Merge tag 'v4.4.177' into toradex_vf_4.4-nextColibri-VF_LXDE-Image_2.8b6.183-20190331

This is the 4.4.177 stable release

98 files changed, 2499 insertions, 809 deletions

diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index a69260f27555..103ca5e1267b 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -243,14 +243,14 @@ void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp)
 	if (!v9inode->fscache)
 		return;
 
-	spin_lock(&v9inode->fscache_lock);
+	mutex_lock(&v9inode->fscache_lock);
 
 	if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
 		v9fs_cache_inode_flush_cookie(inode);
 	else
 		v9fs_cache_inode_get_cookie(inode);
 
-	spin_unlock(&v9inode->fscache_lock);
+	mutex_unlock(&v9inode->fscache_lock);
 }
 
 void v9fs_cache_inode_reset_cookie(struct inode *inode)
@@ -264,7 +264,7 @@ void v9fs_cache_inode_reset_cookie(struct inode *inode)
 
 	old = v9inode->fscache;
 
-	spin_lock(&v9inode->fscache_lock);
+	mutex_lock(&v9inode->fscache_lock);
 	fscache_relinquish_cookie(v9inode->fscache, 1);
 
 	v9ses = v9fs_inode2v9ses(inode);
@@ -274,7 +274,7 @@ void v9fs_cache_inode_reset_cookie(struct inode *inode)
 	p9_debug(P9_DEBUG_FSC, "inode %p revalidating cookie old %p new %p\n",
 		 inode, old, v9inode->fscache);
 
-	spin_unlock(&v9inode->fscache_lock);
+	mutex_unlock(&v9inode->fscache_lock);
 }
 
 int __v9fs_fscache_release_page(struct page *page, gfp_t gfp)
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 0923f2cf3c80..6877050384a1 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -123,7 +123,7 @@ struct v9fs_session_info {
 
 struct v9fs_inode {
 #ifdef CONFIG_9P_FSCACHE
-	spinlock_t fscache_lock;
+	struct mutex fscache_lock;
 	struct fscache_cookie *fscache;
 #endif
 	struct p9_qid qid;
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 5a0db6dec8d1..aaee1e6584e6 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -40,6 +40,9 @@
  */
 #define P9_LOCK_TIMEOUT (30*HZ)
 
+/* flags for v9fs_stat2inode() & v9fs_stat2inode_dotl() */
+#define V9FS_STAT2INODE_KEEP_ISIZE 1
+
 extern struct file_system_type v9fs_fs_type;
 extern const struct address_space_operations v9fs_addr_operations;
 extern const struct file_operations v9fs_file_operations;
@@ -61,8 +64,10 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses,
 		    struct inode *inode, umode_t mode, dev_t);
 void v9fs_evict_inode(struct inode *inode);
 ino_t v9fs_qid2ino(struct p9_qid *qid);
-void v9fs_stat2inode(struct p9_wstat *, struct inode *, struct super_block *);
-void v9fs_stat2inode_dotl(struct p9_stat_dotl *, struct inode *);
+void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
+		      struct super_block *sb, unsigned int flags);
+void v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
+			   unsigned int flags);
 int v9fs_dir_release(struct inode *inode, struct file *filp);
 int v9fs_file_open(struct inode *inode, struct file *file);
 void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
@@ -83,4 +88,18 @@ static inline void v9fs_invalidate_inode_attr(struct inode *inode)
 }
 
 int v9fs_open_to_dotl_flags(int flags);
+
+static inline void v9fs_i_size_write(struct inode *inode, loff_t i_size)
+{
+	/*
+	 * 32-bit need the lock, concurrent updates could break the
+	 * sequences and make i_size_read() loop forever.
+	 * 64-bit updates are atomic and can skip the locking.
+	 */
+	if (sizeof(i_size) > sizeof(long))
+		spin_lock(&inode->i_lock);
+	i_size_write(inode, i_size);
+	if (sizeof(i_size) > sizeof(long))
+		spin_unlock(&inode->i_lock);
+}
 #endif
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index e7b3d2c4472d..62ce8b4a7e5f 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -442,7 +442,11 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		i_size = i_size_read(inode);
 		if (iocb->ki_pos > i_size) {
 			inode_add_bytes(inode, iocb->ki_pos - i_size);
-			i_size_write(inode, iocb->ki_pos);
+			/*
+			 * Need to serialize against i_size_write() in
+			 * v9fs_stat2inode()
+			 */
+			v9fs_i_size_write(inode, iocb->ki_pos);
 		}
 		return retval;
 	}
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 73f1d1b3a51c..2de1505aedfd 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -244,7 +244,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb)
 		return NULL;
 #ifdef CONFIG_9P_FSCACHE
 	v9inode->fscache = NULL;
-	spin_lock_init(&v9inode->fscache_lock);
+	mutex_init(&v9inode->fscache_lock);
 #endif
 	v9inode->writeback_fid = NULL;
 	v9inode->cache_validity = 0;
@@ -538,7 +538,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb,
 	if (retval)
 		goto error;
 
-	v9fs_stat2inode(st, inode, sb);
+	v9fs_stat2inode(st, inode, sb, 0);
 	v9fs_cache_inode_get_cookie(inode);
 	unlock_new_inode(inode);
 	return inode;
@@ -1074,7 +1074,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	if (IS_ERR(st))
 		return PTR_ERR(st);
 
-	v9fs_stat2inode(st, d_inode(dentry), d_inode(dentry)->i_sb);
+	v9fs_stat2inode(st, d_inode(dentry), d_inode(dentry)->i_sb, 0);
 	generic_fillattr(d_inode(dentry), stat);
 
 	p9stat_free(st);
@@ -1152,12 +1152,13 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
  * @stat: Plan 9 metadata (mistat) structure
  * @inode: inode to populate
  * @sb: superblock of filesystem
+ * @flags: control flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE)
  *
  */
 
 void
 v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
-	struct super_block *sb)
+		 struct super_block *sb, unsigned int flags)
 {
 	umode_t mode;
 	char ext[32];
@@ -1198,10 +1199,11 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
 	mode = p9mode2perm(v9ses, stat);
 	mode |= inode->i_mode & ~S_IALLUGO;
 	inode->i_mode = mode;
-	i_size_write(inode, stat->length);
 
+	if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
+		v9fs_i_size_write(inode, stat->length);
 	/* not real number of blocks, but 512 byte ones ... */
-	inode->i_blocks = (i_size_read(inode) + 512 - 1) >> 9;
+	inode->i_blocks = (stat->length + 512 - 1) >> 9;
 	v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR;
 }
 
@@ -1389,9 +1391,9 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode)
 {
 	int umode;
 	dev_t rdev;
-	loff_t i_size;
 	struct p9_wstat *st;
 	struct v9fs_session_info *v9ses;
+	unsigned int flags;
 
 	v9ses = v9fs_inode2v9ses(inode);
 	st = p9_client_stat(fid);
@@ -1404,16 +1406,13 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode)
 	if ((inode->i_mode & S_IFMT) != (umode & S_IFMT))
 		goto out;
 
-	spin_lock(&inode->i_lock);
 	/*
 	 * We don't want to refresh inode->i_size,
 	 * because we may have cached data
 	 */
-	i_size = inode->i_size;
-	v9fs_stat2inode(st, inode, inode->i_sb);
-	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
-		inode->i_size = i_size;
-	spin_unlock(&inode->i_lock);
+	flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ?
+		V9FS_STAT2INODE_KEEP_ISIZE : 0;
+	v9fs_stat2inode(st, inode, inode->i_sb, flags);
 out:
 	p9stat_free(st);
 	kfree(st);
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 0b88744c6446..7ae67fcca031 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -143,7 +143,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
 	if (retval)
 		goto error;
 
-	v9fs_stat2inode_dotl(st, inode);
+	v9fs_stat2inode_dotl(st, inode, 0);
 	v9fs_cache_inode_get_cookie(inode);
 	retval = v9fs_get_acl(inode, fid);
 	if (retval)
@@ -498,7 +498,7 @@ v9fs_vfs_getattr_dotl(struct vfsmount *mnt, struct dentry *dentry,
 	if (IS_ERR(st))
 		return PTR_ERR(st);
 
-	v9fs_stat2inode_dotl(st, d_inode(dentry));
+	v9fs_stat2inode_dotl(st, d_inode(dentry), 0);
 	generic_fillattr(d_inode(dentry), stat);
 	/* Change block size to what the server returned */
 	stat->blksize = st->st_blksize;
@@ -609,11 +609,13 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
  * v9fs_stat2inode_dotl - populate an inode structure with stat info
  * @stat: stat structure
  * @inode: inode to populate
+ * @flags: ctrl flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE)
  *
  */
 
 void
-v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode)
+v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
+		      unsigned int flags)
 {
 	umode_t mode;
 	struct v9fs_inode *v9inode = V9FS_I(inode);
@@ -633,7 +635,8 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode)
 		mode |= inode->i_mode & ~S_IALLUGO;
 		inode->i_mode = mode;
 
-		i_size_write(inode, stat->st_size);
+		if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
+			v9fs_i_size_write(inode, stat->st_size);
 		inode->i_blocks = stat->st_blocks;
 	} else {
 		if (stat->st_result_mask & P9_STATS_ATIME) {
@@ -663,8 +666,9 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode)
 		}
 		if (stat->st_result_mask & P9_STATS_RDEV)
 			inode->i_rdev = new_decode_dev(stat->st_rdev);
-		if (stat->st_result_mask & P9_STATS_SIZE)
-			i_size_write(inode, stat->st_size);
+		if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) &&
+		    stat->st_result_mask & P9_STATS_SIZE)
+			v9fs_i_size_write(inode, stat->st_size);
 		if (stat->st_result_mask & P9_STATS_BLOCKS)
 			inode->i_blocks = stat->st_blocks;
 	}
@@ -926,9 +930,9 @@ v9fs_vfs_follow_link_dotl(struct dentry *dentry, void **cookie)
 
 int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
 {
-	loff_t i_size;
 	struct p9_stat_dotl *st;
 	struct v9fs_session_info *v9ses;
+	unsigned int flags;
 
 	v9ses = v9fs_inode2v9ses(inode);
 	st = p9_client_getattr_dotl(fid, P9_STATS_ALL);
@@ -940,16 +944,13 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
 	if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT))
 		goto out;
 
-	spin_lock(&inode->i_lock);
 	/*
 	 * We don't want to refresh inode->i_size,
 	 * because we may have cached data
 	 */
-	i_size = inode->i_size;
-	v9fs_stat2inode_dotl(st, inode);
-	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
-		inode->i_size = i_size;
-	spin_unlock(&inode->i_lock);
+	flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ?
+		V9FS_STAT2INODE_KEEP_ISIZE : 0;
+	v9fs_stat2inode_dotl(st, inode, flags);
 out:
 	kfree(st);
 	return 0;
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index bf495cedec26..ccf935d9e722 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -165,7 +165,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 			goto release_sb;
 		}
 		d_inode(root)->i_ino = v9fs_qid2ino(&st->qid);
-		v9fs_stat2inode_dotl(st, d_inode(root));
+		v9fs_stat2inode_dotl(st, d_inode(root), 0);
 		kfree(st);
 	} else {
 		struct p9_wstat *st = NULL;
@@ -176,7 +176,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 		}
 
 		d_inode(root)->i_ino = v9fs_qid2ino(&st->qid);
-		v9fs_stat2inode(st, d_inode(root), sb);
+		v9fs_stat2inode(st, d_inode(root), sb, 0);
 
 		p9stat_free(st);
 		kfree(st);
diff --git a/fs/aio.c b/fs/aio.c
index c283eb03cb38..7187d03aa0bc 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -40,6 +40,7 @@
 #include <linux/ramfs.h>
 #include <linux/percpu-refcount.h>
 #include <linux/mount.h>
+#include <linux/nospec.h>
 
 #include <asm/kmap_types.h>
 #include <asm/uaccess.h>
@@ -1063,6 +1064,7 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 	if (!table || id >= table->nr)
 		goto out;
 
+	id = array_index_nospec(id, table->nr);
 	ctx = rcu_dereference(table->table[id]);
 	if (ctx && ctx->user_id == ctx_id) {
 		if (percpu_ref_tryget_live(&ctx->users))
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 7a5a598a2d94..0d8b9c4f27f2 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -560,7 +560,6 @@ int autofs4_expire_run(struct super_block *sb,
 	pkt.len = dentry->d_name.len;
 	memcpy(pkt.name, dentry->d_name.name, pkt.len);
 	pkt.name[pkt.len] = '\0';
-	dput(dentry);
 
 	if ( copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)) )
 		ret = -EFAULT;
@@ -573,6 +572,8 @@ int autofs4_expire_run(struct super_block *sb,
 	complete_all(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
 
+	dput(dentry);
+
 	return ret;
 }
 
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 1132fe71b312..0fd472d67029 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -255,8 +255,10 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	}
 	root_inode = autofs4_get_inode(s, S_IFDIR | 0755);
 	root = d_make_root(root_inode);
-	if (!root)
+	if (!root) {
+		ret = -ENOMEM;
 		goto fail_ino;
+	}
 	pipe = NULL;
 
 	root->d_fsdata = ino;
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 6d1d0b93b1aa..c792df826e12 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -9,7 +9,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   export.o tree-log.o free-space-cache.o zlib.o lzo.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
 	   reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
-	   uuid-tree.o props.o hash.o
+	   uuid-tree.o props.o hash.o tree-checker.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 38ee08675468..8f4baa3cb992 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1726,20 +1726,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 	return err;
 }
 
-/*
- * The leaf data grows from end-to-front in the node.
- * this returns the address of the start of the last item,
- * which is the stop of the leaf data stack
- */
-static inline unsigned int leaf_data_end(struct btrfs_root *root,
-					 struct extent_buffer *leaf)
-{
-	u32 nr = btrfs_header_nritems(leaf);
-	if (nr == 0)
-		return BTRFS_LEAF_DATA_SIZE(root);
-	return btrfs_item_offset_nr(leaf, nr - 1);
-}
-
 
 /*
  * search for key in the extent_buffer.  The items start at offset p,
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index e847573c6db0..4a91d3119e59 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -35,6 +35,7 @@
 #include <linux/btrfs.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
+#include <linux/sizes.h>
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
@@ -897,6 +898,7 @@ struct btrfs_balance_item {
 #define BTRFS_FILE_EXTENT_INLINE 0
 #define BTRFS_FILE_EXTENT_REG 1
 #define BTRFS_FILE_EXTENT_PREALLOC 2
+#define BTRFS_FILE_EXTENT_TYPES	2
 
 struct btrfs_file_extent_item {
 	/*
@@ -2283,7 +2285,7 @@ do {                                                                   \
 #define BTRFS_INODE_ROOT_ITEM_INIT	(1 << 31)
 
 struct btrfs_map_token {
-	struct extent_buffer *eb;
+	const struct extent_buffer *eb;
 	char *kaddr;
 	unsigned long offset;
 };
@@ -2314,18 +2316,19 @@ static inline void btrfs_init_map_token (struct btrfs_map_token *token)
 			   sizeof(((type *)0)->member)))
 
 #define DECLARE_BTRFS_SETGET_BITS(bits)					\
-u##bits btrfs_get_token_##bits(struct extent_buffer *eb, void *ptr,	\
-			       unsigned long off,			\
-                              struct btrfs_map_token *token);		\
-void btrfs_set_token_##bits(struct extent_buffer *eb, void *ptr,	\
+u##bits btrfs_get_token_##bits(const struct extent_buffer *eb,		\
+			       const void *ptr, unsigned long off,	\
+			       struct btrfs_map_token *token);		\
+void btrfs_set_token_##bits(struct extent_buffer *eb, const void *ptr,	\
 			    unsigned long off, u##bits val,		\
 			    struct btrfs_map_token *token);		\
-static inline u##bits btrfs_get_##bits(struct extent_buffer *eb, void *ptr, \
+static inline u##bits btrfs_get_##bits(const struct extent_buffer *eb,	\
+				       const void *ptr,			\
 				       unsigned long off)		\
 {									\
 	return btrfs_get_token_##bits(eb, ptr, off, NULL);		\
 }									\
-static inline void btrfs_set_##bits(struct extent_buffer *eb, void *ptr, \
+static inline void btrfs_set_##bits(struct extent_buffer *eb, void *ptr,\
 				    unsigned long off, u##bits val)	\
 {									\
        btrfs_set_token_##bits(eb, ptr, off, val, NULL);			\
@@ -2337,7 +2340,8 @@ DECLARE_BTRFS_SETGET_BITS(32)
 DECLARE_BTRFS_SETGET_BITS(64)
 
 #define BTRFS_SETGET_FUNCS(name, type, member, bits)			\
-static inline u##bits btrfs_##name(struct extent_buffer *eb, type *s)	\
+static inline u##bits btrfs_##name(const struct extent_buffer *eb,	\
+				   const type *s)			\
 {									\
 	BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member);	\
 	return btrfs_get_##bits(eb, s, offsetof(type, member));		\
@@ -2348,7 +2352,8 @@ static inline void btrfs_set_##name(struct extent_buffer *eb, type *s,	\
 	BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member);	\
 	btrfs_set_##bits(eb, s, offsetof(type, member), val);		\
 }									\
-static inline u##bits btrfs_token_##name(struct extent_buffer *eb, type *s, \
+static inline u##bits btrfs_token_##name(const struct extent_buffer *eb,\
+					 const type *s,			\
 					 struct btrfs_map_token *token)	\
 {									\
 	BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member);	\
@@ -2363,9 +2368,9 @@ static inline void btrfs_set_token_##name(struct extent_buffer *eb,	\
 }
 
 #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits)		\
-static inline u##bits btrfs_##name(struct extent_buffer *eb)		\
+static inline u##bits btrfs_##name(const struct extent_buffer *eb)	\
 {									\
-	type *p = page_address(eb->pages[0]);				\
+	const type *p = page_address(eb->pages[0]);			\
 	u##bits res = le##bits##_to_cpu(p->member);			\
 	return res;							\
 }									\
@@ -2377,7 +2382,7 @@ static inline void btrfs_set_##name(struct extent_buffer *eb,		\
 }
 
 #define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits)		\
-static inline u##bits btrfs_##name(type *s)				\
+static inline u##bits btrfs_##name(const type *s)			\
 {									\
 	return le##bits##_to_cpu(s->member);				\
 }									\
@@ -2678,7 +2683,7 @@ static inline unsigned long btrfs_node_key_ptr_offset(int nr)
 		sizeof(struct btrfs_key_ptr) * nr;
 }
 
-void btrfs_node_key(struct extent_buffer *eb,
+void btrfs_node_key(const struct extent_buffer *eb,
 		    struct btrfs_disk_key *disk_key, int nr);
 
 static inline void btrfs_set_node_key(struct extent_buffer *eb,
@@ -2707,28 +2712,28 @@ static inline struct btrfs_item *btrfs_item_nr(int nr)
 	return (struct btrfs_item *)btrfs_item_nr_offset(nr);
 }
 
-static inline u32 btrfs_item_end(struct extent_buffer *eb,
+static inline u32 btrfs_item_end(const struct extent_buffer *eb,
 				 struct btrfs_item *item)
 {
 	return btrfs_item_offset(eb, item) + btrfs_item_size(eb, item);
 }
 
-static inline u32 btrfs_item_end_nr(struct extent_buffer *eb, int nr)
+static inline u32 btrfs_item_end_nr(const struct extent_buffer *eb, int nr)
 {
 	return btrfs_item_end(eb, btrfs_item_nr(nr));
 }
 
-static inline u32 btrfs_item_offset_nr(struct extent_buffer *eb, int nr)
+static inline u32 btrfs_item_offset_nr(const struct extent_buffer *eb, int nr)
 {
 	return btrfs_item_offset(eb, btrfs_item_nr(nr));
 }
 
-static inline u32 btrfs_item_size_nr(struct extent_buffer *eb, int nr)
+static inline u32 btrfs_item_size_nr(const struct extent_buffer *eb, int nr)
 {
 	return btrfs_item_size(eb, btrfs_item_nr(nr));
 }
 
-static inline void btrfs_item_key(struct extent_buffer *eb,
+static inline void btrfs_item_key(const struct extent_buffer *eb,
 			   struct btrfs_disk_key *disk_key, int nr)
 {
 	struct btrfs_item *item = btrfs_item_nr(nr);
@@ -2764,8 +2769,8 @@ BTRFS_SETGET_STACK_FUNCS(stack_dir_name_len, struct btrfs_dir_item,
 BTRFS_SETGET_STACK_FUNCS(stack_dir_transid, struct btrfs_dir_item,
 			 transid, 64);
 
-static inline void btrfs_dir_item_key(struct extent_buffer *eb,
-				      struct btrfs_dir_item *item,
+static inline void btrfs_dir_item_key(const struct extent_buffer *eb,
+				      const struct btrfs_dir_item *item,
 				      struct btrfs_disk_key *key)
 {
 	read_eb_member(eb, item, struct btrfs_dir_item, location, key);
@@ -2773,7 +2778,7 @@ static inline void btrfs_dir_item_key(struct extent_buffer *eb,
 
 static inline void btrfs_set_dir_item_key(struct extent_buffer *eb,
 					  struct btrfs_dir_item *item,
-					  struct btrfs_disk_key *key)
+					  const struct btrfs_disk_key *key)
 {
 	write_eb_member(eb, item, struct btrfs_dir_item, location, key);
 }
@@ -2785,8 +2790,8 @@ BTRFS_SETGET_FUNCS(free_space_bitmaps, struct btrfs_free_space_header,
 BTRFS_SETGET_FUNCS(free_space_generation, struct btrfs_free_space_header,
 		   generation, 64);
 
-static inline void btrfs_free_space_key(struct extent_buffer *eb,
-					struct btrfs_free_space_header *h,
+static inline void btrfs_free_space_key(const struct extent_buffer *eb,
+					const struct btrfs_free_space_header *h,
 					struct btrfs_disk_key *key)
 {
 	read_eb_member(eb, h, struct btrfs_free_space_header, location, key);
@@ -2794,7 +2799,7 @@ static inline void btrfs_free_space_key(struct extent_buffer *eb,
 
 static inline void btrfs_set_free_space_key(struct extent_buffer *eb,
 					    struct btrfs_free_space_header *h,
-					    struct btrfs_disk_key *key)
+					    const struct btrfs_disk_key *key)
 {
 	write_eb_member(eb, h, struct btrfs_free_space_header, location, key);
 }
@@ -2821,25 +2826,25 @@ static inline void btrfs_cpu_key_to_disk(struct btrfs_disk_key *disk,
 	disk->objectid = cpu_to_le64(cpu->objectid);
 }
 
-static inline void btrfs_node_key_to_cpu(struct extent_buffer *eb,
-				  struct btrfs_key *key, int nr)
+static inline void btrfs_node_key_to_cpu(const struct extent_buffer *eb,
+					 struct btrfs_key *key, int nr)
 {
 	struct btrfs_disk_key disk_key;
 	btrfs_node_key(eb, &disk_key, nr);
 	btrfs_disk_key_to_cpu(key, &disk_key);
 }
 
-static inline void btrfs_item_key_to_cpu(struct extent_buffer *eb,
-				  struct btrfs_key *key, int nr)
+static inline void btrfs_item_key_to_cpu(const struct extent_buffer *eb,
+					 struct btrfs_key *key, int nr)
 {
 	struct btrfs_disk_key disk_key;
 	btrfs_item_key(eb, &disk_key, nr);
 	btrfs_disk_key_to_cpu(key, &disk_key);
 }
 
-static inline void btrfs_dir_item_key_to_cpu(struct extent_buffer *eb,
-				      struct btrfs_dir_item *item,
-				      struct btrfs_key *key)
+static inline void btrfs_dir_item_key_to_cpu(const struct extent_buffer *eb,
+					     const struct btrfs_dir_item *item,
+					     struct btrfs_key *key)
 {
 	struct btrfs_disk_key disk_key;
 	btrfs_dir_item_key(eb, item, &disk_key);
@@ -2872,7 +2877,7 @@ BTRFS_SETGET_STACK_FUNCS(stack_header_nritems, struct btrfs_header,
 			 nritems, 32);
 BTRFS_SETGET_STACK_FUNCS(stack_header_bytenr, struct btrfs_header, bytenr, 64);
 
-static inline int btrfs_header_flag(struct extent_buffer *eb, u64 flag)
+static inline int btrfs_header_flag(const struct extent_buffer *eb, u64 flag)
 {
 	return (btrfs_header_flags(eb) & flag) == flag;
 }
@@ -2891,7 +2896,7 @@ static inline int btrfs_clear_header_flag(struct extent_buffer *eb, u64 flag)
 	return (flags & flag) == flag;
 }
 
-static inline int btrfs_header_backref_rev(struct extent_buffer *eb)
+static inline int btrfs_header_backref_rev(const struct extent_buffer *eb)
 {
 	u64 flags = btrfs_header_flags(eb);
 	return flags >> BTRFS_BACKREF_REV_SHIFT;
@@ -2911,12 +2916,12 @@ static inline unsigned long btrfs_header_fsid(void)
 	return offsetof(struct btrfs_header, fsid);
 }
 
-static inline unsigned long btrfs_header_chunk_tree_uuid(struct extent_buffer *eb)
+static inline unsigned long btrfs_header_chunk_tree_uuid(const struct extent_buffer *eb)
 {
 	return offsetof(struct btrfs_header, chunk_tree_uuid);
 }
 
-static inline int btrfs_is_leaf(struct extent_buffer *eb)
+static inline int btrfs_is_leaf(const struct extent_buffer *eb)
 {
 	return btrfs_header_level(eb) == 0;
 }
@@ -2950,12 +2955,12 @@ BTRFS_SETGET_STACK_FUNCS(root_stransid, struct btrfs_root_item,
 BTRFS_SETGET_STACK_FUNCS(root_rtransid, struct btrfs_root_item,
 			 rtransid, 64);
 
-static inline bool btrfs_root_readonly(struct btrfs_root *root)
+static inline bool btrfs_root_readonly(const struct btrfs_root *root)
 {
 	return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_RDONLY)) != 0;
 }
 
-static inline bool btrfs_root_dead(struct btrfs_root *root)
+static inline bool btrfs_root_dead(const struct btrfs_root *root)
 {
 	return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0;
 }
@@ -3012,51 +3017,51 @@ BTRFS_SETGET_STACK_FUNCS(backup_num_devices, struct btrfs_root_backup,
 /* struct btrfs_balance_item */
 BTRFS_SETGET_FUNCS(balance_flags, struct btrfs_balance_item, flags, 64);
 
-static inline void btrfs_balance_data(struct extent_buffer *eb,
-				      struct btrfs_balance_item *bi,
+static inline void btrfs_balance_data(const struct extent_buffer *eb,
+				      const struct btrfs_balance_item *bi,
 				      struct btrfs_disk_balance_args *ba)
 {
 	read_eb_member(eb, bi, struct btrfs_balance_item, data, ba);
 }
 
 static inline void btrfs_set_balance_data(struct extent_buffer *eb,
-					  struct btrfs_balance_item *bi,
-					  struct btrfs_disk_balance_args *ba)
+				  struct btrfs_balance_item *bi,
+				  const struct btrfs_disk_balance_args *ba)
 {
 	write_eb_member(eb, bi, struct btrfs_balance_item, data, ba);
 }
 
-static inline void btrfs_balance_meta(struct extent_buffer *eb,
-				      struct btrfs_balance_item *bi,
+static inline void btrfs_balance_meta(const struct extent_buffer *eb,
+				      const struct btrfs_balance_item *bi,
 				      struct btrfs_disk_balance_args *ba)
 {
 	read_eb_member(eb, bi, struct btrfs_balance_item, meta, ba);
 }
 
 static inline void btrfs_set_balance_meta(struct extent_buffer *eb,
-					  struct btrfs_balance_item *bi,
-					  struct btrfs_disk_balance_args *ba)
+				  struct btrfs_balance_item *bi,
+				  const struct btrfs_disk_balance_args *ba)
 {
 	write_eb_member(eb, bi, struct btrfs_balance_item, meta, ba);
 }
 
-static inline void btrfs_balance_sys(struct extent_buffer *eb,
-				     struct btrfs_balance_item *bi,
+static inline void btrfs_balance_sys(const struct extent_buffer *eb,
+				     const struct btrfs_balance_item *bi,
 				     struct btrfs_disk_balance_args *ba)
 {
 	read_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
 }
 
 static inline void btrfs_set_balance_sys(struct extent_buffer *eb,
-					 struct btrfs_balance_item *bi,
-					 struct btrfs_disk_balance_args *ba)
+				 struct btrfs_balance_item *bi,
+				 const struct btrfs_disk_balance_args *ba)
 {
 	write_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
 }
 
 static inline void
 btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
-			       struct btrfs_disk_balance_args *disk)
+			       const struct btrfs_disk_balance_args *disk)
 {
 	memset(cpu, 0, sizeof(*cpu));
 
@@ -3076,7 +3081,7 @@ btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
 
 static inline void
 btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
-			       struct btrfs_balance_args *cpu)
+			       const struct btrfs_balance_args *cpu)
 {
 	memset(disk, 0, sizeof(*disk));
 
@@ -3144,7 +3149,7 @@ BTRFS_SETGET_STACK_FUNCS(super_magic, struct btrfs_super_block, magic, 64);
 BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
 			 uuid_tree_generation, 64);
 
-static inline int btrfs_super_csum_size(struct btrfs_super_block *s)
+static inline int btrfs_super_csum_size(const struct btrfs_super_block *s)
 {
 	u16 t = btrfs_super_csum_type(s);
 	/*
@@ -3158,6 +3163,21 @@ static inline unsigned long btrfs_leaf_data(struct extent_buffer *l)
 	return offsetof(struct btrfs_leaf, items);
 }
 
+/*
+ * The leaf data grows from end-to-front in the node.
+ * this returns the address of the start of the last item,
+ * which is the stop of the leaf data stack
+ */
+static inline unsigned int leaf_data_end(const struct btrfs_root *root,
+					 const struct extent_buffer *leaf)
+{
+	u32 nr = btrfs_header_nritems(leaf);
+
+	if (nr == 0)
+		return BTRFS_LEAF_DATA_SIZE(root);
+	return btrfs_item_offset_nr(leaf, nr - 1);
+}
+
 /* struct btrfs_file_extent_item */
 BTRFS_SETGET_FUNCS(file_extent_type, struct btrfs_file_extent_item, type, 8);
 BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_bytenr,
@@ -3174,7 +3194,7 @@ BTRFS_SETGET_STACK_FUNCS(stack_file_extent_compression,
 			 struct btrfs_file_extent_item, compression, 8);
 
 static inline unsigned long
-btrfs_file_extent_inline_start(struct btrfs_file_extent_item *e)
+btrfs_file_extent_inline_start(const struct btrfs_file_extent_item *e)
 {
 	return (unsigned long)e + BTRFS_FILE_EXTENT_INLINE_DATA_START;
 }
@@ -3208,8 +3228,9 @@ BTRFS_SETGET_FUNCS(file_extent_other_encoding, struct btrfs_file_extent_item,
  * size of any extent headers.  If a file is compressed on disk, this is
  * the compressed size
  */
-static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb,
-						    struct btrfs_item *e)
+static inline u32 btrfs_file_extent_inline_item_len(
+						const struct extent_buffer *eb,
+						struct btrfs_item *e)
 {
 	return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START;
 }
@@ -3217,9 +3238,9 @@ static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb,
 /* this returns the number of file bytes represented by the inline item.
  * If an item is compressed, this is the uncompressed size
  */
-static inline u32 btrfs_file_extent_inline_len(struct extent_buffer *eb,
-					       int slot,
-					       struct btrfs_file_extent_item *fi)
+static inline u32 btrfs_file_extent_inline_len(const struct extent_buffer *eb,
+					int slot,
+					const struct btrfs_file_extent_item *fi)
 {
 	struct btrfs_map_token token;
 
@@ -3241,8 +3262,8 @@ static inline u32 btrfs_file_extent_inline_len(struct extent_buffer *eb,
 
 
 /* btrfs_dev_stats_item */
-static inline u64 btrfs_dev_stats_value(struct extent_buffer *eb,
-					struct btrfs_dev_stats_item *ptr,
+static inline u64 btrfs_dev_stats_value(const struct extent_buffer *eb,
+					const struct btrfs_dev_stats_item *ptr,
 					int index)
 {
 	u64 val;
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 176a27bc63aa..81e5bc62e8e3 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -620,7 +620,7 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
 		em = lookup_extent_mapping(em_tree, start, (u64)-1);
 		if (!em)
 			break;
-		map = (struct map_lookup *)em->bdev;
+		map = em->map_lookup;
 		for (i = 0; i < map->num_stripes; i++)
 			if (srcdev == map->stripes[i].dev)
 				map->stripes[i].dev = tgtdev;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1f21c6c33228..78722aaffecd 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -49,6 +49,7 @@
 #include "raid56.h"
 #include "sysfs.h"
 #include "qgroup.h"
+#include "tree-checker.h"
 
 #ifdef CONFIG_X86
 #include <asm/cpufeature.h>
@@ -522,72 +523,6 @@ static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
 	return ret;
 }
 
-#define CORRUPT(reason, eb, root, slot)				\
-	btrfs_crit(root->fs_info, "corrupt leaf, %s: block=%llu,"	\
-		   "root=%llu, slot=%d", reason,			\
-	       btrfs_header_bytenr(eb),	root->objectid, slot)
-
-static noinline int check_leaf(struct btrfs_root *root,
-			       struct extent_buffer *leaf)
-{
-	struct btrfs_key key;
-	struct btrfs_key leaf_key;
-	u32 nritems = btrfs_header_nritems(leaf);
-	int slot;
-
-	if (nritems == 0)
-		return 0;
-
-	/* Check the 0 item */
-	if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
-	    BTRFS_LEAF_DATA_SIZE(root)) {
-		CORRUPT("invalid item offset size pair", leaf, root, 0);
-		return -EIO;
-	}
-
-	/*
-	 * Check to make sure each items keys are in the correct order and their
-	 * offsets make sense.  We only have to loop through nritems-1 because
-	 * we check the current slot against the next slot, which verifies the
-	 * next slot's offset+size makes sense and that the current's slot
-	 * offset is correct.
-	 */
-	for (slot = 0; slot < nritems - 1; slot++) {
-		btrfs_item_key_to_cpu(leaf, &leaf_key, slot);
-		btrfs_item_key_to_cpu(leaf, &key, slot + 1);
-
-		/* Make sure the keys are in the right order */
-		if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) {
-			CORRUPT("bad key order", leaf, root, slot);
-			return -EIO;
-		}
-
-		/*
-		 * Make sure the offset and ends are right, remember that the
-		 * item data starts at the end of the leaf and grows towards the
-		 * front.
-		 */
-		if (btrfs_item_offset_nr(leaf, slot) !=
-			btrfs_item_end_nr(leaf, slot + 1)) {
-			CORRUPT("slot offset bad", leaf, root, slot);
-			return -EIO;
-		}
-
-		/*
-		 * Check to make sure that we don't point outside of the leaf,
-		 * just incase all the items are consistent to eachother, but
-		 * all point outside of the leaf.
-		 */
-		if (btrfs_item_end_nr(leaf, slot) >
-		    BTRFS_LEAF_DATA_SIZE(root)) {
-			CORRUPT("slot end outside of leaf", leaf, root, slot);
-			return -EIO;
-		}
-	}
-
-	return 0;
-}
-
 static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 				      u64 phy_offset, struct page *page,
 				      u64 start, u64 end, int mirror)
@@ -654,11 +589,14 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	 * that we don't try and read the other copies of this block, just
 	 * return -EIO.
 	 */
-	if (found_level == 0 && check_leaf(root, eb)) {
+	if (found_level == 0 && btrfs_check_leaf_full(root, eb)) {
 		set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
 		ret = -EIO;
 	}
 
+	if (found_level > 0 && btrfs_check_node(root, eb))
+		ret = -EIO;
+
 	if (!ret)
 		set_extent_buffer_uptodate(eb);
 err:
@@ -3958,7 +3896,13 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 				     buf->len,
 				     root->fs_info->dirty_metadata_batch);
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
-	if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) {
+	/*
+	 * Since btrfs_mark_buffer_dirty() can be called with item pointer set
+	 * but item data not updated.
+	 * So here we should only check item pointers, not item data.
+	 */
+	if (btrfs_header_level(buf) == 0 &&
+	    btrfs_check_leaf_relaxed(root, buf)) {
 		btrfs_print_leaf(root, buf);
 		ASSERT(0);
 	}
@@ -4167,6 +4111,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)
 		spin_lock(&fs_info->ordered_root_lock);
 	}
 	spin_unlock(&fs_info->ordered_root_lock);
+
+	/*
+	 * We need this here because if we've been flipped read-only we won't
+	 * get sync() from the umount, so we need to make sure any ordered
+	 * extents that haven't had their dirty pages IO start writeout yet
+	 * actually get run and error out properly.
+	 */
+	btrfs_wait_ordered_roots(fs_info, -1);
 }
 
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 13ff0fdae03e..978bbfed5a2c 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2342,7 +2342,13 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		ins.type = BTRFS_EXTENT_ITEM_KEY;
 	}
 
-	BUG_ON(node->ref_mod != 1);
+	if (node->ref_mod != 1) {
+		btrfs_err(root->fs_info,
+	"btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu",
+			  node->bytenr, node->ref_mod, node->action, ref_root,
+			  parent);
+		return -EIO;
+	}
 	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
 		BUG_ON(!extent_op || !extent_op->update_flags);
 		ret = alloc_reserved_tree_block(trans, root,
@@ -9481,6 +9487,8 @@ static int find_first_block_group(struct btrfs_root *root,
 	int ret = 0;
 	struct btrfs_key found_key;
 	struct extent_buffer *leaf;
+	struct btrfs_block_group_item bg;
+	u64 flags;
 	int slot;
 
 	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
@@ -9502,7 +9510,47 @@ static int find_first_block_group(struct btrfs_root *root,
 
 		if (found_key.objectid >= key->objectid &&
 		    found_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
-			ret = 0;
+			struct extent_map_tree *em_tree;
+			struct extent_map *em;
+
+			em_tree = &root->fs_info->mapping_tree.map_tree;
+			read_lock(&em_tree->lock);
+			em = lookup_extent_mapping(em_tree, found_key.objectid,
+						   found_key.offset);
+			read_unlock(&em_tree->lock);
+			if (!em) {
+				btrfs_err(root->fs_info,
+			"logical %llu len %llu found bg but no related chunk",
+					  found_key.objectid, found_key.offset);
+				ret = -ENOENT;
+			} else if (em->start != found_key.objectid ||
+				   em->len != found_key.offset) {
+				btrfs_err(root->fs_info,
+		"block group %llu len %llu mismatch with chunk %llu len %llu",
+					  found_key.objectid, found_key.offset,
+					  em->start, em->len);
+				ret = -EUCLEAN;
+			} else {
+				read_extent_buffer(leaf, &bg,
+					btrfs_item_ptr_offset(leaf, slot),
+					sizeof(bg));
+				flags = btrfs_block_group_flags(&bg) &
+					BTRFS_BLOCK_GROUP_TYPE_MASK;
+
+				if (flags != (em->map_lookup->type &
+					      BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+					btrfs_err(root->fs_info,
+"block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx",
+						found_key.objectid,
+						found_key.offset, flags,
+						(BTRFS_BLOCK_GROUP_TYPE_MASK &
+						 em->map_lookup->type));
+					ret = -EUCLEAN;
+				} else {
+					ret = 0;
+				}
+			}
+			free_extent_map(em);
 			goto out;
 		}
 		path->slots[0]++;
@@ -9717,6 +9765,62 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size)
 	return cache;
 }
 
+
+/*
+ * Iterate all chunks and verify that each of them has the corresponding block
+ * group
+ */
+static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
+	struct extent_map *em;
+	struct btrfs_block_group_cache *bg;
+	u64 start = 0;
+	int ret = 0;
+
+	while (1) {
+		read_lock(&map_tree->map_tree.lock);
+		/*
+		 * lookup_extent_mapping will return the first extent map
+		 * intersecting the range, so setting @len to 1 is enough to
+		 * get the first chunk.
+		 */
+		em = lookup_extent_mapping(&map_tree->map_tree, start, 1);
+		read_unlock(&map_tree->map_tree.lock);
+		if (!em)
+			break;
+
+		bg = btrfs_lookup_block_group(fs_info, em->start);
+		if (!bg) {
+			btrfs_err(fs_info,
+	"chunk start=%llu len=%llu doesn't have corresponding block group",
+				     em->start, em->len);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			break;
+		}
+		if (bg->key.objectid != em->start ||
+		    bg->key.offset != em->len ||
+		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
+		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+			btrfs_err(fs_info,
+"chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
+				em->start, em->len,
+				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
+				bg->key.objectid, bg->key.offset,
+				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			btrfs_put_block_group(bg);
+			break;
+		}
+		start = em->start + em->len;
+		free_extent_map(em);
+		btrfs_put_block_group(bg);
+	}
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_root *root)
 {
 	struct btrfs_path *path;
@@ -9903,7 +10007,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 	}
 
 	init_global_block_rsv(info);
-	ret = 0;
+	ret = check_chunk_block_group_mappings(info);
 error:
 	btrfs_free_path(path);
 	return ret;
@@ -10388,7 +10492,7 @@ btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info,
 	 * more device items and remove one chunk item), but this is done at
 	 * btrfs_remove_chunk() through a call to check_system_chunk().
 	 */
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	num_items = 3 + map->num_stripes;
 	free_extent_map(em);
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 88bee6703cc0..a18f558b4477 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3106,11 +3106,11 @@ static int __do_readpage(struct extent_io_tree *tree,
 		 */
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) &&
 		    prev_em_start && *prev_em_start != (u64)-1 &&
-		    *prev_em_start != em->orig_start)
+		    *prev_em_start != em->start)
 			force_bio_submit = true;
 
 		if (prev_em_start)
-			*prev_em_start = em->orig_start;
+			*prev_em_start = em->start;
 
 		free_extent_map(em);
 		em = NULL;
@@ -3847,8 +3847,10 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	struct block_device *bdev = fs_info->fs_devices->latest_bdev;
 	struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
 	u64 offset = eb->start;
+	u32 nritems;
 	unsigned long i, num_pages;
 	unsigned long bio_flags = 0;
+	unsigned long start, end;
 	int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
 	int ret = 0;
 
@@ -3858,6 +3860,23 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	if (btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID)
 		bio_flags = EXTENT_BIO_TREE_LOG;
 
+	/* set btree blocks beyond nritems with 0 to avoid stale content. */
+	nritems = btrfs_header_nritems(eb);
+	if (btrfs_header_level(eb) > 0) {
+		end = btrfs_node_key_ptr_offset(nritems);
+
+		memset_extent_buffer(eb, 0, end, eb->len - end);
+	} else {
+		/*
+		 * leaf:
+		 * header 0 1 2 .. N ... data_N .. data_2 data_1 data_0
+		 */
+		start = btrfs_item_nr_offset(nritems);
+		end = btrfs_leaf_data(eb) +
+		      leaf_data_end(fs_info->tree_root, eb);
+		memset_extent_buffer(eb, 0, start, end - start);
+	}
+
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = eb->pages[i];
 
@@ -5362,9 +5381,8 @@ unlock_exit:
 	return ret;
 }
 
-void read_extent_buffer(struct extent_buffer *eb, void *dstv,
-			unsigned long start,
-			unsigned long len)
+void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
+			unsigned long start, unsigned long len)
 {
 	size_t cur;
 	size_t offset;
@@ -5393,9 +5411,9 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv,
 	}
 }
 
-int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
-			unsigned long start,
-			unsigned long len)
+int read_extent_buffer_to_user(const struct extent_buffer *eb,
+			       void __user *dstv,
+			       unsigned long start, unsigned long len)
 {
 	size_t cur;
 	size_t offset;
@@ -5430,10 +5448,10 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
 	return ret;
 }
 
-int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
-			       unsigned long min_len, char **map,
-			       unsigned long *map_start,
-			       unsigned long *map_len)
+int map_private_extent_buffer(const struct extent_buffer *eb,
+			      unsigned long start, unsigned long min_len,
+			      char **map, unsigned long *map_start,
+			      unsigned long *map_len)
 {
 	size_t offset = start & (PAGE_CACHE_SIZE - 1);
 	char *kaddr;
@@ -5468,9 +5486,8 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 	return 0;
 }
 
-int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
-			  unsigned long start,
-			  unsigned long len)
+int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
+			 unsigned long start, unsigned long len)
 {
 	size_t cur;
 	size_t offset;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index f4c1ae11855f..751435967724 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -308,14 +308,13 @@ static inline void extent_buffer_get(struct extent_buffer *eb)
 	atomic_inc(&eb->refs);
 }
 
-int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
-			  unsigned long start,
-			  unsigned long len);
-void read_extent_buffer(struct extent_buffer *eb, void *dst,
+int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
+			 unsigned long start, unsigned long len);
+void read_extent_buffer(const struct extent_buffer *eb, void *dst,
 			unsigned long start,
 			unsigned long len);
-int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dst,
-			       unsigned long start,
+int read_extent_buffer_to_user(const struct extent_buffer *eb,
+			       void __user *dst, unsigned long start,
 			       unsigned long len);
 void write_extent_buffer(struct extent_buffer *eb, const void *src,
 			 unsigned long start, unsigned long len);
@@ -334,10 +333,10 @@ int set_extent_buffer_uptodate(struct extent_buffer *eb);
 int clear_extent_buffer_uptodate(struct extent_buffer *eb);
 int extent_buffer_uptodate(struct extent_buffer *eb);
 int extent_buffer_under_io(struct extent_buffer *eb);
-int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset,
-		      unsigned long min_len, char **map,
-		      unsigned long *map_start,
-		      unsigned long *map_len);
+int map_private_extent_buffer(const struct extent_buffer *eb,
+			      unsigned long offset, unsigned long min_len,
+			      char **map, unsigned long *map_start,
+			      unsigned long *map_len);
 int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
 int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
 int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 6a98bddd8f33..84fb56d5c018 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -76,7 +76,7 @@ void free_extent_map(struct extent_map *em)
 		WARN_ON(extent_map_in_tree(em));
 		WARN_ON(!list_empty(&em->list));
 		if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
-			kfree(em->bdev);
+			kfree(em->map_lookup);
 		kmem_cache_free(extent_map_cache, em);
 	}
 }
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index b2991fd8583e..eb8b8fae036b 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -32,7 +32,15 @@ struct extent_map {
 	u64 block_len;
 	u64 generation;
 	unsigned long flags;
-	struct block_device *bdev;
+	union {
+		struct block_device *bdev;
+
+		/*
+		 * used for chunk mappings
+		 * flags & EXTENT_FLAG_FS_MAPPING must be set
+		 */
+		struct map_lookup *map_lookup;
+	};
 	atomic_t refs;
 	unsigned int compress_type;
 	struct list_head list;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 6dca9f937bf6..cc9ccc42f469 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3460,7 +3460,7 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
 		return ret;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (em->start != chunk_offset)
 		goto out;
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 83c73738165e..40d1ab957fb6 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -3232,7 +3232,8 @@ static void free_pending_move(struct send_ctx *sctx, struct pending_dir_move *m)
 	kfree(m);
 }
 
-static void tail_append_pending_moves(struct pending_dir_move *moves,
+static void tail_append_pending_moves(struct send_ctx *sctx,
+				      struct pending_dir_move *moves,
 				      struct list_head *stack)
 {
 	if (list_empty(&moves->list)) {
@@ -3243,6 +3244,10 @@ static void tail_append_pending_moves(struct pending_dir_move *moves,
 		list_add_tail(&moves->list, stack);
 		list_splice_tail(&list, stack);
 	}
+	if (!RB_EMPTY_NODE(&moves->node)) {
+		rb_erase(&moves->node, &sctx->pending_dir_moves);
+		RB_CLEAR_NODE(&moves->node);
+	}
 }
 
 static int apply_children_dir_moves(struct send_ctx *sctx)
@@ -3257,7 +3262,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx)
 		return 0;
 
 	INIT_LIST_HEAD(&stack);
-	tail_append_pending_moves(pm, &stack);
+	tail_append_pending_moves(sctx, pm, &stack);
 
 	while (!list_empty(&stack)) {
 		pm = list_first_entry(&stack, struct pending_dir_move, list);
@@ -3268,7 +3273,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx)
 			goto out;
 		pm = get_pending_dir_moves(sctx, parent_ino);
 		if (pm)
-			tail_append_pending_moves(pm, &stack);
+			tail_append_pending_moves(sctx, pm, &stack);
 	}
 	return 0;
 
diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c
index b976597b0721..63ffd213b0b7 100644
--- a/fs/btrfs/struct-funcs.c
+++ b/fs/btrfs/struct-funcs.c
@@ -50,8 +50,8 @@ static inline void put_unaligned_le8(u8 val, void *p)
  */
 
 #define DEFINE_BTRFS_SETGET_BITS(bits)					\
-u##bits btrfs_get_token_##bits(struct extent_buffer *eb, void *ptr,	\
-			       unsigned long off,			\
+u##bits btrfs_get_token_##bits(const struct extent_buffer *eb,		\
+			       const void *ptr, unsigned long off,	\
 			       struct btrfs_map_token *token)		\
 {									\
 	unsigned long part_offset = (unsigned long)ptr;			\
@@ -90,7 +90,8 @@ u##bits btrfs_get_token_##bits(struct extent_buffer *eb, void *ptr,	\
 	return res;							\
 }									\
 void btrfs_set_token_##bits(struct extent_buffer *eb,			\
-			    void *ptr, unsigned long off, u##bits val,	\
+			    const void *ptr, unsigned long off,		\
+			    u##bits val,				\
 			    struct btrfs_map_token *token)		\
 {									\
 	unsigned long part_offset = (unsigned long)ptr;			\
@@ -133,7 +134,7 @@ DEFINE_BTRFS_SETGET_BITS(16)
 DEFINE_BTRFS_SETGET_BITS(32)
 DEFINE_BTRFS_SETGET_BITS(64)
 
-void btrfs_node_key(struct extent_buffer *eb,
+void btrfs_node_key(const struct extent_buffer *eb,
 		    struct btrfs_disk_key *disk_key, int nr)
 {
 	unsigned long ptr = btrfs_node_key_ptr_offset(nr);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
new file mode 100644
index 000000000000..5b98f3c76ce4
--- /dev/null
+++ b/fs/btrfs/tree-checker.c
@@ -0,0 +1,649 @@
+/*
+ * Copyright (C) Qu Wenruo 2017.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program.
+ */
+
+/*
+ * The module is used to catch unexpected/corrupted tree block data.
+ * Such behavior can be caused either by a fuzzed image or bugs.
+ *
+ * The objective is to do leaf/node validation checks when tree block is read
+ * from disk, and check *every* possible member, so other code won't
+ * need to checking them again.
+ *
+ * Due to the potential and unwanted damage, every checker needs to be
+ * carefully reviewed otherwise so it does not prevent mount of valid images.
+ */
+
+#include "ctree.h"
+#include "tree-checker.h"
+#include "disk-io.h"
+#include "compression.h"
+#include "hash.h"
+#include "volumes.h"
+
+#define CORRUPT(reason, eb, root, slot)					\
+	btrfs_crit(root->fs_info,					\
+		   "corrupt %s, %s: block=%llu, root=%llu, slot=%d",	\
+		   btrfs_header_level(eb) == 0 ? "leaf" : "node",	\
+		   reason, btrfs_header_bytenr(eb), root->objectid, slot)
+
+/*
+ * Error message should follow the following format:
+ * corrupt <type>: <identifier>, <reason>[, <bad_value>]
+ *
+ * @type:	leaf or node
+ * @identifier:	the necessary info to locate the leaf/node.
+ * 		It's recommened to decode key.objecitd/offset if it's
+ * 		meaningful.
+ * @reason:	describe the error
+ * @bad_value:	optional, it's recommened to output bad value and its
+ *		expected value (range).
+ *
+ * Since comma is used to separate the components, only space is allowed
+ * inside each component.
+ */
+
+/*
+ * Append generic "corrupt leaf/node root=%llu block=%llu slot=%d: " to @fmt.
+ * Allows callers to customize the output.
+ */
+__printf(4, 5)
+static void generic_err(const struct btrfs_root *root,
+			const struct extent_buffer *eb, int slot,
+			const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(root->fs_info,
+		"corrupt %s: root=%llu block=%llu slot=%d, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node",
+		root->objectid, btrfs_header_bytenr(eb), slot, &vaf);
+	va_end(args);
+}
+
+static int check_extent_data_item(struct btrfs_root *root,
+				  struct extent_buffer *leaf,
+				  struct btrfs_key *key, int slot)
+{
+	struct btrfs_file_extent_item *fi;
+	u32 sectorsize = root->sectorsize;
+	u32 item_size = btrfs_item_size_nr(leaf, slot);
+
+	if (!IS_ALIGNED(key->offset, sectorsize)) {
+		CORRUPT("unaligned key offset for file extent",
+			leaf, root, slot);
+		return -EUCLEAN;
+	}
+
+	fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+
+	if (btrfs_file_extent_type(leaf, fi) > BTRFS_FILE_EXTENT_TYPES) {
+		CORRUPT("invalid file extent type", leaf, root, slot);
+		return -EUCLEAN;
+	}
+
+	/*
+	 * Support for new compression/encrption must introduce incompat flag,
+	 * and must be caught in open_ctree().
+	 */
+	if (btrfs_file_extent_compression(leaf, fi) > BTRFS_COMPRESS_TYPES) {
+		CORRUPT("invalid file extent compression", leaf, root, slot);
+		return -EUCLEAN;
+	}
+	if (btrfs_file_extent_encryption(leaf, fi)) {
+		CORRUPT("invalid file extent encryption", leaf, root, slot);
+		return -EUCLEAN;
+	}
+	if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) {
+		/* Inline extent must have 0 as key offset */
+		if (key->offset) {
+			CORRUPT("inline extent has non-zero key offset",
+				leaf, root, slot);
+			return -EUCLEAN;
+		}
+
+		/* Compressed inline extent has no on-disk size, skip it */
+		if (btrfs_file_extent_compression(leaf, fi) !=
+		    BTRFS_COMPRESS_NONE)
+			return 0;
+
+		/* Uncompressed inline extent size must match item size */
+		if (item_size != BTRFS_FILE_EXTENT_INLINE_DATA_START +
+		    btrfs_file_extent_ram_bytes(leaf, fi)) {
+			CORRUPT("plaintext inline extent has invalid size",
+				leaf, root, slot);
+			return -EUCLEAN;
+		}
+		return 0;
+	}
+
+	/* Regular or preallocated extent has fixed item size */
+	if (item_size != sizeof(*fi)) {
+		CORRUPT(
+		"regluar or preallocated extent data item size is invalid",
+			leaf, root, slot);
+		return -EUCLEAN;
+	}
+	if (!IS_ALIGNED(btrfs_file_extent_ram_bytes(leaf, fi), sectorsize) ||
+	    !IS_ALIGNED(btrfs_file_extent_disk_bytenr(leaf, fi), sectorsize) ||
+	    !IS_ALIGNED(btrfs_file_extent_disk_num_bytes(leaf, fi), sectorsize) ||
+	    !IS_ALIGNED(btrfs_file_extent_offset(leaf, fi), sectorsize) ||
+	    !IS_ALIGNED(btrfs_file_extent_num_bytes(leaf, fi), sectorsize)) {
+		CORRUPT(
+		"regular or preallocated extent data item has unaligned value",
+			leaf, root, slot);
+		return -EUCLEAN;
+	}
+
+	return 0;
+}
+
+static int check_csum_item(struct btrfs_root *root, struct extent_buffer *leaf,
+			   struct btrfs_key *key, int slot)
+{
+	u32 sectorsize = root->sectorsize;
+	u32 csumsize = btrfs_super_csum_size(root->fs_info->super_copy);
+
+	if (key->objectid != BTRFS_EXTENT_CSUM_OBJECTID) {
+		CORRUPT("invalid objectid for csum item", leaf, root, slot);
+		return -EUCLEAN;
+	}
+	if (!IS_ALIGNED(key->offset, sectorsize)) {
+		CORRUPT("unaligned key offset for csum item", leaf, root, slot);
+		return -EUCLEAN;
+	}
+	if (!IS_ALIGNED(btrfs_item_size_nr(leaf, slot), csumsize)) {
+		CORRUPT("unaligned csum item size", leaf, root, slot);
+		return -EUCLEAN;
+	}
+	return 0;
+}
+
+/*
+ * Customized reported for dir_item, only important new info is key->objectid,
+ * which represents inode number
+ */
+__printf(4, 5)
+static void dir_item_err(const struct btrfs_root *root,
+			 const struct extent_buffer *eb, int slot,
+			 const char *fmt, ...)
+{
+	struct btrfs_key key;
+	struct va_format vaf;
+	va_list args;
+
+	btrfs_item_key_to_cpu(eb, &key, slot);
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(root->fs_info,
+	"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node", root->objectid,
+		btrfs_header_bytenr(eb), slot, key.objectid, &vaf);
+	va_end(args);
+}
+
+static int check_dir_item(struct btrfs_root *root,
+			  struct extent_buffer *leaf,
+			  struct btrfs_key *key, int slot)
+{
+	struct btrfs_dir_item *di;
+	u32 item_size = btrfs_item_size_nr(leaf, slot);
+	u32 cur = 0;
+
+	di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
+	while (cur < item_size) {
+		u32 name_len;
+		u32 data_len;
+		u32 max_name_len;
+		u32 total_size;
+		u32 name_hash;
+		u8 dir_type;
+
+		/* header itself should not cross item boundary */
+		if (cur + sizeof(*di) > item_size) {
+			dir_item_err(root, leaf, slot,
+		"dir item header crosses item boundary, have %zu boundary %u",
+				cur + sizeof(*di), item_size);
+			return -EUCLEAN;
+		}
+
+		/* dir type check */
+		dir_type = btrfs_dir_type(leaf, di);
+		if (dir_type >= BTRFS_FT_MAX) {
+			dir_item_err(root, leaf, slot,
+			"invalid dir item type, have %u expect [0, %u)",
+				dir_type, BTRFS_FT_MAX);
+			return -EUCLEAN;
+		}
+
+		if (key->type == BTRFS_XATTR_ITEM_KEY &&
+		    dir_type != BTRFS_FT_XATTR) {
+			dir_item_err(root, leaf, slot,
+		"invalid dir item type for XATTR key, have %u expect %u",
+				dir_type, BTRFS_FT_XATTR);
+			return -EUCLEAN;
+		}
+		if (dir_type == BTRFS_FT_XATTR &&
+		    key->type != BTRFS_XATTR_ITEM_KEY) {
+			dir_item_err(root, leaf, slot,
+			"xattr dir type found for non-XATTR key");
+			return -EUCLEAN;
+		}
+		if (dir_type == BTRFS_FT_XATTR)
+			max_name_len = XATTR_NAME_MAX;
+		else
+			max_name_len = BTRFS_NAME_LEN;
+
+		/* Name/data length check */
+		name_len = btrfs_dir_name_len(leaf, di);
+		data_len = btrfs_dir_data_len(leaf, di);
+		if (name_len > max_name_len) {
+			dir_item_err(root, leaf, slot,
+			"dir item name len too long, have %u max %u",
+				name_len, max_name_len);
+			return -EUCLEAN;
+		}
+		if (name_len + data_len > BTRFS_MAX_XATTR_SIZE(root)) {
+			dir_item_err(root, leaf, slot,
+			"dir item name and data len too long, have %u max %zu",
+				name_len + data_len,
+				BTRFS_MAX_XATTR_SIZE(root));
+			return -EUCLEAN;
+		}
+
+		if (data_len && dir_type != BTRFS_FT_XATTR) {
+			dir_item_err(root, leaf, slot,
+			"dir item with invalid data len, have %u expect 0",
+				data_len);
+			return -EUCLEAN;
+		}
+
+		total_size = sizeof(*di) + name_len + data_len;
+
+		/* header and name/data should not cross item boundary */
+		if (cur + total_size > item_size) {
+			dir_item_err(root, leaf, slot,
+		"dir item data crosses item boundary, have %u boundary %u",
+				cur + total_size, item_size);
+			return -EUCLEAN;
+		}
+
+		/*
+		 * Special check for XATTR/DIR_ITEM, as key->offset is name
+		 * hash, should match its name
+		 */
+		if (key->type == BTRFS_DIR_ITEM_KEY ||
+		    key->type == BTRFS_XATTR_ITEM_KEY) {
+			char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
+
+			read_extent_buffer(leaf, namebuf,
+					(unsigned long)(di + 1), name_len);
+			name_hash = btrfs_name_hash(namebuf, name_len);
+			if (key->offset != name_hash) {
+				dir_item_err(root, leaf, slot,
+		"name hash mismatch with key, have 0x%016x expect 0x%016llx",
+					name_hash, key->offset);
+				return -EUCLEAN;
+			}
+		}
+		cur += total_size;
+		di = (struct btrfs_dir_item *)((void *)di + total_size);
+	}
+	return 0;
+}
+
+__printf(4, 5)
+__cold
+static void block_group_err(const struct btrfs_fs_info *fs_info,
+			    const struct extent_buffer *eb, int slot,
+			    const char *fmt, ...)
+{
+	struct btrfs_key key;
+	struct va_format vaf;
+	va_list args;
+
+	btrfs_item_key_to_cpu(eb, &key, slot);
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(fs_info,
+	"corrupt %s: root=%llu block=%llu slot=%d bg_start=%llu bg_len=%llu, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node",
+		btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
+		key.objectid, key.offset, &vaf);
+	va_end(args);
+}
+
+static int check_block_group_item(struct btrfs_fs_info *fs_info,
+				  struct extent_buffer *leaf,
+				  struct btrfs_key *key, int slot)
+{
+	struct btrfs_block_group_item bgi;
+	u32 item_size = btrfs_item_size_nr(leaf, slot);
+	u64 flags;
+	u64 type;
+
+	/*
+	 * Here we don't really care about alignment since extent allocator can
+	 * handle it.  We care more about the size, as if one block group is
+	 * larger than maximum size, it's must be some obvious corruption.
+	 */
+	if (key->offset > BTRFS_MAX_DATA_CHUNK_SIZE || key->offset == 0) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid block group size, have %llu expect (0, %llu]",
+				key->offset, BTRFS_MAX_DATA_CHUNK_SIZE);
+		return -EUCLEAN;
+	}
+
+	if (item_size != sizeof(bgi)) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid item size, have %u expect %zu",
+				item_size, sizeof(bgi));
+		return -EUCLEAN;
+	}
+
+	read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
+			   sizeof(bgi));
+	if (btrfs_block_group_chunk_objectid(&bgi) !=
+	    BTRFS_FIRST_CHUNK_TREE_OBJECTID) {
+		block_group_err(fs_info, leaf, slot,
+		"invalid block group chunk objectid, have %llu expect %llu",
+				btrfs_block_group_chunk_objectid(&bgi),
+				BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+		return -EUCLEAN;
+	}
+
+	if (btrfs_block_group_used(&bgi) > key->offset) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid block group used, have %llu expect [0, %llu)",
+				btrfs_block_group_used(&bgi), key->offset);
+		return -EUCLEAN;
+	}
+
+	flags = btrfs_block_group_flags(&bgi);
+	if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) {
+		block_group_err(fs_info, leaf, slot,
+"invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
+			flags & BTRFS_BLOCK_GROUP_PROFILE_MASK,
+			hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK));
+		return -EUCLEAN;
+	}
+
+	type = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
+	if (type != BTRFS_BLOCK_GROUP_DATA &&
+	    type != BTRFS_BLOCK_GROUP_METADATA &&
+	    type != BTRFS_BLOCK_GROUP_SYSTEM &&
+	    type != (BTRFS_BLOCK_GROUP_METADATA |
+			   BTRFS_BLOCK_GROUP_DATA)) {
+		block_group_err(fs_info, leaf, slot,
+"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx",
+			type, hweight64(type),
+			BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA,
+			BTRFS_BLOCK_GROUP_SYSTEM,
+			BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA);
+		return -EUCLEAN;
+	}
+	return 0;
+}
+
+/*
+ * Common point to switch the item-specific validation.
+ */
+static int check_leaf_item(struct btrfs_root *root,
+			   struct extent_buffer *leaf,
+			   struct btrfs_key *key, int slot)
+{
+	int ret = 0;
+
+	switch (key->type) {
+	case BTRFS_EXTENT_DATA_KEY:
+		ret = check_extent_data_item(root, leaf, key, slot);
+		break;
+	case BTRFS_EXTENT_CSUM_KEY:
+		ret = check_csum_item(root, leaf, key, slot);
+		break;
+	case BTRFS_DIR_ITEM_KEY:
+	case BTRFS_DIR_INDEX_KEY:
+	case BTRFS_XATTR_ITEM_KEY:
+		ret = check_dir_item(root, leaf, key, slot);
+		break;
+	case BTRFS_BLOCK_GROUP_ITEM_KEY:
+		ret = check_block_group_item(root->fs_info, leaf, key, slot);
+		break;
+	}
+	return ret;
+}
+
+static int check_leaf(struct btrfs_root *root, struct extent_buffer *leaf,
+		      bool check_item_data)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	/* No valid key type is 0, so all key should be larger than this key */
+	struct btrfs_key prev_key = {0, 0, 0};
+	struct btrfs_key key;
+	u32 nritems = btrfs_header_nritems(leaf);
+	int slot;
+
+	if (btrfs_header_level(leaf) != 0) {
+		generic_err(root, leaf, 0,
+			"invalid level for leaf, have %d expect 0",
+			btrfs_header_level(leaf));
+		return -EUCLEAN;
+	}
+
+	/*
+	 * Extent buffers from a relocation tree have a owner field that
+	 * corresponds to the subvolume tree they are based on. So just from an
+	 * extent buffer alone we can not find out what is the id of the
+	 * corresponding subvolume tree, so we can not figure out if the extent
+	 * buffer corresponds to the root of the relocation tree or not. So
+	 * skip this check for relocation trees.
+	 */
+	if (nritems == 0 && !btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_RELOC)) {
+		u64 owner = btrfs_header_owner(leaf);
+		struct btrfs_root *check_root;
+
+		/* These trees must never be empty */
+		if (owner == BTRFS_ROOT_TREE_OBJECTID ||
+		    owner == BTRFS_CHUNK_TREE_OBJECTID ||
+		    owner == BTRFS_EXTENT_TREE_OBJECTID ||
+		    owner == BTRFS_DEV_TREE_OBJECTID ||
+		    owner == BTRFS_FS_TREE_OBJECTID ||
+		    owner == BTRFS_DATA_RELOC_TREE_OBJECTID) {
+			generic_err(root, leaf, 0,
+			"invalid root, root %llu must never be empty",
+				    owner);
+			return -EUCLEAN;
+		}
+		key.objectid = owner;
+		key.type = BTRFS_ROOT_ITEM_KEY;
+		key.offset = (u64)-1;
+
+		check_root = btrfs_get_fs_root(fs_info, &key, false);
+		/*
+		 * The only reason we also check NULL here is that during
+		 * open_ctree() some roots has not yet been set up.
+		 */
+		if (!IS_ERR_OR_NULL(check_root)) {
+			struct extent_buffer *eb;
+
+			eb = btrfs_root_node(check_root);
+			/* if leaf is the root, then it's fine */
+			if (leaf != eb) {
+				CORRUPT("non-root leaf's nritems is 0",
+					leaf, check_root, 0);
+				free_extent_buffer(eb);
+				return -EUCLEAN;
+			}
+			free_extent_buffer(eb);
+		}
+		return 0;
+	}
+
+	if (nritems == 0)
+		return 0;
+
+	/*
+	 * Check the following things to make sure this is a good leaf, and
+	 * leaf users won't need to bother with similar sanity checks:
+	 *
+	 * 1) key ordering
+	 * 2) item offset and size
+	 *    No overlap, no hole, all inside the leaf.
+	 * 3) item content
+	 *    If possible, do comprehensive sanity check.
+	 *    NOTE: All checks must only rely on the item data itself.
+	 */
+	for (slot = 0; slot < nritems; slot++) {
+		u32 item_end_expected;
+		int ret;
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+
+		/* Make sure the keys are in the right order */
+		if (btrfs_comp_cpu_keys(&prev_key, &key) >= 0) {
+			CORRUPT("bad key order", leaf, root, slot);
+			return -EUCLEAN;
+		}
+
+		/*
+		 * Make sure the offset and ends are right, remember that the
+		 * item data starts at the end of the leaf and grows towards the
+		 * front.
+		 */
+		if (slot == 0)
+			item_end_expected = BTRFS_LEAF_DATA_SIZE(root);
+		else
+			item_end_expected = btrfs_item_offset_nr(leaf,
+								 slot - 1);
+		if (btrfs_item_end_nr(leaf, slot) != item_end_expected) {
+			CORRUPT("slot offset bad", leaf, root, slot);
+			return -EUCLEAN;
+		}
+
+		/*
+		 * Check to make sure that we don't point outside of the leaf,
+		 * just in case all the items are consistent to each other, but
+		 * all point outside of the leaf.
+		 */
+		if (btrfs_item_end_nr(leaf, slot) >
+		    BTRFS_LEAF_DATA_SIZE(root)) {
+			CORRUPT("slot end outside of leaf", leaf, root, slot);
+			return -EUCLEAN;
+		}
+
+		/* Also check if the item pointer overlaps with btrfs item. */
+		if (btrfs_item_nr_offset(slot) + sizeof(struct btrfs_item) >
+		    btrfs_item_ptr_offset(leaf, slot)) {
+			CORRUPT("slot overlap with its data", leaf, root, slot);
+			return -EUCLEAN;
+		}
+
+		if (check_item_data) {
+			/*
+			 * Check if the item size and content meet other
+			 * criteria
+			 */
+			ret = check_leaf_item(root, leaf, &key, slot);
+			if (ret < 0)
+				return ret;
+		}
+
+		prev_key.objectid = key.objectid;
+		prev_key.type = key.type;
+		prev_key.offset = key.offset;
+	}
+
+	return 0;
+}
+
+int btrfs_check_leaf_full(struct btrfs_root *root, struct extent_buffer *leaf)
+{
+	return check_leaf(root, leaf, true);
+}
+
+int btrfs_check_leaf_relaxed(struct btrfs_root *root,
+			     struct extent_buffer *leaf)
+{
+	return check_leaf(root, leaf, false);
+}
+
+int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node)
+{
+	unsigned long nr = btrfs_header_nritems(node);
+	struct btrfs_key key, next_key;
+	int slot;
+	int level = btrfs_header_level(node);
+	u64 bytenr;
+	int ret = 0;
+
+	if (level <= 0 || level >= BTRFS_MAX_LEVEL) {
+		generic_err(root, node, 0,
+			"invalid level for node, have %d expect [1, %d]",
+			level, BTRFS_MAX_LEVEL - 1);
+		return -EUCLEAN;
+	}
+	if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root)) {
+		btrfs_crit(root->fs_info,
+"corrupt node: root=%llu block=%llu, nritems too %s, have %lu expect range [1,%zu]",
+			   root->objectid, node->start,
+			   nr == 0 ? "small" : "large", nr,
+			   BTRFS_NODEPTRS_PER_BLOCK(root));
+		return -EUCLEAN;
+	}
+
+	for (slot = 0; slot < nr - 1; slot++) {
+		bytenr = btrfs_node_blockptr(node, slot);
+		btrfs_node_key_to_cpu(node, &key, slot);
+		btrfs_node_key_to_cpu(node, &next_key, slot + 1);
+
+		if (!bytenr) {
+			generic_err(root, node, slot,
+				"invalid NULL node pointer");
+			ret = -EUCLEAN;
+			goto out;
+		}
+		if (!IS_ALIGNED(bytenr, root->sectorsize)) {
+			generic_err(root, node, slot,
+			"unaligned pointer, have %llu should be aligned to %u",
+				bytenr, root->sectorsize);
+			ret = -EUCLEAN;
+			goto out;
+		}
+
+		if (btrfs_comp_cpu_keys(&key, &next_key) >= 0) {
+			generic_err(root, node, slot,
+	"bad key order, current (%llu %u %llu) next (%llu %u %llu)",
+				key.objectid, key.type, key.offset,
+				next_key.objectid, next_key.type,
+				next_key.offset);
+			ret = -EUCLEAN;
+			goto out;
+		}
+	}
+out:
+	return ret;
+}
diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h
new file mode 100644
index 000000000000..3d53e8d6fda0
--- /dev/null
+++ b/fs/btrfs/tree-checker.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) Qu Wenruo 2017.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program.
+ */
+
+#ifndef __BTRFS_TREE_CHECKER__
+#define __BTRFS_TREE_CHECKER__
+
+#include "ctree.h"
+#include "extent_io.h"
+
+/*
+ * Comprehensive leaf checker.
+ * Will check not only the item pointers, but also every possible member
+ * in item data.
+ */
+int btrfs_check_leaf_full(struct btrfs_root *root, struct extent_buffer *leaf);
+
+/*
+ * Less strict leaf checker.
+ * Will only check item pointers, not reading item data.
+ */
+int btrfs_check_leaf_relaxed(struct btrfs_root *root,
+			     struct extent_buffer *leaf);
+int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node);
+
+#endif
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b4d63a9842fa..d1cca19b29d3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1184,7 +1184,7 @@ again:
 		struct map_lookup *map;
 		int i;
 
-		map = (struct map_lookup *)em->bdev;
+		map = em->map_lookup;
 		for (i = 0; i < map->num_stripes; i++) {
 			u64 end;
 
@@ -2757,7 +2757,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 			free_extent_map(em);
 		return -EINVAL;
 	}
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	lock_chunks(root->fs_info->chunk_root);
 	check_system_chunk(trans, extent_root, map->type);
 	unlock_chunks(root->fs_info->chunk_root);
@@ -4540,7 +4540,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	if (type & BTRFS_BLOCK_GROUP_DATA) {
 		max_stripe_size = 1024 * 1024 * 1024;
-		max_chunk_size = 10 * max_stripe_size;
+		max_chunk_size = BTRFS_MAX_DATA_CHUNK_SIZE;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS(info->chunk_root);
 	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
@@ -4731,7 +4731,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 		goto error;
 	}
 	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
-	em->bdev = (struct block_device *)map;
+	em->map_lookup = map;
 	em->start = start;
 	em->len = num_bytes;
 	em->block_start = 0;
@@ -4826,7 +4826,7 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 		return -EINVAL;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	item_size = btrfs_chunk_item_size(map->num_stripes);
 	stripe_size = em->orig_block_len;
 
@@ -4968,7 +4968,7 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
 	if (!em)
 		return 1;
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	for (i = 0; i < map->num_stripes; i++) {
 		if (map->stripes[i].dev->missing) {
 			miss_ndevs++;
@@ -5048,7 +5048,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		return 1;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1))
 		ret = map->num_stripes;
 	else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
@@ -5091,7 +5091,7 @@ unsigned long btrfs_full_stripe_len(struct btrfs_root *root,
 	BUG_ON(!em);
 
 	BUG_ON(em->start > logical || em->start + em->len < logical);
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		len = map->stripe_len * nr_data_stripes(map);
 	free_extent_map(em);
@@ -5112,7 +5112,7 @@ int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
 	BUG_ON(!em);
 
 	BUG_ON(em->start > logical || em->start + em->len < logical);
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		ret = 1;
 	free_extent_map(em);
@@ -5271,7 +5271,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		return -EINVAL;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	offset = logical - em->start;
 
 	stripe_len = map->stripe_len;
@@ -5813,7 +5813,7 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 		free_extent_map(em);
 		return -EIO;
 	}
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 
 	length = em->len;
 	rmap_len = map->stripe_len;
@@ -6208,6 +6208,101 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 	return dev;
 }
 
+/* Return -EIO if any error, otherwise return 0. */
+static int btrfs_check_chunk_valid(struct btrfs_root *root,
+				   struct extent_buffer *leaf,
+				   struct btrfs_chunk *chunk, u64 logical)
+{
+	u64 length;
+	u64 stripe_len;
+	u16 num_stripes;
+	u16 sub_stripes;
+	u64 type;
+	u64 features;
+	bool mixed = false;
+
+	length = btrfs_chunk_length(leaf, chunk);
+	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
+	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+	sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
+	type = btrfs_chunk_type(leaf, chunk);
+
+	if (!num_stripes) {
+		btrfs_err(root->fs_info, "invalid chunk num_stripes: %u",
+			  num_stripes);
+		return -EIO;
+	}
+	if (!IS_ALIGNED(logical, root->sectorsize)) {
+		btrfs_err(root->fs_info,
+			  "invalid chunk logical %llu", logical);
+		return -EIO;
+	}
+	if (btrfs_chunk_sector_size(leaf, chunk) != root->sectorsize) {
+		btrfs_err(root->fs_info, "invalid chunk sectorsize %u",
+			  btrfs_chunk_sector_size(leaf, chunk));
+		return -EIO;
+	}
+	if (!length || !IS_ALIGNED(length, root->sectorsize)) {
+		btrfs_err(root->fs_info,
+			"invalid chunk length %llu", length);
+		return -EIO;
+	}
+	if (!is_power_of_2(stripe_len)) {
+		btrfs_err(root->fs_info, "invalid chunk stripe length: %llu",
+			  stripe_len);
+		return -EIO;
+	}
+	if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+	    type) {
+		btrfs_err(root->fs_info, "unrecognized chunk type: %llu",
+			  ~(BTRFS_BLOCK_GROUP_TYPE_MASK |
+			    BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+			  btrfs_chunk_type(leaf, chunk));
+		return -EIO;
+	}
+
+	if ((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0) {
+		btrfs_err(root->fs_info, "missing chunk type flag: 0x%llx", type);
+		return -EIO;
+	}
+
+	if ((type & BTRFS_BLOCK_GROUP_SYSTEM) &&
+	    (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) {
+		btrfs_err(root->fs_info,
+			"system chunk with data or metadata type: 0x%llx", type);
+		return -EIO;
+	}
+
+	features = btrfs_super_incompat_flags(root->fs_info->super_copy);
+	if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
+		mixed = true;
+
+	if (!mixed) {
+		if ((type & BTRFS_BLOCK_GROUP_METADATA) &&
+		    (type & BTRFS_BLOCK_GROUP_DATA)) {
+			btrfs_err(root->fs_info,
+			"mixed chunk type in non-mixed mode: 0x%llx", type);
+			return -EIO;
+		}
+	}
+
+	if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) ||
+	    (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes != 2) ||
+	    (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) ||
+	    (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) ||
+	    (type & BTRFS_BLOCK_GROUP_DUP && num_stripes != 2) ||
+	    ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 &&
+	     num_stripes != 1)) {
+		btrfs_err(root->fs_info,
+			"invalid num_stripes:sub_stripes %u:%u for profile %llu",
+			num_stripes, sub_stripes,
+			type & BTRFS_BLOCK_GROUP_PROFILE_MASK);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 			  struct extent_buffer *leaf,
 			  struct btrfs_chunk *chunk)
@@ -6217,6 +6312,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 	struct extent_map *em;
 	u64 logical;
 	u64 length;
+	u64 stripe_len;
 	u64 devid;
 	u8 uuid[BTRFS_UUID_SIZE];
 	int num_stripes;
@@ -6225,6 +6321,12 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 
 	logical = key->offset;
 	length = btrfs_chunk_length(leaf, chunk);
+	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
+	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+
+	ret = btrfs_check_chunk_valid(root, leaf, chunk, logical);
+	if (ret)
+		return ret;
 
 	read_lock(&map_tree->map_tree.lock);
 	em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);
@@ -6241,7 +6343,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 	em = alloc_extent_map();
 	if (!em)
 		return -ENOMEM;
-	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
 	map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
 	if (!map) {
 		free_extent_map(em);
@@ -6249,7 +6350,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 	}
 
 	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
-	em->bdev = (struct block_device *)map;
+	em->map_lookup = map;
 	em->start = logical;
 	em->len = length;
 	em->orig_start = 0;
@@ -6473,6 +6574,7 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	u32 array_size;
 	u32 len = 0;
 	u32 cur_offset;
+	u64 type;
 	struct btrfs_key key;
 
 	ASSERT(BTRFS_SUPER_INFO_SIZE <= root->nodesize);
@@ -6539,6 +6641,15 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 				break;
 			}
 
+			type = btrfs_chunk_type(sb, chunk);
+			if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
+				btrfs_err(root->fs_info,
+			    "invalid chunk type %llu in sys_array at offset %u",
+					type, cur_offset);
+				ret = -EIO;
+				break;
+			}
+
 			len = btrfs_chunk_item_size(num_stripes);
 			if (cur_offset + len > array_size)
 				goto out_short_read;
@@ -6948,7 +7059,7 @@ void btrfs_update_commit_device_bytes_used(struct btrfs_root *root,
 	/* In order to kick the device replace finish process */
 	lock_chunks(root);
 	list_for_each_entry(em, &transaction->pending_chunks, list) {
-		map = (struct map_lookup *)em->bdev;
+		map = em->map_lookup;
 
 		for (i = 0; i < map->num_stripes; i++) {
 			dev = map->stripes[i].dev;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index d5c84f6b1353..3c651df420be 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -24,6 +24,8 @@
 #include <linux/btrfs.h>
 #include "async-thread.h"
 
+#define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
+
 extern struct mutex uuid_mutex;
 
 #define BTRFS_STRIPE_LEN	(64 * 1024)
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 5b68cf526887..c05ab2ec0fef 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -963,11 +963,8 @@ error:
 void cachefiles_uncache_page(struct fscache_object *_object, struct page *page)
 {
 	struct cachefiles_object *object;
-	struct cachefiles_cache *cache;
 
 	object = container_of(_object, struct cachefiles_object, fscache);
-	cache = container_of(object->fscache.cache,
-			     struct cachefiles_cache, cache);
 
 	_enter("%p,{%lu}", object, page->index);
 
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 0e3de1bb6500..e7b54514d99a 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3243,7 +3243,6 @@ retry:
 			tcap->cap_id = t_cap_id;
 			tcap->seq = t_seq - 1;
 			tcap->issue_seq = t_seq - 1;
-			tcap->mseq = t_mseq;
 			tcap->issued |= issued;
 			tcap->implemented |= issued;
 			if (cap == ci->i_auth_cap)
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 4aa7122a8d38..a485d0cdc559 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -611,7 +611,8 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 	     capsnap->size);
 
 	spin_lock(&mdsc->snap_flush_lock);
-	list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list);
+	if (list_empty(&ci->i_snap_flush_item))
+		list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list);
 	spin_unlock(&mdsc->snap_flush_lock);
 	return 1;  /* caller may want to ceph_flush_snaps */
 }
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 1eeb4780c3ed..eacf57c24ca9 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -48,6 +48,7 @@
 #include "cifs_unicode.h"
 #include "cifs_debug.h"
 #include "cifs_fs_sb.h"
+#include "dns_resolve.h"
 #include "ntlmssp.h"
 #include "nterr.h"
 #include "rfc1002pdu.h"
@@ -304,6 +305,53 @@ static int cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data,
 					const char *devname);
 
 /*
+ * Resolve hostname and set ip addr in tcp ses. Useful for hostnames that may
+ * get their ip addresses changed at some point.
+ *
+ * This should be called with server->srv_mutex held.
+ */
+#ifdef CONFIG_CIFS_DFS_UPCALL
+static int reconn_set_ipaddr(struct TCP_Server_Info *server)
+{
+	int rc;
+	int len;
+	char *unc, *ipaddr = NULL;
+
+	if (!server->hostname)
+		return -EINVAL;
+
+	len = strlen(server->hostname) + 3;
+
+	unc = kmalloc(len, GFP_KERNEL);
+	if (!unc) {
+		cifs_dbg(FYI, "%s: failed to create UNC path\n", __func__);
+		return -ENOMEM;
+	}
+	snprintf(unc, len, "\\\\%s", server->hostname);
+
+	rc = dns_resolve_server_name_to_ip(unc, &ipaddr);
+	kfree(unc);
+
+	if (rc < 0) {
+		cifs_dbg(FYI, "%s: failed to resolve server part of %s to IP: %d\n",
+			 __func__, server->hostname, rc);
+		return rc;
+	}
+
+	rc = cifs_convert_address((struct sockaddr *)&server->dstaddr, ipaddr,
+				  strlen(ipaddr));
+	kfree(ipaddr);
+
+	return !rc ? -1 : 0;
+}
+#else
+static inline int reconn_set_ipaddr(struct TCP_Server_Info *server)
+{
+	return 0;
+}
+#endif
+
+/*
  * cifs tcp session reconnection
  *
  * mark tcp session as reconnecting so temporarily locked
@@ -400,6 +448,11 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		rc = generic_ip_connect(server);
 		if (rc) {
 			cifs_dbg(FYI, "reconnect error %d\n", rc);
+			rc = reconn_set_ipaddr(server);
+			if (rc) {
+				cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
+					 __func__, rc);
+			}
 			mutex_unlock(&server->srv_mutex);
 			msleep(3000);
 		} else {
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0141aba9eca6..0305e3866216 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1073,14 +1073,18 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
 
 	/*
 	 * Accessing maxBuf is racy with cifs_reconnect - need to store value
-	 * and check it for zero before using.
+	 * and check it before using.
 	 */
 	max_buf = tcon->ses->server->maxBuf;
-	if (!max_buf) {
+	if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) {
 		free_xid(xid);
 		return -EINVAL;
 	}
 
+	BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) >
+		     PAGE_SIZE);
+	max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr),
+			PAGE_SIZE);
 	max_num = (max_buf - sizeof(struct smb_hdr)) /
 						sizeof(LOCKING_ANDX_RANGE);
 	buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
@@ -1404,12 +1408,16 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 
 	/*
 	 * Accessing maxBuf is racy with cifs_reconnect - need to store value
-	 * and check it for zero before using.
+	 * and check it before using.
 	 */
 	max_buf = tcon->ses->server->maxBuf;
-	if (!max_buf)
+	if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE)))
 		return -EINVAL;
 
+	BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) >
+		     PAGE_SIZE);
+	max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr),
+			PAGE_SIZE);
 	max_num = (max_buf - sizeof(struct smb_hdr)) /
 						sizeof(LOCKING_ANDX_RANGE);
 	buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
@@ -2745,14 +2753,16 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
 	 * these pages but not on the region from pos to ppos+len-1.
 	 */
 	written = cifs_user_writev(iocb, from);
-	if (written > 0 && CIFS_CACHE_READ(cinode)) {
+	if (CIFS_CACHE_READ(cinode)) {
 		/*
-		 * Windows 7 server can delay breaking level2 oplock if a write
-		 * request comes - break it on the client to prevent reading
-		 * an old data.
+		 * We have read level caching and we have just sent a write
+		 * request to the server thus making data in the cache stale.
+		 * Zap the cache and set oplock/lease level to NONE to avoid
+		 * reading stale data from the cache. All subsequent read
+		 * operations will read new data from the server.
 		 */
 		cifs_zap_mapping(inode);
-		cifs_dbg(FYI, "Set no oplock for inode=%p after a write operation\n",
+		cifs_dbg(FYI, "Set Oplock/Lease to NONE for inode=%p after write\n",
 			 inode);
 		cinode->oplock = 0;
 	}
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 57b039ebfb1f..43fa471c88d7 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -652,7 +652,14 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
 		/* scan and find it */
 		int i;
 		char *cur_ent;
-		char *end_of_smb = cfile->srch_inf.ntwrk_buf_start +
+		char *end_of_smb;
+
+		if (cfile->srch_inf.ntwrk_buf_start == NULL) {
+			cifs_dbg(VFS, "ntwrk_buf_start is NULL during readdir\n");
+			return -EIO;
+		}
+
+		end_of_smb = cfile->srch_inf.ntwrk_buf_start +
 			server->ops->calc_smb_size(
 					cfile->srch_inf.ntwrk_buf_start);
 
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index b2aff0c6f22c..dee5250701de 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -123,12 +123,14 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 
 	/*
 	 * Accessing maxBuf is racy with cifs_reconnect - need to store value
-	 * and check it for zero before using.
+	 * and check it before using.
 	 */
 	max_buf = tcon->ses->server->maxBuf;
-	if (!max_buf)
+	if (max_buf < sizeof(struct smb2_lock_element))
 		return -EINVAL;
 
+	BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE);
+	max_buf = min_t(unsigned int, max_buf, PAGE_SIZE);
 	max_num = max_buf / sizeof(struct smb2_lock_element);
 	buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
 	if (!buf)
@@ -265,6 +267,8 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile)
 		return -EINVAL;
 	}
 
+	BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE);
+	max_buf = min_t(unsigned int, max_buf, PAGE_SIZE);
 	max_num = max_buf / sizeof(struct smb2_lock_element);
 	buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
 	if (!buf) {
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 8257a5a97cc0..98c25b969ab8 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -377,8 +377,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_NONEXISTENT_EA_ENTRY, -EIO, "STATUS_NONEXISTENT_EA_ENTRY"},
 	{STATUS_NO_EAS_ON_FILE, -ENODATA, "STATUS_NO_EAS_ON_FILE"},
 	{STATUS_EA_CORRUPT_ERROR, -EIO, "STATUS_EA_CORRUPT_ERROR"},
-	{STATUS_FILE_LOCK_CONFLICT, -EIO, "STATUS_FILE_LOCK_CONFLICT"},
-	{STATUS_LOCK_NOT_GRANTED, -EIO, "STATUS_LOCK_NOT_GRANTED"},
+	{STATUS_FILE_LOCK_CONFLICT, -EACCES, "STATUS_FILE_LOCK_CONFLICT"},
+	{STATUS_LOCK_NOT_GRANTED, -EACCES, "STATUS_LOCK_NOT_GRANTED"},
 	{STATUS_DELETE_PENDING, -ENOENT, "STATUS_DELETE_PENDING"},
 	{STATUS_CTL_FILE_NOT_SUPPORTED, -ENOSYS,
 	"STATUS_CTL_FILE_NOT_SUPPORTED"},
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 2725085a3f9f..eae3cdffaf7f 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -143,14 +143,14 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size,
 
 			scredits = server->credits;
 			/* can deadlock with reopen */
-			if (scredits == 1) {
+			if (scredits <= 8) {
 				*num = SMB2_MAX_BUFFER_SIZE;
 				*credits = 0;
 				break;
 			}
 
-			/* leave one credit for a possible reopen */
-			scredits--;
+			/* leave some credits for reopen and other ops */
+			scredits -= 8;
 			*num = min_t(unsigned int, size,
 				     scredits * SMB2_MAX_BUFFER_SIZE);
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index f7111bb88ec1..5e21d58c49ef 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2523,8 +2523,8 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 		if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) {
 			srch_inf->endOfSearch = true;
 			rc = 0;
-		}
-		cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
+		} else
+			cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
 		goto qdir_exit;
 	}
 
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index aacb15bd56fe..f087158c5555 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -82,8 +82,8 @@
 
 #define NUMBER_OF_SMB2_COMMANDS	0x0013
 
-/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */
-#define MAX_SMB2_HDR_SIZE 0x00b0
+/* 52 transform hdr + 64 hdr + 88 create rsp */
+#define MAX_SMB2_HDR_SIZE 204
 
 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
 
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 54af10204e83..1cf0a336ec06 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -360,7 +360,7 @@ uncork:
 	if (rc < 0 && rc != -EINTR)
 		cifs_dbg(VFS, "Error %d sending data on socket to server\n",
 			 rc);
-	else
+	else if (rc > 0)
 		rc = 0;
 
 	return rc;
diff --git a/fs/dcache.c b/fs/dcache.c
index 141651b0c766..9ffe60702299 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1155,15 +1155,11 @@ static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
  */
 void shrink_dcache_sb(struct super_block *sb)
 {
-	long freed;
-
 	do {
 		LIST_HEAD(dispose);
 
-		freed = list_lru_walk(&sb->s_dentry_lru,
+		list_lru_walk(&sb->s_dentry_lru,
 			dentry_lru_isolate_shrink, &dispose, 1024);
-
-		this_cpu_sub(nr_dentry_unused, freed);
 		shrink_dentry_list(&dispose);
 		cond_resched();
 	} while (list_lru_count(&sb->s_dentry_lru) > 0);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index e49ba072bd64..22fe11baef2b 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -671,6 +671,13 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
 	struct dentry *dentry = NULL, *trap;
 	struct name_snapshot old_name;
 
+	if (IS_ERR(old_dir))
+		return old_dir;
+	if (IS_ERR(new_dir))
+		return new_dir;
+	if (IS_ERR_OR_NULL(old_dentry))
+		return old_dentry;
+
 	trap = lock_rename(new_dir, old_dir);
 	/* Source or destination directories don't exist? */
 	if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir))
diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c
index dcea1e37a1b7..f18619bc2e09 100644
--- a/fs/dlm/ast.c
+++ b/fs/dlm/ast.c
@@ -290,6 +290,8 @@ void dlm_callback_suspend(struct dlm_ls *ls)
 		flush_workqueue(ls->ls_callback_wq);
 }
 
+#define MAX_CB_QUEUE 25
+
 void dlm_callback_resume(struct dlm_ls *ls)
 {
 	struct dlm_lkb *lkb, *safe;
@@ -300,15 +302,23 @@ void dlm_callback_resume(struct dlm_ls *ls)
 	if (!ls->ls_callback_wq)
 		return;
 
+more:
 	mutex_lock(&ls->ls_cb_mutex);
 	list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) {
 		list_del_init(&lkb->lkb_cb_list);
 		queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
 		count++;
+		if (count == MAX_CB_QUEUE)
+			break;
 	}
 	mutex_unlock(&ls->ls_cb_mutex);
 
 	if (count)
 		log_rinfo(ls, "dlm_callback_resume %d", count);
+	if (count == MAX_CB_QUEUE) {
+		count = 0;
+		cond_resched();
+		goto more;
+	}
 }
 
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 35502d4046f5..3a7f401e943c 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1210,6 +1210,7 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
 
 	if (rv < 0) {
 		log_error(ls, "create_lkb idr error %d", rv);
+		dlm_free_lkb(lkb);
 		return rv;
 	}
 
@@ -4177,6 +4178,7 @@ static int receive_convert(struct dlm_ls *ls, struct dlm_message *ms)
 			  (unsigned long long)lkb->lkb_recover_seq,
 			  ms->m_header.h_nodeid, ms->m_lkid);
 		error = -ENOENT;
+		dlm_put_lkb(lkb);
 		goto fail;
 	}
 
@@ -4230,6 +4232,7 @@ static int receive_unlock(struct dlm_ls *ls, struct dlm_message *ms)
 			  lkb->lkb_id, lkb->lkb_remid,
 			  ms->m_header.h_nodeid, ms->m_lkid);
 		error = -ENOENT;
+		dlm_put_lkb(lkb);
 		goto fail;
 	}
 
@@ -5792,20 +5795,20 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
 			goto out;
 		}
 	}
-
-	/* After ua is attached to lkb it will be freed by dlm_free_lkb().
-	   When DLM_IFL_USER is set, the dlm knows that this is a userspace
-	   lock and that lkb_astparam is the dlm_user_args structure. */
-
 	error = set_lock_args(mode, &ua->lksb, flags, namelen, timeout_cs,
 			      fake_astfn, ua, fake_bastfn, &args);
-	lkb->lkb_flags |= DLM_IFL_USER;
-
 	if (error) {
+		kfree(ua->lksb.sb_lvbptr);
+		ua->lksb.sb_lvbptr = NULL;
+		kfree(ua);
 		__put_lkb(ls, lkb);
 		goto out;
 	}
 
+	/* After ua is attached to lkb it will be freed by dlm_free_lkb().
+	   When DLM_IFL_USER is set, the dlm knows that this is a userspace
+	   lock and that lkb_astparam is the dlm_user_args structure. */
+	lkb->lkb_flags |= DLM_IFL_USER;
 	error = request_lock(ls, lkb, name, namelen, &args);
 
 	switch (error) {
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index f3e72787e7f9..30e4e01db35a 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -673,11 +673,11 @@ static int new_lockspace(const char *name, const char *cluster,
 	kfree(ls->ls_recover_buf);
  out_lkbidr:
 	idr_destroy(&ls->ls_lkbidr);
+ out_rsbtbl:
 	for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++) {
 		if (ls->ls_remove_names[i])
 			kfree(ls->ls_remove_names[i]);
 	}
- out_rsbtbl:
 	vfree(ls->ls_rsbtbl);
  out_lsfree:
 	if (do_unreg)
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index d72d52b90433..280460fef066 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -20,8 +20,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		spin_lock(&inode->i_lock);
+		/*
+		 * We must skip inodes in unusual state. We may also skip
+		 * inodes without pages but we deliberately won't in case
+		 * we need to reschedule to avoid softlockups.
+		 */
 		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
-		    (inode->i_mapping->nrpages == 0)) {
+		    (inode->i_mapping->nrpages == 0 && !need_resched())) {
 			spin_unlock(&inode->i_lock);
 			continue;
 		}
@@ -29,6 +34,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 		spin_unlock(&inode->i_lock);
 		spin_unlock(&sb->s_inode_list_lock);
 
+		cond_resched();
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
 		iput(toput_inode);
 		toput_inode = inode;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1b08556776ce..240d9ceb8d0c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1034,7 +1034,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	 * semantics). All the events that happen during that period of time are
 	 * chained in ep->ovflist and requeued later on.
 	 */
-	if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) {
+	if (ep->ovflist != EP_UNACTIVE_PTR) {
 		if (epi->next == EP_UNACTIVE_PTR) {
 			epi->next = ep->ovflist;
 			ep->ovflist = epi;
diff --git a/fs/exec.c b/fs/exec.c
index 910fc70c4542..3dad755b7048 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -191,6 +191,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 {
 	struct page *page;
 	int ret;
+	unsigned int gup_flags = FOLL_FORCE;
 
 #ifdef CONFIG_STACK_GROWSUP
 	if (write) {
@@ -199,8 +200,12 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 			return NULL;
 	}
 #endif
-	ret = get_user_pages(current, bprm->mm, pos,
-			1, write, 1, &page, NULL);
+
+	if (write)
+		gup_flags |= FOLL_WRITE;
+
+	ret = get_user_pages(current, bprm->mm, pos, 1, gup_flags,
+			&page, NULL);
 	if (ret <= 0)
 		return NULL;
 
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 714cd37a6ba3..6599c6124552 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -76,7 +76,7 @@ static bool dentry_connected(struct dentry *dentry)
 		struct dentry *parent = dget_parent(dentry);
 
 		dput(dentry);
-		if (IS_ROOT(dentry)) {
+		if (dentry == parent) {
 			dput(parent);
 			return false;
 		}
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 748d35afc902..860024392969 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -721,7 +721,8 @@ static loff_t ext2_max_size(int bits)
 {
 	loff_t res = EXT2_NDIR_BLOCKS;
 	int meta_blocks;
-	loff_t upper_limit;
+	unsigned int upper_limit;
+	unsigned int ppb = 1 << (bits-2);
 
 	/* This is calculated to be the largest file size for a
 	 * dense, file such that the total number of
@@ -735,24 +736,34 @@ static loff_t ext2_max_size(int bits)
 	/* total blocks in file system block size */
 	upper_limit >>= (bits - 9);
 
+	/* Compute how many blocks we can address by block tree */
+	res += 1LL << (bits-2);
+	res += 1LL << (2*(bits-2));
+	res += 1LL << (3*(bits-2));
+	/* Does block tree limit file size? */
+	if (res < upper_limit)
+		goto check_lfs;
 
+	res = upper_limit;
+	/* How many metadata blocks are needed for addressing upper_limit? */
+	upper_limit -= EXT2_NDIR_BLOCKS;
 	/* indirect blocks */
 	meta_blocks = 1;
+	upper_limit -= ppb;
 	/* double indirect blocks */
-	meta_blocks += 1 + (1LL << (bits-2));
-	/* tripple indirect blocks */
-	meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
-
-	upper_limit -= meta_blocks;
-	upper_limit <<= bits;
-
-	res += 1LL << (bits-2);
-	res += 1LL << (2*(bits-2));
-	res += 1LL << (3*(bits-2));
+	if (upper_limit < ppb * ppb) {
+		meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb);
+		res -= meta_blocks;
+		goto check_lfs;
+	}
+	meta_blocks += 1 + ppb;
+	upper_limit -= ppb * ppb;
+	/* tripple indirect blocks for the rest */
+	meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb) +
+		DIV_ROUND_UP(upper_limit, ppb*ppb);
+	res -= meta_blocks;
+check_lfs:
 	res <<= bits;
-	if (res > upper_limit)
-		res = upper_limit;
-
 	if (res > MAX_LFS_FILESIZE)
 		res = MAX_LFS_FILESIZE;
 
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 1aec46733ef8..0dcd33f62637 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -701,8 +701,11 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 
 	if (!PageUptodate(page)) {
 		ret = ext4_read_inline_page(inode, page);
-		if (ret < 0)
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
 			goto out_up_read;
+		}
 	}
 
 	ret = 1;
@@ -1858,12 +1861,12 @@ int ext4_inline_data_fiemap(struct inode *inode,
 	physical += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data;
 	physical += offsetof(struct ext4_inode, i_block);
 
-	if (physical)
-		error = fiemap_fill_next_extent(fieinfo, start, physical,
-						inline_len, flags);
 	brelse(iloc.bh);
 out:
 	up_read(&EXT4_I(inode)->xattr_sem);
+	if (physical)
+		error = fiemap_fill_next_extent(fieinfo, start, physical,
+						inline_len, flags);
 	return (error < 0 ? error : 0);
 }
 
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index bad13f049fb0..4bd12247a9be 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1600,7 +1600,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	}
 
 	if (reserved_gdb || gdb_off == 0) {
-		if (ext4_has_feature_resize_inode(sb) ||
+		if (!ext4_has_feature_resize_inode(sb) ||
 		    !le16_to_cpu(es->s_reserved_gdt_blocks)) {
 			ext4_warning(sb,
 				     "No reserved GDT blocks, can't resize");
@@ -1928,7 +1928,8 @@ retry:
 				le16_to_cpu(es->s_reserved_gdt_blocks);
 			n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb);
 			n_blocks_count = (ext4_fsblk_t)n_group *
-				EXT4_BLOCKS_PER_GROUP(sb);
+				EXT4_BLOCKS_PER_GROUP(sb) +
+				le32_to_cpu(es->s_first_data_block);
 			n_group--; /* set to last group number */
 		}
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index cd9cd581fd92..6a7df72cb3da 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1049,6 +1049,16 @@ static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid,
 				    ext4_nfs_get_inode);
 }
 
+static int ext4_nfs_commit_metadata(struct inode *inode)
+{
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_ALL
+	};
+
+	trace_ext4_nfs_commit_metadata(inode);
+	return ext4_write_inode(inode, &wbc);
+}
+
 /*
  * Try to release metadata pages (indirect blocks, directories) which are
  * mapped via the block device.  Since these pages could have journal heads
@@ -1143,6 +1153,7 @@ static const struct export_operations ext4_export_ops = {
 	.fh_to_dentry = ext4_fh_to_dentry,
 	.fh_to_parent = ext4_fh_to_parent,
 	.get_parent = ext4_get_parent,
+	.commit_metadata = ext4_nfs_commit_metadata,
 };
 
 enum {
@@ -5184,9 +5195,9 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
 	qf_inode->i_flags |= S_NOQUOTA;
 	lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA);
 	err = dquot_enable(qf_inode, type, format_id, flags);
-	iput(qf_inode);
 	if (err)
 		lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL);
+	iput(qf_inode);
 
 	return err;
 }
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 83dcf7bfd7b8..f0ea91925343 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -350,12 +350,14 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode,
 		return PTR_ERR(p);
 
 	clone = f2fs_acl_clone(p, GFP_NOFS);
-	if (!clone)
-		goto no_mem;
+	if (!clone) {
+		ret = -ENOMEM;
+		goto release_acl;
+	}
 
 	ret = f2fs_acl_create_masq(clone, mode);
 	if (ret < 0)
-		goto no_mem_clone;
+		goto release_clone;
 
 	if (ret == 0)
 		posix_acl_release(clone);
@@ -369,11 +371,11 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode,
 
 	return 0;
 
-no_mem_clone:
+release_clone:
 	posix_acl_release(clone);
-no_mem:
+release_acl:
 	posix_acl_release(p);
-	return -ENOMEM;
+	return ret;
 }
 
 int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index f661d80474be..4b2f609f376d 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -58,6 +58,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO,
 		.blk_addr = index,
 		.encrypted_page = NULL,
+		.is_meta = is_meta,
 	};
 
 	if (unlikely(!is_meta))
@@ -74,8 +75,10 @@ repeat:
 	fio.page = page;
 
 	if (f2fs_submit_page_bio(&fio)) {
-		f2fs_put_page(page, 1);
-		goto repeat;
+		memset(page_address(page), 0, PAGE_SIZE);
+		f2fs_stop_checkpoint(sbi);
+		f2fs_bug_on(sbi, 1);
+		return page;
 	}
 
 	lock_page(page);
@@ -106,7 +109,8 @@ struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	return __get_meta_page(sbi, index, false);
 }
 
-bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+					block_t blkaddr, int type)
 {
 	switch (type) {
 	case META_NAT:
@@ -126,8 +130,20 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
 			return false;
 		break;
 	case META_POR:
+	case DATA_GENERIC:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
-			blkaddr < MAIN_BLKADDR(sbi)))
+			blkaddr < MAIN_BLKADDR(sbi))) {
+			if (type == DATA_GENERIC) {
+				f2fs_msg(sbi->sb, KERN_WARNING,
+					"access invalid blkaddr:%u", blkaddr);
+				WARN_ON(1);
+			}
+			return false;
+		}
+		break;
+	case META_GENERIC:
+		if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
+			blkaddr >= MAIN_BLKADDR(sbi)))
 			return false;
 		break;
 	default:
@@ -151,6 +167,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		.type = META,
 		.rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
 		.encrypted_page = NULL,
+		.is_meta = (type != META_POR),
 	};
 
 	if (unlikely(type == META_POR))
@@ -158,7 +175,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 
 	for (; nrpages-- > 0; blkno++) {
 
-		if (!is_valid_blkaddr(sbi, blkno, type))
+		if (!f2fs_is_valid_blkaddr(sbi, blkno, type))
 			goto out;
 
 		switch (type) {
@@ -601,54 +618,73 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
 	}
 }
 
-static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
-				block_t cp_addr, unsigned long long *version)
+static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
+		struct f2fs_checkpoint **cp_block, struct page **cp_page,
+		unsigned long long *version)
 {
-	struct page *cp_page_1, *cp_page_2 = NULL;
 	unsigned long blk_size = sbi->blocksize;
-	struct f2fs_checkpoint *cp_block;
-	unsigned long long cur_version = 0, pre_version = 0;
-	size_t crc_offset;
+	size_t crc_offset = 0;
 	__u32 crc = 0;
 
-	/* Read the 1st cp block in this CP pack */
-	cp_page_1 = get_meta_page(sbi, cp_addr);
+	*cp_page = get_meta_page(sbi, cp_addr);
+	*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
 
-	/* get the version number */
-	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_1);
-	crc_offset = le32_to_cpu(cp_block->checksum_offset);
-	if (crc_offset >= blk_size)
-		goto invalid_cp1;
-
-	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
-		goto invalid_cp1;
+	crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
+	if (crc_offset >= blk_size) {
+		f2fs_put_page(*cp_page, 1);
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"invalid crc_offset: %zu", crc_offset);
+		return -EINVAL;
+	}
 
-	pre_version = cur_cp_version(cp_block);
+	crc = le32_to_cpu(*((__le32 *)((unsigned char *)*cp_block
+							+ crc_offset)));
+	if (!f2fs_crc_valid(crc, *cp_block, crc_offset)) {
+		f2fs_put_page(*cp_page, 1);
+		f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
+		return -EINVAL;
+	}
 
-	/* Read the 2nd cp block in this CP pack */
-	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
-	cp_page_2 = get_meta_page(sbi, cp_addr);
+	*version = cur_cp_version(*cp_block);
+	return 0;
+}
 
-	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2);
-	crc_offset = le32_to_cpu(cp_block->checksum_offset);
-	if (crc_offset >= blk_size)
-		goto invalid_cp2;
+static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
+				block_t cp_addr, unsigned long long *version)
+{
+	struct page *cp_page_1 = NULL, *cp_page_2 = NULL;
+	struct f2fs_checkpoint *cp_block = NULL;
+	unsigned long long cur_version = 0, pre_version = 0;
+	int err;
 
-	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
-		goto invalid_cp2;
+	err = get_checkpoint_version(sbi, cp_addr, &cp_block,
+					&cp_page_1, version);
+	if (err)
+		return NULL;
+
+	if (le32_to_cpu(cp_block->cp_pack_total_block_count) >
+					sbi->blocks_per_seg) {
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"invalid cp_pack_total_block_count:%u",
+			le32_to_cpu(cp_block->cp_pack_total_block_count));
+		goto invalid_cp;
+	}
+	pre_version = *version;
 
-	cur_version = cur_cp_version(cp_block);
+	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
+	err = get_checkpoint_version(sbi, cp_addr, &cp_block,
+					&cp_page_2, version);
+	if (err)
+		goto invalid_cp;
+	cur_version = *version;
 
 	if (cur_version == pre_version) {
 		*version = cur_version;
 		f2fs_put_page(cp_page_2, 1);
 		return cp_page_1;
 	}
-invalid_cp2:
 	f2fs_put_page(cp_page_2, 1);
-invalid_cp1:
+invalid_cp:
 	f2fs_put_page(cp_page_1, 1);
 	return NULL;
 }
@@ -696,6 +732,15 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
 	memcpy(sbi->ckpt, cp_block, blk_size);
 
+	if (cur_page == cp1)
+		sbi->cur_cp_pack = 1;
+	else
+		sbi->cur_cp_pack = 2;
+
+	/* Sanity checking of checkpoint */
+	if (sanity_check_ckpt(sbi))
+		goto free_fail_no_cp;
+
 	if (cp_blks <= 1)
 		goto done;
 
@@ -717,6 +762,9 @@ done:
 	f2fs_put_page(cp2, 1);
 	return 0;
 
+free_fail_no_cp:
+	f2fs_put_page(cp1, 1);
+	f2fs_put_page(cp2, 1);
 fail_no_cp:
 	kfree(sbi->ckpt);
 	return -EINVAL;
@@ -767,24 +815,6 @@ out:
 	f2fs_trace_pid(page);
 }
 
-void add_dirty_dir_inode(struct inode *inode)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct inode_entry *new =
-			f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
-	int ret = 0;
-
-	new->inode = inode;
-	INIT_LIST_HEAD(&new->list);
-
-	spin_lock(&sbi->dir_inode_lock);
-	ret = __add_dirty_inode(inode, new);
-	spin_unlock(&sbi->dir_inode_lock);
-
-	if (ret)
-		kmem_cache_free(inode_entry_slab, new);
-}
-
 void remove_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -807,12 +837,6 @@ void remove_dirty_dir_inode(struct inode *inode)
 	stat_dec_dirty_dir(sbi);
 	spin_unlock(&sbi->dir_inode_lock);
 	kmem_cache_free(inode_entry_slab, entry);
-
-	/* Only from the recovery routine */
-	if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
-		clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
-		iput(inode);
-	}
 }
 
 void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
@@ -922,7 +946,6 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
 	nid_t last_nid = nm_i->next_scan_nid;
@@ -931,15 +954,6 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	__u32 crc32 = 0;
 	int i;
 	int cp_payload_blks = __cp_payload(sbi);
-	block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
-	bool invalidate = false;
-
-	/*
-	 * This avoids to conduct wrong roll-forward operations and uses
-	 * metapages, so should be called prior to sync_meta_pages below.
-	 */
-	if (discard_next_dnode(sbi, discard_blk))
-		invalidate = true;
 
 	/* Flush all the NAT/SIT pages */
 	while (get_pages(sbi, F2FS_DIRTY_META)) {
@@ -1016,6 +1030,9 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
 		set_ckpt_flags(ckpt, CP_FSCK_FLAG);
 
+	/* set this flag to activate crc|cp_ver for recovery */
+	set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
+
 	/* update SIT/NAT bitmap */
 	get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
 	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
@@ -1025,7 +1042,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 				le32_to_cpu(ckpt->checksum_offset)))
 				= cpu_to_le32(crc32);
 
-	start_blk = __start_cp_addr(sbi);
+	start_blk = __start_cp_next_addr(sbi);
 
 	/* need to wait for end_io results */
 	wait_on_all_pages_writeback(sbi);
@@ -1073,14 +1090,6 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* wait for previous submitted meta pages writeback */
 	wait_on_all_pages_writeback(sbi);
 
-	/*
-	 * invalidate meta page which is used temporarily for zeroing out
-	 * block at the end of warm node chain.
-	 */
-	if (invalidate)
-		invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
-								discard_blk);
-
 	release_dirty_inode(sbi);
 
 	if (unlikely(f2fs_cp_error(sbi)))
@@ -1088,6 +1097,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	clear_prefree_segments(sbi, cpc);
 	clear_sbi_flag(sbi, SBI_IS_DIRTY);
+	__set_cp_next_pack(sbi);
 }
 
 /*
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f6ccb21f286b..2b0b671484bd 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -147,6 +147,10 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	struct bio *bio;
 	struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page;
 
+	if (!f2fs_is_valid_blkaddr(fio->sbi, fio->blk_addr,
+			__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
+		return -EFAULT;
+
 	trace_f2fs_submit_page_bio(page, fio);
 	f2fs_trace_ios(fio, 0);
 
@@ -172,7 +176,7 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 
 	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
 
-	verify_block_addr(sbi, fio->blk_addr);
+	verify_block_addr(fio, fio->blk_addr);
 
 	down_write(&io->io_rwsem);
 
@@ -603,7 +607,13 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 		goto unlock_out;
 	}
 
-	if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) {
+	if (__is_valid_data_blkaddr(dn.data_blkaddr) &&
+		!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, DATA_GENERIC)) {
+		err = -EFAULT;
+		goto sync_out;
+	}
+
+	if (!is_valid_data_blkaddr(sbi, dn.data_blkaddr)) {
 		if (create) {
 			if (unlikely(f2fs_cp_error(sbi))) {
 				err = -EIO;
@@ -866,6 +876,40 @@ out:
 	return ret;
 }
 
+struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
+							unsigned nr_pages)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_crypto_ctx *ctx = NULL;
+	struct block_device *bdev = sbi->sb->s_bdev;
+	struct bio *bio;
+
+	if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
+		return ERR_PTR(-EFAULT);
+
+	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+		ctx = f2fs_get_crypto_ctx(inode);
+		if (IS_ERR(ctx))
+			return ERR_CAST(ctx);
+
+		/* wait the page to be moved by cleaning */
+		f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
+	}
+
+	bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
+	if (!bio) {
+		if (ctx)
+			f2fs_release_crypto_ctx(ctx);
+		return ERR_PTR(-ENOMEM);
+	}
+	bio->bi_bdev = bdev;
+	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blkaddr);
+	bio->bi_end_io = f2fs_read_end_io;
+	bio->bi_private = ctx;
+
+	return bio;
+}
+
 /*
  * This function was originally taken from fs/mpage.c, and customized for f2fs.
  * Major change was from block_size == page_size in f2fs by default.
@@ -884,7 +928,6 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 	sector_t last_block;
 	sector_t last_block_in_file;
 	sector_t block_nr;
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	struct f2fs_map_blocks map;
 
 	map.m_pblk = 0;
@@ -941,6 +984,10 @@ got_it:
 				SetPageUptodate(page);
 				goto confused;
 			}
+
+			if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
+								DATA_GENERIC))
+				goto set_error_page;
 		} else {
 			zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 			SetPageUptodate(page);
@@ -958,31 +1005,9 @@ submit_and_realloc:
 			bio = NULL;
 		}
 		if (bio == NULL) {
-			struct f2fs_crypto_ctx *ctx = NULL;
-
-			if (f2fs_encrypted_inode(inode) &&
-					S_ISREG(inode->i_mode)) {
-
-				ctx = f2fs_get_crypto_ctx(inode);
-				if (IS_ERR(ctx))
-					goto set_error_page;
-
-				/* wait the page to be moved by cleaning */
-				f2fs_wait_on_encrypted_page_writeback(
-						F2FS_I_SB(inode), block_nr);
-			}
-
-			bio = bio_alloc(GFP_KERNEL,
-				min_t(int, nr_pages, BIO_MAX_PAGES));
-			if (!bio) {
-				if (ctx)
-					f2fs_release_crypto_ctx(ctx);
+			bio = f2fs_grab_bio(inode, block_nr, nr_pages);
+			if (IS_ERR(bio))
 				goto set_error_page;
-			}
-			bio->bi_bdev = bdev;
-			bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(block_nr);
-			bio->bi_end_io = f2fs_read_end_io;
-			bio->bi_private = ctx;
 		}
 
 		if (bio_add_page(bio, page, blocksize, 0) < blocksize)
@@ -1077,11 +1102,17 @@ int do_write_data_page(struct f2fs_io_info *fio)
 
 	set_page_writeback(page);
 
+	if (__is_valid_data_blkaddr(fio->blk_addr) &&
+		!f2fs_is_valid_blkaddr(fio->sbi, fio->blk_addr,
+							DATA_GENERIC)) {
+		err = -EFAULT;
+		goto out_writepage;
+	}
 	/*
 	 * If current allocation needs SSR,
 	 * it had better in-place writes for updated data.
 	 */
-	if (unlikely(fio->blk_addr != NEW_ADDR &&
+	if (unlikely(is_valid_data_blkaddr(fio->sbi, fio->blk_addr) &&
 			!is_cold_data(page) &&
 			need_inplace_update(inode))) {
 		rewrite_data_page(fio);
@@ -1482,17 +1513,21 @@ put_next:
 	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 	} else {
-		struct f2fs_io_info fio = {
-			.sbi = sbi,
-			.type = DATA,
-			.rw = READ_SYNC,
-			.blk_addr = dn.data_blkaddr,
-			.page = page,
-			.encrypted_page = NULL,
-		};
-		err = f2fs_submit_page_bio(&fio);
-		if (err)
+		struct bio *bio;
+
+		bio = f2fs_grab_bio(inode, dn.data_blkaddr, 1);
+		if (IS_ERR(bio)) {
+			err = PTR_ERR(bio);
 			goto fail;
+		}
+
+		if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
+			bio_put(bio);
+			err = -EFAULT;
+			goto fail;
+		}
+
+		submit_bio(READ_SYNC, bio);
 
 		lock_page(page);
 		if (unlikely(!PageUptodate(page))) {
@@ -1503,13 +1538,6 @@ put_next:
 			f2fs_put_page(page, 1);
 			goto repeat;
 		}
-
-		/* avoid symlink page */
-		if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
-			err = f2fs_decrypt_one(inode, page);
-			if (err)
-				goto fail;
-		}
 	}
 out_update:
 	SetPageUptodate(page);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 60972a559685..92a240616f52 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -48,7 +48,6 @@ unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
 	[F2FS_FT_SYMLINK]	= DT_LNK,
 };
 
-#define S_SHIFT 12
 static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
 	[S_IFREG >> S_SHIFT]	= F2FS_FT_REG_FILE,
 	[S_IFDIR >> S_SHIFT]	= F2FS_FT_DIR,
@@ -64,6 +63,13 @@ void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
 	de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
 }
 
+unsigned char get_de_type(struct f2fs_dir_entry *de)
+{
+	if (de->file_type < F2FS_FT_MAX)
+		return f2fs_filetype_table[de->file_type];
+	return DT_UNKNOWN;
+}
+
 static unsigned long dir_block_index(unsigned int level,
 				int dir_level, unsigned int idx)
 {
@@ -519,11 +525,7 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
 		test_and_set_bit_le(bit_pos + i, (void *)d->bitmap);
 }
 
-/*
- * Caller should grab and release a rwsem by calling f2fs_lock_op() and
- * f2fs_unlock_op().
- */
-int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
 				struct inode *inode, nid_t ino, umode_t mode)
 {
 	unsigned int bit_pos;
@@ -536,28 +538,11 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	struct f2fs_dentry_ptr d;
 	struct page *page = NULL;
-	struct f2fs_filename fname;
-	struct qstr new_name;
-	int slots, err;
-
-	err = f2fs_fname_setup_filename(dir, name, 0, &fname);
-	if (err)
-		return err;
-
-	new_name.name = fname_name(&fname);
-	new_name.len = fname_len(&fname);
-
-	if (f2fs_has_inline_dentry(dir)) {
-		err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
-		if (!err || err != -EAGAIN)
-			goto out;
-		else
-			err = 0;
-	}
+	int slots, err = 0;
 
 	level = 0;
-	slots = GET_DENTRY_SLOTS(new_name.len);
-	dentry_hash = f2fs_dentry_hash(&new_name, NULL);
+	slots = GET_DENTRY_SLOTS(new_name->len);
+	dentry_hash = f2fs_dentry_hash(new_name, NULL);
 
 	current_depth = F2FS_I(dir)->i_current_depth;
 	if (F2FS_I(dir)->chash == dentry_hash) {
@@ -566,10 +551,8 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 	}
 
 start:
-	if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) {
-		err = -ENOSPC;
-		goto out;
-	}
+	if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
+		return -ENOSPC;
 
 	/* Increase the depth, if required */
 	if (level == current_depth)
@@ -583,10 +566,8 @@ start:
 
 	for (block = bidx; block <= (bidx + nblock - 1); block++) {
 		dentry_page = get_new_data_page(dir, NULL, block, true);
-		if (IS_ERR(dentry_page)) {
-			err = PTR_ERR(dentry_page);
-			goto out;
-		}
+		if (IS_ERR(dentry_page))
+			return PTR_ERR(dentry_page);
 
 		dentry_blk = kmap(dentry_page);
 		bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
@@ -606,7 +587,7 @@ add_dentry:
 
 	if (inode) {
 		down_write(&F2FS_I(inode)->i_sem);
-		page = init_inode_metadata(inode, dir, &new_name, NULL);
+		page = init_inode_metadata(inode, dir, new_name, NULL);
 		if (IS_ERR(page)) {
 			err = PTR_ERR(page);
 			goto fail;
@@ -616,7 +597,7 @@ add_dentry:
 	}
 
 	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
-	f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos);
+	f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
 
 	set_page_dirty(dentry_page);
 
@@ -638,7 +619,34 @@ fail:
 	}
 	kunmap(dentry_page);
 	f2fs_put_page(dentry_page, 1);
-out:
+
+	return err;
+}
+
+/*
+ * Caller should grab and release a rwsem by calling f2fs_lock_op() and
+ * f2fs_unlock_op().
+ */
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+				struct inode *inode, nid_t ino, umode_t mode)
+{
+	struct f2fs_filename fname;
+	struct qstr new_name;
+	int err;
+
+	err = f2fs_fname_setup_filename(dir, name, 0, &fname);
+	if (err)
+		return err;
+
+	new_name.name = fname_name(&fname);
+	new_name.len = fname_len(&fname);
+
+	err = -EAGAIN;
+	if (f2fs_has_inline_dentry(dir))
+		err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
+	if (err == -EAGAIN)
+		err = f2fs_add_regular_entry(dir, &new_name, inode, ino, mode);
+
 	f2fs_fname_free_filename(&fname);
 	return err;
 }
@@ -792,10 +800,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			break;
 
 		de = &d->dentry[bit_pos];
-		if (de->file_type < F2FS_FT_MAX)
-			d_type = f2fs_filetype_table[de->file_type];
-		else
-			d_type = DT_UNKNOWN;
+		d_type = get_de_type(de);
 
 		de_name.name = d->filename[bit_pos];
 		de_name.len = le16_to_cpu(de->name_len);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2871576fbca4..2bfce887dce2 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -135,7 +135,7 @@ struct cp_control {
 };
 
 /*
- * For CP/NAT/SIT/SSA readahead
+ * indicate meta/data type
  */
 enum {
 	META_CP,
@@ -143,6 +143,8 @@ enum {
 	META_SIT,
 	META_SSA,
 	META_POR,
+	DATA_GENERIC,
+	META_GENERIC,
 };
 
 /* for the list of ino */
@@ -684,6 +686,7 @@ struct f2fs_io_info {
 	block_t blk_addr;	/* block address to be written */
 	struct page *page;	/* page to be written */
 	struct page *encrypted_page;	/* encrypted page */
+	bool is_meta;		/* indicate borrow meta inode mapping or not */
 };
 
 #define is_read_io(rw)	(((rw) & 1) == READ)
@@ -731,6 +734,7 @@ struct f2fs_sb_info {
 
 	/* for checkpoint */
 	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
+	int cur_cp_pack;			/* remain current cp pack */
 	struct inode *meta_inode;		/* cache meta blocks */
 	struct mutex cp_mutex;			/* checkpoint procedure lock */
 	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
@@ -1140,22 +1144,27 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
 
 static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
 {
-	block_t start_addr;
-	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	unsigned long long ckpt_version = cur_cp_version(ckpt);
-
-	start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
+	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
 
-	/*
-	 * odd numbered checkpoint should at cp segment 0
-	 * and even segment must be at cp segment 1
-	 */
-	if (!(ckpt_version & 1))
+	if (sbi->cur_cp_pack == 2)
 		start_addr += sbi->blocks_per_seg;
+	return start_addr;
+}
+
+static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi)
+{
+	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
 
+	if (sbi->cur_cp_pack == 1)
+		start_addr += sbi->blocks_per_seg;
 	return start_addr;
 }
 
+static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
+{
+	sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
+}
+
 static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
 {
 	return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
@@ -1402,7 +1411,6 @@ enum {
 	FI_NO_ALLOC,		/* should not allocate any blocks */
 	FI_FREE_NID,		/* free allocated nide */
 	FI_UPDATE_DIR,		/* should update inode block for consistency */
-	FI_DELAY_IPUT,		/* used for the recovery */
 	FI_NO_EXTENT,		/* not to use the extent cache */
 	FI_INLINE_XATTR,	/* used for inline xattr */
 	FI_INLINE_DATA,		/* used for inline data*/
@@ -1641,6 +1649,39 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
 	(pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) /	\
 	ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
 
+#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO(fio->type) == META &&	\
+				(!is_read_io(fio->rw) || fio->is_meta))
+
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+					block_t blkaddr, int type);
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
+static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
+					block_t blkaddr, int type)
+{
+	if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"invalid blkaddr: %u, type: %d, run fsck to fix.",
+			blkaddr, type);
+		f2fs_bug_on(sbi, 1);
+	}
+}
+
+static inline bool __is_valid_data_blkaddr(block_t blkaddr)
+{
+	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+		return false;
+	return true;
+}
+
+static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi,
+						block_t blkaddr)
+{
+	if (!__is_valid_data_blkaddr(blkaddr))
+		return false;
+	verify_blkaddr(sbi, blkaddr, DATA_GENERIC);
+	return true;
+}
+
 /*
  * file.c
  */
@@ -1677,7 +1718,7 @@ struct dentry *f2fs_get_parent(struct dentry *child);
  */
 extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
 void set_de_type(struct f2fs_dir_entry *, umode_t);
-
+unsigned char get_de_type(struct f2fs_dir_entry *);
 struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *,
 			f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
 bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
@@ -1698,6 +1739,8 @@ void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
 int update_dent_inode(struct inode *, struct inode *, const struct qstr *);
 void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *,
 			const struct qstr *, f2fs_hash_t , unsigned int);
+int f2fs_add_regular_entry(struct inode *, const struct qstr *,
+						struct inode *, nid_t, umode_t);
 int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t,
 			umode_t);
 void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
@@ -1718,6 +1761,7 @@ int f2fs_commit_super(struct f2fs_sb_info *, bool);
 int f2fs_sync_fs(struct super_block *, int);
 extern __printf(3, 4)
 void f2fs_msg(struct super_block *, const char *, const char *, ...);
+int sanity_check_ckpt(struct f2fs_sb_info *sbi);
 
 /*
  * hash.c
@@ -1778,7 +1822,6 @@ bool is_checkpointed_data(struct f2fs_sb_info *, block_t);
 void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
 void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *);
 void release_discard_addrs(struct f2fs_sb_info *);
-bool discard_next_dnode(struct f2fs_sb_info *, block_t);
 int npages_for_summary_flush(struct f2fs_sb_info *, bool);
 void allocate_new_segments(struct f2fs_sb_info *);
 int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
@@ -1810,7 +1853,8 @@ void destroy_segment_manager_caches(void);
 struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
 struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
 struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
-bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int);
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+					block_t blkaddr, int type);
 int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool);
 void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
 long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
@@ -1825,7 +1869,6 @@ void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
 int recover_orphan_inodes(struct f2fs_sb_info *);
 int get_valid_checkpoint(struct f2fs_sb_info *);
 void update_dirty_page(struct inode *, struct page *);
-void add_dirty_dir_inode(struct inode *);
 void remove_dirty_dir_inode(struct inode *);
 void sync_dirty_dir_inodes(struct f2fs_sb_info *);
 void write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
@@ -1864,7 +1907,7 @@ void build_gc_manager(struct f2fs_sb_info *);
 /*
  * recovery.c
  */
-int recover_fsync_data(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *, bool);
 bool space_for_roll_forward(struct f2fs_sb_info *);
 
 /*
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 01eed94b01ea..bee3bc7a16ac 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -200,6 +200,9 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	trace_f2fs_sync_file_enter(inode);
 
+	if (S_ISDIR(inode->i_mode))
+		goto go_write;
+
 	/* if fdatasync is triggered, let's do in-place-update */
 	if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
 		set_inode_flag(fi, FI_NEED_IPU);
@@ -305,13 +308,13 @@ static pgoff_t __get_first_dirty_index(struct address_space *mapping,
 	return pgofs;
 }
 
-static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
-							int whence)
+static bool __found_offset(struct f2fs_sb_info *sbi, block_t blkaddr,
+				pgoff_t dirty, pgoff_t pgofs, int whence)
 {
 	switch (whence) {
 	case SEEK_DATA:
 		if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
-			(blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
+			is_valid_data_blkaddr(sbi, blkaddr))
 			return true;
 		break;
 	case SEEK_HOLE:
@@ -374,7 +377,15 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 			block_t blkaddr;
 			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
 
-			if (__found_offset(blkaddr, dirty, pgofs, whence)) {
+			if (__is_valid_data_blkaddr(blkaddr) &&
+				!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
+						blkaddr, DATA_GENERIC)) {
+				f2fs_put_dnode(&dn);
+				goto fail;
+			}
+
+			if (__found_offset(F2FS_I_SB(inode), blkaddr, dirty,
+							pgofs, whence)) {
 				f2fs_put_dnode(&dn);
 				goto found;
 			}
@@ -466,6 +477,11 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 
 		dn->data_blkaddr = NULL_ADDR;
 		set_data_blkaddr(dn);
+
+		if (__is_valid_data_blkaddr(blkaddr) &&
+			!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
+			continue;
+
 		invalidate_blocks(sbi, blkaddr);
 		if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
 			clear_inode_flag(F2FS_I(dn->inode),
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index ad80f916b64d..00685a8b1418 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -127,6 +127,16 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	if (err)
 		return err;
 
+	if (unlikely(dn->data_blkaddr != NEW_ADDR)) {
+		f2fs_put_dnode(dn);
+		set_sbi_flag(fio.sbi, SBI_NEED_FSCK);
+		f2fs_msg(fio.sbi->sb, KERN_WARNING,
+			"%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, "
+			"run fsck to fix.",
+			__func__, dn->inode->i_ino, dn->data_blkaddr);
+		return -EINVAL;
+	}
+
 	f2fs_wait_on_page_writeback(page, DATA);
 
 	if (PageUptodate(page))
@@ -367,7 +377,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
  * NOTE: ipage is grabbed by caller, but if any error occurs, we should
  * release ipage in this function.
  */
-static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
 				struct f2fs_inline_dentry *inline_dentry)
 {
 	struct page *page;
@@ -386,6 +396,17 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	if (err)
 		goto out;
 
+	if (unlikely(dn.data_blkaddr != NEW_ADDR)) {
+		f2fs_put_dnode(&dn);
+		set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK);
+		f2fs_msg(F2FS_P_SB(page)->sb, KERN_WARNING,
+			"%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, "
+			"run fsck to fix.",
+			__func__, dir->i_ino, dn.data_blkaddr);
+		err = -EINVAL;
+		goto out;
+	}
+
 	f2fs_wait_on_page_writeback(page, DATA);
 	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
 
@@ -428,6 +449,98 @@ out:
 	return err;
 }
 
+static int f2fs_add_inline_entries(struct inode *dir,
+			struct f2fs_inline_dentry *inline_dentry)
+{
+	struct f2fs_dentry_ptr d;
+	unsigned long bit_pos = 0;
+	int err = 0;
+
+	make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+
+	while (bit_pos < d.max) {
+		struct f2fs_dir_entry *de;
+		struct qstr new_name;
+		nid_t ino;
+		umode_t fake_mode;
+
+		if (!test_bit_le(bit_pos, d.bitmap)) {
+			bit_pos++;
+			continue;
+		}
+
+		de = &d.dentry[bit_pos];
+		new_name.name = d.filename[bit_pos];
+		new_name.len = de->name_len;
+
+		ino = le32_to_cpu(de->ino);
+		fake_mode = get_de_type(de) << S_SHIFT;
+
+		err = f2fs_add_regular_entry(dir, &new_name, NULL,
+							ino, fake_mode);
+		if (err)
+			goto punch_dentry_pages;
+
+		if (unlikely(!de->name_len))
+			d.max = -1;
+
+		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+	}
+	return 0;
+punch_dentry_pages:
+	truncate_inode_pages(&dir->i_data, 0);
+	truncate_blocks(dir, 0, false);
+	remove_dirty_dir_inode(dir);
+	return err;
+}
+
+static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
+				struct f2fs_inline_dentry *inline_dentry)
+{
+	struct f2fs_inline_dentry *backup_dentry;
+	int err;
+
+	backup_dentry = kmalloc(sizeof(struct f2fs_inline_dentry),
+							GFP_F2FS_ZERO);
+	if (!backup_dentry)
+		return -ENOMEM;
+
+	memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
+	truncate_inline_inode(ipage, 0);
+
+	unlock_page(ipage);
+
+	err = f2fs_add_inline_entries(dir, backup_dentry);
+	if (err)
+		goto recover;
+
+	lock_page(ipage);
+
+	stat_dec_inline_dir(dir);
+	clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
+	update_inode(dir, ipage);
+	kfree(backup_dentry);
+	return 0;
+recover:
+	lock_page(ipage);
+	memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+	i_size_write(dir, MAX_INLINE_DATA);
+	update_inode(dir, ipage);
+	f2fs_put_page(ipage, 1);
+
+	kfree(backup_dentry);
+	return err;
+}
+
+static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+				struct f2fs_inline_dentry *inline_dentry)
+{
+	if (!F2FS_I(dir)->i_dir_level)
+		return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
+	else
+		return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
+}
+
 int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
 			struct inode *inode, nid_t ino, umode_t mode)
 {
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 5528801a5baf..89bf8dd7758c 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -50,13 +50,16 @@ static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 	}
 }
 
-static bool __written_first_block(struct f2fs_inode *ri)
+static int __written_first_block(struct f2fs_sb_info *sbi,
+					struct f2fs_inode *ri)
 {
 	block_t addr = le32_to_cpu(ri->i_addr[0]);
 
-	if (addr != NEW_ADDR && addr != NULL_ADDR)
-		return true;
-	return false;
+	if (!__is_valid_data_blkaddr(addr))
+		return 1;
+	if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC))
+		return -EFAULT;
+	return 0;
 }
 
 static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -94,12 +97,57 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
 	return;
 }
 
+static bool sanity_check_inode(struct inode *inode, struct page *node_page)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	unsigned long long iblocks;
+
+	iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks);
+	if (!iblocks) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"%s: corrupted inode i_blocks i_ino=%lx iblocks=%llu, "
+			"run fsck to fix.",
+			__func__, inode->i_ino, iblocks);
+		return false;
+	}
+
+	if (ino_of_node(node_page) != nid_of_node(node_page)) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"%s: corrupted inode footer i_ino=%lx, ino,nid: "
+			"[%u, %u] run fsck to fix.",
+			__func__, inode->i_ino,
+			ino_of_node(node_page), nid_of_node(node_page));
+		return false;
+	}
+
+	if (F2FS_I(inode)->extent_tree) {
+		struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest;
+
+		if (ei->len &&
+			(!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC) ||
+			!f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
+							DATA_GENERIC))) {
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			f2fs_msg(sbi->sb, KERN_WARNING,
+				"%s: inode (ino=%lx) extent info [%u, %u, %u] "
+				"is incorrect, run fsck to fix",
+				__func__, inode->i_ino,
+				ei->blk, ei->fofs, ei->len);
+			return false;
+		}
+	}
+	return true;
+}
+
 static int do_read_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct page *node_page;
 	struct f2fs_inode *ri;
+	int err;
 
 	/* Check if ino is within scope */
 	if (check_nid_range(sbi, inode->i_ino)) {
@@ -142,6 +190,11 @@ static int do_read_inode(struct inode *inode)
 
 	get_inline_info(fi, ri);
 
+	if (!sanity_check_inode(inode, node_page)) {
+		f2fs_put_page(node_page, 1);
+		return -EINVAL;
+	}
+
 	/* check data exist */
 	if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
 		__recover_inline_status(inode, node_page);
@@ -149,7 +202,12 @@ static int do_read_inode(struct inode *inode)
 	/* get rdev by using inline_info */
 	__get_inode_rdev(inode, ri);
 
-	if (__written_first_block(ri))
+	err = __written_first_block(sbi, ri);
+	if (err < 0) {
+		f2fs_put_page(node_page, 1);
+		return err;
+	}
+	if (!err)
 		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
 
 	f2fs_put_page(node_page, 1);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 7bcbc6e9c40d..582373849332 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -261,13 +261,11 @@ static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
 {
 	struct nat_entry *e;
 
-	down_write(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
 	if (!e) {
 		e = grab_nat_entry(nm_i, nid);
 		node_info_from_raw_nat(&e->ni, ne);
 	}
-	up_write(&nm_i->nat_tree_lock);
 }
 
 static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
@@ -298,8 +296,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 			new_blkaddr == NULL_ADDR);
 	f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR &&
 			new_blkaddr == NEW_ADDR);
-	f2fs_bug_on(sbi, nat_get_blkaddr(e) != NEW_ADDR &&
-			nat_get_blkaddr(e) != NULL_ADDR &&
+	f2fs_bug_on(sbi, is_valid_data_blkaddr(sbi, nat_get_blkaddr(e)) &&
 			new_blkaddr == NEW_ADDR);
 
 	/* increment version no as node is removed */
@@ -314,7 +311,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 
 	/* change address */
 	nat_set_blkaddr(e, new_blkaddr);
-	if (new_blkaddr == NEW_ADDR || new_blkaddr == NULL_ADDR)
+	if (!is_valid_data_blkaddr(sbi, new_blkaddr))
 		set_nat_flag(e, IS_CHECKPOINTED, false);
 	__set_nat_cache_dirty(nm_i, e);
 
@@ -379,6 +376,8 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 
 	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
 
+	down_write(&nm_i->nat_tree_lock);
+
 	/* Check current segment summary */
 	mutex_lock(&curseg->curseg_mutex);
 	i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
@@ -399,6 +398,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 cache:
 	/* cache nat entry */
 	cache_nat_entry(NM_I(sbi), nid, &ne);
+	up_write(&nm_i->nat_tree_lock);
 }
 
 /*
@@ -590,6 +590,7 @@ static void truncate_node(struct dnode_of_data *dn)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct node_info ni;
+	pgoff_t index;
 
 	get_node_info(sbi, dn->nid, &ni);
 	if (dn->inode->i_blocks == 0) {
@@ -613,10 +614,11 @@ invalidate:
 	clear_node_page_dirty(dn->node_page);
 	set_sbi_flag(sbi, SBI_IS_DIRTY);
 
+	index = dn->node_page->index;
 	f2fs_put_page(dn->node_page, 1);
 
 	invalidate_mapping_pages(NODE_MAPPING(sbi),
-			dn->node_page->index, dn->node_page->index);
+			index, index);
 
 	dn->node_page = NULL;
 	trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);
@@ -1341,6 +1343,12 @@ static int f2fs_write_node_page(struct page *page,
 		return 0;
 	}
 
+	if (__is_valid_data_blkaddr(ni.blk_addr) &&
+		!f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) {
+		up_read(&sbi->node_write);
+		goto redirty_out;
+	}
+
 	set_page_writeback(page);
 	fio.blk_addr = ni.blk_addr;
 	write_node_page(nid, &fio);
@@ -1427,9 +1435,9 @@ static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i,
 static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	struct free_nid *i;
+	struct free_nid *i, *e;
 	struct nat_entry *ne;
-	bool allocated = false;
+	int err = -EINVAL;
 
 	if (!available_free_memory(sbi, FREE_NIDS))
 		return -1;
@@ -1438,40 +1446,58 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 	if (unlikely(nid == 0))
 		return 0;
 
-	if (build) {
-		/* do not add allocated nids */
-		down_read(&nm_i->nat_tree_lock);
-		ne = __lookup_nat_cache(nm_i, nid);
-		if (ne &&
-			(!get_nat_flag(ne, IS_CHECKPOINTED) ||
-				nat_get_blkaddr(ne) != NULL_ADDR))
-			allocated = true;
-		up_read(&nm_i->nat_tree_lock);
-		if (allocated)
-			return 0;
-	}
-
 	i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS);
 	i->nid = nid;
 	i->state = NID_NEW;
 
-	if (radix_tree_preload(GFP_NOFS)) {
-		kmem_cache_free(free_nid_slab, i);
-		return 0;
-	}
+	if (radix_tree_preload(GFP_NOFS))
+		goto err;
 
 	spin_lock(&nm_i->free_nid_list_lock);
-	if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) {
-		spin_unlock(&nm_i->free_nid_list_lock);
-		radix_tree_preload_end();
-		kmem_cache_free(free_nid_slab, i);
-		return 0;
+
+	if (build) {
+		/*
+		 *   Thread A             Thread B
+		 *  - f2fs_create
+		 *   - f2fs_new_inode
+		 *    - alloc_nid
+		 *     - __insert_nid_to_list(ALLOC_NID_LIST)
+		 *                     - f2fs_balance_fs_bg
+		 *                      - build_free_nids
+		 *                       - __build_free_nids
+		 *                        - scan_nat_page
+		 *                         - add_free_nid
+		 *                          - __lookup_nat_cache
+		 *  - f2fs_add_link
+		 *   - init_inode_metadata
+		 *    - new_inode_page
+		 *     - new_node_page
+		 *      - set_node_addr
+		 *  - alloc_nid_done
+		 *   - __remove_nid_from_list(ALLOC_NID_LIST)
+		 *                         - __insert_nid_to_list(FREE_NID_LIST)
+		 */
+		ne = __lookup_nat_cache(nm_i, nid);
+		if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
+				nat_get_blkaddr(ne) != NULL_ADDR))
+			goto err_out;
+
+		e = __lookup_free_nid_list(nm_i, nid);
+		if (e)
+			goto err_out;
 	}
+	if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i))
+		goto err_out;
+	err = 0;
 	list_add_tail(&i->list, &nm_i->free_nid_list);
 	nm_i->fcnt++;
+err_out:
 	spin_unlock(&nm_i->free_nid_list_lock);
 	radix_tree_preload_end();
-	return 1;
+err:
+	if (err)
+		kmem_cache_free(free_nid_slab, i);
+	return !err;
 }
 
 static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
@@ -1532,6 +1558,8 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
 							META_NAT, true);
 
+	down_read(&nm_i->nat_tree_lock);
+
 	while (1) {
 		struct page *page = get_current_nat_page(sbi, nid);
 
@@ -1560,6 +1588,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 			remove_free_nid(nm_i, nid);
 	}
 	mutex_unlock(&curseg->curseg_mutex);
+	up_read(&nm_i->nat_tree_lock);
 
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
 					nm_i->ra_nid_pages, META_NAT, false);
@@ -1842,14 +1871,12 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 
 		raw_ne = nat_in_journal(sum, i);
 
-		down_write(&nm_i->nat_tree_lock);
 		ne = __lookup_nat_cache(nm_i, nid);
 		if (!ne) {
 			ne = grab_nat_entry(nm_i, nid);
 			node_info_from_raw_nat(&ne->ni, &raw_ne);
 		}
 		__set_nat_cache_dirty(nm_i, ne);
-		up_write(&nm_i->nat_tree_lock);
 	}
 	update_nats_in_cursum(sum, -i);
 	mutex_unlock(&curseg->curseg_mutex);
@@ -1883,7 +1910,6 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 	struct f2fs_nat_block *nat_blk;
 	struct nat_entry *ne, *cur;
 	struct page *page = NULL;
-	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
 	/*
 	 * there are two steps to flush nat entries:
@@ -1920,12 +1946,8 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 			raw_ne = &nat_blk->entries[nid - start_nid];
 		}
 		raw_nat_from_node_info(raw_ne, &ne->ni);
-
-		down_write(&NM_I(sbi)->nat_tree_lock);
 		nat_reset_flag(ne);
 		__clear_nat_cache_dirty(NM_I(sbi), ne);
-		up_write(&NM_I(sbi)->nat_tree_lock);
-
 		if (nat_get_blkaddr(ne) == NULL_ADDR)
 			add_free_nid(sbi, nid, false);
 	}
@@ -1937,9 +1959,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 
 	f2fs_bug_on(sbi, set->entry_cnt);
 
-	down_write(&nm_i->nat_tree_lock);
 	radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
-	up_write(&nm_i->nat_tree_lock);
 	kmem_cache_free(nat_entry_set_slab, set);
 }
 
@@ -1959,6 +1979,9 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 
 	if (!nm_i->dirty_nat_cnt)
 		return;
+
+	down_write(&nm_i->nat_tree_lock);
+
 	/*
 	 * if there are no enough space in journal to store dirty nat
 	 * entries, remove all entries from journal and merge them
@@ -1967,7 +1990,6 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 	if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL))
 		remove_nats_in_journal(sbi);
 
-	down_write(&nm_i->nat_tree_lock);
 	while ((found = __gang_lookup_nat_set(nm_i,
 					set_idx, SETVEC_SIZE, setvec))) {
 		unsigned idx;
@@ -1976,12 +1998,13 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 			__adjust_nat_entry_set(setvec[idx], &sets,
 							MAX_NAT_JENTRIES(sum));
 	}
-	up_write(&nm_i->nat_tree_lock);
 
 	/* flush dirty nats in nat entry set */
 	list_for_each_entry_safe(set, tmp, &sets, set_list)
 		__flush_nat_entry_set(sbi, set);
 
+	up_write(&nm_i->nat_tree_lock);
+
 	f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
 }
 
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index e4fffd2d98c4..0d6f0e3dc655 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -212,6 +212,37 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
 	f2fs_change_bit(block_off, nm_i->nat_bitmap);
 }
 
+static inline nid_t ino_of_node(struct page *node_page)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_page);
+	return le32_to_cpu(rn->footer.ino);
+}
+
+static inline nid_t nid_of_node(struct page *node_page)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_page);
+	return le32_to_cpu(rn->footer.nid);
+}
+
+static inline unsigned int ofs_of_node(struct page *node_page)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_page);
+	unsigned flag = le32_to_cpu(rn->footer.flag);
+	return flag >> OFFSET_BIT_SHIFT;
+}
+
+static inline __u64 cpver_of_node(struct page *node_page)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_page);
+	return le64_to_cpu(rn->footer.cp_ver);
+}
+
+static inline block_t next_blkaddr_of_node(struct page *node_page)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_page);
+	return le32_to_cpu(rn->footer.next_blkaddr);
+}
+
 static inline void fill_node_footer(struct page *page, nid_t nid,
 				nid_t ino, unsigned int ofs, bool reset)
 {
@@ -242,40 +273,30 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
 	struct f2fs_node *rn = F2FS_NODE(page);
+	size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
+	__u64 cp_ver = le64_to_cpu(ckpt->checkpoint_ver);
 
-	rn->footer.cp_ver = ckpt->checkpoint_ver;
+	if (is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
+		__u64 crc = le32_to_cpu(*((__le32 *)
+				((unsigned char *)ckpt + crc_offset)));
+		cp_ver |= (crc << 32);
+	}
+	rn->footer.cp_ver = cpu_to_le64(cp_ver);
 	rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
 }
 
-static inline nid_t ino_of_node(struct page *node_page)
-{
-	struct f2fs_node *rn = F2FS_NODE(node_page);
-	return le32_to_cpu(rn->footer.ino);
-}
-
-static inline nid_t nid_of_node(struct page *node_page)
+static inline bool is_recoverable_dnode(struct page *page)
 {
-	struct f2fs_node *rn = F2FS_NODE(node_page);
-	return le32_to_cpu(rn->footer.nid);
-}
-
-static inline unsigned int ofs_of_node(struct page *node_page)
-{
-	struct f2fs_node *rn = F2FS_NODE(node_page);
-	unsigned flag = le32_to_cpu(rn->footer.flag);
-	return flag >> OFFSET_BIT_SHIFT;
-}
-
-static inline unsigned long long cpver_of_node(struct page *node_page)
-{
-	struct f2fs_node *rn = F2FS_NODE(node_page);
-	return le64_to_cpu(rn->footer.cp_ver);
-}
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
+	size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
+	__u64 cp_ver = cur_cp_version(ckpt);
 
-static inline block_t next_blkaddr_of_node(struct page *node_page)
-{
-	struct f2fs_node *rn = F2FS_NODE(node_page);
-	return le32_to_cpu(rn->footer.next_blkaddr);
+	if (is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
+		__u64 crc = le32_to_cpu(*((__le32 *)
+				((unsigned char *)ckpt + crc_offset)));
+		cp_ver |= (crc << 32);
+	}
+	return cpu_to_le64(cp_ver) == cpver_of_node(page);
 }
 
 /*
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index e32f349f341b..2878be3e448f 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -67,7 +67,30 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
 	return NULL;
 }
 
-static int recover_dentry(struct inode *inode, struct page *ipage)
+static struct fsync_inode_entry *add_fsync_inode(struct list_head *head,
+							struct inode *inode)
+{
+	struct fsync_inode_entry *entry;
+
+	entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
+	if (!entry)
+		return NULL;
+
+	entry->inode = inode;
+	list_add_tail(&entry->list, head);
+
+	return entry;
+}
+
+static void del_fsync_inode(struct fsync_inode_entry *entry)
+{
+	iput(entry->inode);
+	list_del(&entry->list);
+	kmem_cache_free(fsync_entry_slab, entry);
+}
+
+static int recover_dentry(struct inode *inode, struct page *ipage,
+						struct list_head *dir_list)
 {
 	struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
 	nid_t pino = le32_to_cpu(raw_inode->i_pino);
@@ -75,18 +98,29 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
 	struct qstr name;
 	struct page *page;
 	struct inode *dir, *einode;
+	struct fsync_inode_entry *entry;
 	int err = 0;
 
-	dir = f2fs_iget(inode->i_sb, pino);
-	if (IS_ERR(dir)) {
-		err = PTR_ERR(dir);
-		goto out;
+	entry = get_fsync_inode(dir_list, pino);
+	if (!entry) {
+		dir = f2fs_iget(inode->i_sb, pino);
+		if (IS_ERR(dir)) {
+			err = PTR_ERR(dir);
+			goto out;
+		}
+
+		entry = add_fsync_inode(dir_list, dir);
+		if (!entry) {
+			err = -ENOMEM;
+			iput(dir);
+			goto out;
+		}
 	}
 
-	if (file_enc_name(inode)) {
-		iput(dir);
+	dir = entry->inode;
+
+	if (file_enc_name(inode))
 		return 0;
-	}
 
 	name.len = le32_to_cpu(raw_inode->i_namelen);
 	name.name = raw_inode->i_name;
@@ -94,7 +128,7 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
 	if (unlikely(name.len > F2FS_NAME_LEN)) {
 		WARN_ON(1);
 		err = -ENAMETOOLONG;
-		goto out_err;
+		goto out;
 	}
 retry:
 	de = f2fs_find_entry(dir, &name, &page);
@@ -120,23 +154,12 @@ retry:
 		goto retry;
 	}
 	err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode);
-	if (err)
-		goto out_err;
-
-	if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) {
-		iput(dir);
-	} else {
-		add_dirty_dir_inode(dir);
-		set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
-	}
 
 	goto out;
 
 out_unmap_put:
 	f2fs_dentry_kunmap(dir, page);
 	f2fs_put_page(page, 0);
-out_err:
-	iput(dir);
 out:
 	f2fs_msg(inode->i_sb, KERN_NOTICE,
 			"%s: ino = %x, name = %s, dir = %lx, err = %d",
@@ -170,8 +193,8 @@ static void recover_inode(struct inode *inode, struct page *page)
 
 static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 {
-	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
 	struct curseg_info *curseg;
+	struct inode *inode;
 	struct page *page = NULL;
 	block_t blkaddr;
 	int err = 0;
@@ -185,12 +208,12 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 	while (1) {
 		struct fsync_inode_entry *entry;
 
-		if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
+		if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
 			return 0;
 
 		page = get_tmp_page(sbi, blkaddr);
 
-		if (cp_ver != cpver_of_node(page))
+		if (!is_recoverable_dnode(page))
 			break;
 
 		if (!is_fsync_dnode(page))
@@ -204,27 +227,27 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 					break;
 			}
 
-			/* add this fsync inode to the list */
-			entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
-			if (!entry) {
-				err = -ENOMEM;
-				break;
-			}
 			/*
 			 * CP | dnode(F) | inode(DF)
 			 * For this case, we should not give up now.
 			 */
-			entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
-			if (IS_ERR(entry->inode)) {
-				err = PTR_ERR(entry->inode);
-				kmem_cache_free(fsync_entry_slab, entry);
+			inode = f2fs_iget(sbi->sb, ino_of_node(page));
+			if (IS_ERR(inode)) {
+				err = PTR_ERR(inode);
 				if (err == -ENOENT) {
 					err = 0;
 					goto next;
 				}
 				break;
 			}
-			list_add_tail(&entry->list, head);
+
+			/* add this fsync inode to the list */
+			entry = add_fsync_inode(head, inode);
+			if (!entry) {
+				err = -ENOMEM;
+				iput(inode);
+				break;
+			}
 		}
 		entry->blkaddr = blkaddr;
 
@@ -248,11 +271,8 @@ static void destroy_fsync_dnodes(struct list_head *head)
 {
 	struct fsync_inode_entry *entry, *tmp;
 
-	list_for_each_entry_safe(entry, tmp, head, list) {
-		iput(entry->inode);
-		list_del(&entry->list);
-		kmem_cache_free(fsync_entry_slab, entry);
-	}
+	list_for_each_entry_safe(entry, tmp, head, list)
+		del_fsync_inode(entry);
 }
 
 static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
@@ -423,7 +443,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 		}
 
 		/* dest is valid block, try to recover from src to dest */
-		if (is_valid_blkaddr(sbi, dest, META_POR)) {
+		if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
 
 			if (src == NULL_ADDR) {
 				err = reserve_new_block(&dn);
@@ -459,35 +479,34 @@ out:
 	return err;
 }
 
-static int recover_data(struct f2fs_sb_info *sbi,
-				struct list_head *head, int type)
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
+						struct list_head *dir_list)
 {
-	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
 	struct curseg_info *curseg;
 	struct page *page = NULL;
 	int err = 0;
 	block_t blkaddr;
 
 	/* get node pages in the current segment */
-	curseg = CURSEG_I(sbi, type);
+	curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	while (1) {
 		struct fsync_inode_entry *entry;
 
-		if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
+		if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
 			break;
 
 		ra_meta_pages_cond(sbi, blkaddr);
 
 		page = get_tmp_page(sbi, blkaddr);
 
-		if (cp_ver != cpver_of_node(page)) {
+		if (!is_recoverable_dnode(page)) {
 			f2fs_put_page(page, 1);
 			break;
 		}
 
-		entry = get_fsync_inode(head, ino_of_node(page));
+		entry = get_fsync_inode(inode_list, ino_of_node(page));
 		if (!entry)
 			goto next;
 		/*
@@ -498,7 +517,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
 		if (entry->last_inode == blkaddr)
 			recover_inode(entry->inode, page);
 		if (entry->last_dentry == blkaddr) {
-			err = recover_dentry(entry->inode, page);
+			err = recover_dentry(entry->inode, page, dir_list);
 			if (err) {
 				f2fs_put_page(page, 1);
 				break;
@@ -510,11 +529,8 @@ static int recover_data(struct f2fs_sb_info *sbi,
 			break;
 		}
 
-		if (entry->blkaddr == blkaddr) {
-			iput(entry->inode);
-			list_del(&entry->list);
-			kmem_cache_free(fsync_entry_slab, entry);
-		}
+		if (entry->blkaddr == blkaddr)
+			del_fsync_inode(entry);
 next:
 		/* check next segment */
 		blkaddr = next_blkaddr_of_node(page);
@@ -525,12 +541,14 @@ next:
 	return err;
 }
 
-int recover_fsync_data(struct f2fs_sb_info *sbi)
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	struct list_head inode_list;
+	struct list_head dir_list;
 	block_t blkaddr;
 	int err;
+	int ret = 0;
 	bool need_writecp = false;
 
 	fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
@@ -539,6 +557,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&inode_list);
+	INIT_LIST_HEAD(&dir_list);
 
 	/* prevent checkpoint */
 	mutex_lock(&sbi->cp_mutex);
@@ -547,21 +566,22 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 
 	/* step #1: find fsynced inode numbers */
 	err = find_fsync_dnodes(sbi, &inode_list);
-	if (err)
+	if (err || list_empty(&inode_list))
 		goto out;
 
-	if (list_empty(&inode_list))
+	if (check_only) {
+		ret = 1;
 		goto out;
+	}
 
 	need_writecp = true;
 
 	/* step #2: recover data */
-	err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
+	err = recover_data(sbi, &inode_list, &dir_list);
 	if (!err)
 		f2fs_bug_on(sbi, !list_empty(&inode_list));
 out:
 	destroy_fsync_dnodes(&inode_list);
-	kmem_cache_destroy(fsync_entry_slab);
 
 	/* truncate meta pages to be used by the recovery */
 	truncate_inode_pages_range(META_MAPPING(sbi),
@@ -573,31 +593,20 @@ out:
 	}
 
 	clear_sbi_flag(sbi, SBI_POR_DOING);
-	if (err) {
-		bool invalidate = false;
-
-		if (discard_next_dnode(sbi, blkaddr))
-			invalidate = true;
-
-		/* Flush all the NAT/SIT pages */
-		while (get_pages(sbi, F2FS_DIRTY_META))
-			sync_meta_pages(sbi, META, LONG_MAX);
+	if (err)
+		set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
+	mutex_unlock(&sbi->cp_mutex);
 
-		/* invalidate temporary meta page */
-		if (invalidate)
-			invalidate_mapping_pages(META_MAPPING(sbi),
-							blkaddr, blkaddr);
+	/* let's drop all the directory inodes for clean checkpoint */
+	destroy_fsync_dnodes(&dir_list);
 
-		set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
-		mutex_unlock(&sbi->cp_mutex);
-	} else if (need_writecp) {
+	if (!err && need_writecp) {
 		struct cp_control cpc = {
 			.reason = CP_RECOVERY,
 		};
-		mutex_unlock(&sbi->cp_mutex);
 		write_checkpoint(sbi, &cpc);
-	} else {
-		mutex_unlock(&sbi->cp_mutex);
 	}
-	return err;
+
+	kmem_cache_destroy(fsync_entry_slab);
+	return ret ? ret: err;
 }
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 2bba0c4ef4b7..6802cd754eda 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -398,6 +398,9 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	init_waitqueue_head(&fcc->flush_wait_queue);
 	init_llist_head(&fcc->issue_list);
 	SM_I(sbi)->cmd_control_info = fcc;
+	if (!test_opt(sbi, FLUSH_MERGE))
+		return err;
+
 	fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
 				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(fcc->f2fs_issue_flush)) {
@@ -516,28 +519,6 @@ static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 	return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
 }
 
-bool discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
-{
-	int err = -ENOTSUPP;
-
-	if (test_opt(sbi, DISCARD)) {
-		struct seg_entry *se = get_seg_entry(sbi,
-				GET_SEGNO(sbi, blkaddr));
-		unsigned int offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
-
-		if (f2fs_test_bit(offset, se->discard_map))
-			return false;
-
-		err = f2fs_issue_discard(sbi, blkaddr, 1);
-	}
-
-	if (err) {
-		update_meta_page(sbi, NULL, blkaddr);
-		return true;
-	}
-	return false;
-}
-
 static void __add_discard_entry(struct f2fs_sb_info *sbi,
 		struct cp_control *cpc, struct seg_entry *se,
 		unsigned int start, unsigned int end)
@@ -771,7 +752,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
 	struct seg_entry *se;
 	bool is_cp = false;
 
-	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+	if (!is_valid_data_blkaddr(sbi, blkaddr))
 		return true;
 
 	mutex_lock(&sit_i->sentry_lock);
@@ -1485,7 +1466,7 @@ void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
 {
 	struct page *cpage;
 
-	if (blkaddr == NEW_ADDR)
+	if (!is_valid_data_blkaddr(sbi, blkaddr))
 		return;
 
 	f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
@@ -2120,7 +2101,7 @@ static int build_curseg(struct f2fs_sb_info *sbi)
 	return restore_curseg_summaries(sbi);
 }
 
-static void build_sit_entries(struct f2fs_sb_info *sbi)
+static int build_sit_entries(struct f2fs_sb_info *sbi)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
@@ -2129,6 +2110,7 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 	unsigned int i, start, end;
 	unsigned int readed, start_blk = 0;
 	int nrpages = MAX_BIO_BLOCKS(sbi);
+	int err = 0;
 
 	do {
 		readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
@@ -2142,36 +2124,62 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 			struct f2fs_sit_entry sit;
 			struct page *page;
 
-			mutex_lock(&curseg->curseg_mutex);
-			for (i = 0; i < sits_in_cursum(sum); i++) {
-				if (le32_to_cpu(segno_in_journal(sum, i))
-								== start) {
-					sit = sit_in_journal(sum, i);
-					mutex_unlock(&curseg->curseg_mutex);
-					goto got_it;
-				}
-			}
-			mutex_unlock(&curseg->curseg_mutex);
-
 			page = get_current_sit_page(sbi, start);
 			sit_blk = (struct f2fs_sit_block *)page_address(page);
 			sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
 			f2fs_put_page(page, 1);
-got_it:
-			check_block_count(sbi, start, &sit);
+
+			err = check_block_count(sbi, start, &sit);
+			if (err)
+				return err;
 			seg_info_from_raw_sit(se, &sit);
 
 			/* build discard map only one time */
 			memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
 			sbi->discard_blks += sbi->blocks_per_seg - se->valid_blocks;
 
-			if (sbi->segs_per_sec > 1) {
-				struct sec_entry *e = get_sec_entry(sbi, start);
-				e->valid_blocks += se->valid_blocks;
-			}
+			if (sbi->segs_per_sec > 1)
+				get_sec_entry(sbi, start)->valid_blocks +=
+							se->valid_blocks;
 		}
 		start_blk += readed;
 	} while (start_blk < sit_blk_cnt);
+
+	mutex_lock(&curseg->curseg_mutex);
+	for (i = 0; i < sits_in_cursum(sum); i++) {
+		struct f2fs_sit_entry sit;
+		struct seg_entry *se;
+		unsigned int old_valid_blocks;
+
+		start = le32_to_cpu(segno_in_journal(sum, i));
+		if (start >= MAIN_SEGS(sbi)) {
+			f2fs_msg(sbi->sb, KERN_ERR,
+					"Wrong journal entry on segno %u",
+					start);
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			err = -EINVAL;
+			break;
+		}
+
+		se = &sit_i->sentries[start];
+		sit = sit_in_journal(sum, i);
+
+		old_valid_blocks = se->valid_blocks;
+
+		err = check_block_count(sbi, start, &sit);
+		if (err)
+			break;
+		seg_info_from_raw_sit(se, &sit);
+
+		memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
+		sbi->discard_blks += old_valid_blocks - se->valid_blocks;
+
+		if (sbi->segs_per_sec > 1)
+			get_sec_entry(sbi, start)->valid_blocks +=
+				se->valid_blocks - old_valid_blocks;
+	}
+	mutex_unlock(&curseg->curseg_mutex);
+	return err;
 }
 
 static void init_free_segmap(struct f2fs_sb_info *sbi)
@@ -2316,7 +2324,7 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 
 	INIT_LIST_HEAD(&sm_info->sit_entry_set);
 
-	if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
+	if (!f2fs_readonly(sbi->sb)) {
 		err = create_flush_cmd_control(sbi);
 		if (err)
 			return err;
@@ -2333,7 +2341,9 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 		return err;
 
 	/* reinit free segmap based on SIT */
-	build_sit_entries(sbi);
+	err = build_sit_entries(sbi);
+	if (err)
+		return err;
 
 	init_free_segmap(sbi);
 	err = build_dirty_segmap(sbi);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index bfa1d31f79aa..08b08ae6ba9d 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -17,6 +17,8 @@
 
 #define DEF_RECLAIM_PREFREE_SEGMENTS	5	/* 5% over total segments */
 
+#define F2FS_MIN_SEGMENTS	9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
+
 /* L: Logical segment # in volume, R: Relative segment # in main area */
 #define GET_L2R_SEGNO(free_i, segno)	(segno - free_i->start_segno)
 #define GET_R2L_SEGNO(free_i, segno)	(segno + free_i->start_segno)
@@ -46,13 +48,19 @@
 	 (secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
 	  sbi->segs_per_sec))	\
 
-#define MAIN_BLKADDR(sbi)	(SM_I(sbi)->main_blkaddr)
-#define SEG0_BLKADDR(sbi)	(SM_I(sbi)->seg0_blkaddr)
+#define MAIN_BLKADDR(sbi)						\
+	(SM_I(sbi) ? SM_I(sbi)->main_blkaddr : 				\
+		le32_to_cpu(F2FS_RAW_SUPER(sbi)->main_blkaddr))
+#define SEG0_BLKADDR(sbi)						\
+	(SM_I(sbi) ? SM_I(sbi)->seg0_blkaddr : 				\
+		le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment0_blkaddr))
 
 #define MAIN_SEGS(sbi)	(SM_I(sbi)->main_segments)
 #define MAIN_SECS(sbi)	(sbi->total_sections)
 
-#define TOTAL_SEGS(sbi)	(SM_I(sbi)->segment_count)
+#define TOTAL_SEGS(sbi)							\
+	(SM_I(sbi) ? SM_I(sbi)->segment_count : 				\
+		le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count))
 #define TOTAL_BLKS(sbi)	(TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)
 
 #define MAX_BLKADDR(sbi)	(SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
@@ -72,7 +80,7 @@
 	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (sbi->blocks_per_seg - 1))
 
 #define GET_SEGNO(sbi, blk_addr)					\
-	(((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ?		\
+	((!is_valid_data_blkaddr(sbi, blk_addr)) ?			\
 	NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi),			\
 		GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
 #define GET_SECNO(sbi, segno)					\
@@ -574,16 +582,20 @@ static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
 	f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1);
 }
 
-static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
+static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr)
 {
-	f2fs_bug_on(sbi, blk_addr < SEG0_BLKADDR(sbi)
-					|| blk_addr >= MAX_BLKADDR(sbi));
+	struct f2fs_sb_info *sbi = fio->sbi;
+
+	if (__is_meta_io(fio))
+		verify_blkaddr(sbi, blk_addr, META_GENERIC);
+	else
+		verify_blkaddr(sbi, blk_addr, DATA_GENERIC);
 }
 
 /*
  * Summary block is always treated as an invalid block
  */
-static inline void check_block_count(struct f2fs_sb_info *sbi,
+static inline int check_block_count(struct f2fs_sb_info *sbi,
 		int segno, struct f2fs_sit_entry *raw_sit)
 {
 #ifdef CONFIG_F2FS_CHECK_FS
@@ -605,11 +617,25 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
 		cur_pos = next_pos;
 		is_valid = !is_valid;
 	} while (cur_pos < sbi->blocks_per_seg);
-	BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
+
+	if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+				"Mismatch valid blocks %d vs. %d",
+					GET_SIT_VBLOCKS(raw_sit), valid_blocks);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		return -EINVAL;
+	}
 #endif
 	/* check segment usage, and check boundary of a given segment number */
-	f2fs_bug_on(sbi, GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
-					|| segno > TOTAL_SEGS(sbi) - 1);
+	if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
+					|| segno > TOTAL_SEGS(sbi) - 1)) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+				"Wrong valid blocks %d or segno %u",
+					GET_SIT_VBLOCKS(raw_sit), segno);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		return -EINVAL;
+	}
+	return 0;
 }
 
 static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 2ffc53d0c9c7..dbd7adff8b5a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -994,6 +994,8 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
 static int sanity_check_raw_super(struct super_block *sb,
 			struct f2fs_super_block *raw_super)
 {
+	block_t segment_count, segs_per_sec, secs_per_zone;
+	block_t total_sections, blocks_per_seg;
 	unsigned int blocksize;
 
 	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
@@ -1047,6 +1049,68 @@ static int sanity_check_raw_super(struct super_block *sb,
 		return 1;
 	}
 
+	segment_count = le32_to_cpu(raw_super->segment_count);
+	segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
+	secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
+	total_sections = le32_to_cpu(raw_super->section_count);
+
+	/* blocks_per_seg should be 512, given the above check */
+	blocks_per_seg = 1 << le32_to_cpu(raw_super->log_blocks_per_seg);
+
+	if (segment_count > F2FS_MAX_SEGMENT ||
+				segment_count < F2FS_MIN_SEGMENTS) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid segment count (%u)",
+			segment_count);
+		return 1;
+	}
+
+	if (total_sections > segment_count ||
+			total_sections < F2FS_MIN_SEGMENTS ||
+			segs_per_sec > segment_count || !segs_per_sec) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid segment/section count (%u, %u x %u)",
+			segment_count, total_sections, segs_per_sec);
+		return 1;
+	}
+
+	if ((segment_count / segs_per_sec) < total_sections) {
+		f2fs_msg(sb, KERN_INFO,
+			"Small segment_count (%u < %u * %u)",
+			segment_count, segs_per_sec, total_sections);
+		return 1;
+	}
+
+	if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong segment_count / block_count (%u > %llu)",
+			segment_count, le64_to_cpu(raw_super->block_count));
+		return 1;
+	}
+
+	if (secs_per_zone > total_sections || !secs_per_zone) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong secs_per_zone / total_sections (%u, %u)",
+			secs_per_zone, total_sections);
+		return 1;
+	}
+	if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION) {
+		f2fs_msg(sb, KERN_INFO,
+			"Corrupted extension count (%u > %u)",
+			le32_to_cpu(raw_super->extension_count),
+			F2FS_MAX_EXTENSION);
+		return 1;
+	}
+
+	if (le32_to_cpu(raw_super->cp_payload) >
+				(blocks_per_seg - F2FS_CP_PACKS)) {
+		f2fs_msg(sb, KERN_INFO,
+			"Insane cp_payload (%u > %u)",
+			le32_to_cpu(raw_super->cp_payload),
+			blocks_per_seg - F2FS_CP_PACKS);
+		return 1;
+	}
+
 	/* check reserved ino info */
 	if (le32_to_cpu(raw_super->node_ino) != 1 ||
 		le32_to_cpu(raw_super->meta_ino) != 2 ||
@@ -1059,13 +1123,6 @@ static int sanity_check_raw_super(struct super_block *sb,
 		return 1;
 	}
 
-	if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) {
-		f2fs_msg(sb, KERN_INFO,
-			"Invalid segment count (%u)",
-			le32_to_cpu(raw_super->segment_count));
-		return 1;
-	}
-
 	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
 	if (sanity_check_area_boundary(sb, raw_super))
 		return 1;
@@ -1073,15 +1130,19 @@ static int sanity_check_raw_super(struct super_block *sb,
 	return 0;
 }
 
-static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
+int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 {
 	unsigned int total, fsmeta;
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	unsigned int ovp_segments, reserved_segments;
 	unsigned int main_segs, blocks_per_seg;
 	unsigned int sit_segs, nat_segs;
 	unsigned int sit_bitmap_size, nat_bitmap_size;
 	unsigned int log_blocks_per_seg;
+	unsigned int segment_count_main;
+	unsigned int cp_pack_start_sum, cp_payload;
+	block_t user_block_count;
 	int i;
 
 	total = le32_to_cpu(raw_super->segment_count);
@@ -1096,6 +1157,26 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	if (unlikely(fsmeta >= total))
 		return 1;
 
+	ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
+	reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
+
+	if (unlikely(fsmeta < F2FS_MIN_SEGMENTS ||
+			ovp_segments == 0 || reserved_segments == 0)) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"Wrong layout: check mkfs.f2fs version");
+		return 1;
+	}
+
+	user_block_count = le64_to_cpu(ckpt->user_block_count);
+	segment_count_main = le32_to_cpu(raw_super->segment_count_main);
+	log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+	if (!user_block_count || user_block_count >=
+			segment_count_main << log_blocks_per_seg) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"Wrong user_block_count: %u", user_block_count);
+		return 1;
+	}
+
 	main_segs = le32_to_cpu(raw_super->segment_count_main);
 	blocks_per_seg = sbi->blocks_per_seg;
 
@@ -1112,7 +1193,6 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 
 	sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);
 	nat_bitmap_size = le32_to_cpu(ckpt->nat_ver_bitmap_bytesize);
-	log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
 
 	if (sit_bitmap_size != ((sit_segs / 2) << log_blocks_per_seg) / 8 ||
 		nat_bitmap_size != ((nat_segs / 2) << log_blocks_per_seg) / 8) {
@@ -1122,6 +1202,17 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 		return 1;
 	}
 
+	cp_pack_start_sum = __start_sum_addr(sbi);
+	cp_payload = __cp_payload(sbi);
+	if (cp_pack_start_sum < cp_payload + 1 ||
+		cp_pack_start_sum > blocks_per_seg - 1 -
+			NR_CURSEG_TYPE) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"Wrong cp_pack_start_sum: %u",
+			cp_pack_start_sum);
+		return 1;
+	}
+
 	if (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
 		return 1;
@@ -1358,13 +1449,6 @@ try_onemore:
 		goto free_meta_inode;
 	}
 
-	/* sanity checking of checkpoint */
-	err = -EINVAL;
-	if (sanity_check_ckpt(sbi)) {
-		f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
-		goto free_cp;
-	}
-
 	sbi->total_valid_node_count =
 				le32_to_cpu(sbi->ckpt->valid_node_count);
 	sbi->total_valid_inode_count =
@@ -1464,14 +1548,27 @@ try_onemore:
 		if (need_fsck)
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
 
-		err = recover_fsync_data(sbi);
-		if (err) {
+		if (!retry)
+			goto skip_recovery;
+
+		err = recover_fsync_data(sbi, false);
+		if (err < 0) {
 			need_fsck = true;
 			f2fs_msg(sb, KERN_ERR,
 				"Cannot recover all fsync data errno=%ld", err);
 			goto free_kobj;
 		}
+	} else {
+		err = recover_fsync_data(sbi, true);
+
+		if (!f2fs_readonly(sb) && err > 0) {
+			err = -EINVAL;
+			f2fs_msg(sb, KERN_ERR,
+				"Need to recover fsync data");
+			goto free_kobj;
+		}
 	}
+skip_recovery:
 	/* recover_fsync_data() cleared this already */
 	clear_sbi_flag(sbi, SBI_POR_DOING);
 
@@ -1517,7 +1614,6 @@ free_nm:
 	destroy_node_manager(sbi);
 free_sm:
 	destroy_segment_manager(sbi);
-free_cp:
 	kfree(sbi->ckpt);
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 7a182c87f378..ab1d7f35f6c2 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -715,6 +715,9 @@ static const struct fscache_state *fscache_drop_object(struct fscache_object *ob
 
 	if (awaken)
 		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
+	if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+
 
 	/* Prevent a race with our last child, which has to signal EV_CLEARED
 	 * before dropping our spinlock.
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index e566652ac922..341196338e48 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1741,7 +1741,6 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
 	req->in.h.nodeid = outarg->nodeid;
 	req->in.numargs = 2;
 	req->in.argpages = 1;
-	req->page_descs[0].offset = offset;
 	req->end = fuse_retrieve_end;
 
 	index = outarg->offset >> PAGE_CACHE_SHIFT;
@@ -1756,6 +1755,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
 
 		this_num = min_t(unsigned, num, PAGE_CACHE_SIZE - offset);
 		req->pages[req->num_pages] = page;
+		req->page_descs[req->num_pages].offset = offset;
 		req->page_descs[req->num_pages].length = this_num;
 		req->num_pages++;
 
@@ -2074,10 +2074,13 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 
 	ret = fuse_dev_do_write(fud, &cs, len);
 
+	pipe_lock(pipe);
 	for (idx = 0; idx < nbuf; idx++) {
 		struct pipe_buffer *buf = &bufs[idx];
 		buf->ops->release(pipe, buf);
 	}
+	pipe_unlock(pipe);
+
 out:
 	kfree(bufs);
 	return ret;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 7014318f6d18..d40c2451487c 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1784,7 +1784,7 @@ 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_zone_page_state(new_req->pages[0], NR_WRITEBACK_TEMP);
 		wb_writeout_inc(&bdi->wb);
 		fuse_writepage_free(fc, new_req);
 		fuse_request_free(new_req);
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 1ab19e660e69..1ff5774a5382 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -328,13 +328,14 @@ void hfs_bmap_free(struct hfs_bnode *node)
 
 		nidx -= len * 8;
 		i = node->next;
-		hfs_bnode_put(node);
 		if (!i) {
 			/* panic */;
 			pr_crit("unable to free bnode %u. bmap not found!\n",
 				node->this);
+			hfs_bnode_put(node);
 			return;
 		}
+		hfs_bnode_put(node);
 		node = hfs_bnode_find(tree, i);
 		if (IS_ERR(node))
 			return;
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index 3345c7553edc..7adc8a327e03 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -453,14 +453,15 @@ void hfs_bmap_free(struct hfs_bnode *node)
 
 		nidx -= len * 8;
 		i = node->next;
-		hfs_bnode_put(node);
 		if (!i) {
 			/* panic */;
 			pr_crit("unable to free bnode %u. "
 					"bmap not found!\n",
 				node->this);
+			hfs_bnode_put(node);
 			return;
 		}
+		hfs_bnode_put(node);
 		node = hfs_bnode_find(tree, i);
 		if (IS_ERR(node))
 			return;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a17da8b57fc6..cefae2350da5 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -118,6 +118,16 @@ static void huge_pagevec_release(struct pagevec *pvec)
 	pagevec_reinit(pvec);
 }
 
+/*
+ * Mask used when checking the page offset value passed in via system
+ * calls.  This value will be converted to a loff_t which is signed.
+ * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the
+ * value.  The extra bit (- 1 in the shift value) is to take the sign
+ * bit into account.
+ */
+#define PGOFF_LOFFT_MAX \
+	(((1UL << (PAGE_SHIFT + 1)) - 1) <<  (BITS_PER_LONG - (PAGE_SHIFT + 1)))
+
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file_inode(file);
@@ -136,17 +146,31 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
 	vma->vm_ops = &hugetlb_vm_ops;
 
+	/*
+	 * page based offset in vm_pgoff could be sufficiently large to
+	 * overflow a loff_t when converted to byte offset.  This can
+	 * only happen on architectures where sizeof(loff_t) ==
+	 * sizeof(unsigned long).  So, only check in those instances.
+	 */
+	if (sizeof(unsigned long) == sizeof(loff_t)) {
+		if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
+			return -EINVAL;
+	}
+
+	/* must be huge page aligned */
 	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
 		return -EINVAL;
 
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
+	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	/* check for overflow */
+	if (len < vma_len)
+		return -EINVAL;
 
 	mutex_lock(&inode->i_mutex);
 	file_accessed(file);
 
 	ret = -ENOMEM;
-	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-
 	if (hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
@@ -155,7 +179,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ret = 0;
 	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
-		inode->i_size = len;
+		i_size_write(inode, len);
 out:
 	mutex_unlock(&inode->i_mutex);
 
@@ -845,6 +869,18 @@ static int hugetlbfs_migrate_page(struct address_space *mapping,
 	rc = migrate_huge_page_move_mapping(mapping, newpage, page);
 	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
+
+	/*
+	 * page_private is subpool pointer in hugetlb pages.  Transfer to
+	 * new page.  PagePrivate is not associated with page_private for
+	 * hugetlb pages and can not be set here as only page_huge_active
+	 * pages can be migrated.
+	 */
+	if (page_private(page)) {
+		set_page_private(newpage, page_private(page));
+		set_page_private(page, 0);
+	}
+
 	migrate_page_copy(newpage, page);
 
 	return MIGRATEPAGE_SUCCESS;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index bce343febb9e..c34433432d47 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1215,11 +1215,12 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 	struct journal_head *jh;
 	char *committed_data = NULL;
 
-	JBUFFER_TRACE(jh, "entry");
 	if (jbd2_write_access_granted(handle, bh, true))
 		return 0;
 
 	jh = jbd2_journal_add_journal_head(bh);
+	JBUFFER_TRACE(jh, "entry");
+
 	/*
 	 * Do this first --- it can drop the journal lock, so we want to
 	 * make sure that obtaining the committed_data is done
@@ -1336,15 +1337,17 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 
 	if (is_handle_aborted(handle))
 		return -EROFS;
-	if (!buffer_jbd(bh)) {
-		ret = -EUCLEAN;
-		goto out;
-	}
+	if (!buffer_jbd(bh))
+		return -EUCLEAN;
+
 	/*
 	 * We don't grab jh reference here since the buffer must be part
 	 * of the running transaction.
 	 */
 	jh = bh2jh(bh);
+	jbd_debug(5, "journal_head %p\n", jh);
+	JBUFFER_TRACE(jh, "entry");
+
 	/*
 	 * This and the following assertions are unreliable since we may see jh
 	 * in inconsistent state unless we grab bh_state lock. But this is
@@ -1378,9 +1381,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	}
 
 	journal = transaction->t_journal;
-	jbd_debug(5, "journal_head %p\n", jh);
-	JBUFFER_TRACE(jh, "entry");
-
 	jbd_lock_bh_state(bh);
 
 	if (jh->b_modified == 0) {
@@ -1578,14 +1578,21 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 		/* However, if the buffer is still owned by a prior
 		 * (committing) transaction, we can't drop it yet... */
 		JBUFFER_TRACE(jh, "belongs to older transaction");
-		/* ... but we CAN drop it from the new transaction if we
-		 * have also modified it since the original commit. */
+		/* ... but we CAN drop it from the new transaction through
+		 * marking the buffer as freed and set j_next_transaction to
+		 * the new transaction, so that not only the commit code
+		 * knows it should clear dirty bits when it is done with the
+		 * buffer, but also the buffer can be checkpointed only
+		 * after the new transaction commits. */
 
-		if (jh->b_next_transaction) {
-			J_ASSERT(jh->b_next_transaction == transaction);
+		set_buffer_freed(bh);
+
+		if (!jh->b_next_transaction) {
 			spin_lock(&journal->j_list_lock);
-			jh->b_next_transaction = NULL;
+			jh->b_next_transaction = transaction;
 			spin_unlock(&journal->j_list_lock);
+		} else {
+			J_ASSERT(jh->b_next_transaction == transaction);
 
 			/*
 			 * only drop a reference if this transaction modified
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 1544f530ccd0..023e7f32ee1b 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -101,7 +101,8 @@ static int jffs2_sync_fs(struct super_block *sb, int wait)
 	struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
 
 #ifdef CONFIG_JFFS2_FS_WRITEBUFFER
-	cancel_delayed_work_sync(&c->wbuf_dwork);
+	if (jffs2_is_writebuffered(c))
+		cancel_delayed_work_sync(&c->wbuf_dwork);
 #endif
 
 	mutex_lock(&c->alloc_sem);
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 0a3f9b594602..37779ed3f790 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -233,7 +233,7 @@ ncp_get_charsets(struct ncp_server* server, struct ncp_nls_ioctl __user *arg)
 		len = strlen(server->nls_vol->charset);
 		if (len > NCP_IOCSNAME_LEN)
 			len = NCP_IOCSNAME_LEN;
-		strncpy(user.codepage, server->nls_vol->charset, len);
+		strscpy(user.codepage, server->nls_vol->charset, NCP_IOCSNAME_LEN);
 		user.codepage[len] = 0;
 	}
 
@@ -243,7 +243,7 @@ ncp_get_charsets(struct ncp_server* server, struct ncp_nls_ioctl __user *arg)
 		len = strlen(server->nls_io->charset);
 		if (len > NCP_IOCSNAME_LEN)
 			len = NCP_IOCSNAME_LEN;
-		strncpy(user.iocharset,	server->nls_io->charset, len);
+		strscpy(user.iocharset,	server->nls_io->charset, NCP_IOCSNAME_LEN);
 		user.iocharset[len] = 0;
 	}
 	mutex_unlock(&server->root_setup_lock);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 211440722e24..88cb8e0d6014 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -670,6 +670,10 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 
 	req = nfs_list_entry(reqs.next);
 	nfs_direct_setup_mirroring(dreq, &desc, req);
+	if (desc.pg_error < 0) {
+		list_splice_init(&reqs, &failed);
+		goto out_failed;
+	}
 
 	list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
 		if (!nfs_pageio_add_request(&desc, req)) {
@@ -677,13 +681,17 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 			nfs_list_add_request(req, &failed);
 			spin_lock(cinfo.lock);
 			dreq->flags = 0;
-			dreq->error = -EIO;
+			if (desc.pg_error < 0)
+				dreq->error = desc.pg_error;
+			else
+				dreq->error = -EIO;
 			spin_unlock(cinfo.lock);
 		}
 		nfs_release_request(req);
 	}
 	nfs_pageio_complete(&desc);
 
+out_failed:
 	while (!list_empty(&failed)) {
 		req = nfs_list_entry(failed.next);
 		nfs_list_remove_request(req);
@@ -898,6 +906,11 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 			}
 
 			nfs_direct_setup_mirroring(dreq, &desc, req);
+			if (desc.pg_error < 0) {
+				nfs_free_request(req);
+				result = desc.pg_error;
+				break;
+			}
 
 			nfs_lock_request(req);
 			req->wb_index = pos >> PAGE_SHIFT;
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index fd8da630fd22..8e268965c96d 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -882,13 +882,19 @@ static void
 filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			struct nfs_page *req)
 {
-	if (!pgio->pg_lseg)
+	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   0,
 					   NFS4_MAX_UINT64,
 					   IOMODE_READ,
 					   GFP_KERNEL);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
 	/* If no lseg, fall back to read through mds */
 	if (pgio->pg_lseg == NULL)
 		nfs_pageio_reset_read_mds(pgio);
@@ -901,13 +907,20 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	struct nfs_commit_info cinfo;
 	int status;
 
-	if (!pgio->pg_lseg)
+	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   0,
 					   NFS4_MAX_UINT64,
 					   IOMODE_RW,
 					   GFP_NOFS);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
+
 	/* If no lseg, fall back to write through mds */
 	if (pgio->pg_lseg == NULL)
 		goto out_mds;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index c8e90152b61b..6506775575aa 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -786,13 +786,19 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	int ds_idx;
 
 	/* Use full layout for now */
-	if (!pgio->pg_lseg)
+	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
 						   0,
 						   NFS4_MAX_UINT64,
 						   IOMODE_READ,
 						   GFP_KERNEL);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
 	/* If no lseg, fall back to read through mds */
 	if (pgio->pg_lseg == NULL)
 		goto out_mds;
@@ -826,13 +832,19 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	int i;
 	int status;
 
-	if (!pgio->pg_lseg)
+	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
 						   0,
 						   NFS4_MAX_UINT64,
 						   IOMODE_RW,
 						   GFP_NOFS);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
 	/* If no lseg, fall back to write through mds */
 	if (pgio->pg_lseg == NULL)
 		goto out_mds;
@@ -868,18 +880,25 @@ static unsigned int
 ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
 				    struct nfs_page *req)
 {
-	if (!pgio->pg_lseg)
+	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
 						   0,
 						   NFS4_MAX_UINT64,
 						   IOMODE_RW,
 						   GFP_NOFS);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			goto out;
+		}
+	}
 	if (pgio->pg_lseg)
 		return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg);
 
 	/* no lseg means that pnfs is not in use, so no mirroring here */
 	nfs_pageio_reset_write_mds(pgio);
+out:
 	return 1;
 }
 
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 4bdc2fc86280..8a2077408ab0 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -872,6 +872,9 @@ static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio,
 
 	mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req);
 
+	if (pgio->pg_error < 0)
+		return pgio->pg_error;
+
 	if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX)
 		return -EINVAL;
 
@@ -980,6 +983,8 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
 	} else {
 		if (desc->pg_ops->pg_init)
 			desc->pg_ops->pg_init(desc, req);
+		if (desc->pg_error < 0)
+			return 0;
 		mirror->pg_base = req->wb_pgbase;
 	}
 	if (!nfs_can_coalesce_requests(prev, req, desc))
@@ -1102,7 +1107,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
 			struct nfs_page *req;
 
 			req = list_first_entry(&head, struct nfs_page, wb_list);
-			nfs_list_remove_request(req);
 			if (__nfs_pageio_add_request(desc, req))
 				continue;
 			if (desc->pg_error < 0) {
@@ -1145,6 +1149,8 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 	bytes = req->wb_bytes;
 
 	nfs_pageio_setup_mirroring(desc, req);
+	if (desc->pg_error < 0)
+		return 0;
 
 	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
 		if (midx) {
@@ -1196,7 +1202,7 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc,
 		desc->pg_mirror_idx = mirror_idx;
 	for (;;) {
 		nfs_pageio_doio(desc);
-		if (!mirror->pg_recoalesce)
+		if (desc->pg_error < 0 || !mirror->pg_recoalesce)
 			break;
 		if (!nfs_do_recoalesce(desc))
 			break;
@@ -1230,7 +1236,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
 	nfs_pageio_complete(desc);
 	if (!list_empty(&failed)) {
 		list_move(&failed, &hdr->pages);
-		return -EIO;
+		return desc->pg_error < 0 ? desc->pg_error : -EIO;
 	}
 	return 0;
 }
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index c8e75e5e6a67..d34fb0feb5c2 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -909,14 +909,15 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 
 	if (IS_ERR(lseg)) {
 		switch (PTR_ERR(lseg)) {
-		case -ENOMEM:
 		case -ERESTARTSYS:
+		case -EIO:
+		case -ENOSPC:
+		case -EROFS:
+		case -E2BIG:
 			break;
 		default:
-			/* remember that LAYOUTGET failed and suspend trying */
-			pnfs_layout_io_set_failed(lo, range->iomode);
+			return NULL;
 		}
-		return NULL;
 	} else
 		pnfs_layout_clear_fail_bit(lo,
 				pnfs_iomode_to_fail_bit(range->iomode));
@@ -1625,7 +1626,7 @@ out:
 			"(%s, offset: %llu, length: %llu)\n",
 			__func__, ino->i_sb->s_id,
 			(unsigned long long)NFS_FILEID(ino),
-			lseg == NULL ? "not found" : "found",
+			IS_ERR_OR_NULL(lseg) ? "not found" : "found",
 			iomode==IOMODE_RW ?  "read/write" : "read-only",
 			(unsigned long long)pos,
 			(unsigned long long)count);
@@ -1804,6 +1805,11 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 						   rd_size,
 						   IOMODE_READ,
 						   GFP_KERNEL);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
 	}
 	/* If no lseg, fall back to read through mds */
 	if (pgio->pg_lseg == NULL)
@@ -1816,13 +1822,19 @@ void
 pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			   struct nfs_page *req, u64 wb_size)
 {
-	if (pgio->pg_lseg == NULL)
+	if (pgio->pg_lseg == NULL) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
 						   req_offset(req),
 						   wb_size,
 						   IOMODE_RW,
 						   GFP_NOFS);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
 	/* If no lseg, fall back to write through mds */
 	if (pgio->pg_lseg == NULL)
 		nfs_pageio_reset_write_mds(pgio);
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 0a5e33f33b5c..0bb580174cb3 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -115,7 +115,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 	pgm = &pgio.pg_mirrors[0];
 	NFS_I(inode)->read_io += pgm->pg_bytes_written;
 
-	return 0;
+	return pgio.pg_error < 0 ? pgio.pg_error : 0;
 }
 
 static void nfs_readpage_release(struct nfs_page *req)
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 62f358f67764..9b42139a479b 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1877,6 +1877,11 @@ static int nfs_parse_devname(const char *dev_name,
 	size_t len;
 	char *end;
 
+	if (unlikely(!dev_name || !*dev_name)) {
+		dfprintk(MOUNT, "NFS: device name not specified\n");
+		return -EINVAL;
+	}
+
 	/* Is the host name protected with square brakcets? */
 	if (*dev_name == '[') {
 		end = strchr(++dev_name, ']');
@@ -2376,8 +2381,7 @@ static int nfs_compare_mount_options(const struct super_block *s, const struct n
 		goto Ebusy;
 	if (a->acdirmax != b->acdirmax)
 		goto Ebusy;
-	if (b->auth_info.flavor_len > 0 &&
-	   clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor)
+	if (clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor)
 		goto Ebusy;
 	return 1;
 Ebusy:
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 7b755b7f785c..91146f025769 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -430,8 +430,19 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
 					&resp->common, nfs3svc_encode_entry);
 	memcpy(resp->verf, argp->verf, 8);
 	resp->count = resp->buffer - argp->buffer;
-	if (resp->offset)
-		xdr_encode_hyper(resp->offset, argp->cookie);
+	if (resp->offset) {
+		loff_t offset = argp->cookie;
+
+		if (unlikely(resp->offset1)) {
+			/* we ended up with offset on a page boundary */
+			*resp->offset = htonl(offset >> 32);
+			*resp->offset1 = htonl(offset & 0xffffffff);
+			resp->offset1 = NULL;
+		} else {
+			xdr_encode_hyper(resp->offset, offset);
+		}
+		resp->offset = NULL;
+	}
 
 	RETURN_STATUS(nfserr);
 }
@@ -499,6 +510,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
 		} else {
 			xdr_encode_hyper(resp->offset, offset);
 		}
+		resp->offset = NULL;
 	}
 
 	RETURN_STATUS(nfserr);
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 7162ab7bc093..d4fa7fbc37dc 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -898,6 +898,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 		} else {
 			xdr_encode_hyper(cd->offset, offset64);
 		}
+		cd->offset = NULL;
 	}
 
 	/*
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 9690cb4dd588..0cd57db5c5af 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1106,6 +1106,8 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size)
 		case 'Y':
 		case 'y':
 		case '1':
+			if (!nn->nfsd_serv)
+				return -EBUSY;
 			nfsd4_end_grace(nn);
 			break;
 		default:
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 272269f1c310..9ee8bcfbf00f 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -146,7 +146,6 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 			BUG();
 		}
 
-		clear_buffer_uptodate(bh);
 		get_bh(bh); /* for end_buffer_read_sync() */
 		bh->b_end_io = end_buffer_read_sync;
 		submit_bh(READ, bh);
@@ -300,7 +299,6 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 				continue;
 			}
 
-			clear_buffer_uptodate(bh);
 			get_bh(bh); /* for end_buffer_read_sync() */
 			if (validate)
 				set_buffer_needs_validate(bh);
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 827fc9809bc2..3494e220b510 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -125,10 +125,10 @@ check_err:
 
 check_gen:
 	if (handle->ih_generation != inode->i_generation) {
-		iput(inode);
 		trace_ocfs2_get_dentry_generation((unsigned long long)blkno,
 						  handle->ih_generation,
 						  inode->i_generation);
+		iput(inode);
 		result = ERR_PTR(-ESTALE);
 		goto bail;
 	}
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 0a4457fb0711..85111d740c9d 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -345,13 +345,18 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb)
 	if (num_used
 	    || alloc->id1.bitmap1.i_used
 	    || alloc->id1.bitmap1.i_total
-	    || la->la_bm_off)
-		mlog(ML_ERROR, "Local alloc hasn't been recovered!\n"
+	    || la->la_bm_off) {
+		mlog(ML_ERROR, "inconsistent detected, clean journal with"
+		     " unrecovered local alloc, please run fsck.ocfs2!\n"
 		     "found = %u, set = %u, taken = %u, off = %u\n",
 		     num_used, le32_to_cpu(alloc->id1.bitmap1.i_used),
 		     le32_to_cpu(alloc->id1.bitmap1.i_total),
 		     OCFS2_LOCAL_ALLOC(alloc)->la_bm_off);
 
+		status = -EINVAL;
+		goto bail;
+	}
+
 	osb->local_alloc_bh = alloc_bh;
 	osb->local_alloc_state = OCFS2_LA_ENABLED;
 
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 124471d26a73..c1a83c58456e 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -156,18 +156,14 @@ out:
 }
 
 /*
- * lock allocators, and reserving appropriate number of bits for
- * meta blocks and data clusters.
- *
- * in some cases, we don't need to reserve clusters, just let data_ac
- * be NULL.
+ * lock allocator, and reserve appropriate number of bits for
+ * meta blocks.
  */
-static int ocfs2_lock_allocators_move_extents(struct inode *inode,
+static int ocfs2_lock_meta_allocator_move_extents(struct inode *inode,
 					struct ocfs2_extent_tree *et,
 					u32 clusters_to_move,
 					u32 extents_to_split,
 					struct ocfs2_alloc_context **meta_ac,
-					struct ocfs2_alloc_context **data_ac,
 					int extra_blocks,
 					int *credits)
 {
@@ -192,13 +188,6 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode,
 		goto out;
 	}
 
-	if (data_ac) {
-		ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
-		if (ret) {
-			mlog_errno(ret);
-			goto out;
-		}
-	}
 
 	*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el);
 
@@ -260,10 +249,10 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
 		}
 	}
 
-	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, *len, 1,
-						 &context->meta_ac,
-						 &context->data_ac,
-						 extra_blocks, &credits);
+	ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
+						*len, 1,
+						&context->meta_ac,
+						extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
@@ -286,6 +275,21 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
 		}
 	}
 
+	/*
+	 * Make sure ocfs2_reserve_cluster is called after
+	 * __ocfs2_flush_truncate_log, otherwise, dead lock may happen.
+	 *
+	 * If ocfs2_reserve_cluster is called
+	 * before __ocfs2_flush_truncate_log, dead lock on global bitmap
+	 * may happen.
+	 *
+	 */
+	ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_unlock_mutex;
+	}
+
 	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
@@ -606,9 +610,10 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
 		}
 	}
 
-	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
-						 &context->meta_ac,
-						 NULL, extra_blocks, &credits);
+	ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
+						len, 1,
+						&context->meta_ac,
+						extra_blocks, &credits);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index cb71cbae606d..60cbaa821164 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -333,7 +333,7 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
 #ifdef CONFIG_SECCOMP
 	seq_printf(m, "Seccomp:\t%d\n", p->seccomp.mode);
 #endif
-	seq_printf(m, "\nSpeculation_Store_Bypass:\t");
+	seq_printf(m, "Speculation_Store_Bypass:\t");
 	switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
 	case -EINVAL:
 		seq_printf(m, "unknown");
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4beed301e224..bd8c26a409a7 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -254,7 +254,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 	 * Inherently racy -- command line shares address space
 	 * with code and data.
 	 */
-	rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
+	rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON);
 	if (rv <= 0)
 		goto out_free_page;
 
@@ -272,7 +272,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 			int nr_read;
 
 			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count, 0);
+			nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
 			if (nr_read < 0)
 				rv = nr_read;
 			if (nr_read <= 0)
@@ -307,7 +307,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 			bool final;
 
 			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count, 0);
+			nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
 			if (nr_read < 0)
 				rv = nr_read;
 			if (nr_read <= 0)
@@ -356,7 +356,7 @@ skip_argv:
 			bool final;
 
 			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count, 0);
+			nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
 			if (nr_read < 0)
 				rv = nr_read;
 			if (nr_read <= 0)
@@ -868,6 +868,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
 	unsigned long addr = *ppos;
 	ssize_t copied;
 	char *page;
+	unsigned int flags;
 
 	if (!mm)
 		return 0;
@@ -880,6 +881,11 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
 	if (!atomic_inc_not_zero(&mm->mm_users))
 		goto free;
 
+	/* Maybe we should limit FOLL_FORCE to actual ptrace users? */
+	flags = FOLL_FORCE;
+	if (write)
+		flags |= FOLL_WRITE;
+
 	while (count > 0) {
 		int this_len = min_t(int, count, PAGE_SIZE);
 
@@ -888,7 +894,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
 			break;
 		}
 
-		this_len = access_remote_vm(mm, addr, page, this_len, write);
+		this_len = access_remote_vm(mm, addr, page, this_len, flags);
 		if (!this_len) {
 			if (!copied)
 				copied = -EIO;
@@ -1000,8 +1006,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 		max_len = min_t(size_t, PAGE_SIZE, count);
 		this_len = min(max_len, this_len);
 
-		retval = access_remote_vm(mm, (env_start + src),
-			page, this_len, 0);
+		retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON);
 
 		if (retval <= 0) {
 			ret = retval;
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 588461bb2dd4..e97e7d74e134 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -392,8 +392,8 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
 		} else {
 			spin_lock_irqsave(&psinfo->buf_lock, flags);
 		}
-		memcpy(psinfo->buf, s, c);
-		psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, 0, 0, c, psinfo);
+		psinfo->write_buf(PSTORE_TYPE_CONSOLE, 0, &id, 0,
+				  s, 0, c, psinfo);
 		spin_unlock_irqrestore(&psinfo->buf_lock, flags);
 		s += c;
 		c = e - s;
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index bd21795ce657..679d75a864d0 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -445,6 +445,11 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig,
 	sig ^= PERSISTENT_RAM_SIG;
 
 	if (prz->buffer->sig == sig) {
+		if (buffer_size(prz) == 0) {
+			pr_debug("found existing empty buffer\n");
+			return 0;
+		}
+
 		if (buffer_size(prz) > prz->buffer_size ||
 		    buffer_start(prz) > buffer_size(prz))
 			pr_info("found existing invalid buffer, size %zu, start %zu\n",
diff --git a/fs/read_write.c b/fs/read_write.c
index bfd1a5dddf6e..16e554ba885d 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -363,8 +363,10 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
 	iter->type |= WRITE;
 	ret = file->f_op->write_iter(&kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
-	if (ret > 0)
+	if (ret > 0) {
 		*ppos = kiocb.ki_pos;
+		fsnotify_modify(file);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(vfs_iter_write);
diff --git a/fs/super.c b/fs/super.c
index 09b526a50986..b9cd7982f6e2 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -118,13 +118,23 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 	sb = container_of(shrink, struct super_block, s_shrink);
 
 	/*
-	 * Don't call trylock_super as it is a potential
-	 * scalability bottleneck. The counts could get updated
-	 * between super_cache_count and super_cache_scan anyway.
-	 * Call to super_cache_count with shrinker_rwsem held
-	 * ensures the safety of call to list_lru_shrink_count() and
-	 * s_op->nr_cached_objects().
+	 * We don't call trylock_super() here as it is a scalability bottleneck,
+	 * so we're exposed to partial setup state. The shrinker rwsem does not
+	 * protect filesystem operations backing list_lru_shrink_count() or
+	 * s_op->nr_cached_objects(). Counts can change between
+	 * super_cache_count and super_cache_scan, so we really don't need locks
+	 * here.
+	 *
+	 * However, if we are currently mounting the superblock, the underlying
+	 * filesystem might be in a state of partial construction and hence it
+	 * is dangerous to access it.  trylock_super() uses a MS_BORN check to
+	 * avoid this situation, so do the same here. The memory barrier is
+	 * matched with the one in mount_fs() as we don't hold locks here.
 	 */
+	if (!(sb->s_flags & MS_BORN))
+		return 0;
+	smp_rmb();
+
 	if (sb->s_op && sb->s_op->nr_cached_objects)
 		total_objects = sb->s_op->nr_cached_objects(sb, sc);
 
@@ -1133,6 +1143,14 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
 	sb = root->d_sb;
 	BUG_ON(!sb);
 	WARN_ON(!sb->s_bdi);
+
+	/*
+	 * Write barrier is for super_cache_count(). We place it before setting
+	 * MS_BORN as the data dependency between the two functions is the
+	 * superblock structure contents that we just set up, not the MS_BORN
+	 * flag.
+	 */
+	smp_wmb();
 	sb->s_flags |= MS_BORN;
 
 	error = security_sb_kern_mount(sb, flags, secdata);
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 02fa1dcc5969..29f5b2e589a1 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -275,7 +275,7 @@ static int __sysv_write_inode(struct inode *inode, int wait)
                 }
         }
 	brelse(bh);
-	return 0;
+	return err;
 }
 
 int sysv_write_inode(struct inode *inode, struct writeback_control *wbc)
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 0e659d9c69a1..613193c6bb42 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1364,6 +1364,12 @@ reread:
 
 	iinfo->i_alloc_type = le16_to_cpu(fe->icbTag.flags) &
 							ICBTAG_FLAG_AD_MASK;
+	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_SHORT &&
+	    iinfo->i_alloc_type != ICBTAG_FLAG_AD_LONG &&
+	    iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
+		ret = -EIO;
+		goto out;
+	}
 	iinfo->i_unique = 0;
 	iinfo->i_lenEAttr = 0;
 	iinfo->i_lenExtents = 0;
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index fb9636cc927c..5d8d12746e6e 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -528,7 +528,14 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
 		if (args->flags & ATTR_CREATE)
 			return retval;
 		retval = xfs_attr_shortform_remove(args);
-		ASSERT(retval == 0);
+		if (retval)
+			return retval;
+		/*
+		 * Since we have removed the old attr, clear ATTR_REPLACE so
+		 * that the leaf format add routine won't trip over the attr
+		 * not being around.
+		 */
+		args->flags &= ~ATTR_REPLACE;
 	}
 
 	if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||