cache radix tree
+ * identify the node) is stored in the now empty page cache radix tree
  * slot of the evicted page.  This is called a shadow entry.
  *
  * On cache misses for which there are shadow entries, an eligible
@@ -153,7 +153,7 @@
  */
 
 #define EVICTION_SHIFT	(RADIX_TREE_EXCEPTIONAL_ENTRY + \
-			 ZONES_SHIFT + NODES_SHIFT +	\
+			 NODES_SHIFT +	\
 			 MEM_CGROUP_ID_SHIFT)
 #define EVICTION_MASK	(~0UL >> EVICTION_SHIFT)
 
@@ -167,33 +167,30 @@
  */
 static unsigned int bucket_order __read_mostly;
 
-static void *pack_shadow(int memcgid, struct zone *zone, unsigned long eviction)
+static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction)
 {
 	eviction >>= bucket_order;
 	eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
-	eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone);
-	eviction = (eviction << ZONES_SHIFT) | zone_idx(zone);
+	eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
 	eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
 
 	return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
 }
 
-static void unpack_shadow(void *shadow, int *memcgidp, struct zone **zonep,
+static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
 			  unsigned long *evictionp)
 {
 	unsigned long entry = (unsigned long)shadow;
-	int memcgid, nid, zid;
+	int memcgid, nid;
 
 	entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
-	zid = entry & ((1UL << ZONES_SHIFT) - 1);
-	entry >>= ZONES_SHIFT;
 	nid = entry & ((1UL << NODES_SHIFT) - 1);
 	entry >>= NODES_SHIFT;
 	memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
 	entry >>= MEM_CGROUP_ID_SHIFT;
 
 	*memcgidp = memcgid;
-	*zonep = NODE_DATA(nid)->node_zones + zid;
+	*pgdat = NODE_DATA(nid);
 	*evictionp = entry << bucket_order;
 }
 
@@ -208,7 +205,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, struct zone **zonep,
 void *workingset_eviction(struct address_space *mapping, struct page *page)
 {
 	struct mem_cgroup *memcg = page_memcg(page);
-	struct zone *zone = page_zone(page);
+	struct pglist_data *pgdat = page_pgdat(page);
 	int memcgid = mem_cgroup_id(memcg);
 	unsigned long eviction;
 	struct lruvec *lruvec;
@@ -218,9 +215,9 @@ void *workingset_eviction(struct address_space *mapping, struct page *page)
 	VM_BUG_ON_PAGE(page_count(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
-	lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+	lruvec = mem_cgroup_lruvec(pgdat, memcg);
 	eviction = atomic_long_inc_return(&lruvec->inactive_age);
-	return pack_shadow(memcgid, zone, eviction);
+	return pack_shadow(memcgid, pgdat, eviction);
 }
 
 /**
@@ -228,7 +225,7 @@ void *workingset_eviction(struct address_space *mapping, struct page *page)
  * @shadow: shadow entry of the evicted page
  *
  * Calculates and evaluates the refault distance of the previously
- * evicted page in the context of the zone it was allocated in.
+ * evicted page in the context of the node it was allocated in.
  *
  * Returns %true if the page should be activated, %false otherwise.
  */
@@ -240,10 +237,10 @@ bool workingset_refault(void *shadow)
 	unsigned long eviction;
 	struct lruvec *lruvec;
 	unsigned long refault;
-	struct zone *zone;
+	struct pglist_data *pgdat;
 	int memcgid;
 
-	unpack_shadow(shadow, &memcgid, &zone, &eviction);
+	unpack_shadow(shadow, &memcgid, &pgdat, &eviction);
 
 	rcu_read_lock();
 	/*
@@ -267,7 +264,7 @@ bool workingset_refault(void *shadow)
 		rcu_read_unlock();
 		return false;
 	}
-	lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+	lruvec = mem_cgroup_lruvec(pgdat, memcg);
 	refault = atomic_long_read(&lruvec->inactive_age);
 	active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE);
 	rcu_read_unlock();
@@ -290,10 +287,10 @@ bool workingset_refault(void *shadow)
 	 */
 	refault_distance = (refault - eviction) & EVICTION_MASK;
 
-	inc_zone_state(zone, WORKINGSET_REFAULT);
+	inc_node_state(pgdat, WORKINGSET_REFAULT);
 
 	if (refault_distance <= active_file) {
-		inc_zone_state(zone, WORKINGSET_ACTIVATE);
+		inc_node_state(pgdat, WORKINGSET_ACTIVATE);
 		return true;
 	}
 	return false;
@@ -305,9 +302,10 @@ bool workingset_refault(void *shadow)
  */
 void workingset_activation(struct page *page)
 {
+	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 
-	lock_page_memcg(page);
+	rcu_read_lock();
 	/*
 	 * Filter non-memcg pages here, e.g. unmap can call
 	 * mark_page_accessed() on VDSO pages.
@@ -315,12 +313,13 @@ void workingset_activation(struct page *page)
 	 * XXX: See workingset_refault() - this should return
 	 * root_mem_cgroup even for !CONFIG_MEMCG.
 	 */
-	if (!mem_cgroup_disabled() && !page_memcg(page))
+	memcg = page_memcg_rcu(page);
+	if (!mem_cgroup_disabled() && !memcg)
 		goto out;
-	lruvec = mem_cgroup_zone_lruvec(page_zone(page), page_memcg(page));
+	lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
 	atomic_long_inc(&lruvec->inactive_age);
 out:
-	unlock_page_memcg(page);
+	rcu_read_unlock();
 }
 
 /*
@@ -349,12 +348,13 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 	shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc);
 	local_irq_enable();
 
-	if (memcg_kmem_enabled())
+	if (memcg_kmem_enabled()) {
 		pages = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid,
 						     LRU_ALL_FILE);
-	else
-		pages = node_page_state(sc->nid, NR_ACTIVE_FILE) +
-			node_page_state(sc->nid, NR_INACTIVE_FILE);
+	} else {
+		pages = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) +
+			node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE);
+	}
 
 	/*
 	 * Active cache pages are limited to 50% of memory, and shadow
@@ -433,7 +433,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 		}
 	}
 	BUG_ON(node->count);
-	inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM);
+	inc_node_state(page_pgdat(virt_to_page(node)), WORKINGSET_NODERECLAIM);
 	if (!__radix_tree_delete_node(&mapping->page_tree, node))
 		BUG();
 

mm/zsmalloc.c

@@ -20,6 +20,7 @@
  *	page->freelist(index): links together all component pages of a zspage
  *		For the huge page, this is always 0, so we use this field
  *		to store handle.
+ *	page->units: first object offset in a subpage of zspage
  *
  * Usage of struct page flags:
  *	PG_private: identifies the first component page
@@ -137,9 +138,6 @@
  */
 #define ZS_SIZE_CLASS_DELTA	(PAGE_SIZE >> CLASS_BITS)
 
-/*
- * We do not maintain any list for completely empty or full pages
- */
 enum fullness_group {
 	ZS_EMPTY,
 	ZS_ALMOST_EMPTY,
@@ -467,11 +465,6 @@ static struct zpool_driver zs_zpool_driver = {
 MODULE_ALIAS("zpool-zsmalloc");
 #endif /* CONFIG_ZPOOL */
 
-static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage)
-{
-	return pages_per_zspage * PAGE_SIZE / size;
-}
-
 /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
 static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
 
@@ -635,8 +628,7 @@ static int zs_stats_size_show(struct seq_file *s, void *v)
 		freeable = zs_can_compact(class);
 		spin_unlock(&class->lock);
 
-		objs_per_zspage = get_maxobj_per_zspage(class->size,
-				class->pages_per_zspage);
+		objs_per_zspage = class->objs_per_zspage;
 		pages_used = obj_allocated / objs_per_zspage *
 				class->pages_per_zspage;
 
@@ -945,8 +937,8 @@ static void unpin_tag(unsigned long handle)
 static void reset_page(struct page *page)
 {
 	__ClearPageMovable(page);
-	clear_bit(PG_private, &page->flags);
-	clear_bit(PG_private_2, &page->flags);
+	ClearPagePrivate(page);
+	ClearPagePrivate2(page);
 	set_page_private(page, 0);
 	page_mapcount_reset(page);
 	ClearPageHugeObject(page);
@@ -1014,8 +1006,7 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class,
 
 	cache_free_zspage(pool, zspage);
 
-	zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
-			class->size, class->pages_per_zspage));
+	zs_stat_dec(class, OBJ_ALLOCATED, class->objs_per_zspage);
 	atomic_long_sub(class->pages_per_zspage,
 					&pool->pages_allocated);
 }
@@ -1350,7 +1341,7 @@ static void zs_unregister_cpu_notifier(void)
 	cpu_notifier_register_done();
 }
 
-static void init_zs_size_classes(void)
+static void __init init_zs_size_classes(void)
 {
 	int nr;
 
@@ -1361,16 +1352,14 @@ static void init_zs_size_classes(void)
 	zs_size_classes = nr;
 }
 
-static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
+static bool can_merge(struct size_class *prev, int pages_per_zspage,
+					int objs_per_zspage)
 {
-	if (prev->pages_per_zspage != pages_per_zspage)
-		return false;
+	if (prev->pages_per_zspage == pages_per_zspage &&
+		prev->objs_per_zspage == objs_per_zspage)
+		return true;
 
-	if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage)
-		!= get_maxobj_per_zspage(size, pages_per_zspage))
-		return false;
-
-	return true;
+	return false;
 }
 
 static bool zspage_full(struct size_class *class, struct zspage *zspage)
@@ -1541,6 +1530,7 @@ static unsigned long obj_malloc(struct size_class *class,
  * zs_malloc - Allocate block of given size from pool.
  * @pool: pool to allocate from
  * @size: size of block to allocate
+ * @gfp: gfp flags when allocating object
  *
  * On success, handle to the allocated object is returned,
  * otherwise 0.
@@ -1592,8 +1582,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp)
 	record_obj(handle, obj);
 	atomic_long_add(class->pages_per_zspage,
 				&pool->pages_allocated);
-	zs_stat_inc(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
-			class->size, class->pages_per_zspage));
+	zs_stat_inc(class, OBJ_ALLOCATED, class->objs_per_zspage);
 
 	/* We completely set up zspage so mark them as movable */
 	SetZsPageMovable(pool, zspage);
@@ -1741,10 +1730,11 @@ static void zs_object_copy(struct size_class *class, unsigned long dst,
  * return handle.
  */
 static unsigned long find_alloced_obj(struct size_class *class,
-					struct page *page, int index)
+					struct page *page, int *obj_idx)
 {
 	unsigned long head;
 	int offset = 0;
+	int index = *obj_idx;
 	unsigned long handle = 0;
 	void *addr = kmap_atomic(page);
 
@@ -1765,6 +1755,9 @@ static unsigned long find_alloced_obj(struct size_class *class,
 	}
 
 	kunmap_atomic(addr);
+
+	*obj_idx = index;
+
 	return handle;
 }
 
@@ -1776,7 +1769,7 @@ struct zs_compact_control {
 	struct page *d_page;
 	 /* Starting object index within @s_page which used for live object
 	  * in the subpage. */
-	int index;
+	int obj_idx;
 };
 
 static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
@@ -1786,16 +1779,16 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
 	unsigned long handle;
 	struct page *s_page = cc->s_page;
 	struct page *d_page = cc->d_page;
-	unsigned long index = cc->index;
+	int obj_idx = cc->obj_idx;
 	int ret = 0;
 
 	while (1) {
-		handle = find_alloced_obj(class, s_page, index);
+		handle = find_alloced_obj(class, s_page, &obj_idx);
 		if (!handle) {
 			s_page = get_next_page(s_page);
 			if (!s_page)
 				break;
-			index = 0;
+			obj_idx = 0;
 			continue;
 		}
 
@@ -1809,7 +1802,7 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
 		used_obj = handle_to_obj(handle);
 		free_obj = obj_malloc(class, get_zspage(d_page), handle);
 		zs_object_copy(class, free_obj, used_obj);
-		index++;
+		obj_idx++;
 		/*
 		 * record_obj updates handle's value to free_obj and it will
 		 * invalidate lock bit(ie, HANDLE_PIN_BIT) of handle, which
@@ -1824,7 +1817,7 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
 
 	/* Remember last position in this iteration */
 	cc->s_page = s_page;
-	cc->index = index;
+	cc->obj_idx = obj_idx;
 
 	return ret;
 }
@@ -2181,8 +2174,7 @@ static int zs_register_migration(struct zs_pool *pool)
 static void zs_unregister_migration(struct zs_pool *pool)
 {
 	flush_work(&pool->free_work);
-	if (pool->inode)
-		iput(pool->inode);
+	iput(pool->inode);
 }
 
 /*
@@ -2261,8 +2253,7 @@ static unsigned long zs_can_compact(struct size_class *class)
 		return 0;
 
 	obj_wasted = obj_allocated - obj_used;
-	obj_wasted /= get_maxobj_per_zspage(class->size,
-			class->pages_per_zspage);
+	obj_wasted /= class->objs_per_zspage;
 
 	return obj_wasted * class->pages_per_zspage;
 }
@@ -2279,7 +2270,7 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class)
 		if (!zs_can_compact(class))
 			break;
 
-		cc.index = 0;
+		cc.obj_idx = 0;
 		cc.s_page = get_first_page(src_zspage);
 
 		while ((dst_zspage = isolate_zspage(class, false))) {
@@ -2398,7 +2389,7 @@ static int zs_register_shrinker(struct zs_pool *pool)
 
 /**
  * zs_create_pool - Creates an allocation pool to work from.
- * @flags: allocation flags used to allocate pool metadata
+ * @name: pool name to be created
  *
  * This function must be called before anything when using
  * the zsmalloc allocator.
@@ -2438,6 +2429,7 @@ struct zs_pool *zs_create_pool(const char *name)
 	for (i = zs_size_classes - 1; i >= 0; i--) {
 		int size;
 		int pages_per_zspage;
+		int objs_per_zspage;
 		struct size_class *class;
 		int fullness = 0;
 
@@ -2445,6 +2437,7 @@ struct zs_pool *zs_create_pool(const char *name)
 		if (size > ZS_MAX_ALLOC_SIZE)
 			size = ZS_MAX_ALLOC_SIZE;
 		pages_per_zspage = get_pages_per_zspage(size);
+		objs_per_zspage = pages_per_zspage * PAGE_SIZE / size;
 
 		/*
 		 * size_class is used for normal zsmalloc operation such
@@ -2456,7 +2449,7 @@ struct zs_pool *zs_create_pool(const char *name)
 		 * previous size_class if possible.
 		 */
 		if (prev_class) {
-			if (can_merge(prev_class, size, pages_per_zspage)) {
+			if (can_merge(prev_class, pages_per_zspage, objs_per_zspage)) {
 				pool->size_class[i] = prev_class;
 				continue;
 			}
@@ -2469,8 +2462,7 @@ struct zs_pool *zs_create_pool(const char *name)
 		class->size = size;
 		class->index = i;
 		class->pages_per_zspage = pages_per_zspage;
-		class->objs_per_zspage = class->pages_per_zspage *
-						PAGE_SIZE / class->size;
+		class->objs_per_zspage = objs_per_zspage;
 		spin_lock_init(&class->lock);
 		pool->size_class[i] = class;
 		for (fullness = ZS_EMPTY; fullness < NR_ZS_FULLNESS;

tools/perf/builtin-kmem.c

@@ -608,6 +608,7 @@ static const struct {
 	const char *compact;
 } gfp_compact_table[] = {
 	{ "GFP_TRANSHUGE",		"THP" },
+	{ "GFP_TRANSHUGE_LIGHT",	"THL" },
 	{ "GFP_HIGHUSER_MOVABLE",	"HUM" },
 	{ "GFP_HIGHUSER",		"HU" },
 	{ "GFP_USER",			"U" },