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
  ...

6 files changed, 115 insertions, 108 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 6f9c9f6f5157..56c8fda436c0 100644
--- a/fs/fs-writeback.c
+++ b/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();
 }
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 9154f8679024..2382f22a2a8b 100644
--- a/fs/fuse/file.c
+++ b/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)) {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 5154fa65a2f2..5ea04d87fc65 100644
--- a/fs/nfs/internal.h
+++ b/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);
 	}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index e1c74d3db64d..593fa21a02c0 100644
--- a/fs/nfs/write.c
+++ b/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);
 }
diff --git a/fs/proc/base.c b/fs/proc/base.c
index a11eb7196ec8..31370da2ee7c 100644
--- a/fs/proc/base.c
+++ b/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;
 }
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index cf301a9ef512..09e18fdf61e5 100644
--- a/fs/proc/meminfo.c
+++ b/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)