Merge tag 'v4.9.89' into linux-linaro-lsk-v4.9

 This is the 4.9.89 stable release

9 files changed, 71 insertions, 36 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 0fcb49ad67d4..0606f033cd9b 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -68,9 +68,9 @@ struct aio_ring {
 #define AIO_RING_PAGES	8
 
 struct kioctx_table {
-	struct rcu_head	rcu;
-	unsigned	nr;
-	struct kioctx	*table[];
+	struct rcu_head		rcu;
+	unsigned		nr;
+	struct kioctx __rcu	*table[];
 };
 
 struct kioctx_cpu {
@@ -115,7 +115,8 @@ struct kioctx {
 	struct page		**ring_pages;
 	long			nr_pages;
 
-	struct work_struct	free_work;
+	struct rcu_head		free_rcu;
+	struct work_struct	free_work;	/* see free_ioctx() */
 
 	/*
 	 * signals when all in-flight requests are done
@@ -329,7 +330,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma)
 	for (i = 0; i < table->nr; i++) {
 		struct kioctx *ctx;
 
-		ctx = table->table[i];
+		ctx = rcu_dereference(table->table[i]);
 		if (ctx && ctx->aio_ring_file == file) {
 			if (!atomic_read(&ctx->dead)) {
 				ctx->user_id = ctx->mmap_base = vma->vm_start;
@@ -581,6 +582,12 @@ static int kiocb_cancel(struct aio_kiocb *kiocb)
 	return cancel(&kiocb->common);
 }
 
+/*
+ * free_ioctx() should be RCU delayed to synchronize against the RCU
+ * protected lookup_ioctx() and also needs process context to call
+ * aio_free_ring(), so the double bouncing through kioctx->free_rcu and
+ * ->free_work.
+ */
 static void free_ioctx(struct work_struct *work)
 {
 	struct kioctx *ctx = container_of(work, struct kioctx, free_work);
@@ -594,6 +601,14 @@ static void free_ioctx(struct work_struct *work)
 	kmem_cache_free(kioctx_cachep, ctx);
 }
 
+static void free_ioctx_rcufn(struct rcu_head *head)
+{
+	struct kioctx *ctx = container_of(head, struct kioctx, free_rcu);
+
+	INIT_WORK(&ctx->free_work, free_ioctx);
+	schedule_work(&ctx->free_work);
+}
+
 static void free_ioctx_reqs(struct percpu_ref *ref)
 {
 	struct kioctx *ctx = container_of(ref, struct kioctx, reqs);
@@ -602,8 +617,8 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
 	if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count))
 		complete(&ctx->rq_wait->comp);
 
-	INIT_WORK(&ctx->free_work, free_ioctx);
-	schedule_work(&ctx->free_work);
+	/* Synchronize against RCU protected table->table[] dereferences */
+	call_rcu(&ctx->free_rcu, free_ioctx_rcufn);
 }
 
 /*
@@ -644,9 +659,9 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
 	while (1) {
 		if (table)
 			for (i = 0; i < table->nr; i++)
-				if (!table->table[i]) {
+				if (!rcu_access_pointer(table->table[i])) {
 					ctx->id = i;
-					table->table[i] = ctx;
+					rcu_assign_pointer(table->table[i], ctx);
 					spin_unlock(&mm->ioctx_lock);
 
 					/* While kioctx setup is in progress,
@@ -821,11 +836,11 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
 	}
 
 	table = rcu_dereference_raw(mm->ioctx_table);
-	WARN_ON(ctx != table->table[ctx->id]);
-	table->table[ctx->id] = NULL;
+	WARN_ON(ctx != rcu_access_pointer(table->table[ctx->id]));
+	RCU_INIT_POINTER(table->table[ctx->id], NULL);
 	spin_unlock(&mm->ioctx_lock);
 
-	/* percpu_ref_kill() will do the necessary call_rcu() */
+	/* free_ioctx_reqs() will do the necessary RCU synchronization */
 	wake_up_all(&ctx->wait);
 
 	/*
@@ -867,7 +882,8 @@ void exit_aio(struct mm_struct *mm)
 
 	skipped = 0;
 	for (i = 0; i < table->nr; ++i) {
-		struct kioctx *ctx = table->table[i];
+		struct kioctx *ctx =
+			rcu_dereference_protected(table->table[i], true);
 
 		if (!ctx) {
 			skipped++;
@@ -1056,7 +1072,7 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 	if (!table || id >= table->nr)
 		goto out;
 
-	ctx = table->table[id];
+	ctx = rcu_dereference(table->table[id]);
 	if (ctx && ctx->user_id == ctx_id) {
 		percpu_ref_get(&ctx->users);
 		ret = ctx;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 06a77e47957d..5900508ca6ed 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -583,6 +583,7 @@ void btrfs_free_stale_device(struct btrfs_device *cur_dev)
 				btrfs_sysfs_remove_fsid(fs_devs);
 				list_del(&fs_devs->list);
 				free_fs_devices(fs_devs);
+				break;
 			} else {
 				fs_devs->num_devices--;
 				list_del(&dev->dev_list);
@@ -4748,10 +4749,13 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	if (devs_max && ndevs > devs_max)
 		ndevs = devs_max;
 	/*
-	 * the primary goal is to maximize the number of stripes, so use as many
-	 * devices as possible, even if the stripes are not maximum sized.
+	 * The primary goal is to maximize the number of stripes, so use as
+	 * many devices as possible, even if the stripes are not maximum sized.
+	 *
+	 * The DUP profile stores more than one stripe per device, the
+	 * max_avail is the total size so we have to adjust.
 	 */
-	stripe_size = devices_info[ndevs-1].max_avail;
+	stripe_size = div_u64(devices_info[ndevs - 1].max_avail, dev_stripes);
 	num_stripes = ndevs * dev_stripes;
 
 	/*
@@ -4791,8 +4795,6 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 			stripe_size = devices_info[ndevs-1].max_avail;
 	}
 
-	stripe_size = div_u64(stripe_size, dev_stripes);
-
 	/* align to BTRFS_STRIPE_LEN */
 	stripe_size = div_u64(stripe_size, raid_stripe_len);
 	stripe_size *= raid_stripe_len;
diff --git a/fs/dcache.c b/fs/dcache.c
index 67957f5b325c..c0c7fa8224ba 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -637,11 +637,16 @@ again:
 		spin_unlock(&parent->d_lock);
 		goto again;
 	}
-	rcu_read_unlock();
-	if (parent != dentry)
+	if (parent != dentry) {
 		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-	else
+		if (unlikely(dentry->d_lockref.count < 0)) {
+			spin_unlock(&parent->d_lock);
+			parent = NULL;
+		}
+	} else {
 		parent = NULL;
+	}
+	rcu_read_unlock();
 	return parent;
 }
 
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 34a69e7ed90b..17ab23f64bba 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -538,8 +538,10 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	get_node_info(sbi, nid, dni);
 
 	if (sum->version != dni->version) {
-		f2fs_put_page(node_page, 1);
-		return false;
+		f2fs_msg(sbi->sb, KERN_WARNING,
+				"%s: valid data with mismatched node version.",
+				__func__);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 	}
 
 	*nofs = ofs_of_node(node_page);
diff --git a/fs/namei.c b/fs/namei.c
index 6cfb45f262aa..891670e0956b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -578,9 +578,10 @@ static int __nd_alloc_stack(struct nameidata *nd)
 static bool path_connected(const struct path *path)
 {
 	struct vfsmount *mnt = path->mnt;
+	struct super_block *sb = mnt->mnt_sb;
 
-	/* Only bind mounts can have disconnected paths */
-	if (mnt->mnt_root == mnt->mnt_sb->s_root)
+	/* Bind mounts and multi-root filesystems can have disconnected paths */
+	if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root))
 		return true;
 
 	return is_subdir(path->dentry, mnt->mnt_root);
@@ -1121,9 +1122,6 @@ static int follow_automount(struct path *path, struct nameidata *nd,
 	    path->dentry->d_inode)
 		return -EISDIR;
 
-	if (path->dentry->d_sb->s_user_ns != &init_user_ns)
-		return -EACCES;
-
 	nd->total_link_count++;
 	if (nd->total_link_count >= 40)
 		return -ELOOP;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 51bf1f9ab287..2fdb8f5a7b69 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2613,6 +2613,8 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
 		/* initial superblock/root creation */
 		mount_info->fill_super(s, mount_info);
 		nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned);
+		if (!(server->flags & NFS_MOUNT_UNSHARED))
+			s->s_iflags |= SB_I_MULTIROOT;
 	}
 
 	mntroot = nfs_get_root(s, mount_info->mntfh, dev_name);
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index bc2dde2423c2..76108185854e 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -1959,7 +1959,7 @@ static int do_journal_release(struct reiserfs_transaction_handle *th,
 	 * will be requeued because superblock is being shutdown and doesn't
 	 * have MS_ACTIVE set.
 	 */
-	cancel_delayed_work_sync(&REISERFS_SB(sb)->old_work);
+	reiserfs_cancel_old_flush(sb);
 	/* wait for all commits to finish */
 	cancel_delayed_work_sync(&SB_JOURNAL(sb)->j_work);
 
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 5dcf3ab83886..6ca00471afbf 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -2948,6 +2948,7 @@ int reiserfs_allocate_list_bitmaps(struct super_block *s,
 				   struct reiserfs_list_bitmap *, unsigned int);
 
 void reiserfs_schedule_old_flush(struct super_block *s);
+void reiserfs_cancel_old_flush(struct super_block *s);
 void add_save_link(struct reiserfs_transaction_handle *th,
 		   struct inode *inode, int truncate);
 int remove_save_link(struct inode *inode, int truncate);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index e101d70d2327..dec6c93044fa 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -90,7 +90,9 @@ static void flush_old_commits(struct work_struct *work)
 	s = sbi->s_journal->j_work_sb;
 
 	spin_lock(&sbi->old_work_lock);
-	sbi->work_queued = 0;
+	/* Avoid clobbering the cancel state... */
+	if (sbi->work_queued == 1)
+		sbi->work_queued = 0;
 	spin_unlock(&sbi->old_work_lock);
 
 	reiserfs_sync_fs(s, 1);
@@ -117,21 +119,22 @@ void reiserfs_schedule_old_flush(struct super_block *s)
 	spin_unlock(&sbi->old_work_lock);
 }
 
-static void cancel_old_flush(struct super_block *s)
+void reiserfs_cancel_old_flush(struct super_block *s)
 {
 	struct reiserfs_sb_info *sbi = REISERFS_SB(s);
 
-	cancel_delayed_work_sync(&REISERFS_SB(s)->old_work);
 	spin_lock(&sbi->old_work_lock);
-	sbi->work_queued = 0;
+	/* Make sure no new flushes will be queued */
+	sbi->work_queued = 2;
 	spin_unlock(&sbi->old_work_lock);
+	cancel_delayed_work_sync(&REISERFS_SB(s)->old_work);
 }
 
 static int reiserfs_freeze(struct super_block *s)
 {
 	struct reiserfs_transaction_handle th;
 
-	cancel_old_flush(s);
+	reiserfs_cancel_old_flush(s);
 
 	reiserfs_write_lock(s);
 	if (!(s->s_flags & MS_RDONLY)) {
@@ -152,7 +155,13 @@ static int reiserfs_freeze(struct super_block *s)
 
 static int reiserfs_unfreeze(struct super_block *s)
 {
+	struct reiserfs_sb_info *sbi = REISERFS_SB(s);
+
 	reiserfs_allow_writes(s);
+	spin_lock(&sbi->old_work_lock);
+	/* Allow old_work to run again */
+	sbi->work_queued = 0;
+	spin_unlock(&sbi->old_work_lock);
 	return 0;
 }
 
@@ -2194,7 +2203,7 @@ error_unlocked:
 	if (sbi->commit_wq)
 		destroy_workqueue(sbi->commit_wq);
 
-	cancel_delayed_work_sync(&REISERFS_SB(s)->old_work);
+	reiserfs_cancel_old_flush(s);
 
 	reiserfs_free_bitmap_cache(s);
 	if (SB_BUFFER_WITH_SB(s))