Merge tag 'v4.9.117' into v4.9-rt

This is the 4.9.117 stable release

17 files changed, 110 insertions, 33 deletions

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index dfd99867ff4d..9afad8c14220 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2237,6 +2237,21 @@ void assert_qgroups_uptodate(struct btrfs_trans_handle *trans)
 }
 
 /*
+ * Check if the leaf is the last leaf. Which means all node pointers
+ * are at their last position.
+ */
+static bool is_last_leaf(struct btrfs_path *path)
+{
+	int i;
+
+	for (i = 1; i < BTRFS_MAX_LEVEL && path->nodes[i]; i++) {
+		if (path->slots[i] != btrfs_header_nritems(path->nodes[i]) - 1)
+			return false;
+	}
+	return true;
+}
+
+/*
  * returns < 0 on error, 0 when more leafs are to be scanned.
  * returns 1 when done.
  */
@@ -2249,6 +2264,7 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	struct ulist *roots = NULL;
 	struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem);
 	u64 num_bytes;
+	bool done;
 	int slot;
 	int ret;
 
@@ -2277,6 +2293,7 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 		mutex_unlock(&fs_info->qgroup_rescan_lock);
 		return ret;
 	}
+	done = is_last_leaf(path);
 
 	btrfs_item_key_to_cpu(path->nodes[0], &found,
 			      btrfs_header_nritems(path->nodes[0]) - 1);
@@ -2323,6 +2340,8 @@ out:
 	}
 	btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem);
 
+	if (done && !ret)
+		ret = 1;
 	return ret;
 }
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 44d34923de9c..44966fd00790 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2979,8 +2979,11 @@ out_wake_log_root:
 	mutex_unlock(&log_root_tree->log_mutex);
 
 	/*
-	 * The barrier before waitqueue_active is implied by mutex_unlock
+	 * The barrier before waitqueue_active is needed so all the updates
+	 * above are seen by the woken threads. It might not be necessary, but
+	 * proving that seems to be hard.
 	 */
+	smp_mb();
 	if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
 		wake_up(&log_root_tree->log_commit_wait[index2]);
 out:
@@ -2991,8 +2994,11 @@ out:
 	mutex_unlock(&root->log_mutex);
 
 	/*
-	 * The barrier before waitqueue_active is implied by mutex_unlock
+	 * The barrier before waitqueue_active is needed so all the updates
+	 * above are seen by the woken threads. It might not be necessary, but
+	 * proving that seems to be hard.
 	 */
+	smp_mb();
 	if (waitqueue_active(&root->log_commit_wait[index1]))
 		wake_up(&root->log_commit_wait[index1]);
 	return ret;
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 73de1446c8d4..1a8962569b5c 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -517,8 +517,17 @@ EXPORT_SYMBOL(fscrypt_initialize);
  */
 static int __init fscrypt_init(void)
 {
+	/*
+	 * Use an unbound workqueue to allow bios to be decrypted in parallel
+	 * even when they happen to complete on the same CPU.  This sacrifices
+	 * locality, but it's worthwhile since decryption is CPU-intensive.
+	 *
+	 * Also use a high-priority workqueue to prioritize decryption work,
+	 * which blocks reads from completing, over regular application tasks.
+	 */
 	fscrypt_read_workqueue = alloc_workqueue("fscrypt_read_queue",
-							WQ_HIGHPRI, 0);
+						 WQ_UNBOUND | WQ_HIGHPRI,
+						 num_online_cpus());
 	if (!fscrypt_read_workqueue)
 		goto fail;
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index ad13f07cf0d3..2455fe1446d6 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -378,6 +378,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 		return -EFSCORRUPTED;
 
 	ext4_lock_group(sb, block_group);
+	if (buffer_verified(bh))
+		goto verified;
 	if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
 			desc, bh))) {
 		ext4_unlock_group(sb, block_group);
@@ -400,6 +402,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 		return -EFSCORRUPTED;
 	}
 	set_buffer_verified(bh);
+verified:
 	ext4_unlock_group(sb, block_group);
 	return 0;
 }
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 460866b2166d..ffaf66a51de3 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -88,6 +88,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 		return -EFSCORRUPTED;
 
 	ext4_lock_group(sb, block_group);
+	if (buffer_verified(bh))
+		goto verified;
 	blk = ext4_inode_bitmap(sb, desc);
 	if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
 					   EXT4_INODES_PER_GROUP(sb) / 8)) {
@@ -105,6 +107,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 		return -EFSBADCRC;
 	}
 	set_buffer_verified(bh);
+verified:
 	ext4_unlock_group(sb, block_group);
 	return 0;
 }
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index e6ac24de119d..436baf7cdca3 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -679,6 +679,10 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 		goto convert;
 	}
 
+	ret = ext4_journal_get_write_access(handle, iloc.bh);
+	if (ret)
+		goto out;
+
 	flags |= AOP_FLAG_NOFS;
 
 	page = grab_cache_page_write_begin(mapping, 0, flags);
@@ -707,7 +711,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 out_up_read:
 	up_read(&EXT4_I(inode)->xattr_sem);
 out:
-	if (handle)
+	if (handle && (ret != 1))
 		ext4_journal_stop(handle);
 	brelse(iloc.bh);
 	return ret;
@@ -749,6 +753,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 
 	ext4_write_unlock_xattr(inode, &no_expand);
 	brelse(iloc.bh);
+	mark_inode_dirty(inode);
 out:
 	return copied;
 }
@@ -895,7 +900,6 @@ retry_journal:
 		goto out;
 	}
 
-
 	page = grab_cache_page_write_begin(mapping, 0, flags);
 	if (!page) {
 		ret = -ENOMEM;
@@ -913,6 +917,9 @@ retry_journal:
 		if (ret < 0)
 			goto out_release_page;
 	}
+	ret = ext4_journal_get_write_access(handle, iloc.bh);
+	if (ret)
+		goto out_release_page;
 
 	up_read(&EXT4_I(inode)->xattr_sem);
 	*pagep = page;
@@ -933,7 +940,6 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 				  unsigned len, unsigned copied,
 				  struct page *page)
 {
-	int i_size_changed = 0;
 	int ret;
 
 	ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
@@ -951,10 +957,8 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 	 * But it's important to update i_size while still holding page lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
 	 */
-	if (pos+copied > inode->i_size) {
+	if (pos+copied > inode->i_size)
 		i_size_write(inode, pos+copied);
-		i_size_changed = 1;
-	}
 	unlock_page(page);
 	put_page(page);
 
@@ -964,8 +968,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 	 * ordering of page lock and transaction start for journaling
 	 * filesystems.
 	 */
-	if (i_size_changed)
-		mark_inode_dirty(inode);
+	mark_inode_dirty(inode);
 
 	return copied;
 }
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5c4c9af4aaf4..f62eca8cbde0 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1318,9 +1318,10 @@ static int ext4_write_end(struct file *file,
 	loff_t old_size = inode->i_size;
 	int ret = 0, ret2;
 	int i_size_changed = 0;
+	int inline_data = ext4_has_inline_data(inode);
 
 	trace_ext4_write_end(inode, pos, len, copied);
-	if (ext4_has_inline_data(inode)) {
+	if (inline_data) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
 		if (ret < 0) {
@@ -1348,7 +1349,7 @@ static int ext4_write_end(struct file *file,
 	 * ordering of page lock and transaction start for journaling
 	 * filesystems.
 	 */
-	if (i_size_changed)
+	if (i_size_changed || inline_data)
 		ext4_mark_inode_dirty(handle, inode);
 
 	if (pos + len > inode->i_size && ext4_can_truncate(inode))
@@ -1422,6 +1423,7 @@ static int ext4_journalled_write_end(struct file *file,
 	int partial = 0;
 	unsigned from, to;
 	int size_changed = 0;
+	int inline_data = ext4_has_inline_data(inode);
 
 	trace_ext4_journalled_write_end(inode, pos, len, copied);
 	from = pos & (PAGE_SIZE - 1);
@@ -1429,7 +1431,7 @@ static int ext4_journalled_write_end(struct file *file,
 
 	BUG_ON(!ext4_handle_valid(handle));
 
-	if (ext4_has_inline_data(inode)) {
+	if (inline_data) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
 		if (ret < 0) {
@@ -1460,7 +1462,7 @@ static int ext4_journalled_write_end(struct file *file,
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
 
-	if (size_changed) {
+	if (size_changed || inline_data) {
 		ret2 = ext4_mark_inode_dirty(handle, inode);
 		if (!ret)
 			ret = ret2;
@@ -1958,11 +1960,7 @@ static int __ext4_journalled_writepage(struct page *page,
 	}
 
 	if (inline_data) {
-		BUFFER_TRACE(inode_bh, "get write access");
-		ret = ext4_journal_get_write_access(handle, inode_bh);
-
-		err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
-
+		ret = ext4_mark_inode_dirty(handle, inode);
 	} else {
 		ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL,
 					     do_journal_get_write_access);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 801111e1f8ef..7d0e8d6bf009 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1512,6 +1512,8 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 
 	inode_lock(inode);
 
+	down_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
+
 	if (f2fs_is_atomic_file(inode))
 		goto out;
 
@@ -1532,6 +1534,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 	if (ret)
 		clear_inode_flag(inode, FI_ATOMIC_FILE);
 out:
+	up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
 	inode_unlock(inode);
 	mnt_drop_write_file(filp);
 	return ret;
@@ -1670,9 +1673,11 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 	if (get_user(in, (__u32 __user *)arg))
 		return -EFAULT;
 
-	ret = mnt_want_write_file(filp);
-	if (ret)
-		return ret;
+	if (in != F2FS_GOING_DOWN_FULLSYNC) {
+		ret = mnt_want_write_file(filp);
+		if (ret)
+			return ret;
+	}
 
 	switch (in) {
 	case F2FS_GOING_DOWN_FULLSYNC:
@@ -1700,7 +1705,8 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 	}
 	f2fs_update_time(sbi, REQ_TIME);
 out:
-	mnt_drop_write_file(filp);
+	if (in != F2FS_GOING_DOWN_FULLSYNC)
+		mnt_drop_write_file(filp);
 	return ret;
 }
 
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 17ab23f64bba..ad4dfd29d923 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -688,9 +688,14 @@ retry:
 		set_cold_data(page);
 
 		err = do_write_data_page(&fio);
-		if (err == -ENOMEM && is_dirty) {
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
-			goto retry;
+		if (err) {
+			clear_cold_data(page);
+			if (err == -ENOMEM) {
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				goto retry;
+			}
+			if (is_dirty)
+				set_page_dirty(page);
 		}
 
 		clear_cold_data(page);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index e10f61684ea4..35d48ef0573c 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -207,6 +207,8 @@ static int __revoke_inmem_pages(struct inode *inode,
 
 		lock_page(page);
 
+		f2fs_wait_on_page_writeback(page, DATA, true);
+
 		if (recover) {
 			struct dnode_of_data dn;
 			struct node_info ni;
@@ -369,6 +371,9 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 
 void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 {
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		return;
+
 	/* try to shrink extent cache when there is no enough memory */
 	if (!available_free_memory(sbi, EXTENT_CACHE))
 		f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index eb20b8767f3c..e627671f0183 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1980,6 +1980,12 @@ static int __init init_f2fs_fs(void)
 {
 	int err;
 
+	if (PAGE_SIZE != F2FS_BLKSIZE) {
+		printk("F2FS not supported on PAGE_SIZE(%lu) != %d\n",
+				PAGE_SIZE, F2FS_BLKSIZE);
+		return -EINVAL;
+	}
+
 	f2fs_build_trace_ios();
 
 	err = init_inodecache();
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 99c7de167726..12753db610bf 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2701,7 +2701,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	if (ret != 0)
 		goto out;
 
-	state = nfs4_opendata_to_nfs4_state(opendata);
+	state = _nfs4_opendata_to_nfs4_state(opendata);
 	ret = PTR_ERR(state);
 	if (IS_ERR(state))
 		goto out;
@@ -2737,6 +2737,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 			nfs4_schedule_stateid_recovery(server, state);
 	}
 out:
+	nfs4_sequence_free_slot(&opendata->o_res.seq_res);
 	return ret;
 }
 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index bdbd9e6d1ace..b16a6c036352 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1536,6 +1536,8 @@ nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp,
 	gdev->gd_maxcount = be32_to_cpup(p++);
 	num = be32_to_cpup(p++);
 	if (num) {
+		if (num > 1000)
+			goto xdr_error;
 		READ_BUF(4 * num);
 		gdev->gd_notify_types = be32_to_cpup(p++);
 		for (i = 1; i < num; i++) {
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 23813c078cc9..0839efa720b3 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -350,6 +350,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer,
 
 	TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset);
 
+	if (unlikely(length < 0))
+		return -EIO;
+
 	while (length) {
 		entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0);
 		if (entry->error) {
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 13d80947bf9e..fcff2e0487fe 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -194,7 +194,11 @@ static long long read_indexes(struct super_block *sb, int n,
 		}
 
 		for (i = 0; i < blocks; i++) {
-			int size = le32_to_cpu(blist[i]);
+			int size = squashfs_block_size(blist[i]);
+			if (size < 0) {
+				err = size;
+				goto failure;
+			}
 			block += SQUASHFS_COMPRESSED_SIZE_BLOCK(size);
 		}
 		n -= blocks;
@@ -367,7 +371,7 @@ static int read_blocklist(struct inode *inode, int index, u64 *block)
 			sizeof(size));
 	if (res < 0)
 		return res;
-	return le32_to_cpu(size);
+	return squashfs_block_size(size);
 }
 
 /* Copy data into page cache  */
diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c
index 0ed6edbc5c71..86ad9a4b8c36 100644
--- a/fs/squashfs/fragment.c
+++ b/fs/squashfs/fragment.c
@@ -61,9 +61,7 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment,
 		return size;
 
 	*fragment_block = le64_to_cpu(fragment_entry.start_block);
-	size = le32_to_cpu(fragment_entry.size);
-
-	return size;
+	return squashfs_block_size(fragment_entry.size);
 }
 
 
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 506f4ba5b983..e66486366f02 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -129,6 +129,12 @@
 
 #define SQUASHFS_COMPRESSED_BLOCK(B)	(!((B) & SQUASHFS_COMPRESSED_BIT_BLOCK))
 
+static inline int squashfs_block_size(__le32 raw)
+{
+	u32 size = le32_to_cpu(raw);
+	return (size >> 25) ? -EIO : size;
+}
+
 /*
  * Inode number ops.  Inodes consist of a compressed block number, and an
  * uncompressed offset within that block