Merge branch 'sched/urgent' into sched/core, to pick up fixes before applying new patches

Signed-off-by: Ingo Molnar <mingo@kernel.org>

407 files changed, 16333 insertions, 7355 deletions

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 6894b085f0ee..620d93489539 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -335,7 +335,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	}
 	init_rwsem(&v9ses->rename_sem);
 
-	rc = bdi_setup_and_register(&v9ses->bdi, "9p", BDI_CAP_MAP_COPY);
+	rc = bdi_setup_and_register(&v9ses->bdi, "9p");
 	if (rc) {
 		kfree(v9ses->aname);
 		kfree(v9ses->uname);
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 5594505e6e73..b40133796b87 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -831,7 +831,6 @@ static const struct vm_operations_struct v9fs_file_vm_ops = {
 	.fault = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = v9fs_vm_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
@@ -839,7 +838,6 @@ static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
 	.fault = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = v9fs_vm_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 9ee5343d4884..3662f1d1d9cf 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1127,7 +1127,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
 	}
 
 	/* Write all dirty data */
-	if (S_ISREG(dentry->d_inode->i_mode))
+	if (d_is_reg(dentry))
 		filemap_write_and_wait(dentry->d_inode->i_mapping);
 
 	retval = p9_client_wstat(fid, &wstat);
diff --git a/fs/Kconfig b/fs/Kconfig
index a6bb530b1ec5..ec35851e5b71 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -13,13 +13,6 @@ if BLOCK
 source "fs/ext2/Kconfig"
 source "fs/ext3/Kconfig"
 source "fs/ext4/Kconfig"
-
-config FS_XIP
-# execute in place
-	bool
-	depends on EXT2_FS_XIP
-	default y
-
 source "fs/jbd/Kconfig"
 source "fs/jbd2/Kconfig"
 
@@ -40,6 +33,21 @@ source "fs/ocfs2/Kconfig"
 source "fs/btrfs/Kconfig"
 source "fs/nilfs2/Kconfig"
 
+config FS_DAX
+	bool "Direct Access (DAX) support"
+	depends on MMU
+	depends on !(ARM || MIPS || SPARC)
+	help
+	  Direct Access (DAX) can be used on memory-backed block devices.
+	  If the block device supports DAX and the filesystem supports DAX,
+	  then you can avoid using the pagecache to buffer I/Os.  Turning
+	  on this option will compile in support for DAX; you will need to
+	  mount the filesystem using the -o dax option.
+
+	  If you do not have a block device that is capable of using this,
+	  or if unsure, say N.  Saying Y will increase the size of the kernel
+	  by about 5kB.
+
 endif # BLOCK
 
 # Posix ACL utility routines
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index c055d56ec63d..270c48148f79 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -149,13 +149,6 @@ config BINFMT_EM86
 	  later load the module when you want to use a Linux/Intel binary. The
 	  module will be called binfmt_em86. If unsure, say Y.
 
-config BINFMT_SOM
-	tristate "Kernel support for SOM binaries"
-	depends on PARISC && HPUX
-	help
-	  SOM is a binary executable format inherited from HP/UX.  Say
-	  Y here to be able to load and execute SOM binaries directly.
-
 config BINFMT_MISC
 	tristate "Kernel support for MISC binaries"
 	---help---
diff --git a/fs/Makefile b/fs/Makefile
index bedff48e8fdc..a88ac4838c9e 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_SIGNALFD)		+= signalfd.o
 obj-$(CONFIG_TIMERFD)		+= timerfd.o
 obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_AIO)               += aio.o
+obj-$(CONFIG_FS_DAX)		+= dax.o
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o
@@ -37,7 +38,6 @@ obj-$(CONFIG_BINFMT_SCRIPT)	+= binfmt_script.o
 obj-$(CONFIG_BINFMT_ELF)	+= binfmt_elf.o
 obj-$(CONFIG_COMPAT_BINFMT_ELF)	+= compat_binfmt_elf.o
 obj-$(CONFIG_BINFMT_ELF_FDPIC)	+= binfmt_elf_fdpic.o
-obj-$(CONFIG_BINFMT_SOM)	+= binfmt_som.o
 obj-$(CONFIG_BINFMT_FLAT)	+= binfmt_flat.o
 
 obj-$(CONFIG_FS_MBCACHE)	+= mbcache.o
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index ff44ff3ff015..c8764bd7497d 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -30,6 +30,8 @@
 #define AFFS_AC_SIZE		(AFFS_CACHE_SIZE/sizeof(struct affs_ext_key)/2)
 #define AFFS_AC_MASK		(AFFS_AC_SIZE-1)
 
+#define AFFSNAMEMAX 30U
+
 struct affs_ext_key {
 	u32	ext;				/* idx of the extended block */
 	u32	key;				/* block number */
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index c852f2fa1710..388da1ea815d 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -30,7 +30,7 @@ affs_insert_hash(struct inode *dir, struct buffer_head *bh)
 	ino = bh->b_blocknr;
 	offset = affs_hash_name(sb, AFFS_TAIL(sb, bh)->name + 1, AFFS_TAIL(sb, bh)->name[0]);
 
-	pr_debug("%s(dir=%u, ino=%d)\n", __func__, (u32)dir->i_ino, ino);
+	pr_debug("%s(dir=%lu, ino=%d)\n", __func__, dir->i_ino, ino);
 
 	dir_bh = affs_bread(sb, dir->i_ino);
 	if (!dir_bh)
@@ -80,8 +80,8 @@ affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh)
 	sb = dir->i_sb;
 	rem_ino = rem_bh->b_blocknr;
 	offset = affs_hash_name(sb, AFFS_TAIL(sb, rem_bh)->name+1, AFFS_TAIL(sb, rem_bh)->name[0]);
-	pr_debug("%s(dir=%d, ino=%d, hashval=%d)\n",
-		 __func__, (u32)dir->i_ino, rem_ino, offset);
+	pr_debug("%s(dir=%lu, ino=%d, hashval=%d)\n", __func__, dir->i_ino,
+		 rem_ino, offset);
 
 	bh = affs_bread(sb, dir->i_ino);
 	if (!bh)
@@ -483,11 +483,10 @@ affs_check_name(const unsigned char *name, int len, bool notruncate)
 {
 	int	 i;
 
-	if (len > 30) {
+	if (len > AFFSNAMEMAX) {
 		if (notruncate)
 			return -ENAMETOOLONG;
-		else
-			len = 30;
+		len = AFFSNAMEMAX;
 	}
 	for (i = 0; i < len; i++) {
 		if (name[i] < ' ' || name[i] == ':'
@@ -508,7 +507,7 @@ affs_check_name(const unsigned char *name, int len, bool notruncate)
 int
 affs_copy_name(unsigned char *bstr, struct dentry *dentry)
 {
-	int len = min(dentry->d_name.len, 30u);
+	u32 len = min(dentry->d_name.len, AFFSNAMEMAX);
 
 	*bstr++ = len;
 	memcpy(bstr, dentry->d_name.name, len);
diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c
index c8de51185c23..675148950fed 100644
--- a/fs/affs/bitmap.c
+++ b/fs/affs/bitmap.c
@@ -99,7 +99,6 @@ err_bh_read:
 
 err_range:
 	affs_error(sb, "affs_free_block","Block %u outside partition", block);
-	return;
 }
 
 /*
diff --git a/fs/affs/dir.c b/fs/affs/dir.c
index 59f07bec92a6..ac4f318aafba 100644
--- a/fs/affs/dir.c
+++ b/fs/affs/dir.c
@@ -54,8 +54,7 @@ affs_readdir(struct file *file, struct dir_context *ctx)
 	u32			 ino;
 	int			 error = 0;
 
-	pr_debug("%s(ino=%lu,f_pos=%lx)\n",
-		 __func__, inode->i_ino, (unsigned long)ctx->pos);
+	pr_debug("%s(ino=%lu,f_pos=%llx)\n", __func__, inode->i_ino, ctx->pos);
 
 	if (ctx->pos < 2) {
 		file->private_data = (void *)0;
@@ -115,11 +114,11 @@ inside:
 				break;
 			}
 
-			namelen = min(AFFS_TAIL(sb, fh_bh)->name[0], (u8)30);
+			namelen = min(AFFS_TAIL(sb, fh_bh)->name[0],
+				      (u8)AFFSNAMEMAX);
 			name = AFFS_TAIL(sb, fh_bh)->name + 1;
-			pr_debug("readdir(): dir_emit(\"%.*s\", "
-				 "ino=%u), hash=%d, f_pos=%x\n",
-				 namelen, name, ino, hash_pos, (u32)ctx->pos);
+			pr_debug("readdir(): dir_emit(\"%.*s\", ino=%u), hash=%d, f_pos=%llx\n",
+				 namelen, name, ino, hash_pos, ctx->pos);
 
 			if (!dir_emit(ctx, name, namelen, ino, DT_UNKNOWN))
 				goto done;
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 8faa6593ca6d..d2468bf95669 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -180,8 +180,7 @@ affs_get_extblock_slow(struct inode *inode, u32 ext)
 		ext_key = be32_to_cpu(AFFS_TAIL(sb, bh)->extension);
 		if (ext < AFFS_I(inode)->i_extcnt)
 			goto read_ext;
-		if (ext > AFFS_I(inode)->i_extcnt)
-			BUG();
+		BUG_ON(ext > AFFS_I(inode)->i_extcnt);
 		bh = affs_alloc_extblock(inode, bh, ext);
 		if (IS_ERR(bh))
 			return bh;
@@ -198,8 +197,7 @@ affs_get_extblock_slow(struct inode *inode, u32 ext)
 		struct buffer_head *prev_bh;
 
 		/* allocate a new extended block */
-		if (ext > AFFS_I(inode)->i_extcnt)
-			BUG();
+		BUG_ON(ext > AFFS_I(inode)->i_extcnt);
 
 		/* get previous extended block */
 		prev_bh = affs_get_extblock(inode, ext - 1);
@@ -299,8 +297,8 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
 	struct buffer_head	*ext_bh;
 	u32			 ext;
 
-	pr_debug("%s(%u, %lu)\n",
-		 __func__, (u32)inode->i_ino, (unsigned long)block);
+	pr_debug("%s(%lu, %llu)\n", __func__, inode->i_ino,
+		 (unsigned long long)block);
 
 	BUG_ON(block > (sector_t)0x7fffffffUL);
 
@@ -330,8 +328,9 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
 
 		/* store new block */
 		if (bh_result->b_blocknr)
-			affs_warning(sb, "get_block", "block already set (%lx)",
-				     (unsigned long)bh_result->b_blocknr);
+			affs_warning(sb, "get_block",
+				     "block already set (%llx)",
+				     (unsigned long long)bh_result->b_blocknr);
 		AFFS_BLOCK(sb, ext_bh, block) = cpu_to_be32(blocknr);
 		AFFS_HEAD(ext_bh)->block_count = cpu_to_be32(block + 1);
 		affs_adjust_checksum(ext_bh, blocknr - bh_result->b_blocknr + 1);
@@ -353,8 +352,8 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
 	return 0;
 
 err_big:
-	affs_error(inode->i_sb, "get_block", "strange block request %d",
-		   (int)block);
+	affs_error(inode->i_sb, "get_block", "strange block request %llu",
+		   (unsigned long long)block);
 	return -EIO;
 err_ext:
 	// unlock cache
@@ -399,6 +398,13 @@ affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
+	if (rw == WRITE) {
+		loff_t size = offset + count;
+
+		if (AFFS_I(inode)->mmu_private < size)
+			return 0;
+	}
+
 	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, affs_get_block);
 	if (ret < 0 && (rw & WRITE))
 		affs_write_failed(mapping, offset + count);
@@ -503,7 +509,7 @@ affs_do_readpage_ofs(struct page *page, unsigned to)
 	u32 bidx, boff, bsize;
 	u32 tmp;
 
-	pr_debug("%s(%u, %ld, 0, %d)\n", __func__, (u32)inode->i_ino,
+	pr_debug("%s(%lu, %ld, 0, %d)\n", __func__, inode->i_ino,
 		 page->index, to);
 	BUG_ON(to > PAGE_CACHE_SIZE);
 	kmap(page);
@@ -539,7 +545,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
 	u32 size, bsize;
 	u32 tmp;
 
-	pr_debug("%s(%u, %d)\n", __func__, (u32)inode->i_ino, newsize);
+	pr_debug("%s(%lu, %d)\n", __func__, inode->i_ino, newsize);
 	bsize = AFFS_SB(sb)->s_data_blksize;
 	bh = NULL;
 	size = AFFS_I(inode)->mmu_private;
@@ -608,7 +614,7 @@ affs_readpage_ofs(struct file *file, struct page *page)
 	u32 to;
 	int err;
 
-	pr_debug("%s(%u, %ld)\n", __func__, (u32)inode->i_ino, page->index);
+	pr_debug("%s(%lu, %ld)\n", __func__, inode->i_ino, page->index);
 	to = PAGE_CACHE_SIZE;
 	if (((page->index + 1) << PAGE_CACHE_SHIFT) > inode->i_size) {
 		to = inode->i_size & ~PAGE_CACHE_MASK;
@@ -631,8 +637,8 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 	pgoff_t index;
 	int err = 0;
 
-	pr_debug("%s(%u, %llu, %llu)\n", __func__, (u32)inode->i_ino,
-		 (unsigned long long)pos, (unsigned long long)pos + len);
+	pr_debug("%s(%lu, %llu, %llu)\n", __func__, inode->i_ino, pos,
+		 pos + len);
 	if (pos > AFFS_I(inode)->mmu_private) {
 		/* XXX: this probably leaves a too-big i_size in case of
 		 * failure. Should really be updating i_size at write_end time
@@ -681,9 +687,8 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 	 * due to write_begin.
 	 */
 
-	pr_debug("%s(%u, %llu, %llu)\n",
-		 __func__, (u32)inode->i_ino, (unsigned long long)pos,
-		(unsigned long long)pos + len);
+	pr_debug("%s(%lu, %llu, %llu)\n", __func__, inode->i_ino, pos,
+		 pos + len);
 	bsize = AFFS_SB(sb)->s_data_blksize;
 	data = page_address(page);
 
@@ -831,8 +836,8 @@ affs_truncate(struct inode *inode)
 	struct buffer_head *ext_bh;
 	int i;
 
-	pr_debug("truncate(inode=%d, oldsize=%u, newsize=%u)\n",
-		 (u32)inode->i_ino, (u32)AFFS_I(inode)->mmu_private, (u32)inode->i_size);
+	pr_debug("truncate(inode=%lu, oldsize=%llu, newsize=%llu)\n",
+		 inode->i_ino, AFFS_I(inode)->mmu_private, inode->i_size);
 
 	last_blk = 0;
 	ext = 0;
@@ -863,7 +868,7 @@ affs_truncate(struct inode *inode)
 	if (IS_ERR(ext_bh)) {
 		affs_warning(sb, "truncate",
 			     "unexpected read error for ext block %u (%ld)",
-			     (unsigned int)ext, PTR_ERR(ext_bh));
+			     ext, PTR_ERR(ext_bh));
 		return;
 	}
 	if (AFFS_I(inode)->i_lc) {
@@ -911,7 +916,7 @@ affs_truncate(struct inode *inode)
 			if (IS_ERR(bh)) {
 				affs_warning(sb, "truncate",
 					     "unexpected read error for last block %u (%ld)",
-					     (unsigned int)ext, PTR_ERR(bh));
+					     ext, PTR_ERR(bh));
 				return;
 			}
 			tmp = be32_to_cpu(AFFS_DATA_HEAD(bh)->next);
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index d0609a282e1d..6f34510449e8 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -13,8 +13,6 @@
 #include <linux/gfp.h>
 #include "affs.h"
 
-extern const struct inode_operations affs_symlink_inode_operations;
-
 struct inode *affs_iget(struct super_block *sb, unsigned long ino)
 {
 	struct affs_sb_info	*sbi = AFFS_SB(sb);
@@ -348,9 +346,8 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3
 	u32 block = 0;
 	int retval;
 
-	pr_debug("%s(dir=%u, inode=%u, \"%pd\", type=%d)\n",
-		 __func__, (u32)dir->i_ino,
-	         (u32)inode->i_ino, dentry, type);
+	pr_debug("%s(dir=%lu, inode=%lu, \"%pd\", type=%d)\n", __func__,
+		 dir->i_ino, inode->i_ino, dentry, type);
 
 	retval = -EIO;
 	bh = affs_bread(sb, inode->i_ino);
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index bbc38530e924..ffb7bd82c2a5 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -64,15 +64,16 @@ __affs_hash_dentry(struct qstr *qstr, toupper_t toupper, bool notruncate)
 {
 	const u8 *name = qstr->name;
 	unsigned long hash;
-	int i;
+	int retval;
+	u32 len;
 
-	i = affs_check_name(qstr->name, qstr->len, notruncate);
-	if (i)
-		return i;
+	retval = affs_check_name(qstr->name, qstr->len, notruncate);
+	if (retval)
+		return retval;
 
 	hash = init_name_hash();
-	i = min(qstr->len, 30u);
-	for (; i > 0; name++, i--)
+	len = min(qstr->len, AFFSNAMEMAX);
+	for (; len > 0; name++, len--)
 		hash = partial_name_hash(toupper(*name), hash);
 	qstr->hash = end_name_hash(hash);
 
@@ -114,10 +115,10 @@ static inline int __affs_compare_dentry(unsigned int len,
 	 * If the names are longer than the allowed 30 chars,
 	 * the excess is ignored, so their length may differ.
 	 */
-	if (len >= 30) {
-		if (name->len < 30)
+	if (len >= AFFSNAMEMAX) {
+		if (name->len < AFFSNAMEMAX)
 			return 1;
-		len = 30;
+		len = AFFSNAMEMAX;
 	} else if (len != name->len)
 		return 1;
 
@@ -156,10 +157,10 @@ affs_match(struct dentry *dentry, const u8 *name2, toupper_t toupper)
 	const u8 *name = dentry->d_name.name;
 	int len = dentry->d_name.len;
 
-	if (len >= 30) {
-		if (*name2 < 30)
+	if (len >= AFFSNAMEMAX) {
+		if (*name2 < AFFSNAMEMAX)
 			return 0;
-		len = 30;
+		len = AFFSNAMEMAX;
 	} else if (len != *name2)
 		return 0;
 
@@ -173,9 +174,9 @@ int
 affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len)
 {
 	toupper_t toupper = affs_get_toupper(sb);
-	int hash;
+	u32 hash;
 
-	hash = len = min(len, 30u);
+	hash = len = min(len, AFFSNAMEMAX);
 	for (; len > 0; len--)
 		hash = (hash * 13 + toupper(*name++)) & 0x7ff;
 
@@ -248,9 +249,8 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 int
 affs_unlink(struct inode *dir, struct dentry *dentry)
 {
-	pr_debug("%s(dir=%d, %lu \"%pd\")\n",
-		 __func__, (u32)dir->i_ino, dentry->d_inode->i_ino,
-		dentry);
+	pr_debug("%s(dir=%lu, %lu \"%pd\")\n", __func__, dir->i_ino,
+		 dentry->d_inode->i_ino, dentry);
 
 	return affs_remove_header(dentry);
 }
@@ -317,9 +317,8 @@ affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 int
 affs_rmdir(struct inode *dir, struct dentry *dentry)
 {
-	pr_debug("%s(dir=%u, %lu \"%pd\")\n",
-		__func__, (u32)dir->i_ino, dentry->d_inode->i_ino,
-		 dentry);
+	pr_debug("%s(dir=%lu, %lu \"%pd\")\n", __func__, dir->i_ino,
+		 dentry->d_inode->i_ino, dentry);
 
 	return affs_remove_header(dentry);
 }
@@ -404,8 +403,7 @@ affs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = old_dentry->d_inode;
 
-	pr_debug("%s(%u, %u, \"%pd\")\n",
-		 __func__, (u32)inode->i_ino, (u32)dir->i_ino,
+	pr_debug("%s(%lu, %lu, \"%pd\")\n", __func__, inode->i_ino, dir->i_ino,
 		 dentry);
 
 	return affs_add_entry(dir, inode, dentry, ST_LINKFILE);
@@ -419,9 +417,8 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct buffer_head *bh = NULL;
 	int retval;
 
-	pr_debug("%s(old=%u,\"%pd\" to new=%u,\"%pd\")\n",
-		 __func__, (u32)old_dir->i_ino, old_dentry,
-		 (u32)new_dir->i_ino, new_dentry);
+	pr_debug("%s(old=%lu,\"%pd\" to new=%lu,\"%pd\")\n", __func__,
+		 old_dir->i_ino, old_dentry, new_dir->i_ino, new_dentry);
 
 	retval = affs_check_name(new_dentry->d_name.name,
 				 new_dentry->d_name.len,
diff --git a/fs/affs/super.c b/fs/affs/super.c
index f754ab68a840..4cf0e9113fb6 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -432,39 +432,39 @@ got_root:
 		sb->s_flags |= MS_RDONLY;
 	}
 	switch (chksum) {
-		case MUFS_FS:
-		case MUFS_INTLFFS:
-		case MUFS_DCFFS:
-			sbi->s_flags |= SF_MUFS;
-			/* fall thru */
-		case FS_INTLFFS:
-		case FS_DCFFS:
-			sbi->s_flags |= SF_INTL;
-			break;
-		case MUFS_FFS:
-			sbi->s_flags |= SF_MUFS;
-			break;
-		case FS_FFS:
-			break;
-		case MUFS_OFS:
-			sbi->s_flags |= SF_MUFS;
-			/* fall thru */
-		case FS_OFS:
-			sbi->s_flags |= SF_OFS;
-			sb->s_flags |= MS_NOEXEC;
-			break;
-		case MUFS_DCOFS:
-		case MUFS_INTLOFS:
-			sbi->s_flags |= SF_MUFS;
-		case FS_DCOFS:
-		case FS_INTLOFS:
-			sbi->s_flags |= SF_INTL | SF_OFS;
-			sb->s_flags |= MS_NOEXEC;
-			break;
-		default:
-			pr_err("Unknown filesystem on device %s: %08X\n",
-			       sb->s_id, chksum);
-			return -EINVAL;
+	case MUFS_FS:
+	case MUFS_INTLFFS:
+	case MUFS_DCFFS:
+		sbi->s_flags |= SF_MUFS;
+		/* fall thru */
+	case FS_INTLFFS:
+	case FS_DCFFS:
+		sbi->s_flags |= SF_INTL;
+		break;
+	case MUFS_FFS:
+		sbi->s_flags |= SF_MUFS;
+		break;
+	case FS_FFS:
+		break;
+	case MUFS_OFS:
+		sbi->s_flags |= SF_MUFS;
+		/* fall thru */
+	case FS_OFS:
+		sbi->s_flags |= SF_OFS;
+		sb->s_flags |= MS_NOEXEC;
+		break;
+	case MUFS_DCOFS:
+	case MUFS_INTLOFS:
+		sbi->s_flags |= SF_MUFS;
+	case FS_DCOFS:
+	case FS_INTLOFS:
+		sbi->s_flags |= SF_INTL | SF_OFS;
+		sb->s_flags |= MS_NOEXEC;
+		break;
+	default:
+		pr_err("Unknown filesystem on device %s: %08X\n",
+		       sb->s_id, chksum);
+		return -EINVAL;
 	}
 
 	if (mount_flags & SF_VERBOSE) {
@@ -584,7 +584,7 @@ affs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail  = free;
 	buf->f_fsid.val[0] = (u32)id;
 	buf->f_fsid.val[1] = (u32)(id >> 32);
-	buf->f_namelen = 30;
+	buf->f_namelen = AFFSNAMEMAX;
 	return 0;
 }
 
@@ -602,6 +602,7 @@ static void affs_kill_sb(struct super_block *sb)
 		affs_free_bitmap(sb);
 		affs_brelse(sbi->s_root_bh);
 		kfree(sbi->s_prefix);
+		mutex_destroy(&sbi->s_bmlock);
 		kfree(sbi);
 	}
 }
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 06e14bfb3496..dbc732e9a5c0 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -306,8 +306,8 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
 
 			_debug("- range %u-%u%s",
 			       offset, to, msg->msg_flags ? " [more]" : "");
-			iov_iter_init(&msg->msg_iter, WRITE,
-				      (struct iovec *) iov, 1, to - offset);
+			iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC,
+				      iov, 1, to - offset);
 
 			/* have to change the state *before* sending the last
 			 * packet as RxRPC might give us the reply before it
@@ -384,7 +384,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)iov, 1,
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1,
 		      call->request_size);
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
@@ -770,7 +770,7 @@ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb,
 void afs_send_empty_reply(struct afs_call *call)
 {
 	struct msghdr msg;
-	struct iovec iov[1];
+	struct kvec iov[1];
 
 	_enter("");
 
@@ -778,7 +778,7 @@ void afs_send_empty_reply(struct afs_call *call)
 	iov[0].iov_len		= 0;
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	iov_iter_init(&msg.msg_iter, WRITE, iov, 0, 0);	/* WTF? */
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 0, 0);	/* WTF? */
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= 0;
@@ -805,7 +805,7 @@ void afs_send_empty_reply(struct afs_call *call)
 void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 {
 	struct msghdr msg;
-	struct iovec iov[1];
+	struct kvec iov[1];
 	int n;
 
 	_enter("");
@@ -814,7 +814,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 	iov[0].iov_len		= len;
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	iov_iter_init(&msg.msg_iter, WRITE, iov, 1, len);
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, len);
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= 0;
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 2b607257820c..d142a2449e65 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -106,7 +106,7 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params)
 	volume->cell		= params->cell;
 	volume->vid		= vlocation->vldb.vid[params->type];
 
-	ret = bdi_setup_and_register(&volume->bdi, "afs", BDI_CAP_MAP_COPY);
+	ret = bdi_setup_and_register(&volume->bdi, "afs");
 	if (ret)
 		goto error_bdi;
 
diff --git a/fs/aio.c b/fs/aio.c
index c428871f1093..f8e52a1854c1 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -165,15 +165,6 @@ static struct vfsmount *aio_mnt;
 static const struct file_operations aio_ring_fops;
 static const struct address_space_operations aio_ctx_aops;
 
-/* Backing dev info for aio fs.
- * -no dirty page accounting or writeback happens
- */
-static struct backing_dev_info aio_fs_backing_dev_info = {
-	.name           = "aiofs",
-	.state          = 0,
-	.capabilities   = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY,
-};
-
 static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 {
 	struct qstr this = QSTR_INIT("[aio]", 5);
@@ -185,7 +176,6 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 
 	inode->i_mapping->a_ops = &aio_ctx_aops;
 	inode->i_mapping->private_data = ctx;
-	inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
 	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
@@ -230,9 +220,6 @@ static int __init aio_setup(void)
 	if (IS_ERR(aio_mnt))
 		panic("Failed to create aio fs mount.");
 
-	if (bdi_init(&aio_fs_backing_dev_info))
-		panic("Failed to init aio fs backing dev info.");
-
 	kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
@@ -1298,7 +1285,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 
 	ret = -EINVAL;
 	if (unlikely(ctx || nr_events == 0)) {
-		pr_debug("EINVAL: io_setup: ctx %lu nr_events %u\n",
+		pr_debug("EINVAL: ctx %lu nr_events %u\n",
 		         ctx, nr_events);
 		goto out;
 	}
@@ -1346,7 +1333,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 
 		return ret;
 	}
-	pr_debug("EINVAL: io_destroy: invalid context id\n");
+	pr_debug("EINVAL: invalid context id\n");
 	return -EINVAL;
 }
 
@@ -1528,7 +1515,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	    (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) ||
 	    ((ssize_t)iocb->aio_nbytes < 0)
 	   )) {
-		pr_debug("EINVAL: io_submit: overflow check\n");
+		pr_debug("EINVAL: overflow check\n");
 		return -EINVAL;
 	}
 
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index aaf96cb25452..ac7d921ed984 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -95,7 +95,7 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param)
  */
 static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in)
 {
-	struct autofs_dev_ioctl tmp;
+	struct autofs_dev_ioctl tmp, *res;
 
 	if (copy_from_user(&tmp, in, sizeof(tmp)))
 		return ERR_PTR(-EFAULT);
@@ -106,7 +106,11 @@ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *i
 	if (tmp.size > (PATH_MAX + sizeof(tmp)))
 		return ERR_PTR(-ENAMETOOLONG);
 
-	return memdup_user(in, tmp.size);
+	res = memdup_user(in, tmp.size);
+	if (!IS_ERR(res))
+		res->size = tmp.size;
+
+	return res;
 }
 
 static inline void free_dev_ioctl(struct autofs_dev_ioctl *param)
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index bfdbaba9c2ba..11dd118f75e2 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -374,7 +374,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 		return NULL;
 	}
 
-	if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)) {
+	if (dentry->d_inode && d_is_symlink(dentry)) {
 		DPRINTK("checking symlink %p %pd", dentry, dentry);
 		/*
 		 * A symlink can't be "busy" in the usual sense so
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index dbb5b7212ce1..7e44fdd03e2d 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -108,7 +108,7 @@ static int autofs4_dir_open(struct inode *inode, struct file *file)
 	struct dentry *dentry = file->f_path.dentry;
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 
-	DPRINTK("file=%p dentry=%p %pD", file, dentry, dentry);
+	DPRINTK("file=%p dentry=%p %pd", file, dentry, dentry);
 
 	if (autofs4_oz_mode(sbi))
 		goto out;
@@ -371,7 +371,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 	 * having d_mountpoint() true, so there's no need to call back
 	 * to the daemon.
 	 */
-	if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)) {
+	if (dentry->d_inode && d_is_symlink(dentry)) {
 		spin_unlock(&sbi->fs_lock);
 		goto done;
 	}
@@ -485,7 +485,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 		 * an incorrect ELOOP error return.
 		 */
 		if ((!d_mountpoint(dentry) && !simple_empty(dentry)) ||
-		    (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)))
+		    (dentry->d_inode && d_is_symlink(dentry)))
 			status = -EISDIR;
 	}
 	spin_unlock(&sbi->fs_lock);
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index afd2b4408adf..861b1e1c4777 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -15,161 +15,14 @@
 #include <linux/namei.h>
 #include <linux/poll.h>
 
-
-static loff_t bad_file_llseek(struct file *file, loff_t offset, int whence)
-{
-	return -EIO;
-}
-
-static ssize_t bad_file_read(struct file *filp, char __user *buf,
-			size_t size, loff_t *ppos)
-{
-        return -EIO;
-}
-
-static ssize_t bad_file_write(struct file *filp, const char __user *buf,
-			size_t siz, loff_t *ppos)
-{
-        return -EIO;
-}
-
-static ssize_t bad_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
-			unsigned long nr_segs, loff_t pos)
-{
-	return -EIO;
-}
-
-static ssize_t bad_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			unsigned long nr_segs, loff_t pos)
-{
-	return -EIO;
-}
-
-static int bad_file_readdir(struct file *file, struct dir_context *ctx)
-{
-	return -EIO;
-}
-
-static unsigned int bad_file_poll(struct file *filp, poll_table *wait)
-{
-	return POLLERR;
-}
-
-static long bad_file_unlocked_ioctl(struct file *file, unsigned cmd,
-			unsigned long arg)
-{
-	return -EIO;
-}
-
-static long bad_file_compat_ioctl(struct file *file, unsigned int cmd,
-			unsigned long arg)
-{
-	return -EIO;
-}
-
-static int bad_file_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	return -EIO;
-}
-
 static int bad_file_open(struct inode *inode, struct file *filp)
 {
 	return -EIO;
 }
 
-static int bad_file_flush(struct file *file, fl_owner_t id)
-{
-	return -EIO;
-}
-
-static int bad_file_release(struct inode *inode, struct file *filp)
-{
-	return -EIO;
-}
-
-static int bad_file_fsync(struct file *file, loff_t start, loff_t end,
-			  int datasync)
-{
-	return -EIO;
-}
-
-static int bad_file_aio_fsync(struct kiocb *iocb, int datasync)
-{
-	return -EIO;
-}
-
-static int bad_file_fasync(int fd, struct file *filp, int on)
-{
-	return -EIO;
-}
-
-static int bad_file_lock(struct file *file, int cmd, struct file_lock *fl)
-{
-	return -EIO;
-}
-
-static ssize_t bad_file_sendpage(struct file *file, struct page *page,
-			int off, size_t len, loff_t *pos, int more)
-{
-	return -EIO;
-}
-
-static unsigned long bad_file_get_unmapped_area(struct file *file,
-				unsigned long addr, unsigned long len,
-				unsigned long pgoff, unsigned long flags)
-{
-	return -EIO;
-}
-
-static int bad_file_check_flags(int flags)
-{
-	return -EIO;
-}
-
-static int bad_file_flock(struct file *filp, int cmd, struct file_lock *fl)
-{
-	return -EIO;
-}
-
-static ssize_t bad_file_splice_write(struct pipe_inode_info *pipe,
-			struct file *out, loff_t *ppos, size_t len,
-			unsigned int flags)
-{
-	return -EIO;
-}
-
-static ssize_t bad_file_splice_read(struct file *in, loff_t *ppos,
-			struct pipe_inode_info *pipe, size_t len,
-			unsigned int flags)
-{
-	return -EIO;
-}
-
 static const struct file_operations bad_file_ops =
 {
-	.llseek		= bad_file_llseek,
-	.read		= bad_file_read,
-	.write		= bad_file_write,
-	.aio_read	= bad_file_aio_read,
-	.aio_write	= bad_file_aio_write,
-	.iterate	= bad_file_readdir,
-	.poll		= bad_file_poll,
-	.unlocked_ioctl	= bad_file_unlocked_ioctl,
-	.compat_ioctl	= bad_file_compat_ioctl,
-	.mmap		= bad_file_mmap,
 	.open		= bad_file_open,
-	.flush		= bad_file_flush,
-	.release	= bad_file_release,
-	.fsync		= bad_file_fsync,
-	.aio_fsync	= bad_file_aio_fsync,
-	.fasync		= bad_file_fasync,
-	.lock		= bad_file_lock,
-	.sendpage	= bad_file_sendpage,
-	.get_unmapped_area = bad_file_get_unmapped_area,
-	.check_flags	= bad_file_check_flags,
-	.flock		= bad_file_flock,
-	.splice_write	= bad_file_splice_write,
-	.splice_read	= bad_file_splice_read,
 };
 
 static int bad_inode_create (struct inode *dir, struct dentry *dentry,
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index edf47774b03d..e089f1985fca 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -274,9 +274,9 @@ more:
 static struct inode *
 befs_alloc_inode(struct super_block *sb)
 {
-        struct befs_inode_info *bi;
-        bi = (struct befs_inode_info *)kmem_cache_alloc(befs_inode_cachep,
-							GFP_KERNEL);
+	struct befs_inode_info *bi;
+
+	bi = kmem_cache_alloc(befs_inode_cachep, GFP_KERNEL);
         if (!bi)
                 return NULL;
         return &bi->vfs_inode;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 02b16910f4c9..995986b8e36b 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -645,11 +645,12 @@ out:
 
 static unsigned long randomize_stack_top(unsigned long stack_top)
 {
-	unsigned int random_variable = 0;
+	unsigned long random_variable = 0;
 
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		random_variable = get_random_int() & STACK_RND_MASK;
+		random_variable = (unsigned long) get_random_int();
+		random_variable &= STACK_RND_MASK;
 		random_variable <<= PAGE_SHIFT;
 	}
 #ifdef CONFIG_STACK_GROWSUP
diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c
deleted file mode 100644
index 4e00ed68d4a6..000000000000
--- a/fs/binfmt_som.c
+++ /dev/null
@@ -1,299 +0,0 @@
-/*
- * linux/fs/binfmt_som.c
- *
- * These are the functions used to load SOM format executables as used
- * by HP-UX.  
- *
- * Copyright 1999 Matthew Wilcox <willy@bofh.ai>
- * based on binfmt_elf which is
- * Copyright 1993, 1994: Eric Youngdale (ericy@cais.com).
- */
-
-#include <linux/module.h>
-
-#include <linux/fs.h>
-#include <linux/stat.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/binfmts.h>
-#include <linux/som.h>
-#include <linux/string.h>
-#include <linux/file.h>
-#include <linux/fcntl.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/shm.h>
-#include <linux/personality.h>
-#include <linux/init.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
-
-
-#include <linux/elf.h>
-
-static int load_som_binary(struct linux_binprm * bprm);
-static int load_som_library(struct file *);
-
-/*
- * If we don't support core dumping, then supply a NULL so we
- * don't even try.
- */
-#if 0
-static int som_core_dump(struct coredump_params *cprm);
-#else
-#define som_core_dump	NULL
-#endif
-
-#define SOM_PAGESTART(_v) ((_v) & ~(unsigned long)(SOM_PAGESIZE-1))
-#define SOM_PAGEOFFSET(_v) ((_v) & (SOM_PAGESIZE-1))
-#define SOM_PAGEALIGN(_v) (((_v) + SOM_PAGESIZE - 1) & ~(SOM_PAGESIZE - 1))
-
-static struct linux_binfmt som_format = {
-	.module		= THIS_MODULE,
-	.load_binary	= load_som_binary,
-	.load_shlib	= load_som_library,
-	.core_dump	= som_core_dump,
-	.min_coredump	= SOM_PAGESIZE
-};
-
-/*
- * create_som_tables() parses the env- and arg-strings in new user
- * memory and creates the pointer tables from them, and puts their
- * addresses on the "stack", returning the new stack pointer value.
- */
-static void create_som_tables(struct linux_binprm *bprm)
-{
-	char **argv, **envp;
-	int argc = bprm->argc;
-	int envc = bprm->envc;
-	unsigned long p;
-	unsigned long *sp;
-
-	/* Word-align the stack pointer */
-	sp = (unsigned long *)((bprm->p + 3) & ~3);
-
-	envp = (char **) sp;
-	sp += envc + 1;
-	argv = (char **) sp;
-	sp += argc + 1;
-
-	__put_user((unsigned long) envp,++sp);
-	__put_user((unsigned long) argv,++sp);
-
-	__put_user(argc, ++sp);
-
-	bprm->p = (unsigned long) sp;
-
-	p = current->mm->arg_start;
-	while (argc-- > 0) {
-		__put_user((char *)p,argv++);
-		p += strlen_user((char *)p);
-	}
-	__put_user(NULL, argv);
-	current->mm->arg_end = current->mm->env_start = p;
-	while (envc-- > 0) {
-		__put_user((char *)p,envp++);
-		p += strlen_user((char *)p);
-	}
-	__put_user(NULL, envp);
-	current->mm->env_end = p;
-}
-
-static int check_som_header(struct som_hdr *som_ex)
-{
-	int *buf = (int *)som_ex;
-	int i, ck;
-
-	if (som_ex->system_id != SOM_SID_PARISC_1_0 &&
-	    som_ex->system_id != SOM_SID_PARISC_1_1 &&
-	    som_ex->system_id != SOM_SID_PARISC_2_0)
-		return -ENOEXEC;
-
-	if (som_ex->a_magic != SOM_EXEC_NONSHARE &&
-	    som_ex->a_magic != SOM_EXEC_SHARE &&
-	    som_ex->a_magic != SOM_EXEC_DEMAND)
-		return -ENOEXEC;
-
-	if (som_ex->version_id != SOM_ID_OLD &&
-	    som_ex->version_id != SOM_ID_NEW)
-		return -ENOEXEC;
-
-	ck = 0;
-	for (i=0; i<32; i++)
-		ck ^= buf[i];
-	if (ck != 0)
-		return -ENOEXEC;
-
-	return 0;
-}
-
-static int map_som_binary(struct file *file,
-		const struct som_exec_auxhdr *hpuxhdr)
-{
-	unsigned long code_start, code_size, data_start, data_size;
-	unsigned long bss_start, som_brk;
-	int retval;
-	int prot = PROT_READ | PROT_EXEC;
-	int flags = MAP_FIXED|MAP_PRIVATE|MAP_DENYWRITE|MAP_EXECUTABLE;
-
-	mm_segment_t old_fs = get_fs();
-	set_fs(get_ds());
-
-	code_start = SOM_PAGESTART(hpuxhdr->exec_tmem);
-	code_size = SOM_PAGEALIGN(hpuxhdr->exec_tsize);
-	current->mm->start_code = code_start;
-	current->mm->end_code = code_start + code_size;
-	retval = vm_mmap(file, code_start, code_size, prot,
-			flags, SOM_PAGESTART(hpuxhdr->exec_tfile));
-	if (retval < 0 && retval > -1024)
-		goto out;
-
-	data_start = SOM_PAGESTART(hpuxhdr->exec_dmem);
-	data_size = SOM_PAGEALIGN(hpuxhdr->exec_dsize);
-	current->mm->start_data = data_start;
-	current->mm->end_data = bss_start = data_start + data_size;
-	retval = vm_mmap(file, data_start, data_size,
-			prot | PROT_WRITE, flags,
-			SOM_PAGESTART(hpuxhdr->exec_dfile));
-	if (retval < 0 && retval > -1024)
-		goto out;
-
-	som_brk = bss_start + SOM_PAGEALIGN(hpuxhdr->exec_bsize);
-	current->mm->start_brk = current->mm->brk = som_brk;
-	retval = vm_mmap(NULL, bss_start, som_brk - bss_start,
-			prot | PROT_WRITE, MAP_FIXED | MAP_PRIVATE, 0);
-	if (retval > 0 || retval < -1024)
-		retval = 0;
-out:
-	set_fs(old_fs);
-	return retval;
-}
-
-
-/*
- * These are the functions used to load SOM executables and shared
- * libraries.  There is no binary dependent code anywhere else.
- */
-
-static int
-load_som_binary(struct linux_binprm * bprm)
-{
-	int retval;
-	unsigned int size;
-	unsigned long som_entry;
-	struct som_hdr *som_ex;
-	struct som_exec_auxhdr *hpuxhdr;
-	struct pt_regs *regs = current_pt_regs();
-
-	/* Get the exec-header */
-	som_ex = (struct som_hdr *) bprm->buf;
-
-	retval = check_som_header(som_ex);
-	if (retval != 0)
-		goto out;
-
-	/* Now read in the auxiliary header information */
-
-	retval = -ENOMEM;
-	size = som_ex->aux_header_size;
-	if (size > SOM_PAGESIZE)
-		goto out;
-	hpuxhdr = kmalloc(size, GFP_KERNEL);
-	if (!hpuxhdr)
-		goto out;
-
-	retval = kernel_read(bprm->file, som_ex->aux_header_location,
-			(char *) hpuxhdr, size);
-	if (retval != size) {
-		if (retval >= 0)
-			retval = -EIO;
-		goto out_free;
-	}
-
-	/* Flush all traces of the currently running executable */
-	retval = flush_old_exec(bprm);
-	if (retval)
-		goto out_free;
-
-	/* OK, This is the point of no return */
-	current->personality = PER_HPUX;
-	setup_new_exec(bprm);
-
-	/* Set the task size for HP-UX processes such that
-	 * the gateway page is outside the address space.
-	 * This can be fixed later, but for now, this is much
-	 * easier.
-	 */
-
-	current->thread.task_size = 0xc0000000;
-
-	/* Set map base to allow enough room for hp-ux heap growth */
-
-	current->thread.map_base = 0x80000000;
-
-	retval = map_som_binary(bprm->file, hpuxhdr);
-	if (retval < 0)
-		goto out_free;
-
-	som_entry = hpuxhdr->exec_entry;
-	kfree(hpuxhdr);
-
-	set_binfmt(&som_format);
-	install_exec_creds(bprm);
-	setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
-
-	create_som_tables(bprm);
-
-	current->mm->start_stack = bprm->p;
-
-#if 0
-	printk("(start_brk) %08lx\n" , (unsigned long) current->mm->start_brk);
-	printk("(end_code) %08lx\n" , (unsigned long) current->mm->end_code);
-	printk("(start_code) %08lx\n" , (unsigned long) current->mm->start_code);
-	printk("(end_data) %08lx\n" , (unsigned long) current->mm->end_data);
-	printk("(start_stack) %08lx\n" , (unsigned long) current->mm->start_stack);
-	printk("(brk) %08lx\n" , (unsigned long) current->mm->brk);
-#endif
-
-	map_hpux_gateway_page(current,current->mm);
-
-	start_thread_som(regs, som_entry, bprm->p);
-	return 0;
-
-	/* error cleanup */
-out_free:
-	kfree(hpuxhdr);
-out:
-	return retval;
-}
-
-static int load_som_library(struct file *f)
-{
-/* No lib support in SOM yet.  gizza chance.. */
-	return -ENOEXEC;
-}
-	/* Install the SOM loader.
-	 * N.B. We *rely* on the table being the right size with the
-	 * right number of free slots...
-	 */
-
-static int __init init_som_binfmt(void)
-{
-	register_binfmt(&som_format);
-	return 0;
-}
-
-static void __exit exit_som_binfmt(void)
-{
-	/* Remove the SOM loader. */
-	unregister_binfmt(&som_format);
-}
-
-core_initcall(init_som_binfmt);
-module_exit(exit_som_binfmt);
-
-MODULE_LICENSE("GPL");
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b48c41bf0f86..975266be67d3 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -49,23 +49,15 @@ inline struct block_device *I_BDEV(struct inode *inode)
 }
 EXPORT_SYMBOL(I_BDEV);
 
-/*
- * Move the inode from its current bdi to a new bdi.  Make sure the inode
- * is clean before moving so that it doesn't linger on the old bdi.
- */
-static void bdev_inode_switch_bdi(struct inode *inode,
-			struct backing_dev_info *dst)
+static void bdev_write_inode(struct inode *inode)
 {
-	while (true) {
-		spin_lock(&inode->i_lock);
-		if (!(inode->i_state & I_DIRTY)) {
-			inode->i_data.backing_dev_info = dst;
-			spin_unlock(&inode->i_lock);
-			return;
-		}
+	spin_lock(&inode->i_lock);
+	while (inode->i_state & I_DIRTY) {
 		spin_unlock(&inode->i_lock);
 		WARN_ON_ONCE(write_inode_now(inode, true));
+		spin_lock(&inode->i_lock);
 	}
+	spin_unlock(&inode->i_lock);
 }
 
 /* Kill _all_ buffers and pagecache , dirty or not.. */
@@ -429,6 +421,46 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(bdev_write_page);
 
+/**
+ * bdev_direct_access() - Get the address for directly-accessibly memory
+ * @bdev: The device containing the memory
+ * @sector: The offset within the device
+ * @addr: Where to put the address of the memory
+ * @pfn: The Page Frame Number for the memory
+ * @size: The number of bytes requested
+ *
+ * If a block device is made up of directly addressable memory, this function
+ * will tell the caller the PFN and the address of the memory.  The address
+ * may be directly dereferenced within the kernel without the need to call
+ * ioremap(), kmap() or similar.  The PFN is suitable for inserting into
+ * page tables.
+ *
+ * Return: negative errno if an error occurs, otherwise the number of bytes
+ * accessible at this address.
+ */
+long bdev_direct_access(struct block_device *bdev, sector_t sector,
+			void **addr, unsigned long *pfn, long size)
+{
+	long avail;
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+
+	if (size < 0)
+		return size;
+	if (!ops->direct_access)
+		return -EOPNOTSUPP;
+	if ((sector + DIV_ROUND_UP(size, 512)) >
+					part_nr_sects_read(bdev->bd_part))
+		return -ERANGE;
+	sector += get_start_sect(bdev);
+	if (sector % (PAGE_SIZE / 512))
+		return -EINVAL;
+	avail = ops->direct_access(bdev, sector, addr, pfn, size);
+	if (!avail)
+		return -ERANGE;
+	return min(avail, size);
+}
+EXPORT_SYMBOL_GPL(bdev_direct_access);
+
 /*
  * pseudo-fs
  */
@@ -584,7 +616,6 @@ struct block_device *bdget(dev_t dev)
 		inode->i_bdev = bdev;
 		inode->i_data.a_ops = &def_blk_aops;
 		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
-		inode->i_data.backing_dev_info = &default_backing_dev_info;
 		spin_lock(&bdev_lock);
 		list_add(&bdev->bd_list, &all_bdevs);
 		spin_unlock(&bdev_lock);
@@ -1145,8 +1176,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
 		if (!partno) {
-			struct backing_dev_info *bdi;
-
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!bdev->bd_part)
@@ -1172,11 +1201,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				}
 			}
 
-			if (!ret) {
+			if (!ret)
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
-				bdi = blk_get_backing_dev_info(bdev);
-				bdev_inode_switch_bdi(bdev->bd_inode, bdi);
-			}
 
 			/*
 			 * If the device is invalidated, rescan partition
@@ -1203,8 +1229,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (ret)
 				goto out_clear;
 			bdev->bd_contains = whole;
-			bdev_inode_switch_bdi(bdev->bd_inode,
-				whole->bd_inode->i_data.backing_dev_info);
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
 			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
@@ -1244,7 +1268,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
 	bdev->bd_queue = NULL;
-	bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
@@ -1464,11 +1487,11 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		WARN_ON_ONCE(bdev->bd_holders);
 		sync_blockdev(bdev);
 		kill_bdev(bdev);
-		/* ->release can cause the old bdi to disappear,
-		 * so must switch it out first
+		/*
+		 * ->release can cause the queue to disappear, so flush all
+		 * dirty data before.
 		 */
-		bdev_inode_switch_bdi(bdev->bd_inode,
-					&default_backing_dev_info);
+		bdev_write_inode(bdev->bd_inode);
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 8729cf68d2fe..f55721ff9385 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1246,25 +1246,6 @@ int btrfs_check_shared(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-/*
- * this makes the path point to (inum INODE_ITEM ioff)
- */
-int inode_item_info(u64 inum, u64 ioff, struct btrfs_root *fs_root,
-			struct btrfs_path *path)
-{
-	struct btrfs_key key;
-	return btrfs_find_item(fs_root, path, inum, ioff,
-			BTRFS_INODE_ITEM_KEY, &key);
-}
-
-static int inode_ref_info(u64 inum, u64 ioff, struct btrfs_root *fs_root,
-				struct btrfs_path *path,
-				struct btrfs_key *found_key)
-{
-	return btrfs_find_item(fs_root, path, inum, ioff,
-			BTRFS_INODE_REF_KEY, found_key);
-}
-
 int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
 			  u64 start_off, struct btrfs_path *path,
 			  struct btrfs_inode_extref **ret_extref,
@@ -1374,7 +1355,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 			btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
 		}
-		ret = inode_ref_info(parent, 0, fs_root, path, &found_key);
+		ret = btrfs_find_item(fs_root, path, parent, 0,
+				BTRFS_INODE_REF_KEY, &found_key);
 		if (ret > 0)
 			ret = -ENOENT;
 		if (ret)
@@ -1727,8 +1709,10 @@ static int iterate_inode_refs(u64 inum, struct btrfs_root *fs_root,
 	struct btrfs_key found_key;
 
 	while (!ret) {
-		ret = inode_ref_info(inum, parent ? parent+1 : 0, fs_root, path,
-				     &found_key);
+		ret = btrfs_find_item(fs_root, path, inum,
+				parent ? parent + 1 : 0, BTRFS_INODE_REF_KEY,
+				&found_key);
+
 		if (ret < 0)
 			break;
 		if (ret) {
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 2a1ac6bfc724..9c41fbac3009 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -32,9 +32,6 @@ struct inode_fs_paths {
 typedef int (iterate_extent_inodes_t)(u64 inum, u64 offset, u64 root,
 		void *ctx);
 
-int inode_item_info(u64 inum, u64 ioff, struct btrfs_root *fs_root,
-			struct btrfs_path *path);
-
 int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 			struct btrfs_path *path, struct btrfs_key *found_key,
 			u64 *flags);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 4aadadcfab20..de5e4f2adfea 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -185,6 +185,9 @@ struct btrfs_inode {
 
 	struct btrfs_delayed_node *delayed_node;
 
+	/* File creation time. */
+	struct timespec i_otime;
+
 	struct inode vfs_inode;
 };
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 14a72ed14ef7..6d67f32e648d 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -213,11 +213,19 @@ static struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
  */
 static void add_root_to_dirty_list(struct btrfs_root *root)
 {
+	if (test_bit(BTRFS_ROOT_DIRTY, &root->state) ||
+	    !test_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state))
+		return;
+
 	spin_lock(&root->fs_info->trans_lock);
-	if (test_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state) &&
-	    list_empty(&root->dirty_list)) {
-		list_add(&root->dirty_list,
-			 &root->fs_info->dirty_cowonly_roots);
+	if (!test_and_set_bit(BTRFS_ROOT_DIRTY, &root->state)) {
+		/* Want the extent tree to be the last on the list */
+		if (root->objectid == BTRFS_EXTENT_TREE_OBJECTID)
+			list_move_tail(&root->dirty_list,
+				       &root->fs_info->dirty_cowonly_roots);
+		else
+			list_move(&root->dirty_list,
+				  &root->fs_info->dirty_cowonly_roots);
 	}
 	spin_unlock(&root->fs_info->trans_lock);
 }
@@ -1363,8 +1371,7 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 
 	if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
 		BUG_ON(tm->slot != 0);
-		eb_rewin = alloc_dummy_extent_buffer(eb->start,
-						fs_info->tree_root->nodesize);
+		eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start);
 		if (!eb_rewin) {
 			btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
@@ -1444,7 +1451,7 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 	} else if (old_root) {
 		btrfs_tree_read_unlock(eb_root);
 		free_extent_buffer(eb_root);
-		eb = alloc_dummy_extent_buffer(logical, root->nodesize);
+		eb = alloc_dummy_extent_buffer(root->fs_info, logical);
 	} else {
 		btrfs_set_lock_blocking_rw(eb_root, BTRFS_READ_LOCK);
 		eb = btrfs_clone_extent_buffer(eb_root);
@@ -1638,14 +1645,14 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 
 	parent_nritems = btrfs_header_nritems(parent);
 	blocksize = root->nodesize;
-	end_slot = parent_nritems;
+	end_slot = parent_nritems - 1;
 
-	if (parent_nritems == 1)
+	if (parent_nritems <= 1)
 		return 0;
 
 	btrfs_set_lock_blocking(parent);
 
-	for (i = start_slot; i < end_slot; i++) {
+	for (i = start_slot; i <= end_slot; i++) {
 		int close = 1;
 
 		btrfs_node_key(parent, &disk_key, i);
@@ -1662,7 +1669,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 			other = btrfs_node_blockptr(parent, i - 1);
 			close = close_blocks(blocknr, other, blocksize);
 		}
-		if (!close && i < end_slot - 2) {
+		if (!close && i < end_slot) {
 			other = btrfs_node_blockptr(parent, i + 1);
 			close = close_blocks(blocknr, other, blocksize);
 		}
@@ -2282,7 +2289,7 @@ static void reada_for_search(struct btrfs_root *root,
 		if ((search <= target && target - search <= 65536) ||
 		    (search > target && search - target <= 65536)) {
 			gen = btrfs_node_ptr_generation(node, nr);
-			readahead_tree_block(root, search, blocksize);
+			readahead_tree_block(root, search);
 			nread += blocksize;
 		}
 		nscan++;
@@ -2301,7 +2308,6 @@ static noinline void reada_for_balance(struct btrfs_root *root,
 	u64 gen;
 	u64 block1 = 0;
 	u64 block2 = 0;
-	int blocksize;
 
 	parent = path->nodes[level + 1];
 	if (!parent)
@@ -2309,7 +2315,6 @@ static noinline void reada_for_balance(struct btrfs_root *root,
 
 	nritems = btrfs_header_nritems(parent);
 	slot = path->slots[level + 1];
-	blocksize = root->nodesize;
 
 	if (slot > 0) {
 		block1 = btrfs_node_blockptr(parent, slot - 1);
@@ -2334,9 +2339,9 @@ static noinline void reada_for_balance(struct btrfs_root *root,
 	}
 
 	if (block1)
-		readahead_tree_block(root, block1, blocksize);
+		readahead_tree_block(root, block1);
 	if (block2)
-		readahead_tree_block(root, block2, blocksize);
+		readahead_tree_block(root, block2);
 }
 
 
@@ -2609,32 +2614,24 @@ static int key_search(struct extent_buffer *b, struct btrfs_key *key,
 	return 0;
 }
 
-int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *found_path,
+int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
 		u64 iobjectid, u64 ioff, u8 key_type,
 		struct btrfs_key *found_key)
 {
 	int ret;
 	struct btrfs_key key;
 	struct extent_buffer *eb;
-	struct btrfs_path *path;
+
+	ASSERT(path);
+	ASSERT(found_key);
 
 	key.type = key_type;
 	key.objectid = iobjectid;
 	key.offset = ioff;
 
-	if (found_path == NULL) {
-		path = btrfs_alloc_path();
-		if (!path)
-			return -ENOMEM;
-	} else
-		path = found_path;
-
 	ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0);
-	if ((ret < 0) || (found_key == NULL)) {
-		if (path != found_path)
-			btrfs_free_path(path);
+	if (ret < 0)
 		return ret;
-	}
 
 	eb = path->nodes[0];
 	if (ret && path->slots[0] >= btrfs_header_nritems(eb)) {
@@ -3383,7 +3380,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 	add_root_to_dirty_list(root);
 	extent_buffer_get(c);
 	path->nodes[level] = c;
-	path->locks[level] = BTRFS_WRITE_LOCK;
+	path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 	path->slots[level] = 0;
 	return 0;
 }
@@ -4356,13 +4353,15 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans,
 	path->search_for_split = 1;
 	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
 	path->search_for_split = 0;
+	if (ret > 0)
+		ret = -EAGAIN;
 	if (ret < 0)
 		goto err;
 
 	ret = -EAGAIN;
 	leaf = path->nodes[0];
-	/* if our item isn't there or got smaller, return now */
-	if (ret > 0 || item_size != btrfs_item_size_nr(leaf, path->slots[0]))
+	/* if our item isn't there, return now */
+	if (item_size != btrfs_item_size_nr(leaf, path->slots[0]))
 		goto err;
 
 	/* the leaf has  changed, it now has room.  return now */
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0b180708bf79..f9c89cae39ee 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -198,6 +198,8 @@ static int btrfs_csum_sizes[] = { 4, 0 };
 
 #define BTRFS_DIRTY_METADATA_THRESH	(32 * 1024 * 1024)
 
+#define BTRFS_MAX_EXTENT_SIZE (128 * 1024 * 1024)
+
 /*
  * The key defines the order in the tree, and so it also defines (optimal)
  * block layout.
@@ -1020,6 +1022,9 @@ enum btrfs_raid_types {
 					 BTRFS_BLOCK_GROUP_RAID6 |   \
 					 BTRFS_BLOCK_GROUP_DUP |     \
 					 BTRFS_BLOCK_GROUP_RAID10)
+#define BTRFS_BLOCK_GROUP_RAID56_MASK	(BTRFS_BLOCK_GROUP_RAID5 |   \
+					 BTRFS_BLOCK_GROUP_RAID6)
+
 /*
  * We need a bit for restriper to be able to tell when chunks of type
  * SINGLE are available.  This "extended" profile format is used in
@@ -1239,7 +1244,6 @@ enum btrfs_disk_cache_state {
 	BTRFS_DC_ERROR		= 1,
 	BTRFS_DC_CLEAR		= 2,
 	BTRFS_DC_SETUP		= 3,
-	BTRFS_DC_NEED_WRITE	= 4,
 };
 
 struct btrfs_caching_control {
@@ -1277,7 +1281,6 @@ struct btrfs_block_group_cache {
 	unsigned long full_stripe_len;
 
 	unsigned int ro:1;
-	unsigned int dirty:1;
 	unsigned int iref:1;
 	unsigned int has_caching_ctl:1;
 	unsigned int removed:1;
@@ -1315,6 +1318,9 @@ struct btrfs_block_group_cache {
 	struct list_head ro_list;
 
 	atomic_t trimming;
+
+	/* For dirty block groups */
+	struct list_head dirty_list;
 };
 
 /* delayed seq elem */
@@ -1741,6 +1747,7 @@ struct btrfs_fs_info {
 
 	spinlock_t unused_bgs_lock;
 	struct list_head unused_bgs;
+	struct mutex unused_bg_unpin_mutex;
 
 	/* For btrfs to record security options */
 	struct security_mnt_opts security_opts;
@@ -1776,6 +1783,7 @@ struct btrfs_subvolume_writers {
 #define BTRFS_ROOT_DEFRAG_RUNNING	6
 #define BTRFS_ROOT_FORCE_COW		7
 #define BTRFS_ROOT_MULTI_LOG_TASKS	8
+#define BTRFS_ROOT_DIRTY		9
 
 /*
  * in ram representation of the tree.  extent_root is used for all allocations
@@ -1794,8 +1802,6 @@ struct btrfs_root {
 	struct btrfs_fs_info *fs_info;
 	struct extent_io_tree dirty_log_pages;
 
-	struct kobject root_kobj;
-	struct completion kobj_unregister;
 	struct mutex objectid_mutex;
 
 	spinlock_t accounting_lock;
@@ -2465,31 +2471,6 @@ BTRFS_SETGET_STACK_FUNCS(stack_inode_gid, struct btrfs_inode_item, gid, 32);
 BTRFS_SETGET_STACK_FUNCS(stack_inode_mode, struct btrfs_inode_item, mode, 32);
 BTRFS_SETGET_STACK_FUNCS(stack_inode_rdev, struct btrfs_inode_item, rdev, 64);
 BTRFS_SETGET_STACK_FUNCS(stack_inode_flags, struct btrfs_inode_item, flags, 64);
-
-static inline struct btrfs_timespec *
-btrfs_inode_atime(struct btrfs_inode_item *inode_item)
-{
-	unsigned long ptr = (unsigned long)inode_item;
-	ptr += offsetof(struct btrfs_inode_item, atime);
-	return (struct btrfs_timespec *)ptr;
-}
-
-static inline struct btrfs_timespec *
-btrfs_inode_mtime(struct btrfs_inode_item *inode_item)
-{
-	unsigned long ptr = (unsigned long)inode_item;
-	ptr += offsetof(struct btrfs_inode_item, mtime);
-	return (struct btrfs_timespec *)ptr;
-}
-
-static inline struct btrfs_timespec *
-btrfs_inode_ctime(struct btrfs_inode_item *inode_item)
-{
-	unsigned long ptr = (unsigned long)inode_item;
-	ptr += offsetof(struct btrfs_inode_item, ctime);
-	return (struct btrfs_timespec *)ptr;
-}
-
 BTRFS_SETGET_FUNCS(timespec_sec, struct btrfs_timespec, sec, 64);
 BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32);
 BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64);
@@ -3406,6 +3387,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 				    struct btrfs_root *root);
+int btrfs_setup_space_cache(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root);
 int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr);
 int btrfs_free_block_groups(struct btrfs_fs_info *info);
 int btrfs_read_block_groups(struct btrfs_root *root);
@@ -3928,6 +3911,9 @@ int btrfs_prealloc_file_range_trans(struct inode *inode,
 				    loff_t actual_len, u64 *alloc_hint);
 int btrfs_inode_check_errors(struct inode *inode);
 extern const struct dentry_operations btrfs_dentry_operations;
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode);
+#endif
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index de4e70fb3cbb..82f0c7c95474 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1755,27 +1755,31 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_inode_flags(inode_item, BTRFS_I(inode)->flags);
 	btrfs_set_stack_inode_block_group(inode_item, 0);
 
-	btrfs_set_stack_timespec_sec(btrfs_inode_atime(inode_item),
+	btrfs_set_stack_timespec_sec(&inode_item->atime,
 				     inode->i_atime.tv_sec);
-	btrfs_set_stack_timespec_nsec(btrfs_inode_atime(inode_item),
+	btrfs_set_stack_timespec_nsec(&inode_item->atime,
 				      inode->i_atime.tv_nsec);
 
-	btrfs_set_stack_timespec_sec(btrfs_inode_mtime(inode_item),
+	btrfs_set_stack_timespec_sec(&inode_item->mtime,
 				     inode->i_mtime.tv_sec);
-	btrfs_set_stack_timespec_nsec(btrfs_inode_mtime(inode_item),
+	btrfs_set_stack_timespec_nsec(&inode_item->mtime,
 				      inode->i_mtime.tv_nsec);
 
-	btrfs_set_stack_timespec_sec(btrfs_inode_ctime(inode_item),
+	btrfs_set_stack_timespec_sec(&inode_item->ctime,
 				     inode->i_ctime.tv_sec);
-	btrfs_set_stack_timespec_nsec(btrfs_inode_ctime(inode_item),
+	btrfs_set_stack_timespec_nsec(&inode_item->ctime,
 				      inode->i_ctime.tv_nsec);
+
+	btrfs_set_stack_timespec_sec(&inode_item->otime,
+				     BTRFS_I(inode)->i_otime.tv_sec);
+	btrfs_set_stack_timespec_nsec(&inode_item->otime,
+				     BTRFS_I(inode)->i_otime.tv_nsec);
 }
 
 int btrfs_fill_inode(struct inode *inode, u32 *rdev)
 {
 	struct btrfs_delayed_node *delayed_node;
 	struct btrfs_inode_item *inode_item;
-	struct btrfs_timespec *tspec;
 
 	delayed_node = btrfs_get_delayed_node(inode);
 	if (!delayed_node)
@@ -1802,17 +1806,19 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
 	*rdev = btrfs_stack_inode_rdev(inode_item);
 	BTRFS_I(inode)->flags = btrfs_stack_inode_flags(inode_item);
 
-	tspec = btrfs_inode_atime(inode_item);
-	inode->i_atime.tv_sec = btrfs_stack_timespec_sec(tspec);
-	inode->i_atime.tv_nsec = btrfs_stack_timespec_nsec(tspec);
+	inode->i_atime.tv_sec = btrfs_stack_timespec_sec(&inode_item->atime);
+	inode->i_atime.tv_nsec = btrfs_stack_timespec_nsec(&inode_item->atime);
+
+	inode->i_mtime.tv_sec = btrfs_stack_timespec_sec(&inode_item->mtime);
+	inode->i_mtime.tv_nsec = btrfs_stack_timespec_nsec(&inode_item->mtime);
 
-	tspec = btrfs_inode_mtime(inode_item);
-	inode->i_mtime.tv_sec = btrfs_stack_timespec_sec(tspec);
-	inode->i_mtime.tv_nsec = btrfs_stack_timespec_nsec(tspec);
+	inode->i_ctime.tv_sec = btrfs_stack_timespec_sec(&inode_item->ctime);
+	inode->i_ctime.tv_nsec = btrfs_stack_timespec_nsec(&inode_item->ctime);
 
-	tspec = btrfs_inode_ctime(inode_item);
-	inode->i_ctime.tv_sec = btrfs_stack_timespec_sec(tspec);
-	inode->i_ctime.tv_nsec = btrfs_stack_timespec_nsec(tspec);
+	BTRFS_I(inode)->i_otime.tv_sec =
+		btrfs_stack_timespec_sec(&inode_item->otime);
+	BTRFS_I(inode)->i_otime.tv_nsec =
+		btrfs_stack_timespec_nsec(&inode_item->otime);
 
 	inode->i_generation = BTRFS_I(inode)->generation;
 	BTRFS_I(inode)->index_cnt = (u64)-1;
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index ca6a3a3b6b6c..5ec03d999c37 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -440,18 +440,9 @@ leave:
  */
 static void btrfs_rm_dev_replace_blocked(struct btrfs_fs_info *fs_info)
 {
-	s64 writers;
-	DEFINE_WAIT(wait);
-
 	set_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state);
-	do {
-		prepare_to_wait(&fs_info->replace_wait, &wait,
-				TASK_UNINTERRUPTIBLE);
-		writers = percpu_counter_sum(&fs_info->bio_counter);
-		if (writers)
-			schedule();
-		finish_wait(&fs_info->replace_wait, &wait);
-	} while (writers);
+	wait_event(fs_info->replace_wait, !percpu_counter_sum(
+		   &fs_info->bio_counter));
 }
 
 /*
@@ -932,15 +923,15 @@ void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount)
 
 void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info)
 {
-	DEFINE_WAIT(wait);
-again:
-	percpu_counter_inc(&fs_info->bio_counter);
-	if (test_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state)) {
+	while (1) {
+		percpu_counter_inc(&fs_info->bio_counter);
+		if (likely(!test_bit(BTRFS_FS_STATE_DEV_REPLACING,
+				     &fs_info->fs_state)))
+			break;
+
 		btrfs_bio_counter_dec(fs_info);
 		wait_event(fs_info->replace_wait,
 			   !test_bit(BTRFS_FS_STATE_DEV_REPLACING,
 				     &fs_info->fs_state));
-		goto again;
 	}
-
 }
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8c63419a7f70..639f2663ed3f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -318,7 +318,7 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
 			memcpy(&found, result, csum_size);
 
 			read_extent_buffer(buf, &val, 0, csum_size);
-			printk_ratelimited(KERN_INFO
+			printk_ratelimited(KERN_WARNING
 				"BTRFS: %s checksum verify failed on %llu wanted %X found %X "
 				"level %d\n",
 				root->fs_info->sb->s_id, buf->start,
@@ -367,7 +367,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 		ret = 0;
 		goto out;
 	}
-	printk_ratelimited(KERN_INFO "BTRFS (device %s): parent transid verify failed on %llu wanted %llu found %llu\n",
+	printk_ratelimited(KERN_ERR
+	    "BTRFS (device %s): parent transid verify failed on %llu wanted %llu found %llu\n",
 			eb->fs_info->sb->s_id, eb->start,
 			parent_transid, btrfs_header_generation(eb));
 	ret = 1;
@@ -633,21 +634,21 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != eb->start) {
-		printk_ratelimited(KERN_INFO "BTRFS (device %s): bad tree block start "
+		printk_ratelimited(KERN_ERR "BTRFS (device %s): bad tree block start "
 			       "%llu %llu\n",
 			       eb->fs_info->sb->s_id, found_start, eb->start);
 		ret = -EIO;
 		goto err;
 	}
 	if (check_tree_block_fsid(root, eb)) {
-		printk_ratelimited(KERN_INFO "BTRFS (device %s): bad fsid on block %llu\n",
+		printk_ratelimited(KERN_ERR "BTRFS (device %s): bad fsid on block %llu\n",
 			       eb->fs_info->sb->s_id, eb->start);
 		ret = -EIO;
 		goto err;
 	}
 	found_level = btrfs_header_level(eb);
 	if (found_level >= BTRFS_MAX_LEVEL) {
-		btrfs_info(root->fs_info, "bad tree block level %d",
+		btrfs_err(root->fs_info, "bad tree block level %d",
 			   (int)btrfs_header_level(eb));
 		ret = -EIO;
 		goto err;
@@ -1073,12 +1074,12 @@ static const struct address_space_operations btree_aops = {
 	.set_page_dirty = btree_set_page_dirty,
 };
 
-void readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize)
+void readahead_tree_block(struct btrfs_root *root, u64 bytenr)
 {
 	struct extent_buffer *buf = NULL;
 	struct inode *btree_inode = root->fs_info->btree_inode;
 
-	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
+	buf = btrfs_find_create_tree_block(root, bytenr);
 	if (!buf)
 		return;
 	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
@@ -1086,7 +1087,7 @@ void readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize)
 	free_extent_buffer(buf);
 }
 
-int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
+int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
 			 int mirror_num, struct extent_buffer **eb)
 {
 	struct extent_buffer *buf = NULL;
@@ -1094,7 +1095,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
 	struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree;
 	int ret;
 
-	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
+	buf = btrfs_find_create_tree_block(root, bytenr);
 	if (!buf)
 		return 0;
 
@@ -1125,12 +1126,11 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
 }
 
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
-						 u64 bytenr, u32 blocksize)
+						 u64 bytenr)
 {
 	if (btrfs_test_is_dummy_root(root))
-		return alloc_test_extent_buffer(root->fs_info, bytenr,
-						blocksize);
-	return alloc_extent_buffer(root->fs_info, bytenr, blocksize);
+		return alloc_test_extent_buffer(root->fs_info, bytenr);
+	return alloc_extent_buffer(root->fs_info, bytenr);
 }
 
 
@@ -1152,7 +1152,7 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
 	struct extent_buffer *buf = NULL;
 	int ret;
 
-	buf = btrfs_find_create_tree_block(root, bytenr, root->nodesize);
+	buf = btrfs_find_create_tree_block(root, bytenr);
 	if (!buf)
 		return NULL;
 
@@ -1275,12 +1275,10 @@ static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize,
 	memset(&root->root_key, 0, sizeof(root->root_key));
 	memset(&root->root_item, 0, sizeof(root->root_item));
 	memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
-	memset(&root->root_kobj, 0, sizeof(root->root_kobj));
 	if (fs_info)
 		root->defrag_trans_start = fs_info->generation;
 	else
 		root->defrag_trans_start = 0;
-	init_completion(&root->kobj_unregister);
 	root->root_key.objectid = objectid;
 	root->anon_dev = 0;
 
@@ -1630,6 +1628,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 				     bool check_ref)
 {
 	struct btrfs_root *root;
+	struct btrfs_path *path;
+	struct btrfs_key key;
 	int ret;
 
 	if (location->objectid == BTRFS_ROOT_TREE_OBJECTID)
@@ -1669,8 +1669,17 @@ again:
 	if (ret)
 		goto fail;
 
-	ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID,
-			location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL);
+	path = btrfs_alloc_path();
+	if (!path) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+	key.objectid = BTRFS_ORPHAN_OBJECTID;
+	key.type = BTRFS_ORPHAN_ITEM_KEY;
+	key.offset = location->objectid;
+
+	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
+	btrfs_free_path(path);
 	if (ret < 0)
 		goto fail;
 	if (ret == 0)
@@ -1715,12 +1724,11 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 {
 	int err;
 
-	bdi->capabilities = BDI_CAP_MAP_COPY;
-	err = bdi_setup_and_register(bdi, "btrfs", BDI_CAP_MAP_COPY);
+	err = bdi_setup_and_register(bdi, "btrfs");
 	if (err)
 		return err;
 
-	bdi->ra_pages	= default_backing_dev_info.ra_pages;
+	bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
 	bdi->congested_fn	= btrfs_congested_fn;
 	bdi->congested_data	= info;
 	return 0;
@@ -2233,6 +2241,7 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->qgroup_op_lock);
 	spin_lock_init(&fs_info->buffer_lock);
 	spin_lock_init(&fs_info->unused_bgs_lock);
+	mutex_init(&fs_info->unused_bg_unpin_mutex);
 	rwlock_init(&fs_info->tree_mod_log_lock);
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
@@ -2319,7 +2328,6 @@ int open_ctree(struct super_block *sb,
 	 */
 	fs_info->btree_inode->i_size = OFFSET_MAX;
 	fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
-	fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;
 
 	RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
 	extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
@@ -2498,7 +2506,7 @@ int open_ctree(struct super_block *sb,
 		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
 
 	if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
-		printk(KERN_ERR "BTRFS: has skinny extents\n");
+		printk(KERN_INFO "BTRFS: has skinny extents\n");
 
 	/*
 	 * flag our filesystem as having big metadata blocks if
@@ -2522,7 +2530,7 @@ int open_ctree(struct super_block *sb,
 	 */
 	if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
 	    (sectorsize != nodesize)) {
-		printk(KERN_WARNING "BTRFS: unequal leaf/node/sector sizes "
+		printk(KERN_ERR "BTRFS: unequal leaf/node/sector sizes "
 				"are not allowed for mixed block groups on %s\n",
 				sb->s_id);
 		goto fail_alloc;
@@ -2630,12 +2638,12 @@ int open_ctree(struct super_block *sb,
 	sb->s_blocksize_bits = blksize_bits(sectorsize);
 
 	if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
-		printk(KERN_INFO "BTRFS: valid FS not found on %s\n", sb->s_id);
+		printk(KERN_ERR "BTRFS: valid FS not found on %s\n", sb->s_id);
 		goto fail_sb_buffer;
 	}
 
 	if (sectorsize != PAGE_SIZE) {
-		printk(KERN_WARNING "BTRFS: Incompatible sector size(%lu) "
+		printk(KERN_ERR "BTRFS: incompatible sector size (%lu) "
 		       "found on %s\n", (unsigned long)sectorsize, sb->s_id);
 		goto fail_sb_buffer;
 	}
@@ -2644,7 +2652,7 @@ int open_ctree(struct super_block *sb,
 	ret = btrfs_read_sys_array(tree_root);
 	mutex_unlock(&fs_info->chunk_mutex);
 	if (ret) {
-		printk(KERN_WARNING "BTRFS: failed to read the system "
+		printk(KERN_ERR "BTRFS: failed to read the system "
 		       "array on %s\n", sb->s_id);
 		goto fail_sb_buffer;
 	}
@@ -2659,7 +2667,7 @@ int open_ctree(struct super_block *sb,
 					   generation);
 	if (!chunk_root->node ||
 	    !test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) {
-		printk(KERN_WARNING "BTRFS: failed to read chunk root on %s\n",
+		printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n",
 		       sb->s_id);
 		goto fail_tree_roots;
 	}
@@ -2671,7 +2679,7 @@ int open_ctree(struct super_block *sb,
 
 	ret = btrfs_read_chunk_tree(chunk_root);
 	if (ret) {
-		printk(KERN_WARNING "BTRFS: failed to read chunk tree on %s\n",
+		printk(KERN_ERR "BTRFS: failed to read chunk tree on %s\n",
 		       sb->s_id);
 		goto fail_tree_roots;
 	}
@@ -2683,7 +2691,7 @@ int open_ctree(struct super_block *sb,
 	btrfs_close_extra_devices(fs_info, fs_devices, 0);
 
 	if (!fs_devices->latest_bdev) {
-		printk(KERN_CRIT "BTRFS: failed to read devices on %s\n",
+		printk(KERN_ERR "BTRFS: failed to read devices on %s\n",
 		       sb->s_id);
 		goto fail_tree_roots;
 	}
@@ -2767,7 +2775,7 @@ retry_root_backup:
 
 	ret = btrfs_recover_balance(fs_info);
 	if (ret) {
-		printk(KERN_WARNING "BTRFS: failed to recover balance\n");
+		printk(KERN_ERR "BTRFS: failed to recover balance\n");
 		goto fail_block_groups;
 	}
 
@@ -3862,6 +3870,21 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 		printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
 				btrfs_super_log_root(sb));
 
+	/*
+	 * Check the lower bound, the alignment and other constraints are
+	 * checked later.
+	 */
+	if (btrfs_super_nodesize(sb) < 4096) {
+		printk(KERN_ERR "BTRFS: nodesize too small: %u < 4096\n",
+				btrfs_super_nodesize(sb));
+		ret = -EINVAL;
+	}
+	if (btrfs_super_sectorsize(sb) < 4096) {
+		printk(KERN_ERR "BTRFS: sectorsize too small: %u < 4096\n",
+				btrfs_super_sectorsize(sb));
+		ret = -EINVAL;
+	}
+
 	if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) {
 		printk(KERN_ERR "BTRFS: dev_item UUID does not match fsid: %pU != %pU\n",
 				fs_info->fsid, sb->dev_item.fsid);
@@ -3875,6 +3898,10 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	if (btrfs_super_num_devices(sb) > (1UL << 31))
 		printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
 				btrfs_super_num_devices(sb));
+	if (btrfs_super_num_devices(sb) == 0) {
+		printk(KERN_ERR "BTRFS: number of devices is 0\n");
+		ret = -EINVAL;
+	}
 
 	if (btrfs_super_bytenr(sb) != BTRFS_SUPER_INFO_OFFSET) {
 		printk(KERN_ERR "BTRFS: super offset mismatch %llu != %u\n",
@@ -3883,6 +3910,25 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	}
 
 	/*
+	 * Obvious sys_chunk_array corruptions, it must hold at least one key
+	 * and one chunk
+	 */
+	if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
+		printk(KERN_ERR "BTRFS: system chunk array too big %u > %u\n",
+				btrfs_super_sys_array_size(sb),
+				BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
+		ret = -EINVAL;
+	}
+	if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
+			+ sizeof(struct btrfs_chunk)) {
+		printk(KERN_ERR "BTRFS: system chunk array too small %u < %zu\n",
+				btrfs_super_sys_array_size(sb),
+				sizeof(struct btrfs_disk_key)
+				+ sizeof(struct btrfs_chunk));
+		ret = -EINVAL;
+	}
+
+	/*
 	 * The generation is a global counter, we'll trust it more than the others
 	 * but it's still possible that it's the one that's wrong.
 	 */
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 414651821fb3..27d44c0fd236 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -46,11 +46,11 @@ struct btrfs_fs_devices;
 
 struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
 				      u64 parent_transid);
-void readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize);
-int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
+void readahead_tree_block(struct btrfs_root *root, u64 bytenr);
+int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
 			 int mirror_num, struct extent_buffer **eb);
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
-						   u64 bytenr, u32 blocksize);
+						   u64 bytenr);
 void clean_tree_block(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root, struct extent_buffer *buf);
 int open_ctree(struct super_block *sb,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a684086c3c81..8b353ad02f03 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -74,8 +74,9 @@ enum {
 	RESERVE_ALLOC_NO_ACCOUNT = 2,
 };
 
-static int update_block_group(struct btrfs_root *root,
-			      u64 bytenr, u64 num_bytes, int alloc);
+static int update_block_group(struct btrfs_trans_handle *trans,
+			      struct btrfs_root *root, u64 bytenr,
+			      u64 num_bytes, int alloc);
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
 				u64 bytenr, u64 num_bytes, u64 parent,
@@ -1925,7 +1926,7 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 			 */
 			ret = 0;
 		}
-		kfree(bbio);
+		btrfs_put_bbio(bbio);
 	}
 
 	if (actual_bytes)
@@ -2768,7 +2769,6 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_head *head;
 	int ret;
 	int run_all = count == (unsigned long)-1;
-	int run_most = 0;
 
 	/* We'll clean this up in btrfs_cleanup_transaction */
 	if (trans->aborted)
@@ -2778,10 +2778,8 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		root = root->fs_info->tree_root;
 
 	delayed_refs = &trans->transaction->delayed_refs;
-	if (count == 0) {
+	if (count == 0)
 		count = atomic_read(&delayed_refs->num_entries) * 2;
-		run_most = 1;
-	}
 
 again:
 #ifdef SCRAMBLE_DELAYED_REFS
@@ -3210,6 +3208,8 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 		return 0;
 	}
 
+	if (trans->aborted)
+		return 0;
 again:
 	inode = lookup_free_space_inode(root, block_group, path);
 	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
@@ -3245,6 +3245,20 @@ again:
 	 */
 	BTRFS_I(inode)->generation = 0;
 	ret = btrfs_update_inode(trans, root, inode);
+	if (ret) {
+		/*
+		 * So theoretically we could recover from this, simply set the
+		 * super cache generation to 0 so we know to invalidate the
+		 * cache, but then we'd have to keep track of the block groups
+		 * that fail this way so we know we _have_ to reset this cache
+		 * before the next commit or risk reading stale cache.  So to
+		 * limit our exposure to horrible edge cases lets just abort the
+		 * transaction, this only happens in really bad situations
+		 * anyway.
+		 */
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_put;
+	}
 	WARN_ON(ret);
 
 	if (i_size_read(inode) > 0) {
@@ -3311,124 +3325,72 @@ out:
 	return ret;
 }
 
-int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
-				   struct btrfs_root *root)
+int btrfs_setup_space_cache(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root)
 {
-	struct btrfs_block_group_cache *cache;
-	int err = 0;
+	struct btrfs_block_group_cache *cache, *tmp;
+	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_path *path;
-	u64 last = 0;
+
+	if (list_empty(&cur_trans->dirty_bgs) ||
+	    !btrfs_test_opt(root, SPACE_CACHE))
+		return 0;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
-again:
-	while (1) {
-		cache = btrfs_lookup_first_block_group(root->fs_info, last);
-		while (cache) {
-			if (cache->disk_cache_state == BTRFS_DC_CLEAR)
-				break;
-			cache = next_block_group(root, cache);
-		}
-		if (!cache) {
-			if (last == 0)
-				break;
-			last = 0;
-			continue;
-		}
-		err = cache_save_setup(cache, trans, path);
-		last = cache->key.objectid + cache->key.offset;
-		btrfs_put_block_group(cache);
+	/* Could add new block groups, use _safe just in case */
+	list_for_each_entry_safe(cache, tmp, &cur_trans->dirty_bgs,
+				 dirty_list) {
+		if (cache->disk_cache_state == BTRFS_DC_CLEAR)
+			cache_save_setup(cache, trans, path);
 	}
 
-	while (1) {
-		if (last == 0) {
-			err = btrfs_run_delayed_refs(trans, root,
-						     (unsigned long)-1);
-			if (err) /* File system offline */
-				goto out;
-		}
-
-		cache = btrfs_lookup_first_block_group(root->fs_info, last);
-		while (cache) {
-			if (cache->disk_cache_state == BTRFS_DC_CLEAR) {
-				btrfs_put_block_group(cache);
-				goto again;
-			}
-
-			if (cache->dirty)
-				break;
-			cache = next_block_group(root, cache);
-		}
-		if (!cache) {
-			if (last == 0)
-				break;
-			last = 0;
-			continue;
-		}
-
-		if (cache->disk_cache_state == BTRFS_DC_SETUP)
-			cache->disk_cache_state = BTRFS_DC_NEED_WRITE;
-		cache->dirty = 0;
-		last = cache->key.objectid + cache->key.offset;
-
-		err = write_one_cache_group(trans, root, path, cache);
-		btrfs_put_block_group(cache);
-		if (err) /* File system offline */
-			goto out;
-	}
+	btrfs_free_path(path);
+	return 0;
+}
 
-	while (1) {
-		/*
-		 * I don't think this is needed since we're just marking our
-		 * preallocated extent as written, but just in case it can't
-		 * hurt.
-		 */
-		if (last == 0) {
-			err = btrfs_run_delayed_refs(trans, root,
-						     (unsigned long)-1);
-			if (err) /* File system offline */
-				goto out;
-		}
+int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root)
+{
+	struct btrfs_block_group_cache *cache;
+	struct btrfs_transaction *cur_trans = trans->transaction;
+	int ret = 0;
+	struct btrfs_path *path;
 
-		cache = btrfs_lookup_first_block_group(root->fs_info, last);
-		while (cache) {
-			/*
-			 * Really this shouldn't happen, but it could if we
-			 * couldn't write the entire preallocated extent and
-			 * splitting the extent resulted in a new block.
-			 */
-			if (cache->dirty) {
-				btrfs_put_block_group(cache);
-				goto again;
-			}
-			if (cache->disk_cache_state == BTRFS_DC_NEED_WRITE)
-				break;
-			cache = next_block_group(root, cache);
-		}
-		if (!cache) {
-			if (last == 0)
-				break;
-			last = 0;
-			continue;
-		}
+	if (list_empty(&cur_trans->dirty_bgs))
+		return 0;
 
-		err = btrfs_write_out_cache(root, trans, cache, path);
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
 
-		/*
-		 * If we didn't have an error then the cache state is still
-		 * NEED_WRITE, so we can set it to WRITTEN.
-		 */
-		if (!err && cache->disk_cache_state == BTRFS_DC_NEED_WRITE)
-			cache->disk_cache_state = BTRFS_DC_WRITTEN;
-		last = cache->key.objectid + cache->key.offset;
+	/*
+	 * We don't need the lock here since we are protected by the transaction
+	 * commit.  We want to do the cache_save_setup first and then run the
+	 * delayed refs to make sure we have the best chance at doing this all
+	 * in one shot.
+	 */
+	while (!list_empty(&cur_trans->dirty_bgs)) {
+		cache = list_first_entry(&cur_trans->dirty_bgs,
+					 struct btrfs_block_group_cache,
+					 dirty_list);
+		list_del_init(&cache->dirty_list);
+		if (cache->disk_cache_state == BTRFS_DC_CLEAR)
+			cache_save_setup(cache, trans, path);
+		if (!ret)
+			ret = btrfs_run_delayed_refs(trans, root,
+						     (unsigned long) -1);
+		if (!ret && cache->disk_cache_state == BTRFS_DC_SETUP)
+			btrfs_write_out_cache(root, trans, cache, path);
+		if (!ret)
+			ret = write_one_cache_group(trans, root, path, cache);
 		btrfs_put_block_group(cache);
 	}
-out:
 
 	btrfs_free_path(path);
-	return err;
+	return ret;
 }
 
 int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr)
@@ -5043,19 +5005,25 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root,
 /**
  * drop_outstanding_extent - drop an outstanding extent
  * @inode: the inode we're dropping the extent for
+ * @num_bytes: the number of bytes we're relaseing.
  *
  * This is called when we are freeing up an outstanding extent, either called
  * after an error or after an extent is written.  This will return the number of
  * reserved extents that need to be freed.  This must be called with
  * BTRFS_I(inode)->lock held.
  */
-static unsigned drop_outstanding_extent(struct inode *inode)
+static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes)
 {
 	unsigned drop_inode_space = 0;
 	unsigned dropped_extents = 0;
+	unsigned num_extents = 0;
 
-	BUG_ON(!BTRFS_I(inode)->outstanding_extents);
-	BTRFS_I(inode)->outstanding_extents--;
+	num_extents = (unsigned)div64_u64(num_bytes +
+					  BTRFS_MAX_EXTENT_SIZE - 1,
+					  BTRFS_MAX_EXTENT_SIZE);
+	ASSERT(num_extents);
+	ASSERT(BTRFS_I(inode)->outstanding_extents >= num_extents);
+	BTRFS_I(inode)->outstanding_extents -= num_extents;
 
 	if (BTRFS_I(inode)->outstanding_extents == 0 &&
 	    test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
@@ -5168,7 +5136,11 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	num_bytes = ALIGN(num_bytes, root->sectorsize);
 
 	spin_lock(&BTRFS_I(inode)->lock);
-	BTRFS_I(inode)->outstanding_extents++;
+	nr_extents = (unsigned)div64_u64(num_bytes +
+					 BTRFS_MAX_EXTENT_SIZE - 1,
+					 BTRFS_MAX_EXTENT_SIZE);
+	BTRFS_I(inode)->outstanding_extents += nr_extents;
+	nr_extents = 0;
 
 	if (BTRFS_I(inode)->outstanding_extents >
 	    BTRFS_I(inode)->reserved_extents)
@@ -5226,7 +5198,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 
 out_fail:
 	spin_lock(&BTRFS_I(inode)->lock);
-	dropped = drop_outstanding_extent(inode);
+	dropped = drop_outstanding_extent(inode, num_bytes);
 	/*
 	 * If the inodes csum_bytes is the same as the original
 	 * csum_bytes then we know we haven't raced with any free()ers
@@ -5305,7 +5277,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
 
 	num_bytes = ALIGN(num_bytes, root->sectorsize);
 	spin_lock(&BTRFS_I(inode)->lock);
-	dropped = drop_outstanding_extent(inode);
+	dropped = drop_outstanding_extent(inode, num_bytes);
 
 	if (num_bytes)
 		to_free = calc_csum_metadata_size(inode, num_bytes, 0);
@@ -5313,6 +5285,9 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
 	if (dropped > 0)
 		to_free += btrfs_calc_trans_metadata_size(root, dropped);
 
+	if (btrfs_test_is_dummy_root(root))
+		return;
+
 	trace_btrfs_space_reservation(root->fs_info, "delalloc",
 				      btrfs_ino(inode), to_free, 0);
 	if (root->fs_info->quota_enabled) {
@@ -5375,8 +5350,9 @@ void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes)
 	btrfs_free_reserved_data_space(inode, num_bytes);
 }
 
-static int update_block_group(struct btrfs_root *root,
-			      u64 bytenr, u64 num_bytes, int alloc)
+static int update_block_group(struct btrfs_trans_handle *trans,
+			      struct btrfs_root *root, u64 bytenr,
+			      u64 num_bytes, int alloc)
 {
 	struct btrfs_block_group_cache *cache = NULL;
 	struct btrfs_fs_info *info = root->fs_info;
@@ -5414,6 +5390,14 @@ static int update_block_group(struct btrfs_root *root,
 		if (!alloc && cache->cached == BTRFS_CACHE_NO)
 			cache_block_group(cache, 1);
 
+		spin_lock(&trans->transaction->dirty_bgs_lock);
+		if (list_empty(&cache->dirty_list)) {
+			list_add_tail(&cache->dirty_list,
+				      &trans->transaction->dirty_bgs);
+			btrfs_get_block_group(cache);
+		}
+		spin_unlock(&trans->transaction->dirty_bgs_lock);
+
 		byte_in_group = bytenr - cache->key.objectid;
 		WARN_ON(byte_in_group > cache->key.offset);
 
@@ -5424,7 +5408,6 @@ static int update_block_group(struct btrfs_root *root,
 		    cache->disk_cache_state < BTRFS_DC_CLEAR)
 			cache->disk_cache_state = BTRFS_DC_CLEAR;
 
-		cache->dirty = 1;
 		old_val = btrfs_block_group_used(&cache->item);
 		num_bytes = min(total, cache->key.offset - byte_in_group);
 		if (alloc) {
@@ -5807,10 +5790,13 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 		unpin = &fs_info->freed_extents[0];
 
 	while (1) {
+		mutex_lock(&fs_info->unused_bg_unpin_mutex);
 		ret = find_first_extent_bit(unpin, 0, &start, &end,
 					    EXTENT_DIRTY, NULL);
-		if (ret)
+		if (ret) {
+			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 			break;
+		}
 
 		if (btrfs_test_opt(root, DISCARD))
 			ret = btrfs_discard_extent(root, start,
@@ -5818,6 +5804,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
 		unpin_extent_range(root, start, end, true);
+		mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 		cond_resched();
 	}
 
@@ -6103,7 +6090,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			}
 		}
 
-		ret = update_block_group(root, bytenr, num_bytes, 0);
+		ret = update_block_group(trans, root, bytenr, num_bytes, 0);
 		if (ret) {
 			btrfs_abort_transaction(trans, extent_root, ret);
 			goto out;
@@ -6205,7 +6192,6 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			   struct extent_buffer *buf,
 			   u64 parent, int last_ref)
 {
-	struct btrfs_block_group_cache *cache = NULL;
 	int pin = 1;
 	int ret;
 
@@ -6221,17 +6207,20 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 	if (!last_ref)
 		return;
 
-	cache = btrfs_lookup_block_group(root->fs_info, buf->start);
-
 	if (btrfs_header_generation(buf) == trans->transid) {
+		struct btrfs_block_group_cache *cache;
+
 		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
 			ret = check_ref_cleanup(trans, root, buf->start);
 			if (!ret)
 				goto out;
 		}
 
+		cache = btrfs_lookup_block_group(root->fs_info, buf->start);
+
 		if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {
 			pin_down_extent(root, cache, buf->start, buf->len, 1);
+			btrfs_put_block_group(cache);
 			goto out;
 		}
 
@@ -6239,6 +6228,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 
 		btrfs_add_free_space(cache, buf->start, buf->len);
 		btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0);
+		btrfs_put_block_group(cache);
 		trace_btrfs_reserved_extent_free(root, buf->start, buf->len);
 		pin = 0;
 	}
@@ -6253,7 +6243,6 @@ out:
 	 * anymore.
 	 */
 	clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
-	btrfs_put_block_group(cache);
 }
 
 /* Can return -ENOMEM */
@@ -7063,7 +7052,7 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	if (ret)
 		return ret;
 
-	ret = update_block_group(root, ins->objectid, ins->offset, 1);
+	ret = update_block_group(trans, root, ins->objectid, ins->offset, 1);
 	if (ret) { /* -ENOENT, logic error */
 		btrfs_err(fs_info, "update block group failed for %llu %llu",
 			ins->objectid, ins->offset);
@@ -7152,7 +7141,8 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 			return ret;
 	}
 
-	ret = update_block_group(root, ins->objectid, root->nodesize, 1);
+	ret = update_block_group(trans, root, ins->objectid, root->nodesize,
+				 1);
 	if (ret) { /* -ENOENT, logic error */
 		btrfs_err(fs_info, "update block group failed for %llu %llu",
 			ins->objectid, ins->offset);
@@ -7217,11 +7207,11 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 
 static struct extent_buffer *
 btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		      u64 bytenr, u32 blocksize, int level)
+		      u64 bytenr, int level)
 {
 	struct extent_buffer *buf;
 
-	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
+	buf = btrfs_find_create_tree_block(root, bytenr);
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
 	btrfs_set_header_generation(buf, trans->transid);
@@ -7340,7 +7330,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 
 	if (btrfs_test_is_dummy_root(root)) {
 		buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr,
-					    blocksize, level);
+					    level);
 		if (!IS_ERR(buf))
 			root->alloc_bytenr += blocksize;
 		return buf;
@@ -7357,8 +7347,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		return ERR_PTR(ret);
 	}
 
-	buf = btrfs_init_new_buffer(trans, root, ins.objectid,
-				    blocksize, level);
+	buf = btrfs_init_new_buffer(trans, root, ins.objectid, level);
 	BUG_ON(IS_ERR(buf)); /* -ENOMEM */
 
 	if (root_objectid == BTRFS_TREE_RELOC_OBJECTID) {
@@ -7487,7 +7476,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
 				continue;
 		}
 reada:
-		readahead_tree_block(root, bytenr, blocksize);
+		readahead_tree_block(root, bytenr);
 		nread++;
 	}
 	wc->reada_slot = slot;
@@ -7828,7 +7817,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 
 	next = btrfs_find_tree_block(root, bytenr);
 	if (!next) {
-		next = btrfs_find_create_tree_block(root, bytenr, blocksize);
+		next = btrfs_find_create_tree_block(root, bytenr);
 		if (!next)
 			return -ENOMEM;
 		btrfs_set_buffer_lockdep_class(root->root_key.objectid, next,
@@ -8548,14 +8537,6 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	alloc_flags = update_block_group_flags(root, cache->flags);
-	if (alloc_flags != cache->flags) {
-		ret = do_chunk_alloc(trans, root, alloc_flags,
-				     CHUNK_ALLOC_FORCE);
-		if (ret < 0)
-			goto out;
-	}
-
 	ret = set_block_group_ro(cache, 0);
 	if (!ret)
 		goto out;
@@ -8566,6 +8547,11 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 		goto out;
 	ret = set_block_group_ro(cache, 0);
 out:
+	if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) {
+		alloc_flags = update_block_group_flags(root, cache->flags);
+		check_system_chunk(trans, root, alloc_flags);
+	}
+
 	btrfs_end_transaction(trans, root);
 	return ret;
 }
@@ -9005,6 +8991,7 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size)
 	INIT_LIST_HEAD(&cache->cluster_list);
 	INIT_LIST_HEAD(&cache->bg_list);
 	INIT_LIST_HEAD(&cache->ro_list);
+	INIT_LIST_HEAD(&cache->dirty_list);
 	btrfs_init_free_space_ctl(cache);
 	atomic_set(&cache->trimming, 0);
 
@@ -9068,9 +9055,8 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 			 * b) Setting 'dirty flag' makes sure that we flush
 			 *    the new space cache info onto disk.
 			 */
-			cache->disk_cache_state = BTRFS_DC_CLEAR;
 			if (btrfs_test_opt(root, SPACE_CACHE))
-				cache->dirty = 1;
+				cache->disk_cache_state = BTRFS_DC_CLEAR;
 		}
 
 		read_extent_buffer(leaf, &cache->item,
@@ -9460,6 +9446,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		}
 	}
 
+	spin_lock(&trans->transaction->dirty_bgs_lock);
+	if (!list_empty(&block_group->dirty_list)) {
+		list_del_init(&block_group->dirty_list);
+		btrfs_put_block_group(block_group);
+	}
+	spin_unlock(&trans->transaction->dirty_bgs_lock);
+
 	btrfs_remove_free_space_cache(block_group);
 
 	spin_lock(&block_group->space_info->lock);
@@ -9611,7 +9604,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * Want to do this before we do anything else so we can recover
 		 * properly if we fail to join the transaction.
 		 */
-		trans = btrfs_join_transaction(root);
+		/* 1 for btrfs_orphan_reserve_metadata() */
+		trans = btrfs_start_transaction(root, 1);
 		if (IS_ERR(trans)) {
 			btrfs_set_block_group_rw(root, block_group);
 			ret = PTR_ERR(trans);
@@ -9624,18 +9618,33 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 */
 		start = block_group->key.objectid;
 		end = start + block_group->key.offset - 1;
+		/*
+		 * Hold the unused_bg_unpin_mutex lock to avoid racing with
+		 * btrfs_finish_extent_commit(). If we are at transaction N,
+		 * another task might be running finish_extent_commit() for the
+		 * previous transaction N - 1, and have seen a range belonging
+		 * to the block group in freed_extents[] before we were able to
+		 * clear the whole block group range from freed_extents[]. This
+		 * means that task can lookup for the block group after we
+		 * unpinned it from freed_extents[] and removed it, leading to
+		 * a BUG_ON() at btrfs_unpin_extent_range().
+		 */
+		mutex_lock(&fs_info->unused_bg_unpin_mutex);
 		ret = clear_extent_bits(&fs_info->freed_extents[0], start, end,
 				  EXTENT_DIRTY, GFP_NOFS);
 		if (ret) {
+			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 			btrfs_set_block_group_rw(root, block_group);
 			goto end_trans;
 		}
 		ret = clear_extent_bits(&fs_info->freed_extents[1], start, end,
 				  EXTENT_DIRTY, GFP_NOFS);
 		if (ret) {
+			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 			btrfs_set_block_group_rw(root, block_group);
 			goto end_trans;
 		}
+		mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 
 		/* Reset pinned so btrfs_put_block_group doesn't complain */
 		block_group->pinned = 0;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 790dbae3343c..d688cfe5d496 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -64,7 +64,7 @@ void btrfs_leak_debug_check(void)
 
 	while (!list_empty(&states)) {
 		state = list_entry(states.next, struct extent_state, leak_list);
-		pr_err("BTRFS: state leak: start %llu end %llu state %lu in tree %d refs %d\n",
+		pr_err("BTRFS: state leak: start %llu end %llu state %u in tree %d refs %d\n",
 		       state->start, state->end, state->state,
 		       extent_state_in_tree(state),
 		       atomic_read(&state->refs));
@@ -396,21 +396,21 @@ static void merge_state(struct extent_io_tree *tree,
 }
 
 static void set_state_cb(struct extent_io_tree *tree,
-			 struct extent_state *state, unsigned long *bits)
+			 struct extent_state *state, unsigned *bits)
 {
 	if (tree->ops && tree->ops->set_bit_hook)
 		tree->ops->set_bit_hook(tree->mapping->host, state, bits);
 }
 
 static void clear_state_cb(struct extent_io_tree *tree,
-			   struct extent_state *state, unsigned long *bits)
+			   struct extent_state *state, unsigned *bits)
 {
 	if (tree->ops && tree->ops->clear_bit_hook)
 		tree->ops->clear_bit_hook(tree->mapping->host, state, bits);
 }
 
 static void set_state_bits(struct extent_io_tree *tree,
-			   struct extent_state *state, unsigned long *bits);
+			   struct extent_state *state, unsigned *bits);
 
 /*
  * insert an extent_state struct into the tree.  'bits' are set on the
@@ -426,7 +426,7 @@ static int insert_state(struct extent_io_tree *tree,
 			struct extent_state *state, u64 start, u64 end,
 			struct rb_node ***p,
 			struct rb_node **parent,
-			unsigned long *bits)
+			unsigned *bits)
 {
 	struct rb_node *node;
 
@@ -511,10 +511,10 @@ static struct extent_state *next_state(struct extent_state *state)
  */
 static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
 					    struct extent_state *state,
-					    unsigned long *bits, int wake)
+					    unsigned *bits, int wake)
 {
 	struct extent_state *next;
-	unsigned long bits_to_clear = *bits & ~EXTENT_CTLBITS;
+	unsigned bits_to_clear = *bits & ~EXTENT_CTLBITS;
 
 	if ((bits_to_clear & EXTENT_DIRTY) && (state->state & EXTENT_DIRTY)) {
 		u64 range = state->end - state->start + 1;
@@ -570,7 +570,7 @@ static void extent_io_tree_panic(struct extent_io_tree *tree, int err)
  * This takes the tree lock, and returns 0 on success and < 0 on error.
  */
 int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned long bits, int wake, int delete,
+		     unsigned bits, int wake, int delete,
 		     struct extent_state **cached_state,
 		     gfp_t mask)
 {
@@ -789,9 +789,9 @@ out:
 
 static void set_state_bits(struct extent_io_tree *tree,
 			   struct extent_state *state,
-			   unsigned long *bits)
+			   unsigned *bits)
 {
-	unsigned long bits_to_set = *bits & ~EXTENT_CTLBITS;
+	unsigned bits_to_set = *bits & ~EXTENT_CTLBITS;
 
 	set_state_cb(tree, state, bits);
 	if ((bits_to_set & EXTENT_DIRTY) && !(state->state & EXTENT_DIRTY)) {
@@ -803,7 +803,7 @@ static void set_state_bits(struct extent_io_tree *tree,
 
 static void cache_state_if_flags(struct extent_state *state,
 				 struct extent_state **cached_ptr,
-				 const u64 flags)
+				 unsigned flags)
 {
 	if (cached_ptr && !(*cached_ptr)) {
 		if (!flags || (state->state & flags)) {
@@ -833,7 +833,7 @@ static void cache_state(struct extent_state *state,
 
 static int __must_check
 __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		 unsigned long bits, unsigned long exclusive_bits,
+		 unsigned bits, unsigned exclusive_bits,
 		 u64 *failed_start, struct extent_state **cached_state,
 		 gfp_t mask)
 {
@@ -1034,7 +1034,7 @@ search_again:
 }
 
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   unsigned long bits, u64 * failed_start,
+		   unsigned bits, u64 * failed_start,
 		   struct extent_state **cached_state, gfp_t mask)
 {
 	return __set_extent_bit(tree, start, end, bits, 0, failed_start,
@@ -1060,7 +1060,7 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
  * boundary bits like LOCK.
  */
 int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		       unsigned long bits, unsigned long clear_bits,
+		       unsigned bits, unsigned clear_bits,
 		       struct extent_state **cached_state, gfp_t mask)
 {
 	struct extent_state *state;
@@ -1268,14 +1268,14 @@ int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
 }
 
 int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		    unsigned long bits, gfp_t mask)
+		    unsigned bits, gfp_t mask)
 {
 	return set_extent_bit(tree, start, end, bits, NULL,
 			      NULL, mask);
 }
 
 int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		      unsigned long bits, gfp_t mask)
+		      unsigned bits, gfp_t mask)
 {
 	return clear_extent_bit(tree, start, end, bits, 0, 0, NULL, mask);
 }
@@ -1330,10 +1330,11 @@ int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
  * us if waiting is desired.
  */
 int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned long bits, struct extent_state **cached_state)
+		     unsigned bits, struct extent_state **cached_state)
 {
 	int err;
 	u64 failed_start;
+
 	while (1) {
 		err = __set_extent_bit(tree, start, end, EXTENT_LOCKED | bits,
 				       EXTENT_LOCKED, &failed_start,
@@ -1407,8 +1408,8 @@ int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
 	while (index <= end_index) {
 		page = find_get_page(inode->i_mapping, index);
 		BUG_ON(!page); /* Pages should be in the extent_io_tree */
-		account_page_redirty(page);
 		__set_page_dirty_nobuffers(page);
+		account_page_redirty(page);
 		page_cache_release(page);
 		index++;
 	}
@@ -1440,7 +1441,7 @@ static int set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
  */
 static struct extent_state *
 find_first_extent_bit_state(struct extent_io_tree *tree,
-			    u64 start, unsigned long bits)
+			    u64 start, unsigned bits)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -1474,7 +1475,7 @@ out:
  * If nothing was found, 1 is returned. If found something, return 0.
  */
 int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
-			  u64 *start_ret, u64 *end_ret, unsigned long bits,
+			  u64 *start_ret, u64 *end_ret, unsigned bits,
 			  struct extent_state **cached_state)
 {
 	struct extent_state *state;
@@ -1753,7 +1754,7 @@ out_failed:
 
 int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 				 struct page *locked_page,
-				 unsigned long clear_bits,
+				 unsigned clear_bits,
 				 unsigned long page_ops)
 {
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
@@ -1810,7 +1811,7 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
  */
 u64 count_range_bits(struct extent_io_tree *tree,
 		     u64 *start, u64 search_end, u64 max_bytes,
-		     unsigned long bits, int contig)
+		     unsigned bits, int contig)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -1928,7 +1929,7 @@ out:
  * range is found set.
  */
 int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   unsigned long bits, int filled, struct extent_state *cached)
+		   unsigned bits, int filled, struct extent_state *cached)
 {
 	struct extent_state *state = NULL;
 	struct rb_node *node;
@@ -2057,7 +2058,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	sector = bbio->stripes[mirror_num-1].physical >> 9;
 	bio->bi_iter.bi_sector = sector;
 	dev = bbio->stripes[mirror_num-1].dev;
-	kfree(bbio);
+	btrfs_put_bbio(bbio);
 	if (!dev || !dev->bdev || !dev->writeable) {
 		bio_put(bio);
 		return -EIO;
@@ -2816,8 +2817,10 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 		    bio_add_page(bio, page, page_size, offset) < page_size) {
 			ret = submit_one_bio(rw, bio, mirror_num,
 					     prev_bio_flags);
-			if (ret < 0)
+			if (ret < 0) {
+				*bio_ret = NULL;
 				return ret;
+			}
 			bio = NULL;
 		} else {
 			return 0;
@@ -3239,7 +3242,7 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode,
 					       page,
 					       &delalloc_start,
 					       &delalloc_end,
-					       128 * 1024 * 1024);
+					       BTRFS_MAX_EXTENT_SIZE);
 		if (nr_delalloc == 0) {
 			delalloc_start = delalloc_end + 1;
 			continue;
@@ -4598,11 +4601,11 @@ static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
 
 static struct extent_buffer *
 __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
-		      unsigned long len, gfp_t mask)
+		      unsigned long len)
 {
 	struct extent_buffer *eb = NULL;
 
-	eb = kmem_cache_zalloc(extent_buffer_cache, mask);
+	eb = kmem_cache_zalloc(extent_buffer_cache, GFP_NOFS);
 	if (eb == NULL)
 		return NULL;
 	eb->start = start;
@@ -4643,7 +4646,7 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 	struct extent_buffer *new;
 	unsigned long num_pages = num_extent_pages(src->start, src->len);
 
-	new = __alloc_extent_buffer(NULL, src->start, src->len, GFP_NOFS);
+	new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
 	if (new == NULL)
 		return NULL;
 
@@ -4666,13 +4669,26 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 	return new;
 }
 
-struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len)
+struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
+						u64 start)
 {
 	struct extent_buffer *eb;
-	unsigned long num_pages = num_extent_pages(0, len);
+	unsigned long len;
+	unsigned long num_pages;
 	unsigned long i;
 
-	eb = __alloc_extent_buffer(NULL, start, len, GFP_NOFS);
+	if (!fs_info) {
+		/*
+		 * Called only from tests that don't always have a fs_info
+		 * available, but we know that nodesize is 4096
+		 */
+		len = 4096;
+	} else {
+		len = fs_info->tree_root->nodesize;
+	}
+	num_pages = num_extent_pages(0, len);
+
+	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
 		return NULL;
 
@@ -4762,7 +4778,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
-					       u64 start, unsigned long len)
+					       u64 start)
 {
 	struct extent_buffer *eb, *exists = NULL;
 	int ret;
@@ -4770,7 +4786,7 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
 	eb = find_extent_buffer(fs_info, start);
 	if (eb)
 		return eb;
-	eb = alloc_dummy_extent_buffer(start, len);
+	eb = alloc_dummy_extent_buffer(fs_info, start);
 	if (!eb)
 		return NULL;
 	eb->fs_info = fs_info;
@@ -4808,8 +4824,9 @@ free_eb:
 #endif
 
 struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
-					  u64 start, unsigned long len)
+					  u64 start)
 {
+	unsigned long len = fs_info->tree_root->nodesize;
 	unsigned long num_pages = num_extent_pages(start, len);
 	unsigned long i;
 	unsigned long index = start >> PAGE_CACHE_SHIFT;
@@ -4824,7 +4841,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	if (eb)
 		return eb;
 
-	eb = __alloc_extent_buffer(fs_info, start, len, GFP_NOFS);
+	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
 		return NULL;
 
@@ -4951,6 +4968,12 @@ static int release_extent_buffer(struct extent_buffer *eb)
 
 		/* Should be safe to release our pages at this point */
 		btrfs_release_extent_buffer_page(eb);
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+		if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))) {
+			__free_extent_buffer(eb);
+			return 1;
+		}
+#endif
 		call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
 		return 1;
 	}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index ece9ce87edff..695b0ccfb755 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -4,22 +4,22 @@
 #include <linux/rbtree.h>
 
 /* bits for the extent state */
-#define EXTENT_DIRTY 1
-#define EXTENT_WRITEBACK (1 << 1)
-#define EXTENT_UPTODATE (1 << 2)
-#define EXTENT_LOCKED (1 << 3)
-#define EXTENT_NEW (1 << 4)
-#define EXTENT_DELALLOC (1 << 5)
-#define EXTENT_DEFRAG (1 << 6)
-#define EXTENT_BOUNDARY (1 << 9)
-#define EXTENT_NODATASUM (1 << 10)
-#define EXTENT_DO_ACCOUNTING (1 << 11)
-#define EXTENT_FIRST_DELALLOC (1 << 12)
-#define EXTENT_NEED_WAIT (1 << 13)
-#define EXTENT_DAMAGED (1 << 14)
-#define EXTENT_NORESERVE (1 << 15)
-#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
-#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
+#define EXTENT_DIRTY		(1U << 0)
+#define EXTENT_WRITEBACK	(1U << 1)
+#define EXTENT_UPTODATE		(1U << 2)
+#define EXTENT_LOCKED		(1U << 3)
+#define EXTENT_NEW		(1U << 4)
+#define EXTENT_DELALLOC		(1U << 5)
+#define EXTENT_DEFRAG		(1U << 6)
+#define EXTENT_BOUNDARY		(1U << 9)
+#define EXTENT_NODATASUM	(1U << 10)
+#define EXTENT_DO_ACCOUNTING	(1U << 11)
+#define EXTENT_FIRST_DELALLOC	(1U << 12)
+#define EXTENT_NEED_WAIT	(1U << 13)
+#define EXTENT_DAMAGED		(1U << 14)
+#define EXTENT_NORESERVE	(1U << 15)
+#define EXTENT_IOBITS		(EXTENT_LOCKED | EXTENT_WRITEBACK)
+#define EXTENT_CTLBITS		(EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
 
 /*
  * flags for bio submission. The high bits indicate the compression
@@ -81,9 +81,9 @@ struct extent_io_ops {
 	int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
 				      struct extent_state *state, int uptodate);
 	void (*set_bit_hook)(struct inode *inode, struct extent_state *state,
-			     unsigned long *bits);
+			     unsigned *bits);
 	void (*clear_bit_hook)(struct inode *inode, struct extent_state *state,
-			       unsigned long *bits);
+			       unsigned *bits);
 	void (*merge_extent_hook)(struct inode *inode,
 				  struct extent_state *new,
 				  struct extent_state *other);
@@ -108,7 +108,7 @@ struct extent_state {
 	/* ADD NEW ELEMENTS AFTER THIS */
 	wait_queue_head_t wq;
 	atomic_t refs;
-	unsigned long state;
+	unsigned state;
 
 	/* for use by the FS */
 	u64 private;
@@ -188,7 +188,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 int try_release_extent_buffer(struct page *page);
 int lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned long bits, struct extent_state **cached);
+		     unsigned bits, struct extent_state **cached);
 int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end,
 			 struct extent_state **cached, gfp_t mask);
@@ -202,21 +202,21 @@ void extent_io_exit(void);
 
 u64 count_range_bits(struct extent_io_tree *tree,
 		     u64 *start, u64 search_end,
-		     u64 max_bytes, unsigned long bits, int contig);
+		     u64 max_bytes, unsigned bits, int contig);
 
 void free_extent_state(struct extent_state *state);
 int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   unsigned long bits, int filled,
+		   unsigned bits, int filled,
 		   struct extent_state *cached_state);
 int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		      unsigned long bits, gfp_t mask);
+		      unsigned bits, gfp_t mask);
 int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned long bits, int wake, int delete,
+		     unsigned bits, int wake, int delete,
 		     struct extent_state **cached, gfp_t mask);
 int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		    unsigned long bits, gfp_t mask);
+		    unsigned bits, gfp_t mask);
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   unsigned long bits, u64 *failed_start,
+		   unsigned bits, u64 *failed_start,
 		   struct extent_state **cached_state, gfp_t mask);
 int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
 			struct extent_state **cached_state, gfp_t mask);
@@ -229,14 +229,14 @@ int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
 int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
 		       gfp_t mask);
 int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		       unsigned long bits, unsigned long clear_bits,
+		       unsigned bits, unsigned clear_bits,
 		       struct extent_state **cached_state, gfp_t mask);
 int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
 			struct extent_state **cached_state, gfp_t mask);
 int set_extent_defrag(struct extent_io_tree *tree, u64 start, u64 end,
 		      struct extent_state **cached_state, gfp_t mask);
 int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
-			  u64 *start_ret, u64 *end_ret, unsigned long bits,
+			  u64 *start_ret, u64 *end_ret, unsigned bits,
 			  struct extent_state **cached_state);
 int extent_invalidatepage(struct extent_io_tree *tree,
 			  struct page *page, unsigned long offset);
@@ -262,8 +262,9 @@ int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private);
 void set_page_extent_mapped(struct page *page);
 
 struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
-					  u64 start, unsigned long len);
-struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len);
+					  u64 start);
+struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
+		u64 start);
 struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src);
 struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 					 u64 start);
@@ -322,7 +323,7 @@ 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,
 				 struct page *locked_page,
-				 unsigned long bits_to_clear,
+				 unsigned bits_to_clear,
 				 unsigned long page_ops);
 struct bio *
 btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
@@ -377,5 +378,5 @@ noinline u64 find_lock_delalloc_range(struct inode *inode,
 				      u64 *end, u64 max_bytes);
 #endif
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
-					       u64 start, unsigned long len);
+					       u64 start);
 #endif
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e4090259569b..30982bbd31c3 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1746,7 +1746,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 
 	mutex_lock(&inode->i_mutex);
 
-	current->backing_dev_info = inode->i_mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err) {
 		mutex_unlock(&inode->i_mutex);
@@ -1811,22 +1811,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	mutex_unlock(&inode->i_mutex);
 
 	/*
-	 * we want to make sure fsync finds this change
-	 * but we haven't joined a transaction running right now.
-	 *
-	 * Later on, someone is sure to update the inode and get the
-	 * real transid recorded.
-	 *
-	 * We set last_trans now to the fs_info generation + 1,
-	 * this will either be one more than the running transaction
-	 * or the generation used for the next transaction if there isn't
-	 * one running right now.
-	 *
 	 * We also have to set last_sub_trans to the current log transid,
 	 * otherwise subsequent syncs to a file that's been synced in this
 	 * transaction will appear to have already occured.
 	 */
-	BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
 	if (num_written > 0) {
 		err = generic_write_sync(file, pos, num_written);
@@ -1959,25 +1947,37 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	atomic_inc(&root->log_batch);
 
 	/*
-	 * check the transaction that last modified this inode
-	 * and see if its already been committed
-	 */
-	if (!BTRFS_I(inode)->last_trans) {
-		mutex_unlock(&inode->i_mutex);
-		goto out;
-	}
-
-	/*
-	 * if the last transaction that changed this file was before
-	 * the current transaction, we can bail out now without any
-	 * syncing
+	 * If the last transaction that changed this file was before the current
+	 * transaction and we have the full sync flag set in our inode, we can
+	 * bail out now without any syncing.
+	 *
+	 * Note that we can't bail out if the full sync flag isn't set. This is
+	 * because when the full sync flag is set we start all ordered extents
+	 * and wait for them to fully complete - when they complete they update
+	 * the inode's last_trans field through:
+	 *
+	 *     btrfs_finish_ordered_io() ->
+	 *         btrfs_update_inode_fallback() ->
+	 *             btrfs_update_inode() ->
+	 *                 btrfs_set_inode_last_trans()
+	 *
+	 * So we are sure that last_trans is up to date and can do this check to
+	 * bail out safely. For the fast path, when the full sync flag is not
+	 * set in our inode, we can not do it because we start only our ordered
+	 * extents and don't wait for them to complete (that is when
+	 * btrfs_finish_ordered_io runs), so here at this point their last_trans
+	 * value might be less than or equals to fs_info->last_trans_committed,
+	 * and setting a speculative last_trans for an inode when a buffered
+	 * write is made (such as fs_info->generation + 1 for example) would not
+	 * be reliable since after setting the value and before fsync is called
+	 * any number of transactions can start and commit (transaction kthread
+	 * commits the current transaction periodically), and a transaction
+	 * commit does not start nor waits for ordered extents to complete.
 	 */
 	smp_mb();
 	if (btrfs_inode_in_log(inode, root->fs_info->generation) ||
-	    BTRFS_I(inode)->last_trans <=
-	    root->fs_info->last_trans_committed) {
-		BTRFS_I(inode)->last_trans = 0;
-
+	    (full_sync && BTRFS_I(inode)->last_trans <=
+	     root->fs_info->last_trans_committed)) {
 		/*
 		 * We'v had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
@@ -2081,7 +2081,6 @@ static const struct vm_operations_struct btrfs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= btrfs_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
@@ -2276,6 +2275,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	bool same_page;
 	bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
 	u64 ino_size;
+	bool truncated_page = false;
+	bool updated_inode = false;
 
 	ret = btrfs_wait_ordered_range(inode, offset, len);
 	if (ret)
@@ -2307,13 +2308,18 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	 * entire page.
 	 */
 	if (same_page && len < PAGE_CACHE_SIZE) {
-		if (offset < ino_size)
+		if (offset < ino_size) {
+			truncated_page = true;
 			ret = btrfs_truncate_page(inode, offset, len, 0);
+		} else {
+			ret = 0;
+		}
 		goto out_only_mutex;
 	}
 
 	/* zero back part of the first page */
 	if (offset < ino_size) {
+		truncated_page = true;
 		ret = btrfs_truncate_page(inode, offset, 0, 0);
 		if (ret) {
 			mutex_unlock(&inode->i_mutex);
@@ -2349,6 +2355,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		if (!ret) {
 			/* zero the front end of the last page */
 			if (tail_start + tail_len < ino_size) {
+				truncated_page = true;
 				ret = btrfs_truncate_page(inode,
 						tail_start + tail_len, 0, 1);
 				if (ret)
@@ -2358,8 +2365,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	}
 
 	if (lockend < lockstart) {
-		mutex_unlock(&inode->i_mutex);
-		return 0;
+		ret = 0;
+		goto out_only_mutex;
 	}
 
 	while (1) {
@@ -2507,6 +2514,7 @@ out_trans:
 
 	trans->block_rsv = &root->fs_info->trans_block_rsv;
 	ret = btrfs_update_inode(trans, root, inode);
+	updated_inode = true;
 	btrfs_end_transaction(trans, root);
 	btrfs_btree_balance_dirty(root);
 out_free:
@@ -2516,6 +2524,22 @@ out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state, GFP_NOFS);
 out_only_mutex:
+	if (!updated_inode && truncated_page && !ret && !err) {
+		/*
+		 * If we only end up zeroing part of a page, we still need to
+		 * update the inode item, so that all the time fields are
+		 * updated as well as the necessary btrfs inode in memory fields
+		 * for detecting, at fsync time, if the inode isn't yet in the
+		 * log tree or it's there but not up to date.
+		 */
+		trans = btrfs_start_transaction(root, 1);
+		if (IS_ERR(trans)) {
+			err = PTR_ERR(trans);
+		} else {
+			err = btrfs_update_inode(trans, root, inode);
+			ret = btrfs_end_transaction(trans, root);
+		}
+	}
 	mutex_unlock(&inode->i_mutex);
 	if (ret && !err)
 		err = ret;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d6c03f7f136b..a71978578fa7 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -651,15 +651,13 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 	struct io_ctl io_ctl;
 	struct btrfs_key key;
 	struct btrfs_free_space *e, *n;
-	struct list_head bitmaps;
+	LIST_HEAD(bitmaps);
 	u64 num_entries;
 	u64 num_bitmaps;
 	u64 generation;
 	u8 type;
 	int ret = 0;
 
-	INIT_LIST_HEAD(&bitmaps);
-
 	/* Nothing in the space cache, goodbye */
 	if (!i_size_read(inode))
 		return 0;
@@ -1243,6 +1241,7 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct inode *inode;
 	int ret = 0;
+	enum btrfs_disk_cache_state dcs = BTRFS_DC_WRITTEN;
 
 	root = root->fs_info->tree_root;
 
@@ -1266,9 +1265,7 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 	ret = __btrfs_write_out_cache(root, inode, ctl, block_group, trans,
 				      path, block_group->key.objectid);
 	if (ret) {
-		spin_lock(&block_group->lock);
-		block_group->disk_cache_state = BTRFS_DC_ERROR;
-		spin_unlock(&block_group->lock);
+		dcs = BTRFS_DC_ERROR;
 		ret = 0;
 #ifdef DEBUG
 		btrfs_err(root->fs_info,
@@ -1277,6 +1274,9 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 #endif
 	}
 
+	spin_lock(&block_group->lock);
+	block_group->disk_cache_state = dcs;
+	spin_unlock(&block_group->lock);
 	iput(inode);
 	return ret;
 }
@@ -2903,7 +2903,6 @@ int btrfs_find_space_cluster(struct btrfs_root *root,
 	trace_btrfs_find_cluster(block_group, offset, bytes, empty_size,
 				 min_bytes);
 
-	INIT_LIST_HEAD(&bitmaps);
 	ret = setup_cluster_no_bitmap(block_group, cluster, &bitmaps, offset,
 				      bytes + empty_size,
 				      cont1_bytes, min_bytes);
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index 8ffa4783cbf4..265e03c73f4d 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -344,6 +344,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	path->leave_spinning = 1;
+	path->skip_release_on_error = 1;
 	ret = btrfs_insert_empty_item(trans, root, path, &key,
 				      ins_len);
 	if (ret == -EEXIST) {
@@ -362,8 +363,12 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 		ptr = (unsigned long)(ref + 1);
 		ret = 0;
 	} else if (ret < 0) {
-		if (ret == -EOVERFLOW)
-			ret = -EMLINK;
+		if (ret == -EOVERFLOW) {
+			if (find_name_in_backref(path, name, name_len, &ref))
+				ret = -EEXIST;
+			else
+				ret = -EMLINK;
+		}
 		goto out;
 	} else {
 		ref = btrfs_item_ptr(path->nodes[0], path->slots[0],
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8bf326affb94..d2e732d7af52 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -108,6 +108,13 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
 
 static int btrfs_dirty_inode(struct inode *inode);
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode)
+{
+	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+}
+#endif
+
 static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
 				     struct inode *inode,  struct inode *dir,
 				     const struct qstr *qstr)
@@ -1530,10 +1537,32 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
 static void btrfs_split_extent_hook(struct inode *inode,
 				    struct extent_state *orig, u64 split)
 {
+	u64 size;
+
 	/* not delalloc, ignore it */
 	if (!(orig->state & EXTENT_DELALLOC))
 		return;
 
+	size = orig->end - orig->start + 1;
+	if (size > BTRFS_MAX_EXTENT_SIZE) {
+		u64 num_extents;
+		u64 new_size;
+
+		/*
+		 * See the explanation in btrfs_merge_extent_hook, the same
+		 * applies here, just in reverse.
+		 */
+		new_size = orig->end - split + 1;
+		num_extents = div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
+					BTRFS_MAX_EXTENT_SIZE);
+		new_size = split - orig->start;
+		num_extents += div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
+					BTRFS_MAX_EXTENT_SIZE);
+		if (div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+			      BTRFS_MAX_EXTENT_SIZE) >= num_extents)
+			return;
+	}
+
 	spin_lock(&BTRFS_I(inode)->lock);
 	BTRFS_I(inode)->outstanding_extents++;
 	spin_unlock(&BTRFS_I(inode)->lock);
@@ -1549,10 +1578,55 @@ static void btrfs_merge_extent_hook(struct inode *inode,
 				    struct extent_state *new,
 				    struct extent_state *other)
 {
+	u64 new_size, old_size;
+	u64 num_extents;
+
 	/* not delalloc, ignore it */
 	if (!(other->state & EXTENT_DELALLOC))
 		return;
 
+	if (new->start > other->start)
+		new_size = new->end - other->start + 1;
+	else
+		new_size = other->end - new->start + 1;
+
+	/* we're not bigger than the max, unreserve the space and go */
+	if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
+		spin_lock(&BTRFS_I(inode)->lock);
+		BTRFS_I(inode)->outstanding_extents--;
+		spin_unlock(&BTRFS_I(inode)->lock);
+		return;
+	}
+
+	/*
+	 * We have to add up either side to figure out how many extents were
+	 * accounted for before we merged into one big extent.  If the number of
+	 * extents we accounted for is <= the amount we need for the new range
+	 * then we can return, otherwise drop.  Think of it like this
+	 *
+	 * [ 4k][MAX_SIZE]
+	 *
+	 * So we've grown the extent by a MAX_SIZE extent, this would mean we
+	 * need 2 outstanding extents, on one side we have 1 and the other side
+	 * we have 1 so they are == and we can return.  But in this case
+	 *
+	 * [MAX_SIZE+4k][MAX_SIZE+4k]
+	 *
+	 * Each range on their own accounts for 2 extents, but merged together
+	 * they are only 3 extents worth of accounting, so we need to drop in
+	 * this case.
+	 */
+	old_size = other->end - other->start + 1;
+	num_extents = div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
+				BTRFS_MAX_EXTENT_SIZE);
+	old_size = new->end - new->start + 1;
+	num_extents += div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
+				 BTRFS_MAX_EXTENT_SIZE);
+
+	if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
+		      BTRFS_MAX_EXTENT_SIZE) >= num_extents)
+		return;
+
 	spin_lock(&BTRFS_I(inode)->lock);
 	BTRFS_I(inode)->outstanding_extents--;
 	spin_unlock(&BTRFS_I(inode)->lock);
@@ -1604,7 +1678,7 @@ static void btrfs_del_delalloc_inode(struct btrfs_root *root,
  * have pending delalloc work to be done.
  */
 static void btrfs_set_bit_hook(struct inode *inode,
-			       struct extent_state *state, unsigned long *bits)
+			       struct extent_state *state, unsigned *bits)
 {
 
 	if ((*bits & EXTENT_DEFRAG) && !(*bits & EXTENT_DELALLOC))
@@ -1627,6 +1701,10 @@ static void btrfs_set_bit_hook(struct inode *inode,
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
 
+		/* For sanity tests */
+		if (btrfs_test_is_dummy_root(root))
+			return;
+
 		__percpu_counter_add(&root->fs_info->delalloc_bytes, len,
 				     root->fs_info->delalloc_batch);
 		spin_lock(&BTRFS_I(inode)->lock);
@@ -1645,9 +1723,11 @@ static void btrfs_set_bit_hook(struct inode *inode,
  */
 static void btrfs_clear_bit_hook(struct inode *inode,
 				 struct extent_state *state,
-				 unsigned long *bits)
+				 unsigned *bits)
 {
 	u64 len = state->end + 1 - state->start;
+	u64 num_extents = div64_u64(len + BTRFS_MAX_EXTENT_SIZE -1,
+				    BTRFS_MAX_EXTENT_SIZE);
 
 	spin_lock(&BTRFS_I(inode)->lock);
 	if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG))
@@ -1667,7 +1747,7 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 			*bits &= ~EXTENT_FIRST_DELALLOC;
 		} else if (!(*bits & EXTENT_DO_ACCOUNTING)) {
 			spin_lock(&BTRFS_I(inode)->lock);
-			BTRFS_I(inode)->outstanding_extents--;
+			BTRFS_I(inode)->outstanding_extents -= num_extents;
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
 
@@ -1680,6 +1760,10 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 		    root != root->fs_info->tree_root)
 			btrfs_delalloc_release_metadata(inode, len);
 
+		/* For sanity tests. */
+		if (btrfs_test_is_dummy_root(root))
+			return;
+
 		if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
 		    && do_list && !(state->state & EXTENT_NORESERVE))
 			btrfs_free_reserved_data_space(inode, len);
@@ -2945,7 +3029,7 @@ static int __readpage_endio_check(struct inode *inode,
 	return 0;
 zeroit:
 	if (__ratelimit(&_rs))
-		btrfs_info(BTRFS_I(inode)->root->fs_info,
+		btrfs_warn(BTRFS_I(inode)->root->fs_info,
 			   "csum failed ino %llu off %llu csum %u expected csum %u",
 			   btrfs_ino(inode), start, csum, csum_expected);
 	memset(kaddr + pgoff, 1, len);
@@ -3407,7 +3491,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 
 out:
 	if (ret)
-		btrfs_crit(root->fs_info,
+		btrfs_err(root->fs_info,
 			"could not do orphan cleanup %d", ret);
 	btrfs_free_path(path);
 	return ret;
@@ -3490,7 +3574,6 @@ static void btrfs_read_locked_inode(struct inode *inode)
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_inode_item *inode_item;
-	struct btrfs_timespec *tspec;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_key location;
 	unsigned long ptr;
@@ -3527,17 +3610,19 @@ static void btrfs_read_locked_inode(struct inode *inode)
 	i_gid_write(inode, btrfs_inode_gid(leaf, inode_item));
 	btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item));
 
-	tspec = btrfs_inode_atime(inode_item);
-	inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, tspec);
-	inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, tspec);
+	inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->atime);
+	inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->atime);
 
-	tspec = btrfs_inode_mtime(inode_item);
-	inode->i_mtime.tv_sec = btrfs_timespec_sec(leaf, tspec);
-	inode->i_mtime.tv_nsec = btrfs_timespec_nsec(leaf, tspec);
+	inode->i_mtime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->mtime);
+	inode->i_mtime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->mtime);
 
-	tspec = btrfs_inode_ctime(inode_item);
-	inode->i_ctime.tv_sec = btrfs_timespec_sec(leaf, tspec);
-	inode->i_ctime.tv_nsec = btrfs_timespec_nsec(leaf, tspec);
+	inode->i_ctime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->ctime);
+	inode->i_ctime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->ctime);
+
+	BTRFS_I(inode)->i_otime.tv_sec =
+		btrfs_timespec_sec(leaf, &inode_item->otime);
+	BTRFS_I(inode)->i_otime.tv_nsec =
+		btrfs_timespec_nsec(leaf, &inode_item->otime);
 
 	inode_set_bytes(inode, btrfs_inode_nbytes(leaf, inode_item));
 	BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item);
@@ -3608,7 +3693,6 @@ cache_acl:
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_mapping->a_ops = &btrfs_aops;
-		inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 		inode->i_fop = &btrfs_file_operations;
 		inode->i_op = &btrfs_file_inode_operations;
@@ -3623,7 +3707,6 @@ cache_acl:
 	case S_IFLNK:
 		inode->i_op = &btrfs_symlink_inode_operations;
 		inode->i_mapping->a_ops = &btrfs_symlink_aops;
-		inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 		break;
 	default:
 		inode->i_op = &btrfs_special_inode_operations;
@@ -3658,21 +3741,26 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 	btrfs_set_token_inode_mode(leaf, item, inode->i_mode, &token);
 	btrfs_set_token_inode_nlink(leaf, item, inode->i_nlink, &token);
 
-	btrfs_set_token_timespec_sec(leaf, btrfs_inode_atime(item),
+	btrfs_set_token_timespec_sec(leaf, &item->atime,
 				     inode->i_atime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_atime(item),
+	btrfs_set_token_timespec_nsec(leaf, &item->atime,
 				      inode->i_atime.tv_nsec, &token);
 
-	btrfs_set_token_timespec_sec(leaf, btrfs_inode_mtime(item),
+	btrfs_set_token_timespec_sec(leaf, &item->mtime,
 				     inode->i_mtime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_mtime(item),
+	btrfs_set_token_timespec_nsec(leaf, &item->mtime,
 				      inode->i_mtime.tv_nsec, &token);
 
-	btrfs_set_token_timespec_sec(leaf, btrfs_inode_ctime(item),
+	btrfs_set_token_timespec_sec(leaf, &item->ctime,
 				     inode->i_ctime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_ctime(item),
+	btrfs_set_token_timespec_nsec(leaf, &item->ctime,
 				      inode->i_ctime.tv_nsec, &token);
 
+	btrfs_set_token_timespec_sec(leaf, &item->otime,
+				     BTRFS_I(inode)->i_otime.tv_sec, &token);
+	btrfs_set_token_timespec_nsec(leaf, &item->otime,
+				      BTRFS_I(inode)->i_otime.tv_nsec, &token);
+
 	btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
 				     &token);
 	btrfs_set_token_inode_generation(leaf, item, BTRFS_I(inode)->generation,
@@ -5009,6 +5097,7 @@ static int fixup_tree_root_location(struct btrfs_root *root,
 	struct btrfs_root *new_root;
 	struct btrfs_root_ref *ref;
 	struct extent_buffer *leaf;
+	struct btrfs_key key;
 	int ret;
 	int err = 0;
 
@@ -5019,9 +5108,12 @@ static int fixup_tree_root_location(struct btrfs_root *root,
 	}
 
 	err = -ENOENT;
-	ret = btrfs_find_item(root->fs_info->tree_root, path,
-				BTRFS_I(dir)->root->root_key.objectid,
-				location->objectid, BTRFS_ROOT_REF_KEY, NULL);
+	key.objectid = BTRFS_I(dir)->root->root_key.objectid;
+	key.type = BTRFS_ROOT_REF_KEY;
+	key.offset = location->objectid;
+
+	ret = btrfs_search_slot(NULL, root->fs_info->tree_root, &key, path,
+				0, 0);
 	if (ret) {
 		if (ret < 0)
 			err = ret;
@@ -5260,7 +5352,10 @@ static struct inode *new_simple_dir(struct super_block *s,
 	inode->i_op = &btrfs_dir_ro_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 	inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
-	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	inode->i_mtime = CURRENT_TIME;
+	inode->i_atime = inode->i_mtime;
+	inode->i_ctime = inode->i_mtime;
+	BTRFS_I(inode)->i_otime = inode->i_mtime;
 
 	return inode;
 }
@@ -5828,7 +5923,12 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 
 	inode_init_owner(inode, dir, mode);
 	inode_set_bytes(inode, 0);
-	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+
+	inode->i_mtime = CURRENT_TIME;
+	inode->i_atime = inode->i_mtime;
+	inode->i_ctime = inode->i_mtime;
+	BTRFS_I(inode)->i_otime = inode->i_mtime;
+
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				  struct btrfs_inode_item);
 	memset_extent_buffer(path->nodes[0], 0, (unsigned long)inode_item,
@@ -6088,7 +6188,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	inode->i_fop = &btrfs_file_operations;
 	inode->i_op = &btrfs_file_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
@@ -7137,17 +7236,28 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	u64 start = iblock << inode->i_blkbits;
 	u64 lockstart, lockend;
 	u64 len = bh_result->b_size;
+	u64 *outstanding_extents = NULL;
 	int unlock_bits = EXTENT_LOCKED;
 	int ret = 0;
 
 	if (create)
-		unlock_bits |= EXTENT_DELALLOC | EXTENT_DIRTY;
+		unlock_bits |= EXTENT_DIRTY;
 	else
 		len = min_t(u64, len, root->sectorsize);
 
 	lockstart = start;
 	lockend = start + len - 1;
 
+	if (current->journal_info) {
+		/*
+		 * Need to pull our outstanding extents and set journal_info to NULL so
+		 * that anything that needs to check if there's a transction doesn't get
+		 * confused.
+		 */
+		outstanding_extents = current->journal_info;
+		current->journal_info = NULL;
+	}
+
 	/*
 	 * If this errors out it's because we couldn't invalidate pagecache for
 	 * this range and we need to fallback to buffered.
@@ -7208,7 +7318,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
 	     em->block_start != EXTENT_MAP_HOLE)) {
 		int type;
-		int ret;
 		u64 block_start, orig_start, orig_block_len, ram_bytes;
 
 		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
@@ -7272,14 +7381,21 @@ unlock:
 		if (start + len > i_size_read(inode))
 			i_size_write(inode, start + len);
 
-		spin_lock(&BTRFS_I(inode)->lock);
-		BTRFS_I(inode)->outstanding_extents++;
-		spin_unlock(&BTRFS_I(inode)->lock);
+		/*
+		 * If we have an outstanding_extents count still set then we're
+		 * within our reservation, otherwise we need to adjust our inode
+		 * counter appropriately.
+		 */
+		if (*outstanding_extents) {
+			(*outstanding_extents)--;
+		} else {
+			spin_lock(&BTRFS_I(inode)->lock);
+			BTRFS_I(inode)->outstanding_extents++;
+			spin_unlock(&BTRFS_I(inode)->lock);
+		}
 
-		ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
-				     lockstart + len - 1, EXTENT_DELALLOC, NULL,
-				     &cached_state, GFP_NOFS);
-		BUG_ON(ret);
+		current->journal_info = outstanding_extents;
+		btrfs_free_reserved_data_space(inode, len);
 	}
 
 	/*
@@ -7302,6 +7418,8 @@ unlock:
 unlock_err:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 unlock_bits, 1, 0, &cached_state, GFP_NOFS);
+	if (outstanding_extents)
+		current->journal_info = outstanding_extents;
 	return ret;
 }
 
@@ -7808,8 +7926,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	}
 
 	/* async crcs make it difficult to collect full stripe writes. */
-	if (btrfs_get_alloc_profile(root, 1) &
-	    (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6))
+	if (btrfs_get_alloc_profile(root, 1) & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		async_submit = 0;
 	else
 		async_submit = 1;
@@ -8002,6 +8119,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	u64 outstanding_extents = 0;
 	size_t count = 0;
 	int flags = 0;
 	bool wakeup = true;
@@ -8039,6 +8157,16 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		ret = btrfs_delalloc_reserve_space(inode, count);
 		if (ret)
 			goto out;
+		outstanding_extents = div64_u64(count +
+						BTRFS_MAX_EXTENT_SIZE - 1,
+						BTRFS_MAX_EXTENT_SIZE);
+
+		/*
+		 * We need to know how many extents we reserved so that we can
+		 * do the accounting properly if we go over the number we
+		 * originally calculated.  Abuse current->journal_info for this.
+		 */
+		current->journal_info = &outstanding_extents;
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
 		inode_dio_done(inode);
@@ -8051,13 +8179,12 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 			iter, offset, btrfs_get_blocks_direct, NULL,
 			btrfs_submit_direct, flags);
 	if (rw & WRITE) {
+		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED)
 			btrfs_delalloc_release_space(inode, count);
 		else if (ret >= 0 && (size_t)ret < count)
 			btrfs_delalloc_release_space(inode,
 						     count - (size_t)ret);
-		else
-			btrfs_delalloc_release_metadata(inode, 0);
 	}
 out:
 	if (wakeup)
@@ -8578,6 +8705,9 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 
 	ei->delayed_node = NULL;
 
+	ei->i_otime.tv_sec = 0;
+	ei->i_otime.tv_nsec = 0;
+
 	inode = &ei->vfs_inode;
 	extent_map_tree_init(&ei->extent_tree);
 	extent_io_tree_init(&ei->io_tree, &inode->i_data);
@@ -9203,7 +9333,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	inode->i_fop = &btrfs_file_operations;
 	inode->i_op = &btrfs_file_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
@@ -9247,7 +9376,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 
 	inode->i_op = &btrfs_symlink_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_symlink_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 	inode_set_bytes(inode, name_len);
 	btrfs_i_size_write(inode, name_len);
 	err = btrfs_update_inode(trans, root, inode);
@@ -9459,7 +9587,6 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_op = &btrfs_file_inode_operations;
 
 	inode->i_mapping->a_ops = &btrfs_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 
 	ret = btrfs_init_inode_security(trans, inode, dir, NULL);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index d49fe8a0f6b5..74609b931ba5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -776,11 +776,11 @@ static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir)
 	    IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
 		return -EPERM;
 	if (isdir) {
-		if (!S_ISDIR(victim->d_inode->i_mode))
+		if (!d_is_dir(victim))
 			return -ENOTDIR;
 		if (IS_ROOT(victim))
 			return -EBUSY;
-	} else if (S_ISDIR(victim->d_inode->i_mode))
+	} else if (d_is_dir(victim))
 		return -EISDIR;
 	if (IS_DEADDIR(dir))
 		return -ENOENT;
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 534544e08f76..157cc54fc634 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -452,9 +452,7 @@ void btrfs_get_logged_extents(struct inode *inode,
 			continue;
 		if (entry_end(ordered) <= start)
 			break;
-		if (!list_empty(&ordered->log_list))
-			continue;
-		if (test_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
+		if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
 			continue;
 		list_add(&ordered->log_list, logged_list);
 		atomic_inc(&ordered->refs);
@@ -511,8 +509,7 @@ void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
 		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
 						   &ordered->flags));
 
-		if (!test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
-			list_add_tail(&ordered->trans_list, &trans->ordered);
+		list_add_tail(&ordered->trans_list, &trans->ordered);
 		spin_lock_irq(&log->log_extents_lock[index]);
 	}
 	spin_unlock_irq(&log->log_extents_lock[index]);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 48b60dbf807f..058c79eecbfb 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1259,7 +1259,7 @@ static int comp_oper(struct btrfs_qgroup_operation *oper1,
 	if (oper1->seq < oper2->seq)
 		return -1;
 	if (oper1->seq > oper2->seq)
-		return -1;
+		return 1;
 	if (oper1->ref_root < oper2->ref_root)
 		return -1;
 	if (oper1->ref_root > oper2->ref_root)
@@ -1431,9 +1431,8 @@ static int qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 		qgroup = u64_to_ptr(unode->aux);
 		qgroup->rfer += sign * oper->num_bytes;
 		qgroup->rfer_cmpr += sign * oper->num_bytes;
+		WARN_ON(sign < 0 && qgroup->excl < oper->num_bytes);
 		qgroup->excl += sign * oper->num_bytes;
-		if (sign < 0)
-			WARN_ON(qgroup->excl < oper->num_bytes);
 		qgroup->excl_cmpr += sign * oper->num_bytes;
 		qgroup_dirty(fs_info, qgroup);
 
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 8ab2a17bbba8..5264858ed768 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -58,15 +58,6 @@
  */
 #define RBIO_CACHE_READY_BIT	3
 
-/*
- * bbio and raid_map is managed by the caller, so we shouldn't free
- * them here. And besides that, all rbios with this flag should not
- * be cached, because we need raid_map to check the rbios' stripe
- * is the same or not, but it is very likely that the caller has
- * free raid_map, so don't cache those rbios.
- */
-#define RBIO_HOLD_BBIO_MAP_BIT	4
-
 #define RBIO_CACHE_SIZE 1024
 
 enum btrfs_rbio_ops {
@@ -79,13 +70,6 @@ struct btrfs_raid_bio {
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_bio *bbio;
 
-	/*
-	 * logical block numbers for the start of each stripe
-	 * The last one or two are p/q.  These are sorted,
-	 * so raid_map[0] is the start of our full stripe
-	 */
-	u64 *raid_map;
-
 	/* while we're doing rmw on a stripe
 	 * we put it into a hash table so we can
 	 * lock the stripe and merge more rbios
@@ -303,7 +287,7 @@ static void cache_rbio_pages(struct btrfs_raid_bio *rbio)
  */
 static int rbio_bucket(struct btrfs_raid_bio *rbio)
 {
-	u64 num = rbio->raid_map[0];
+	u64 num = rbio->bbio->raid_map[0];
 
 	/*
 	 * we shift down quite a bit.  We're using byte
@@ -606,8 +590,8 @@ static int rbio_can_merge(struct btrfs_raid_bio *last,
 	    test_bit(RBIO_CACHE_BIT, &cur->flags))
 		return 0;
 
-	if (last->raid_map[0] !=
-	    cur->raid_map[0])
+	if (last->bbio->raid_map[0] !=
+	    cur->bbio->raid_map[0])
 		return 0;
 
 	/* we can't merge with different operations */
@@ -689,7 +673,7 @@ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
 	spin_lock_irqsave(&h->lock, flags);
 	list_for_each_entry(cur, &h->hash_list, hash_list) {
 		walk++;
-		if (cur->raid_map[0] == rbio->raid_map[0]) {
+		if (cur->bbio->raid_map[0] == rbio->bbio->raid_map[0]) {
 			spin_lock(&cur->bio_list_lock);
 
 			/* can we steal this cached rbio's pages? */
@@ -841,21 +825,6 @@ done_nolock:
 		remove_rbio_from_cache(rbio);
 }
 
-static inline void
-__free_bbio_and_raid_map(struct btrfs_bio *bbio, u64 *raid_map, int need)
-{
-	if (need) {
-		kfree(raid_map);
-		kfree(bbio);
-	}
-}
-
-static inline void free_bbio_and_raid_map(struct btrfs_raid_bio *rbio)
-{
-	__free_bbio_and_raid_map(rbio->bbio, rbio->raid_map,
-			!test_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags));
-}
-
 static void __free_raid_bio(struct btrfs_raid_bio *rbio)
 {
 	int i;
@@ -875,8 +844,7 @@ static void __free_raid_bio(struct btrfs_raid_bio *rbio)
 		}
 	}
 
-	free_bbio_and_raid_map(rbio);
-
+	btrfs_put_bbio(rbio->bbio);
 	kfree(rbio);
 }
 
@@ -985,8 +953,7 @@ static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes)
  * this does not allocate any pages for rbio->pages.
  */
 static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
-			  struct btrfs_bio *bbio, u64 *raid_map,
-			  u64 stripe_len)
+			  struct btrfs_bio *bbio, u64 stripe_len)
 {
 	struct btrfs_raid_bio *rbio;
 	int nr_data = 0;
@@ -1007,7 +974,6 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
 	INIT_LIST_HEAD(&rbio->stripe_cache);
 	INIT_LIST_HEAD(&rbio->hash_list);
 	rbio->bbio = bbio;
-	rbio->raid_map = raid_map;
 	rbio->fs_info = root->fs_info;
 	rbio->stripe_len = stripe_len;
 	rbio->nr_pages = num_pages;
@@ -1028,10 +994,12 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
 	rbio->bio_pages = p + sizeof(struct page *) * num_pages;
 	rbio->dbitmap = p + sizeof(struct page *) * num_pages * 2;
 
-	if (raid_map[real_stripes - 1] == RAID6_Q_STRIPE)
+	if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID5)
+		nr_data = real_stripes - 1;
+	else if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID6)
 		nr_data = real_stripes - 2;
 	else
-		nr_data = real_stripes - 1;
+		BUG();
 
 	rbio->nr_data = nr_data;
 	return rbio;
@@ -1182,7 +1150,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
 	spin_lock_irq(&rbio->bio_list_lock);
 	bio_list_for_each(bio, &rbio->bio_list) {
 		start = (u64)bio->bi_iter.bi_sector << 9;
-		stripe_offset = start - rbio->raid_map[0];
+		stripe_offset = start - rbio->bbio->raid_map[0];
 		page_index = stripe_offset >> PAGE_CACHE_SHIFT;
 
 		for (i = 0; i < bio->bi_vcnt; i++) {
@@ -1402,7 +1370,7 @@ static int find_logical_bio_stripe(struct btrfs_raid_bio *rbio,
 	logical <<= 9;
 
 	for (i = 0; i < rbio->nr_data; i++) {
-		stripe_start = rbio->raid_map[i];
+		stripe_start = rbio->bbio->raid_map[i];
 		if (logical >= stripe_start &&
 		    logical < stripe_start + rbio->stripe_len) {
 			return i;
@@ -1776,17 +1744,16 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
  * our main entry point for writes from the rest of the FS.
  */
 int raid56_parity_write(struct btrfs_root *root, struct bio *bio,
-			struct btrfs_bio *bbio, u64 *raid_map,
-			u64 stripe_len)
+			struct btrfs_bio *bbio, u64 stripe_len)
 {
 	struct btrfs_raid_bio *rbio;
 	struct btrfs_plug_cb *plug = NULL;
 	struct blk_plug_cb *cb;
 	int ret;
 
-	rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
+	rbio = alloc_rbio(root, bbio, stripe_len);
 	if (IS_ERR(rbio)) {
-		__free_bbio_and_raid_map(bbio, raid_map, 1);
+		btrfs_put_bbio(bbio);
 		return PTR_ERR(rbio);
 	}
 	bio_list_add(&rbio->bio_list, bio);
@@ -1885,9 +1852,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 		}
 
 		/* all raid6 handling here */
-		if (rbio->raid_map[rbio->real_stripes - 1] ==
-		    RAID6_Q_STRIPE) {
-
+		if (rbio->bbio->map_type & BTRFS_BLOCK_GROUP_RAID6) {
 			/*
 			 * single failure, rebuild from parity raid5
 			 * style
@@ -1922,8 +1887,9 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 			 * here due to a crc mismatch and we can't give them the
 			 * data they want
 			 */
-			if (rbio->raid_map[failb] == RAID6_Q_STRIPE) {
-				if (rbio->raid_map[faila] == RAID5_P_STRIPE) {
+			if (rbio->bbio->raid_map[failb] == RAID6_Q_STRIPE) {
+				if (rbio->bbio->raid_map[faila] ==
+				    RAID5_P_STRIPE) {
 					err = -EIO;
 					goto cleanup;
 				}
@@ -1934,7 +1900,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 				goto pstripe;
 			}
 
-			if (rbio->raid_map[failb] == RAID5_P_STRIPE) {
+			if (rbio->bbio->raid_map[failb] == RAID5_P_STRIPE) {
 				raid6_datap_recov(rbio->real_stripes,
 						  PAGE_SIZE, faila, pointers);
 			} else {
@@ -2001,8 +1967,7 @@ cleanup:
 
 cleanup_io:
 	if (rbio->operation == BTRFS_RBIO_READ_REBUILD) {
-		if (err == 0 &&
-		    !test_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags))
+		if (err == 0)
 			cache_rbio_pages(rbio);
 		else
 			clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
@@ -2156,15 +2121,16 @@ cleanup:
  * of the drive.
  */
 int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
-			  struct btrfs_bio *bbio, u64 *raid_map,
-			  u64 stripe_len, int mirror_num, int generic_io)
+			  struct btrfs_bio *bbio, u64 stripe_len,
+			  int mirror_num, int generic_io)
 {
 	struct btrfs_raid_bio *rbio;
 	int ret;
 
-	rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
+	rbio = alloc_rbio(root, bbio, stripe_len);
 	if (IS_ERR(rbio)) {
-		__free_bbio_and_raid_map(bbio, raid_map, generic_io);
+		if (generic_io)
+			btrfs_put_bbio(bbio);
 		return PTR_ERR(rbio);
 	}
 
@@ -2175,7 +2141,8 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
 	rbio->faila = find_logical_bio_stripe(rbio, bio);
 	if (rbio->faila == -1) {
 		BUG();
-		__free_bbio_and_raid_map(bbio, raid_map, generic_io);
+		if (generic_io)
+			btrfs_put_bbio(bbio);
 		kfree(rbio);
 		return -EIO;
 	}
@@ -2184,7 +2151,7 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
 		btrfs_bio_counter_inc_noblocked(root->fs_info);
 		rbio->generic_bio_cnt = 1;
 	} else {
-		set_bit(RBIO_HOLD_BBIO_MAP_BIT, &rbio->flags);
+		btrfs_get_bbio(bbio);
 	}
 
 	/*
@@ -2240,14 +2207,14 @@ static void read_rebuild_work(struct btrfs_work *work)
 
 struct btrfs_raid_bio *
 raid56_parity_alloc_scrub_rbio(struct btrfs_root *root, struct bio *bio,
-			       struct btrfs_bio *bbio, u64 *raid_map,
-			       u64 stripe_len, struct btrfs_device *scrub_dev,
+			       struct btrfs_bio *bbio, u64 stripe_len,
+			       struct btrfs_device *scrub_dev,
 			       unsigned long *dbitmap, int stripe_nsectors)
 {
 	struct btrfs_raid_bio *rbio;
 	int i;
 
-	rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
+	rbio = alloc_rbio(root, bbio, stripe_len);
 	if (IS_ERR(rbio))
 		return NULL;
 	bio_list_add(&rbio->bio_list, bio);
@@ -2279,10 +2246,10 @@ void raid56_parity_add_scrub_pages(struct btrfs_raid_bio *rbio,
 	int stripe_offset;
 	int index;
 
-	ASSERT(logical >= rbio->raid_map[0]);
-	ASSERT(logical + PAGE_SIZE <= rbio->raid_map[0] +
+	ASSERT(logical >= rbio->bbio->raid_map[0]);
+	ASSERT(logical + PAGE_SIZE <= rbio->bbio->raid_map[0] +
 				rbio->stripe_len * rbio->nr_data);
-	stripe_offset = (int)(logical - rbio->raid_map[0]);
+	stripe_offset = (int)(logical - rbio->bbio->raid_map[0]);
 	index = stripe_offset >> PAGE_CACHE_SHIFT;
 	rbio->bio_pages[index] = page;
 }
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index 31d4a157b5e3..2b5d7977d83b 100644
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -43,16 +43,15 @@ struct btrfs_raid_bio;
 struct btrfs_device;
 
 int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
-			  struct btrfs_bio *bbio, u64 *raid_map,
-			  u64 stripe_len, int mirror_num, int generic_io);
+			  struct btrfs_bio *bbio, u64 stripe_len,
+			  int mirror_num, int generic_io);
 int raid56_parity_write(struct btrfs_root *root, struct bio *bio,
-			       struct btrfs_bio *bbio, u64 *raid_map,
-			       u64 stripe_len);
+			       struct btrfs_bio *bbio, u64 stripe_len);
 
 struct btrfs_raid_bio *
 raid56_parity_alloc_scrub_rbio(struct btrfs_root *root, struct bio *bio,
-			       struct btrfs_bio *bbio, u64 *raid_map,
-			       u64 stripe_len, struct btrfs_device *scrub_dev,
+			       struct btrfs_bio *bbio, u64 stripe_len,
+			       struct btrfs_device *scrub_dev,
 			       unsigned long *dbitmap, int stripe_nsectors);
 void raid56_parity_add_scrub_pages(struct btrfs_raid_bio *rbio,
 				   struct page *page, u64 logical);
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index b63ae20618fb..0e7beea92b4c 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -66,7 +66,6 @@ struct reada_extctl {
 struct reada_extent {
 	u64			logical;
 	struct btrfs_key	top;
-	u32			blocksize;
 	int			err;
 	struct list_head	extctl;
 	int 			refcnt;
@@ -349,7 +348,6 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 
 	blocksize = root->nodesize;
 	re->logical = logical;
-	re->blocksize = blocksize;
 	re->top = *top;
 	INIT_LIST_HEAD(&re->extctl);
 	spin_lock_init(&re->lock);
@@ -463,7 +461,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	spin_unlock(&fs_info->reada_lock);
 	btrfs_dev_replace_unlock(&fs_info->dev_replace);
 
-	kfree(bbio);
+	btrfs_put_bbio(bbio);
 	return re;
 
 error:
@@ -488,7 +486,7 @@ error:
 		kref_put(&zone->refcnt, reada_zone_release);
 		spin_unlock(&fs_info->reada_lock);
 	}
-	kfree(bbio);
+	btrfs_put_bbio(bbio);
 	kfree(re);
 	return re_exist;
 }
@@ -660,7 +658,6 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 	int mirror_num = 0;
 	struct extent_buffer *eb = NULL;
 	u64 logical;
-	u32 blocksize;
 	int ret;
 	int i;
 	int need_kick = 0;
@@ -694,7 +691,7 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 		spin_unlock(&fs_info->reada_lock);
 		return 0;
 	}
-	dev->reada_next = re->logical + re->blocksize;
+	dev->reada_next = re->logical + fs_info->tree_root->nodesize;
 	re->refcnt++;
 
 	spin_unlock(&fs_info->reada_lock);
@@ -709,7 +706,6 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 		}
 	}
 	logical = re->logical;
-	blocksize = re->blocksize;
 
 	spin_lock(&re->lock);
 	if (re->scheduled_for == NULL) {
@@ -724,8 +720,8 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 		return 0;
 
 	atomic_inc(&dev->reada_in_flight);
-	ret = reada_tree_block_flagged(fs_info->extent_root, logical, blocksize,
-			 mirror_num, &eb);
+	ret = reada_tree_block_flagged(fs_info->extent_root, logical,
+			mirror_num, &eb);
 	if (ret)
 		__readahead_hook(fs_info->extent_root, NULL, logical, ret);
 	else if (eb)
@@ -851,7 +847,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 				break;
 			printk(KERN_DEBUG
 				"  re: logical %llu size %u empty %d for %lld",
-				re->logical, re->blocksize,
+				re->logical, fs_info->tree_root->nodesize,
 				list_empty(&re->extctl), re->scheduled_for ?
 				re->scheduled_for->devid : -1);
 
@@ -886,7 +882,8 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 		}
 		printk(KERN_DEBUG
 			"re: logical %llu size %u list empty %d for %lld",
-			re->logical, re->blocksize, list_empty(&re->extctl),
+			re->logical, fs_info->tree_root->nodesize,
+			list_empty(&re->extctl),
 			re->scheduled_for ? re->scheduled_for->devid : -1);
 		for (i = 0; i < re->nzones; ++i) {
 			printk(KERN_CONT " zone %llu-%llu devs",
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 74257d6436ad..d83085381bcc 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2855,9 +2855,10 @@ static void update_processed_blocks(struct reloc_control *rc,
 	}
 }
 
-static int tree_block_processed(u64 bytenr, u32 blocksize,
-				struct reloc_control *rc)
+static int tree_block_processed(u64 bytenr, struct reloc_control *rc)
 {
+	u32 blocksize = rc->extent_root->nodesize;
+
 	if (test_range_bit(&rc->processed_blocks, bytenr,
 			   bytenr + blocksize - 1, EXTENT_DIRTY, 1, NULL))
 		return 1;
@@ -2965,8 +2966,7 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 	while (rb_node) {
 		block = rb_entry(rb_node, struct tree_block, rb_node);
 		if (!block->key_ready)
-			readahead_tree_block(rc->extent_root, block->bytenr,
-					block->key.objectid);
+			readahead_tree_block(rc->extent_root, block->bytenr);
 		rb_node = rb_next(rb_node);
 	}
 
@@ -3353,7 +3353,7 @@ static int __add_tree_block(struct reloc_control *rc,
 	bool skinny = btrfs_fs_incompat(rc->extent_root->fs_info,
 					SKINNY_METADATA);
 
-	if (tree_block_processed(bytenr, blocksize, rc))
+	if (tree_block_processed(bytenr, rc))
 		return 0;
 
 	if (tree_search(blocks, bytenr))
@@ -3611,7 +3611,7 @@ static int find_data_references(struct reloc_control *rc,
 		if (added)
 			goto next;
 
-		if (!tree_block_processed(leaf->start, leaf->len, rc)) {
+		if (!tree_block_processed(leaf->start, rc)) {
 			block = kmalloc(sizeof(*block), GFP_NOFS);
 			if (!block) {
 				err = -ENOMEM;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index e427cb7ee12c..ec57687c9a4d 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -66,7 +66,6 @@ struct scrub_ctx;
 struct scrub_recover {
 	atomic_t		refs;
 	struct btrfs_bio	*bbio;
-	u64			*raid_map;
 	u64			map_length;
 };
 
@@ -80,7 +79,7 @@ struct scrub_page {
 	u64			logical;
 	u64			physical;
 	u64			physical_for_dev_replace;
-	atomic_t		ref_count;
+	atomic_t		refs;
 	struct {
 		unsigned int	mirror_num:8;
 		unsigned int	have_csum:1;
@@ -113,7 +112,7 @@ struct scrub_block {
 	struct scrub_page	*pagev[SCRUB_MAX_PAGES_PER_BLOCK];
 	int			page_count;
 	atomic_t		outstanding_pages;
-	atomic_t		ref_count; /* free mem on transition to zero */
+	atomic_t		refs; /* free mem on transition to zero */
 	struct scrub_ctx	*sctx;
 	struct scrub_parity	*sparity;
 	struct {
@@ -142,7 +141,7 @@ struct scrub_parity {
 
 	int			stripe_len;
 
-	atomic_t		ref_count;
+	atomic_t		refs;
 
 	struct list_head	spages;
 
@@ -194,6 +193,15 @@ struct scrub_ctx {
 	 */
 	struct btrfs_scrub_progress stat;
 	spinlock_t		stat_lock;
+
+	/*
+	 * Use a ref counter to avoid use-after-free issues. Scrub workers
+	 * decrement bios_in_flight and workers_pending and then do a wakeup
+	 * on the list_wait wait queue. We must ensure the main scrub task
+	 * doesn't free the scrub context before or while the workers are
+	 * doing the wakeup() call.
+	 */
+	atomic_t                refs;
 };
 
 struct scrub_fixup_nodatasum {
@@ -236,10 +244,7 @@ static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
 static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx);
 static void scrub_pending_trans_workers_dec(struct scrub_ctx *sctx);
 static int scrub_handle_errored_block(struct scrub_block *sblock_to_check);
-static int scrub_setup_recheck_block(struct scrub_ctx *sctx,
-				     struct btrfs_fs_info *fs_info,
-				     struct scrub_block *original_sblock,
-				     u64 length, u64 logical,
+static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 				     struct scrub_block *sblocks_for_recheck);
 static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 				struct scrub_block *sblock, int is_metadata,
@@ -251,8 +256,7 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
 					 const u8 *csum, u64 generation,
 					 u16 csum_size);
 static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
-					     struct scrub_block *sblock_good,
-					     int force_write);
+					     struct scrub_block *sblock_good);
 static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
 					    struct scrub_block *sblock_good,
 					    int page_num, int force_write);
@@ -302,10 +306,12 @@ static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 static void copy_nocow_pages_worker(struct btrfs_work *work);
 static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
+static void scrub_put_ctx(struct scrub_ctx *sctx);
 
 
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx)
 {
+	atomic_inc(&sctx->refs);
 	atomic_inc(&sctx->bios_in_flight);
 }
 
@@ -313,6 +319,7 @@ static void scrub_pending_bio_dec(struct scrub_ctx *sctx)
 {
 	atomic_dec(&sctx->bios_in_flight);
 	wake_up(&sctx->list_wait);
+	scrub_put_ctx(sctx);
 }
 
 static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info)
@@ -346,6 +353,7 @@ static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx)
 {
 	struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info;
 
+	atomic_inc(&sctx->refs);
 	/*
 	 * increment scrubs_running to prevent cancel requests from
 	 * completing as long as a worker is running. we must also
@@ -388,6 +396,7 @@ static void scrub_pending_trans_workers_dec(struct scrub_ctx *sctx)
 	atomic_dec(&sctx->workers_pending);
 	wake_up(&fs_info->scrub_pause_wait);
 	wake_up(&sctx->list_wait);
+	scrub_put_ctx(sctx);
 }
 
 static void scrub_free_csums(struct scrub_ctx *sctx)
@@ -433,6 +442,12 @@ static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx)
 	kfree(sctx);
 }
 
+static void scrub_put_ctx(struct scrub_ctx *sctx)
+{
+	if (atomic_dec_and_test(&sctx->refs))
+		scrub_free_ctx(sctx);
+}
+
 static noinline_for_stack
 struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 {
@@ -457,6 +472,7 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 	sctx = kzalloc(sizeof(*sctx), GFP_NOFS);
 	if (!sctx)
 		goto nomem;
+	atomic_set(&sctx->refs, 1);
 	sctx->is_dev_replace = is_dev_replace;
 	sctx->pages_per_rd_bio = pages_per_rd_bio;
 	sctx->curr = -1;
@@ -520,6 +536,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root,
 	struct inode_fs_paths *ipath = NULL;
 	struct btrfs_root *local_root;
 	struct btrfs_key root_key;
+	struct btrfs_key key;
 
 	root_key.objectid = root;
 	root_key.type = BTRFS_ROOT_ITEM_KEY;
@@ -530,7 +547,14 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root,
 		goto err;
 	}
 
-	ret = inode_item_info(inum, 0, local_root, swarn->path);
+	/*
+	 * this makes the path point to (inum INODE_ITEM ioff)
+	 */
+	key.objectid = inum;
+	key.type = BTRFS_INODE_ITEM_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, local_root, &key, swarn->path, 0, 0);
 	if (ret) {
 		btrfs_release_path(swarn->path);
 		goto err;
@@ -848,8 +872,7 @@ static inline void scrub_get_recover(struct scrub_recover *recover)
 static inline void scrub_put_recover(struct scrub_recover *recover)
 {
 	if (atomic_dec_and_test(&recover->refs)) {
-		kfree(recover->bbio);
-		kfree(recover->raid_map);
+		btrfs_put_bbio(recover->bbio);
 		kfree(recover);
 	}
 }
@@ -955,8 +978,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	}
 
 	/* setup the context, map the logical blocks and alloc the pages */
-	ret = scrub_setup_recheck_block(sctx, fs_info, sblock_to_check, length,
-					logical, sblocks_for_recheck);
+	ret = scrub_setup_recheck_block(sblock_to_check, sblocks_for_recheck);
 	if (ret) {
 		spin_lock(&sctx->stat_lock);
 		sctx->stat.read_errors++;
@@ -1030,9 +1052,10 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	if (!is_metadata && !have_csum) {
 		struct scrub_fixup_nodatasum *fixup_nodatasum;
 
-nodatasum_case:
 		WARN_ON(sctx->is_dev_replace);
 
+nodatasum_case:
+
 		/*
 		 * !is_metadata and !have_csum, this means that the data
 		 * might not be COW'ed, that it might be modified
@@ -1091,76 +1114,20 @@ nodatasum_case:
 		    sblock_other->no_io_error_seen) {
 			if (sctx->is_dev_replace) {
 				scrub_write_block_to_dev_replace(sblock_other);
+				goto corrected_error;
 			} else {
-				int force_write = is_metadata || have_csum;
-
 				ret = scrub_repair_block_from_good_copy(
-						sblock_bad, sblock_other,
-						force_write);
+						sblock_bad, sblock_other);
+				if (!ret)
+					goto corrected_error;
 			}
-			if (0 == ret)
-				goto corrected_error;
 		}
 	}
 
-	/*
-	 * for dev_replace, pick good pages and write to the target device.
-	 */
-	if (sctx->is_dev_replace) {
-		success = 1;
-		for (page_num = 0; page_num < sblock_bad->page_count;
-		     page_num++) {
-			int sub_success;
-
-			sub_success = 0;
-			for (mirror_index = 0;
-			     mirror_index < BTRFS_MAX_MIRRORS &&
-			     sblocks_for_recheck[mirror_index].page_count > 0;
-			     mirror_index++) {
-				struct scrub_block *sblock_other =
-					sblocks_for_recheck + mirror_index;
-				struct scrub_page *page_other =
-					sblock_other->pagev[page_num];
-
-				if (!page_other->io_error) {
-					ret = scrub_write_page_to_dev_replace(
-							sblock_other, page_num);
-					if (ret == 0) {
-						/* succeeded for this page */
-						sub_success = 1;
-						break;
-					} else {
-						btrfs_dev_replace_stats_inc(
-							&sctx->dev_root->
-							fs_info->dev_replace.
-							num_write_errors);
-					}
-				}
-			}
-
-			if (!sub_success) {
-				/*
-				 * did not find a mirror to fetch the page
-				 * from. scrub_write_page_to_dev_replace()
-				 * handles this case (page->io_error), by
-				 * filling the block with zeros before
-				 * submitting the write request
-				 */
-				success = 0;
-				ret = scrub_write_page_to_dev_replace(
-						sblock_bad, page_num);
-				if (ret)
-					btrfs_dev_replace_stats_inc(
-						&sctx->dev_root->fs_info->
-						dev_replace.num_write_errors);
-			}
-		}
-
-		goto out;
-	}
+	if (sblock_bad->no_io_error_seen && !sctx->is_dev_replace)
+		goto did_not_correct_error;
 
 	/*
-	 * for regular scrub, repair those pages that are errored.
 	 * In case of I/O errors in the area that is supposed to be
 	 * repaired, continue by picking good copies of those pages.
 	 * Select the good pages from mirrors to rewrite bad pages from
@@ -1184,44 +1151,64 @@ nodatasum_case:
 	 * mirror, even if other 512 byte sectors in the same PAGE_SIZE
 	 * area are unreadable.
 	 */
-
-	/* can only fix I/O errors from here on */
-	if (sblock_bad->no_io_error_seen)
-		goto did_not_correct_error;
-
 	success = 1;
-	for (page_num = 0; page_num < sblock_bad->page_count; page_num++) {
+	for (page_num = 0; page_num < sblock_bad->page_count;
+	     page_num++) {
 		struct scrub_page *page_bad = sblock_bad->pagev[page_num];
+		struct scrub_block *sblock_other = NULL;
 
-		if (!page_bad->io_error)
+		/* skip no-io-error page in scrub */
+		if (!page_bad->io_error && !sctx->is_dev_replace)
 			continue;
 
-		for (mirror_index = 0;
-		     mirror_index < BTRFS_MAX_MIRRORS &&
-		     sblocks_for_recheck[mirror_index].page_count > 0;
-		     mirror_index++) {
-			struct scrub_block *sblock_other = sblocks_for_recheck +
-							   mirror_index;
-			struct scrub_page *page_other = sblock_other->pagev[
-							page_num];
-
-			if (!page_other->io_error) {
-				ret = scrub_repair_page_from_good_copy(
-					sblock_bad, sblock_other, page_num, 0);
-				if (0 == ret) {
-					page_bad->io_error = 0;
-					break; /* succeeded for this page */
+		/* try to find no-io-error page in mirrors */
+		if (page_bad->io_error) {
+			for (mirror_index = 0;
+			     mirror_index < BTRFS_MAX_MIRRORS &&
+			     sblocks_for_recheck[mirror_index].page_count > 0;
+			     mirror_index++) {
+				if (!sblocks_for_recheck[mirror_index].
+				    pagev[page_num]->io_error) {
+					sblock_other = sblocks_for_recheck +
+						       mirror_index;
+					break;
 				}
 			}
+			if (!sblock_other)
+				success = 0;
 		}
 
-		if (page_bad->io_error) {
-			/* did not find a mirror to copy the page from */
-			success = 0;
+		if (sctx->is_dev_replace) {
+			/*
+			 * did not find a mirror to fetch the page
+			 * from. scrub_write_page_to_dev_replace()
+			 * handles this case (page->io_error), by
+			 * filling the block with zeros before
+			 * submitting the write request
+			 */
+			if (!sblock_other)
+				sblock_other = sblock_bad;
+
+			if (scrub_write_page_to_dev_replace(sblock_other,
+							    page_num) != 0) {
+				btrfs_dev_replace_stats_inc(
+					&sctx->dev_root->
+					fs_info->dev_replace.
+					num_write_errors);
+				success = 0;
+			}
+		} else if (sblock_other) {
+			ret = scrub_repair_page_from_good_copy(sblock_bad,
+							       sblock_other,
+							       page_num, 0);
+			if (0 == ret)
+				page_bad->io_error = 0;
+			else
+				success = 0;
 		}
 	}
 
-	if (success) {
+	if (success && !sctx->is_dev_replace) {
 		if (is_metadata || have_csum) {
 			/*
 			 * need to verify the checksum now that all
@@ -1288,19 +1275,18 @@ out:
 	return 0;
 }
 
-static inline int scrub_nr_raid_mirrors(struct btrfs_bio *bbio, u64 *raid_map)
+static inline int scrub_nr_raid_mirrors(struct btrfs_bio *bbio)
 {
-	if (raid_map) {
-		if (raid_map[bbio->num_stripes - 1] == RAID6_Q_STRIPE)
-			return 3;
-		else
-			return 2;
-	} else {
+	if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID5)
+		return 2;
+	else if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID6)
+		return 3;
+	else
 		return (int)bbio->num_stripes;
-	}
 }
 
-static inline void scrub_stripe_index_and_offset(u64 logical, u64 *raid_map,
+static inline void scrub_stripe_index_and_offset(u64 logical, u64 map_type,
+						 u64 *raid_map,
 						 u64 mapped_length,
 						 int nstripes, int mirror,
 						 int *stripe_index,
@@ -1308,7 +1294,7 @@ static inline void scrub_stripe_index_and_offset(u64 logical, u64 *raid_map,
 {
 	int i;
 
-	if (raid_map) {
+	if (map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 		/* RAID5/6 */
 		for (i = 0; i < nstripes; i++) {
 			if (raid_map[i] == RAID6_Q_STRIPE ||
@@ -1329,72 +1315,65 @@ static inline void scrub_stripe_index_and_offset(u64 logical, u64 *raid_map,
 	}
 }
 
-static int scrub_setup_recheck_block(struct scrub_ctx *sctx,
-				     struct btrfs_fs_info *fs_info,
-				     struct scrub_block *original_sblock,
-				     u64 length, u64 logical,
+static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 				     struct scrub_block *sblocks_for_recheck)
 {
+	struct scrub_ctx *sctx = original_sblock->sctx;
+	struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info;
+	u64 length = original_sblock->page_count * PAGE_SIZE;
+	u64 logical = original_sblock->pagev[0]->logical;
 	struct scrub_recover *recover;
 	struct btrfs_bio *bbio;
-	u64 *raid_map;
 	u64 sublen;
 	u64 mapped_length;
 	u64 stripe_offset;
 	int stripe_index;
-	int page_index;
+	int page_index = 0;
 	int mirror_index;
 	int nmirrors;
 	int ret;
 
 	/*
-	 * note: the two members ref_count and outstanding_pages
+	 * note: the two members refs and outstanding_pages
 	 * are not used (and not set) in the blocks that are used for
 	 * the recheck procedure
 	 */
 
-	page_index = 0;
 	while (length > 0) {
 		sublen = min_t(u64, length, PAGE_SIZE);
 		mapped_length = sublen;
 		bbio = NULL;
-		raid_map = NULL;
 
 		/*
 		 * with a length of PAGE_SIZE, each returned stripe
 		 * represents one mirror
 		 */
 		ret = btrfs_map_sblock(fs_info, REQ_GET_READ_MIRRORS, logical,
-				       &mapped_length, &bbio, 0, &raid_map);
+				       &mapped_length, &bbio, 0, 1);
 		if (ret || !bbio || mapped_length < sublen) {
-			kfree(bbio);
-			kfree(raid_map);
+			btrfs_put_bbio(bbio);
 			return -EIO;
 		}
 
 		recover = kzalloc(sizeof(struct scrub_recover), GFP_NOFS);
 		if (!recover) {
-			kfree(bbio);
-			kfree(raid_map);
+			btrfs_put_bbio(bbio);
 			return -ENOMEM;
 		}
 
 		atomic_set(&recover->refs, 1);
 		recover->bbio = bbio;
-		recover->raid_map = raid_map;
 		recover->map_length = mapped_length;
 
 		BUG_ON(page_index >= SCRUB_PAGES_PER_RD_BIO);
 
-		nmirrors = scrub_nr_raid_mirrors(bbio, raid_map);
+		nmirrors = min(scrub_nr_raid_mirrors(bbio), BTRFS_MAX_MIRRORS);
+
 		for (mirror_index = 0; mirror_index < nmirrors;
 		     mirror_index++) {
 			struct scrub_block *sblock;
 			struct scrub_page *page;
 
-			if (mirror_index >= BTRFS_MAX_MIRRORS)
-				continue;
-
 			sblock = sblocks_for_recheck + mirror_index;
 			sblock->sctx = sctx;
 			page = kzalloc(sizeof(*page), GFP_NOFS);
@@ -1410,9 +1389,12 @@ leave_nomem:
 			sblock->pagev[page_index] = page;
 			page->logical = logical;
 
-			scrub_stripe_index_and_offset(logical, raid_map,
+			scrub_stripe_index_and_offset(logical,
+						      bbio->map_type,
+						      bbio->raid_map,
 						      mapped_length,
-						      bbio->num_stripes,
+						      bbio->num_stripes -
+						      bbio->num_tgtdevs,
 						      mirror_index,
 						      &stripe_index,
 						      &stripe_offset);
@@ -1458,7 +1440,8 @@ static void scrub_bio_wait_endio(struct bio *bio, int error)
 
 static inline int scrub_is_page_on_raid56(struct scrub_page *page)
 {
-	return page->recover && page->recover->raid_map;
+	return page->recover &&
+	       (page->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK);
 }
 
 static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
@@ -1475,7 +1458,6 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
 	bio->bi_end_io = scrub_bio_wait_endio;
 
 	ret = raid56_parity_recover(fs_info->fs_root, bio, page->recover->bbio,
-				    page->recover->raid_map,
 				    page->recover->map_length,
 				    page->mirror_num, 0);
 	if (ret)
@@ -1615,8 +1597,7 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
 }
 
 static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
-					     struct scrub_block *sblock_good,
-					     int force_write)
+					     struct scrub_block *sblock_good)
 {
 	int page_num;
 	int ret = 0;
@@ -1626,8 +1607,7 @@ static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
 
 		ret_sub = scrub_repair_page_from_good_copy(sblock_bad,
 							   sblock_good,
-							   page_num,
-							   force_write);
+							   page_num, 1);
 		if (ret_sub)
 			ret = ret_sub;
 	}
@@ -2067,12 +2047,12 @@ static int scrub_checksum_super(struct scrub_block *sblock)
 
 static void scrub_block_get(struct scrub_block *sblock)
 {
-	atomic_inc(&sblock->ref_count);
+	atomic_inc(&sblock->refs);
 }
 
 static void scrub_block_put(struct scrub_block *sblock)
 {
-	if (atomic_dec_and_test(&sblock->ref_count)) {
+	if (atomic_dec_and_test(&sblock->refs)) {
 		int i;
 
 		if (sblock->sparity)
@@ -2086,12 +2066,12 @@ static void scrub_block_put(struct scrub_block *sblock)
 
 static void scrub_page_get(struct scrub_page *spage)
 {
-	atomic_inc(&spage->ref_count);
+	atomic_inc(&spage->refs);
 }
 
 static void scrub_page_put(struct scrub_page *spage)
 {
-	if (atomic_dec_and_test(&spage->ref_count)) {
+	if (atomic_dec_and_test(&spage->refs)) {
 		if (spage->page)
 			__free_page(spage->page);
 		kfree(spage);
@@ -2217,7 +2197,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 
 	/* one ref inside this function, plus one for each page added to
 	 * a bio later on */
-	atomic_set(&sblock->ref_count, 1);
+	atomic_set(&sblock->refs, 1);
 	sblock->sctx = sctx;
 	sblock->no_io_error_seen = 1;
 
@@ -2510,7 +2490,7 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
 
 	/* one ref inside this function, plus one for each page added to
 	 * a bio later on */
-	atomic_set(&sblock->ref_count, 1);
+	atomic_set(&sblock->refs, 1);
 	sblock->sctx = sctx;
 	sblock->no_io_error_seen = 1;
 	sblock->sparity = sparity;
@@ -2705,7 +2685,6 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 	struct btrfs_raid_bio *rbio;
 	struct scrub_page *spage;
 	struct btrfs_bio *bbio = NULL;
-	u64 *raid_map = NULL;
 	u64 length;
 	int ret;
 
@@ -2716,8 +2695,8 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 	length = sparity->logic_end - sparity->logic_start + 1;
 	ret = btrfs_map_sblock(sctx->dev_root->fs_info, WRITE,
 			       sparity->logic_start,
-			       &length, &bbio, 0, &raid_map);
-	if (ret || !bbio || !raid_map)
+			       &length, &bbio, 0, 1);
+	if (ret || !bbio || !bbio->raid_map)
 		goto bbio_out;
 
 	bio = btrfs_io_bio_alloc(GFP_NOFS, 0);
@@ -2729,8 +2708,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 	bio->bi_end_io = scrub_parity_bio_endio;
 
 	rbio = raid56_parity_alloc_scrub_rbio(sctx->dev_root, bio, bbio,
-					      raid_map, length,
-					      sparity->scrub_dev,
+					      length, sparity->scrub_dev,
 					      sparity->dbitmap,
 					      sparity->nsectors);
 	if (!rbio)
@@ -2747,8 +2725,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 rbio_out:
 	bio_put(bio);
 bbio_out:
-	kfree(bbio);
-	kfree(raid_map);
+	btrfs_put_bbio(bbio);
 	bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap,
 		  sparity->nsectors);
 	spin_lock(&sctx->stat_lock);
@@ -2765,12 +2742,12 @@ static inline int scrub_calc_parity_bitmap_len(int nsectors)
 
 static void scrub_parity_get(struct scrub_parity *sparity)
 {
-	atomic_inc(&sparity->ref_count);
+	atomic_inc(&sparity->refs);
 }
 
 static void scrub_parity_put(struct scrub_parity *sparity)
 {
-	if (!atomic_dec_and_test(&sparity->ref_count))
+	if (!atomic_dec_and_test(&sparity->refs))
 		return;
 
 	scrub_parity_check_and_repair(sparity);
@@ -2820,7 +2797,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 	sparity->scrub_dev = sdev;
 	sparity->logic_start = logic_start;
 	sparity->logic_end = logic_end;
-	atomic_set(&sparity->ref_count, 1);
+	atomic_set(&sparity->refs, 1);
 	INIT_LIST_HEAD(&sparity->spages);
 	sparity->dbitmap = sparity->bitmap;
 	sparity->ebitmap = (void *)sparity->bitmap + bitmap_len;
@@ -3037,8 +3014,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
 		increment = map->stripe_len;
 		mirror_num = num % map->num_stripes + 1;
-	} else if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
-				BTRFS_BLOCK_GROUP_RAID6)) {
+	} else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 		get_raid56_logic_offset(physical, num, map, &offset, NULL);
 		increment = map->stripe_len * nr_data_stripes(map);
 		mirror_num = 1;
@@ -3074,8 +3050,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	 */
 	logical = base + offset;
 	physical_end = physical + nstripes * map->stripe_len;
-	if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
-			 BTRFS_BLOCK_GROUP_RAID6)) {
+	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 		get_raid56_logic_offset(physical_end, num,
 					map, &logic_end, NULL);
 		logic_end += base;
@@ -3121,8 +3096,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	ret = 0;
 	while (physical < physical_end) {
 		/* for raid56, we skip parity stripe */
-		if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
-				BTRFS_BLOCK_GROUP_RAID6)) {
+		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 			ret = get_raid56_logic_offset(physical, num,
 					map, &logical, &stripe_logical);
 			logical += base;
@@ -3280,8 +3254,7 @@ again:
 			scrub_free_csums(sctx);
 			if (extent_logical + extent_len <
 			    key.objectid + bytes) {
-				if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
-					BTRFS_BLOCK_GROUP_RAID6)) {
+				if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 					/*
 					 * loop until we find next data stripe
 					 * or we have finished all stripes.
@@ -3775,7 +3748,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	scrub_workers_put(fs_info);
 	mutex_unlock(&fs_info->scrub_lock);
 
-	scrub_free_ctx(sctx);
+	scrub_put_ctx(sctx);
 
 	return ret;
 }
@@ -3881,14 +3854,14 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
 			      &mapped_length, &bbio, 0);
 	if (ret || !bbio || mapped_length < extent_len ||
 	    !bbio->stripes[0].dev->bdev) {
-		kfree(bbio);
+		btrfs_put_bbio(bbio);
 		return;
 	}
 
 	*extent_physical = bbio->stripes[0].physical;
 	*extent_mirror_num = bbio->mirror_num;
 	*extent_dev = bbio->stripes[0].dev;
-	kfree(bbio);
+	btrfs_put_bbio(bbio);
 }
 
 static int scrub_setup_wr_ctx(struct scrub_ctx *sctx,
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 804432dbc351..d6033f540cc7 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -230,6 +230,7 @@ struct pending_dir_move {
 	u64 parent_ino;
 	u64 ino;
 	u64 gen;
+	bool is_orphan;
 	struct list_head update_refs;
 };
 
@@ -2471,12 +2472,9 @@ verbose_printk("btrfs: send_utimes %llu\n", ino);
 	if (ret < 0)
 		goto out;
 	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
-	TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_ATIME, eb,
-			btrfs_inode_atime(ii));
-	TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_MTIME, eb,
-			btrfs_inode_mtime(ii));
-	TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_CTIME, eb,
-			btrfs_inode_ctime(ii));
+	TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_ATIME, eb, &ii->atime);
+	TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_MTIME, eb, &ii->mtime);
+	TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_CTIME, eb, &ii->ctime);
 	/* TODO Add otime support when the otime patches get into upstream */
 
 	ret = send_cmd(sctx);
@@ -2987,7 +2985,8 @@ static int add_pending_dir_move(struct send_ctx *sctx,
 				u64 ino_gen,
 				u64 parent_ino,
 				struct list_head *new_refs,
-				struct list_head *deleted_refs)
+				struct list_head *deleted_refs,
+				const bool is_orphan)
 {
 	struct rb_node **p = &sctx->pending_dir_moves.rb_node;
 	struct rb_node *parent = NULL;
@@ -3002,6 +3001,7 @@ static int add_pending_dir_move(struct send_ctx *sctx,
 	pm->parent_ino = parent_ino;
 	pm->ino = ino;
 	pm->gen = ino_gen;
+	pm->is_orphan = is_orphan;
 	INIT_LIST_HEAD(&pm->list);
 	INIT_LIST_HEAD(&pm->update_refs);
 	RB_CLEAR_NODE(&pm->node);
@@ -3134,16 +3134,20 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 	rmdir_ino = dm->rmdir_ino;
 	free_waiting_dir_move(sctx, dm);
 
-	ret = get_first_ref(sctx->parent_root, pm->ino,
-			    &parent_ino, &parent_gen, name);
-	if (ret < 0)
-		goto out;
-
-	ret = get_cur_path(sctx, parent_ino, parent_gen,
-			   from_path);
-	if (ret < 0)
-		goto out;
-	ret = fs_path_add_path(from_path, name);
+	if (pm->is_orphan) {
+		ret = gen_unique_name(sctx, pm->ino,
+				      pm->gen, from_path);
+	} else {
+		ret = get_first_ref(sctx->parent_root, pm->ino,
+				    &parent_ino, &parent_gen, name);
+		if (ret < 0)
+			goto out;
+		ret = get_cur_path(sctx, parent_ino, parent_gen,
+				   from_path);
+		if (ret < 0)
+			goto out;
+		ret = fs_path_add_path(from_path, name);
+	}
 	if (ret < 0)
 		goto out;
 
@@ -3153,7 +3157,8 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 		LIST_HEAD(deleted_refs);
 		ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID);
 		ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor,
-					   &pm->update_refs, &deleted_refs);
+					   &pm->update_refs, &deleted_refs,
+					   pm->is_orphan);
 		if (ret < 0)
 			goto out;
 		if (rmdir_ino) {
@@ -3286,6 +3291,127 @@ out:
 	return ret;
 }
 
+/*
+ * We might need to delay a directory rename even when no ancestor directory
+ * (in the send root) with a higher inode number than ours (sctx->cur_ino) was
+ * renamed. This happens when we rename a directory to the old name (the name
+ * in the parent root) of some other unrelated directory that got its rename
+ * delayed due to some ancestor with higher number that got renamed.
+ *
+ * Example:
+ *
+ * Parent snapshot:
+ * .                                       (ino 256)
+ * |---- a/                                (ino 257)
+ * |     |---- file                        (ino 260)
+ * |
+ * |---- b/                                (ino 258)
+ * |---- c/                                (ino 259)
+ *
+ * Send snapshot:
+ * .                                       (ino 256)
+ * |---- a/                                (ino 258)
+ * |---- x/                                (ino 259)
+ *       |---- y/                          (ino 257)
+ *             |----- file                 (ino 260)
+ *
+ * Here we can not rename 258 from 'b' to 'a' without the rename of inode 257
+ * from 'a' to 'x/y' happening first, which in turn depends on the rename of
+ * inode 259 from 'c' to 'x'. So the order of rename commands the send stream
+ * must issue is:
+ *
+ * 1 - rename 259 from 'c' to 'x'
+ * 2 - rename 257 from 'a' to 'x/y'
+ * 3 - rename 258 from 'b' to 'a'
+ *
+ * Returns 1 if the rename of sctx->cur_ino needs to be delayed, 0 if it can
+ * be done right away and < 0 on error.
+ */
+static int wait_for_dest_dir_move(struct send_ctx *sctx,
+				  struct recorded_ref *parent_ref,
+				  const bool is_orphan)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct btrfs_key di_key;
+	struct btrfs_dir_item *di;
+	u64 left_gen;
+	u64 right_gen;
+	int ret = 0;
+
+	if (RB_EMPTY_ROOT(&sctx->waiting_dir_moves))
+		return 0;
+
+	path = alloc_path_for_send();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = parent_ref->dir;
+	key.type = BTRFS_DIR_ITEM_KEY;
+	key.offset = btrfs_name_hash(parent_ref->name, parent_ref->name_len);
+
+	ret = btrfs_search_slot(NULL, sctx->parent_root, &key, path, 0, 0);
+	if (ret < 0) {
+		goto out;
+	} else if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
+
+	di = btrfs_match_dir_item_name(sctx->parent_root, path,
+				       parent_ref->name, parent_ref->name_len);
+	if (!di) {
+		ret = 0;
+		goto out;
+	}
+	/*
+	 * di_key.objectid has the number of the inode that has a dentry in the
+	 * parent directory with the same name that sctx->cur_ino is being
+	 * renamed to. We need to check if that inode is in the send root as
+	 * well and if it is currently marked as an inode with a pending rename,
+	 * if it is, we need to delay the rename of sctx->cur_ino as well, so
+	 * that it happens after that other inode is renamed.
+	 */
+	btrfs_dir_item_key_to_cpu(path->nodes[0], di, &di_key);
+	if (di_key.type != BTRFS_INODE_ITEM_KEY) {
+		ret = 0;
+		goto out;
+	}
+
+	ret = get_inode_info(sctx->parent_root, di_key.objectid, NULL,
+			     &left_gen, NULL, NULL, NULL, NULL);
+	if (ret < 0)
+		goto out;
+	ret = get_inode_info(sctx->send_root, di_key.objectid, NULL,
+			     &right_gen, NULL, NULL, NULL, NULL);
+	if (ret < 0) {
+		if (ret == -ENOENT)
+			ret = 0;
+		goto out;
+	}
+
+	/* Different inode, no need to delay the rename of sctx->cur_ino */
+	if (right_gen != left_gen) {
+		ret = 0;
+		goto out;
+	}
+
+	if (is_waiting_for_move(sctx, di_key.objectid)) {
+		ret = add_pending_dir_move(sctx,
+					   sctx->cur_ino,
+					   sctx->cur_inode_gen,
+					   di_key.objectid,
+					   &sctx->new_refs,
+					   &sctx->deleted_refs,
+					   is_orphan);
+		if (!ret)
+			ret = 1;
+	}
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 static int wait_for_parent_move(struct send_ctx *sctx,
 				struct recorded_ref *parent_ref)
 {
@@ -3352,7 +3478,8 @@ out:
 					   sctx->cur_inode_gen,
 					   ino,
 					   &sctx->new_refs,
-					   &sctx->deleted_refs);
+					   &sctx->deleted_refs,
+					   false);
 		if (!ret)
 			ret = 1;
 	}
@@ -3375,6 +3502,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 	int did_overwrite = 0;
 	int is_orphan = 0;
 	u64 last_dir_ino_rm = 0;
+	bool can_rename = true;
 
 verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 
@@ -3493,12 +3621,22 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 			}
 		}
 
+		if (S_ISDIR(sctx->cur_inode_mode) && sctx->parent_root) {
+			ret = wait_for_dest_dir_move(sctx, cur, is_orphan);
+			if (ret < 0)
+				goto out;
+			if (ret == 1) {
+				can_rename = false;
+				*pending_move = 1;
+			}
+		}
+
 		/*
 		 * link/move the ref to the new place. If we have an orphan
 		 * inode, move it and update valid_path. If not, link or move
 		 * it depending on the inode mode.
 		 */
-		if (is_orphan) {
+		if (is_orphan && can_rename) {
 			ret = send_rename(sctx, valid_path, cur->full_path);
 			if (ret < 0)
 				goto out;
@@ -3506,7 +3644,7 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 			ret = fs_path_copy(valid_path, cur->full_path);
 			if (ret < 0)
 				goto out;
-		} else {
+		} else if (can_rename) {
 			if (S_ISDIR(sctx->cur_inode_mode)) {
 				/*
 				 * Dirs can't be linked, so move it. For moved
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 6f49b2872a64..05fef198ff94 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1958,11 +1958,6 @@ static int btrfs_freeze(struct super_block *sb)
 	return btrfs_commit_transaction(trans, root);
 }
 
-static int btrfs_unfreeze(struct super_block *sb)
-{
-	return 0;
-}
-
 static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
@@ -2011,7 +2006,6 @@ static const struct super_operations btrfs_super_ops = {
 	.statfs		= btrfs_statfs,
 	.remount_fs	= btrfs_remount,
 	.freeze_fs	= btrfs_freeze,
-	.unfreeze_fs	= btrfs_unfreeze,
 };
 
 static const struct file_operations btrfs_ctl_fops = {
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 92db3f648df4..94edb0a2a026 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -733,10 +733,18 @@ int btrfs_init_sysfs(void)
 
 	ret = btrfs_init_debugfs();
 	if (ret)
-		return ret;
+		goto out1;
 
 	init_feature_attrs();
 	ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
+	if (ret)
+		goto out2;
+
+	return 0;
+out2:
+	debugfs_remove_recursive(btrfs_debugfs_root_dentry);
+out1:
+	kset_unregister(btrfs_kset);
 
 	return ret;
 }
diff --git a/fs/btrfs/tests/extent-buffer-tests.c b/fs/btrfs/tests/extent-buffer-tests.c
index cc286ce97d1e..f51963a8f929 100644
--- a/fs/btrfs/tests/extent-buffer-tests.c
+++ b/fs/btrfs/tests/extent-buffer-tests.c
@@ -53,7 +53,7 @@ static int test_btrfs_split_item(void)
 		return -ENOMEM;
 	}
 
-	path->nodes[0] = eb = alloc_dummy_extent_buffer(0, 4096);
+	path->nodes[0] = eb = alloc_dummy_extent_buffer(NULL, 4096);
 	if (!eb) {
 		test_msg("Could not allocate dummy buffer\n");
 		ret = -ENOMEM;
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 7e99c2f98dd0..9e9f2368177d 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -258,8 +258,7 @@ static int test_find_delalloc(void)
 	}
 	ret = 0;
 out_bits:
-	clear_extent_bits(&tmp, 0, total_dirty - 1,
-			  (unsigned long)-1, GFP_NOFS);
+	clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_NOFS);
 out:
 	if (locked_page)
 		page_cache_release(locked_page);
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 3ae0f5b8bb80..054fc0d97131 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -255,7 +255,7 @@ static noinline int test_btrfs_get_extent(void)
 		goto out;
 	}
 
-	root->node = alloc_dummy_extent_buffer(0, 4096);
+	root->node = alloc_dummy_extent_buffer(NULL, 4096);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		goto out;
@@ -843,7 +843,7 @@ static int test_hole_first(void)
 		goto out;
 	}
 
-	root->node = alloc_dummy_extent_buffer(0, 4096);
+	root->node = alloc_dummy_extent_buffer(NULL, 4096);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		goto out;
@@ -911,6 +911,197 @@ out:
 	return ret;
 }
 
+static int test_extent_accounting(void)
+{
+	struct inode *inode = NULL;
+	struct btrfs_root *root = NULL;
+	int ret = -ENOMEM;
+
+	inode = btrfs_new_test_inode();
+	if (!inode) {
+		test_msg("Couldn't allocate inode\n");
+		return ret;
+	}
+
+	root = btrfs_alloc_dummy_root();
+	if (IS_ERR(root)) {
+		test_msg("Couldn't allocate root\n");
+		goto out;
+	}
+
+	root->fs_info = btrfs_alloc_dummy_fs_info();
+	if (!root->fs_info) {
+		test_msg("Couldn't allocate dummy fs info\n");
+		goto out;
+	}
+
+	BTRFS_I(inode)->root = root;
+	btrfs_test_inode_set_ops(inode);
+
+	/* [BTRFS_MAX_EXTENT_SIZE] */
+	BTRFS_I(inode)->outstanding_extents++;
+	ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1,
+					NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 1) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 1, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* [BTRFS_MAX_EXTENT_SIZE][4k] */
+	BTRFS_I(inode)->outstanding_extents++;
+	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE,
+					BTRFS_MAX_EXTENT_SIZE + 4095, NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 2) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 2, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* [BTRFS_MAX_EXTENT_SIZE/2][4K HOLE][the rest] */
+	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
+			       BTRFS_MAX_EXTENT_SIZE >> 1,
+			       (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+			       EXTENT_DELALLOC | EXTENT_DIRTY |
+			       EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0,
+			       NULL, GFP_NOFS);
+	if (ret) {
+		test_msg("clear_extent_bit returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 2) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 2, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* [BTRFS_MAX_EXTENT_SIZE][4K] */
+	BTRFS_I(inode)->outstanding_extents++;
+	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1,
+					(BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+					NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 2) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 2, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/*
+	 * [BTRFS_MAX_EXTENT_SIZE+4K][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4K]
+	 *
+	 * I'm artificially adding 2 to outstanding_extents because in the
+	 * buffered IO case we'd add things up as we go, but I don't feel like
+	 * doing that here, this isn't the interesting case we want to test.
+	 */
+	BTRFS_I(inode)->outstanding_extents += 2;
+	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + 8192,
+					(BTRFS_MAX_EXTENT_SIZE << 1) + 12287,
+					NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 4) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 4, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* [BTRFS_MAX_EXTENT_SIZE+4k][4k][BTRFS_MAX_EXTENT_SIZE+4k] */
+	BTRFS_I(inode)->outstanding_extents++;
+	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
+					BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 3) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 3, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* [BTRFS_MAX_EXTENT_SIZE+4k][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4k] */
+	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
+			       BTRFS_MAX_EXTENT_SIZE+4096,
+			       BTRFS_MAX_EXTENT_SIZE+8191,
+			       EXTENT_DIRTY | EXTENT_DELALLOC |
+			       EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
+			       NULL, GFP_NOFS);
+	if (ret) {
+		test_msg("clear_extent_bit returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 4) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 4, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/*
+	 * Refill the hole again just for good measure, because I thought it
+	 * might fail and I'd rather satisfy my paranoia at this point.
+	 */
+	BTRFS_I(inode)->outstanding_extents++;
+	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
+					BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 3) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 3, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* Empty */
+	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
+			       EXTENT_DIRTY | EXTENT_DELALLOC |
+			       EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
+			       NULL, GFP_NOFS);
+	if (ret) {
+		test_msg("clear_extent_bit returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 0, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+	ret = 0;
+out:
+	if (ret)
+		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
+				 EXTENT_DIRTY | EXTENT_DELALLOC |
+				 EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
+				 NULL, GFP_NOFS);
+	iput(inode);
+	btrfs_free_dummy_root(root);
+	return ret;
+}
+
 int btrfs_test_inodes(void)
 {
 	int ret;
@@ -924,5 +1115,9 @@ int btrfs_test_inodes(void)
 	if (ret)
 		return ret;
 	test_msg("Running hole first btrfs_get_extent test\n");
-	return test_hole_first();
+	ret = test_hole_first();
+	if (ret)
+		return ret;
+	test_msg("Running outstanding_extents tests\n");
+	return test_extent_accounting();
 }
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index ec3dcb202357..73f299ebdabb 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -404,12 +404,22 @@ int btrfs_test_qgroups(void)
 		ret = -ENOMEM;
 		goto out;
 	}
+	/* We are using this root as our extent root */
+	root->fs_info->extent_root = root;
+
+	/*
+	 * Some of the paths we test assume we have a filled out fs_info, so we
+	 * just need to add the root in there so we don't panic.
+	 */
+	root->fs_info->tree_root = root;
+	root->fs_info->quota_root = root;
+	root->fs_info->quota_enabled = 1;
 
 	/*
 	 * Can't use bytenr 0, some things freak out
 	 * *cough*backref walking code*cough*
 	 */
-	root->node = alloc_test_extent_buffer(root->fs_info, 4096, 4096);
+	root->node = alloc_test_extent_buffer(root->fs_info, 4096);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		ret = -ENOMEM;
@@ -448,17 +458,6 @@ int btrfs_test_qgroups(void)
 		goto out;
 	}
 
-	/* We are using this root as our extent root */
-	root->fs_info->extent_root = root;
-
-	/*
-	 * Some of the paths we test assume we have a filled out fs_info, so we
-	 * just need to addt he root in there so we don't panic.
-	 */
-	root->fs_info->tree_root = root;
-	root->fs_info->quota_root = root;
-	root->fs_info->quota_enabled = 1;
-
 	test_msg("Running qgroup tests\n");
 	ret = test_no_shared_qgroup(root);
 	if (ret)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index e88b59d13439..8be4278e25e8 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -220,6 +220,7 @@ loop:
 	 * commit the transaction.
 	 */
 	atomic_set(&cur_trans->use_count, 2);
+	cur_trans->have_free_bgs = 0;
 	cur_trans->start_time = get_seconds();
 
 	cur_trans->delayed_refs.href_root = RB_ROOT;
@@ -248,6 +249,8 @@ loop:
 	INIT_LIST_HEAD(&cur_trans->pending_chunks);
 	INIT_LIST_HEAD(&cur_trans->switch_commits);
 	INIT_LIST_HEAD(&cur_trans->pending_ordered);
+	INIT_LIST_HEAD(&cur_trans->dirty_bgs);
+	spin_lock_init(&cur_trans->dirty_bgs_lock);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(&cur_trans->dirty_pages,
 			     fs_info->btree_inode->i_mapping);
@@ -1022,7 +1025,6 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
 	struct btrfs_root *tree_root = root->fs_info->tree_root;
 
 	old_root_used = btrfs_root_used(&root->root_item);
-	btrfs_write_dirty_block_groups(trans, root);
 
 	while (1) {
 		old_root_bytenr = btrfs_root_bytenr(&root->root_item);
@@ -1038,9 +1040,6 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
 			return ret;
 
 		old_root_used = btrfs_root_used(&root->root_item);
-		ret = btrfs_write_dirty_block_groups(trans, root);
-		if (ret)
-			return ret;
 	}
 
 	return 0;
@@ -1057,14 +1056,11 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
 					 struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct list_head *dirty_bgs = &trans->transaction->dirty_bgs;
 	struct list_head *next;
 	struct extent_buffer *eb;
 	int ret;
 
-	ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
-	if (ret)
-		return ret;
-
 	eb = btrfs_lock_root_node(fs_info->tree_root);
 	ret = btrfs_cow_block(trans, fs_info->tree_root, eb, NULL,
 			      0, &eb);
@@ -1088,15 +1084,20 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
 	if (ret)
 		return ret;
 
+	ret = btrfs_setup_space_cache(trans, root);
+	if (ret)
+		return ret;
+
 	/* run_qgroups might have added some more refs */
 	ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
 	if (ret)
 		return ret;
-
+again:
 	while (!list_empty(&fs_info->dirty_cowonly_roots)) {
 		next = fs_info->dirty_cowonly_roots.next;
 		list_del_init(next);
 		root = list_entry(next, struct btrfs_root, dirty_list);
+		clear_bit(BTRFS_ROOT_DIRTY, &root->state);
 
 		if (root != fs_info->extent_root)
 			list_add_tail(&root->dirty_list,
@@ -1104,8 +1105,23 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
 		ret = update_cowonly_root(trans, root);
 		if (ret)
 			return ret;
+		ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
+		if (ret)
+			return ret;
+	}
+
+	while (!list_empty(dirty_bgs)) {
+		ret = btrfs_write_dirty_block_groups(trans, root);
+		if (ret)
+			return ret;
+		ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
+		if (ret)
+			return ret;
 	}
 
+	if (!list_empty(&fs_info->dirty_cowonly_roots))
+		goto again;
+
 	list_add_tail(&fs_info->extent_root->dirty_list,
 		      &trans->transaction->switch_commits);
 	btrfs_after_dev_replace_commit(fs_info);
@@ -1803,6 +1819,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 		wait_for_commit(root, cur_trans);
 
+		if (unlikely(cur_trans->aborted))
+			ret = cur_trans->aborted;
+
 		btrfs_put_transaction(cur_trans);
 
 		return ret;
@@ -1983,6 +2002,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	switch_commit_roots(cur_trans, root->fs_info);
 
 	assert_qgroups_uptodate(trans);
+	ASSERT(list_empty(&cur_trans->dirty_bgs));
 	update_super_roots(root);
 
 	btrfs_set_super_log_root(root->fs_info->super_copy, 0);
@@ -2026,6 +2046,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	btrfs_finish_extent_commit(trans, root);
 
+	if (cur_trans->have_free_bgs)
+		btrfs_clear_space_info_full(root->fs_info);
+
 	root->fs_info->last_trans_committed = cur_trans->transid;
 	/*
 	 * We needn't acquire the lock here because there is no other task
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 00ed29c4b3f9..937050a2b68e 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -47,6 +47,11 @@ struct btrfs_transaction {
 	atomic_t num_writers;
 	atomic_t use_count;
 
+	/*
+	 * true if there is free bgs operations in this transaction
+	 */
+	int have_free_bgs;
+
 	/* Be protected by fs_info->trans_lock when we want to change it. */
 	enum btrfs_trans_state state;
 	struct list_head list;
@@ -58,6 +63,8 @@ struct btrfs_transaction {
 	struct list_head pending_chunks;
 	struct list_head pending_ordered;
 	struct list_head switch_commits;
+	struct list_head dirty_bgs;
+	spinlock_t dirty_bgs_lock;
 	struct btrfs_delayed_ref_root delayed_refs;
 	int aborted;
 };
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 1a9585d4380a..c5b8ba37f88e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -453,11 +453,13 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 insert:
 	btrfs_release_path(path);
 	/* try to insert the key into the destination tree */
+	path->skip_release_on_error = 1;
 	ret = btrfs_insert_empty_item(trans, root, path,
 				      key, item_size);
+	path->skip_release_on_error = 0;
 
 	/* make sure any existing item is the correct size */
-	if (ret == -EEXIST) {
+	if (ret == -EEXIST || ret == -EOVERFLOW) {
 		u32 found_size;
 		found_size = btrfs_item_size_nr(path->nodes[0],
 						path->slots[0]);
@@ -488,8 +490,20 @@ insert:
 		src_item = (struct btrfs_inode_item *)src_ptr;
 		dst_item = (struct btrfs_inode_item *)dst_ptr;
 
-		if (btrfs_inode_generation(eb, src_item) == 0)
+		if (btrfs_inode_generation(eb, src_item) == 0) {
+			struct extent_buffer *dst_eb = path->nodes[0];
+
+			if (S_ISREG(btrfs_inode_mode(eb, src_item)) &&
+			    S_ISREG(btrfs_inode_mode(dst_eb, dst_item))) {
+				struct btrfs_map_token token;
+				u64 ino_size = btrfs_inode_size(eb, src_item);
+
+				btrfs_init_map_token(&token);
+				btrfs_set_token_inode_size(dst_eb, dst_item,
+							   ino_size, &token);
+			}
 			goto no_copy;
+		}
 
 		if (overwrite_root &&
 		    S_ISDIR(btrfs_inode_mode(eb, src_item)) &&
@@ -844,7 +858,7 @@ out:
 static noinline int backref_in_log(struct btrfs_root *log,
 				   struct btrfs_key *key,
 				   u64 ref_objectid,
-				   char *name, int namelen)
+				   const char *name, int namelen)
 {
 	struct btrfs_path *path;
 	struct btrfs_inode_ref *ref;
@@ -998,7 +1012,7 @@ again:
 		base = btrfs_item_ptr_offset(leaf, path->slots[0]);
 
 		while (cur_offset < item_size) {
-			extref = (struct btrfs_inode_extref *)base + cur_offset;
+			extref = (struct btrfs_inode_extref *)(base + cur_offset);
 
 			victim_name_len = btrfs_inode_extref_name_len(leaf, extref);
 
@@ -1254,13 +1268,14 @@ out:
 }
 
 static int insert_orphan_item(struct btrfs_trans_handle *trans,
-			      struct btrfs_root *root, u64 offset)
+			      struct btrfs_root *root, u64 ino)
 {
 	int ret;
-	ret = btrfs_find_item(root, NULL, BTRFS_ORPHAN_OBJECTID,
-			offset, BTRFS_ORPHAN_ITEM_KEY, NULL);
-	if (ret > 0)
-		ret = btrfs_insert_orphan_item(trans, root, offset);
+
+	ret = btrfs_insert_orphan_item(trans, root, ino);
+	if (ret == -EEXIST)
+		ret = 0;
+
 	return ret;
 }
 
@@ -1287,6 +1302,7 @@ static int count_inode_extrefs(struct btrfs_root *root,
 		leaf = path->nodes[0];
 		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
 		ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+		cur_offset = 0;
 
 		while (cur_offset < item_size) {
 			extref = (struct btrfs_inode_extref *) (ptr + cur_offset);
@@ -1302,7 +1318,7 @@ static int count_inode_extrefs(struct btrfs_root *root,
 	}
 	btrfs_release_path(path);
 
-	if (ret < 0)
+	if (ret < 0 && ret != -ENOENT)
 		return ret;
 	return nlink;
 }
@@ -1394,9 +1410,6 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 	nlink = ret;
 
 	ret = count_inode_extrefs(root, inode, path);
-	if (ret == -ENOENT)
-		ret = 0;
-
 	if (ret < 0)
 		goto out;
 
@@ -1557,6 +1570,30 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans,
 }
 
 /*
+ * Return true if an inode reference exists in the log for the given name,
+ * inode and parent inode.
+ */
+static bool name_in_log_ref(struct btrfs_root *log_root,
+			    const char *name, const int name_len,
+			    const u64 dirid, const u64 ino)
+{
+	struct btrfs_key search_key;
+
+	search_key.objectid = ino;
+	search_key.type = BTRFS_INODE_REF_KEY;
+	search_key.offset = dirid;
+	if (backref_in_log(log_root, &search_key, dirid, name, name_len))
+		return true;
+
+	search_key.type = BTRFS_INODE_EXTREF_KEY;
+	search_key.offset = btrfs_extref_hash(dirid, name, name_len);
+	if (backref_in_log(log_root, &search_key, dirid, name, name_len))
+		return true;
+
+	return false;
+}
+
+/*
  * take a single entry in a log directory item and replay it into
  * the subvolume.
  *
@@ -1666,10 +1703,17 @@ out:
 	return ret;
 
 insert:
+	if (name_in_log_ref(root->log_root, name, name_len,
+			    key->objectid, log_key.objectid)) {
+		/* The dentry will be added later. */
+		ret = 0;
+		update_size = false;
+		goto out;
+	}
 	btrfs_release_path(path);
 	ret = insert_one_name(trans, root, path, key->objectid, key->offset,
 			      name, name_len, log_type, &log_key);
-	if (ret && ret != -ENOENT)
+	if (ret && ret != -ENOENT && ret != -EEXIST)
 		goto out;
 	update_size = false;
 	ret = 0;
@@ -2164,7 +2208,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 		parent = path->nodes[*level];
 		root_owner = btrfs_header_owner(parent);
 
-		next = btrfs_find_create_tree_block(root, bytenr, blocksize);
+		next = btrfs_find_create_tree_block(root, bytenr);
 		if (!next)
 			return -ENOMEM;
 
@@ -2416,8 +2460,8 @@ static void wait_for_writer(struct btrfs_trans_handle *trans,
 		mutex_unlock(&root->log_mutex);
 		if (atomic_read(&root->log_writers))
 			schedule();
-		mutex_lock(&root->log_mutex);
 		finish_wait(&root->log_writer_wait, &wait);
+		mutex_lock(&root->log_mutex);
 	}
 }
 
@@ -3219,7 +3263,8 @@ static int drop_objectid_items(struct btrfs_trans_handle *trans,
 static void fill_inode_item(struct btrfs_trans_handle *trans,
 			    struct extent_buffer *leaf,
 			    struct btrfs_inode_item *item,
-			    struct inode *inode, int log_inode_only)
+			    struct inode *inode, int log_inode_only,
+			    u64 logged_isize)
 {
 	struct btrfs_map_token token;
 
@@ -3232,7 +3277,7 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 		 * to say 'update this inode with these values'
 		 */
 		btrfs_set_token_inode_generation(leaf, item, 0, &token);
-		btrfs_set_token_inode_size(leaf, item, 0, &token);
+		btrfs_set_token_inode_size(leaf, item, logged_isize, &token);
 	} else {
 		btrfs_set_token_inode_generation(leaf, item,
 						 BTRFS_I(inode)->generation,
@@ -3245,19 +3290,19 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 	btrfs_set_token_inode_mode(leaf, item, inode->i_mode, &token);
 	btrfs_set_token_inode_nlink(leaf, item, inode->i_nlink, &token);
 
-	btrfs_set_token_timespec_sec(leaf, btrfs_inode_atime(item),
+	btrfs_set_token_timespec_sec(leaf, &item->atime,
 				     inode->i_atime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_atime(item),
+	btrfs_set_token_timespec_nsec(leaf, &item->atime,
 				      inode->i_atime.tv_nsec, &token);
 
-	btrfs_set_token_timespec_sec(leaf, btrfs_inode_mtime(item),
+	btrfs_set_token_timespec_sec(leaf, &item->mtime,
 				     inode->i_mtime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_mtime(item),
+	btrfs_set_token_timespec_nsec(leaf, &item->mtime,
 				      inode->i_mtime.tv_nsec, &token);
 
-	btrfs_set_token_timespec_sec(leaf, btrfs_inode_ctime(item),
+	btrfs_set_token_timespec_sec(leaf, &item->ctime,
 				     inode->i_ctime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, btrfs_inode_ctime(item),
+	btrfs_set_token_timespec_nsec(leaf, &item->ctime,
 				      inode->i_ctime.tv_nsec, &token);
 
 	btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
@@ -3284,7 +3329,7 @@ static int log_inode_item(struct btrfs_trans_handle *trans,
 		return ret;
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				    struct btrfs_inode_item);
-	fill_inode_item(trans, path->nodes[0], inode_item, inode, 0);
+	fill_inode_item(trans, path->nodes[0], inode_item, inode, 0, 0);
 	btrfs_release_path(path);
 	return 0;
 }
@@ -3293,7 +3338,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 			       struct inode *inode,
 			       struct btrfs_path *dst_path,
 			       struct btrfs_path *src_path, u64 *last_extent,
-			       int start_slot, int nr, int inode_only)
+			       int start_slot, int nr, int inode_only,
+			       u64 logged_isize)
 {
 	unsigned long src_offset;
 	unsigned long dst_offset;
@@ -3350,7 +3396,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 						    dst_path->slots[0],
 						    struct btrfs_inode_item);
 			fill_inode_item(trans, dst_path->nodes[0], inode_item,
-					inode, inode_only == LOG_INODE_EXISTS);
+					inode, inode_only == LOG_INODE_EXISTS,
+					logged_isize);
 		} else {
 			copy_extent_buffer(dst_path->nodes[0], src, dst_offset,
 					   src_offset, ins_sizes[i]);
@@ -3902,6 +3949,33 @@ process:
 	return ret;
 }
 
+static int logged_inode_size(struct btrfs_root *log, struct inode *inode,
+			     struct btrfs_path *path, u64 *size_ret)
+{
+	struct btrfs_key key;
+	int ret;
+
+	key.objectid = btrfs_ino(inode);
+	key.type = BTRFS_INODE_ITEM_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, log, &key, path, 0, 0);
+	if (ret < 0) {
+		return ret;
+	} else if (ret > 0) {
+		*size_ret = i_size_read(inode);
+	} else {
+		struct btrfs_inode_item *item;
+
+		item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+				      struct btrfs_inode_item);
+		*size_ret = btrfs_inode_size(path->nodes[0], item);
+	}
+
+	btrfs_release_path(path);
+	return 0;
+}
+
 /* log a single inode in the tree log.
  * At least one parent directory for this inode must exist in the tree
  * or be logged already.
@@ -3939,6 +4013,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	bool fast_search = false;
 	u64 ino = btrfs_ino(inode);
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	u64 logged_isize = 0;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -3966,15 +4041,22 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		max_key.type = (u8)-1;
 	max_key.offset = (u64)-1;
 
-	/* Only run delayed items if we are a dir or a new file */
+	/*
+	 * Only run delayed items if we are a dir or a new file.
+	 * Otherwise commit the delayed inode only, which is needed in
+	 * order for the log replay code to mark inodes for link count
+	 * fixup (create temporary BTRFS_TREE_LOG_FIXUP_OBJECTID items).
+	 */
 	if (S_ISDIR(inode->i_mode) ||
-	    BTRFS_I(inode)->generation > root->fs_info->last_trans_committed) {
+	    BTRFS_I(inode)->generation > root->fs_info->last_trans_committed)
 		ret = btrfs_commit_inode_delayed_items(trans, inode);
-		if (ret) {
-			btrfs_free_path(path);
-			btrfs_free_path(dst_path);
-			return ret;
-		}
+	else
+		ret = btrfs_commit_inode_delayed_inode(inode);
+
+	if (ret) {
+		btrfs_free_path(path);
+		btrfs_free_path(dst_path);
+		return ret;
 	}
 
 	mutex_lock(&BTRFS_I(inode)->log_mutex);
@@ -3988,22 +4070,56 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	if (S_ISDIR(inode->i_mode)) {
 		int max_key_type = BTRFS_DIR_LOG_INDEX_KEY;
 
-		if (inode_only == LOG_INODE_EXISTS)
-			max_key_type = BTRFS_XATTR_ITEM_KEY;
+		if (inode_only == LOG_INODE_EXISTS) {
+			max_key_type = BTRFS_INODE_EXTREF_KEY;
+			max_key.type = max_key_type;
+		}
 		ret = drop_objectid_items(trans, log, path, ino, max_key_type);
 	} else {
-		if (test_and_clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-				       &BTRFS_I(inode)->runtime_flags)) {
-			clear_bit(BTRFS_INODE_COPY_EVERYTHING,
-				  &BTRFS_I(inode)->runtime_flags);
-			ret = btrfs_truncate_inode_items(trans, log,
-							 inode, 0, 0);
-		} else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING,
-					      &BTRFS_I(inode)->runtime_flags) ||
+		if (inode_only == LOG_INODE_EXISTS) {
+			/*
+			 * Make sure the new inode item we write to the log has
+			 * the same isize as the current one (if it exists).
+			 * This is necessary to prevent data loss after log
+			 * replay, and also to prevent doing a wrong expanding
+			 * truncate - for e.g. create file, write 4K into offset
+			 * 0, fsync, write 4K into offset 4096, add hard link,
+			 * fsync some other file (to sync log), power fail - if
+			 * we use the inode's current i_size, after log replay
+			 * we get a 8Kb file, with the last 4Kb extent as a hole
+			 * (zeroes), as if an expanding truncate happened,
+			 * instead of getting a file of 4Kb only.
+			 */
+			err = logged_inode_size(log, inode, path,
+						&logged_isize);
+			if (err)
+				goto out_unlock;
+		}
+		if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+			     &BTRFS_I(inode)->runtime_flags)) {
+			if (inode_only == LOG_INODE_EXISTS) {
+				max_key.type = BTRFS_INODE_EXTREF_KEY;
+				ret = drop_objectid_items(trans, log, path, ino,
+							  max_key.type);
+			} else {
+				clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+					  &BTRFS_I(inode)->runtime_flags);
+				clear_bit(BTRFS_INODE_COPY_EVERYTHING,
+					  &BTRFS_I(inode)->runtime_flags);
+				ret = btrfs_truncate_inode_items(trans, log,
+								 inode, 0, 0);
+			}
+		} else if (test_bit(BTRFS_INODE_COPY_EVERYTHING,
+				    &BTRFS_I(inode)->runtime_flags) ||
 			   inode_only == LOG_INODE_EXISTS) {
-			if (inode_only == LOG_INODE_ALL)
+			if (inode_only == LOG_INODE_ALL) {
+				clear_bit(BTRFS_INODE_COPY_EVERYTHING,
+					  &BTRFS_I(inode)->runtime_flags);
 				fast_search = true;
-			max_key.type = BTRFS_XATTR_ITEM_KEY;
+				max_key.type = BTRFS_XATTR_ITEM_KEY;
+			} else {
+				max_key.type = BTRFS_INODE_EXTREF_KEY;
+			}
 			ret = drop_objectid_items(trans, log, path, ino,
 						  max_key.type);
 		} else {
@@ -4047,7 +4163,8 @@ again:
 		}
 
 		ret = copy_items(trans, inode, dst_path, path, &last_extent,
-				 ins_start_slot, ins_nr, inode_only);
+				 ins_start_slot, ins_nr, inode_only,
+				 logged_isize);
 		if (ret < 0) {
 			err = ret;
 			goto out_unlock;
@@ -4071,7 +4188,7 @@ next_slot:
 		if (ins_nr) {
 			ret = copy_items(trans, inode, dst_path, path,
 					 &last_extent, ins_start_slot,
-					 ins_nr, inode_only);
+					 ins_nr, inode_only, logged_isize);
 			if (ret < 0) {
 				err = ret;
 				goto out_unlock;
@@ -4092,7 +4209,8 @@ next_slot:
 	}
 	if (ins_nr) {
 		ret = copy_items(trans, inode, dst_path, path, &last_extent,
-				 ins_start_slot, ins_nr, inode_only);
+				 ins_start_slot, ins_nr, inode_only,
+				 logged_isize);
 		if (ret < 0) {
 			err = ret;
 			goto out_unlock;
@@ -4273,6 +4391,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	struct dentry *old_parent = NULL;
 	int ret = 0;
 	u64 last_committed = root->fs_info->last_trans_committed;
+	const struct dentry * const first_parent = parent;
+	const bool did_unlink = (BTRFS_I(inode)->last_unlink_trans >
+				 last_committed);
 
 	sb = inode->i_sb;
 
@@ -4328,7 +4449,6 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		goto end_trans;
 	}
 
-	inode_only = LOG_INODE_EXISTS;
 	while (1) {
 		if (!parent || !parent->d_inode || sb != parent->d_inode->i_sb)
 			break;
@@ -4337,8 +4457,22 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		if (root != BTRFS_I(inode)->root)
 			break;
 
+		/*
+		 * On unlink we must make sure our immediate parent directory
+		 * inode is fully logged. This is to prevent leaving dangling
+		 * directory index entries and a wrong directory inode's i_size.
+		 * Not doing so can result in a directory being impossible to
+		 * delete after log replay (rmdir will always fail with error
+		 * -ENOTEMPTY).
+		 */
+		if (did_unlink && parent == first_parent)
+			inode_only = LOG_INODE_ALL;
+		else
+			inode_only = LOG_INODE_EXISTS;
+
 		if (BTRFS_I(inode)->generation >
-		    root->fs_info->last_trans_committed) {
+		    root->fs_info->last_trans_committed ||
+		    inode_only == LOG_INODE_ALL) {
 			ret = btrfs_log_inode(trans, root, inode, inode_only,
 					      0, LLONG_MAX, ctx);
 			if (ret)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 50c5a8762aed..8222f6f74147 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1310,6 +1310,8 @@ again:
 	if (ret) {
 		btrfs_error(root->fs_info, ret,
 			    "Failed to remove dev extent item");
+	} else {
+		trans->transaction->have_free_bgs = 1;
 	}
 out:
 	btrfs_free_path(path);
@@ -4196,7 +4198,7 @@ static u32 find_raid56_stripe_len(u32 data_devices, u32 dev_stripe_target)
 
 static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type)
 {
-	if (!(type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)))
+	if (!(type & BTRFS_BLOCK_GROUP_RAID56_MASK))
 		return;
 
 	btrfs_set_fs_incompat(info, RAID56);
@@ -4803,10 +4805,8 @@ unsigned long btrfs_full_stripe_len(struct btrfs_root *root,
 
 	BUG_ON(em->start > logical || em->start + em->len < logical);
 	map = (struct map_lookup *)em->bdev;
-	if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
-			 BTRFS_BLOCK_GROUP_RAID6)) {
+	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		len = map->stripe_len * nr_data_stripes(map);
-	}
 	free_extent_map(em);
 	return len;
 }
@@ -4826,8 +4826,7 @@ int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
 
 	BUG_ON(em->start > logical || em->start + em->len < logical);
 	map = (struct map_lookup *)em->bdev;
-	if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
-			 BTRFS_BLOCK_GROUP_RAID6))
+	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		ret = 1;
 	free_extent_map(em);
 	return ret;
@@ -4876,32 +4875,24 @@ static inline int parity_smaller(u64 a, u64 b)
 }
 
 /* Bubble-sort the stripe set to put the parity/syndrome stripes last */
-static void sort_parity_stripes(struct btrfs_bio *bbio, u64 *raid_map)
+static void sort_parity_stripes(struct btrfs_bio *bbio, int num_stripes)
 {
 	struct btrfs_bio_stripe s;
-	int real_stripes = bbio->num_stripes - bbio->num_tgtdevs;
 	int i;
 	u64 l;
 	int again = 1;
-	int m;
 
 	while (again) {
 		again = 0;
-		for (i = 0; i < real_stripes - 1; i++) {
-			if (parity_smaller(raid_map[i], raid_map[i+1])) {
+		for (i = 0; i < num_stripes - 1; i++) {
+			if (parity_smaller(bbio->raid_map[i],
+					   bbio->raid_map[i+1])) {
 				s = bbio->stripes[i];
-				l = raid_map[i];
+				l = bbio->raid_map[i];
 				bbio->stripes[i] = bbio->stripes[i+1];
-				raid_map[i] = raid_map[i+1];
+				bbio->raid_map[i] = bbio->raid_map[i+1];
 				bbio->stripes[i+1] = s;
-				raid_map[i+1] = l;
-
-				if (bbio->tgtdev_map) {
-					m = bbio->tgtdev_map[i];
-					bbio->tgtdev_map[i] =
-							bbio->tgtdev_map[i + 1];
-					bbio->tgtdev_map[i + 1] = m;
-				}
+				bbio->raid_map[i+1] = l;
 
 				again = 1;
 			}
@@ -4909,10 +4900,48 @@ static void sort_parity_stripes(struct btrfs_bio *bbio, u64 *raid_map)
 	}
 }
 
+static struct btrfs_bio *alloc_btrfs_bio(int total_stripes, int real_stripes)
+{
+	struct btrfs_bio *bbio = kzalloc(
+		 /* the size of the btrfs_bio */
+		sizeof(struct btrfs_bio) +
+		/* plus the variable array for the stripes */
+		sizeof(struct btrfs_bio_stripe) * (total_stripes) +
+		/* plus the variable array for the tgt dev */
+		sizeof(int) * (real_stripes) +
+		/*
+		 * plus the raid_map, which includes both the tgt dev
+		 * and the stripes
+		 */
+		sizeof(u64) * (total_stripes),
+		GFP_NOFS);
+	if (!bbio)
+		return NULL;
+
+	atomic_set(&bbio->error, 0);
+	atomic_set(&bbio->refs, 1);
+
+	return bbio;
+}
+
+void btrfs_get_bbio(struct btrfs_bio *bbio)
+{
+	WARN_ON(!atomic_read(&bbio->refs));
+	atomic_inc(&bbio->refs);
+}
+
+void btrfs_put_bbio(struct btrfs_bio *bbio)
+{
+	if (!bbio)
+		return;
+	if (atomic_dec_and_test(&bbio->refs))
+		kfree(bbio);
+}
+
 static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			     u64 logical, u64 *length,
 			     struct btrfs_bio **bbio_ret,
-			     int mirror_num, u64 **raid_map_ret)
+			     int mirror_num, int need_raid_map)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
@@ -4925,7 +4954,6 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 	u64 stripe_nr_orig;
 	u64 stripe_nr_end;
 	u64 stripe_len;
-	u64 *raid_map = NULL;
 	int stripe_index;
 	int i;
 	int ret = 0;
@@ -4976,7 +5004,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 	stripe_offset = offset - stripe_offset;
 
 	/* if we're here for raid56, we need to know the stripe aligned start */
-	if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)) {
+	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 		unsigned long full_stripe_len = stripe_len * nr_data_stripes(map);
 		raid56_full_stripe_start = offset;
 
@@ -4989,8 +5017,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 
 	if (rw & REQ_DISCARD) {
 		/* we don't discard raid56 yet */
-		if (map->type &
-		    (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)) {
+		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 			ret = -EOPNOTSUPP;
 			goto out;
 		}
@@ -5000,7 +5027,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		/* For writes to RAID[56], allow a full stripeset across all disks.
 		   For other RAID types and for RAID[56] reads, just allow a single
 		   stripe (on a single disk). */
-		if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6) &&
+		if ((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
 		    (rw & REQ_WRITE)) {
 			max_len = stripe_len * nr_data_stripes(map) -
 				(offset - raid56_full_stripe_start);
@@ -5047,7 +5074,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		u64 physical_of_found = 0;
 
 		ret = __btrfs_map_block(fs_info, REQ_GET_READ_MIRRORS,
-			     logical, &tmp_length, &tmp_bbio, 0, NULL);
+			     logical, &tmp_length, &tmp_bbio, 0, 0);
 		if (ret) {
 			WARN_ON(tmp_bbio != NULL);
 			goto out;
@@ -5061,7 +5088,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			 * is not left of the left cursor
 			 */
 			ret = -EIO;
-			kfree(tmp_bbio);
+			btrfs_put_bbio(tmp_bbio);
 			goto out;
 		}
 
@@ -5096,11 +5123,11 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		} else {
 			WARN_ON(1);
 			ret = -EIO;
-			kfree(tmp_bbio);
+			btrfs_put_bbio(tmp_bbio);
 			goto out;
 		}
 
-		kfree(tmp_bbio);
+		btrfs_put_bbio(tmp_bbio);
 	} else if (mirror_num > map->num_stripes) {
 		mirror_num = 0;
 	}
@@ -5166,15 +5193,10 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			mirror_num = stripe_index - old_stripe_index + 1;
 		}
 
-	} else if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
-				BTRFS_BLOCK_GROUP_RAID6)) {
-		u64 tmp;
-
-		if (raid_map_ret &&
+	} else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+		if (need_raid_map &&
 		    ((rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) ||
 		     mirror_num > 1)) {
-			int i, rot;
-
 			/* push stripe_nr back to the start of the full stripe */
 			stripe_nr = raid56_full_stripe_start;
 			do_div(stripe_nr, stripe_len * nr_data_stripes(map));
@@ -5183,32 +5205,12 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			num_stripes = map->num_stripes;
 			max_errors = nr_parity_stripes(map);
 
-			raid_map = kmalloc_array(num_stripes, sizeof(u64),
-					   GFP_NOFS);
-			if (!raid_map) {
-				ret = -ENOMEM;
-				goto out;
-			}
-
-			/* Work out the disk rotation on this stripe-set */
-			tmp = stripe_nr;
-			rot = do_div(tmp, num_stripes);
-
-			/* Fill in the logical address of each stripe */
-			tmp = stripe_nr * nr_data_stripes(map);
-			for (i = 0; i < nr_data_stripes(map); i++)
-				raid_map[(i+rot) % num_stripes] =
-					em->start + (tmp + i) * map->stripe_len;
-
-			raid_map[(i+rot) % map->num_stripes] = RAID5_P_STRIPE;
-			if (map->type & BTRFS_BLOCK_GROUP_RAID6)
-				raid_map[(i+rot+1) % num_stripes] =
-					RAID6_Q_STRIPE;
-
 			*length = map->stripe_len;
 			stripe_index = 0;
 			stripe_offset = 0;
 		} else {
+			u64 tmp;
+
 			/*
 			 * Mirror #0 or #1 means the original data block.
 			 * Mirror #2 is RAID5 parity block.
@@ -5246,17 +5248,42 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		tgtdev_indexes = num_stripes;
 	}
 
-	bbio = kzalloc(btrfs_bio_size(num_alloc_stripes, tgtdev_indexes),
-		       GFP_NOFS);
+	bbio = alloc_btrfs_bio(num_alloc_stripes, tgtdev_indexes);
 	if (!bbio) {
-		kfree(raid_map);
 		ret = -ENOMEM;
 		goto out;
 	}
-	atomic_set(&bbio->error, 0);
 	if (dev_replace_is_ongoing)
 		bbio->tgtdev_map = (int *)(bbio->stripes + num_alloc_stripes);
 
+	/* build raid_map */
+	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK &&
+	    need_raid_map && ((rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) ||
+	    mirror_num > 1)) {
+		u64 tmp;
+		int i, rot;
+
+		bbio->raid_map = (u64 *)((void *)bbio->stripes +
+				 sizeof(struct btrfs_bio_stripe) *
+				 num_alloc_stripes +
+				 sizeof(int) * tgtdev_indexes);
+
+		/* Work out the disk rotation on this stripe-set */
+		tmp = stripe_nr;
+		rot = do_div(tmp, num_stripes);
+
+		/* Fill in the logical address of each stripe */
+		tmp = stripe_nr * nr_data_stripes(map);
+		for (i = 0; i < nr_data_stripes(map); i++)
+			bbio->raid_map[(i+rot) % num_stripes] =
+				em->start + (tmp + i) * map->stripe_len;
+
+		bbio->raid_map[(i+rot) % map->num_stripes] = RAID5_P_STRIPE;
+		if (map->type & BTRFS_BLOCK_GROUP_RAID6)
+			bbio->raid_map[(i+rot+1) % num_stripes] =
+				RAID6_Q_STRIPE;
+	}
+
 	if (rw & REQ_DISCARD) {
 		int factor = 0;
 		int sub_stripes = 0;
@@ -5340,6 +5367,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 	if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS))
 		max_errors = btrfs_chunk_max_errors(map);
 
+	if (bbio->raid_map)
+		sort_parity_stripes(bbio, num_stripes);
+
 	tgtdev_indexes = 0;
 	if (dev_replace_is_ongoing && (rw & (REQ_WRITE | REQ_DISCARD)) &&
 	    dev_replace->tgtdev != NULL) {
@@ -5427,6 +5457,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 	}
 
 	*bbio_ret = bbio;
+	bbio->map_type = map->type;
 	bbio->num_stripes = num_stripes;
 	bbio->max_errors = max_errors;
 	bbio->mirror_num = mirror_num;
@@ -5443,10 +5474,6 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		bbio->stripes[0].physical = physical_to_patch_in_first_stripe;
 		bbio->mirror_num = map->num_stripes + 1;
 	}
-	if (raid_map) {
-		sort_parity_stripes(bbio, raid_map);
-		*raid_map_ret = raid_map;
-	}
 out:
 	if (dev_replace_is_ongoing)
 		btrfs_dev_replace_unlock(dev_replace);
@@ -5459,17 +5486,17 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		      struct btrfs_bio **bbio_ret, int mirror_num)
 {
 	return __btrfs_map_block(fs_info, rw, logical, length, bbio_ret,
-				 mirror_num, NULL);
+				 mirror_num, 0);
 }
 
 /* For Scrub/replace */
 int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int rw,
 		     u64 logical, u64 *length,
 		     struct btrfs_bio **bbio_ret, int mirror_num,
-		     u64 **raid_map_ret)
+		     int need_raid_map)
 {
 	return __btrfs_map_block(fs_info, rw, logical, length, bbio_ret,
-				 mirror_num, raid_map_ret);
+				 mirror_num, need_raid_map);
 }
 
 int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
@@ -5511,8 +5538,7 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 		do_div(length, map->num_stripes / map->sub_stripes);
 	else if (map->type & BTRFS_BLOCK_GROUP_RAID0)
 		do_div(length, map->num_stripes);
-	else if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
-			      BTRFS_BLOCK_GROUP_RAID6)) {
+	else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 		do_div(length, nr_data_stripes(map));
 		rmap_len = map->stripe_len * nr_data_stripes(map);
 	}
@@ -5565,7 +5591,7 @@ static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio, int e
 		bio_endio_nodec(bio, err);
 	else
 		bio_endio(bio, err);
-	kfree(bbio);
+	btrfs_put_bbio(bbio);
 }
 
 static void btrfs_end_bio(struct bio *bio, int err)
@@ -5808,7 +5834,6 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 	u64 logical = (u64)bio->bi_iter.bi_sector << 9;
 	u64 length = 0;
 	u64 map_length;
-	u64 *raid_map = NULL;
 	int ret;
 	int dev_nr = 0;
 	int total_devs = 1;
@@ -5819,7 +5844,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 
 	btrfs_bio_counter_inc_blocked(root->fs_info);
 	ret = __btrfs_map_block(root->fs_info, rw, logical, &map_length, &bbio,
-			      mirror_num, &raid_map);
+			      mirror_num, 1);
 	if (ret) {
 		btrfs_bio_counter_dec(root->fs_info);
 		return ret;
@@ -5832,15 +5857,13 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 	bbio->fs_info = root->fs_info;
 	atomic_set(&bbio->stripes_pending, bbio->num_stripes);
 
-	if (raid_map) {
+	if (bbio->raid_map) {
 		/* In this case, map_length has been set to the length of
 		   a single stripe; not the whole write */
 		if (rw & WRITE) {
-			ret = raid56_parity_write(root, bio, bbio,
-						  raid_map, map_length);
+			ret = raid56_parity_write(root, bio, bbio, map_length);
 		} else {
-			ret = raid56_parity_recover(root, bio, bbio,
-						    raid_map, map_length,
+			ret = raid56_parity_recover(root, bio, bbio, map_length,
 						    mirror_num, 1);
 		}
 
@@ -6238,17 +6261,22 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	struct extent_buffer *sb;
 	struct btrfs_disk_key *disk_key;
 	struct btrfs_chunk *chunk;
-	u8 *ptr;
-	unsigned long sb_ptr;
+	u8 *array_ptr;
+	unsigned long sb_array_offset;
 	int ret = 0;
 	u32 num_stripes;
 	u32 array_size;
 	u32 len = 0;
-	u32 cur;
+	u32 cur_offset;
 	struct btrfs_key key;
 
-	sb = btrfs_find_create_tree_block(root, BTRFS_SUPER_INFO_OFFSET,
-					  BTRFS_SUPER_INFO_SIZE);
+	ASSERT(BTRFS_SUPER_INFO_SIZE <= root->nodesize);
+	/*
+	 * This will create extent buffer of nodesize, superblock size is
+	 * fixed to BTRFS_SUPER_INFO_SIZE. If nodesize > sb size, this will
+	 * overallocate but we can keep it as-is, only the first page is used.
+	 */
+	sb = btrfs_find_create_tree_block(root, BTRFS_SUPER_INFO_OFFSET);
 	if (!sb)
 		return -ENOMEM;
 	btrfs_set_buffer_uptodate(sb);
@@ -6271,35 +6299,56 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE);
 	array_size = btrfs_super_sys_array_size(super_copy);
 
-	ptr = super_copy->sys_chunk_array;
-	sb_ptr = offsetof(struct btrfs_super_block, sys_chunk_array);
-	cur = 0;
+	array_ptr = super_copy->sys_chunk_array;
+	sb_array_offset = offsetof(struct btrfs_super_block, sys_chunk_array);
+	cur_offset = 0;
+
+	while (cur_offset < array_size) {
+		disk_key = (struct btrfs_disk_key *)array_ptr;
+		len = sizeof(*disk_key);
+		if (cur_offset + len > array_size)
+			goto out_short_read;
 
-	while (cur < array_size) {
-		disk_key = (struct btrfs_disk_key *)ptr;
 		btrfs_disk_key_to_cpu(&key, disk_key);
 
-		len = sizeof(*disk_key); ptr += len;
-		sb_ptr += len;
-		cur += len;
+		array_ptr += len;
+		sb_array_offset += len;
+		cur_offset += len;
 
 		if (key.type == BTRFS_CHUNK_ITEM_KEY) {
-			chunk = (struct btrfs_chunk *)sb_ptr;
+			chunk = (struct btrfs_chunk *)sb_array_offset;
+			/*
+			 * At least one btrfs_chunk with one stripe must be
+			 * present, exact stripe count check comes afterwards
+			 */
+			len = btrfs_chunk_item_size(1);
+			if (cur_offset + len > array_size)
+				goto out_short_read;
+
+			num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+			len = btrfs_chunk_item_size(num_stripes);
+			if (cur_offset + len > array_size)
+				goto out_short_read;
+
 			ret = read_one_chunk(root, &key, sb, chunk);
 			if (ret)
 				break;
-			num_stripes = btrfs_chunk_num_stripes(sb, chunk);
-			len = btrfs_chunk_item_size(num_stripes);
 		} else {
 			ret = -EIO;
 			break;
 		}
-		ptr += len;
-		sb_ptr += len;
-		cur += len;
+		array_ptr += len;
+		sb_array_offset += len;
+		cur_offset += len;
 	}
 	free_extent_buffer(sb);
 	return ret;
+
+out_short_read:
+	printk(KERN_ERR "BTRFS: sys_array too short to read %u bytes at offset %u\n",
+			len, cur_offset);
+	free_extent_buffer(sb);
+	return -EIO;
 }
 
 int btrfs_read_chunk_tree(struct btrfs_root *root)
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index d6fe73c0f4a2..83069dec6898 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -295,8 +295,10 @@ typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
 #define BTRFS_BIO_ORIG_BIO_SUBMITTED	(1 << 0)
 
 struct btrfs_bio {
+	atomic_t refs;
 	atomic_t stripes_pending;
 	struct btrfs_fs_info *fs_info;
+	u64 map_type; /* get from map_lookup->type */
 	bio_end_io_t *end_io;
 	struct bio *orig_bio;
 	unsigned long flags;
@@ -307,6 +309,12 @@ struct btrfs_bio {
 	int mirror_num;
 	int num_tgtdevs;
 	int *tgtdev_map;
+	/*
+	 * logical block numbers for the start of each stripe
+	 * The last one or two are p/q.  These are sorted,
+	 * so raid_map[0] is the start of our full stripe
+	 */
+	u64 *raid_map;
 	struct btrfs_bio_stripe stripes[];
 };
 
@@ -388,19 +396,15 @@ struct btrfs_balance_control {
 
 int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
 				   u64 end, u64 *length);
-
-#define btrfs_bio_size(total_stripes, real_stripes)		\
-	(sizeof(struct btrfs_bio) +				\
-	 (sizeof(struct btrfs_bio_stripe) * (total_stripes)) +	\
-	 (sizeof(int) * (real_stripes)))
-
+void btrfs_get_bbio(struct btrfs_bio *bbio);
+void btrfs_put_bbio(struct btrfs_bio *bbio);
 int btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		    u64 logical, u64 *length,
 		    struct btrfs_bio **bbio_ret, int mirror_num);
 int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int rw,
 		     u64 logical, u64 *length,
 		     struct btrfs_bio **bbio_ret, int mirror_num,
-		     u64 **raid_map_ret);
+		     int need_raid_map);
 int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 		     u64 chunk_start, u64 physical, u64 devid,
 		     u64 **logical, int *naddrs, int *stripe_len);
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 47b19465f0dc..883b93623bc5 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -111,6 +111,8 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 					name, name_len, -1);
 		if (!di && (flags & XATTR_REPLACE))
 			ret = -ENODATA;
+		else if (IS_ERR(di))
+			ret = PTR_ERR(di);
 		else if (di)
 			ret = btrfs_delete_one_dir_name(trans, root, path, di);
 		goto out;
@@ -127,10 +129,12 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 		ASSERT(mutex_is_locked(&inode->i_mutex));
 		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
 					name, name_len, 0);
-		if (!di) {
+		if (!di)
 			ret = -ENODATA;
+		else if (IS_ERR(di))
+			ret = PTR_ERR(di);
+		if (ret)
 			goto out;
-		}
 		btrfs_release_path(path);
 		di = NULL;
 	}
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index ce1b115dcc28..f601def05bdf 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -574,7 +574,7 @@ static int cachefiles_daemon_cull(struct cachefiles_cache *cache, char *args)
 	/* extract the directory dentry from the cwd */
 	get_fs_pwd(current->fs, &path);
 
-	if (!S_ISDIR(path.dentry->d_inode->i_mode))
+	if (!d_can_lookup(path.dentry))
 		goto notdir;
 
 	cachefiles_begin_secure(cache, &saved_cred);
@@ -646,7 +646,7 @@ static int cachefiles_daemon_inuse(struct cachefiles_cache *cache, char *args)
 	/* extract the directory dentry from the cwd */
 	get_fs_pwd(current->fs, &path);
 
-	if (!S_ISDIR(path.dentry->d_inode->i_mode))
+	if (!d_can_lookup(path.dentry))
 		goto notdir;
 
 	cachefiles_begin_secure(cache, &saved_cred);
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 1c7293c3a93a..232426214fdd 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -437,7 +437,7 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
 	if (!object->backer)
 		return -ENOBUFS;
 
-	ASSERT(S_ISREG(object->backer->d_inode->i_mode));
+	ASSERT(d_is_reg(object->backer));
 
 	fscache_set_store_limit(&object->fscache, ni_size);
 
@@ -501,7 +501,7 @@ static void cachefiles_invalidate_object(struct fscache_operation *op)
 	       op->object->debug_id, (unsigned long long)ni_size);
 
 	if (object->backer) {
-		ASSERT(S_ISREG(object->backer->d_inode->i_mode));
+		ASSERT(d_is_reg(object->backer));
 
 		fscache_set_store_limit(&object->fscache, ni_size);
 
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 7f8e83f9d74e..1e51714eb33e 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -277,7 +277,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
 	_debug("remove %p from %p", rep, dir);
 
 	/* non-directories can just be unlinked */
-	if (!S_ISDIR(rep->d_inode->i_mode)) {
+	if (!d_is_dir(rep)) {
 		_debug("unlink stale object");
 
 		path.mnt = cache->mnt;
@@ -323,7 +323,7 @@ try_again:
 		return 0;
 	}
 
-	if (!S_ISDIR(cache->graveyard->d_inode->i_mode)) {
+	if (!d_can_lookup(cache->graveyard)) {
 		unlock_rename(cache->graveyard, dir);
 		cachefiles_io_error(cache, "Graveyard no longer a directory");
 		return -EIO;
@@ -475,7 +475,7 @@ int cachefiles_walk_to_object(struct cachefiles_object *parent,
 	ASSERT(parent->dentry);
 	ASSERT(parent->dentry->d_inode);
 
-	if (!(S_ISDIR(parent->dentry->d_inode->i_mode))) {
+	if (!(d_is_dir(parent->dentry))) {
 		// TODO: convert file to dir
 		_leave("looking up in none directory");
 		return -ENOBUFS;
@@ -539,7 +539,7 @@ lookup_again:
 			_debug("mkdir -> %p{%p{ino=%lu}}",
 			       next, next->d_inode, next->d_inode->i_ino);
 
-		} else if (!S_ISDIR(next->d_inode->i_mode)) {
+		} else if (!d_can_lookup(next)) {
 			pr_err("inode %lu is not a directory\n",
 			       next->d_inode->i_ino);
 			ret = -ENOBUFS;
@@ -568,8 +568,8 @@ lookup_again:
 			_debug("create -> %p{%p{ino=%lu}}",
 			       next, next->d_inode, next->d_inode->i_ino);
 
-		} else if (!S_ISDIR(next->d_inode->i_mode) &&
-			   !S_ISREG(next->d_inode->i_mode)
+		} else if (!d_can_lookup(next) &&
+			   !d_is_reg(next)
 			   ) {
 			pr_err("inode %lu is not a file or directory\n",
 			       next->d_inode->i_ino);
@@ -642,7 +642,7 @@ lookup_again:
 
 	/* open a file interface onto a data file */
 	if (object->type != FSCACHE_COOKIE_TYPE_INDEX) {
-		if (S_ISREG(object->dentry->d_inode->i_mode)) {
+		if (d_is_reg(object->dentry)) {
 			const struct address_space_operations *aops;
 
 			ret = -EPERM;
@@ -763,7 +763,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
 	/* we need to make sure the subdir is a directory */
 	ASSERT(subdir->d_inode);
 
-	if (!S_ISDIR(subdir->d_inode->i_mode)) {
+	if (!d_can_lookup(subdir)) {
 		pr_err("%s is not a directory\n", dirname);
 		ret = -EIO;
 		goto check_error;
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 616db0e77b44..c6cd8d7a4eef 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -900,7 +900,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 		return -ENOBUFS;
 	}
 
-	ASSERT(S_ISREG(object->backer->d_inode->i_mode));
+	ASSERT(d_is_reg(object->backer));
 
 	cache = container_of(object->fscache.cache,
 			     struct cachefiles_cache, cache);
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 5bd853ba44ff..64fa248343f6 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -40,20 +40,6 @@ static inline void ceph_set_cached_acl(struct inode *inode,
 	spin_unlock(&ci->i_ceph_lock);
 }
 
-static inline struct posix_acl *ceph_get_cached_acl(struct inode *inode,
-							int type)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct posix_acl *acl = ACL_NOT_CACHED;
-
-	spin_lock(&ci->i_ceph_lock);
-	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0))
-		acl = get_cached_acl(inode, type);
-	spin_unlock(&ci->i_ceph_lock);
-
-	return acl;
-}
-
 struct posix_acl *ceph_get_acl(struct inode *inode, int type)
 {
 	int size;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index c81c0e004588..fd5599d32362 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -196,17 +196,22 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 	u64 len = PAGE_CACHE_SIZE;
 
 	if (off >= i_size_read(inode)) {
-		zero_user_segment(page, err, PAGE_CACHE_SIZE);
+		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 		SetPageUptodate(page);
 		return 0;
 	}
 
-	/*
-	 * Uptodate inline data should have been added into page cache
-	 * while getting Fcr caps.
-	 */
-	if (ci->i_inline_version != CEPH_INLINE_NONE)
-		return -EINVAL;
+	if (ci->i_inline_version != CEPH_INLINE_NONE) {
+		/*
+		 * Uptodate inline data should have been added
+		 * into page cache while getting Fcr caps.
+		 */
+		if (off == 0)
+			return -EINVAL;
+		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		SetPageUptodate(page);
+		return 0;
+	}
 
 	err = ceph_readpage_from_fscache(inode, page);
 	if (err == 0)
@@ -1569,7 +1574,6 @@ out:
 static struct vm_operations_struct ceph_vmops = {
 	.fault		= ceph_filemap_fault,
 	.page_mkwrite	= ceph_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 int ceph_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index b93c631c6c87..8172775428a0 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -577,7 +577,6 @@ void ceph_add_cap(struct inode *inode,
 		struct ceph_snap_realm *realm = ceph_lookup_snap_realm(mdsc,
 							       realmino);
 		if (realm) {
-			ceph_get_snap_realm(mdsc, realm);
 			spin_lock(&realm->inodes_with_caps_lock);
 			ci->i_snap_realm = realm;
 			list_add(&ci->i_snap_realm_item,
@@ -1451,8 +1450,8 @@ static int __mark_caps_flushing(struct inode *inode,
 	spin_lock(&mdsc->cap_dirty_lock);
 	list_del_init(&ci->i_dirty_item);
 
-	ci->i_cap_flush_seq = ++mdsc->cap_flush_seq;
 	if (list_empty(&ci->i_flushing_item)) {
+		ci->i_cap_flush_seq = ++mdsc->cap_flush_seq;
 		list_add_tail(&ci->i_flushing_item, &session->s_cap_flushing);
 		mdsc->num_cap_flushing++;
 		dout(" inode %p now flushing seq %lld\n", inode,
@@ -2073,17 +2072,16 @@ static void __take_cap_refs(struct ceph_inode_info *ci, int got)
  * requested from the MDS.
  */
 static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
-			    loff_t endoff, int *got, struct page **pinned_page,
-			    int *check_max, int *err)
+			    loff_t endoff, int *got, int *check_max, int *err)
 {
 	struct inode *inode = &ci->vfs_inode;
 	int ret = 0;
-	int have, implemented, _got = 0;
+	int have, implemented;
 	int file_wanted;
 
 	dout("get_cap_refs %p need %s want %s\n", inode,
 	     ceph_cap_string(need), ceph_cap_string(want));
-again:
+
 	spin_lock(&ci->i_ceph_lock);
 
 	/* make sure file is actually open */
@@ -2138,50 +2136,34 @@ again:
 		     inode, ceph_cap_string(have), ceph_cap_string(not),
 		     ceph_cap_string(revoking));
 		if ((revoking & not) == 0) {
-			_got = need | (have & want);
-			__take_cap_refs(ci, _got);
+			*got = need | (have & want);
+			__take_cap_refs(ci, *got);
 			ret = 1;
 		}
 	} else {
+		int session_readonly = false;
+		if ((need & CEPH_CAP_FILE_WR) && ci->i_auth_cap) {
+			struct ceph_mds_session *s = ci->i_auth_cap->session;
+			spin_lock(&s->s_cap_lock);
+			session_readonly = s->s_readonly;
+			spin_unlock(&s->s_cap_lock);
+		}
+		if (session_readonly) {
+			dout("get_cap_refs %p needed %s but mds%d readonly\n",
+			     inode, ceph_cap_string(need), ci->i_auth_cap->mds);
+			*err = -EROFS;
+			ret = 1;
+			goto out_unlock;
+		}
+
 		dout("get_cap_refs %p have %s needed %s\n", inode,
 		     ceph_cap_string(have), ceph_cap_string(need));
 	}
 out_unlock:
 	spin_unlock(&ci->i_ceph_lock);
 
-	if (ci->i_inline_version != CEPH_INLINE_NONE &&
-	    (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
-	    i_size_read(inode) > 0) {
-		int ret1;
-		struct page *page = find_get_page(inode->i_mapping, 0);
-		if (page) {
-			if (PageUptodate(page)) {
-				*pinned_page = page;
-				goto out;
-			}
-			page_cache_release(page);
-		}
-		/*
-		 * drop cap refs first because getattr while holding
-		 * caps refs can cause deadlock.
-		 */
-		ceph_put_cap_refs(ci, _got);
-		_got = 0;
-
-		/* getattr request will bring inline data into page cache */
-		ret1 = __ceph_do_getattr(inode, NULL,
-					 CEPH_STAT_CAP_INLINE_DATA, true);
-		if (ret1 >= 0) {
-			ret = 0;
-			goto again;
-		}
-		*err = ret1;
-		ret = 1;
-	}
-out:
 	dout("get_cap_refs %p ret %d got %s\n", inode,
-	     ret, ceph_cap_string(_got));
-	*got = _got;
+	     ret, ceph_cap_string(*got));
 	return ret;
 }
 
@@ -2221,22 +2203,52 @@ static void check_max_size(struct inode *inode, loff_t endoff)
 int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
 		  loff_t endoff, int *got, struct page **pinned_page)
 {
-	int check_max, ret, err;
+	int _got, check_max, ret, err = 0;
 
 retry:
 	if (endoff > 0)
 		check_max_size(&ci->vfs_inode, endoff);
+	_got = 0;
 	check_max = 0;
-	err = 0;
 	ret = wait_event_interruptible(ci->i_cap_wq,
-				       try_get_cap_refs(ci, need, want, endoff,
-							got, pinned_page,
-							&check_max, &err));
+				try_get_cap_refs(ci, need, want, endoff,
+						 &_got, &check_max, &err));
 	if (err)
 		ret = err;
+	if (ret < 0)
+		return ret;
+
 	if (check_max)
 		goto retry;
-	return ret;
+
+	if (ci->i_inline_version != CEPH_INLINE_NONE &&
+	    (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
+	    i_size_read(&ci->vfs_inode) > 0) {
+		struct page *page = find_get_page(ci->vfs_inode.i_mapping, 0);
+		if (page) {
+			if (PageUptodate(page)) {
+				*pinned_page = page;
+				goto out;
+			}
+			page_cache_release(page);
+		}
+		/*
+		 * drop cap refs first because getattr while holding
+		 * caps refs can cause deadlock.
+		 */
+		ceph_put_cap_refs(ci, _got);
+		_got = 0;
+
+		/* getattr request will bring inline data into page cache */
+		ret = __ceph_do_getattr(&ci->vfs_inode, NULL,
+					CEPH_STAT_CAP_INLINE_DATA, true);
+		if (ret < 0)
+			return ret;
+		goto retry;
+	}
+out:
+	*got = _got;
+	return 0;
 }
 
 /*
@@ -2432,13 +2444,13 @@ static void invalidate_aliases(struct inode *inode)
  */
 static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			     struct inode *inode, struct ceph_mds_caps *grant,
-			     void *snaptrace, int snaptrace_len,
 			     u64 inline_version,
 			     void *inline_data, int inline_len,
 			     struct ceph_buffer *xattr_buf,
 			     struct ceph_mds_session *session,
 			     struct ceph_cap *cap, int issued)
 	__releases(ci->i_ceph_lock)
+	__releases(mdsc->snap_rwsem)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int mds = session->s_mds;
@@ -2639,10 +2651,6 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	spin_unlock(&ci->i_ceph_lock);
 
 	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
-		down_write(&mdsc->snap_rwsem);
-		ceph_update_snap_trace(mdsc, snaptrace,
-				       snaptrace + snaptrace_len, false);
-		downgrade_write(&mdsc->snap_rwsem);
 		kick_flushing_inode_caps(mdsc, session, inode);
 		up_read(&mdsc->snap_rwsem);
 		if (newcaps & ~issued)
@@ -3052,6 +3060,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	struct ceph_cap *cap;
 	struct ceph_mds_caps *h;
 	struct ceph_mds_cap_peer *peer = NULL;
+	struct ceph_snap_realm *realm;
 	int mds = session->s_mds;
 	int op, issued;
 	u32 seq, mseq;
@@ -3153,11 +3162,23 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		goto done_unlocked;
 
 	case CEPH_CAP_OP_IMPORT:
+		realm = NULL;
+		if (snaptrace_len) {
+			down_write(&mdsc->snap_rwsem);
+			ceph_update_snap_trace(mdsc, snaptrace,
+					       snaptrace + snaptrace_len,
+					       false, &realm);
+			downgrade_write(&mdsc->snap_rwsem);
+		} else {
+			down_read(&mdsc->snap_rwsem);
+		}
 		handle_cap_import(mdsc, inode, h, peer, session,
 				  &cap, &issued);
-		handle_cap_grant(mdsc, inode, h,  snaptrace, snaptrace_len,
+		handle_cap_grant(mdsc, inode, h,
 				 inline_version, inline_data, inline_len,
 				 msg->middle, session, cap, issued);
+		if (realm)
+			ceph_put_snap_realm(mdsc, realm);
 		goto done_unlocked;
 	}
 
@@ -3177,7 +3198,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	case CEPH_CAP_OP_GRANT:
 		__ceph_caps_issued(ci, &issued);
 		issued |= __ceph_caps_dirty(ci);
-		handle_cap_grant(mdsc, inode, h, NULL, 0,
+		handle_cap_grant(mdsc, inode, h,
 				 inline_version, inline_data, inline_len,
 				 msg->middle, session, cap, issued);
 		goto done_unlocked;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index c241603764fd..83e9976f7189 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -26,8 +26,6 @@
  * point by name.
  */
 
-const struct inode_operations ceph_dir_iops;
-const struct file_operations ceph_dir_fops;
 const struct dentry_operations ceph_dentry_ops;
 
 /*
@@ -672,13 +670,17 @@ int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
 		/*
 		 * We created the item, then did a lookup, and found
 		 * it was already linked to another inode we already
-		 * had in our cache (and thus got spliced).  Link our
-		 * dentry to that inode, but don't hash it, just in
-		 * case the VFS wants to dereference it.
+		 * had in our cache (and thus got spliced). To not
+		 * confuse VFS (especially when inode is a directory),
+		 * we don't link our dentry to that inode, return an
+		 * error instead.
+		 *
+		 * This event should be rare and it happens only when
+		 * we talk to old MDS. Recent MDS does not send traceless
+		 * reply for request that creates new inode.
 		 */
-		BUG_ON(!result->d_inode);
-		d_instantiate(dentry, result->d_inode);
-		return 0;
+		d_drop(result);
+		return -ESTALE;
 	}
 	return PTR_ERR(result);
 }
@@ -902,7 +904,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 	} else if (ceph_snap(dir) == CEPH_NOSNAP) {
 		dout("unlink/rmdir dir %p dn %p inode %p\n",
 		     dir, dentry, inode);
-		op = S_ISDIR(dentry->d_inode->i_mode) ?
+		op = d_is_dir(dentry) ?
 			CEPH_MDS_OP_RMDIR : CEPH_MDS_OP_UNLINK;
 	} else
 		goto out;
@@ -1335,6 +1337,13 @@ const struct file_operations ceph_dir_fops = {
 	.fsync = ceph_dir_fsync,
 };
 
+const struct file_operations ceph_snapdir_fops = {
+	.iterate = ceph_readdir,
+	.llseek = ceph_dir_llseek,
+	.open = ceph_open,
+	.release = ceph_release,
+};
+
 const struct inode_operations ceph_dir_iops = {
 	.lookup = ceph_lookup,
 	.permission = ceph_permission,
@@ -1357,6 +1366,14 @@ const struct inode_operations ceph_dir_iops = {
 	.atomic_open = ceph_atomic_open,
 };
 
+const struct inode_operations ceph_snapdir_iops = {
+	.lookup = ceph_lookup,
+	.permission = ceph_permission,
+	.getattr = ceph_getattr,
+	.mkdir = ceph_mkdir,
+	.rmdir = ceph_unlink,
+};
+
 const struct dentry_operations ceph_dentry_ops = {
 	.d_revalidate = ceph_d_revalidate,
 	.d_release = ceph_d_release,
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ce74b394b49d..d533075a823d 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -275,10 +275,10 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	err = ceph_mdsc_do_request(mdsc,
 				   (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
 				   req);
+	err = ceph_handle_snapdir(req, dentry, err);
 	if (err)
 		goto out_req;
 
-	err = ceph_handle_snapdir(req, dentry, err);
 	if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
 
@@ -292,7 +292,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	}
 	if (err)
 		goto out_req;
-	if (dn || dentry->d_inode == NULL || S_ISLNK(dentry->d_inode->i_mode)) {
+	if (dn || dentry->d_inode == NULL || d_is_symlink(dentry)) {
 		/* make vfs retry on splice, ENOENT, or symlink */
 		dout("atomic_open finish_no_open on dn %p\n", dn);
 		err = finish_no_open(file, dn);
@@ -392,13 +392,14 @@ more:
 	if (ret >= 0) {
 		int didpages;
 		if (was_short && (pos + ret < inode->i_size)) {
-			u64 tmp = min(this_len - ret,
-					inode->i_size - pos - ret);
+			int zlen = min(this_len - ret,
+				       inode->i_size - pos - ret);
+			int zoff = (o_direct ? buf_align : io_align) +
+				    read + ret;
 			dout(" zero gap %llu to %llu\n",
-				pos + ret, pos + ret + tmp);
-			ceph_zero_page_vector_range(page_align + read + ret,
-							tmp, pages);
-			ret += tmp;
+				pos + ret, pos + ret + zlen);
+			ceph_zero_page_vector_range(zoff, zlen, pages);
+			ret += zlen;
 		}
 
 		didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
@@ -878,28 +879,34 @@ again:
 
 		i_size = i_size_read(inode);
 		if (retry_op == READ_INLINE) {
-			/* does not support inline data > PAGE_SIZE */
-			if (i_size > PAGE_CACHE_SIZE) {
-				ret = -EIO;
-			} else if (iocb->ki_pos < i_size) {
+			BUG_ON(ret > 0 || read > 0);
+			if (iocb->ki_pos < i_size &&
+			    iocb->ki_pos < PAGE_CACHE_SIZE) {
 				loff_t end = min_t(loff_t, i_size,
 						   iocb->ki_pos + len);
+				end = min_t(loff_t, end, PAGE_CACHE_SIZE);
 				if (statret < end)
 					zero_user_segment(page, statret, end);
 				ret = copy_page_to_iter(page,
 						iocb->ki_pos & ~PAGE_MASK,
 						end - iocb->ki_pos, to);
 				iocb->ki_pos += ret;
-			} else {
-				ret = 0;
+				read += ret;
+			}
+			if (iocb->ki_pos < i_size && read < len) {
+				size_t zlen = min_t(size_t, len - read,
+						    i_size - iocb->ki_pos);
+				ret = iov_iter_zero(zlen, to);
+				iocb->ki_pos += ret;
+				read += ret;
 			}
 			__free_pages(page, 0);
-			return ret;
+			return read;
 		}
 
 		/* hit EOF or hole? */
 		if (retry_op == CHECK_EOF && iocb->ki_pos < i_size &&
-			ret < len) {
+		    ret < len) {
 			dout("sync_read hit hole, ppos %lld < size %lld"
 			     ", reading more\n", iocb->ki_pos,
 			     inode->i_size);
@@ -945,7 +952,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	mutex_lock(&inode->i_mutex);
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = file->f_mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index f61a74115beb..119c43c80638 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -82,8 +82,8 @@ struct inode *ceph_get_snapdir(struct inode *parent)
 	inode->i_mode = parent->i_mode;
 	inode->i_uid = parent->i_uid;
 	inode->i_gid = parent->i_gid;
-	inode->i_op = &ceph_dir_iops;
-	inode->i_fop = &ceph_dir_fops;
+	inode->i_op = &ceph_snapdir_iops;
+	inode->i_fop = &ceph_snapdir_fops;
 	ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
 	ci->i_rbytes = 0;
 	return inode;
@@ -783,8 +783,6 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	}
 
 	inode->i_mapping->a_ops = &ceph_aops;
-	inode->i_mapping->backing_dev_info =
-		&ceph_sb_to_client(inode->i_sb)->backing_dev_info;
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFIFO:
@@ -840,30 +838,31 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 		       ceph_vinop(inode), inode->i_mode);
 	}
 
-	/* set dir completion flag? */
-	if (S_ISDIR(inode->i_mode) &&
-	    ci->i_files == 0 && ci->i_subdirs == 0 &&
-	    ceph_snap(inode) == CEPH_NOSNAP &&
-	    (le32_to_cpu(info->cap.caps) & CEPH_CAP_FILE_SHARED) &&
-	    (issued & CEPH_CAP_FILE_EXCL) == 0 &&
-	    !__ceph_dir_is_complete(ci)) {
-		dout(" marking %p complete (empty)\n", inode);
-		__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count),
-					ci->i_ordered_count);
-	}
-
 	/* were we issued a capability? */
 	if (info->cap.caps) {
 		if (ceph_snap(inode) == CEPH_NOSNAP) {
+			unsigned caps = le32_to_cpu(info->cap.caps);
 			ceph_add_cap(inode, session,
 				     le64_to_cpu(info->cap.cap_id),
-				     cap_fmode,
-				     le32_to_cpu(info->cap.caps),
+				     cap_fmode, caps,
 				     le32_to_cpu(info->cap.wanted),
 				     le32_to_cpu(info->cap.seq),
 				     le32_to_cpu(info->cap.mseq),
 				     le64_to_cpu(info->cap.realm),
 				     info->cap.flags, &new_cap);
+
+			/* set dir completion flag? */
+			if (S_ISDIR(inode->i_mode) &&
+			    ci->i_files == 0 && ci->i_subdirs == 0 &&
+			    (caps & CEPH_CAP_FILE_SHARED) &&
+			    (issued & CEPH_CAP_FILE_EXCL) == 0 &&
+			    !__ceph_dir_is_complete(ci)) {
+				dout(" marking %p complete (empty)\n", inode);
+				__ceph_dir_set_complete(ci,
+					atomic_read(&ci->i_release_count),
+					ci->i_ordered_count);
+			}
+
 			wake = true;
 		} else {
 			dout(" %p got snap_caps %s\n", inode,
@@ -1448,12 +1447,14 @@ retry_lookup:
 		}
 
 		if (!dn->d_inode) {
-			dn = splice_dentry(dn, in, NULL);
-			if (IS_ERR(dn)) {
-				err = PTR_ERR(dn);
+			struct dentry *realdn = splice_dentry(dn, in, NULL);
+			if (IS_ERR(realdn)) {
+				err = PTR_ERR(realdn);
+				d_drop(dn);
 				dn = NULL;
 				goto next_item;
 			}
+			dn = realdn;
 		}
 
 		di = dn->d_fsdata;
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index c35c5c614e38..4347039ecc18 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -239,23 +239,26 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	return err;
 }
 
-/**
- * Must be called with lock_flocks() already held. Fills in the passed
- * counter variables, so you can prepare pagelist metadata before calling
- * ceph_encode_locks.
+/*
+ * Fills in the passed counter variables, so you can prepare pagelist metadata
+ * before calling ceph_encode_locks.
  */
 void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 {
 	struct file_lock *lock;
+	struct file_lock_context *ctx;
 
 	*fcntl_count = 0;
 	*flock_count = 0;
 
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_POSIX)
+	ctx = inode->i_flctx;
+	if (ctx) {
+		spin_lock(&ctx->flc_lock);
+		list_for_each_entry(lock, &ctx->flc_posix, fl_list)
 			++(*fcntl_count);
-		else if (lock->fl_flags & FL_FLOCK)
+		list_for_each_entry(lock, &ctx->flc_flock, fl_list)
 			++(*flock_count);
+		spin_unlock(&ctx->flc_lock);
 	}
 	dout("counted %d flock locks and %d fcntl locks",
 	     *flock_count, *fcntl_count);
@@ -271,6 +274,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 				int num_fcntl_locks, int num_flock_locks)
 {
 	struct file_lock *lock;
+	struct file_lock_context *ctx = inode->i_flctx;
 	int err = 0;
 	int seen_fcntl = 0;
 	int seen_flock = 0;
@@ -279,33 +283,34 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 	dout("encoding %d flock and %d fcntl locks", num_flock_locks,
 	     num_fcntl_locks);
 
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_POSIX) {
-			++seen_fcntl;
-			if (seen_fcntl > num_fcntl_locks) {
-				err = -ENOSPC;
-				goto fail;
-			}
-			err = lock_to_ceph_filelock(lock, &flocks[l]);
-			if (err)
-				goto fail;
-			++l;
+	if (!ctx)
+		return 0;
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+		++seen_fcntl;
+		if (seen_fcntl > num_fcntl_locks) {
+			err = -ENOSPC;
+			goto fail;
 		}
+		err = lock_to_ceph_filelock(lock, &flocks[l]);
+		if (err)
+			goto fail;
+		++l;
 	}
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_FLOCK) {
-			++seen_flock;
-			if (seen_flock > num_flock_locks) {
-				err = -ENOSPC;
-				goto fail;
-			}
-			err = lock_to_ceph_filelock(lock, &flocks[l]);
-			if (err)
-				goto fail;
-			++l;
+	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+		++seen_flock;
+		if (seen_flock > num_flock_locks) {
+			err = -ENOSPC;
+			goto fail;
 		}
+		err = lock_to_ceph_filelock(lock, &flocks[l]);
+		if (err)
+			goto fail;
+		++l;
 	}
 fail:
+	spin_unlock(&ctx->flc_lock);
 	return err;
 }
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d2171f4a6980..71c073f38e54 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -480,6 +480,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 		mdsc->max_sessions = newmax;
 	}
 	mdsc->sessions[mds] = s;
+	atomic_inc(&mdsc->num_sessions);
 	atomic_inc(&s->s_ref);  /* one ref to sessions[], one to caller */
 
 	ceph_con_open(&s->s_con, CEPH_ENTITY_TYPE_MDS, mds,
@@ -503,6 +504,7 @@ static void __unregister_session(struct ceph_mds_client *mdsc,
 	mdsc->sessions[s->s_mds] = NULL;
 	ceph_con_close(&s->s_con);
 	ceph_put_mds_session(s);
+	atomic_dec(&mdsc->num_sessions);
 }
 
 /*
@@ -842,8 +844,9 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	struct ceph_options *opt = mdsc->fsc->client->options;
 	void *p;
 
-	const char* metadata[3][2] = {
+	const char* metadata[][2] = {
 		{"hostname", utsname()->nodename},
+		{"kernel_version", utsname()->release},
 		{"entity_id", opt->name ? opt->name : ""},
 		{NULL, NULL}
 	};
@@ -1464,19 +1467,33 @@ out_unlocked:
 	return err;
 }
 
+static int check_cap_flush(struct inode *inode, u64 want_flush_seq)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	int ret;
+	spin_lock(&ci->i_ceph_lock);
+	if (ci->i_flushing_caps)
+		ret = ci->i_cap_flush_seq >= want_flush_seq;
+	else
+		ret = 1;
+	spin_unlock(&ci->i_ceph_lock);
+	return ret;
+}
+
 /*
  * flush all dirty inode data to disk.
  *
  * returns true if we've flushed through want_flush_seq
  */
-static int check_cap_flush(struct ceph_mds_client *mdsc, u64 want_flush_seq)
+static void wait_caps_flush(struct ceph_mds_client *mdsc, u64 want_flush_seq)
 {
-	int mds, ret = 1;
+	int mds;
 
 	dout("check_cap_flush want %lld\n", want_flush_seq);
 	mutex_lock(&mdsc->mutex);
-	for (mds = 0; ret && mds < mdsc->max_sessions; mds++) {
+	for (mds = 0; mds < mdsc->max_sessions; mds++) {
 		struct ceph_mds_session *session = mdsc->sessions[mds];
+		struct inode *inode = NULL;
 
 		if (!session)
 			continue;
@@ -1489,29 +1506,29 @@ static int check_cap_flush(struct ceph_mds_client *mdsc, u64 want_flush_seq)
 				list_entry(session->s_cap_flushing.next,
 					   struct ceph_inode_info,
 					   i_flushing_item);
-			struct inode *inode = &ci->vfs_inode;
 
-			spin_lock(&ci->i_ceph_lock);
-			if (ci->i_cap_flush_seq <= want_flush_seq) {
+			if (!check_cap_flush(&ci->vfs_inode, want_flush_seq)) {
 				dout("check_cap_flush still flushing %p "
-				     "seq %lld <= %lld to mds%d\n", inode,
-				     ci->i_cap_flush_seq, want_flush_seq,
-				     session->s_mds);
-				ret = 0;
+				     "seq %lld <= %lld to mds%d\n",
+				     &ci->vfs_inode, ci->i_cap_flush_seq,
+				     want_flush_seq, session->s_mds);
+				inode = igrab(&ci->vfs_inode);
 			}
-			spin_unlock(&ci->i_ceph_lock);
 		}
 		mutex_unlock(&session->s_mutex);
 		ceph_put_mds_session(session);
 
-		if (!ret)
-			return ret;
+		if (inode) {
+			wait_event(mdsc->cap_flushing_wq,
+				   check_cap_flush(inode, want_flush_seq));
+			iput(inode);
+		}
+
 		mutex_lock(&mdsc->mutex);
 	}
 
 	mutex_unlock(&mdsc->mutex);
 	dout("check_cap_flush ok, flushed thru %lld\n", want_flush_seq);
-	return ret;
 }
 
 /*
@@ -1923,7 +1940,11 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 	head->num_releases = cpu_to_le16(releases);
 
 	/* time stamp */
-	ceph_encode_copy(&p, &req->r_stamp, sizeof(req->r_stamp));
+	{
+		struct ceph_timespec ts;
+		ceph_encode_timespec(&ts, &req->r_stamp);
+		ceph_encode_copy(&p, &ts, sizeof(ts));
+	}
 
 	BUG_ON(p > end);
 	msg->front.iov_len = p - msg->front.iov_base;
@@ -2012,7 +2033,11 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc,
 
 		/* time stamp */
 		p = msg->front.iov_base + req->r_request_release_offset;
-		ceph_encode_copy(&p, &req->r_stamp, sizeof(req->r_stamp));
+		{
+			struct ceph_timespec ts;
+			ceph_encode_timespec(&ts, &req->r_stamp);
+			ceph_encode_copy(&p, &ts, sizeof(ts));
+		}
 
 		msg->front.iov_len = p - msg->front.iov_base;
 		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
@@ -2159,6 +2184,8 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds)
 		p = rb_next(p);
 		if (req->r_got_unsafe)
 			continue;
+		if (req->r_attempts > 0)
+			continue; /* only new requests */
 		if (req->r_session &&
 		    req->r_session->s_mds == mds) {
 			dout(" kicking tid %llu\n", req->r_tid);
@@ -2286,6 +2313,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	struct ceph_mds_request *req;
 	struct ceph_mds_reply_head *head = msg->front.iov_base;
 	struct ceph_mds_reply_info_parsed *rinfo;  /* parsed reply info */
+	struct ceph_snap_realm *realm;
 	u64 tid;
 	int err, result;
 	int mds = session->s_mds;
@@ -2401,11 +2429,13 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	}
 
 	/* snap trace */
+	realm = NULL;
 	if (rinfo->snapblob_len) {
 		down_write(&mdsc->snap_rwsem);
 		ceph_update_snap_trace(mdsc, rinfo->snapblob,
-			       rinfo->snapblob + rinfo->snapblob_len,
-			       le32_to_cpu(head->op) == CEPH_MDS_OP_RMSNAP);
+				rinfo->snapblob + rinfo->snapblob_len,
+				le32_to_cpu(head->op) == CEPH_MDS_OP_RMSNAP,
+				&realm);
 		downgrade_write(&mdsc->snap_rwsem);
 	} else {
 		down_read(&mdsc->snap_rwsem);
@@ -2423,6 +2453,8 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	mutex_unlock(&req->r_fill_mutex);
 
 	up_read(&mdsc->snap_rwsem);
+	if (realm)
+		ceph_put_snap_realm(mdsc, realm);
 out_err:
 	mutex_lock(&mdsc->mutex);
 	if (!req->r_aborted) {
@@ -2487,6 +2519,7 @@ static void handle_forward(struct ceph_mds_client *mdsc,
 		dout("forward tid %llu to mds%d (we resend)\n", tid, next_mds);
 		BUG_ON(req->r_err);
 		BUG_ON(req->r_got_result);
+		req->r_attempts = 0;
 		req->r_num_fwd = fwd_seq;
 		req->r_resend_mds = next_mds;
 		put_request_session(req);
@@ -2580,6 +2613,14 @@ static void handle_session(struct ceph_mds_session *session,
 		send_flushmsg_ack(mdsc, session, seq);
 		break;
 
+	case CEPH_SESSION_FORCE_RO:
+		dout("force_session_readonly %p\n", session);
+		spin_lock(&session->s_cap_lock);
+		session->s_readonly = true;
+		spin_unlock(&session->s_cap_lock);
+		wake_up_session_caps(session, 0);
+		break;
+
 	default:
 		pr_err("mdsc_handle_session bad op %d mds%d\n", op, mds);
 		WARN_ON(1);
@@ -2610,6 +2651,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
 				   struct ceph_mds_session *session)
 {
 	struct ceph_mds_request *req, *nreq;
+	struct rb_node *p;
 	int err;
 
 	dout("replay_unsafe_requests mds%d\n", session->s_mds);
@@ -2622,6 +2664,28 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
 			ceph_con_send(&session->s_con, req->r_request);
 		}
 	}
+
+	/*
+	 * also re-send old requests when MDS enters reconnect stage. So that MDS
+	 * can process completed request in clientreplay stage.
+	 */
+	p = rb_first(&mdsc->request_tree);
+	while (p) {
+		req = rb_entry(p, struct ceph_mds_request, r_node);
+		p = rb_next(p);
+		if (req->r_got_unsafe)
+			continue;
+		if (req->r_attempts == 0)
+			continue; /* only old requests */
+		if (req->r_session &&
+		    req->r_session->s_mds == session->s_mds) {
+			err = __prepare_send_request(mdsc, req, session->s_mds);
+			if (!err) {
+				ceph_msg_get(req->r_request);
+				ceph_con_send(&session->s_con, req->r_request);
+			}
+		}
+	}
 	mutex_unlock(&mdsc->mutex);
 }
 
@@ -2700,20 +2764,16 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		struct ceph_filelock *flocks;
 
 encode_again:
-		spin_lock(&inode->i_lock);
 		ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks);
-		spin_unlock(&inode->i_lock);
 		flocks = kmalloc((num_fcntl_locks+num_flock_locks) *
 				 sizeof(struct ceph_filelock), GFP_NOFS);
 		if (!flocks) {
 			err = -ENOMEM;
 			goto out_free;
 		}
-		spin_lock(&inode->i_lock);
 		err = ceph_encode_locks_to_buffer(inode, flocks,
 						  num_fcntl_locks,
 						  num_flock_locks);
-		spin_unlock(&inode->i_lock);
 		if (err) {
 			kfree(flocks);
 			if (err == -ENOSPC)
@@ -2791,6 +2851,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	spin_unlock(&session->s_gen_ttl_lock);
 
 	spin_lock(&session->s_cap_lock);
+	/* don't know if session is readonly */
+	session->s_readonly = 0;
 	/*
 	 * notify __ceph_remove_cap() that we are composing cap reconnect.
 	 * If a cap get released before being added to the cap reconnect,
@@ -2937,9 +2999,6 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 				mutex_unlock(&s->s_mutex);
 				s->s_state = CEPH_MDS_SESSION_RESTARTING;
 			}
-
-			/* kick any requests waiting on the recovering mds */
-			kick_requests(mdsc, i);
 		} else if (oldstate == newstate) {
 			continue;  /* nothing new with this mds */
 		}
@@ -3299,6 +3358,7 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	init_waitqueue_head(&mdsc->session_close_wq);
 	INIT_LIST_HEAD(&mdsc->waiting_for_map);
 	mdsc->sessions = NULL;
+	atomic_set(&mdsc->num_sessions, 0);
 	mdsc->max_sessions = 0;
 	mdsc->stopping = 0;
 	init_rwsem(&mdsc->snap_rwsem);
@@ -3432,14 +3492,17 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 	dout("sync\n");
 	mutex_lock(&mdsc->mutex);
 	want_tid = mdsc->last_tid;
-	want_flush = mdsc->cap_flush_seq;
 	mutex_unlock(&mdsc->mutex);
-	dout("sync want tid %lld flush_seq %lld\n", want_tid, want_flush);
 
 	ceph_flush_dirty_caps(mdsc);
+	spin_lock(&mdsc->cap_dirty_lock);
+	want_flush = mdsc->cap_flush_seq;
+	spin_unlock(&mdsc->cap_dirty_lock);
+
+	dout("sync want tid %lld flush_seq %lld\n", want_tid, want_flush);
 
 	wait_unsafe_requests(mdsc, want_tid);
-	wait_event(mdsc->cap_flushing_wq, check_cap_flush(mdsc, want_flush));
+	wait_caps_flush(mdsc, want_flush);
 }
 
 /*
@@ -3447,17 +3510,9 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
  */
 static bool done_closing_sessions(struct ceph_mds_client *mdsc)
 {
-	int i, n = 0;
-
 	if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN)
 		return true;
-
-	mutex_lock(&mdsc->mutex);
-	for (i = 0; i < mdsc->max_sessions; i++)
-		if (mdsc->sessions[i])
-			n++;
-	mutex_unlock(&mdsc->mutex);
-	return n == 0;
+	return atomic_read(&mdsc->num_sessions) == 0;
 }
 
 /*
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index e2817d00f7d9..1875b5d985c6 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -137,6 +137,7 @@ struct ceph_mds_session {
 	int               s_nr_caps, s_trim_caps;
 	int               s_num_cap_releases;
 	int		  s_cap_reconnect;
+	int		  s_readonly;
 	struct list_head  s_cap_releases; /* waiting cap_release messages */
 	struct list_head  s_cap_releases_done; /* ready to send */
 	struct ceph_cap  *s_cap_iterator;
@@ -272,6 +273,7 @@ struct ceph_mds_client {
 	struct list_head        waiting_for_map;
 
 	struct ceph_mds_session **sessions;    /* NULL for mds if no session */
+	atomic_t		num_sessions;
 	int                     max_sessions;  /* len of s_mds_sessions */
 	int                     stopping;      /* true if shutting down */
 
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index ce35fbd4ba5d..a97e39f09ba6 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -70,13 +70,11 @@ void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
 	 * safe.  we do need to protect against concurrent empty list
 	 * additions, however.
 	 */
-	if (atomic_read(&realm->nref) == 0) {
+	if (atomic_inc_return(&realm->nref) == 1) {
 		spin_lock(&mdsc->snap_empty_lock);
 		list_del_init(&realm->empty_item);
 		spin_unlock(&mdsc->snap_empty_lock);
 	}
-
-	atomic_inc(&realm->nref);
 }
 
 static void __insert_snap_realm(struct rb_root *root,
@@ -116,7 +114,7 @@ static struct ceph_snap_realm *ceph_create_snap_realm(
 	if (!realm)
 		return ERR_PTR(-ENOMEM);
 
-	atomic_set(&realm->nref, 0);    /* tree does not take a ref */
+	atomic_set(&realm->nref, 1);    /* for caller */
 	realm->ino = ino;
 	INIT_LIST_HEAD(&realm->children);
 	INIT_LIST_HEAD(&realm->child_item);
@@ -134,8 +132,8 @@ static struct ceph_snap_realm *ceph_create_snap_realm(
  *
  * caller must hold snap_rwsem for write.
  */
-struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
-					       u64 ino)
+static struct ceph_snap_realm *__lookup_snap_realm(struct ceph_mds_client *mdsc,
+						   u64 ino)
 {
 	struct rb_node *n = mdsc->snap_realms.rb_node;
 	struct ceph_snap_realm *r;
@@ -154,6 +152,16 @@ struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
 	return NULL;
 }
 
+struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
+					       u64 ino)
+{
+	struct ceph_snap_realm *r;
+	r = __lookup_snap_realm(mdsc, ino);
+	if (r)
+		ceph_get_snap_realm(mdsc, r);
+	return r;
+}
+
 static void __put_snap_realm(struct ceph_mds_client *mdsc,
 			     struct ceph_snap_realm *realm);
 
@@ -273,7 +281,6 @@ static int adjust_snap_realm_parent(struct ceph_mds_client *mdsc,
 	}
 	realm->parent_ino = parentino;
 	realm->parent = parent;
-	ceph_get_snap_realm(mdsc, parent);
 	list_add(&realm->child_item, &parent->children);
 	return 1;
 }
@@ -631,12 +638,14 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm)
  * Caller must hold snap_rwsem for write.
  */
 int ceph_update_snap_trace(struct ceph_mds_client *mdsc,
-			   void *p, void *e, bool deletion)
+			   void *p, void *e, bool deletion,
+			   struct ceph_snap_realm **realm_ret)
 {
 	struct ceph_mds_snap_realm *ri;    /* encoded */
 	__le64 *snaps;                     /* encoded */
 	__le64 *prior_parent_snaps;        /* encoded */
-	struct ceph_snap_realm *realm;
+	struct ceph_snap_realm *realm = NULL;
+	struct ceph_snap_realm *first_realm = NULL;
 	int invalidate = 0;
 	int err = -ENOMEM;
 	LIST_HEAD(dirty_realms);
@@ -704,13 +713,18 @@ more:
 	dout("done with %llx %p, invalidated=%d, %p %p\n", realm->ino,
 	     realm, invalidate, p, e);
 
-	if (p < e)
-		goto more;
-
 	/* invalidate when we reach the _end_ (root) of the trace */
-	if (invalidate)
+	if (invalidate && p >= e)
 		rebuild_snap_realms(realm);
 
+	if (!first_realm)
+		first_realm = realm;
+	else
+		ceph_put_snap_realm(mdsc, realm);
+
+	if (p < e)
+		goto more;
+
 	/*
 	 * queue cap snaps _after_ we've built the new snap contexts,
 	 * so that i_head_snapc can be set appropriately.
@@ -721,12 +735,21 @@ more:
 		queue_realm_cap_snaps(realm);
 	}
 
+	if (realm_ret)
+		*realm_ret = first_realm;
+	else
+		ceph_put_snap_realm(mdsc, first_realm);
+
 	__cleanup_empty_realms(mdsc);
 	return 0;
 
 bad:
 	err = -EINVAL;
 fail:
+	if (realm && !IS_ERR(realm))
+		ceph_put_snap_realm(mdsc, realm);
+	if (first_realm)
+		ceph_put_snap_realm(mdsc, first_realm);
 	pr_err("update_snap_trace error %d\n", err);
 	return err;
 }
@@ -844,7 +867,6 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 			if (IS_ERR(realm))
 				goto out;
 		}
-		ceph_get_snap_realm(mdsc, realm);
 
 		dout("splitting snap_realm %llx %p\n", realm->ino, realm);
 		for (i = 0; i < num_split_inos; i++) {
@@ -905,7 +927,7 @@ skip_inode:
 		/* we may have taken some of the old realm's children. */
 		for (i = 0; i < num_split_realms; i++) {
 			struct ceph_snap_realm *child =
-				ceph_lookup_snap_realm(mdsc,
+				__lookup_snap_realm(mdsc,
 					   le64_to_cpu(split_realms[i]));
 			if (!child)
 				continue;
@@ -918,7 +940,7 @@ skip_inode:
 	 * snap, we can avoid queueing cap_snaps.
 	 */
 	ceph_update_snap_trace(mdsc, p, e,
-			       op == CEPH_SNAP_OP_DESTROY);
+			       op == CEPH_SNAP_OP_DESTROY, NULL);
 
 	if (op == CEPH_SNAP_OP_SPLIT)
 		/* we took a reference when we created the realm, above */
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 50f06cddc94b..a63997b8bcff 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -40,17 +40,6 @@ static void ceph_put_super(struct super_block *s)
 
 	dout("put_super\n");
 	ceph_mdsc_close_sessions(fsc->mdsc);
-
-	/*
-	 * ensure we release the bdi before put_anon_super releases
-	 * the device name.
-	 */
-	if (s->s_bdi == &fsc->backing_dev_info) {
-		bdi_unregister(&fsc->backing_dev_info);
-		s->s_bdi = NULL;
-	}
-
-	return;
 }
 
 static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -425,6 +414,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 		seq_puts(m, ",noshare");
 	if (opt->flags & CEPH_OPT_NOCRC)
 		seq_puts(m, ",nocrc");
+	if (opt->flags & CEPH_OPT_NOMSGAUTH)
+		seq_puts(m, ",nocephx_require_signatures");
+	if ((opt->flags & CEPH_OPT_TCP_NODELAY) == 0)
+		seq_puts(m, ",notcp_nodelay");
 
 	if (opt->name)
 		seq_printf(m, ",name=%s", opt->name);
@@ -910,7 +903,7 @@ static int ceph_register_bdi(struct super_block *sb,
 			>> PAGE_SHIFT;
 	else
 		fsc->backing_dev_info.ra_pages =
-			default_backing_dev_info.ra_pages;
+			VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
 
 	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
 			   atomic_long_inc_return(&bdi_seq));
@@ -1002,11 +995,16 @@ out_final:
 static void ceph_kill_sb(struct super_block *s)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
+	dev_t dev = s->s_dev;
+
 	dout("kill_sb %p\n", s);
+
 	ceph_mdsc_pre_umount(fsc->mdsc);
-	kill_anon_super(s);    /* will call put_super after sb is r/o */
+	generic_shutdown_super(s);
 	ceph_mdsc_destroy(fsc);
+
 	destroy_fs_client(fsc);
+	free_anon_bdev(dev);
 }
 
 static struct file_system_type ceph_fs_type = {
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index e1aa32d0759d..04c8124ed30e 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -693,7 +693,8 @@ extern void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
 extern void ceph_put_snap_realm(struct ceph_mds_client *mdsc,
 				struct ceph_snap_realm *realm);
 extern int ceph_update_snap_trace(struct ceph_mds_client *m,
-				  void *p, void *e, bool deletion);
+				  void *p, void *e, bool deletion,
+				  struct ceph_snap_realm **realm_ret);
 extern void ceph_handle_snap(struct ceph_mds_client *mdsc,
 			     struct ceph_mds_session *session,
 			     struct ceph_msg *msg);
@@ -892,7 +893,9 @@ extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 int ceph_uninline_data(struct file *filp, struct page *locked_page);
 /* dir.c */
 extern const struct file_operations ceph_dir_fops;
+extern const struct file_operations ceph_snapdir_fops;
 extern const struct inode_operations ceph_dir_iops;
+extern const struct inode_operations ceph_snapdir_iops;
 extern const struct dentry_operations ceph_dentry_ops, ceph_snap_dentry_ops,
 	ceph_snapdir_dentry_ops;
 
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 67b2007f10fe..ea06a3d0364c 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -24,27 +24,6 @@
 
 #include "internal.h"
 
-/*
- * capabilities for /dev/mem, /dev/kmem and similar directly mappable character
- * devices
- * - permits shared-mmap for read, write and/or exec
- * - does not permit private mmap in NOMMU mode (can't do COW)
- * - no readahead or I/O queue unplugging required
- */
-struct backing_dev_info directly_mappable_cdev_bdi = {
-	.name = "char",
-	.capabilities	= (
-#ifdef CONFIG_MMU
-		/* permit private copies of the data to be taken */
-		BDI_CAP_MAP_COPY |
-#endif
-		/* permit direct mmap, for read, write or exec */
-		BDI_CAP_MAP_DIRECT |
-		BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP |
-		/* no writeback happens */
-		BDI_CAP_NO_ACCT_AND_WRITEBACK),
-};
-
 static struct kobj_map *cdev_map;
 
 static DEFINE_MUTEX(chrdevs_lock);
@@ -575,8 +554,6 @@ static struct kobject *base_probe(dev_t dev, int *part, void *data)
 void __init chrdev_init(void)
 {
 	cdev_map = kobj_map_init(base_probe, &chrdevs_lock);
-	if (bdi_init(&directly_mappable_cdev_bdi))
-		panic("Failed to init directly mappable cdev bdi");
 }
 
 
@@ -590,4 +567,3 @@ EXPORT_SYMBOL(cdev_del);
 EXPORT_SYMBOL(cdev_add);
 EXPORT_SYMBOL(__register_chrdev);
 EXPORT_SYMBOL(__unregister_chrdev);
-EXPORT_SYMBOL(directly_mappable_cdev_bdi);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 2a772da16b83..d3aa999ab785 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3446,7 +3446,7 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 	int referral_walks_count = 0;
 #endif
 
-	rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY);
+	rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs");
 	if (rc)
 		return rc;
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 74f12877493a..a94b3e673182 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1113,11 +1113,6 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
 	return rc;
 }
 
-/* copied from fs/locks.c with a name change */
-#define cifs_for_each_lock(inode, lockp) \
-	for (lockp = &inode->i_flock; *lockp != NULL; \
-	     lockp = &(*lockp)->fl_next)
-
 struct lock_to_push {
 	struct list_head llist;
 	__u64 offset;
@@ -1132,8 +1127,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 {
 	struct inode *inode = cfile->dentry->d_inode;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
-	struct file_lock *flock, **before;
-	unsigned int count = 0, i = 0;
+	struct file_lock *flock;
+	struct file_lock_context *flctx = inode->i_flctx;
+	unsigned int count = 0, i;
 	int rc = 0, xid, type;
 	struct list_head locks_to_send, *el;
 	struct lock_to_push *lck, *tmp;
@@ -1141,12 +1137,14 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 
 	xid = get_xid();
 
-	spin_lock(&inode->i_lock);
-	cifs_for_each_lock(inode, before) {
-		if ((*before)->fl_flags & FL_POSIX)
-			count++;
+	if (!flctx)
+		goto out;
+
+	spin_lock(&flctx->flc_lock);
+	list_for_each(el, &flctx->flc_posix) {
+		count++;
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 
 	INIT_LIST_HEAD(&locks_to_send);
 
@@ -1155,7 +1153,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 	 * added to the list while we are holding cinode->lock_sem that
 	 * protects locking operations of this inode.
 	 */
-	for (; i < count; i++) {
+	for (i = 0; i < count; i++) {
 		lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL);
 		if (!lck) {
 			rc = -ENOMEM;
@@ -1165,11 +1163,8 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 	}
 
 	el = locks_to_send.next;
-	spin_lock(&inode->i_lock);
-	cifs_for_each_lock(inode, before) {
-		flock = *before;
-		if ((flock->fl_flags & FL_POSIX) == 0)
-			continue;
+	spin_lock(&flctx->flc_lock);
+	list_for_each_entry(flock, &flctx->flc_posix, fl_list) {
 		if (el == &locks_to_send) {
 			/*
 			 * The list ended. We don't have enough allocated
@@ -1189,9 +1184,8 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 		lck->length = length;
 		lck->type = type;
 		lck->offset = flock->fl_start;
-		el = el->next;
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 
 	list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
 		int stored_rc;
@@ -3248,7 +3242,6 @@ static struct vm_operations_struct cifs_file_vm_ops = {
 	.fault = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = cifs_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 0c3ce464cae4..2d4f37235ed0 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -937,8 +937,6 @@ retry_iget5_locked:
 			inode->i_flags |= S_NOATIME | S_NOCMTIME;
 		if (inode->i_state & I_NEW) {
 			inode->i_ino = hash;
-			if (S_ISREG(inode->i_mode))
-				inode->i_data.backing_dev_info = sb->s_bdi;
 #ifdef CONFIG_CIFS_FSCACHE
 			/* initialize per-inode cache cookie pointer */
 			CIFS_I(inode)->fscache = NULL;
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 86c893884eb9..60cb88c1dd2b 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -28,29 +28,6 @@
 
 #include "coda_int.h"
 
-/* dir inode-ops */
-static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, bool excl);
-static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, unsigned int flags);
-static int coda_link(struct dentry *old_dentry, struct inode *dir_inode, 
-		     struct dentry *entry);
-static int coda_unlink(struct inode *dir_inode, struct dentry *entry);
-static int coda_symlink(struct inode *dir_inode, struct dentry *entry,
-			const char *symname);
-static int coda_mkdir(struct inode *dir_inode, struct dentry *entry, umode_t mode);
-static int coda_rmdir(struct inode *dir_inode, struct dentry *entry);
-static int coda_rename(struct inode *old_inode, struct dentry *old_dentry, 
-                       struct inode *new_inode, struct dentry *new_dentry);
-
-/* dir file-ops */
-static int coda_readdir(struct file *file, struct dir_context *ctx);
-
-/* dentry ops */
-static int coda_dentry_revalidate(struct dentry *de, unsigned int flags);
-static int coda_dentry_delete(const struct dentry *);
-
-/* support routines */
-static int coda_venus_readdir(struct file *, struct dir_context *);
-
 /* same as fs/bad_inode.c */
 static int coda_return_EIO(void)
 {
@@ -58,38 +35,6 @@ static int coda_return_EIO(void)
 }
 #define CODA_EIO_ERROR ((void *) (coda_return_EIO))
 
-const struct dentry_operations coda_dentry_operations =
-{
-	.d_revalidate	= coda_dentry_revalidate,
-	.d_delete	= coda_dentry_delete,
-};
-
-const struct inode_operations coda_dir_inode_operations =
-{
-	.create		= coda_create,
-	.lookup		= coda_lookup,
-	.link		= coda_link,
-	.unlink		= coda_unlink,
-	.symlink	= coda_symlink,
-	.mkdir		= coda_mkdir,
-	.rmdir		= coda_rmdir,
-	.mknod		= CODA_EIO_ERROR,
-	.rename		= coda_rename,
-	.permission	= coda_permission,
-	.getattr	= coda_getattr,
-	.setattr	= coda_setattr,
-};
-
-const struct file_operations coda_dir_operations = {
-	.llseek		= generic_file_llseek,
-	.read		= generic_read_dir,
-	.iterate	= coda_readdir,
-	.open		= coda_open,
-	.release	= coda_release,
-	.fsync		= coda_fsync,
-};
-
-
 /* inode operations for directories */
 /* access routines: lookup, readlink, permission */
 static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsigned int flags)
@@ -359,7 +304,7 @@ static int coda_rename(struct inode *old_dir, struct dentry *old_dentry,
 			     (const char *) old_name, (const char *)new_name);
 	if (!error) {
 		if (new_dentry->d_inode) {
-			if (S_ISDIR(new_dentry->d_inode->i_mode)) {
+			if (d_is_dir(new_dentry)) {
 				coda_dir_drop_nlink(old_dir);
 				coda_dir_inc_nlink(new_dir);
 			}
@@ -374,33 +319,6 @@ static int coda_rename(struct inode *old_dir, struct dentry *old_dentry,
 	return error;
 }
 
-
-/* file operations for directories */
-static int coda_readdir(struct file *coda_file, struct dir_context *ctx)
-{
-	struct coda_file_info *cfi;
-	struct file *host_file;
-	int ret;
-
-	cfi = CODA_FTOC(coda_file);
-	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
-	host_file = cfi->cfi_container;
-
-	if (host_file->f_op->iterate) {
-		struct inode *host_inode = file_inode(host_file);
-		mutex_lock(&host_inode->i_mutex);
-		ret = -ENOENT;
-		if (!IS_DEADDIR(host_inode)) {
-			ret = host_file->f_op->iterate(host_file, ctx);
-			file_accessed(host_file);
-		}
-		mutex_unlock(&host_inode->i_mutex);
-		return ret;
-	}
-	/* Venus: we must read Venus dirents from a file */
-	return coda_venus_readdir(coda_file, ctx);
-}
-
 static inline unsigned int CDT2DT(unsigned char cdt)
 {
 	unsigned int dt;
@@ -495,6 +413,33 @@ out:
 	return 0;
 }
 
+/* file operations for directories */
+static int coda_readdir(struct file *coda_file, struct dir_context *ctx)
+{
+	struct coda_file_info *cfi;
+	struct file *host_file;
+	int ret;
+
+	cfi = CODA_FTOC(coda_file);
+	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
+	host_file = cfi->cfi_container;
+
+	if (host_file->f_op->iterate) {
+		struct inode *host_inode = file_inode(host_file);
+
+		mutex_lock(&host_inode->i_mutex);
+		ret = -ENOENT;
+		if (!IS_DEADDIR(host_inode)) {
+			ret = host_file->f_op->iterate(host_file, ctx);
+			file_accessed(host_file);
+		}
+		mutex_unlock(&host_inode->i_mutex);
+		return ret;
+	}
+	/* Venus: we must read Venus dirents from a file */
+	return coda_venus_readdir(coda_file, ctx);
+}
+
 /* called when a cache lookup succeeds */
 static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
 {
@@ -603,3 +548,32 @@ int coda_revalidate_inode(struct inode *inode)
 	}
 	return 0;
 }
+
+const struct dentry_operations coda_dentry_operations = {
+	.d_revalidate	= coda_dentry_revalidate,
+	.d_delete	= coda_dentry_delete,
+};
+
+const struct inode_operations coda_dir_inode_operations = {
+	.create		= coda_create,
+	.lookup		= coda_lookup,
+	.link		= coda_link,
+	.unlink		= coda_unlink,
+	.symlink	= coda_symlink,
+	.mkdir		= coda_mkdir,
+	.rmdir		= coda_rmdir,
+	.mknod		= CODA_EIO_ERROR,
+	.rename		= coda_rename,
+	.permission	= coda_permission,
+	.getattr	= coda_getattr,
+	.setattr	= coda_setattr,
+};
+
+const struct file_operations coda_dir_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.iterate	= coda_readdir,
+	.open		= coda_open,
+	.release	= coda_release,
+	.fsync		= coda_fsync,
+};
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index b945410bfcd5..82ec68b59208 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -183,7 +183,7 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
 		goto unlock_out;
 	}
 
-	error = bdi_setup_and_register(&vc->bdi, "coda", BDI_CAP_MAP_COPY);
+	error = bdi_setup_and_register(&vc->bdi, "coda");
 	if (error)
 		goto unlock_out;
 
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index bd4a3c167091..b65d1ef532d5 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -69,16 +69,13 @@ extern struct kmem_cache *configfs_dir_cachep;
 extern int configfs_is_root(struct config_item *item);
 
 extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, struct super_block *);
-extern int configfs_create(struct dentry *, umode_t mode, int (*init)(struct inode *));
-extern int configfs_inode_init(void);
-extern void configfs_inode_exit(void);
+extern int configfs_create(struct dentry *, umode_t mode, void (*init)(struct inode *));
 
 extern int configfs_create_file(struct config_item *, const struct configfs_attribute *);
 extern int configfs_make_dirent(struct configfs_dirent *,
 				struct dentry *, void *, umode_t, int);
 extern int configfs_dirent_is_ready(struct configfs_dirent *);
 
-extern int configfs_add_file(struct dentry *, const struct configfs_attribute *, int);
 extern void configfs_hash_and_remove(struct dentry * dir, const char * name);
 
 extern const unsigned char * configfs_get_name(struct configfs_dirent *sd);
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index c9c298bd3058..cf0db005d2f5 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -240,60 +240,26 @@ int configfs_make_dirent(struct configfs_dirent * parent_sd,
 	return 0;
 }
 
-static int init_dir(struct inode * inode)
+static void init_dir(struct inode * inode)
 {
 	inode->i_op = &configfs_dir_inode_operations;
 	inode->i_fop = &configfs_dir_operations;
 
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
-	return 0;
 }
 
-static int configfs_init_file(struct inode * inode)
+static void configfs_init_file(struct inode * inode)
 {
 	inode->i_size = PAGE_SIZE;
 	inode->i_fop = &configfs_file_operations;
-	return 0;
 }
 
-static int init_symlink(struct inode * inode)
+static void init_symlink(struct inode * inode)
 {
 	inode->i_op = &configfs_symlink_inode_operations;
-	return 0;
-}
-
-static int create_dir(struct config_item *k, struct dentry *d)
-{
-	int error;
-	umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
-	struct dentry *p = d->d_parent;
-
-	BUG_ON(!k);
-
-	error = configfs_dirent_exists(p->d_fsdata, d->d_name.name);
-	if (!error)
-		error = configfs_make_dirent(p->d_fsdata, d, k, mode,
-					     CONFIGFS_DIR | CONFIGFS_USET_CREATING);
-	if (!error) {
-		configfs_set_dir_dirent_depth(p->d_fsdata, d->d_fsdata);
-		error = configfs_create(d, mode, init_dir);
-		if (!error) {
-			inc_nlink(p->d_inode);
-		} else {
-			struct configfs_dirent *sd = d->d_fsdata;
-			if (sd) {
-				spin_lock(&configfs_dirent_lock);
-				list_del_init(&sd->s_sibling);
-				spin_unlock(&configfs_dirent_lock);
-				configfs_put(sd);
-			}
-		}
-	}
-	return error;
 }
 
-
 /**
  *	configfs_create_dir - create a directory for an config_item.
  *	@item:		config_itemwe're creating directory for.
@@ -303,11 +269,37 @@ static int create_dir(struct config_item *k, struct dentry *d)
  *	until it is validated by configfs_dir_set_ready()
  */
 
-static int configfs_create_dir(struct config_item * item, struct dentry *dentry)
+static int configfs_create_dir(struct config_item *item, struct dentry *dentry)
 {
-	int error = create_dir(item, dentry);
-	if (!error)
+	int error;
+	umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
+	struct dentry *p = dentry->d_parent;
+
+	BUG_ON(!item);
+
+	error = configfs_dirent_exists(p->d_fsdata, dentry->d_name.name);
+	if (unlikely(error))
+		return error;
+
+	error = configfs_make_dirent(p->d_fsdata, dentry, item, mode,
+				     CONFIGFS_DIR | CONFIGFS_USET_CREATING);
+	if (unlikely(error))
+		return error;
+
+	configfs_set_dir_dirent_depth(p->d_fsdata, dentry->d_fsdata);
+	error = configfs_create(dentry, mode, init_dir);
+	if (!error) {
+		inc_nlink(p->d_inode);
 		item->ci_dentry = dentry;
+	} else {
+		struct configfs_dirent *sd = dentry->d_fsdata;
+		if (sd) {
+			spin_lock(&configfs_dirent_lock);
+			list_del_init(&sd->s_sibling);
+			spin_unlock(&configfs_dirent_lock);
+			configfs_put(sd);
+		}
+	}
 	return error;
 }
 
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index 1d1c41f1014d..56d2cdc9ae0a 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -313,21 +313,6 @@ const struct file_operations configfs_file_operations = {
 	.release	= configfs_release,
 };
 
-
-int configfs_add_file(struct dentry * dir, const struct configfs_attribute * attr, int type)
-{
-	struct configfs_dirent * parent_sd = dir->d_fsdata;
-	umode_t mode = (attr->ca_mode & S_IALLUGO) | S_IFREG;
-	int error = 0;
-
-	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_NORMAL);
-	error = configfs_make_dirent(parent_sd, NULL, (void *) attr, mode, type);
-	mutex_unlock(&dir->d_inode->i_mutex);
-
-	return error;
-}
-
-
 /**
  *	configfs_create_file - create an attribute file for an item.
  *	@item:	item we're creating for.
@@ -336,9 +321,16 @@ int configfs_add_file(struct dentry * dir, const struct configfs_attribute * att
 
 int configfs_create_file(struct config_item * item, const struct configfs_attribute * attr)
 {
-	BUG_ON(!item || !item->ci_dentry || !attr);
+	struct dentry *dir = item->ci_dentry;
+	struct configfs_dirent *parent_sd = dir->d_fsdata;
+	umode_t mode = (attr->ca_mode & S_IALLUGO) | S_IFREG;
+	int error = 0;
 
-	return configfs_add_file(item->ci_dentry, attr,
-				 CONFIGFS_ITEM_ATTR);
+	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_NORMAL);
+	error = configfs_make_dirent(parent_sd, NULL, (void *) attr, mode,
+				     CONFIGFS_ITEM_ATTR);
+	mutex_unlock(&dir->d_inode->i_mutex);
+
+	return error;
 }
 
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 5946ad98053f..5423a6a6ecc8 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -50,12 +50,6 @@ static const struct address_space_operations configfs_aops = {
 	.write_end	= simple_write_end,
 };
 
-static struct backing_dev_info configfs_backing_dev_info = {
-	.name		= "configfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
 static const struct inode_operations configfs_inode_operations ={
 	.setattr	= configfs_setattr,
 };
@@ -137,7 +131,6 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd,
 	if (inode) {
 		inode->i_ino = get_next_ino();
 		inode->i_mapping->a_ops = &configfs_aops;
-		inode->i_mapping->backing_dev_info = &configfs_backing_dev_info;
 		inode->i_op = &configfs_inode_operations;
 
 		if (sd->s_iattr) {
@@ -183,7 +176,7 @@ static void configfs_set_inode_lock_class(struct configfs_dirent *sd,
 
 #endif /* CONFIG_LOCKDEP */
 
-int configfs_create(struct dentry * dentry, umode_t mode, int (*init)(struct inode *))
+int configfs_create(struct dentry * dentry, umode_t mode, void (*init)(struct inode *))
 {
 	int error = 0;
 	struct inode *inode = NULL;
@@ -205,13 +198,7 @@ int configfs_create(struct dentry * dentry, umode_t mode, int (*init)(struct ino
 	p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME;
 	configfs_set_inode_lock_class(sd, inode);
 
-	if (init) {
-		error = init(inode);
-		if (error) {
-			iput(inode);
-			return error;
-		}
-	}
+	init(inode);
 	d_instantiate(dentry, inode);
 	if (S_ISDIR(mode) || S_ISLNK(mode))
 		dget(dentry);  /* pin link and directory dentries in core */
@@ -249,7 +236,7 @@ void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent)
 
 	if (dentry) {
 		spin_lock(&dentry->d_lock);
-		if (!(d_unhashed(dentry) && dentry->d_inode)) {
+		if (!d_unhashed(dentry) && dentry->d_inode) {
 			dget_dlock(dentry);
 			__d_drop(dentry);
 			spin_unlock(&dentry->d_lock);
@@ -283,13 +270,3 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name)
 	}
 	mutex_unlock(&dir->d_inode->i_mutex);
 }
-
-int __init configfs_inode_init(void)
-{
-	return bdi_init(&configfs_backing_dev_info);
-}
-
-void configfs_inode_exit(void)
-{
-	bdi_destroy(&configfs_backing_dev_info);
-}
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index f6c285833390..da94e41bdbf6 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -145,19 +145,13 @@ static int __init configfs_init(void)
 	if (!config_kobj)
 		goto out2;
 
-	err = configfs_inode_init();
-	if (err)
-		goto out3;
-
 	err = register_filesystem(&configfs_fs_type);
 	if (err)
-		goto out4;
+		goto out3;
 
 	return 0;
-out4:
-	pr_err("Unable to register filesystem!\n");
-	configfs_inode_exit();
 out3:
+	pr_err("Unable to register filesystem!\n");
 	kobject_put(config_kobj);
 out2:
 	kmem_cache_destroy(configfs_dir_cachep);
@@ -172,7 +166,6 @@ static void __exit configfs_exit(void)
 	kobject_put(config_kobj);
 	kmem_cache_destroy(configfs_dir_cachep);
 	configfs_dir_cachep = NULL;
-	configfs_inode_exit();
 }
 
 MODULE_AUTHOR("Oracle");
diff --git a/fs/coredump.c b/fs/coredump.c
index b5c86ffd5033..f319926ddf8c 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -572,7 +572,7 @@ void do_coredump(const siginfo_t *siginfo)
 			 *
 			 * Normally core limits are irrelevant to pipes, since
 			 * we're not writing to the file system, but we use
-			 * cprm.limit of 1 here as a speacial value, this is a
+			 * cprm.limit of 1 here as a special value, this is a
 			 * consistent way to catch recursive crashes.
 			 * We can still crash if the core_pattern binary sets
 			 * RLIM_CORE = !1, but it runs as root, and can do
diff --git a/fs/dax.c b/fs/dax.c
new file mode 100644
index 000000000000..ed1619ec6537
--- /dev/null
+++ b/fs/dax.c
@@ -0,0 +1,534 @@
+/*
+ * fs/dax.c - Direct Access filesystem code
+ * Copyright (c) 2013-2014 Intel Corporation
+ * Author: Matthew Wilcox <matthew.r.wilcox@intel.com>
+ * Author: Ross Zwisler <ross.zwisler@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ */
+
+#include <linux/atomic.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/genhd.h>
+#include <linux/highmem.h>
+#include <linux/memcontrol.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/uio.h>
+#include <linux/vmstat.h>
+
+int dax_clear_blocks(struct inode *inode, sector_t block, long size)
+{
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	sector_t sector = block << (inode->i_blkbits - 9);
+
+	might_sleep();
+	do {
+		void *addr;
+		unsigned long pfn;
+		long count;
+
+		count = bdev_direct_access(bdev, sector, &addr, &pfn, size);
+		if (count < 0)
+			return count;
+		BUG_ON(size < count);
+		while (count > 0) {
+			unsigned pgsz = PAGE_SIZE - offset_in_page(addr);
+			if (pgsz > count)
+				pgsz = count;
+			if (pgsz < PAGE_SIZE)
+				memset(addr, 0, pgsz);
+			else
+				clear_page(addr);
+			addr += pgsz;
+			size -= pgsz;
+			count -= pgsz;
+			BUG_ON(pgsz & 511);
+			sector += pgsz / 512;
+			cond_resched();
+		}
+	} while (size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dax_clear_blocks);
+
+static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
+{
+	unsigned long pfn;
+	sector_t sector = bh->b_blocknr << (blkbits - 9);
+	return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size);
+}
+
+static void dax_new_buf(void *addr, unsigned size, unsigned first, loff_t pos,
+			loff_t end)
+{
+	loff_t final = end - pos + first; /* The final byte of the buffer */
+
+	if (first > 0)
+		memset(addr, 0, first);
+	if (final < size)
+		memset(addr + final, 0, size - final);
+}
+
+static bool buffer_written(struct buffer_head *bh)
+{
+	return buffer_mapped(bh) && !buffer_unwritten(bh);
+}
+
+/*
+ * When ext4 encounters a hole, it returns without modifying the buffer_head
+ * which means that we can't trust b_size.  To cope with this, we set b_state
+ * to 0 before calling get_block and, if any bit is set, we know we can trust
+ * b_size.  Unfortunate, really, since ext4 knows precisely how long a hole is
+ * and would save us time calling get_block repeatedly.
+ */
+static bool buffer_size_valid(struct buffer_head *bh)
+{
+	return bh->b_state != 0;
+}
+
+static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
+			loff_t start, loff_t end, get_block_t get_block,
+			struct buffer_head *bh)
+{
+	ssize_t retval = 0;
+	loff_t pos = start;
+	loff_t max = start;
+	loff_t bh_max = start;
+	void *addr;
+	bool hole = false;
+
+	if (rw != WRITE)
+		end = min(end, i_size_read(inode));
+
+	while (pos < end) {
+		unsigned len;
+		if (pos == max) {
+			unsigned blkbits = inode->i_blkbits;
+			sector_t block = pos >> blkbits;
+			unsigned first = pos - (block << blkbits);
+			long size;
+
+			if (pos == bh_max) {
+				bh->b_size = PAGE_ALIGN(end - pos);
+				bh->b_state = 0;
+				retval = get_block(inode, block, bh,
+								rw == WRITE);
+				if (retval)
+					break;
+				if (!buffer_size_valid(bh))
+					bh->b_size = 1 << blkbits;
+				bh_max = pos - first + bh->b_size;
+			} else {
+				unsigned done = bh->b_size -
+						(bh_max - (pos - first));
+				bh->b_blocknr += done >> blkbits;
+				bh->b_size -= done;
+			}
+
+			hole = (rw != WRITE) && !buffer_written(bh);
+			if (hole) {
+				addr = NULL;
+				size = bh->b_size - first;
+			} else {
+				retval = dax_get_addr(bh, &addr, blkbits);
+				if (retval < 0)
+					break;
+				if (buffer_unwritten(bh) || buffer_new(bh))
+					dax_new_buf(addr, retval, first, pos,
+									end);
+				addr += first;
+				size = retval - first;
+			}
+			max = min(pos + size, end);
+		}
+
+		if (rw == WRITE)
+			len = copy_from_iter(addr, max - pos, iter);
+		else if (!hole)
+			len = copy_to_iter(addr, max - pos, iter);
+		else
+			len = iov_iter_zero(max - pos, iter);
+
+		if (!len)
+			break;
+
+		pos += len;
+		addr += len;
+	}
+
+	return (pos == start) ? retval : pos - start;
+}
+
+/**
+ * dax_do_io - Perform I/O to a DAX file
+ * @rw: READ to read or WRITE to write
+ * @iocb: The control block for this I/O
+ * @inode: The file which the I/O is directed at
+ * @iter: The addresses to do I/O from or to
+ * @pos: The file offset where the I/O starts
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ * @end_io: A filesystem callback for I/O completion
+ * @flags: See below
+ *
+ * This function uses the same locking scheme as do_blockdev_direct_IO:
+ * If @flags has DIO_LOCKING set, we assume that the i_mutex is held by the
+ * caller for writes.  For reads, we take and release the i_mutex ourselves.
+ * If DIO_LOCKING is not set, the filesystem takes care of its own locking.
+ * As with do_blockdev_direct_IO(), we increment i_dio_count while the I/O
+ * is in progress.
+ */
+ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode,
+			struct iov_iter *iter, loff_t pos,
+			get_block_t get_block, dio_iodone_t end_io, int flags)
+{
+	struct buffer_head bh;
+	ssize_t retval = -EINVAL;
+	loff_t end = pos + iov_iter_count(iter);
+
+	memset(&bh, 0, sizeof(bh));
+
+	if ((flags & DIO_LOCKING) && (rw == READ)) {
+		struct address_space *mapping = inode->i_mapping;
+		mutex_lock(&inode->i_mutex);
+		retval = filemap_write_and_wait_range(mapping, pos, end - 1);
+		if (retval) {
+			mutex_unlock(&inode->i_mutex);
+			goto out;
+		}
+	}
+
+	/* Protects against truncate */
+	atomic_inc(&inode->i_dio_count);
+
+	retval = dax_io(rw, inode, iter, pos, end, get_block, &bh);
+
+	if ((flags & DIO_LOCKING) && (rw == READ))
+		mutex_unlock(&inode->i_mutex);
+
+	if ((retval > 0) && end_io)
+		end_io(iocb, pos, retval, bh.b_private);
+
+	inode_dio_done(inode);
+ out:
+	return retval;
+}
+EXPORT_SYMBOL_GPL(dax_do_io);
+
+/*
+ * The user has performed a load from a hole in the file.  Allocating
+ * a new page in the file would cause excessive storage usage for
+ * workloads with sparse files.  We allocate a page cache page instead.
+ * We'll kick it out of the page cache if it's ever written to,
+ * otherwise it will simply fall out of the page cache under memory
+ * pressure without ever having been dirtied.
+ */
+static int dax_load_hole(struct address_space *mapping, struct page *page,
+							struct vm_fault *vmf)
+{
+	unsigned long size;
+	struct inode *inode = mapping->host;
+	if (!page)
+		page = find_or_create_page(mapping, vmf->pgoff,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!page)
+		return VM_FAULT_OOM;
+	/* Recheck i_size under page lock to avoid truncate race */
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size) {
+		unlock_page(page);
+		page_cache_release(page);
+		return VM_FAULT_SIGBUS;
+	}
+
+	vmf->page = page;
+	return VM_FAULT_LOCKED;
+}
+
+static int copy_user_bh(struct page *to, struct buffer_head *bh,
+			unsigned blkbits, unsigned long vaddr)
+{
+	void *vfrom, *vto;
+	if (dax_get_addr(bh, &vfrom, blkbits) < 0)
+		return -EIO;
+	vto = kmap_atomic(to);
+	copy_user_page(vto, vfrom, vaddr, to);
+	kunmap_atomic(vto);
+	return 0;
+}
+
+static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
+			struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct address_space *mapping = inode->i_mapping;
+	sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
+	unsigned long vaddr = (unsigned long)vmf->virtual_address;
+	void *addr;
+	unsigned long pfn;
+	pgoff_t size;
+	int error;
+
+	i_mmap_lock_read(mapping);
+
+	/*
+	 * Check truncate didn't happen while we were allocating a block.
+	 * If it did, this block may or may not be still allocated to the
+	 * file.  We can't tell the filesystem to free it because we can't
+	 * take i_mutex here.  In the worst case, the file still has blocks
+	 * allocated past the end of the file.
+	 */
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (unlikely(vmf->pgoff >= size)) {
+		error = -EIO;
+		goto out;
+	}
+
+	error = bdev_direct_access(bh->b_bdev, sector, &addr, &pfn, bh->b_size);
+	if (error < 0)
+		goto out;
+	if (error < PAGE_SIZE) {
+		error = -EIO;
+		goto out;
+	}
+
+	if (buffer_unwritten(bh) || buffer_new(bh))
+		clear_page(addr);
+
+	error = vm_insert_mixed(vma, vaddr, pfn);
+
+ out:
+	i_mmap_unlock_read(mapping);
+
+	if (bh->b_end_io)
+		bh->b_end_io(bh, 1);
+
+	return error;
+}
+
+static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+			get_block_t get_block)
+{
+	struct file *file = vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	struct page *page;
+	struct buffer_head bh;
+	unsigned long vaddr = (unsigned long)vmf->virtual_address;
+	unsigned blkbits = inode->i_blkbits;
+	sector_t block;
+	pgoff_t size;
+	int error;
+	int major = 0;
+
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		return VM_FAULT_SIGBUS;
+
+	memset(&bh, 0, sizeof(bh));
+	block = (sector_t)vmf->pgoff << (PAGE_SHIFT - blkbits);
+	bh.b_size = PAGE_SIZE;
+
+ repeat:
+	page = find_get_page(mapping, vmf->pgoff);
+	if (page) {
+		if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
+			page_cache_release(page);
+			return VM_FAULT_RETRY;
+		}
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			page_cache_release(page);
+			goto repeat;
+		}
+		size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		if (unlikely(vmf->pgoff >= size)) {
+			/*
+			 * We have a struct page covering a hole in the file
+			 * from a read fault and we've raced with a truncate
+			 */
+			error = -EIO;
+			goto unlock_page;
+		}
+	}
+
+	error = get_block(inode, block, &bh, 0);
+	if (!error && (bh.b_size < PAGE_SIZE))
+		error = -EIO;		/* fs corruption? */
+	if (error)
+		goto unlock_page;
+
+	if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
+		if (vmf->flags & FAULT_FLAG_WRITE) {
+			error = get_block(inode, block, &bh, 1);
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			major = VM_FAULT_MAJOR;
+			if (!error && (bh.b_size < PAGE_SIZE))
+				error = -EIO;
+			if (error)
+				goto unlock_page;
+		} else {
+			return dax_load_hole(mapping, page, vmf);
+		}
+	}
+
+	if (vmf->cow_page) {
+		struct page *new_page = vmf->cow_page;
+		if (buffer_written(&bh))
+			error = copy_user_bh(new_page, &bh, blkbits, vaddr);
+		else
+			clear_user_highpage(new_page, vaddr);
+		if (error)
+			goto unlock_page;
+		vmf->page = page;
+		if (!page) {
+			i_mmap_lock_read(mapping);
+			/* Check we didn't race with truncate */
+			size = (i_size_read(inode) + PAGE_SIZE - 1) >>
+								PAGE_SHIFT;
+			if (vmf->pgoff >= size) {
+				i_mmap_unlock_read(mapping);
+				error = -EIO;
+				goto out;
+			}
+		}
+		return VM_FAULT_LOCKED;
+	}
+
+	/* Check we didn't race with a read fault installing a new page */
+	if (!page && major)
+		page = find_lock_page(mapping, vmf->pgoff);
+
+	if (page) {
+		unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
+							PAGE_CACHE_SIZE, 0);
+		delete_from_page_cache(page);
+		unlock_page(page);
+		page_cache_release(page);
+	}
+
+	error = dax_insert_mapping(inode, &bh, vma, vmf);
+
+ out:
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM | major;
+	/* -EBUSY is fine, somebody else faulted on the same PTE */
+	if ((error < 0) && (error != -EBUSY))
+		return VM_FAULT_SIGBUS | major;
+	return VM_FAULT_NOPAGE | major;
+
+ unlock_page:
+	if (page) {
+		unlock_page(page);
+		page_cache_release(page);
+	}
+	goto out;
+}
+
+/**
+ * dax_fault - handle a page fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * fault handler for DAX files.
+ */
+int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+			get_block_t get_block)
+{
+	int result;
+	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+
+	if (vmf->flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(sb);
+		file_update_time(vma->vm_file);
+	}
+	result = do_dax_fault(vma, vmf, get_block);
+	if (vmf->flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(sb);
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(dax_fault);
+
+/**
+ * dax_zero_page_range - zero a range within a page of a DAX file
+ * @inode: The file being truncated
+ * @from: The file offset that is being truncated to
+ * @length: The number of bytes to zero
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * This function can be called by a filesystem when it is zeroing part of a
+ * page in a DAX file.  This is intended for hole-punch operations.  If
+ * you are truncating a file, the helper function dax_truncate_page() may be
+ * more convenient.
+ *
+ * We work in terms of PAGE_CACHE_SIZE here for commonality with
+ * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
+ * took care of disposing of the unnecessary blocks.  Even if the filesystem
+ * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
+ * since the file might be mmapped.
+ */
+int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
+							get_block_t get_block)
+{
+	struct buffer_head bh;
+	pgoff_t index = from >> PAGE_CACHE_SHIFT;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	int err;
+
+	/* Block boundary? Nothing to do */
+	if (!length)
+		return 0;
+	BUG_ON((offset + length) > PAGE_CACHE_SIZE);
+
+	memset(&bh, 0, sizeof(bh));
+	bh.b_size = PAGE_CACHE_SIZE;
+	err = get_block(inode, index, &bh, 0);
+	if (err < 0)
+		return err;
+	if (buffer_written(&bh)) {
+		void *addr;
+		err = dax_get_addr(&bh, &addr, inode->i_blkbits);
+		if (err < 0)
+			return err;
+		memset(addr + offset, 0, length);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dax_zero_page_range);
+
+/**
+ * dax_truncate_page - handle a partial page being truncated in a DAX file
+ * @inode: The file being truncated
+ * @from: The file offset that is being truncated to
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * Similar to block_truncate_page(), this function can be called by a
+ * filesystem when it is truncating a DAX file to handle the partial page.
+ *
+ * We work in terms of PAGE_CACHE_SIZE here for commonality with
+ * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
+ * took care of disposing of the unnecessary blocks.  Even if the filesystem
+ * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
+ * since the file might be mmapped.
+ */
+int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
+{
+	unsigned length = PAGE_CACHE_ALIGN(from) - from;
+	return dax_zero_page_range(inode, from, length, get_block);
+}
+EXPORT_SYMBOL_GPL(dax_truncate_page);
diff --git a/fs/dcache.c b/fs/dcache.c
index e368d4f412f9..c71e3732e53b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -38,6 +38,8 @@
 #include <linux/prefetch.h>
 #include <linux/ratelimit.h>
 #include <linux/list_lru.h>
+#include <linux/kasan.h>
+
 #include "internal.h"
 #include "mount.h"
 
@@ -400,19 +402,20 @@ static void d_shrink_add(struct dentry *dentry, struct list_head *list)
  * LRU lists entirely, while shrink_move moves it to the indicated
  * private list.
  */
-static void d_lru_isolate(struct dentry *dentry)
+static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry)
 {
 	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
 	dentry->d_flags &= ~DCACHE_LRU_LIST;
 	this_cpu_dec(nr_dentry_unused);
-	list_del_init(&dentry->d_lru);
+	list_lru_isolate(lru, &dentry->d_lru);
 }
 
-static void d_lru_shrink_move(struct dentry *dentry, struct list_head *list)
+static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry,
+			      struct list_head *list)
 {
 	D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
 	dentry->d_flags |= DCACHE_SHRINK_LIST;
-	list_move_tail(&dentry->d_lru, list);
+	list_lru_isolate_move(lru, &dentry->d_lru, list);
 }
 
 /*
@@ -508,7 +511,7 @@ static void __dentry_kill(struct dentry *dentry)
 	 * dentry_iput drops the locks, at which point nobody (except
 	 * transient RCU lookups) can reach this dentry.
 	 */
-	BUG_ON((int)dentry->d_lockref.count > 0);
+	BUG_ON(dentry->d_lockref.count > 0);
 	this_cpu_dec(nr_dentry);
 	if (dentry->d_op && dentry->d_op->d_release)
 		dentry->d_op->d_release(dentry);
@@ -561,7 +564,7 @@ static inline struct dentry *lock_parent(struct dentry *dentry)
 	struct dentry *parent = dentry->d_parent;
 	if (IS_ROOT(dentry))
 		return NULL;
-	if (unlikely((int)dentry->d_lockref.count < 0))
+	if (unlikely(dentry->d_lockref.count < 0))
 		return NULL;
 	if (likely(spin_trylock(&parent->d_lock)))
 		return parent;
@@ -590,6 +593,110 @@ again:
 	return parent;
 }
 
+/*
+ * Try to do a lockless dput(), and return whether that was successful.
+ *
+ * If unsuccessful, we return false, having already taken the dentry lock.
+ *
+ * The caller needs to hold the RCU read lock, so that the dentry is
+ * guaranteed to stay around even if the refcount goes down to zero!
+ */
+static inline bool fast_dput(struct dentry *dentry)
+{
+	int ret;
+	unsigned int d_flags;
+
+	/*
+	 * If we have a d_op->d_delete() operation, we sould not
+	 * let the dentry count go to zero, so use "put__or_lock".
+	 */
+	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE))
+		return lockref_put_or_lock(&dentry->d_lockref);
+
+	/*
+	 * .. otherwise, we can try to just decrement the
+	 * lockref optimistically.
+	 */
+	ret = lockref_put_return(&dentry->d_lockref);
+
+	/*
+	 * If the lockref_put_return() failed due to the lock being held
+	 * by somebody else, the fast path has failed. We will need to
+	 * get the lock, and then check the count again.
+	 */
+	if (unlikely(ret < 0)) {
+		spin_lock(&dentry->d_lock);
+		if (dentry->d_lockref.count > 1) {
+			dentry->d_lockref.count--;
+			spin_unlock(&dentry->d_lock);
+			return 1;
+		}
+		return 0;
+	}
+
+	/*
+	 * If we weren't the last ref, we're done.
+	 */
+	if (ret)
+		return 1;
+
+	/*
+	 * Careful, careful. The reference count went down
+	 * to zero, but we don't hold the dentry lock, so
+	 * somebody else could get it again, and do another
+	 * dput(), and we need to not race with that.
+	 *
+	 * However, there is a very special and common case
+	 * where we don't care, because there is nothing to
+	 * do: the dentry is still hashed, it does not have
+	 * a 'delete' op, and it's referenced and already on
+	 * the LRU list.
+	 *
+	 * NOTE! Since we aren't locked, these values are
+	 * not "stable". However, it is sufficient that at
+	 * some point after we dropped the reference the
+	 * dentry was hashed and the flags had the proper
+	 * value. Other dentry users may have re-gotten
+	 * a reference to the dentry and change that, but
+	 * our work is done - we can leave the dentry
+	 * around with a zero refcount.
+	 */
+	smp_rmb();
+	d_flags = ACCESS_ONCE(dentry->d_flags);
+	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST;
+
+	/* Nothing to do? Dropping the reference was all we needed? */
+	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
+		return 1;
+
+	/*
+	 * Not the fast normal case? Get the lock. We've already decremented
+	 * the refcount, but we'll need to re-check the situation after
+	 * getting the lock.
+	 */
+	spin_lock(&dentry->d_lock);
+
+	/*
+	 * Did somebody else grab a reference to it in the meantime, and
+	 * we're no longer the last user after all? Alternatively, somebody
+	 * else could have killed it and marked it dead. Either way, we
+	 * don't need to do anything else.
+	 */
+	if (dentry->d_lockref.count) {
+		spin_unlock(&dentry->d_lock);
+		return 1;
+	}
+
+	/*
+	 * Re-get the reference we optimistically dropped. We hold the
+	 * lock, and we just tested that it was zero, so we can just
+	 * set it to 1.
+	 */
+	dentry->d_lockref.count = 1;
+	return 0;
+}
+
+
 /* 
  * This is dput
  *
@@ -622,8 +729,14 @@ void dput(struct dentry *dentry)
 		return;
 
 repeat:
-	if (lockref_put_or_lock(&dentry->d_lockref))
+	rcu_read_lock();
+	if (likely(fast_dput(dentry))) {
+		rcu_read_unlock();
 		return;
+	}
+
+	/* Slow case: now with the dentry lock held */
+	rcu_read_unlock();
 
 	/* Unreachable? Get rid of it */
 	if (unlikely(d_unhashed(dentry)))
@@ -810,7 +923,7 @@ static void shrink_dentry_list(struct list_head *list)
 		 * We found an inuse dentry which was not removed from
 		 * the LRU because of laziness during lookup. Do not free it.
 		 */
-		if ((int)dentry->d_lockref.count > 0) {
+		if (dentry->d_lockref.count > 0) {
 			spin_unlock(&dentry->d_lock);
 			if (parent)
 				spin_unlock(&parent->d_lock);
@@ -869,8 +982,8 @@ static void shrink_dentry_list(struct list_head *list)
 	}
 }
 
-static enum lru_status
-dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+static enum lru_status dentry_lru_isolate(struct list_head *item,
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
@@ -890,7 +1003,7 @@ dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 	 * another pass through the LRU.
 	 */
 	if (dentry->d_lockref.count) {
-		d_lru_isolate(dentry);
+		d_lru_isolate(lru, dentry);
 		spin_unlock(&dentry->d_lock);
 		return LRU_REMOVED;
 	}
@@ -921,7 +1034,7 @@ dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 		return LRU_ROTATE;
 	}
 
-	d_lru_shrink_move(dentry, freeable);
+	d_lru_shrink_move(lru, dentry, freeable);
 	spin_unlock(&dentry->d_lock);
 
 	return LRU_REMOVED;
@@ -930,30 +1043,28 @@ dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 /**
  * prune_dcache_sb - shrink the dcache
  * @sb: superblock
- * @nr_to_scan : number of entries to try to free
- * @nid: which node to scan for freeable entities
+ * @sc: shrink control, passed to list_lru_shrink_walk()
  *
- * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
- * done when we need more memory an called from the superblock shrinker
+ * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This
+ * is done when we need more memory and called from the superblock shrinker
  * function.
  *
  * This function may fail to free any resources if all the dentries are in
  * use.
  */
-long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
-		     int nid)
+long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc)
 {
 	LIST_HEAD(dispose);
 	long freed;
 
-	freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate,
-				       &dispose, &nr_to_scan);
+	freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc,
+				     dentry_lru_isolate, &dispose);
 	shrink_dentry_list(&dispose);
 	return freed;
 }
 
 static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
-						spinlock_t *lru_lock, void *arg)
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct dentry	*dentry = container_of(item, struct dentry, d_lru);
@@ -966,7 +1077,7 @@ static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
 	if (!spin_trylock(&dentry->d_lock))
 		return LRU_SKIP;
 
-	d_lru_shrink_move(dentry, freeable);
+	d_lru_shrink_move(lru, dentry, freeable);
 	spin_unlock(&dentry->d_lock);
 
 	return LRU_REMOVED;
@@ -1430,6 +1541,9 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 		}
 		atomic_set(&p->u.count, 1);
 		dname = p->name;
+		if (IS_ENABLED(CONFIG_DCACHE_WORD_ACCESS))
+			kasan_unpoison_shadow(dname,
+				round_up(name->len + 1,	sizeof(unsigned long)));
 	} else  {
 		dname = dentry->d_iname;
 	}	
@@ -1545,9 +1659,25 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 }
 EXPORT_SYMBOL(d_set_d_op);
 
+
+/*
+ * d_set_fallthru - Mark a dentry as falling through to a lower layer
+ * @dentry - The dentry to mark
+ *
+ * Mark a dentry as falling through to the lower layer (as set with
+ * d_pin_lower()).  This flag may be recorded on the medium.
+ */
+void d_set_fallthru(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	dentry->d_flags |= DCACHE_FALLTHRU;
+	spin_unlock(&dentry->d_lock);
+}
+EXPORT_SYMBOL(d_set_fallthru);
+
 static unsigned d_flags_for_inode(struct inode *inode)
 {
-	unsigned add_flags = DCACHE_FILE_TYPE;
+	unsigned add_flags = DCACHE_REGULAR_TYPE;
 
 	if (!inode)
 		return DCACHE_MISS_TYPE;
@@ -1560,13 +1690,21 @@ static unsigned d_flags_for_inode(struct inode *inode)
 			else
 				inode->i_opflags |= IOP_LOOKUP;
 		}
-	} else if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
-		if (unlikely(inode->i_op->follow_link))
+		goto type_determined;
+	}
+
+	if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
+		if (unlikely(inode->i_op->follow_link)) {
 			add_flags = DCACHE_SYMLINK_TYPE;
-		else
-			inode->i_opflags |= IOP_NOFOLLOW;
+			goto type_determined;
+		}
+		inode->i_opflags |= IOP_NOFOLLOW;
 	}
 
+	if (unlikely(!S_ISREG(inode->i_mode)))
+		add_flags = DCACHE_SPECIAL_TYPE;
+
+type_determined:
 	if (unlikely(IS_AUTOMOUNT(inode)))
 		add_flags |= DCACHE_NEED_AUTOMOUNT;
 	return add_flags;
@@ -1577,7 +1715,8 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	unsigned add_flags = d_flags_for_inode(inode);
 
 	spin_lock(&dentry->d_lock);
-	__d_set_type(dentry, add_flags);
+	dentry->d_flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
+	dentry->d_flags |= add_flags;
 	if (inode)
 		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
 	dentry->d_inode = inode;
@@ -2187,37 +2326,6 @@ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
 }
 EXPORT_SYMBOL(d_hash_and_lookup);
 
-/**
- * d_validate - verify dentry provided from insecure source (deprecated)
- * @dentry: The dentry alleged to be valid child of @dparent
- * @dparent: The parent dentry (known to be valid)
- *
- * An insecure source has sent us a dentry, here we verify it and dget() it.
- * This is used by ncpfs in its readdir implementation.
- * Zero is returned in the dentry is invalid.
- *
- * This function is slow for big directories, and deprecated, do not use it.
- */
-int d_validate(struct dentry *dentry, struct dentry *dparent)
-{
-	struct dentry *child;
-
-	spin_lock(&dparent->d_lock);
-	list_for_each_entry(child, &dparent->d_subdirs, d_child) {
-		if (dentry == child) {
-			spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-			__dget_dlock(dentry);
-			spin_unlock(&dentry->d_lock);
-			spin_unlock(&dparent->d_lock);
-			return 1;
-		}
-	}
-	spin_unlock(&dparent->d_lock);
-
-	return 0;
-}
-EXPORT_SYMBOL(d_validate);
-
 /*
  * When a file is deleted, we have two options:
  * - turn this dentry into a negative dentry
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 05f2960ed7c3..96400ab42d13 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -34,93 +34,16 @@ static struct vfsmount *debugfs_mount;
 static int debugfs_mount_count;
 static bool debugfs_registered;
 
-static struct inode *debugfs_get_inode(struct super_block *sb, umode_t mode, dev_t dev,
-				       void *data, const struct file_operations *fops)
-
+static struct inode *debugfs_get_inode(struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
-
 	if (inode) {
 		inode->i_ino = get_next_ino();
-		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		switch (mode & S_IFMT) {
-		default:
-			init_special_inode(inode, mode, dev);
-			break;
-		case S_IFREG:
-			inode->i_fop = fops ? fops : &debugfs_file_operations;
-			inode->i_private = data;
-			break;
-		case S_IFLNK:
-			inode->i_op = &debugfs_link_operations;
-			inode->i_private = data;
-			break;
-		case S_IFDIR:
-			inode->i_op = &simple_dir_inode_operations;
-			inode->i_fop = &simple_dir_operations;
-
-			/* directory inodes start off with i_nlink == 2
-			 * (for "." entry) */
-			inc_nlink(inode);
-			break;
-		}
 	}
 	return inode;
 }
 
-/* SMP-safe */
-static int debugfs_mknod(struct inode *dir, struct dentry *dentry,
-			 umode_t mode, dev_t dev, void *data,
-			 const struct file_operations *fops)
-{
-	struct inode *inode;
-	int error = -EPERM;
-
-	if (dentry->d_inode)
-		return -EEXIST;
-
-	inode = debugfs_get_inode(dir->i_sb, mode, dev, data, fops);
-	if (inode) {
-		d_instantiate(dentry, inode);
-		dget(dentry);
-		error = 0;
-	}
-	return error;
-}
-
-static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
-{
-	int res;
-
-	mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR;
-	res = debugfs_mknod(dir, dentry, mode, 0, NULL, NULL);
-	if (!res) {
-		inc_nlink(dir);
-		fsnotify_mkdir(dir, dentry);
-	}
-	return res;
-}
-
-static int debugfs_link(struct inode *dir, struct dentry *dentry, umode_t mode,
-			void *data)
-{
-	mode = (mode & S_IALLUGO) | S_IFLNK;
-	return debugfs_mknod(dir, dentry, mode, 0, data, NULL);
-}
-
-static int debugfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-			  void *data, const struct file_operations *fops)
-{
-	int res;
-
-	mode = (mode & S_IALLUGO) | S_IFREG;
-	res = debugfs_mknod(dir, dentry, mode, 0, data, fops);
-	if (!res)
-		fsnotify_create(dir, dentry);
-	return res;
-}
-
 static inline int debugfs_positive(struct dentry *dentry)
 {
 	return dentry->d_inode && !d_unhashed(dentry);
@@ -246,10 +169,31 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+static void debugfs_evict_inode(struct inode *inode)
+{
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+	if (S_ISLNK(inode->i_mode))
+		kfree(inode->i_private);
+}
+
 static const struct super_operations debugfs_super_operations = {
 	.statfs		= simple_statfs,
 	.remount_fs	= debugfs_remount,
 	.show_options	= debugfs_show_options,
+	.evict_inode	= debugfs_evict_inode,
+};
+
+static struct vfsmount *debugfs_automount(struct path *path)
+{
+	struct vfsmount *(*f)(void *);
+	f = (struct vfsmount *(*)(void *))path->dentry->d_fsdata;
+	return f(path->dentry->d_inode->i_private);
+}
+
+static const struct dentry_operations debugfs_dops = {
+	.d_delete = always_delete_dentry,
+	.d_automount = debugfs_automount,
 };
 
 static int debug_fill_super(struct super_block *sb, void *data, int silent)
@@ -276,6 +220,7 @@ static int debug_fill_super(struct super_block *sb, void *data, int silent)
 		goto fail;
 
 	sb->s_op = &debugfs_super_operations;
+	sb->s_d_op = &debugfs_dops;
 
 	debugfs_apply_options(sb);
 
@@ -302,11 +247,9 @@ static struct file_system_type debug_fs_type = {
 };
 MODULE_ALIAS_FS("debugfs");
 
-static struct dentry *__create_file(const char *name, umode_t mode,
-				    struct dentry *parent, void *data,
-				    const struct file_operations *fops)
+static struct dentry *start_creating(const char *name, struct dentry *parent)
 {
-	struct dentry *dentry = NULL;
+	struct dentry *dentry;
 	int error;
 
 	pr_debug("debugfs: creating file '%s'\n",name);
@@ -314,7 +257,7 @@ static struct dentry *__create_file(const char *name, umode_t mode,
 	error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
 			      &debugfs_mount_count);
 	if (error)
-		goto exit;
+		return ERR_PTR(error);
 
 	/* If the parent is not specified, we create it in the root.
 	 * We need the root dentry to do this, which is in the super
@@ -326,31 +269,26 @@ static struct dentry *__create_file(const char *name, umode_t mode,
 
 	mutex_lock(&parent->d_inode->i_mutex);
 	dentry = lookup_one_len(name, parent, strlen(name));
-	if (!IS_ERR(dentry)) {
-		switch (mode & S_IFMT) {
-		case S_IFDIR:
-			error = debugfs_mkdir(parent->d_inode, dentry, mode);
-
-			break;
-		case S_IFLNK:
-			error = debugfs_link(parent->d_inode, dentry, mode,
-					     data);
-			break;
-		default:
-			error = debugfs_create(parent->d_inode, dentry, mode,
-					       data, fops);
-			break;
-		}
+	if (!IS_ERR(dentry) && dentry->d_inode) {
 		dput(dentry);
-	} else
-		error = PTR_ERR(dentry);
-	mutex_unlock(&parent->d_inode->i_mutex);
-
-	if (error) {
-		dentry = NULL;
-		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+		dentry = ERR_PTR(-EEXIST);
 	}
-exit:
+	if (IS_ERR(dentry))
+		mutex_unlock(&parent->d_inode->i_mutex);
+	return dentry;
+}
+
+static struct dentry *failed_creating(struct dentry *dentry)
+{
+	mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
+	dput(dentry);
+	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+	return NULL;
+}
+
+static struct dentry *end_creating(struct dentry *dentry)
+{
+	mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
 	return dentry;
 }
 
@@ -384,19 +322,71 @@ struct dentry *debugfs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops)
 {
-	switch (mode & S_IFMT) {
-	case S_IFREG:
-	case 0:
-		break;
-	default:
-		BUG();
-	}
+	struct dentry *dentry;
+	struct inode *inode;
+
+	if (!(mode & S_IFMT))
+		mode |= S_IFREG;
+	BUG_ON(!S_ISREG(mode));
+	dentry = start_creating(name, parent);
+
+	if (IS_ERR(dentry))
+		return NULL;
+
+	inode = debugfs_get_inode(dentry->d_sb);
+	if (unlikely(!inode))
+		return failed_creating(dentry);
 
-	return __create_file(name, mode, parent, data, fops);
+	inode->i_mode = mode;
+	inode->i_fop = fops ? fops : &debugfs_file_operations;
+	inode->i_private = data;
+	d_instantiate(dentry, inode);
+	fsnotify_create(dentry->d_parent->d_inode, dentry);
+	return end_creating(dentry);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_file);
 
 /**
+ * debugfs_create_file_size - create a file in the debugfs filesystem
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have.
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is NULL, then the
+ *          file will be created in the root of the debugfs filesystem.
+ * @data: a pointer to something that the caller will want to get to later
+ *        on.  The inode.i_private pointer will point to this value on
+ *        the open() call.
+ * @fops: a pointer to a struct file_operations that should be used for
+ *        this file.
+ * @file_size: initial file size
+ *
+ * This is the basic "create a file" function for debugfs.  It allows for a
+ * wide range of flexibility in creating a file, or a directory (if you want
+ * to create a directory, the debugfs_create_dir() function is
+ * recommended to be used instead.)
+ *
+ * This function will return a pointer to a dentry if it succeeds.  This
+ * pointer must be passed to the debugfs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here.)  If an error occurs, %NULL will be returned.
+ *
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
+ * returned.
+ */
+struct dentry *debugfs_create_file_size(const char *name, umode_t mode,
+					struct dentry *parent, void *data,
+					const struct file_operations *fops,
+					loff_t file_size)
+{
+	struct dentry *de = debugfs_create_file(name, mode, parent, data, fops);
+
+	if (de)
+		de->d_inode->i_size = file_size;
+	return de;
+}
+EXPORT_SYMBOL_GPL(debugfs_create_file_size);
+
+/**
  * debugfs_create_dir - create a directory in the debugfs filesystem
  * @name: a pointer to a string containing the name of the directory to
  *        create.
@@ -416,12 +406,65 @@ EXPORT_SYMBOL_GPL(debugfs_create_file);
  */
 struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
 {
-	return __create_file(name, S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
-				   parent, NULL, NULL);
+	struct dentry *dentry = start_creating(name, parent);
+	struct inode *inode;
+
+	if (IS_ERR(dentry))
+		return NULL;
+
+	inode = debugfs_get_inode(dentry->d_sb);
+	if (unlikely(!inode))
+		return failed_creating(dentry);
+
+	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	inode->i_op = &simple_dir_inode_operations;
+	inode->i_fop = &simple_dir_operations;
+
+	/* directory inodes start off with i_nlink == 2 (for "." entry) */
+	inc_nlink(inode);
+	d_instantiate(dentry, inode);
+	inc_nlink(dentry->d_parent->d_inode);
+	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
+	return end_creating(dentry);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_dir);
 
 /**
+ * debugfs_create_automount - create automount point in the debugfs filesystem
+ * @name: a pointer to a string containing the name of the file to create.
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is NULL, then the
+ *          file will be created in the root of the debugfs filesystem.
+ * @f: function to be called when pathname resolution steps on that one.
+ * @data: opaque argument to pass to f().
+ *
+ * @f should return what ->d_automount() would.
+ */
+struct dentry *debugfs_create_automount(const char *name,
+					struct dentry *parent,
+					struct vfsmount *(*f)(void *),
+					void *data)
+{
+	struct dentry *dentry = start_creating(name, parent);
+	struct inode *inode;
+
+	if (IS_ERR(dentry))
+		return NULL;
+
+	inode = debugfs_get_inode(dentry->d_sb);
+	if (unlikely(!inode))
+		return failed_creating(dentry);
+
+	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	inode->i_flags |= S_AUTOMOUNT;
+	inode->i_private = data;
+	dentry->d_fsdata = (void *)f;
+	d_instantiate(dentry, inode);
+	return end_creating(dentry);
+}
+EXPORT_SYMBOL(debugfs_create_automount);
+
+/**
  * debugfs_create_symlink- create a symbolic link in the debugfs filesystem
  * @name: a pointer to a string containing the name of the symbolic link to
  *        create.
@@ -447,17 +490,28 @@ EXPORT_SYMBOL_GPL(debugfs_create_dir);
 struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 				      const char *target)
 {
-	struct dentry *result;
-	char *link;
-
-	link = kstrdup(target, GFP_KERNEL);
+	struct dentry *dentry;
+	struct inode *inode;
+	char *link = kstrdup(target, GFP_KERNEL);
 	if (!link)
 		return NULL;
 
-	result = __create_file(name, S_IFLNK | S_IRWXUGO, parent, link, NULL);
-	if (!result)
+	dentry = start_creating(name, parent);
+	if (IS_ERR(dentry)) {
 		kfree(link);
-	return result;
+		return NULL;
+	}
+
+	inode = debugfs_get_inode(dentry->d_sb);
+	if (unlikely(!inode)) {
+		kfree(link);
+		return failed_creating(dentry);
+	}
+	inode->i_mode = S_IFLNK | S_IRWXUGO;
+	inode->i_op = &debugfs_link_operations;
+	inode->i_private = link;
+	d_instantiate(dentry, inode);
+	return end_creating(dentry);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_symlink);
 
@@ -466,23 +520,14 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent)
 	int ret = 0;
 
 	if (debugfs_positive(dentry)) {
-		if (dentry->d_inode) {
-			dget(dentry);
-			switch (dentry->d_inode->i_mode & S_IFMT) {
-			case S_IFDIR:
-				ret = simple_rmdir(parent->d_inode, dentry);
-				break;
-			case S_IFLNK:
-				kfree(dentry->d_inode->i_private);
-				/* fall through */
-			default:
-				simple_unlink(parent->d_inode, dentry);
-				break;
-			}
-			if (!ret)
-				d_delete(dentry);
-			dput(dentry);
-		}
+		dget(dentry);
+		if (S_ISDIR(dentry->d_inode->i_mode))
+			ret = simple_rmdir(parent->d_inode, dentry);
+		else
+			simple_unlink(parent->d_inode, dentry);
+		if (!ret)
+			d_delete(dentry);
+		dput(dentry);
 	}
 	return ret;
 }
@@ -645,7 +690,7 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
 	}
 	d_move(old_dentry, dentry);
 	fsnotify_move(old_dir->d_inode, new_dir->d_inode, old_name,
-		S_ISDIR(old_dentry->d_inode->i_mode),
+		d_is_dir(old_dentry),
 		NULL, old_dentry);
 	fsnotify_oldname_free(old_name);
 	unlock_rename(new_dir, old_dir);
diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c
index e7cfbaf8d0e2..1e6e227134d7 100644
--- a/fs/dlm/netlink.c
+++ b/fs/dlm/netlink.c
@@ -56,13 +56,8 @@ static int send_data(struct sk_buff *skb)
 {
 	struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data);
 	void *data = genlmsg_data(genlhdr);
-	int rv;
 
-	rv = genlmsg_end(skb, data);
-	if (rv < 0) {
-		nlmsg_free(skb);
-		return rv;
-	}
+	genlmsg_end(skb, data);
 
 	return genlmsg_unicast(&init_net, skb, listener_nlportid);
 }
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 2bc2c87f35e7..5718cb9f7273 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -37,20 +37,6 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 	iput(toput_inode);
 }
 
-static void drop_slab(void)
-{
-	int nr_objects;
-
-	do {
-		int nid;
-
-		nr_objects = 0;
-		for_each_online_node(nid)
-			nr_objects += shrink_node_slabs(GFP_KERNEL, nid,
-							1000, 1000);
-	} while (nr_objects > 10);
-}
-
 int drop_caches_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 90d1882b306f..5ba029e627cc 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -124,7 +124,7 @@ ecryptfs_get_key_payload_data(struct key *key)
 }
 
 #define ECRYPTFS_MAX_KEYSET_SIZE 1024
-#define ECRYPTFS_MAX_CIPHER_NAME_SIZE 32
+#define ECRYPTFS_MAX_CIPHER_NAME_SIZE 31
 #define ECRYPTFS_MAX_NUM_ENC_KEYS 64
 #define ECRYPTFS_MAX_IV_BYTES 16	/* 128 bits */
 #define ECRYPTFS_SALT_BYTES 2
@@ -237,7 +237,7 @@ struct ecryptfs_crypt_stat {
 	struct crypto_ablkcipher *tfm;
 	struct crypto_hash *hash_tfm; /* Crypto context for generating
 				       * the initialization vectors */
-	unsigned char cipher[ECRYPTFS_MAX_CIPHER_NAME_SIZE];
+	unsigned char cipher[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
 	unsigned char key[ECRYPTFS_MAX_KEY_BYTES];
 	unsigned char root_iv[ECRYPTFS_MAX_IV_BYTES];
 	struct list_head keysig_list;
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 6f4e659f508f..fd39bad6f1bd 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -230,7 +230,7 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 	}
 	ecryptfs_set_file_lower(
 		file, ecryptfs_inode_to_private(inode)->lower_file);
-	if (S_ISDIR(ecryptfs_dentry->d_inode->i_mode)) {
+	if (d_is_dir(ecryptfs_dentry)) {
 		ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
 		mutex_lock(&crypt_stat->cs_mutex);
 		crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
@@ -303,9 +303,22 @@ ecryptfs_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct file *lower_file = ecryptfs_file_to_lower(file);
 	long rc = -ENOTTY;
 
-	if (lower_file->f_op->unlocked_ioctl)
+	if (!lower_file->f_op->unlocked_ioctl)
+		return rc;
+
+	switch (cmd) {
+	case FITRIM:
+	case FS_IOC_GETFLAGS:
+	case FS_IOC_SETFLAGS:
+	case FS_IOC_GETVERSION:
+	case FS_IOC_SETVERSION:
 		rc = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg);
-	return rc;
+		fsstack_copy_attr_all(file_inode(file), file_inode(lower_file));
+
+		return rc;
+	default:
+		return rc;
+	}
 }
 
 #ifdef CONFIG_COMPAT
@@ -315,9 +328,22 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct file *lower_file = ecryptfs_file_to_lower(file);
 	long rc = -ENOIOCTLCMD;
 
-	if (lower_file->f_op->compat_ioctl)
+	if (!lower_file->f_op->compat_ioctl)
+		return rc;
+
+	switch (cmd) {
+	case FITRIM:
+	case FS_IOC32_GETFLAGS:
+	case FS_IOC32_SETFLAGS:
+	case FS_IOC32_GETVERSION:
+	case FS_IOC32_SETVERSION:
 		rc = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
-	return rc;
+		fsstack_copy_attr_all(file_inode(file), file_inode(lower_file));
+
+		return rc;
+	default:
+		return rc;
+	}
 }
 #endif
 
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 1686dc2da9fd..b08b5187f662 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -67,7 +67,6 @@ static int ecryptfs_inode_set(struct inode *inode, void *opaque)
 	inode->i_ino = lower_inode->i_ino;
 	inode->i_version++;
 	inode->i_mapping->a_ops = &ecryptfs_aops;
-	inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
 
 	if (S_ISLNK(inode->i_mode))
 		inode->i_op = &ecryptfs_symlink_iops;
@@ -908,9 +907,9 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 	lower_inode = ecryptfs_inode_to_lower(inode);
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	mutex_lock(&crypt_stat->cs_mutex);
-	if (S_ISDIR(dentry->d_inode->i_mode))
+	if (d_is_dir(dentry))
 		crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
-	else if (S_ISREG(dentry->d_inode->i_mode)
+	else if (d_is_reg(dentry)
 		 && (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED)
 		     || !(crypt_stat->flags & ECRYPTFS_KEY_VALID))) {
 		struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 917bd5c9776a..6bd67e2011f0 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -891,7 +891,7 @@ struct ecryptfs_parse_tag_70_packet_silly_stack {
 	struct blkcipher_desc desc;
 	char fnek_sig_hex[ECRYPTFS_SIG_SIZE_HEX + 1];
 	char iv[ECRYPTFS_MAX_IV_BYTES];
-	char cipher_string[ECRYPTFS_MAX_CIPHER_NAME_SIZE];
+	char cipher_string[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
 };
 
 /**
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index d9eb84bda559..c095d3264259 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -407,7 +407,7 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 	if (!cipher_name_set) {
 		int cipher_name_len = strlen(ECRYPTFS_DEFAULT_CIPHER);
 
-		BUG_ON(cipher_name_len >= ECRYPTFS_MAX_CIPHER_NAME_SIZE);
+		BUG_ON(cipher_name_len > ECRYPTFS_MAX_CIPHER_NAME_SIZE);
 		strcpy(mount_crypt_stat->global_default_cipher_name,
 		       ECRYPTFS_DEFAULT_CIPHER);
 	}
@@ -520,7 +520,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY);
+	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs");
 	if (rc)
 		goto out1;
 
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 4b0a226024fa..8d0c0df01854 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -118,18 +118,18 @@ static unsigned int eventfd_poll(struct file *file, poll_table *wait)
 {
 	struct eventfd_ctx *ctx = file->private_data;
 	unsigned int events = 0;
-	unsigned long flags;
+	u64 count;
 
 	poll_wait(file, &ctx->wqh, wait);
+	smp_rmb();
+	count = ctx->count;
 
-	spin_lock_irqsave(&ctx->wqh.lock, flags);
-	if (ctx->count > 0)
+	if (count > 0)
 		events |= POLLIN;
-	if (ctx->count == ULLONG_MAX)
+	if (count == ULLONG_MAX)
 		events |= POLLERR;
-	if (ULLONG_MAX - 1 > ctx->count)
+	if (ULLONG_MAX - 1 > count)
 		events |= POLLOUT;
-	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
 	return events;
 }
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index d77f94491352..1e009cad8d5c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1639,9 +1639,9 @@ fetch_events:
 
 			spin_lock_irqsave(&ep->lock, flags);
 		}
-		__remove_wait_queue(&ep->wq, &wait);
 
-		set_current_state(TASK_RUNNING);
+		__remove_wait_queue(&ep->wq, &wait);
+		__set_current_state(TASK_RUNNING);
 	}
 check_events:
 	/* Is it worth to try to dig for events ? */
diff --git a/fs/exec.c b/fs/exec.c
index ad8798e26be9..c7f9b733406d 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -794,8 +794,14 @@ exit:
 
 struct file *open_exec(const char *name)
 {
-	struct filename tmp = { .name = name };
-	return do_open_execat(AT_FDCWD, &tmp, 0);
+	struct filename *filename = getname_kernel(name);
+	struct file *f = ERR_CAST(filename);
+
+	if (!IS_ERR(filename)) {
+		f = do_open_execat(AT_FDCWD, filename, 0);
+		putname(filename);
+	}
+	return f;
 }
 EXPORT_SYMBOL(open_exec);
 
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index f1d3d4eb8c4f..a198e94813fe 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -985,7 +985,6 @@ const struct address_space_operations exofs_aops = {
 	.direct_IO	= exofs_direct_IO,
 
 	/* With these NULL has special meaning or default is not exported */
-	.get_xip_mem	= NULL,
 	.migratepage	= NULL,
 	.launder_page	= NULL,
 	.is_partially_uptodate = NULL,
@@ -1214,7 +1213,6 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
 		memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
 	}
 
-	inode->i_mapping->backing_dev_info = sb->s_bdi;
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &exofs_file_inode_operations;
 		inode->i_fop = &exofs_file_operations;
@@ -1314,7 +1312,6 @@ struct inode *exofs_new_inode(struct inode *dir, umode_t mode)
 
 	set_obj_2bcreated(oi);
 
-	inode->i_mapping->backing_dev_info = sb->s_bdi;
 	inode_init_owner(inode, dir, mode);
 	inode->i_ino = sbi->s_nextid++;
 	inode->i_blkbits = EXOFS_BLKSHIFT;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 95965503afcb..fcc2e565f540 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -836,7 +836,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_sbi;
 	}
 
-	ret = bdi_setup_and_register(&sbi->bdi, "exofs", BDI_CAP_MAP_COPY);
+	ret = bdi_setup_and_register(&sbi->bdi, "exofs");
 	if (ret) {
 		EXOFS_DBGMSG("Failed to bdi_setup_and_register\n");
 		dput(sb->s_root);
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index fdfd206c737a..714cd37a6ba3 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -429,7 +429,7 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 	if (IS_ERR(result))
 		return result;
 
-	if (S_ISDIR(result->d_inode->i_mode)) {
+	if (d_is_dir(result)) {
 		/*
 		 * This request is for a directory.
 		 *
diff --git a/fs/ext2/Kconfig b/fs/ext2/Kconfig
index 14a6780fd034..c634874e12d9 100644
--- a/fs/ext2/Kconfig
+++ b/fs/ext2/Kconfig
@@ -42,14 +42,3 @@ config EXT2_FS_SECURITY
 
 	  If you are not using a security module that requires using
 	  extended attributes for file security labels, say N.
-
-config EXT2_FS_XIP
-	bool "Ext2 execute in place support"
-	depends on EXT2_FS && MMU
-	help
-	  Execute in place can be used on memory-backed block devices. If you
-	  enable this option, you can select to mount block devices which are
-	  capable of this feature without using the page cache.
-
-	  If you do not use a block device that is capable of using this,
-	  or if unsure, say N.
diff --git a/fs/ext2/Makefile b/fs/ext2/Makefile
index f42af45cfd88..445b0e996a12 100644
--- a/fs/ext2/Makefile
+++ b/fs/ext2/Makefile
@@ -10,4 +10,3 @@ ext2-y := balloc.o dir.o file.o ialloc.o inode.o \
 ext2-$(CONFIG_EXT2_FS_XATTR)	 += xattr.o xattr_user.o xattr_trusted.o
 ext2-$(CONFIG_EXT2_FS_POSIX_ACL) += acl.o
 ext2-$(CONFIG_EXT2_FS_SECURITY)	 += xattr_security.o
-ext2-$(CONFIG_EXT2_FS_XIP)	 += xip.o
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index e4279ead4a05..678f9ab08c48 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -380,10 +380,15 @@ struct ext2_inode {
 #define EXT2_MOUNT_NO_UID32		0x000200  /* Disable 32-bit UIDs */
 #define EXT2_MOUNT_XATTR_USER		0x004000  /* Extended user attributes */
 #define EXT2_MOUNT_POSIX_ACL		0x008000  /* POSIX Access Control Lists */
-#define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
+#define EXT2_MOUNT_XIP			0x010000  /* Obsolete, use DAX */
 #define EXT2_MOUNT_USRQUOTA		0x020000  /* user quota */
 #define EXT2_MOUNT_GRPQUOTA		0x040000  /* group quota */
 #define EXT2_MOUNT_RESERVATION		0x080000  /* Preallocation */
+#ifdef CONFIG_FS_DAX
+#define EXT2_MOUNT_DAX			0x100000  /* Direct Access */
+#else
+#define EXT2_MOUNT_DAX			0
+#endif
 
 
 #define clear_opt(o, opt)		o &= ~EXT2_MOUNT_##opt
@@ -788,11 +793,10 @@ extern int ext2_fsync(struct file *file, loff_t start, loff_t end,
 		      int datasync);
 extern const struct inode_operations ext2_file_inode_operations;
 extern const struct file_operations ext2_file_operations;
-extern const struct file_operations ext2_xip_file_operations;
+extern const struct file_operations ext2_dax_file_operations;
 
 /* inode.c */
 extern const struct address_space_operations ext2_aops;
-extern const struct address_space_operations ext2_aops_xip;
 extern const struct address_space_operations ext2_nobh_aops;
 
 /* namei.c */
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 7c87b22a7228..e31701713516 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -25,6 +25,36 @@
 #include "xattr.h"
 #include "acl.h"
 
+#ifdef CONFIG_FS_DAX
+static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_fault(vma, vmf, ext2_get_block);
+}
+
+static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_mkwrite(vma, vmf, ext2_get_block);
+}
+
+static const struct vm_operations_struct ext2_dax_vm_ops = {
+	.fault		= ext2_dax_fault,
+	.page_mkwrite	= ext2_dax_mkwrite,
+};
+
+static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!IS_DAX(file_inode(file)))
+		return generic_file_mmap(file, vma);
+
+	file_accessed(file);
+	vma->vm_ops = &ext2_dax_vm_ops;
+	vma->vm_flags |= VM_MIXEDMAP;
+	return 0;
+}
+#else
+#define ext2_file_mmap	generic_file_mmap
+#endif
+
 /*
  * Called when filp is released. This happens when all file descriptors
  * for a single struct file are closed. Note that different open() calls
@@ -70,7 +100,7 @@ const struct file_operations ext2_file_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext2_compat_ioctl,
 #endif
-	.mmap		= generic_file_mmap,
+	.mmap		= ext2_file_mmap,
 	.open		= dquot_file_open,
 	.release	= ext2_release_file,
 	.fsync		= ext2_fsync,
@@ -78,16 +108,18 @@ const struct file_operations ext2_file_operations = {
 	.splice_write	= iter_file_splice_write,
 };
 
-#ifdef CONFIG_EXT2_FS_XIP
-const struct file_operations ext2_xip_file_operations = {
+#ifdef CONFIG_FS_DAX
+const struct file_operations ext2_dax_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= xip_file_read,
-	.write		= xip_file_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.unlocked_ioctl = ext2_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext2_compat_ioctl,
 #endif
-	.mmap		= xip_file_mmap,
+	.mmap		= ext2_file_mmap,
 	.open		= dquot_file_open,
 	.release	= ext2_release_file,
 	.fsync		= ext2_fsync,
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 7d66fb0e4cca..6c14bb8322fa 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -170,7 +170,7 @@ static void ext2_preread_inode(struct inode *inode)
 	struct ext2_group_desc * gdp;
 	struct backing_dev_info *bdi;
 
-	bdi = inode->i_mapping->backing_dev_info;
+	bdi = inode_to_bdi(inode);
 	if (bdi_read_congested(bdi))
 		return;
 	if (bdi_write_congested(bdi))
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 36d35c36311d..6434bc000125 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -34,7 +34,6 @@
 #include <linux/aio.h>
 #include "ext2.h"
 #include "acl.h"
-#include "xip.h"
 #include "xattr.h"
 
 static int __ext2_write_inode(struct inode *inode, int do_sync);
@@ -731,12 +730,14 @@ static int ext2_get_blocks(struct inode *inode,
 		goto cleanup;
 	}
 
-	if (ext2_use_xip(inode->i_sb)) {
+	if (IS_DAX(inode)) {
 		/*
-		 * we need to clear the block
+		 * block must be initialised before we put it in the tree
+		 * so that it's not found by another thread before it's
+		 * initialised
 		 */
-		err = ext2_clear_xip_target (inode,
-			le32_to_cpu(chain[depth-1].key));
+		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
+						1 << inode->i_blkbits);
 		if (err) {
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
@@ -859,7 +860,12 @@ ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext2_get_block);
+	if (IS_DAX(inode))
+		ret = dax_do_io(rw, iocb, inode, iter, offset, ext2_get_block,
+				NULL, DIO_LOCKING);
+	else
+		ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
+					 ext2_get_block);
 	if (ret < 0 && (rw & WRITE))
 		ext2_write_failed(mapping, offset + count);
 	return ret;
@@ -885,11 +891,6 @@ const struct address_space_operations ext2_aops = {
 	.error_remove_page	= generic_error_remove_page,
 };
 
-const struct address_space_operations ext2_aops_xip = {
-	.bmap			= ext2_bmap,
-	.get_xip_mem		= ext2_get_xip_mem,
-};
-
 const struct address_space_operations ext2_nobh_aops = {
 	.readpage		= ext2_readpage,
 	.readpages		= ext2_readpages,
@@ -1201,8 +1202,8 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 
 	inode_dio_wait(inode);
 
-	if (mapping_is_xip(inode->i_mapping))
-		error = xip_truncate_page(inode->i_mapping, newsize);
+	if (IS_DAX(inode))
+		error = dax_truncate_page(inode, newsize, ext2_get_block);
 	else if (test_opt(inode->i_sb, NOBH))
 		error = nobh_truncate_page(inode->i_mapping,
 				newsize, ext2_get_block);
@@ -1273,7 +1274,8 @@ void ext2_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = EXT2_I(inode)->i_flags;
 
-	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME |
+				S_DIRSYNC | S_DAX);
 	if (flags & EXT2_SYNC_FL)
 		inode->i_flags |= S_SYNC;
 	if (flags & EXT2_APPEND_FL)
@@ -1284,6 +1286,8 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_NOATIME;
 	if (flags & EXT2_DIRSYNC_FL)
 		inode->i_flags |= S_DIRSYNC;
+	if (test_opt(inode->i_sb, DAX))
+		inode->i_flags |= S_DAX;
 }
 
 /* Propagate flags from i_flags to EXT2_I(inode)->i_flags */
@@ -1384,9 +1388,9 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext2_file_inode_operations;
-		if (ext2_use_xip(inode->i_sb)) {
-			inode->i_mapping->a_ops = &ext2_aops_xip;
-			inode->i_fop = &ext2_xip_file_operations;
+		if (test_opt(inode->i_sb, DAX)) {
+			inode->i_mapping->a_ops = &ext2_aops;
+			inode->i_fop = &ext2_dax_file_operations;
 		} else if (test_opt(inode->i_sb, NOBH)) {
 			inode->i_mapping->a_ops = &ext2_nobh_aops;
 			inode->i_fop = &ext2_file_operations;
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index c268d0af1db9..148f6e3789ea 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -35,7 +35,6 @@
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "xip.h"
 
 static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
 {
@@ -105,9 +104,9 @@ static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode
 		return PTR_ERR(inode);
 
 	inode->i_op = &ext2_file_inode_operations;
-	if (ext2_use_xip(inode->i_sb)) {
-		inode->i_mapping->a_ops = &ext2_aops_xip;
-		inode->i_fop = &ext2_xip_file_operations;
+	if (test_opt(inode->i_sb, DAX)) {
+		inode->i_mapping->a_ops = &ext2_aops;
+		inode->i_fop = &ext2_dax_file_operations;
 	} else if (test_opt(inode->i_sb, NOBH)) {
 		inode->i_mapping->a_ops = &ext2_nobh_aops;
 		inode->i_fop = &ext2_file_operations;
@@ -126,9 +125,9 @@ static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 		return PTR_ERR(inode);
 
 	inode->i_op = &ext2_file_inode_operations;
-	if (ext2_use_xip(inode->i_sb)) {
-		inode->i_mapping->a_ops = &ext2_aops_xip;
-		inode->i_fop = &ext2_xip_file_operations;
+	if (test_opt(inode->i_sb, DAX)) {
+		inode->i_mapping->a_ops = &ext2_aops;
+		inode->i_fop = &ext2_dax_file_operations;
 	} else if (test_opt(inode->i_sb, NOBH)) {
 		inode->i_mapping->a_ops = &ext2_nobh_aops;
 		inode->i_fop = &ext2_file_operations;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index ae55fddc26a9..d0e746e96511 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -35,7 +35,6 @@
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "xip.h"
 
 static void ext2_sync_super(struct super_block *sb,
 			    struct ext2_super_block *es, int wait);
@@ -292,9 +291,11 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",grpquota");
 #endif
 
-#if defined(CONFIG_EXT2_FS_XIP)
+#ifdef CONFIG_FS_DAX
 	if (sbi->s_mount_opt & EXT2_MOUNT_XIP)
 		seq_puts(seq, ",xip");
+	if (sbi->s_mount_opt & EXT2_MOUNT_DAX)
+		seq_puts(seq, ",dax");
 #endif
 
 	if (!test_opt(sb, RESERVATION))
@@ -403,7 +404,7 @@ enum {
 	Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic,
 	Opt_err_ro, Opt_nouid32, Opt_nocheck, Opt_debug,
 	Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr,
-	Opt_acl, Opt_noacl, Opt_xip, Opt_ignore, Opt_err, Opt_quota,
+	Opt_acl, Opt_noacl, Opt_xip, Opt_dax, Opt_ignore, Opt_err, Opt_quota,
 	Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation
 };
 
@@ -432,6 +433,7 @@ static const match_table_t tokens = {
 	{Opt_acl, "acl"},
 	{Opt_noacl, "noacl"},
 	{Opt_xip, "xip"},
+	{Opt_dax, "dax"},
 	{Opt_grpquota, "grpquota"},
 	{Opt_ignore, "noquota"},
 	{Opt_quota, "quota"},
@@ -559,10 +561,14 @@ static int parse_options(char *options, struct super_block *sb)
 			break;
 #endif
 		case Opt_xip:
-#ifdef CONFIG_EXT2_FS_XIP
-			set_opt (sbi->s_mount_opt, XIP);
+			ext2_msg(sb, KERN_INFO, "use dax instead of xip");
+			set_opt(sbi->s_mount_opt, XIP);
+			/* Fall through */
+		case Opt_dax:
+#ifdef CONFIG_FS_DAX
+			set_opt(sbi->s_mount_opt, DAX);
 #else
-			ext2_msg(sb, KERN_INFO, "xip option not supported");
+			ext2_msg(sb, KERN_INFO, "dax option not supported");
 #endif
 			break;
 
@@ -877,9 +883,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ?
 		 MS_POSIXACL : 0);
 
-	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
-				    EXT2_MOUNT_XIP if not */
-
 	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV &&
 	    (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) ||
 	     EXT2_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
@@ -909,11 +912,17 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
-	if (ext2_use_xip(sb) && blocksize != PAGE_SIZE) {
-		if (!silent)
+	if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
+		if (blocksize != PAGE_SIZE) {
 			ext2_msg(sb, KERN_ERR,
-				"error: unsupported blocksize for xip");
-		goto failed_mount;
+					"error: unsupported blocksize for dax");
+			goto failed_mount;
+		}
+		if (!sb->s_bdev->bd_disk->fops->direct_access) {
+			ext2_msg(sb, KERN_ERR,
+					"error: device does not support dax");
+			goto failed_mount;
+		}
 	}
 
 	/* If the blocksize doesn't match, re-read the thing.. */
@@ -1259,7 +1268,6 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 {
 	struct ext2_sb_info * sbi = EXT2_SB(sb);
 	struct ext2_super_block * es;
-	unsigned long old_mount_opt = sbi->s_mount_opt;
 	struct ext2_mount_options old_opts;
 	unsigned long old_sb_flags;
 	int err;
@@ -1284,22 +1292,11 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
 
-	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
-				    EXT2_MOUNT_XIP if not */
-
-	if ((ext2_use_xip(sb)) && (sb->s_blocksize != PAGE_SIZE)) {
-		ext2_msg(sb, KERN_WARNING,
-			"warning: unsupported blocksize for xip");
-		err = -EINVAL;
-		goto restore_opts;
-	}
-
 	es = sbi->s_es;
-	if ((sbi->s_mount_opt ^ old_mount_opt) & EXT2_MOUNT_XIP) {
+	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT2_MOUNT_DAX) {
 		ext2_msg(sb, KERN_WARNING, "warning: refusing change of "
-			 "xip flag with busy inodes while remounting");
-		sbi->s_mount_opt &= ~EXT2_MOUNT_XIP;
-		sbi->s_mount_opt |= old_mount_opt & EXT2_MOUNT_XIP;
+			 "dax flag with busy inodes while remounting");
+		sbi->s_mount_opt ^= EXT2_MOUNT_DAX;
 	}
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		spin_unlock(&sbi->s_lock);
diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
deleted file mode 100644
index e98171a11cfe..000000000000
--- a/fs/ext2/xip.c
+++ /dev/null
@@ -1,91 +0,0 @@
-/*
- *  linux/fs/ext2/xip.c
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte (cotte@de.ibm.com)
- */
-
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/genhd.h>
-#include <linux/buffer_head.h>
-#include <linux/blkdev.h>
-#include "ext2.h"
-#include "xip.h"
-
-static inline int
-__inode_direct_access(struct inode *inode, sector_t block,
-		      void **kaddr, unsigned long *pfn)
-{
-	struct block_device *bdev = inode->i_sb->s_bdev;
-	const struct block_device_operations *ops = bdev->bd_disk->fops;
-	sector_t sector;
-
-	sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
-
-	BUG_ON(!ops->direct_access);
-	return ops->direct_access(bdev, sector, kaddr, pfn);
-}
-
-static inline int
-__ext2_get_block(struct inode *inode, pgoff_t pgoff, int create,
-		   sector_t *result)
-{
-	struct buffer_head tmp;
-	int rc;
-
-	memset(&tmp, 0, sizeof(struct buffer_head));
-	tmp.b_size = 1 << inode->i_blkbits;
-	rc = ext2_get_block(inode, pgoff, &tmp, create);
-	*result = tmp.b_blocknr;
-
-	/* did we get a sparse block (hole in the file)? */
-	if (!tmp.b_blocknr && !rc) {
-		BUG_ON(create);
-		rc = -ENODATA;
-	}
-
-	return rc;
-}
-
-int
-ext2_clear_xip_target(struct inode *inode, sector_t block)
-{
-	void *kaddr;
-	unsigned long pfn;
-	int rc;
-
-	rc = __inode_direct_access(inode, block, &kaddr, &pfn);
-	if (!rc)
-		clear_page(kaddr);
-	return rc;
-}
-
-void ext2_xip_verify_sb(struct super_block *sb)
-{
-	struct ext2_sb_info *sbi = EXT2_SB(sb);
-
-	if ((sbi->s_mount_opt & EXT2_MOUNT_XIP) &&
-	    !sb->s_bdev->bd_disk->fops->direct_access) {
-		sbi->s_mount_opt &= (~EXT2_MOUNT_XIP);
-		ext2_msg(sb, KERN_WARNING,
-			     "warning: ignoring xip option - "
-			     "not supported by bdev");
-	}
-}
-
-int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
-				void **kmem, unsigned long *pfn)
-{
-	int rc;
-	sector_t block;
-
-	/* first, retrieve the sector number */
-	rc = __ext2_get_block(mapping->host, pgoff, create, &block);
-	if (rc)
-		return rc;
-
-	/* retrieve address of the target data */
-	rc = __inode_direct_access(mapping->host, block, kmem, pfn);
-	return rc;
-}
diff --git a/fs/ext2/xip.h b/fs/ext2/xip.h
deleted file mode 100644
index 18b34d2f31b3..000000000000
--- a/fs/ext2/xip.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- *  linux/fs/ext2/xip.h
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte (cotte@de.ibm.com)
- */
-
-#ifdef CONFIG_EXT2_FS_XIP
-extern void ext2_xip_verify_sb (struct super_block *);
-extern int ext2_clear_xip_target (struct inode *, sector_t);
-
-static inline int ext2_use_xip (struct super_block *sb)
-{
-	struct ext2_sb_info *sbi = EXT2_SB(sb);
-	return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
-}
-int ext2_get_xip_mem(struct address_space *, pgoff_t, int,
-				void **, unsigned long *);
-#define mapping_is_xip(map) unlikely(map->a_ops->get_xip_mem)
-#else
-#define mapping_is_xip(map)			0
-#define ext2_xip_verify_sb(sb)			do { } while (0)
-#define ext2_use_xip(sb)			0
-#define ext2_clear_xip_target(inode, chain)	0
-#define ext2_get_xip_mem			NULL
-#endif
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 9b4e7d750d4f..d4dbf3c259b3 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -466,6 +466,8 @@ static void ext3_put_super (struct super_block * sb)
 	}
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
+	mutex_destroy(&sbi->s_orphan_lock);
+	mutex_destroy(&sbi->s_resize_lock);
 	kfree(sbi);
 }
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a75fba67bb1f..f63c3d5805c4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -364,7 +364,8 @@ struct flex_groups {
 #define EXT4_DIRTY_FL			0x00000100
 #define EXT4_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
 #define EXT4_NOCOMPR_FL			0x00000400 /* Don't compress */
-#define EXT4_ECOMPR_FL			0x00000800 /* Compression error */
+	/* nb: was previously EXT2_ECOMPR_FL */
+#define EXT4_ENCRYPT_FL			0x00000800 /* encrypted file */
 /* End compression flags --- maybe not all used */
 #define EXT4_INDEX_FL			0x00001000 /* hash-indexed directory */
 #define EXT4_IMAGIC_FL			0x00002000 /* AFS directory */
@@ -421,7 +422,7 @@ enum {
 	EXT4_INODE_DIRTY	= 8,
 	EXT4_INODE_COMPRBLK	= 9,	/* One or more compressed clusters */
 	EXT4_INODE_NOCOMPR	= 10,	/* Don't compress */
-	EXT4_INODE_ECOMPR	= 11,	/* Compression error */
+	EXT4_INODE_ENCRYPT	= 11,	/* Compression error */
 /* End compression flags --- maybe not all used */
 	EXT4_INODE_INDEX	= 12,	/* hash-indexed directory */
 	EXT4_INODE_IMAGIC	= 13,	/* AFS directory */
@@ -466,7 +467,7 @@ static inline void ext4_check_flag_values(void)
 	CHECK_FLAG_VALUE(DIRTY);
 	CHECK_FLAG_VALUE(COMPRBLK);
 	CHECK_FLAG_VALUE(NOCOMPR);
-	CHECK_FLAG_VALUE(ECOMPR);
+	CHECK_FLAG_VALUE(ENCRYPT);
 	CHECK_FLAG_VALUE(INDEX);
 	CHECK_FLAG_VALUE(IMAGIC);
 	CHECK_FLAG_VALUE(JOURNAL_DATA);
@@ -965,6 +966,11 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_ERRORS_MASK		0x00070
 #define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
 #define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
+#ifdef CONFIG_FS_DAX
+#define EXT4_MOUNT_DAX			0x00200	/* Direct Access */
+#else
+#define EXT4_MOUNT_DAX			0
+#endif
 #define EXT4_MOUNT_DATA_FLAGS		0x00C00	/* Mode for data writes: */
 #define EXT4_MOUNT_JOURNAL_DATA		0x00400	/* Write data to journal */
 #define EXT4_MOUNT_ORDERED_DATA		0x00800	/* Flush data before commit */
@@ -1043,6 +1049,12 @@ extern void ext4_set_bits(void *bm, int cur, int len);
 /* Metadata checksum algorithm codes */
 #define EXT4_CRC32C_CHKSUM		1
 
+/* Encryption algorithms */
+#define EXT4_ENCRYPTION_MODE_INVALID		0
+#define EXT4_ENCRYPTION_MODE_AES_256_XTS	1
+#define EXT4_ENCRYPTION_MODE_AES_256_GCM	2
+#define EXT4_ENCRYPTION_MODE_AES_256_CBC	3
+
 /*
  * Structure of the super block
  */
@@ -1156,7 +1168,8 @@ struct ext4_super_block {
 	__le32	s_grp_quota_inum;	/* inode for tracking group quota */
 	__le32	s_overhead_clusters;	/* overhead blocks/clusters in fs */
 	__le32	s_backup_bgs[2];	/* groups with sparse_super2 SBs */
-	__le32	s_reserved[106];	/* Padding to the end of the block */
+	__u8	s_encrypt_algos[4];	/* Encryption algorithms in use  */
+	__le32	s_reserved[105];	/* Padding to the end of the block */
 	__le32	s_checksum;		/* crc32c(superblock) */
 };
 
@@ -1522,6 +1535,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
  * GDT_CSUM bits are mutually exclusive.
  */
 #define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM	0x0400
+#define EXT4_FEATURE_RO_COMPAT_READONLY		0x1000
 
 #define EXT4_FEATURE_INCOMPAT_COMPRESSION	0x0001
 #define EXT4_FEATURE_INCOMPAT_FILETYPE		0x0002
@@ -1537,6 +1551,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM	0x2000 /* use crc32c for bg */
 #define EXT4_FEATURE_INCOMPAT_LARGEDIR		0x4000 /* >2GB or 3-lvl htree */
 #define EXT4_FEATURE_INCOMPAT_INLINE_DATA	0x8000 /* data in inode */
+#define EXT4_FEATURE_INCOMPAT_ENCRYPT		0x10000
 
 #define EXT2_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
 #define EXT2_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
@@ -2578,6 +2593,7 @@ extern const struct file_operations ext4_dir_operations;
 /* file.c */
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
+extern const struct file_operations ext4_dax_file_operations;
 extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
 
 /* inline.c */
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8131be8c0af3..33a09da16c9c 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -95,7 +95,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct mutex *aio_mutex = NULL;
 	struct blk_plug plug;
-	int o_direct = file->f_flags & O_DIRECT;
+	int o_direct = io_is_direct(file);
 	int overwrite = 0;
 	size_t length = iov_iter_count(from);
 	ssize_t ret;
@@ -191,17 +191,41 @@ errout:
 	return ret;
 }
 
+#ifdef CONFIG_FS_DAX
+static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_fault(vma, vmf, ext4_get_block);
+					/* Is this the right get_block? */
+}
+
+static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_mkwrite(vma, vmf, ext4_get_block);
+}
+
+static const struct vm_operations_struct ext4_dax_vm_ops = {
+	.fault		= ext4_dax_fault,
+	.page_mkwrite	= ext4_dax_mkwrite,
+};
+#else
+#define ext4_dax_vm_ops	ext4_file_vm_ops
+#endif
+
 static const struct vm_operations_struct ext4_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	file_accessed(file);
-	vma->vm_ops = &ext4_file_vm_ops;
+	if (IS_DAX(file_inode(file))) {
+		vma->vm_ops = &ext4_dax_vm_ops;
+		vma->vm_flags |= VM_MIXEDMAP;
+	} else {
+		vma->vm_ops = &ext4_file_vm_ops;
+	}
 	return 0;
 }
 
@@ -600,6 +624,26 @@ const struct file_operations ext4_file_operations = {
 	.fallocate	= ext4_fallocate,
 };
 
+#ifdef CONFIG_FS_DAX
+const struct file_operations ext4_dax_file_operations = {
+	.llseek		= ext4_llseek,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= ext4_file_write_iter,
+	.unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext4_compat_ioctl,
+#endif
+	.mmap		= ext4_file_mmap,
+	.open		= ext4_file_open,
+	.release	= ext4_release_file,
+	.fsync		= ext4_sync_file,
+	/* Splice not yet supported with DAX */
+	.fallocate	= ext4_fallocate,
+};
+#endif
+
 const struct inode_operations ext4_file_inode_operations = {
 	.setattr	= ext4_setattr,
 	.getattr	= ext4_getattr,
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 36b369697a13..45fe924f82bc 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -689,14 +689,22 @@ retry:
 			inode_dio_done(inode);
 			goto locked;
 		}
-		ret = __blockdev_direct_IO(rw, iocb, inode,
-				 inode->i_sb->s_bdev, iter, offset,
-				 ext4_get_block, NULL, NULL, 0);
+		if (IS_DAX(inode))
+			ret = dax_do_io(rw, iocb, inode, iter, offset,
+					ext4_get_block, NULL, 0);
+		else
+			ret = __blockdev_direct_IO(rw, iocb, inode,
+					inode->i_sb->s_bdev, iter, offset,
+					ext4_get_block, NULL, NULL, 0);
 		inode_dio_done(inode);
 	} else {
 locked:
-		ret = blockdev_direct_IO(rw, iocb, inode, iter,
-				 offset, ext4_get_block);
+		if (IS_DAX(inode))
+			ret = dax_do_io(rw, iocb, inode, iter, offset,
+					ext4_get_block, NULL, DIO_LOCKING);
+		else
+			ret = blockdev_direct_IO(rw, iocb, inode, iter,
+					offset, ext4_get_block);
 
 		if (unlikely((rw & WRITE) && ret < 0)) {
 			loff_t isize = i_size_read(inode);
@@ -1393,10 +1401,7 @@ end_range:
 				 * to free. Everything was covered by the start
 				 * of the range.
 				 */
-				return 0;
-			} else {
-				/* Shared branch grows from an indirect block */
-				partial2--;
+				goto do_indirects;
 			}
 		} else {
 			/*
@@ -1427,56 +1432,96 @@ end_range:
 	/* Punch happened within the same level (n == n2) */
 	partial = ext4_find_shared(inode, n, offsets, chain, &nr);
 	partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
-	/*
-	 * ext4_find_shared returns Indirect structure which
-	 * points to the last element which should not be
-	 * removed by truncate. But this is end of the range
-	 * in punch_hole so we need to point to the next element
-	 */
-	partial2->p++;
-	while ((partial > chain) || (partial2 > chain2)) {
-		/* We're at the same block, so we're almost finished */
-		if ((partial->bh && partial2->bh) &&
-		    (partial->bh->b_blocknr == partial2->bh->b_blocknr)) {
-			if ((partial > chain) && (partial2 > chain2)) {
+
+	/* Free top, but only if partial2 isn't its subtree. */
+	if (nr) {
+		int level = min(partial - chain, partial2 - chain2);
+		int i;
+		int subtree = 1;
+
+		for (i = 0; i <= level; i++) {
+			if (offsets[i] != offsets2[i]) {
+				subtree = 0;
+				break;
+			}
+		}
+
+		if (!subtree) {
+			if (partial == chain) {
+				/* Shared branch grows from the inode */
+				ext4_free_branches(handle, inode, NULL,
+						   &nr, &nr+1,
+						   (chain+n-1) - partial);
+				*partial->p = 0;
+			} else {
+				/* Shared branch grows from an indirect block */
+				BUFFER_TRACE(partial->bh, "get_write_access");
 				ext4_free_branches(handle, inode, partial->bh,
-						   partial->p + 1,
-						   partial2->p,
+						   partial->p,
+						   partial->p+1,
 						   (chain+n-1) - partial);
-				BUFFER_TRACE(partial->bh, "call brelse");
-				brelse(partial->bh);
-				BUFFER_TRACE(partial2->bh, "call brelse");
-				brelse(partial2->bh);
 			}
-			return 0;
 		}
+	}
+
+	if (!nr2) {
 		/*
-		 * Clear the ends of indirect blocks on the shared branch
-		 * at the start of the range
+		 * ext4_find_shared returns Indirect structure which
+		 * points to the last element which should not be
+		 * removed by truncate. But this is end of the range
+		 * in punch_hole so we need to point to the next element
 		 */
-		if (partial > chain) {
+		partial2->p++;
+	}
+
+	while (partial > chain || partial2 > chain2) {
+		int depth = (chain+n-1) - partial;
+		int depth2 = (chain2+n2-1) - partial2;
+
+		if (partial > chain && partial2 > chain2 &&
+		    partial->bh->b_blocknr == partial2->bh->b_blocknr) {
+			/*
+			 * We've converged on the same block. Clear the range,
+			 * then we're done.
+			 */
 			ext4_free_branches(handle, inode, partial->bh,
-				   partial->p + 1,
-				   (__le32 *)partial->bh->b_data+addr_per_block,
-				   (chain+n-1) - partial);
+					   partial->p + 1,
+					   partial2->p,
+					   (chain+n-1) - partial);
 			BUFFER_TRACE(partial->bh, "call brelse");
 			brelse(partial->bh);
-			partial--;
+			BUFFER_TRACE(partial2->bh, "call brelse");
+			brelse(partial2->bh);
+			return 0;
 		}
+
 		/*
-		 * Clear the ends of indirect blocks on the shared branch
-		 * at the end of the range
+		 * The start and end partial branches may not be at the same
+		 * level even though the punch happened within one level. So, we
+		 * give them a chance to arrive at the same level, then walk
+		 * them in step with each other until we converge on the same
+		 * block.
 		 */
-		if (partial2 > chain2) {
+		if (partial > chain && depth <= depth2) {
+			ext4_free_branches(handle, inode, partial->bh,
+					   partial->p + 1,
+					   (__le32 *)partial->bh->b_data+addr_per_block,
+					   (chain+n-1) - partial);
+			BUFFER_TRACE(partial->bh, "call brelse");
+			brelse(partial->bh);
+			partial--;
+		}
+		if (partial2 > chain2 && depth2 <= depth) {
 			ext4_free_branches(handle, inode, partial2->bh,
 					   (__le32 *)partial2->bh->b_data,
 					   partial2->p,
-					   (chain2+n-1) - partial2);
+					   (chain2+n2-1) - partial2);
 			BUFFER_TRACE(partial2->bh, "call brelse");
 			brelse(partial2->bh);
 			partial2--;
 		}
 	}
+	return 0;
 
 do_indirects:
 	/* Kill the remaining (whole) subtrees */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5653fa42930b..5cb9a212b86f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -657,6 +657,18 @@ has_zeroout:
 	return retval;
 }
 
+static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
+{
+	struct inode *inode = bh->b_assoc_map->host;
+	/* XXX: breaks on 32-bit > 16GB. Is that even supported? */
+	loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
+	int err;
+	if (!uptodate)
+		return;
+	WARN_ON(!buffer_unwritten(bh));
+	err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -694,6 +706,11 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		if (IS_DAX(inode) && buffer_unwritten(bh) && !io_end) {
+			bh->b_assoc_map = inode->i_mapping;
+			bh->b_private = (void *)(unsigned long)iblock;
+			bh->b_end_io = ext4_end_io_unwritten;
+		}
 		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
 			set_buffer_defer_completion(bh);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
@@ -1007,6 +1024,7 @@ static int ext4_write_end(struct file *file,
 {
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
+	loff_t old_size = inode->i_size;
 	int ret = 0, ret2;
 	int i_size_changed = 0;
 
@@ -1037,6 +1055,8 @@ static int ext4_write_end(struct file *file,
 	unlock_page(page);
 	page_cache_release(page);
 
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
 	/*
 	 * Don't mark the inode dirty under page lock. First, it unnecessarily
 	 * makes the holding time of page lock longer. Second, it forces lock
@@ -1078,6 +1098,7 @@ static int ext4_journalled_write_end(struct file *file,
 {
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
+	loff_t old_size = inode->i_size;
 	int ret = 0, ret2;
 	int partial = 0;
 	unsigned from, to;
@@ -1110,6 +1131,9 @@ static int ext4_journalled_write_end(struct file *file,
 	unlock_page(page);
 	page_cache_release(page);
 
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
+
 	if (size_changed) {
 		ret2 = ext4_mark_inode_dirty(handle, inode);
 		if (!ret)
@@ -3010,13 +3034,14 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		get_block_func = ext4_get_block_write;
 		dio_flags = DIO_LOCKING;
 	}
-	ret = __blockdev_direct_IO(rw, iocb, inode,
-				   inode->i_sb->s_bdev, iter,
-				   offset,
-				   get_block_func,
-				   ext4_end_io_dio,
-				   NULL,
-				   dio_flags);
+	if (IS_DAX(inode))
+		ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func,
+				ext4_end_io_dio, dio_flags);
+	else
+		ret = __blockdev_direct_IO(rw, iocb, inode,
+					   inode->i_sb->s_bdev, iter, offset,
+					   get_block_func,
+					   ext4_end_io_dio, NULL, dio_flags);
 
 	/*
 	 * Put our reference to io_end. This can free the io_end structure e.g.
@@ -3180,19 +3205,12 @@ void ext4_set_aops(struct inode *inode)
 		inode->i_mapping->a_ops = &ext4_aops;
 }
 
-/*
- * ext4_block_zero_page_range() zeros out a mapping of length 'length'
- * starting from file offset 'from'.  The range to be zero'd must
- * be contained with in one block.  If the specified range exceeds
- * the end of the block it will be shortened to end of the block
- * that cooresponds to 'from'
- */
-static int ext4_block_zero_page_range(handle_t *handle,
+static int __ext4_block_zero_page_range(handle_t *handle,
 		struct address_space *mapping, loff_t from, loff_t length)
 {
 	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned blocksize, max, pos;
+	unsigned blocksize, pos;
 	ext4_lblk_t iblock;
 	struct inode *inode = mapping->host;
 	struct buffer_head *bh;
@@ -3205,14 +3223,6 @@ static int ext4_block_zero_page_range(handle_t *handle,
 		return -ENOMEM;
 
 	blocksize = inode->i_sb->s_blocksize;
-	max = blocksize - (offset & (blocksize - 1));
-
-	/*
-	 * correct length if it does not fall between
-	 * 'from' and the end of the block
-	 */
-	if (length > max || length < 0)
-		length = max;
 
 	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
 
@@ -3278,6 +3288,33 @@ unlock:
 }
 
 /*
+ * ext4_block_zero_page_range() zeros out a mapping of length 'length'
+ * starting from file offset 'from'.  The range to be zero'd must
+ * be contained with in one block.  If the specified range exceeds
+ * the end of the block it will be shortened to end of the block
+ * that cooresponds to 'from'
+ */
+static int ext4_block_zero_page_range(handle_t *handle,
+		struct address_space *mapping, loff_t from, loff_t length)
+{
+	struct inode *inode = mapping->host;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned blocksize = inode->i_sb->s_blocksize;
+	unsigned max = blocksize - (offset & (blocksize - 1));
+
+	/*
+	 * correct length if it does not fall between
+	 * 'from' and the end of the block
+	 */
+	if (length > max || length < 0)
+		length = max;
+
+	if (IS_DAX(inode))
+		return dax_zero_page_range(inode, from, length, ext4_get_block);
+	return __ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
+/*
  * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
  * up to the end of the block which corresponds to `from'.
  * This required during truncate. We need to physically zero the tail end
@@ -3798,8 +3835,10 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
+	if (test_opt(inode->i_sb, DAX))
+		new_fl |= S_DAX;
 	inode_set_flags(inode, new_fl,
-			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
@@ -4052,7 +4091,10 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 	} else if (S_ISDIR(inode->i_mode)) {
 		inode->i_op = &ext4_dir_inode_operations;
@@ -4139,6 +4181,65 @@ static int ext4_inode_blocks_set(handle_t *handle,
 	return 0;
 }
 
+struct other_inode {
+	unsigned long		orig_ino;
+	struct ext4_inode	*raw_inode;
+};
+
+static int other_inode_match(struct inode * inode, unsigned long ino,
+			     void *data)
+{
+	struct other_inode *oi = (struct other_inode *) data;
+
+	if ((inode->i_ino != ino) ||
+	    (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
+			       I_DIRTY_SYNC | I_DIRTY_DATASYNC)) ||
+	    ((inode->i_state & I_DIRTY_TIME) == 0))
+		return 0;
+	spin_lock(&inode->i_lock);
+	if (((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
+				I_DIRTY_SYNC | I_DIRTY_DATASYNC)) == 0) &&
+	    (inode->i_state & I_DIRTY_TIME)) {
+		struct ext4_inode_info	*ei = EXT4_I(inode);
+
+		inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
+		spin_unlock(&inode->i_lock);
+
+		spin_lock(&ei->i_raw_lock);
+		EXT4_INODE_SET_XTIME(i_ctime, inode, oi->raw_inode);
+		EXT4_INODE_SET_XTIME(i_mtime, inode, oi->raw_inode);
+		EXT4_INODE_SET_XTIME(i_atime, inode, oi->raw_inode);
+		ext4_inode_csum_set(inode, oi->raw_inode, ei);
+		spin_unlock(&ei->i_raw_lock);
+		trace_ext4_other_inode_update_time(inode, oi->orig_ino);
+		return -1;
+	}
+	spin_unlock(&inode->i_lock);
+	return -1;
+}
+
+/*
+ * Opportunistically update the other time fields for other inodes in
+ * the same inode table block.
+ */
+static void ext4_update_other_inodes_time(struct super_block *sb,
+					  unsigned long orig_ino, char *buf)
+{
+	struct other_inode oi;
+	unsigned long ino;
+	int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
+	int inode_size = EXT4_INODE_SIZE(sb);
+
+	oi.orig_ino = orig_ino;
+	ino = orig_ino & ~(inodes_per_block - 1);
+	for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
+		if (ino == orig_ino)
+			continue;
+		oi.raw_inode = (struct ext4_inode *) buf;
+		(void) find_inode_nowait(sb, ino, other_inode_match, &oi);
+	}
+}
+
 /*
  * Post the struct inode info into an on-disk inode location in the
  * buffer-cache.  This gobbles the caller's reference to the
@@ -4248,10 +4349,11 @@ static int ext4_do_update_inode(handle_t *handle,
 				cpu_to_le16(ei->i_extra_isize);
 		}
 	}
-
 	ext4_inode_csum_set(inode, raw_inode, ei);
-
 	spin_unlock(&ei->i_raw_lock);
+	if (inode->i_sb->s_flags & MS_LAZYTIME)
+		ext4_update_other_inodes_time(inode->i_sb, inode->i_ino,
+					      bh->b_data);
 
 	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
 	rc = ext4_handle_dirty_metadata(handle, NULL, bh);
@@ -4534,7 +4636,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
 		 */
-			truncate_pagecache(inode, inode->i_size);
+		truncate_pagecache(inode, inode->i_size);
 	}
 	/*
 	 * We want to call ext4_truncate() even if attr->ia_size ==
@@ -4840,11 +4942,17 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
  * If the inode is marked synchronous, we don't honour that here - doing
  * so would cause a commit on atime updates, which we don't bother doing.
  * We handle synchronous inodes at the highest possible level.
+ *
+ * If only the I_DIRTY_TIME flag is set, we can skip everything.  If
+ * I_DIRTY_TIME and I_DIRTY_SYNC is set, the only inode fields we need
+ * to copy into the on-disk inode structure are the timestamp files.
  */
 void ext4_dirty_inode(struct inode *inode, int flags)
 {
 	handle_t *handle;
 
+	if (flags == I_DIRTY_TIME)
+		return;
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
 	if (IS_ERR(handle))
 		goto out;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 2291923dae4e..28fe71a2904c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2235,7 +2235,10 @@ retry:
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 		err = ext4_add_nondir(handle, dentry, inode);
 		if (!err && IS_DIRSYNC(dir))
@@ -2299,7 +2302,10 @@ retry:
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 		d_tmpfile(dentry, inode);
 		err = ext4_orphan_add(handle, inode);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 74c5f53595fb..e061e66c8280 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -334,7 +334,7 @@ static void save_error_info(struct super_block *sb, const char *func,
 static int block_device_ejected(struct super_block *sb)
 {
 	struct inode *bd_inode = sb->s_bdev->bd_inode;
-	struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(bd_inode);
 
 	return bdi->dev == NULL;
 }
@@ -1046,10 +1046,7 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot);
 static int ext4_write_info(struct super_block *sb, int type);
 static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 			 struct path *path);
-static int ext4_quota_on_sysfile(struct super_block *sb, int type,
-				 int format_id);
 static int ext4_quota_off(struct super_block *sb, int type);
-static int ext4_quota_off_sysfile(struct super_block *sb, int type);
 static int ext4_quota_on_mount(struct super_block *sb, int type);
 static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
 			       size_t len, loff_t off);
@@ -1084,16 +1081,6 @@ static const struct quotactl_ops ext4_qctl_operations = {
 	.get_dqblk	= dquot_get_dqblk,
 	.set_dqblk	= dquot_set_dqblk
 };
-
-static const struct quotactl_ops ext4_qctl_sysfile_operations = {
-	.quota_on_meta	= ext4_quota_on_sysfile,
-	.quota_off	= ext4_quota_off_sysfile,
-	.quota_sync	= dquot_quota_sync,
-	.get_info	= dquot_get_dqinfo,
-	.set_info	= dquot_set_dqinfo,
-	.get_dqblk	= dquot_get_dqblk,
-	.set_dqblk	= dquot_set_dqblk
-};
 #endif
 
 static const struct super_operations ext4_sops = {
@@ -1137,8 +1124,9 @@ enum {
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
-	Opt_usrquota, Opt_grpquota, Opt_i_version,
+	Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_dax,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+	Opt_lazytime, Opt_nolazytime,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
 	Opt_dioread_nolock, Opt_dioread_lock,
@@ -1200,8 +1188,11 @@ static const match_table_t tokens = {
 	{Opt_barrier, "barrier"},
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_i_version, "i_version"},
+	{Opt_dax, "dax"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
+	{Opt_lazytime, "lazytime"},
+	{Opt_nolazytime, "nolazytime"},
 	{Opt_nodelalloc, "nodelalloc"},
 	{Opt_removed, "mblk_io_submit"},
 	{Opt_removed, "nomblk_io_submit"},
@@ -1384,6 +1375,7 @@ static const struct mount_opts {
 	{Opt_min_batch_time, 0, MOPT_GTE0},
 	{Opt_inode_readahead_blks, 0, MOPT_GTE0},
 	{Opt_init_itable, 0, MOPT_GTE0},
+	{Opt_dax, EXT4_MOUNT_DAX, MOPT_SET},
 	{Opt_stripe, 0, MOPT_GTE0},
 	{Opt_resuid, 0, MOPT_GTE0},
 	{Opt_resgid, 0, MOPT_GTE0},
@@ -1459,6 +1451,12 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 	case Opt_i_version:
 		sb->s_flags |= MS_I_VERSION;
 		return 1;
+	case Opt_lazytime:
+		sb->s_flags |= MS_LAZYTIME;
+		return 1;
+	case Opt_nolazytime:
+		sb->s_flags &= ~MS_LAZYTIME;
+		return 1;
 	}
 
 	for (m = ext4_mount_opts; m->token != Opt_err; m++)
@@ -1620,6 +1618,11 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		}
 		sbi->s_jquota_fmt = m->mount_opt;
 #endif
+#ifndef CONFIG_FS_DAX
+	} else if (token == Opt_dax) {
+		ext4_msg(sb, KERN_INFO, "dax option not supported");
+		return -1;
+#endif
 	} else {
 		if (!args->from)
 			arg = 1;
@@ -2776,6 +2779,12 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
 	if (readonly)
 		return 1;
 
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_READONLY)) {
+		ext4_msg(sb, KERN_INFO, "filesystem is read-only");
+		sb->s_flags |= MS_RDONLY;
+		return 1;
+	}
+
 	/* Check that feature set is OK for a read-write mount */
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP)) {
 		ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of "
@@ -3602,6 +3611,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "both data=journal and dioread_nolock");
 			goto failed_mount;
 		}
+		if (test_opt(sb, DAX)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "both data=journal and dax");
+			goto failed_mount;
+		}
 		if (test_opt(sb, DELALLOC))
 			clear_opt(sb, DELALLOC);
 	}
@@ -3665,6 +3679,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
+	if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
+		if (blocksize != PAGE_SIZE) {
+			ext4_msg(sb, KERN_ERR,
+					"error: unsupported blocksize for dax");
+			goto failed_mount;
+		}
+		if (!sb->s_bdev->bd_disk->fops->direct_access) {
+			ext4_msg(sb, KERN_ERR,
+					"error: device does not support dax");
+			goto failed_mount;
+		}
+	}
+
 	if (sb->s_blocksize != blocksize) {
 		/* Validate the filesystem blocksize */
 		if (!sb_set_blocksize(sb, blocksize)) {
@@ -3915,9 +3942,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 	spin_lock_init(&sbi->s_next_gen_lock);
 
-	init_timer(&sbi->s_err_report);
-	sbi->s_err_report.function = print_daily_error_info;
-	sbi->s_err_report.data = (unsigned long) sb;
+	setup_timer(&sbi->s_err_report, print_daily_error_info,
+		(unsigned long) sb);
 
 	/* Register extent status tree shrinker */
 	if (ext4_es_register_shrinker(sbi))
@@ -3935,7 +3961,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #ifdef CONFIG_QUOTA
 	sb->dq_op = &ext4_quota_operations;
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA))
-		sb->s_qcop = &ext4_qctl_sysfile_operations;
+		sb->s_qcop = &dquot_quotactl_sysfile_ops;
 	else
 		sb->s_qcop = &ext4_qctl_operations;
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
@@ -4845,9 +4871,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	if (sbi->s_journal && sbi->s_journal->j_task->io_context)
 		journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
 
-	/*
-	 * Allow the "check" option to be passed as a remount option.
-	 */
 	if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) {
 		err = -EINVAL;
 		goto restore_opts;
@@ -4856,17 +4879,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
 	    test_opt(sb, JOURNAL_CHECKSUM)) {
 		ext4_msg(sb, KERN_ERR, "changing journal_checksum "
-			 "during remount not supported");
-		err = -EINVAL;
-		goto restore_opts;
-	}
-
-	if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
-	    test_opt(sb, JOURNAL_CHECKSUM)) {
-		ext4_msg(sb, KERN_ERR, "changing journal_checksum "
-			 "during remount not supported");
-		err = -EINVAL;
-		goto restore_opts;
+			 "during remount not supported; ignoring");
+		sbi->s_mount_opt ^= EXT4_MOUNT_JOURNAL_CHECKSUM;
 	}
 
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
@@ -4882,6 +4896,18 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			err = -EINVAL;
 			goto restore_opts;
 		}
+		if (test_opt(sb, DAX)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "both data=journal and dax");
+			err = -EINVAL;
+			goto restore_opts;
+		}
+	}
+
+	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
+		ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
+			"dax flag with busy inodes while remounting");
+		sbi->s_mount_opt ^= EXT4_MOUNT_DAX;
 	}
 
 	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
@@ -4930,7 +4956,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 				ext4_mark_recovery_complete(sb, es);
 		} else {
 			/* Make sure we can mount this feature set readwrite */
-			if (!ext4_feature_set_ok(sb, 0)) {
+			if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+					EXT4_FEATURE_RO_COMPAT_READONLY) ||
+			    !ext4_feature_set_ok(sb, 0)) {
 				err = -EROFS;
 				goto restore_opts;
 			}
@@ -5020,6 +5048,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	}
 #endif
 
+	*flags = (*flags & ~MS_LAZYTIME) | (sb->s_flags & MS_LAZYTIME);
 	ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
 	kfree(orig_data);
 	return 0;
@@ -5288,21 +5317,6 @@ static int ext4_enable_quotas(struct super_block *sb)
 	return 0;
 }
 
-/*
- * quota_on function that is used when QUOTA feature is set.
- */
-static int ext4_quota_on_sysfile(struct super_block *sb, int type,
-				 int format_id)
-{
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA))
-		return -EINVAL;
-
-	/*
-	 * USAGE was enabled at mount time. Only need to enable LIMITS now.
-	 */
-	return ext4_quota_enable(sb, type, format_id, DQUOT_LIMITS_ENABLED);
-}
-
 static int ext4_quota_off(struct super_block *sb, int type)
 {
 	struct inode *inode = sb_dqopt(sb)->files[type];
@@ -5329,18 +5343,6 @@ out:
 	return dquot_quota_off(sb, type);
 }
 
-/*
- * quota_off function that is used when QUOTA feature is set.
- */
-static int ext4_quota_off_sysfile(struct super_block *sb, int type)
-{
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA))
-		return -EINVAL;
-
-	/* Disable only the limits. */
-	return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED);
-}
-
 /* Read data from quotafile - avoid pagecache and such because we cannot afford
  * acquiring the locks... As quota files are never truncated and quota code
  * itself serializes the operations (and no one else should touch the files)
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 736a348509f7..94e2d2ffabe1 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -71,3 +71,13 @@ config F2FS_CHECK_FS
 	  Enables BUG_ONs which check the filesystem consistency in runtime.
 
 	  If you want to improve the performance, say N.
+
+config F2FS_IO_TRACE
+	bool "F2FS IO tracer"
+	depends on F2FS_FS
+	depends on FUNCTION_TRACER
+	help
+	  F2FS IO trace is based on a function trace, which gathers process
+	  information and block IO patterns in the filesystem level.
+
+	  If unsure, say N.
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index 2e35da12d292..d92397731db8 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -5,3 +5,4 @@ f2fs-y		+= checkpoint.o gc.o data.o node.o segment.o recovery.o
 f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
 f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
 f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
+f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 1ccb26bc2a0b..742202779bd5 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -62,7 +62,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
 	if (count == 0)
 		return NULL;
 
-	acl = posix_acl_alloc(count, GFP_KERNEL);
+	acl = posix_acl_alloc(count, GFP_NOFS);
 	if (!acl)
 		return ERR_PTR(-ENOMEM);
 
@@ -116,7 +116,7 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
 	int i;
 
 	f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
-			sizeof(struct f2fs_acl_entry), GFP_KERNEL);
+			sizeof(struct f2fs_acl_entry), GFP_NOFS);
 	if (!f2fs_acl)
 		return ERR_PTR(-ENOMEM);
 
@@ -396,7 +396,7 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
 		posix_acl_release(default_acl);
 	}
 	if (acl) {
-		if (error)
+		if (!error)
 			error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl,
 					       ipage);
 		posix_acl_release(acl);
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index e6c271fefaca..7f794b72b3b7 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -20,10 +20,11 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 static struct kmem_cache *ino_entry_slab;
-static struct kmem_cache *inode_entry_slab;
+struct kmem_cache *inode_entry_slab;
 
 /*
  * We guarantee no failure on the returned page.
@@ -50,6 +51,11 @@ struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 {
 	struct address_space *mapping = META_MAPPING(sbi);
 	struct page *page;
+	struct f2fs_io_info fio = {
+		.type = META,
+		.rw = READ_SYNC | REQ_META | REQ_PRIO,
+		.blk_addr = index,
+	};
 repeat:
 	page = grab_cache_page(mapping, index);
 	if (!page) {
@@ -59,8 +65,7 @@ repeat:
 	if (PageUptodate(page))
 		goto out;
 
-	if (f2fs_submit_page_bio(sbi, page, index,
-				READ_SYNC | REQ_META | REQ_PRIO))
+	if (f2fs_submit_page_bio(sbi, page, &fio))
 		goto repeat;
 
 	lock_page(page);
@@ -112,14 +117,12 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 	block_t prev_blk_addr = 0;
 	struct page *page;
 	block_t blkno = start;
-
 	struct f2fs_io_info fio = {
 		.type = META,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO
 	};
 
 	for (; nrpages-- > 0; blkno++) {
-		block_t blk_addr;
 
 		if (!is_valid_blkaddr(sbi, blkno, type))
 			goto out;
@@ -130,27 +133,27 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 					NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
 				blkno = 0;
 			/* get nat block addr */
-			blk_addr = current_nat_addr(sbi,
+			fio.blk_addr = current_nat_addr(sbi,
 					blkno * NAT_ENTRY_PER_BLOCK);
 			break;
 		case META_SIT:
 			/* get sit block addr */
-			blk_addr = current_sit_addr(sbi,
+			fio.blk_addr = current_sit_addr(sbi,
 					blkno * SIT_ENTRY_PER_BLOCK);
-			if (blkno != start && prev_blk_addr + 1 != blk_addr)
+			if (blkno != start && prev_blk_addr + 1 != fio.blk_addr)
 				goto out;
-			prev_blk_addr = blk_addr;
+			prev_blk_addr = fio.blk_addr;
 			break;
 		case META_SSA:
 		case META_CP:
 		case META_POR:
-			blk_addr = blkno;
+			fio.blk_addr = blkno;
 			break;
 		default:
 			BUG();
 		}
 
-		page = grab_cache_page(META_MAPPING(sbi), blk_addr);
+		page = grab_cache_page(META_MAPPING(sbi), fio.blk_addr);
 		if (!page)
 			continue;
 		if (PageUptodate(page)) {
@@ -158,7 +161,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 			continue;
 		}
 
-		f2fs_submit_page_mbio(sbi, page, blk_addr, &fio);
+		f2fs_submit_page_mbio(sbi, page, &fio);
 		f2fs_put_page(page, 0);
 	}
 out:
@@ -187,7 +190,7 @@ static int f2fs_write_meta_page(struct page *page,
 
 	trace_f2fs_writepage(page, META);
 
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 	if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
 		goto redirty_out;
@@ -299,6 +302,8 @@ static int f2fs_set_meta_page_dirty(struct page *page)
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
+		SetPagePrivate(page);
+		f2fs_trace_pid(page);
 		return 1;
 	}
 	return 0;
@@ -308,6 +313,8 @@ const struct address_space_operations f2fs_meta_aops = {
 	.writepage	= f2fs_write_meta_page,
 	.writepages	= f2fs_write_meta_pages,
 	.set_page_dirty	= f2fs_set_meta_page_dirty,
+	.invalidatepage = f2fs_invalidate_page,
+	.releasepage	= f2fs_release_page,
 };
 
 static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
@@ -462,7 +469,7 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
 		return;
 
-	sbi->por_doing = true;
+	set_sbi_flag(sbi, SBI_POR_DOING);
 
 	start_blk = __start_cp_addr(sbi) + 1 +
 		le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
@@ -483,7 +490,7 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	}
 	/* clear Orphan Flag */
 	clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
-	sbi->por_doing = false;
+	clear_sbi_flag(sbi, SBI_POR_DOING);
 	return;
 }
 
@@ -567,7 +574,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	if (crc_offset >= blk_size)
 		goto invalid_cp1;
 
-	crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
+	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
 	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
 		goto invalid_cp1;
 
@@ -582,7 +589,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	if (crc_offset >= blk_size)
 		goto invalid_cp2;
 
-	crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
+	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
 	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
 		goto invalid_cp2;
 
@@ -669,7 +676,7 @@ fail_no_cp:
 	return -EINVAL;
 }
 
-static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
+static int __add_dirty_inode(struct inode *inode, struct inode_entry *new)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
@@ -686,7 +693,7 @@ static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
 void update_dirty_page(struct inode *inode, struct page *page)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dir_inode_entry *new;
+	struct inode_entry *new;
 	int ret = 0;
 
 	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
@@ -710,12 +717,13 @@ void update_dirty_page(struct inode *inode, struct page *page)
 		kmem_cache_free(inode_entry_slab, new);
 out:
 	SetPagePrivate(page);
+	f2fs_trace_pid(page);
 }
 
 void add_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dir_inode_entry *new =
+	struct inode_entry *new =
 			f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
 	int ret = 0;
 
@@ -733,7 +741,7 @@ void add_dirty_dir_inode(struct inode *inode)
 void remove_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dir_inode_entry *entry;
+	struct inode_entry *entry;
 
 	if (!S_ISDIR(inode->i_mode))
 		return;
@@ -763,7 +771,7 @@ void remove_dirty_dir_inode(struct inode *inode)
 void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
 {
 	struct list_head *head;
-	struct dir_inode_entry *entry;
+	struct inode_entry *entry;
 	struct inode *inode;
 retry:
 	if (unlikely(f2fs_cp_error(sbi)))
@@ -776,7 +784,7 @@ retry:
 		spin_unlock(&sbi->dir_inode_lock);
 		return;
 	}
-	entry = list_entry(head->next, struct dir_inode_entry, list);
+	entry = list_entry(head->next, struct inode_entry, list);
 	inode = igrab(entry->inode);
 	spin_unlock(&sbi->dir_inode_lock);
 	if (inode) {
@@ -922,7 +930,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	ckpt->next_free_nid = cpu_to_le32(last_nid);
 
 	/* 2 cp  + n data seg summary + orphan inode blocks */
-	data_sum_blocks = npages_for_summary_flush(sbi);
+	data_sum_blocks = npages_for_summary_flush(sbi, false);
 	if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
 		set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
 	else
@@ -932,24 +940,31 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
 			orphan_blocks);
 
-	if (cpc->reason == CP_UMOUNT) {
-		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+	if (__remain_node_summaries(cpc->reason))
 		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
 				cp_payload_blks + data_sum_blocks +
 				orphan_blocks + NR_CURSEG_NODE_TYPE);
-	} else {
-		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+	else
 		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
 				cp_payload_blks + data_sum_blocks +
 				orphan_blocks);
-	}
+
+	if (cpc->reason == CP_UMOUNT)
+		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+	else
+		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+
+	if (cpc->reason == CP_FASTBOOT)
+		set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
+	else
+		clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
 
 	if (orphan_num)
 		set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 	else
 		clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 
-	if (sbi->need_fsck)
+	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
 		set_ckpt_flags(ckpt, CP_FSCK_FLAG);
 
 	/* update SIT/NAT bitmap */
@@ -966,15 +981,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* write out checkpoint buffer at block 0 */
 	cp_page = grab_meta_page(sbi, start_blk++);
 	kaddr = page_address(cp_page);
-	memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
+	memcpy(kaddr, ckpt, F2FS_BLKSIZE);
 	set_page_dirty(cp_page);
 	f2fs_put_page(cp_page, 1);
 
 	for (i = 1; i < 1 + cp_payload_blks; i++) {
 		cp_page = grab_meta_page(sbi, start_blk++);
 		kaddr = page_address(cp_page);
-		memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE,
-				(1 << sbi->log_blocksize));
+		memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE, F2FS_BLKSIZE);
 		set_page_dirty(cp_page);
 		f2fs_put_page(cp_page, 1);
 	}
@@ -986,7 +1000,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	write_data_summaries(sbi, start_blk);
 	start_blk += data_sum_blocks;
-	if (cpc->reason == CP_UMOUNT) {
+	if (__remain_node_summaries(cpc->reason)) {
 		write_node_summaries(sbi, start_blk);
 		start_blk += NR_CURSEG_NODE_TYPE;
 	}
@@ -994,7 +1008,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* writeout checkpoint block */
 	cp_page = grab_meta_page(sbi, start_blk);
 	kaddr = page_address(cp_page);
-	memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
+	memcpy(kaddr, ckpt, F2FS_BLKSIZE);
 	set_page_dirty(cp_page);
 	f2fs_put_page(cp_page, 1);
 
@@ -1023,7 +1037,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		return;
 
 	clear_prefree_segments(sbi);
-	F2FS_RESET_SB_DIRT(sbi);
+	clear_sbi_flag(sbi, SBI_IS_DIRTY);
 }
 
 /*
@@ -1038,10 +1052,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	mutex_lock(&sbi->cp_mutex);
 
-	if (!sbi->s_dirty && cpc->reason != CP_DISCARD)
+	if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
+			cpc->reason != CP_DISCARD && cpc->reason != CP_UMOUNT)
 		goto out;
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto out;
+	if (f2fs_readonly(sbi->sb))
+		goto out;
 	if (block_operations(sbi))
 		goto out;
 
@@ -1102,8 +1119,8 @@ int __init create_checkpoint_caches(void)
 			sizeof(struct ino_entry));
 	if (!ino_entry_slab)
 		return -ENOMEM;
-	inode_entry_slab = f2fs_kmem_cache_create("f2fs_dirty_dir_entry",
-			sizeof(struct dir_inode_entry));
+	inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
+			sizeof(struct inode_entry));
 	if (!inode_entry_slab) {
 		kmem_cache_destroy(ino_entry_slab);
 		return -ENOMEM;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 7ec697b37f19..985ed023a750 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -22,6 +22,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 static void f2fs_read_end_io(struct bio *bio, int err)
@@ -95,11 +96,9 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 		return;
 
 	if (is_read_io(fio->rw))
-		trace_f2fs_submit_read_bio(io->sbi->sb, fio->rw,
-							fio->type, io->bio);
+		trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio);
 	else
-		trace_f2fs_submit_write_bio(io->sbi->sb, fio->rw,
-							fio->type, io->bio);
+		trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
 
 	submit_bio(fio->rw, io->bio);
 	io->bio = NULL;
@@ -132,14 +131,15 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
  * Return unlocked page.
  */
 int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
-					block_t blk_addr, int rw)
+					struct f2fs_io_info *fio)
 {
 	struct bio *bio;
 
-	trace_f2fs_submit_page_bio(page, blk_addr, rw);
+	trace_f2fs_submit_page_bio(page, fio);
+	f2fs_trace_ios(page, fio, 0);
 
 	/* Allocate a new bio */
-	bio = __bio_alloc(sbi, blk_addr, 1, is_read_io(rw));
+	bio = __bio_alloc(sbi, fio->blk_addr, 1, is_read_io(fio->rw));
 
 	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
 		bio_put(bio);
@@ -147,12 +147,12 @@ int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
 		return -EFAULT;
 	}
 
-	submit_bio(rw, bio);
+	submit_bio(fio->rw, bio);
 	return 0;
 }
 
 void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
-			block_t blk_addr, struct f2fs_io_info *fio)
+					struct f2fs_io_info *fio)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
 	struct f2fs_bio_info *io;
@@ -160,21 +160,21 @@ void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
 
 	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
 
-	verify_block_addr(sbi, blk_addr);
+	verify_block_addr(sbi, fio->blk_addr);
 
 	down_write(&io->io_rwsem);
 
 	if (!is_read)
 		inc_page_count(sbi, F2FS_WRITEBACK);
 
-	if (io->bio && (io->last_block_in_bio != blk_addr - 1 ||
+	if (io->bio && (io->last_block_in_bio != fio->blk_addr - 1 ||
 						io->fio.rw != fio->rw))
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
 		int bio_blocks = MAX_BIO_BLOCKS(sbi);
 
-		io->bio = __bio_alloc(sbi, blk_addr, bio_blocks, is_read);
+		io->bio = __bio_alloc(sbi, fio->blk_addr, bio_blocks, is_read);
 		io->fio = *fio;
 	}
 
@@ -184,10 +184,11 @@ alloc_new:
 		goto alloc_new;
 	}
 
-	io->last_block_in_bio = blk_addr;
+	io->last_block_in_bio = fio->blk_addr;
+	f2fs_trace_ios(page, fio, 0);
 
 	up_write(&io->io_rwsem);
-	trace_f2fs_submit_page_mbio(page, fio->rw, fio->type, blk_addr);
+	trace_f2fs_submit_page_mbio(page, fio);
 }
 
 /*
@@ -196,7 +197,7 @@ alloc_new:
  *  ->node_page
  *    update block addresses in the node page
  */
-static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
+static void __set_data_blkaddr(struct dnode_of_data *dn)
 {
 	struct f2fs_node *rn;
 	__le32 *addr_array;
@@ -209,7 +210,7 @@ static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
 
 	/* Get physical address of data block */
 	addr_array = blkaddr_in_node(rn);
-	addr_array[ofs_in_node] = cpu_to_le32(new_addr);
+	addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
 	set_page_dirty(node_page);
 }
 
@@ -224,8 +225,8 @@ int reserve_new_block(struct dnode_of_data *dn)
 
 	trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
 
-	__set_data_blkaddr(dn, NEW_ADDR);
 	dn->data_blkaddr = NEW_ADDR;
+	__set_data_blkaddr(dn);
 	mark_inode_dirty(dn->inode);
 	sync_inode_page(dn);
 	return 0;
@@ -273,7 +274,7 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 		unsigned int blkbits = inode->i_sb->s_blocksize_bits;
 		size_t count;
 
-		clear_buffer_new(bh_result);
+		set_buffer_new(bh_result);
 		map_bh(bh_result, inode->i_sb,
 				start_blkaddr + pgofs - start_fofs);
 		count = end_fofs - pgofs + 1;
@@ -290,23 +291,24 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 	return 0;
 }
 
-void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
+void update_extent_cache(struct dnode_of_data *dn)
 {
 	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	pgoff_t fofs, start_fofs, end_fofs;
 	block_t start_blkaddr, end_blkaddr;
 	int need_update = true;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), blk_addr == NEW_ADDR);
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
-							dn->ofs_in_node;
+	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
 
 	/* Update the page address in the parent node */
-	__set_data_blkaddr(dn, blk_addr);
+	__set_data_blkaddr(dn);
 
 	if (is_inode_flag_set(fi, FI_NO_EXTENT))
 		return;
 
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+							dn->ofs_in_node;
+
 	write_lock(&fi->ext.ext_lock);
 
 	start_fofs = fi->ext.fofs;
@@ -320,16 +322,16 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
 
 	/* Initial extent */
 	if (fi->ext.len == 0) {
-		if (blk_addr != NULL_ADDR) {
+		if (dn->data_blkaddr != NULL_ADDR) {
 			fi->ext.fofs = fofs;
-			fi->ext.blk_addr = blk_addr;
+			fi->ext.blk_addr = dn->data_blkaddr;
 			fi->ext.len = 1;
 		}
 		goto end_update;
 	}
 
 	/* Front merge */
-	if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) {
+	if (fofs == start_fofs - 1 && dn->data_blkaddr == start_blkaddr - 1) {
 		fi->ext.fofs--;
 		fi->ext.blk_addr--;
 		fi->ext.len++;
@@ -337,7 +339,7 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
 	}
 
 	/* Back merge */
-	if (fofs == end_fofs + 1 && blk_addr == end_blkaddr + 1) {
+	if (fofs == end_fofs + 1 && dn->data_blkaddr == end_blkaddr + 1) {
 		fi->ext.len++;
 		goto end_update;
 	}
@@ -376,6 +378,10 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 	struct dnode_of_data dn;
 	struct page *page;
 	int err;
+	struct f2fs_io_info fio = {
+		.type = DATA,
+		.rw = sync ? READ_SYNC : READA,
+	};
 
 	page = find_get_page(mapping, index);
 	if (page && PageUptodate(page))
@@ -404,8 +410,8 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 		return page;
 	}
 
-	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, dn.data_blkaddr,
-					sync ? READ_SYNC : READA);
+	fio.blk_addr = dn.data_blkaddr;
+	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
 	if (err)
 		return ERR_PTR(err);
 
@@ -430,7 +436,10 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	struct dnode_of_data dn;
 	struct page *page;
 	int err;
-
+	struct f2fs_io_info fio = {
+		.type = DATA,
+		.rw = READ_SYNC,
+	};
 repeat:
 	page = grab_cache_page(mapping, index);
 	if (!page)
@@ -464,8 +473,8 @@ repeat:
 		return page;
 	}
 
-	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
-					dn.data_blkaddr, READ_SYNC);
+	fio.blk_addr = dn.data_blkaddr;
+	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
 	if (err)
 		return ERR_PTR(err);
 
@@ -515,8 +524,12 @@ repeat:
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 		SetPageUptodate(page);
 	} else {
-		err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
-						dn.data_blkaddr, READ_SYNC);
+		struct f2fs_io_info fio = {
+			.type = DATA,
+			.rw = READ_SYNC,
+			.blk_addr = dn.data_blkaddr,
+		};
+		err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
 		if (err)
 			goto put_err;
 
@@ -550,30 +563,25 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	struct f2fs_summary sum;
-	block_t new_blkaddr;
 	struct node_info ni;
+	int seg = CURSEG_WARM_DATA;
 	pgoff_t fofs;
-	int type;
 
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return -EPERM;
 	if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
 		return -ENOSPC;
 
-	__set_data_blkaddr(dn, NEW_ADDR);
-	dn->data_blkaddr = NEW_ADDR;
-
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
-	type = CURSEG_WARM_DATA;
+	if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page)
+		seg = CURSEG_DIRECT_IO;
 
-	allocate_data_block(sbi, NULL, NULL_ADDR, &new_blkaddr, &sum, type);
+	allocate_data_block(sbi, NULL, NULL_ADDR, &dn->data_blkaddr, &sum, seg);
 
 	/* direct IO doesn't use extent cache to maximize the performance */
-	set_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
-	update_extent_cache(new_blkaddr, dn);
-	clear_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
+	__set_data_blkaddr(dn);
 
 	/* update i_size */
 	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
@@ -581,10 +589,59 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT))
 		i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT));
 
-	dn->data_blkaddr = new_blkaddr;
 	return 0;
 }
 
+static void __allocate_data_blocks(struct inode *inode, loff_t offset,
+							size_t count)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct dnode_of_data dn;
+	u64 start = F2FS_BYTES_TO_BLK(offset);
+	u64 len = F2FS_BYTES_TO_BLK(count);
+	bool allocated;
+	u64 end_offset;
+
+	while (len) {
+		f2fs_balance_fs(sbi);
+		f2fs_lock_op(sbi);
+
+		/* When reading holes, we need its node page */
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		if (get_dnode_of_data(&dn, start, ALLOC_NODE))
+			goto out;
+
+		allocated = false;
+		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+
+		while (dn.ofs_in_node < end_offset && len) {
+			if (dn.data_blkaddr == NULL_ADDR) {
+				if (__allocate_data_block(&dn))
+					goto sync_out;
+				allocated = true;
+			}
+			len--;
+			start++;
+			dn.ofs_in_node++;
+		}
+
+		if (allocated)
+			sync_inode_page(&dn);
+
+		f2fs_put_dnode(&dn);
+		f2fs_unlock_op(sbi);
+	}
+	return;
+
+sync_out:
+	if (allocated)
+		sync_inode_page(&dn);
+	f2fs_put_dnode(&dn);
+out:
+	f2fs_unlock_op(sbi);
+	return;
+}
+
 /*
  * get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh.
  * If original data blocks are allocated, then give them to blockdev.
@@ -610,10 +667,8 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 	if (check_extent_cache(inode, pgofs, bh_result))
 		goto out;
 
-	if (create) {
-		f2fs_balance_fs(F2FS_I_SB(inode));
+	if (create)
 		f2fs_lock_op(F2FS_I_SB(inode));
-	}
 
 	/* When reading holes, we need its node page */
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -627,12 +682,14 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 		goto put_out;
 
 	if (dn.data_blkaddr != NULL_ADDR) {
+		set_buffer_new(bh_result);
 		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
 	} else if (create) {
 		err = __allocate_data_block(&dn);
 		if (err)
 			goto put_out;
 		allocated = true;
+		set_buffer_new(bh_result);
 		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
 	} else {
 		goto put_out;
@@ -745,7 +802,6 @@ static int f2fs_read_data_pages(struct file *file,
 int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 {
 	struct inode *inode = page->mapping->host;
-	block_t old_blkaddr, new_blkaddr;
 	struct dnode_of_data dn;
 	int err = 0;
 
@@ -754,10 +810,10 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 	if (err)
 		return err;
 
-	old_blkaddr = dn.data_blkaddr;
+	fio->blk_addr = dn.data_blkaddr;
 
 	/* This page is already truncated */
-	if (old_blkaddr == NULL_ADDR)
+	if (fio->blk_addr == NULL_ADDR)
 		goto out_writepage;
 
 	set_page_writeback(page);
@@ -766,14 +822,14 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 	 * If current allocation needs SSR,
 	 * it had better in-place writes for updated data.
 	 */
-	if (unlikely(old_blkaddr != NEW_ADDR &&
+	if (unlikely(fio->blk_addr != NEW_ADDR &&
 			!is_cold_data(page) &&
 			need_inplace_update(inode))) {
-		rewrite_data_page(page, old_blkaddr, fio);
+		rewrite_data_page(page, fio);
 		set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
 	} else {
-		write_data_page(page, &dn, &new_blkaddr, fio);
-		update_extent_cache(new_blkaddr, &dn);
+		write_data_page(page, &dn, fio);
+		update_extent_cache(&dn);
 		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 	}
 out_writepage:
@@ -812,7 +868,12 @@ static int f2fs_write_data_page(struct page *page,
 
 	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
 write:
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto redirty_out;
+	if (f2fs_is_drop_cache(inode))
+		goto out;
+	if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim &&
+			available_free_memory(sbi, BASE_CHECK))
 		goto redirty_out;
 
 	/* Dentry blocks are controlled by checkpoint */
@@ -826,7 +887,6 @@ write:
 	/* we should bypass data pages to proceed the kworkder jobs */
 	if (unlikely(f2fs_cp_error(sbi))) {
 		SetPageError(page);
-		unlock_page(page);
 		goto out;
 	}
 
@@ -1002,8 +1062,12 @@ put_next:
 	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 	} else {
-		err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
-					   READ_SYNC);
+		struct f2fs_io_info fio = {
+			.type = DATA,
+			.rw = READ_SYNC,
+			.blk_addr = dn.data_blkaddr,
+		};
+		err = f2fs_submit_page_bio(sbi, page, &fio);
 		if (err)
 			goto fail;
 
@@ -1092,6 +1156,9 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 
 	trace_f2fs_direct_IO_enter(inode, offset, count, rw);
 
+	if (rw & WRITE)
+		__allocate_data_blocks(inode, offset, count);
+
 	err = blockdev_direct_IO(rw, iocb, inode, iter, offset, get_data_block);
 	if (err < 0 && (rw & WRITE))
 		f2fs_write_failed(mapping, offset + count);
@@ -1101,24 +1168,33 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 	return err;
 }
 
-static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
-				      unsigned int length)
+void f2fs_invalidate_page(struct page *page, unsigned int offset,
+							unsigned int length)
 {
 	struct inode *inode = page->mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
-	if (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE)
+	if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
+		(offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE))
 		return;
 
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
-		invalidate_inmem_page(inode, page);
-
-	if (PageDirty(page))
-		inode_dec_dirty_pages(inode);
+	if (PageDirty(page)) {
+		if (inode->i_ino == F2FS_META_INO(sbi))
+			dec_page_count(sbi, F2FS_DIRTY_META);
+		else if (inode->i_ino == F2FS_NODE_INO(sbi))
+			dec_page_count(sbi, F2FS_DIRTY_NODES);
+		else
+			inode_dec_dirty_pages(inode);
+	}
 	ClearPagePrivate(page);
 }
 
-static int f2fs_release_data_page(struct page *page, gfp_t wait)
+int f2fs_release_page(struct page *page, gfp_t wait)
 {
+	/* If this is dirty page, keep PagePrivate */
+	if (PageDirty(page))
+		return 0;
+
 	ClearPagePrivate(page);
 	return 1;
 }
@@ -1132,7 +1208,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
 
 	SetPageUptodate(page);
 
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode)) {
+	if (f2fs_is_atomic_file(inode)) {
 		register_inmem_page(inode, page);
 		return 1;
 	}
@@ -1168,8 +1244,8 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.write_begin	= f2fs_write_begin,
 	.write_end	= f2fs_write_end,
 	.set_page_dirty	= f2fs_set_data_page_dirty,
-	.invalidatepage	= f2fs_invalidate_data_page,
-	.releasepage	= f2fs_release_data_page,
+	.invalidatepage	= f2fs_invalidate_page,
+	.releasepage	= f2fs_release_page,
 	.direct_IO	= f2fs_direct_IO,
 	.bmap		= f2fs_bmap,
 };
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 91e8f699ab30..e671373cc8ab 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -40,6 +40,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->ndirty_dirs = sbi->n_dirty_dirs;
 	si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
+	si->wb_pages = get_pages(sbi, F2FS_WRITEBACK);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
 	si->rsvd_segs = reserved_segments(sbi);
 	si->overp_segs = overprovision_segments(sbi);
@@ -57,7 +58,9 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->node_pages = NODE_MAPPING(sbi)->nrpages;
 	si->meta_pages = META_MAPPING(sbi)->nrpages;
 	si->nats = NM_I(sbi)->nat_cnt;
-	si->sits = SIT_I(sbi)->dirty_sentries;
+	si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
+	si->sits = MAIN_SEGS(sbi);
+	si->dirty_sits = SIT_I(sbi)->dirty_sentries;
 	si->fnids = NM_I(sbi)->fcnt;
 	si->bg_gc = sbi->bg_gc;
 	si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
@@ -79,6 +82,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		si->segment_count[i] = sbi->segment_count[i];
 		si->block_count[i] = sbi->block_count[i];
 	}
+
+	si->inplace_count = atomic_read(&sbi->inplace_count);
 }
 
 /*
@@ -137,6 +142,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
 	si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
 	si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+	si->base_mem += SIT_VBLOCK_MAP_SIZE;
 	if (sbi->segs_per_sec > 1)
 		si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
 	si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
@@ -159,20 +165,32 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += sizeof(struct f2fs_nm_info);
 	si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
 
+get_cache:
+	si->cache_mem = 0;
+
 	/* build gc */
-	si->base_mem += sizeof(struct f2fs_gc_kthread);
+	if (sbi->gc_thread)
+		si->cache_mem += sizeof(struct f2fs_gc_kthread);
+
+	/* build merge flush thread */
+	if (SM_I(sbi)->cmd_control_info)
+		si->cache_mem += sizeof(struct flush_cmd_control);
 
-get_cache:
 	/* free nids */
-	si->cache_mem = NM_I(sbi)->fcnt;
-	si->cache_mem += NM_I(sbi)->nat_cnt;
-	npages = NODE_MAPPING(sbi)->nrpages;
-	si->cache_mem += npages << PAGE_CACHE_SHIFT;
-	npages = META_MAPPING(sbi)->nrpages;
-	si->cache_mem += npages << PAGE_CACHE_SHIFT;
-	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct dir_inode_entry);
+	si->cache_mem += NM_I(sbi)->fcnt * sizeof(struct free_nid);
+	si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
+	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
+					sizeof(struct nat_entry_set);
+	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
+	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry);
 	for (i = 0; i <= UPDATE_INO; i++)
 		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
+
+	si->page_mem = 0;
+	npages = NODE_MAPPING(sbi)->nrpages;
+	si->page_mem += npages << PAGE_CACHE_SHIFT;
+	npages = META_MAPPING(sbi)->nrpages;
+	si->page_mem += npages << PAGE_CACHE_SHIFT;
 }
 
 static int stat_show(struct seq_file *s, void *v)
@@ -250,16 +268,16 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "\nExtent Hit Ratio: %d / %d\n",
 			   si->hit_ext, si->total_ext);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
-		seq_printf(s, "  - inmem: %4d\n",
-			   si->inmem_pages);
+		seq_printf(s, "  - inmem: %4d, wb: %4d\n",
+			   si->inmem_pages, si->wb_pages);
 		seq_printf(s, "  - nodes: %4d in %4d\n",
 			   si->ndirty_node, si->node_pages);
 		seq_printf(s, "  - dents: %4d in dirs:%4d\n",
 			   si->ndirty_dent, si->ndirty_dirs);
 		seq_printf(s, "  - meta: %4d in %4d\n",
 			   si->ndirty_meta, si->meta_pages);
-		seq_printf(s, "  - NATs: %9d\n  - SITs: %9d\n",
-			   si->nats, si->sits);
+		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",
+			   si->dirty_nats, si->nats, si->dirty_sits, si->sits);
 		seq_printf(s, "  - free_nids: %9d\n",
 			   si->fnids);
 		seq_puts(s, "\nDistribution of User Blocks:");
@@ -277,6 +295,7 @@ static int stat_show(struct seq_file *s, void *v)
 		for (j = 0; j < si->util_free; j++)
 			seq_putc(s, '-');
 		seq_puts(s, "]\n\n");
+		seq_printf(s, "IPU: %u blocks\n", si->inplace_count);
 		seq_printf(s, "SSR: %u blocks in %u segments\n",
 			   si->block_count[SSR], si->segment_count[SSR]);
 		seq_printf(s, "LFS: %u blocks in %u segments\n",
@@ -289,9 +308,14 @@ static int stat_show(struct seq_file *s, void *v)
 
 		/* memory footprint */
 		update_mem_info(si->sbi);
-		seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n",
-				(si->base_mem + si->cache_mem) >> 10,
-				si->base_mem >> 10, si->cache_mem >> 10);
+		seq_printf(s, "\nMemory: %u KB\n",
+			(si->base_mem + si->cache_mem + si->page_mem) >> 10);
+		seq_printf(s, "  - static: %u KB\n",
+				si->base_mem >> 10);
+		seq_printf(s, "  - cached: %u KB\n",
+				si->cache_mem >> 10);
+		seq_printf(s, "  - paged : %u KB\n",
+				si->page_mem >> 10);
 	}
 	mutex_unlock(&f2fs_stat_mutex);
 	return 0;
@@ -331,6 +355,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 
 	atomic_set(&sbi->inline_inode, 0);
 	atomic_set(&sbi->inline_dir, 0);
+	atomic_set(&sbi->inplace_count, 0);
 
 	mutex_lock(&f2fs_stat_mutex);
 	list_add_tail(&si->stat_list, &f2fs_stat_list);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index b1a7d5737cd0..b74097a7f6d9 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -286,8 +286,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	f2fs_wait_on_page_writeback(page, type);
 	de->ino = cpu_to_le32(inode->i_ino);
 	set_de_type(de, inode);
-	if (!f2fs_has_inline_dentry(dir))
-		kunmap(page);
+	f2fs_dentry_kunmap(dir, page);
 	set_page_dirty(page);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
 	mark_inode_dirty(dir);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ec58bb2373fc..7fa3313ab0e2 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -28,7 +28,7 @@
 	do {								\
 		if (unlikely(condition)) {				\
 			WARN_ON(1);					\
-			sbi->need_fsck = true;				\
+			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
 		}							\
 	} while (0)
 #define f2fs_down_write(x, y)	down_write(x)
@@ -100,10 +100,15 @@ enum {
 
 enum {
 	CP_UMOUNT,
+	CP_FASTBOOT,
 	CP_SYNC,
 	CP_DISCARD,
 };
 
+#define DEF_BATCHED_TRIM_SECTIONS	32
+#define BATCHED_TRIM_SEGMENTS(sbi)	\
+		(SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
+
 struct cp_control {
 	int reason;
 	__u64 trim_start;
@@ -136,8 +141,14 @@ struct ino_entry {
 	nid_t ino;		/* inode number */
 };
 
-/* for the list of directory inodes */
-struct dir_inode_entry {
+/*
+ * for the list of directory inodes or gc inodes.
+ * NOTE: there are two slab users for this structure, if we add/modify/delete
+ * fields in structure for one of slab users, it may affect fields or size of
+ * other one, in this condition, it's better to split both of slab and related
+ * data structure.
+ */
+struct inode_entry {
 	struct list_head list;	/* list head */
 	struct inode *inode;	/* vfs inode pointer */
 };
@@ -196,11 +207,14 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
  */
 #define F2FS_IOC_GETFLAGS		FS_IOC_GETFLAGS
 #define F2FS_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define F2FS_IOC_GETVERSION		FS_IOC_GETVERSION
 
 #define F2FS_IOCTL_MAGIC		0xf5
 #define F2FS_IOC_START_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 1)
 #define F2FS_IOC_COMMIT_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 2)
 #define F2FS_IOC_START_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 3)
+#define F2FS_IOC_RELEASE_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 4)
+#define F2FS_IOC_ABORT_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 5)
 
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
@@ -295,7 +309,7 @@ struct f2fs_inode_info {
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	unsigned long long xattr_ver;	/* cp version of xattr modification */
 	struct extent_info ext;		/* in-memory extent cache entry */
-	struct dir_inode_entry *dirty_dir;	/* the pointer of dirty dir */
+	struct inode_entry *dirty_dir;	/* the pointer of dirty dir */
 
 	struct radix_tree_root inmem_root;	/* radix tree for inmem pages */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
@@ -398,7 +412,8 @@ enum {
 	CURSEG_HOT_NODE,	/* direct node blocks of directory files */
 	CURSEG_WARM_NODE,	/* direct node blocks of normal files */
 	CURSEG_COLD_NODE,	/* indirect node blocks */
-	NO_CHECK_TYPE
+	NO_CHECK_TYPE,
+	CURSEG_DIRECT_IO,	/* to use for the direct IO path */
 };
 
 struct flush_cmd {
@@ -437,6 +452,9 @@ struct f2fs_sm_info {
 	int nr_discards;			/* # of discards in the list */
 	int max_discards;			/* max. discards to be issued */
 
+	/* for batched trimming */
+	unsigned int trim_sections;		/* # of sections to trim */
+
 	struct list_head sit_entry_set;	/* sit entry set list */
 
 	unsigned int ipu_policy;	/* in-place-update policy */
@@ -489,6 +507,7 @@ enum page_type {
 struct f2fs_io_info {
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
 	int rw;			/* contains R/RS/W/WS with REQ_META/REQ_PRIO */
+	block_t blk_addr;	/* block address to be written */
 };
 
 #define is_read_io(rw)	(((rw) & 1) == READ)
@@ -508,13 +527,20 @@ struct inode_management {
 	unsigned long ino_num;			/* number of entries */
 };
 
+/* For s_flag in struct f2fs_sb_info */
+enum {
+	SBI_IS_DIRTY,				/* dirty flag for checkpoint */
+	SBI_IS_CLOSE,				/* specify unmounting */
+	SBI_NEED_FSCK,				/* need fsck.f2fs to fix */
+	SBI_POR_DOING,				/* recovery is doing or not */
+};
+
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
 	struct proc_dir_entry *s_proc;		/* proc entry */
 	struct buffer_head *raw_super_buf;	/* buffer head of raw sb */
 	struct f2fs_super_block *raw_super;	/* raw super block pointer */
-	int s_dirty;				/* dirty flag for checkpoint */
-	bool need_fsck;				/* need fsck.f2fs to fix */
+	int s_flag;				/* flags for sbi */
 
 	/* for node-related operations */
 	struct f2fs_nm_info *nm_info;		/* node manager */
@@ -534,7 +560,6 @@ struct f2fs_sb_info {
 	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
 	struct rw_semaphore node_write;		/* locking node writes */
 	struct mutex writepages;		/* mutex for writepages() */
-	bool por_doing;				/* recovery is doing or not */
 	wait_queue_head_t cp_wait;
 
 	struct inode_management im[MAX_INO_ENTRY];      /* manage inode cache */
@@ -589,6 +614,7 @@ struct f2fs_sb_info {
 	struct f2fs_stat_info *stat_info;	/* FS status information */
 	unsigned int segment_count[2];		/* # of allocated segments */
 	unsigned int block_count[2];		/* # of allocated blocks */
+	atomic_t inplace_count;		/* # of inplace update */
 	int total_hit_ext, read_hit_ext;	/* extent cache hit ratio */
 	atomic_t inline_inode;			/* # of inline_data inodes */
 	atomic_t inline_dir;			/* # of inline_dentry inodes */
@@ -686,14 +712,19 @@ static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi)
 	return sbi->node_inode->i_mapping;
 }
 
-static inline void F2FS_SET_SB_DIRT(struct f2fs_sb_info *sbi)
+static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
 {
-	sbi->s_dirty = 1;
+	return sbi->s_flag & (0x01 << type);
 }
 
-static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi)
+static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
 {
-	sbi->s_dirty = 0;
+	sbi->s_flag |= (0x01 << type);
+}
+
+static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
+{
+	sbi->s_flag &= ~(0x01 << type);
 }
 
 static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
@@ -741,6 +772,28 @@ static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
 	up_write(&sbi->cp_rwsem);
 }
 
+static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
+{
+	int reason = CP_SYNC;
+
+	if (test_opt(sbi, FASTBOOT))
+		reason = CP_FASTBOOT;
+	if (is_sbi_flag_set(sbi, SBI_IS_CLOSE))
+		reason = CP_UMOUNT;
+	return reason;
+}
+
+static inline bool __remain_node_summaries(int reason)
+{
+	return (reason == CP_UMOUNT || reason == CP_FASTBOOT);
+}
+
+static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
+{
+	return (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) ||
+			is_set_ckpt_flags(F2FS_CKPT(sbi), CP_FASTBOOT_FLAG));
+}
+
 /*
  * Check whether the given nid is within node id range.
  */
@@ -805,7 +858,7 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
 {
 	atomic_inc(&sbi->nr_pages[count_type]);
-	F2FS_SET_SB_DIRT(sbi);
+	set_sbi_flag(sbi, SBI_IS_DIRTY);
 }
 
 static inline void inode_inc_dirty_pages(struct inode *inode)
@@ -1113,6 +1166,7 @@ enum {
 	FI_NEED_IPU,		/* used for ipu per file */
 	FI_ATOMIC_FILE,		/* indicate atomic file */
 	FI_VOLATILE_FILE,	/* indicate volatile file */
+	FI_DROP_CACHE,		/* drop dirty page cache */
 	FI_DATA_EXIST,		/* indicate data exists */
 };
 
@@ -1220,6 +1274,11 @@ static inline bool f2fs_is_volatile_file(struct inode *inode)
 	return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE);
 }
 
+static inline bool f2fs_is_drop_cache(struct inode *inode)
+{
+	return is_inode_flag_set(F2FS_I(inode), FI_DROP_CACHE);
+}
+
 static inline void *inline_data_addr(struct page *page)
 {
 	struct f2fs_inode *ri = F2FS_INODE(page);
@@ -1389,7 +1448,6 @@ void destroy_node_manager_caches(void);
  * segment.c
  */
 void register_inmem_page(struct inode *, struct page *);
-void invalidate_inmem_page(struct inode *, struct page *);
 void commit_inmem_pages(struct inode *, bool);
 void f2fs_balance_fs(struct f2fs_sb_info *);
 void f2fs_balance_fs_bg(struct f2fs_sb_info *);
@@ -1401,16 +1459,16 @@ void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
 void clear_prefree_segments(struct f2fs_sb_info *);
 void release_discard_addrs(struct f2fs_sb_info *);
 void discard_next_dnode(struct f2fs_sb_info *, block_t);
-int npages_for_summary_flush(struct f2fs_sb_info *);
+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 *);
 struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
 void write_meta_page(struct f2fs_sb_info *, struct page *);
 void write_node_page(struct f2fs_sb_info *, struct page *,
-		struct f2fs_io_info *, unsigned int, block_t, block_t *);
-void write_data_page(struct page *, struct dnode_of_data *, block_t *,
-					struct f2fs_io_info *);
-void rewrite_data_page(struct page *, block_t, struct f2fs_io_info *);
+				unsigned int, struct f2fs_io_info *);
+void write_data_page(struct page *, struct dnode_of_data *,
+			struct f2fs_io_info *);
+void rewrite_data_page(struct page *, struct f2fs_io_info *);
 void recover_data_page(struct f2fs_sb_info *, struct page *,
 				struct f2fs_summary *, block_t, block_t);
 void allocate_data_block(struct f2fs_sb_info *, struct page *,
@@ -1457,17 +1515,20 @@ void destroy_checkpoint_caches(void);
  * data.c
  */
 void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
-int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, block_t, int);
-void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, block_t,
+int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *,
+						struct f2fs_io_info *);
+void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *,
 						struct f2fs_io_info *);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
-void update_extent_cache(block_t, struct dnode_of_data *);
+void update_extent_cache(struct dnode_of_data *);
 struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
 struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
 int do_write_data_page(struct page *, struct f2fs_io_info *);
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
+void f2fs_invalidate_page(struct page *, unsigned int, unsigned int);
+int f2fs_release_page(struct page *, gfp_t);
 
 /*
  * gc.c
@@ -1477,8 +1538,6 @@ void stop_gc_thread(struct f2fs_sb_info *);
 block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
 int f2fs_gc(struct f2fs_sb_info *);
 void build_gc_manager(struct f2fs_sb_info *);
-int __init create_gc_caches(void);
-void destroy_gc_caches(void);
 
 /*
  * recovery.c
@@ -1497,9 +1556,9 @@ struct f2fs_stat_info {
 	int main_area_segs, main_area_sections, main_area_zones;
 	int hit_ext, total_ext;
 	int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta;
-	int nats, sits, fnids;
+	int nats, dirty_nats, sits, dirty_sits, fnids;
 	int total_count, utilization;
-	int bg_gc, inline_inode, inline_dir, inmem_pages;
+	int bg_gc, inline_inode, inline_dir, inmem_pages, wb_pages;
 	unsigned int valid_count, valid_node_count, valid_inode_count;
 	unsigned int bimodal, avg_vblocks;
 	int util_free, util_valid, util_invalid;
@@ -1514,7 +1573,8 @@ struct f2fs_stat_info {
 
 	unsigned int segment_count[2];
 	unsigned int block_count[2];
-	unsigned base_mem, cache_mem;
+	unsigned int inplace_count;
+	unsigned base_mem, cache_mem, page_mem;
 };
 
 static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
@@ -1553,7 +1613,8 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 		((sbi)->segment_count[(curseg)->alloc_type]++)
 #define stat_inc_block_count(sbi, curseg)				\
 		((sbi)->block_count[(curseg)->alloc_type]++)
-
+#define stat_inc_inplace_blocks(sbi)					\
+		(atomic_inc(&(sbi)->inplace_count))
 #define stat_inc_seg_count(sbi, type)					\
 	do {								\
 		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
@@ -1599,6 +1660,7 @@ void f2fs_destroy_root_stats(void);
 #define stat_dec_inline_dir(inode)
 #define stat_inc_seg_type(sbi, curseg)
 #define stat_inc_block_count(sbi, curseg)
+#define stat_inc_inplace_blocks(sbi)
 #define stat_inc_seg_count(si, type)
 #define stat_inc_tot_blk_count(si, blks)
 #define stat_inc_data_blk_count(si, blks)
@@ -1619,6 +1681,7 @@ extern const struct address_space_operations f2fs_meta_aops;
 extern const struct inode_operations f2fs_dir_inode_operations;
 extern const struct inode_operations f2fs_symlink_inode_operations;
 extern const struct inode_operations f2fs_special_inode_operations;
+extern struct kmem_cache *inode_entry_slab;
 
 /*
  * inline.c
@@ -1629,7 +1692,6 @@ int f2fs_read_inline_data(struct inode *, struct page *);
 int f2fs_convert_inline_page(struct dnode_of_data *, struct page *);
 int f2fs_convert_inline_inode(struct inode *);
 int f2fs_write_inline_data(struct inode *, struct page *);
-void truncate_inline_data(struct page *, u64);
 bool recover_inline_data(struct inode *, struct page *);
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *, struct qstr *,
 							struct page **);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 3c27e0ecb3bc..98dac27bc3f7 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -26,6 +26,7 @@
 #include "segment.h"
 #include "xattr.h"
 #include "acl.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
@@ -92,7 +93,6 @@ static const struct vm_operations_struct f2fs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= f2fs_vm_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static int get_parent_ino(struct inode *inode, nid_t *pino)
@@ -246,6 +246,10 @@ go_write:
 sync_nodes:
 	sync_node_pages(sbi, ino, &wbc);
 
+	/* if cp_error was enabled, we should avoid infinite loop */
+	if (unlikely(f2fs_cp_error(sbi)))
+		goto out;
+
 	if (need_inode_block_update(sbi, ino)) {
 		mark_inode_dirty_sync(inode);
 		f2fs_write_inode(inode, NULL);
@@ -265,6 +269,7 @@ flush_out:
 	ret = f2fs_issue_flush(sbi);
 out:
 	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+	f2fs_trace_ios(NULL, NULL, 1);
 	return ret;
 }
 
@@ -351,7 +356,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 		/* find data/hole in dnode block */
 		for (; dn.ofs_in_node < end_offset;
 				dn.ofs_in_node++, pgofs++,
-				data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+				data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
 			block_t blkaddr;
 			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
 
@@ -427,7 +432,8 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		if (blkaddr == NULL_ADDR)
 			continue;
 
-		update_extent_cache(NULL_ADDR, dn);
+		dn->data_blkaddr = NULL_ADDR;
+		update_extent_cache(dn);
 		invalidate_blocks(sbi, blkaddr);
 		nr_free++;
 	}
@@ -484,8 +490,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 
 	trace_f2fs_truncate_blocks_enter(inode, from);
 
-	free_from = (pgoff_t)
-		((from + blocksize - 1) >> (sbi->log_blocksize));
+	free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);
 
 	if (lock)
 		f2fs_lock_op(sbi);
@@ -836,6 +841,19 @@ static long f2fs_fallocate(struct file *file, int mode,
 	return ret;
 }
 
+static int f2fs_release_file(struct inode *inode, struct file *filp)
+{
+	/* some remained atomic pages should discarded */
+	if (f2fs_is_atomic_file(inode))
+		commit_inmem_pages(inode, true);
+	if (f2fs_is_volatile_file(inode)) {
+		set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+		filemap_fdatawrite(inode->i_mapping);
+		clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+	}
+	return 0;
+}
+
 #define F2FS_REG_FLMASK		(~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
 #define F2FS_OTHER_FLMASK	(FS_NODUMP_FL | FS_NOATIME_FL)
 
@@ -906,29 +924,30 @@ out:
 	return ret;
 }
 
+static int f2fs_ioc_getversion(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+
+	return put_user(inode->i_generation, (int __user *)arg);
+}
+
 static int f2fs_ioc_start_atomic_write(struct file *filp)
 {
 	struct inode *inode = file_inode(filp);
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
-	f2fs_balance_fs(sbi);
+	f2fs_balance_fs(F2FS_I_SB(inode));
+
+	if (f2fs_is_atomic_file(inode))
+		return 0;
 
 	set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 
 	return f2fs_convert_inline_inode(inode);
 }
 
-static int f2fs_release_file(struct inode *inode, struct file *filp)
-{
-	/* some remained atomic pages should discarded */
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
-		commit_inmem_pages(inode, true);
-	return 0;
-}
-
 static int f2fs_ioc_commit_atomic_write(struct file *filp)
 {
 	struct inode *inode = file_inode(filp);
@@ -949,6 +968,7 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 
 	ret = f2fs_sync_file(filp, 0, LONG_MAX, 0);
 	mnt_drop_write_file(filp);
+	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 	return ret;
 }
 
@@ -959,11 +979,56 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
+	if (f2fs_is_volatile_file(inode))
+		return 0;
+
 	set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
 
 	return f2fs_convert_inline_inode(inode);
 }
 
+static int f2fs_ioc_release_volatile_write(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (!f2fs_is_volatile_file(inode))
+		return 0;
+
+	punch_hole(inode, 0, F2FS_BLKSIZE);
+	return 0;
+}
+
+static int f2fs_ioc_abort_volatile_write(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+	int ret;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	f2fs_balance_fs(F2FS_I_SB(inode));
+
+	if (f2fs_is_atomic_file(inode)) {
+		commit_inmem_pages(inode, false);
+		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+	}
+
+	if (f2fs_is_volatile_file(inode)) {
+		clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+		filemap_fdatawrite(inode->i_mapping);
+		set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+	}
+	mnt_drop_write_file(filp);
+	return ret;
+}
+
 static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -1001,12 +1066,18 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_ioc_getflags(filp, arg);
 	case F2FS_IOC_SETFLAGS:
 		return f2fs_ioc_setflags(filp, arg);
+	case F2FS_IOC_GETVERSION:
+		return f2fs_ioc_getversion(filp, arg);
 	case F2FS_IOC_START_ATOMIC_WRITE:
 		return f2fs_ioc_start_atomic_write(filp);
 	case F2FS_IOC_COMMIT_ATOMIC_WRITE:
 		return f2fs_ioc_commit_atomic_write(filp);
 	case F2FS_IOC_START_VOLATILE_WRITE:
 		return f2fs_ioc_start_volatile_write(filp);
+	case F2FS_IOC_RELEASE_VOLATILE_WRITE:
+		return f2fs_ioc_release_volatile_write(filp);
+	case F2FS_IOC_ABORT_VOLATILE_WRITE:
+		return f2fs_ioc_abort_volatile_write(filp);
 	case FITRIM:
 		return f2fs_ioc_fitrim(filp, arg);
 	default:
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index eec0933a4819..76adbc3641f1 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -24,8 +24,6 @@
 #include "gc.h"
 #include <trace/events/f2fs.h>
 
-static struct kmem_cache *winode_slab;
-
 static int gc_thread_func(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
@@ -46,7 +44,7 @@ static int gc_thread_func(void *data)
 			break;
 
 		if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 			continue;
 		}
 
@@ -67,15 +65,15 @@ static int gc_thread_func(void *data)
 			continue;
 
 		if (!is_idle(sbi)) {
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 			mutex_unlock(&sbi->gc_mutex);
 			continue;
 		}
 
 		if (has_enough_invalid_blocks(sbi))
-			wait_ms = decrease_sleep_time(gc_th, wait_ms);
+			decrease_sleep_time(gc_th, &wait_ms);
 		else
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 
 		stat_inc_bggc_count(sbi);
 
@@ -356,13 +354,10 @@ static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode)
 		iput(inode);
 		return;
 	}
-	new_ie = f2fs_kmem_cache_alloc(winode_slab, GFP_NOFS);
+	new_ie = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
 	new_ie->inode = inode;
-retry:
-	if (radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie)) {
-		cond_resched();
-		goto retry;
-	}
+
+	f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie);
 	list_add_tail(&new_ie->list, &gc_list->ilist);
 }
 
@@ -373,7 +368,7 @@ static void put_gc_inode(struct gc_inode_list *gc_list)
 		radix_tree_delete(&gc_list->iroot, ie->inode->i_ino);
 		iput(ie->inode);
 		list_del(&ie->list);
-		kmem_cache_free(winode_slab, ie);
+		kmem_cache_free(inode_entry_slab, ie);
 	}
 }
 
@@ -703,8 +698,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi)
 		.iroot = RADIX_TREE_INIT(GFP_NOFS),
 	};
 
-	cpc.reason = test_opt(sbi, FASTBOOT) ? CP_UMOUNT : CP_SYNC;
-
+	cpc.reason = __get_cp_reason(sbi);
 gc_more:
 	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
 		goto stop;
@@ -750,17 +744,3 @@ void build_gc_manager(struct f2fs_sb_info *sbi)
 {
 	DIRTY_I(sbi)->v_ops = &default_v_ops;
 }
-
-int __init create_gc_caches(void)
-{
-	winode_slab = f2fs_kmem_cache_create("f2fs_gc_inodes",
-			sizeof(struct inode_entry));
-	if (!winode_slab)
-		return -ENOMEM;
-	return 0;
-}
-
-void destroy_gc_caches(void)
-{
-	kmem_cache_destroy(winode_slab);
-}
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index 6ff7ad38463e..b4a65be9f7d3 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -35,11 +35,6 @@ struct f2fs_gc_kthread {
 	unsigned int gc_idle;
 };
 
-struct inode_entry {
-	struct list_head list;
-	struct inode *inode;
-};
-
 struct gc_inode_list {
 	struct list_head ilist;
 	struct radix_tree_root iroot;
@@ -69,26 +64,26 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
 	return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100;
 }
 
-static inline long increase_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
+static inline void increase_sleep_time(struct f2fs_gc_kthread *gc_th,
+								long *wait)
 {
-	if (wait == gc_th->no_gc_sleep_time)
-		return wait;
+	if (*wait == gc_th->no_gc_sleep_time)
+		return;
 
-	wait += gc_th->min_sleep_time;
-	if (wait > gc_th->max_sleep_time)
-		wait = gc_th->max_sleep_time;
-	return wait;
+	*wait += gc_th->min_sleep_time;
+	if (*wait > gc_th->max_sleep_time)
+		*wait = gc_th->max_sleep_time;
 }
 
-static inline long decrease_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
+static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th,
+								long *wait)
 {
-	if (wait == gc_th->no_gc_sleep_time)
-		wait = gc_th->max_sleep_time;
+	if (*wait == gc_th->no_gc_sleep_time)
+		*wait = gc_th->max_sleep_time;
 
-	wait -= gc_th->min_sleep_time;
-	if (wait <= gc_th->min_sleep_time)
-		wait = gc_th->min_sleep_time;
-	return wait;
+	*wait -= gc_th->min_sleep_time;
+	if (*wait <= gc_th->min_sleep_time)
+		*wait = gc_th->min_sleep_time;
 }
 
 static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index f2d3c581e776..1484c00133cd 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -50,6 +50,12 @@ void read_inline_data(struct page *page, struct page *ipage)
 	SetPageUptodate(page);
 }
 
+static void truncate_inline_data(struct page *ipage)
+{
+	f2fs_wait_on_page_writeback(ipage, NODE);
+	memset(inline_data_addr(ipage), 0, MAX_INLINE_DATA);
+}
+
 int f2fs_read_inline_data(struct inode *inode, struct page *page)
 {
 	struct page *ipage;
@@ -79,7 +85,6 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 {
 	void *src_addr, *dst_addr;
-	block_t new_blk_addr;
 	struct f2fs_io_info fio = {
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
@@ -115,9 +120,9 @@ no_update:
 
 	/* write data page to try to make data consistent */
 	set_page_writeback(page);
-
-	write_data_page(page, dn, &new_blk_addr, &fio);
-	update_extent_cache(new_blk_addr, dn);
+	fio.blk_addr = dn->data_blkaddr;
+	write_data_page(page, dn, &fio);
+	update_extent_cache(dn);
 	f2fs_wait_on_page_writeback(page, DATA);
 	if (dirty)
 		inode_dec_dirty_pages(dn->inode);
@@ -126,7 +131,7 @@ no_update:
 	set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE);
 
 	/* clear inline data and flag after data writeback */
-	truncate_inline_data(dn->inode_page, 0);
+	truncate_inline_data(dn->inode_page);
 clear_out:
 	stat_dec_inline_inode(dn->inode);
 	f2fs_clear_inline_inode(dn->inode);
@@ -199,19 +204,6 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
 	return 0;
 }
 
-void truncate_inline_data(struct page *ipage, u64 from)
-{
-	void *addr;
-
-	if (from >= MAX_INLINE_DATA)
-		return;
-
-	f2fs_wait_on_page_writeback(ipage, NODE);
-
-	addr = inline_data_addr(ipage);
-	memset(addr + from, 0, MAX_INLINE_DATA - from);
-}
-
 bool recover_inline_data(struct inode *inode, struct page *npage)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -253,7 +245,7 @@ process_inline:
 	if (f2fs_has_inline_data(inode)) {
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(sbi, IS_ERR(ipage));
-		truncate_inline_data(ipage, 0);
+		truncate_inline_data(ipage);
 		f2fs_clear_inline_inode(inode);
 		update_inode(inode, ipage);
 		f2fs_put_page(ipage, 1);
@@ -371,7 +363,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	set_page_dirty(page);
 
 	/* clear inline dir and flag after data writeback */
-	truncate_inline_data(ipage, 0);
+	truncate_inline_data(ipage);
 
 	stat_dec_inline_dir(dir);
 	clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 196cc7843aaf..2d002e3738a7 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -67,29 +67,23 @@ static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 	}
 }
 
-static int __recover_inline_status(struct inode *inode, struct page *ipage)
+static void __recover_inline_status(struct inode *inode, struct page *ipage)
 {
 	void *inline_data = inline_data_addr(ipage);
-	struct f2fs_inode *ri;
-	void *zbuf;
+	__le32 *start = inline_data;
+	__le32 *end = start + MAX_INLINE_DATA / sizeof(__le32);
 
-	zbuf = kzalloc(MAX_INLINE_DATA, GFP_NOFS);
-	if (!zbuf)
-		return -ENOMEM;
+	while (start < end) {
+		if (*start++) {
+			f2fs_wait_on_page_writeback(ipage, NODE);
 
-	if (!memcmp(zbuf, inline_data, MAX_INLINE_DATA)) {
-		kfree(zbuf);
-		return 0;
+			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+			set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
+			set_page_dirty(ipage);
+			return;
+		}
 	}
-	kfree(zbuf);
-
-	f2fs_wait_on_page_writeback(ipage, NODE);
-	set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
-
-	ri = F2FS_INODE(ipage);
-	set_raw_inline(F2FS_I(inode), ri);
-	set_page_dirty(ipage);
-	return 0;
+	return;
 }
 
 static int do_read_inode(struct inode *inode)
@@ -98,7 +92,6 @@ static int do_read_inode(struct inode *inode)
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct page *node_page;
 	struct f2fs_inode *ri;
-	int err = 0;
 
 	/* Check if ino is within scope */
 	if (check_nid_range(sbi, inode->i_ino)) {
@@ -142,7 +135,7 @@ static int do_read_inode(struct inode *inode)
 
 	/* check data exist */
 	if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
-		err = __recover_inline_status(inode, node_page);
+		__recover_inline_status(inode, node_page);
 
 	/* get rdev by using inline_info */
 	__get_inode_rdev(inode, ri);
@@ -152,7 +145,7 @@ static int do_read_inode(struct inode *inode)
 	stat_inc_inline_inode(inode);
 	stat_inc_inline_dir(inode);
 
-	return err;
+	return 0;
 }
 
 struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
@@ -304,7 +297,7 @@ void f2fs_evict_inode(struct inode *inode)
 	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 
 	/* some remained atomic pages should discarded */
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
+	if (f2fs_is_atomic_file(inode))
 		commit_inmem_pages(inode, true);
 
 	trace_f2fs_evict_inode(inode);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 547a2deeb1ac..e79639a9787a 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -299,7 +299,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_op = &f2fs_dir_inode_operations;
 	inode->i_fop = &f2fs_dir_operations;
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
 
 	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
 	f2fs_lock_op(sbi);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index f83326ca32ef..97bd9d3db882 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -19,6 +19,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 #define on_build_free_nids(nmi) mutex_is_locked(&nm_i->build_lock)
@@ -57,12 +58,13 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 	} else if (type == INO_ENTRIES) {
 		int i;
 
-		if (sbi->sb->s_bdi->dirty_exceeded)
-			return false;
 		for (i = 0; i <= UPDATE_INO; i++)
 			mem_size += (sbi->im[i].ino_num *
 				sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+	} else {
+		if (sbi->sb->s_bdi->dirty_exceeded)
+			return false;
 	}
 	return res;
 }
@@ -268,7 +270,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 	e = __lookup_nat_cache(nm_i, ni->nid);
 	if (!e) {
 		e = grab_nat_entry(nm_i, ni->nid);
-		e->ni = *ni;
+		copy_node_info(&e->ni, ni);
 		f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
 	} else if (new_blkaddr == NEW_ADDR) {
 		/*
@@ -276,7 +278,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 		 * previous nat entry can be remained in nat cache.
 		 * So, reinitialize it with new information.
 		 */
-		e->ni = *ni;
+		copy_node_info(&e->ni, ni);
 		f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR);
 	}
 
@@ -346,7 +348,6 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	struct nat_entry *e;
 	int i;
 
-	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
 	ni->nid = nid;
 
 	/* Check nat cache */
@@ -361,6 +362,8 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	if (e)
 		return;
 
+	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
+
 	/* Check current segment summary */
 	mutex_lock(&curseg->curseg_mutex);
 	i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
@@ -471,7 +474,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct page *npage[4];
-	struct page *parent;
+	struct page *parent = NULL;
 	int offset[4];
 	unsigned int noffset[4];
 	nid_t nids[4];
@@ -488,6 +491,14 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 		if (IS_ERR(npage[0]))
 			return PTR_ERR(npage[0]);
 	}
+
+	/* if inline_data is set, should not report any block indices */
+	if (f2fs_has_inline_data(dn->inode) && index) {
+		err = -EINVAL;
+		f2fs_put_page(npage[0], 1);
+		goto release_out;
+	}
+
 	parent = npage[0];
 	if (level != 0)
 		nids[1] = get_nid(parent, offset[0], true);
@@ -585,7 +596,7 @@ static void truncate_node(struct dnode_of_data *dn)
 	}
 invalidate:
 	clear_node_page_dirty(dn->node_page);
-	F2FS_SET_SB_DIRT(sbi);
+	set_sbi_flag(sbi, SBI_IS_DIRTY);
 
 	f2fs_put_page(dn->node_page, 1);
 
@@ -976,6 +987,10 @@ static int read_node_page(struct page *page, int rw)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	struct node_info ni;
+	struct f2fs_io_info fio = {
+		.type = NODE,
+		.rw = rw,
+	};
 
 	get_node_info(sbi, page->index, &ni);
 
@@ -987,7 +1002,8 @@ static int read_node_page(struct page *page, int rw)
 	if (PageUptodate(page))
 		return LOCKED_PAGE;
 
-	return f2fs_submit_page_bio(sbi, page, ni.blk_addr, rw);
+	fio.blk_addr = ni.blk_addr;
+	return f2fs_submit_page_bio(sbi, page, &fio);
 }
 
 /*
@@ -1028,11 +1044,11 @@ repeat:
 	err = read_node_page(page, READ_SYNC);
 	if (err < 0)
 		return ERR_PTR(err);
-	else if (err == LOCKED_PAGE)
-		goto got_it;
+	else if (err != LOCKED_PAGE)
+		lock_page(page);
 
-	lock_page(page);
 	if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) {
+		ClearPageUptodate(page);
 		f2fs_put_page(page, 1);
 		return ERR_PTR(-EIO);
 	}
@@ -1040,7 +1056,6 @@ repeat:
 		f2fs_put_page(page, 1);
 		goto repeat;
 	}
-got_it:
 	return page;
 }
 
@@ -1268,7 +1283,6 @@ static int f2fs_write_node_page(struct page *page,
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	nid_t nid;
-	block_t new_addr;
 	struct node_info ni;
 	struct f2fs_io_info fio = {
 		.type = NODE,
@@ -1277,7 +1291,7 @@ static int f2fs_write_node_page(struct page *page,
 
 	trace_f2fs_writepage(page, NODE);
 
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto redirty_out;
@@ -1303,9 +1317,11 @@ static int f2fs_write_node_page(struct page *page,
 	} else {
 		down_read(&sbi->node_write);
 	}
+
 	set_page_writeback(page);
-	write_node_page(sbi, page, &fio, nid, ni.blk_addr, &new_addr);
-	set_node_addr(sbi, &ni, new_addr, is_fsync_dnode(page));
+	fio.blk_addr = ni.blk_addr;
+	write_node_page(sbi, page, nid, &fio);
+	set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page));
 	dec_page_count(sbi, F2FS_DIRTY_NODES);
 	up_read(&sbi->node_write);
 	unlock_page(page);
@@ -1355,26 +1371,12 @@ static int f2fs_set_node_page_dirty(struct page *page)
 		__set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
 		SetPagePrivate(page);
+		f2fs_trace_pid(page);
 		return 1;
 	}
 	return 0;
 }
 
-static void f2fs_invalidate_node_page(struct page *page, unsigned int offset,
-				      unsigned int length)
-{
-	struct inode *inode = page->mapping->host;
-	if (PageDirty(page))
-		dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_NODES);
-	ClearPagePrivate(page);
-}
-
-static int f2fs_release_node_page(struct page *page, gfp_t wait)
-{
-	ClearPagePrivate(page);
-	return 1;
-}
-
 /*
  * Structure of the f2fs node operations
  */
@@ -1382,8 +1384,8 @@ const struct address_space_operations f2fs_node_aops = {
 	.writepage	= f2fs_write_node_page,
 	.writepages	= f2fs_write_node_pages,
 	.set_page_dirty	= f2fs_set_node_page_dirty,
-	.invalidatepage	= f2fs_invalidate_node_page,
-	.releasepage	= f2fs_release_node_page,
+	.invalidatepage	= f2fs_invalidate_page,
+	.releasepage	= f2fs_release_page,
 };
 
 static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
@@ -1726,80 +1728,41 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	return 0;
 }
 
-/*
- * ra_sum_pages() merge contiguous pages into one bio and submit.
- * these pre-read pages are allocated in bd_inode's mapping tree.
- */
-static int ra_sum_pages(struct f2fs_sb_info *sbi, struct page **pages,
-				int start, int nrpages)
-{
-	struct inode *inode = sbi->sb->s_bdev->bd_inode;
-	struct address_space *mapping = inode->i_mapping;
-	int i, page_idx = start;
-	struct f2fs_io_info fio = {
-		.type = META,
-		.rw = READ_SYNC | REQ_META | REQ_PRIO
-	};
-
-	for (i = 0; page_idx < start + nrpages; page_idx++, i++) {
-		/* alloc page in bd_inode for reading node summary info */
-		pages[i] = grab_cache_page(mapping, page_idx);
-		if (!pages[i])
-			break;
-		f2fs_submit_page_mbio(sbi, pages[i], page_idx, &fio);
-	}
-
-	f2fs_submit_merged_bio(sbi, META, READ);
-	return i;
-}
-
 int restore_node_summary(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct f2fs_summary_block *sum)
 {
 	struct f2fs_node *rn;
 	struct f2fs_summary *sum_entry;
-	struct inode *inode = sbi->sb->s_bdev->bd_inode;
 	block_t addr;
 	int bio_blocks = MAX_BIO_BLOCKS(sbi);
-	struct page *pages[bio_blocks];
-	int i, idx, last_offset, nrpages, err = 0;
+	int i, idx, last_offset, nrpages;
 
 	/* scan the node segment */
 	last_offset = sbi->blocks_per_seg;
 	addr = START_BLOCK(sbi, segno);
 	sum_entry = &sum->entries[0];
 
-	for (i = 0; !err && i < last_offset; i += nrpages, addr += nrpages) {
+	for (i = 0; i < last_offset; i += nrpages, addr += nrpages) {
 		nrpages = min(last_offset - i, bio_blocks);
 
 		/* readahead node pages */
-		nrpages = ra_sum_pages(sbi, pages, addr, nrpages);
-		if (!nrpages)
-			return -ENOMEM;
+		ra_meta_pages(sbi, addr, nrpages, META_POR);
 
-		for (idx = 0; idx < nrpages; idx++) {
-			if (err)
-				goto skip;
+		for (idx = addr; idx < addr + nrpages; idx++) {
+			struct page *page = get_meta_page(sbi, idx);
 
-			lock_page(pages[idx]);
-			if (unlikely(!PageUptodate(pages[idx]))) {
-				err = -EIO;
-			} else {
-				rn = F2FS_NODE(pages[idx]);
-				sum_entry->nid = rn->footer.nid;
-				sum_entry->version = 0;
-				sum_entry->ofs_in_node = 0;
-				sum_entry++;
-			}
-			unlock_page(pages[idx]);
-skip:
-			page_cache_release(pages[idx]);
+			rn = F2FS_NODE(page);
+			sum_entry->nid = rn->footer.nid;
+			sum_entry->version = 0;
+			sum_entry->ofs_in_node = 0;
+			sum_entry++;
+			f2fs_put_page(page, 1);
 		}
 
-		invalidate_mapping_pages(inode->i_mapping, addr,
+		invalidate_mapping_pages(META_MAPPING(sbi), addr,
 							addr + nrpages);
 	}
-	return err;
+	return 0;
 }
 
 static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
@@ -1923,7 +1886,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
 	struct f2fs_summary_block *sum = curseg->sum_blk;
-	struct nat_entry_set *setvec[NATVEC_SIZE];
+	struct nat_entry_set *setvec[SETVEC_SIZE];
 	struct nat_entry_set *set, *tmp;
 	unsigned int found;
 	nid_t set_idx = 0;
@@ -1940,7 +1903,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 		remove_nats_in_journal(sbi);
 
 	while ((found = __gang_lookup_nat_set(nm_i,
-					set_idx, NATVEC_SIZE, setvec))) {
+					set_idx, SETVEC_SIZE, setvec))) {
 		unsigned idx;
 		set_idx = setvec[found - 1]->set + 1;
 		for (idx = 0; idx < found; idx++)
@@ -2020,6 +1983,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i, *next_i;
 	struct nat_entry *natvec[NATVEC_SIZE];
+	struct nat_entry_set *setvec[SETVEC_SIZE];
 	nid_t nid = 0;
 	unsigned int found;
 
@@ -2044,11 +2008,27 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 	while ((found = __gang_lookup_nat_cache(nm_i,
 					nid, NATVEC_SIZE, natvec))) {
 		unsigned idx;
+
 		nid = nat_get_nid(natvec[found - 1]) + 1;
 		for (idx = 0; idx < found; idx++)
 			__del_from_nat_cache(nm_i, natvec[idx]);
 	}
 	f2fs_bug_on(sbi, nm_i->nat_cnt);
+
+	/* destroy nat set cache */
+	nid = 0;
+	while ((found = __gang_lookup_nat_set(nm_i,
+					nid, SETVEC_SIZE, setvec))) {
+		unsigned idx;
+
+		nid = setvec[found - 1]->set + 1;
+		for (idx = 0; idx < found; idx++) {
+			/* entry_cnt is not zero, when cp_error was occurred */
+			f2fs_bug_on(sbi, !list_empty(&setvec[idx]->entry_list));
+			radix_tree_delete(&nm_i->nat_set_root, setvec[idx]->set);
+			kmem_cache_free(nat_entry_set_slab, setvec[idx]);
+		}
+	}
 	up_write(&nm_i->nat_tree_lock);
 
 	kfree(nm_i->nat_bitmap);
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index d10b6448a671..f405bbf2435a 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -25,10 +25,19 @@
 
 /* vector size for gang look-up from nat cache that consists of radix tree */
 #define NATVEC_SIZE	64
+#define SETVEC_SIZE	32
 
 /* return value for read_node_page */
 #define LOCKED_PAGE	1
 
+/* For flag in struct node_info */
+enum {
+	IS_CHECKPOINTED,	/* is it checkpointed before? */
+	HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
+	HAS_LAST_FSYNC,		/* has the latest node fsync mark? */
+	IS_DIRTY,		/* this nat entry is dirty? */
+};
+
 /*
  * For node information
  */
@@ -37,18 +46,11 @@ struct node_info {
 	nid_t ino;		/* inode number of the node's owner */
 	block_t	blk_addr;	/* block address of the node */
 	unsigned char version;	/* version of the node */
-};
-
-enum {
-	IS_CHECKPOINTED,	/* is it checkpointed before? */
-	HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
-	HAS_LAST_FSYNC,		/* has the latest node fsync mark? */
-	IS_DIRTY,		/* this nat entry is dirty? */
+	unsigned char flag;	/* for node information bits */
 };
 
 struct nat_entry {
 	struct list_head list;	/* for clean or dirty nat list */
-	unsigned char flag;	/* for node information bits */
 	struct node_info ni;	/* in-memory node information */
 };
 
@@ -63,20 +65,30 @@ struct nat_entry {
 
 #define inc_node_version(version)	(++version)
 
+static inline void copy_node_info(struct node_info *dst,
+						struct node_info *src)
+{
+	dst->nid = src->nid;
+	dst->ino = src->ino;
+	dst->blk_addr = src->blk_addr;
+	dst->version = src->version;
+	/* should not copy flag here */
+}
+
 static inline void set_nat_flag(struct nat_entry *ne,
 				unsigned int type, bool set)
 {
 	unsigned char mask = 0x01 << type;
 	if (set)
-		ne->flag |= mask;
+		ne->ni.flag |= mask;
 	else
-		ne->flag &= ~mask;
+		ne->ni.flag &= ~mask;
 }
 
 static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type)
 {
 	unsigned char mask = 0x01 << type;
-	return ne->flag & mask;
+	return ne->ni.flag & mask;
 }
 
 static inline void nat_reset_flag(struct nat_entry *ne)
@@ -108,6 +120,7 @@ enum mem_type {
 	NAT_ENTRIES,	/* indicates the cached nat entry */
 	DIRTY_DENTS,	/* indicates dirty dentry pages */
 	INO_ENTRIES,	/* indicates inode entries */
+	BASE_CHECK,	/* check kernel status */
 };
 
 struct nat_entry_set {
@@ -200,11 +213,19 @@ static inline void fill_node_footer(struct page *page, nid_t nid,
 				nid_t ino, unsigned int ofs, bool reset)
 {
 	struct f2fs_node *rn = F2FS_NODE(page);
+	unsigned int old_flag = 0;
+
 	if (reset)
 		memset(rn, 0, sizeof(*rn));
+	else
+		old_flag = le32_to_cpu(rn->footer.flag);
+
 	rn->footer.nid = cpu_to_le32(nid);
 	rn->footer.ino = cpu_to_le32(ino);
-	rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
+
+	/* should remain old flag bits such as COLD_BIT_SHIFT */
+	rn->footer.flag = cpu_to_le32((ofs << OFFSET_BIT_SHIFT) |
+					(old_flag & OFFSET_BIT_MASK));
 }
 
 static inline void copy_node_footer(struct page *dst, struct page *src)
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 9160a37e1c7a..41afb9534bbd 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -346,6 +346,10 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	if (IS_INODE(page)) {
 		recover_inline_xattr(inode, page);
 	} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
+		/*
+		 * Deprecated; xattr blocks should be found from cold log.
+		 * But, we should remain this for backward compatibility.
+		 */
 		recover_xattr_data(inode, page, blkaddr);
 		goto out;
 	}
@@ -396,7 +400,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 			/* write dummy data page */
 			recover_data_page(sbi, NULL, &sum, src, dest);
-			update_extent_cache(dest, &dn);
+			dn.data_blkaddr = dest;
+			update_extent_cache(&dn);
 			recovered++;
 		}
 		dn.ofs_in_node++;
@@ -503,7 +508,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 	INIT_LIST_HEAD(&inode_list);
 
 	/* step #1: find fsynced inode numbers */
-	sbi->por_doing = true;
+	set_sbi_flag(sbi, SBI_POR_DOING);
 
 	/* prevent checkpoint */
 	mutex_lock(&sbi->cp_mutex);
@@ -536,7 +541,7 @@ out:
 		truncate_inode_pages_final(META_MAPPING(sbi));
 	}
 
-	sbi->por_doing = false;
+	clear_sbi_flag(sbi, SBI_POR_DOING);
 	if (err) {
 		discard_next_dnode(sbi, blkaddr);
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 42607a679923..daee4ab913da 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -20,6 +20,7 @@
 #include "f2fs.h"
 #include "segment.h"
 #include "node.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 #define __reverse_ffz(x) __reverse_ffs(~(x))
@@ -181,6 +182,7 @@ void register_inmem_page(struct inode *inode, struct page *page)
 	int err;
 
 	SetPagePrivate(page);
+	f2fs_trace_pid(page);
 
 	new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
 
@@ -205,23 +207,6 @@ retry:
 	mutex_unlock(&fi->inmem_lock);
 }
 
-void invalidate_inmem_page(struct inode *inode, struct page *page)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct inmem_pages *cur;
-
-	mutex_lock(&fi->inmem_lock);
-	cur = radix_tree_lookup(&fi->inmem_root, page->index);
-	if (cur) {
-		radix_tree_delete(&fi->inmem_root, cur->page->index);
-		f2fs_put_page(cur->page, 0);
-		list_del(&cur->list);
-		kmem_cache_free(inmem_entry_slab, cur);
-		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
-	}
-	mutex_unlock(&fi->inmem_lock);
-}
-
 void commit_inmem_pages(struct inode *inode, bool abort)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -230,7 +215,7 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 	bool submit_bio = false;
 	struct f2fs_io_info fio = {
 		.type = DATA,
-		.rw = WRITE_SYNC,
+		.rw = WRITE_SYNC | REQ_PRIO,
 	};
 
 	/*
@@ -240,33 +225,38 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 	 * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this
 	 * inode becomes free by iget_locked in f2fs_iget.
 	 */
-	if (!abort)
+	if (!abort) {
 		f2fs_balance_fs(sbi);
-
-	f2fs_lock_op(sbi);
+		f2fs_lock_op(sbi);
+	}
 
 	mutex_lock(&fi->inmem_lock);
 	list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
-		lock_page(cur->page);
-		if (!abort && cur->page->mapping == inode->i_mapping) {
-			f2fs_wait_on_page_writeback(cur->page, DATA);
-			if (clear_page_dirty_for_io(cur->page))
-				inode_dec_dirty_pages(inode);
-			do_write_data_page(cur->page, &fio);
-			submit_bio = true;
+		if (!abort) {
+			lock_page(cur->page);
+			if (cur->page->mapping == inode->i_mapping) {
+				f2fs_wait_on_page_writeback(cur->page, DATA);
+				if (clear_page_dirty_for_io(cur->page))
+					inode_dec_dirty_pages(inode);
+				do_write_data_page(cur->page, &fio);
+				submit_bio = true;
+			}
+			f2fs_put_page(cur->page, 1);
+		} else {
+			put_page(cur->page);
 		}
 		radix_tree_delete(&fi->inmem_root, cur->page->index);
-		f2fs_put_page(cur->page, 1);
 		list_del(&cur->list);
 		kmem_cache_free(inmem_entry_slab, cur);
 		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
 	}
-	if (submit_bio)
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
 	mutex_unlock(&fi->inmem_lock);
 
-	filemap_fdatawait_range(inode->i_mapping, 0, LLONG_MAX);
-	f2fs_unlock_op(sbi);
+	if (!abort) {
+		f2fs_unlock_op(sbi);
+		if (submit_bio)
+			f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	}
 }
 
 /*
@@ -290,7 +280,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	/* check the # of cached NAT entries and prefree segments */
 	if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) ||
 			excess_prefree_segs(sbi) ||
-			available_free_memory(sbi, INO_ENTRIES))
+			!available_free_memory(sbi, INO_ENTRIES))
 		f2fs_sync_fs(sbi->sb, true);
 }
 
@@ -515,12 +505,13 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
 	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
-	unsigned long dmap[entries];
+	unsigned long *dmap = SIT_I(sbi)->tmp_map;
 	unsigned int start = 0, end = -1;
 	bool force = (cpc->reason == CP_DISCARD);
 	int i;
 
-	if (!force && !test_opt(sbi, DISCARD))
+	if (!force && (!test_opt(sbi, DISCARD) ||
+			SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards))
 		return;
 
 	if (force && !se->valid_blocks) {
@@ -548,7 +539,8 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
 	for (i = 0; i < entries; i++)
-		dmap[i] = ~(cur_map[i] | ckpt_map[i]);
+		dmap[i] = force ? ~ckpt_map[i] :
+				(cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
 
 	while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
 		start = __find_rev_next_bit(dmap, max_blocks, end + 1);
@@ -735,7 +727,7 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
 /*
  * Calculate the number of current summary pages for writing
  */
-int npages_for_summary_flush(struct f2fs_sb_info *sbi)
+int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
 {
 	int valid_sum_count = 0;
 	int i, sum_in_page;
@@ -743,8 +735,13 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi)
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
 		if (sbi->ckpt->alloc_type[i] == SSR)
 			valid_sum_count += sbi->blocks_per_seg;
-		else
-			valid_sum_count += curseg_blkoff(sbi, i);
+		else {
+			if (for_ra)
+				valid_sum_count += le16_to_cpu(
+					F2FS_CKPT(sbi)->cur_data_blkoff[i]);
+			else
+				valid_sum_count += curseg_blkoff(sbi, i);
+		}
 	}
 
 	sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE -
@@ -803,7 +800,7 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 	int go_left = 0;
 	int i;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 
 	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
 		segno = find_next_zero_bit(free_i->free_segmap,
@@ -876,7 +873,7 @@ got_it:
 	f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
 	__set_inuse(sbi, segno);
 	*newseg = segno;
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
@@ -927,7 +924,7 @@ static void __next_free_blkoff(struct f2fs_sb_info *sbi,
 {
 	struct seg_entry *se = get_seg_entry(sbi, seg->segno);
 	int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
-	unsigned long target_map[entries];
+	unsigned long *target_map = SIT_I(sbi)->tmp_map;
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
 	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
 	int i, pos;
@@ -1027,18 +1024,22 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 	stat_inc_seg_type(sbi, curseg);
 }
 
+static void __allocate_new_segments(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	unsigned int old_segno;
+
+	old_segno = curseg->segno;
+	SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
+	locate_dirty_segment(sbi, old_segno);
+}
+
 void allocate_new_segments(struct f2fs_sb_info *sbi)
 {
-	struct curseg_info *curseg;
-	unsigned int old_curseg;
 	int i;
 
-	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
-		curseg = CURSEG_I(sbi, i);
-		old_curseg = curseg->segno;
-		SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
-		locate_dirty_segment(sbi, old_curseg);
-	}
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
+		__allocate_new_segments(sbi, i);
 }
 
 static const struct segment_allocation default_salloc_ops = {
@@ -1047,8 +1048,8 @@ static const struct segment_allocation default_salloc_ops = {
 
 int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 {
-	__u64 start = range->start >> sbi->log_blocksize;
-	__u64 end = start + (range->len >> sbi->log_blocksize) - 1;
+	__u64 start = F2FS_BYTES_TO_BLK(range->start);
+	__u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
 	unsigned int start_segno, end_segno;
 	struct cp_control cpc;
 
@@ -1065,16 +1066,21 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
 						GET_SEGNO(sbi, end);
 	cpc.reason = CP_DISCARD;
-	cpc.trim_start = start_segno;
-	cpc.trim_end = end_segno;
-	cpc.trim_minlen = range->minlen >> sbi->log_blocksize;
+	cpc.trim_minlen = F2FS_BYTES_TO_BLK(range->minlen);
 
 	/* do checkpoint to issue discard commands safely */
-	mutex_lock(&sbi->gc_mutex);
-	write_checkpoint(sbi, &cpc);
-	mutex_unlock(&sbi->gc_mutex);
+	for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
+		cpc.trim_start = start_segno;
+		cpc.trim_end = min_t(unsigned int, rounddown(start_segno +
+				BATCHED_TRIM_SEGMENTS(sbi),
+				sbi->segs_per_sec) - 1, end_segno);
+
+		mutex_lock(&sbi->gc_mutex);
+		write_checkpoint(sbi, &cpc);
+		mutex_unlock(&sbi->gc_mutex);
+	}
 out:
-	range->len = cpc.trimmed << sbi->log_blocksize;
+	range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
 	return 0;
 }
 
@@ -1151,11 +1157,18 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg;
+	bool direct_io = (type == CURSEG_DIRECT_IO);
+
+	type = direct_io ? CURSEG_WARM_DATA : type;
 
 	curseg = CURSEG_I(sbi, type);
 
 	mutex_lock(&curseg->curseg_mutex);
 
+	/* direct_io'ed data is aligned to the segment for better performance */
+	if (direct_io && curseg->next_blkoff)
+		__allocate_new_segments(sbi, type);
+
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	/*
@@ -1187,39 +1200,39 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 }
 
 static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
-			block_t old_blkaddr, block_t *new_blkaddr,
-			struct f2fs_summary *sum, struct f2fs_io_info *fio)
+			struct f2fs_summary *sum,
+			struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(page, fio->type);
 
-	allocate_data_block(sbi, page, old_blkaddr, new_blkaddr, sum, type);
+	allocate_data_block(sbi, page, fio->blk_addr, &fio->blk_addr, sum, type);
 
 	/* writeout dirty page into bdev */
-	f2fs_submit_page_mbio(sbi, page, *new_blkaddr, fio);
+	f2fs_submit_page_mbio(sbi, page, fio);
 }
 
 void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 {
 	struct f2fs_io_info fio = {
 		.type = META,
-		.rw = WRITE_SYNC | REQ_META | REQ_PRIO
+		.rw = WRITE_SYNC | REQ_META | REQ_PRIO,
+		.blk_addr = page->index,
 	};
 
 	set_page_writeback(page);
-	f2fs_submit_page_mbio(sbi, page, page->index, &fio);
+	f2fs_submit_page_mbio(sbi, page, &fio);
 }
 
 void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
-		struct f2fs_io_info *fio,
-		unsigned int nid, block_t old_blkaddr, block_t *new_blkaddr)
+			unsigned int nid, struct f2fs_io_info *fio)
 {
 	struct f2fs_summary sum;
 	set_summary(&sum, nid, 0, 0);
-	do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, fio);
+	do_write_page(sbi, page, &sum, fio);
 }
 
 void write_data_page(struct page *page, struct dnode_of_data *dn,
-		block_t *new_blkaddr, struct f2fs_io_info *fio)
+				struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct f2fs_summary sum;
@@ -1228,14 +1241,14 @@ void write_data_page(struct page *page, struct dnode_of_data *dn,
 	f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
-
-	do_write_page(sbi, page, dn->data_blkaddr, new_blkaddr, &sum, fio);
+	do_write_page(sbi, page, &sum, fio);
+	dn->data_blkaddr = fio->blk_addr;
 }
 
-void rewrite_data_page(struct page *page, block_t old_blkaddr,
-					struct f2fs_io_info *fio)
+void rewrite_data_page(struct page *page, struct f2fs_io_info *fio)
 {
-	f2fs_submit_page_mbio(F2FS_P_SB(page), page, old_blkaddr, fio);
+	stat_inc_inplace_blocks(F2FS_P_SB(page));
+	f2fs_submit_page_mbio(F2FS_P_SB(page), page, fio);
 }
 
 void recover_data_page(struct f2fs_sb_info *sbi,
@@ -1393,7 +1406,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 		segno = le32_to_cpu(ckpt->cur_data_segno[type]);
 		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type -
 							CURSEG_HOT_DATA]);
-		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+		if (__exist_node_summaries(sbi))
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type);
 		else
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
@@ -1402,7 +1415,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 							CURSEG_HOT_NODE]);
 		blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type -
 							CURSEG_HOT_NODE]);
-		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+		if (__exist_node_summaries(sbi))
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE,
 							type - CURSEG_HOT_NODE);
 		else
@@ -1413,7 +1426,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	sum = (struct f2fs_summary_block *)page_address(new);
 
 	if (IS_NODESEG(type)) {
-		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) {
+		if (__exist_node_summaries(sbi)) {
 			struct f2fs_summary *ns = &sum->entries[0];
 			int i;
 			for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
@@ -1450,12 +1463,22 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 	int err;
 
 	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) {
+		int npages = npages_for_summary_flush(sbi, true);
+
+		if (npages >= 2)
+			ra_meta_pages(sbi, start_sum_block(sbi), npages,
+								META_CP);
+
 		/* restore for compacted data summary */
 		if (read_compacted_summaries(sbi))
 			return -EINVAL;
 		type = CURSEG_HOT_NODE;
 	}
 
+	if (__exist_node_summaries(sbi))
+		ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
+					NR_CURSEG_TYPE - type, META_CP);
+
 	for (; type <= CURSEG_COLD_NODE; type++) {
 		err = read_normal_summaries(sbi, type);
 		if (err)
@@ -1549,8 +1572,7 @@ void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 
 void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 {
-	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG))
-		write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
+	write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
 }
 
 int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
@@ -1754,7 +1776,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			se = get_seg_entry(sbi, segno);
 
 			/* add discard candidates */
-			if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards) {
+			if (cpc->reason != CP_DISCARD) {
 				cpc->trim_start = segno;
 				add_discard_addrs(sbi, cpc);
 			}
@@ -1833,6 +1855,10 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 			return -ENOMEM;
 	}
 
+	sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+	if (!sit_i->tmp_map)
+		return -ENOMEM;
+
 	if (sbi->segs_per_sec > 1) {
 		sit_i->sec_entries = vzalloc(MAIN_SECS(sbi) *
 					sizeof(struct sec_entry));
@@ -1897,7 +1923,7 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
 	free_i->start_segno = GET_SEGNO_FROM_SEG0(sbi, MAIN_BLKADDR(sbi));
 	free_i->free_segments = 0;
 	free_i->free_sections = 0;
-	rwlock_init(&free_i->segmap_lock);
+	spin_lock_init(&free_i->segmap_lock);
 	return 0;
 }
 
@@ -2110,6 +2136,8 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->nr_discards = 0;
 	sm_info->max_discards = 0;
 
+	sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
+
 	INIT_LIST_HEAD(&sm_info->sit_entry_set);
 
 	if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
@@ -2212,6 +2240,8 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 			kfree(sit_i->sentries[start].ckpt_valid_map);
 		}
 	}
+	kfree(sit_i->tmp_map);
+
 	vfree(sit_i->sentries);
 	vfree(sit_i->sec_entries);
 	kfree(sit_i->dirty_sentries_bitmap);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 7f327c0ba4e3..7fd35111cf62 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -189,6 +189,7 @@ struct sit_info {
 	char *sit_bitmap;		/* SIT bitmap pointer */
 	unsigned int bitmap_size;	/* SIT bitmap size */
 
+	unsigned long *tmp_map;			/* bitmap for temporal use */
 	unsigned long *dirty_sentries_bitmap;	/* bitmap for dirty sentries */
 	unsigned int dirty_sentries;		/* # of dirty sentries */
 	unsigned int sents_per_block;		/* # of SIT entries per block */
@@ -207,7 +208,7 @@ struct free_segmap_info {
 	unsigned int start_segno;	/* start segment number logically */
 	unsigned int free_segments;	/* # of free segments */
 	unsigned int free_sections;	/* # of free sections */
-	rwlock_t segmap_lock;		/* free segmap lock */
+	spinlock_t segmap_lock;		/* free segmap lock */
 	unsigned long *free_segmap;	/* free segment bitmap */
 	unsigned long *free_secmap;	/* free section bitmap */
 };
@@ -318,9 +319,9 @@ static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
 		unsigned int max, unsigned int segno)
 {
 	unsigned int ret;
-	read_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	ret = find_next_bit(free_i->free_segmap, max, segno);
-	read_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 	return ret;
 }
 
@@ -331,7 +332,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 	unsigned int start_segno = secno * sbi->segs_per_sec;
 	unsigned int next;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	clear_bit(segno, free_i->free_segmap);
 	free_i->free_segments++;
 
@@ -340,7 +341,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 		clear_bit(secno, free_i->free_secmap);
 		free_i->free_sections++;
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void __set_inuse(struct f2fs_sb_info *sbi,
@@ -362,7 +363,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 	unsigned int start_segno = secno * sbi->segs_per_sec;
 	unsigned int next;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	if (test_and_clear_bit(segno, free_i->free_segmap)) {
 		free_i->free_segments++;
 
@@ -373,7 +374,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 				free_i->free_sections++;
 		}
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
@@ -381,13 +382,13 @@ static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int secno = segno / sbi->segs_per_sec;
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	if (!test_and_set_bit(segno, free_i->free_segmap)) {
 		free_i->free_segments--;
 		if (!test_and_set_bit(secno, free_i->free_secmap))
 			free_i->free_sections--;
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
@@ -460,7 +461,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
 
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		return false;
 
 	return (free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs +
@@ -599,13 +600,13 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
 static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
 {
 	if (segno > TOTAL_SEGS(sbi) - 1)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 
 static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
 {
 	if (blk_addr < SEG0_BLKADDR(sbi) || blk_addr >= MAX_BLKADDR(sbi))
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 
 /*
@@ -616,11 +617,11 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
 {
 	/* check segment usage */
 	if (GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 
 	/* check boundary of a given segment number */
 	if (segno > TOTAL_SEGS(sbi) - 1)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 #endif
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index f71421d70475..f2fe666a6ea9 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -30,6 +30,7 @@
 #include "segment.h"
 #include "xattr.h"
 #include "gc.h"
+#include "trace.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/f2fs.h>
@@ -41,6 +42,7 @@ static struct kset *f2fs_kset;
 enum {
 	Opt_gc_background,
 	Opt_disable_roll_forward,
+	Opt_norecovery,
 	Opt_discard,
 	Opt_noheap,
 	Opt_user_xattr,
@@ -61,6 +63,7 @@ enum {
 static match_table_t f2fs_tokens = {
 	{Opt_gc_background, "background_gc=%s"},
 	{Opt_disable_roll_forward, "disable_roll_forward"},
+	{Opt_norecovery, "norecovery"},
 	{Opt_discard, "discard"},
 	{Opt_noheap, "no_heap"},
 	{Opt_user_xattr, "user_xattr"},
@@ -192,6 +195,7 @@ F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
@@ -207,6 +211,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(gc_idle),
 	ATTR_LIST(reclaim_segments),
 	ATTR_LIST(max_small_discards),
+	ATTR_LIST(batched_trim_sections),
 	ATTR_LIST(ipu_policy),
 	ATTR_LIST(min_ipu_util),
 	ATTR_LIST(min_fsync_blocks),
@@ -286,6 +291,12 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_disable_roll_forward:
 			set_opt(sbi, DISABLE_ROLL_FORWARD);
 			break;
+		case Opt_norecovery:
+			/* this option mounts f2fs with ro */
+			set_opt(sbi, DISABLE_ROLL_FORWARD);
+			if (!f2fs_readonly(sb))
+				return -EINVAL;
+			break;
 		case Opt_discard:
 			set_opt(sbi, DISCARD);
 			break;
@@ -446,8 +457,13 @@ static void f2fs_put_super(struct super_block *sb)
 	f2fs_destroy_stats(sbi);
 	stop_gc_thread(sbi);
 
-	/* We don't need to do checkpoint when it's clean */
-	if (sbi->s_dirty) {
+	/*
+	 * We don't need to do checkpoint when superblock is clean.
+	 * But, the previous checkpoint was not done by umount, it needs to do
+	 * clean checkpoint again.
+	 */
+	if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
+			!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG)) {
 		struct cp_control cpc = {
 			.reason = CP_UMOUNT,
 		};
@@ -486,13 +502,15 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 	if (sync) {
 		struct cp_control cpc;
 
-		cpc.reason = test_opt(sbi, FASTBOOT) ? CP_UMOUNT : CP_SYNC;
+		cpc.reason = __get_cp_reason(sbi);
+
 		mutex_lock(&sbi->gc_mutex);
 		write_checkpoint(sbi, &cpc);
 		mutex_unlock(&sbi->gc_mutex);
 	} else {
 		f2fs_balance_fs(sbi);
 	}
+	f2fs_trace_ios(NULL, NULL, 1);
 
 	return 0;
 }
@@ -887,7 +905,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 		atomic_set(&sbi->nr_pages[i], 0);
 
 	sbi->dir_level = DEF_DIR_LEVEL;
-	sbi->need_fsck = false;
+	clear_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 
 /*
@@ -942,6 +960,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	struct inode *root;
 	long err = -EINVAL;
 	bool retry = true;
+	char *options = NULL;
 	int i;
 
 try_onemore:
@@ -973,9 +992,15 @@ try_onemore:
 	set_opt(sbi, POSIX_ACL);
 #endif
 	/* parse mount options */
-	err = parse_options(sb, (char *)data);
-	if (err)
+	options = kstrdup((const char *)data, GFP_KERNEL);
+	if (data && !options) {
+		err = -ENOMEM;
 		goto free_sb_buf;
+	}
+
+	err = parse_options(sb, options);
+	if (err)
+		goto free_options;
 
 	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
 	sb->s_max_links = F2FS_LINK_MAX;
@@ -998,7 +1023,7 @@ try_onemore:
 	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
 	init_rwsem(&sbi->node_write);
-	sbi->por_doing = false;
+	clear_sbi_flag(sbi, SBI_POR_DOING);
 	spin_lock_init(&sbi->stat_lock);
 
 	init_rwsem(&sbi->read_io.io_rwsem);
@@ -1019,7 +1044,7 @@ try_onemore:
 	if (IS_ERR(sbi->meta_inode)) {
 		f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
 		err = PTR_ERR(sbi->meta_inode);
-		goto free_sb_buf;
+		goto free_options;
 	}
 
 	err = get_valid_checkpoint(sbi);
@@ -1122,10 +1147,19 @@ try_onemore:
 		goto free_proc;
 
 	if (!retry)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 
 	/* recover fsynced data */
 	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
+		/*
+		 * mount should be failed, when device has readonly mode, and
+		 * previous checkpoint was not done by clean system shutdown.
+		 */
+		if (bdev_read_only(sb->s_bdev) &&
+				!is_set_ckpt_flags(sbi->ckpt, CP_UMOUNT_FLAG)) {
+			err = -EROFS;
+			goto free_kobj;
+		}
 		err = recover_fsync_data(sbi);
 		if (err) {
 			f2fs_msg(sb, KERN_ERR,
@@ -1144,6 +1178,7 @@ try_onemore:
 		if (err)
 			goto free_kobj;
 	}
+	kfree(options);
 	return 0;
 
 free_kobj:
@@ -1168,6 +1203,8 @@ free_cp:
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
 	iput(sbi->meta_inode);
+free_options:
+	kfree(options);
 free_sb_buf:
 	brelse(raw_super_buf);
 free_sbi:
@@ -1188,11 +1225,18 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
 	return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super);
 }
 
+static void kill_f2fs_super(struct super_block *sb)
+{
+	if (sb->s_root)
+		set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
+	kill_block_super(sb);
+}
+
 static struct file_system_type f2fs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "f2fs",
 	.mount		= f2fs_mount,
-	.kill_sb	= kill_block_super,
+	.kill_sb	= kill_f2fs_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
 MODULE_ALIAS_FS("f2fs");
@@ -1220,6 +1264,8 @@ static int __init init_f2fs_fs(void)
 {
 	int err;
 
+	f2fs_build_trace_ios();
+
 	err = init_inodecache();
 	if (err)
 		goto fail;
@@ -1229,12 +1275,9 @@ static int __init init_f2fs_fs(void)
 	err = create_segment_manager_caches();
 	if (err)
 		goto free_node_manager_caches;
-	err = create_gc_caches();
-	if (err)
-		goto free_segment_manager_caches;
 	err = create_checkpoint_caches();
 	if (err)
-		goto free_gc_caches;
+		goto free_segment_manager_caches;
 	f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
 	if (!f2fs_kset) {
 		err = -ENOMEM;
@@ -1251,8 +1294,6 @@ free_kset:
 	kset_unregister(f2fs_kset);
 free_checkpoint_caches:
 	destroy_checkpoint_caches();
-free_gc_caches:
-	destroy_gc_caches();
 free_segment_manager_caches:
 	destroy_segment_manager_caches();
 free_node_manager_caches:
@@ -1269,11 +1310,11 @@ static void __exit exit_f2fs_fs(void)
 	f2fs_destroy_root_stats();
 	unregister_filesystem(&f2fs_fs_type);
 	destroy_checkpoint_caches();
-	destroy_gc_caches();
 	destroy_segment_manager_caches();
 	destroy_node_manager_caches();
 	destroy_inodecache();
 	kset_unregister(f2fs_kset);
+	f2fs_destroy_trace_ios();
 }
 
 module_init(init_f2fs_fs)
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
new file mode 100644
index 000000000000..875aa8179bc1
--- /dev/null
+++ b/fs/f2fs/trace.c
@@ -0,0 +1,159 @@
+/*
+ * f2fs IO tracer
+ *
+ * Copyright (c) 2014 Motorola Mobility
+ * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/sched.h>
+#include <linux/radix-tree.h>
+
+#include "f2fs.h"
+#include "trace.h"
+
+static RADIX_TREE(pids, GFP_ATOMIC);
+static spinlock_t pids_lock;
+static struct last_io_info last_io;
+
+static inline void __print_last_io(void)
+{
+	if (!last_io.len)
+		return;
+
+	trace_printk("%3x:%3x %4x %-16s %2x %5x %12x %4x\n",
+			last_io.major, last_io.minor,
+			last_io.pid, "----------------",
+			last_io.type,
+			last_io.fio.rw, last_io.fio.blk_addr,
+			last_io.len);
+	memset(&last_io, 0, sizeof(last_io));
+}
+
+static int __file_type(struct inode *inode, pid_t pid)
+{
+	if (f2fs_is_atomic_file(inode))
+		return __ATOMIC_FILE;
+	else if (f2fs_is_volatile_file(inode))
+		return __VOLATILE_FILE;
+	else if (S_ISDIR(inode->i_mode))
+		return __DIR_FILE;
+	else if (inode->i_ino == F2FS_NODE_INO(F2FS_I_SB(inode)))
+		return __NODE_FILE;
+	else if (inode->i_ino == F2FS_META_INO(F2FS_I_SB(inode)))
+		return __META_FILE;
+	else if (pid)
+		return __NORMAL_FILE;
+	else
+		return __MISC_FILE;
+}
+
+void f2fs_trace_pid(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	pid_t pid = task_pid_nr(current);
+	void *p;
+
+	page->private = pid;
+
+	if (radix_tree_preload(GFP_NOFS))
+		return;
+
+	spin_lock(&pids_lock);
+	p = radix_tree_lookup(&pids, pid);
+	if (p == current)
+		goto out;
+	if (p)
+		radix_tree_delete(&pids, pid);
+
+	f2fs_radix_tree_insert(&pids, pid, current);
+
+	trace_printk("%3x:%3x %4x %-16s\n",
+			MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
+			pid, current->comm);
+out:
+	spin_unlock(&pids_lock);
+	radix_tree_preload_end();
+}
+
+void f2fs_trace_ios(struct page *page, struct f2fs_io_info *fio, int flush)
+{
+	struct inode *inode;
+	pid_t pid;
+	int major, minor;
+
+	if (flush) {
+		__print_last_io();
+		return;
+	}
+
+	inode = page->mapping->host;
+	pid = page_private(page);
+
+	major = MAJOR(inode->i_sb->s_dev);
+	minor = MINOR(inode->i_sb->s_dev);
+
+	if (last_io.major == major && last_io.minor == minor &&
+			last_io.pid == pid &&
+			last_io.type == __file_type(inode, pid) &&
+			last_io.fio.rw == fio->rw &&
+			last_io.fio.blk_addr + last_io.len == fio->blk_addr) {
+		last_io.len++;
+		return;
+	}
+
+	__print_last_io();
+
+	last_io.major = major;
+	last_io.minor = minor;
+	last_io.pid = pid;
+	last_io.type = __file_type(inode, pid);
+	last_io.fio = *fio;
+	last_io.len = 1;
+	return;
+}
+
+void f2fs_build_trace_ios(void)
+{
+	spin_lock_init(&pids_lock);
+}
+
+#define PIDVEC_SIZE	128
+static unsigned int gang_lookup_pids(pid_t *results, unsigned long first_index,
+							unsigned int max_items)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
+
+	if (unlikely(!max_items))
+		return 0;
+
+	radix_tree_for_each_slot(slot, &pids, &iter, first_index) {
+		results[ret] = iter.index;
+		if (++ret == PIDVEC_SIZE)
+			break;
+	}
+	return ret;
+}
+
+void f2fs_destroy_trace_ios(void)
+{
+	pid_t pid[PIDVEC_SIZE];
+	pid_t next_pid = 0;
+	unsigned int found;
+
+	spin_lock(&pids_lock);
+	while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) {
+		unsigned idx;
+
+		next_pid = pid[found - 1] + 1;
+		for (idx = 0; idx < found; idx++)
+			radix_tree_delete(&pids, pid[idx]);
+	}
+	spin_unlock(&pids_lock);
+}
diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h
new file mode 100644
index 000000000000..1041dbeb52ae
--- /dev/null
+++ b/fs/f2fs/trace.h
@@ -0,0 +1,46 @@
+/*
+ * f2fs IO tracer
+ *
+ * Copyright (c) 2014 Motorola Mobility
+ * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __F2FS_TRACE_H__
+#define __F2FS_TRACE_H__
+
+#ifdef CONFIG_F2FS_IO_TRACE
+#include <trace/events/f2fs.h>
+
+enum file_type {
+	__NORMAL_FILE,
+	__DIR_FILE,
+	__NODE_FILE,
+	__META_FILE,
+	__ATOMIC_FILE,
+	__VOLATILE_FILE,
+	__MISC_FILE,
+};
+
+struct last_io_info {
+	int major, minor;
+	pid_t pid;
+	enum file_type type;
+	struct f2fs_io_info fio;
+	block_t len;
+};
+
+extern void f2fs_trace_pid(struct page *);
+extern void f2fs_trace_ios(struct page *, struct f2fs_io_info *, int);
+extern void f2fs_build_trace_ios(void);
+extern void f2fs_destroy_trace_ios(void);
+#else
+#define f2fs_trace_pid(p)
+#define f2fs_trace_ios(p, i, n)
+#define f2fs_build_trace_ios()
+#define f2fs_destroy_trace_ios()
+
+#endif
+#endif /* __F2FS_TRACE_H__ */
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 7b41a2dcdd76..497c7c5263c7 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -580,7 +580,7 @@ static void fat_set_state(struct super_block *sb,
 {
 	struct buffer_head *bh;
 	struct fat_boot_sector *b;
-	struct msdos_sb_info *sbi = sb->s_fs_info;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 
 	/* do not change any thing if mounted read only */
 	if ((sb->s_flags & MS_RDONLY) && !force)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 2d609a5fbfea..e907052eeadb 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -66,15 +66,21 @@ int writeback_in_progress(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(writeback_in_progress);
 
-static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
+struct backing_dev_info *inode_to_bdi(struct inode *inode)
 {
-	struct super_block *sb = inode->i_sb;
+	struct super_block *sb;
 
-	if (sb_is_blkdev_sb(sb))
-		return inode->i_mapping->backing_dev_info;
+	if (!inode)
+		return &noop_backing_dev_info;
 
+	sb = inode->i_sb;
+#ifdef CONFIG_BLOCK
+	if (sb_is_blkdev_sb(sb))
+		return blk_get_backing_dev_info(I_BDEV(inode));
+#endif
 	return sb->s_bdi;
 }
+EXPORT_SYMBOL_GPL(inode_to_bdi);
 
 static inline struct inode *wb_inode(struct list_head *head)
 {
@@ -247,14 +253,19 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 	return ret;
 }
 
+#define EXPIRE_DIRTY_ATIME 0x0001
+
 /*
  * Move expired (dirtied before work->older_than_this) dirty inodes from
  * @delaying_queue to @dispatch_queue.
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
+			       int flags,
 			       struct wb_writeback_work *work)
 {
+	unsigned long *older_than_this = NULL;
+	unsigned long expire_time;
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
 	struct super_block *sb = NULL;
@@ -262,13 +273,21 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 	int moved = 0;
 
+	if ((flags & EXPIRE_DIRTY_ATIME) == 0)
+		older_than_this = work->older_than_this;
+	else if ((work->reason == WB_REASON_SYNC) == 0) {
+		expire_time = jiffies - (HZ * 86400);
+		older_than_this = &expire_time;
+	}
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (work->older_than_this &&
-		    inode_dirtied_after(inode, *work->older_than_this))
+		if (older_than_this &&
+		    inode_dirtied_after(inode, *older_than_this))
 			break;
 		list_move(&inode->i_wb_list, &tmp);
 		moved++;
+		if (flags & EXPIRE_DIRTY_ATIME)
+			set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
 		if (sb_is_blkdev_sb(inode->i_sb))
 			continue;
 		if (sb && sb != inode->i_sb)
@@ -309,9 +328,12 @@ out:
 static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
 {
 	int moved;
+
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, work);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work);
+	moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
+				     EXPIRE_DIRTY_ATIME, work);
 	trace_writeback_queue_io(wb, work, moved);
 }
 
@@ -435,6 +457,8 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 * updates after data IO completion.
 		 */
 		redirty_tail(inode, wb);
+	} else if (inode->i_state & I_DIRTY_TIME) {
+		list_move(&inode->i_wb_list, &wb->b_dirty_time);
 	} else {
 		/* The inode is clean. Remove from writeback lists. */
 		list_del_init(&inode->i_wb_list);
@@ -481,7 +505,13 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	spin_lock(&inode->i_lock);
 
 	dirty = inode->i_state & I_DIRTY;
-	inode->i_state &= ~I_DIRTY;
+	if (((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) &&
+	     (inode->i_state & I_DIRTY_TIME)) ||
+	    (inode->i_state & I_DIRTY_TIME_EXPIRED)) {
+		dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
+		trace_writeback_lazytime(inode);
+	}
+	inode->i_state &= ~dirty;
 
 	/*
 	 * Paired with smp_mb() in __mark_inode_dirty().  This allows
@@ -501,8 +531,10 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 
 	spin_unlock(&inode->i_lock);
 
+	if (dirty & I_DIRTY_TIME)
+		mark_inode_dirty_sync(inode);
 	/* Don't write the inode if only I_DIRTY_PAGES was set */
-	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+	if (dirty & ~I_DIRTY_PAGES) {
 		int err = write_inode(inode, wbc);
 		if (ret == 0)
 			ret = err;
@@ -550,7 +582,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	 * make sure inode is on some writeback list and leave it there unless
 	 * we have completely cleaned the inode.
 	 */
-	if (!(inode->i_state & I_DIRTY) &&
+	if (!(inode->i_state & I_DIRTY_ALL) &&
 	    (wbc->sync_mode != WB_SYNC_ALL ||
 	     !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
 		goto out;
@@ -565,7 +597,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	 * If inode is clean, remove it from writeback lists. Otherwise don't
 	 * touch it. See comment above for explanation.
 	 */
-	if (!(inode->i_state & I_DIRTY))
+	if (!(inode->i_state & I_DIRTY_ALL))
 		list_del_init(&inode->i_wb_list);
 	spin_unlock(&wb->list_lock);
 	inode_sync_complete(inode);
@@ -707,7 +739,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		wrote += write_chunk - wbc.nr_to_write;
 		spin_lock(&wb->list_lock);
 		spin_lock(&inode->i_lock);
-		if (!(inode->i_state & I_DIRTY))
+		if (!(inode->i_state & I_DIRTY_ALL))
 			wrote++;
 		requeue_inode(inode, wb, &wbc);
 		inode_sync_complete(inode);
@@ -737,9 +769,9 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb,
 		struct inode *inode = wb_inode(wb->b_io.prev);
 		struct super_block *sb = inode->i_sb;
 
-		if (!grab_super_passive(sb)) {
+		if (!trylock_super(sb)) {
 			/*
-			 * grab_super_passive() may fail consistently due to
+			 * trylock_super() may fail consistently due to
 			 * s_umount being grabbed by someone else. Don't use
 			 * requeue_io() to avoid busy retrying the inode/sb.
 			 */
@@ -747,7 +779,7 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb,
 			continue;
 		}
 		wrote += writeback_sb_inodes(sb, wb, work);
-		drop_super(sb);
+		up_read(&sb->s_umount);
 
 		/* refer to the same tests at the end of writeback_sb_inodes */
 		if (wrote) {
@@ -1145,16 +1177,20 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
  * page->mapping->host, so the page-dirtying time is recorded in the internal
  * blockdev inode.
  */
+#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 void __mark_inode_dirty(struct inode *inode, int flags)
 {
 	struct super_block *sb = inode->i_sb;
 	struct backing_dev_info *bdi = NULL;
+	int dirtytime;
+
+	trace_writeback_mark_inode_dirty(inode, flags);
 
 	/*
 	 * Don't do this for I_DIRTY_PAGES - that doesn't actually
 	 * dirty the inode itself
 	 */
-	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_TIME)) {
 		trace_writeback_dirty_inode_start(inode, flags);
 
 		if (sb->s_op->dirty_inode)
@@ -1162,6 +1198,9 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 
 		trace_writeback_dirty_inode(inode, flags);
 	}
+	if (flags & I_DIRTY_INODE)
+		flags &= ~I_DIRTY_TIME;
+	dirtytime = flags & I_DIRTY_TIME;
 
 	/*
 	 * Paired with smp_mb() in __writeback_single_inode() for the
@@ -1169,16 +1208,21 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	 */
 	smp_mb();
 
-	if ((inode->i_state & flags) == flags)
+	if (((inode->i_state & flags) == flags) ||
+	    (dirtytime && (inode->i_state & I_DIRTY_INODE)))
 		return;
 
 	if (unlikely(block_dump))
 		block_dump___mark_inode_dirty(inode);
 
 	spin_lock(&inode->i_lock);
+	if (dirtytime && (inode->i_state & I_DIRTY_INODE))
+		goto out_unlock_inode;
 	if ((inode->i_state & flags) != flags) {
 		const int was_dirty = inode->i_state & I_DIRTY;
 
+		if (flags & I_DIRTY_INODE)
+			inode->i_state &= ~I_DIRTY_TIME;
 		inode->i_state |= flags;
 
 		/*
@@ -1225,8 +1269,10 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			}
 
 			inode->dirtied_when = jiffies;
-			list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
+			list_move(&inode->i_wb_list, dirtytime ?
+				  &bdi->wb.b_dirty_time : &bdi->wb.b_dirty);
 			spin_unlock(&bdi->wb.list_lock);
+			trace_writeback_dirty_inode_enqueue(inode);
 
 			if (wakeup_bdi)
 				bdi_wakeup_thread_delayed(bdi);
diff --git a/fs/fs_pin.c b/fs/fs_pin.c
index 9368236ca100..b06c98796afb 100644
--- a/fs/fs_pin.c
+++ b/fs/fs_pin.c
@@ -1,78 +1,102 @@
 #include <linux/fs.h>
+#include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/fs_pin.h>
 #include "internal.h"
 #include "mount.h"
 
-static void pin_free_rcu(struct rcu_head *head)
-{
-	kfree(container_of(head, struct fs_pin, rcu));
-}
-
 static DEFINE_SPINLOCK(pin_lock);
 
-void pin_put(struct fs_pin *p)
-{
-	if (atomic_long_dec_and_test(&p->count))
-		call_rcu(&p->rcu, pin_free_rcu);
-}
-
 void pin_remove(struct fs_pin *pin)
 {
 	spin_lock(&pin_lock);
 	hlist_del(&pin->m_list);
 	hlist_del(&pin->s_list);
 	spin_unlock(&pin_lock);
+	spin_lock_irq(&pin->wait.lock);
+	pin->done = 1;
+	wake_up_locked(&pin->wait);
+	spin_unlock_irq(&pin->wait.lock);
 }
 
-void pin_insert(struct fs_pin *pin, struct vfsmount *m)
+void pin_insert_group(struct fs_pin *pin, struct vfsmount *m, struct hlist_head *p)
 {
 	spin_lock(&pin_lock);
-	hlist_add_head(&pin->s_list, &m->mnt_sb->s_pins);
+	if (p)
+		hlist_add_head(&pin->s_list, p);
 	hlist_add_head(&pin->m_list, &real_mount(m)->mnt_pins);
 	spin_unlock(&pin_lock);
 }
 
+void pin_insert(struct fs_pin *pin, struct vfsmount *m)
+{
+	pin_insert_group(pin, m, &m->mnt_sb->s_pins);
+}
+
+void pin_kill(struct fs_pin *p)
+{
+	wait_queue_t wait;
+
+	if (!p) {
+		rcu_read_unlock();
+		return;
+	}
+	init_wait(&wait);
+	spin_lock_irq(&p->wait.lock);
+	if (likely(!p->done)) {
+		p->done = -1;
+		spin_unlock_irq(&p->wait.lock);
+		rcu_read_unlock();
+		p->kill(p);
+		return;
+	}
+	if (p->done > 0) {
+		spin_unlock_irq(&p->wait.lock);
+		rcu_read_unlock();
+		return;
+	}
+	__add_wait_queue(&p->wait, &wait);
+	while (1) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		spin_unlock_irq(&p->wait.lock);
+		rcu_read_unlock();
+		schedule();
+		rcu_read_lock();
+		if (likely(list_empty(&wait.task_list)))
+			break;
+		/* OK, we know p couldn't have been freed yet */
+		spin_lock_irq(&p->wait.lock);
+		if (p->done > 0) {
+			spin_unlock_irq(&p->wait.lock);
+			break;
+		}
+	}
+	rcu_read_unlock();
+}
+
 void mnt_pin_kill(struct mount *m)
 {
 	while (1) {
 		struct hlist_node *p;
-		struct fs_pin *pin;
 		rcu_read_lock();
 		p = ACCESS_ONCE(m->mnt_pins.first);
 		if (!p) {
 			rcu_read_unlock();
 			break;
 		}
-		pin = hlist_entry(p, struct fs_pin, m_list);
-		if (!atomic_long_inc_not_zero(&pin->count)) {
-			rcu_read_unlock();
-			cpu_relax();
-			continue;
-		}
-		rcu_read_unlock();
-		pin->kill(pin);
+		pin_kill(hlist_entry(p, struct fs_pin, m_list));
 	}
 }
 
-void sb_pin_kill(struct super_block *sb)
+void group_pin_kill(struct hlist_head *p)
 {
 	while (1) {
-		struct hlist_node *p;
-		struct fs_pin *pin;
+		struct hlist_node *q;
 		rcu_read_lock();
-		p = ACCESS_ONCE(sb->s_pins.first);
-		if (!p) {
+		q = ACCESS_ONCE(p->first);
+		if (!q) {
 			rcu_read_unlock();
 			break;
 		}
-		pin = hlist_entry(p, struct fs_pin, s_list);
-		if (!atomic_long_inc_not_zero(&pin->count)) {
-			rcu_read_unlock();
-			cpu_relax();
-			continue;
-		}
-		rcu_read_unlock();
-		pin->kill(pin);
+		pin_kill(hlist_entry(q, struct fs_pin, s_list));
 	}
 }
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ed19a7d622fa..39706c57ad3c 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -890,8 +890,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 
 	newpage = buf->page;
 
-	if (WARN_ON(!PageUptodate(newpage)))
-		return -EIO;
+	if (!PageUptodate(newpage))
+		SetPageUptodate(newpage);
 
 	ClearPageMappedToDisk(newpage);
 
@@ -1353,6 +1353,17 @@ static ssize_t fuse_dev_do_read(struct fuse_conn *fc, struct file *file,
 	return err;
 }
 
+static int fuse_dev_open(struct inode *inode, struct file *file)
+{
+	/*
+	 * The fuse device's file's private_data is used to hold
+	 * the fuse_conn(ection) when it is mounted, and is used to
+	 * keep track of whether the file has been mounted already.
+	 */
+	file->private_data = NULL;
+	return 0;
+}
+
 static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov,
 			      unsigned long nr_segs, loff_t pos)
 {
@@ -1797,6 +1808,9 @@ copy_finish:
 static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 		       unsigned int size, struct fuse_copy_state *cs)
 {
+	/* Don't try to move pages (yet) */
+	cs->move_pages = 0;
+
 	switch (code) {
 	case FUSE_NOTIFY_POLL:
 		return fuse_notify_poll(fc, size, cs);
@@ -2217,6 +2231,7 @@ static int fuse_dev_fasync(int fd, struct file *file, int on)
 
 const struct file_operations fuse_dev_operations = {
 	.owner		= THIS_MODULE,
+	.open		= fuse_dev_open,
 	.llseek		= no_llseek,
 	.read		= do_sync_read,
 	.aio_read	= fuse_dev_read,
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 08e7b1a9d5d0..1545b711ddcf 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -971,7 +971,7 @@ int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
 			err = -EBUSY;
 			goto badentry;
 		}
-		if (S_ISDIR(entry->d_inode->i_mode)) {
+		if (d_is_dir(entry)) {
 			shrink_dcache_parent(entry);
 			if (!simple_empty(entry)) {
 				err = -ENOTEMPTY;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 760b2c552197..c01ec3bdcfd8 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1159,7 +1159,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	mutex_lock(&inode->i_mutex);
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
@@ -1464,7 +1464,7 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
 {
 	struct inode *inode = req->inode;
 	struct fuse_inode *fi = get_fuse_inode(inode);
-	struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(inode);
 	int i;
 
 	list_del(&req->writepages_entry);
@@ -1658,7 +1658,7 @@ static int fuse_writepage_locked(struct page *page)
 	req->end = fuse_writepage_end;
 	req->inode = inode;
 
-	inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK);
+	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	spin_lock(&fc->lock);
@@ -1768,7 +1768,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
 
 	if (old_req->num_pages == 1 && (old_req->state == FUSE_REQ_INIT ||
 					old_req->state == FUSE_REQ_PENDING)) {
-		struct backing_dev_info *bdi = page->mapping->backing_dev_info;
+		struct backing_dev_info *bdi = inode_to_bdi(page->mapping->host);
 
 		copy_highpage(old_req->pages[0], page);
 		spin_unlock(&fc->lock);
@@ -1872,7 +1872,7 @@ static int fuse_writepages_fill(struct page *page,
 	req->page_descs[req->num_pages].offset = 0;
 	req->page_descs[req->num_pages].length = PAGE_SIZE;
 
-	inc_bdi_stat(page->mapping->backing_dev_info, BDI_WRITEBACK);
+	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;
@@ -2062,7 +2062,6 @@ static const struct vm_operations_struct fuse_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= fuse_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f38256e4476e..e8799c11424b 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -308,7 +308,6 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 		if (!fc->writeback_cache || !S_ISREG(attr->mode))
 			inode->i_flags |= S_NOCMTIME;
 		inode->i_generation = generation;
-		inode->i_data.backing_dev_info = &fc->bdi;
 		fuse_init_inode(inode, attr);
 		unlock_new_inode(inode);
 	} else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 3088e2a38e30..7b3143064af1 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -73,7 +73,7 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 
 	BUG_ON(name == NULL);
 
-	if (acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode)))
+	if (acl && acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode)))
 		return -E2BIG;
 
 	if (type == ACL_TYPE_ACCESS) {
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 805b37fed638..4ad4f94edebe 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -289,7 +289,7 @@ continue_unlock:
 		if (!clear_page_dirty_for_io(page))
 			goto continue_unlock;
 
-		trace_wbc_writepage(wbc, mapping->backing_dev_info);
+		trace_wbc_writepage(wbc, inode_to_bdi(inode));
 
 		ret = __gfs2_jdata_writepage(page, wbc);
 		if (unlikely(ret)) {
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index c5a34f09e228..487527b42d94 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1809,7 +1809,7 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry)
 		gfs2_consist_inode(dip);
 	dip->i_entries--;
 	dip->i_inode.i_mtime = dip->i_inode.i_ctime = tv;
-	if (S_ISDIR(dentry->d_inode->i_mode))
+	if (d_is_dir(dentry))
 		drop_nlink(&dip->i_inode);
 	mark_inode_dirty(&dip->i_inode);
 
@@ -1896,7 +1896,8 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
 
 	ht = kzalloc(size, GFP_NOFS | __GFP_NOWARN);
 	if (ht == NULL)
-		ht = vzalloc(size);
+		ht = __vmalloc(size, GFP_NOFS | __GFP_NOWARN | __GFP_ZERO,
+			       PAGE_KERNEL);
 	if (!ht)
 		return -ENOMEM;
 
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 6e600abf694a..3e32bb8e2d7e 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -498,7 +498,6 @@ static const struct vm_operations_struct gfs2_vm_ops = {
 	.fault = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = gfs2_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 /**
@@ -655,7 +654,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 {
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
-	int sync_state = inode->i_state & I_DIRTY;
+	int sync_state = inode->i_state & I_DIRTY_ALL;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	int ret = 0, ret1 = 0;
 
@@ -668,7 +667,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 	if (!gfs2_is_jdata(ip))
 		sync_state &= ~I_DIRTY_PAGES;
 	if (datasync)
-		sync_state &= ~I_DIRTY_SYNC;
+		sync_state &= ~(I_DIRTY_SYNC | I_DIRTY_TIME);
 
 	if (sync_state) {
 		ret = sync_inode_metadata(inode, 1);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index a23524aa3eac..f42dffba056a 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -173,19 +173,14 @@ void gfs2_glock_add_to_lru(struct gfs2_glock *gl)
 	spin_unlock(&lru_lock);
 }
 
-static void __gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
+static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
 {
+	spin_lock(&lru_lock);
 	if (!list_empty(&gl->gl_lru)) {
 		list_del_init(&gl->gl_lru);
 		atomic_dec(&lru_count);
 		clear_bit(GLF_LRU, &gl->gl_flags);
 	}
-}
-
-static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
-{
-	spin_lock(&lru_lock);
-	__gfs2_glock_remove_from_lru(gl);
 	spin_unlock(&lru_lock);
 }
 
@@ -205,9 +200,7 @@ void gfs2_glock_put(struct gfs2_glock *gl)
 
 	lockref_mark_dead(&gl->gl_lockref);
 
-	spin_lock(&lru_lock);
-	__gfs2_glock_remove_from_lru(gl);
-	spin_unlock(&lru_lock);
+	gfs2_glock_remove_from_lru(gl);
 	spin_unlock(&gl->gl_lockref.lock);
 	spin_lock_bucket(gl->gl_hash);
 	hlist_bl_del_rcu(&gl->gl_list);
@@ -775,7 +768,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		mapping->flags = 0;
 		mapping_set_gfp_mask(mapping, GFP_NOFS);
 		mapping->private_data = NULL;
-		mapping->backing_dev_info = s->s_bdi;
 		mapping->writeback_index = 0;
 	}
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 9054002ebe70..73c72253faac 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -543,10 +543,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
 	}
 
 	error = gfs2_dir_add(&dip->i_inode, name, ip, da);
-	if (error)
-		goto fail_end_trans;
 
-fail_end_trans:
 	gfs2_trans_end(sdp);
 fail_ipreserv:
 	gfs2_inplace_release(dip);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 8633ad328ee2..efc8e254787c 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -112,7 +112,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
 	mapping->private_data = NULL;
-	mapping->backing_dev_info = sb->s_bdi;
 	mapping->writeback_index = 0;
 
 	spin_lock_init(&sdp->sd_log_lock);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 3e193cb36996..3aa17d4d1cfc 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -145,7 +145,8 @@ static void gfs2_qd_dispose(struct list_head *list)
 }
 
 
-static enum lru_status gfs2_qd_isolate(struct list_head *item, spinlock_t *lock, void *arg)
+static enum lru_status gfs2_qd_isolate(struct list_head *item,
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *dispose = arg;
 	struct gfs2_quota_data *qd = list_entry(item, struct gfs2_quota_data, qd_lru);
@@ -155,7 +156,7 @@ static enum lru_status gfs2_qd_isolate(struct list_head *item, spinlock_t *lock,
 
 	if (qd->qd_lockref.count == 0) {
 		lockref_mark_dead(&qd->qd_lockref);
-		list_move(&qd->qd_lru, dispose);
+		list_lru_isolate_move(lru, &qd->qd_lru, dispose);
 	}
 
 	spin_unlock(&qd->qd_lockref.lock);
@@ -171,8 +172,8 @@ static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
 	if (!(sc->gfp_mask & __GFP_FS))
 		return SHRINK_STOP;
 
-	freed = list_lru_walk_node(&gfs2_qd_lru, sc->nid, gfs2_qd_isolate,
-				   &dispose, &sc->nr_to_scan);
+	freed = list_lru_shrink_walk(&gfs2_qd_lru, sc,
+				     gfs2_qd_isolate, &dispose);
 
 	gfs2_qd_dispose(&dispose);
 
@@ -182,7 +183,7 @@ static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
 static unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
 					  struct shrink_control *sc)
 {
-	return vfs_pressure_ratio(list_lru_count_node(&gfs2_qd_lru, sc->nid));
+	return vfs_pressure_ratio(list_lru_shrink_count(&gfs2_qd_lru, sc));
 }
 
 struct shrinker gfs2_qd_shrinker = {
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 573bd3b758fa..1b645773c98e 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -439,7 +439,7 @@ static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
 
         ls->ls_recover_jid_done = jid;
         ls->ls_recover_jid_status = message;
-	sprintf(env_jid, "JID=%d", jid);
+	sprintf(env_jid, "JID=%u", jid);
 	sprintf(env_status, "RECOVERY=%s",
 		message == LM_RD_SUCCESS ? "Done" : "Failed");
         kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 5b327f837de7..1666382b198d 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -743,7 +743,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
-	struct backing_dev_info *bdi = metamapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(metamapping->host);
 	int ret = 0;
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 3ab566ba5696..ae8e8811f0e8 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -96,7 +96,7 @@ static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf)
 	struct super_block *sb = sdp->sd_vfs;
 	int frozen = (sb->s_writers.frozen == SB_UNFROZEN) ? 0 : 1;
 
-	return snprintf(buf, PAGE_SIZE, "%u\n", frozen);
+	return snprintf(buf, PAGE_SIZE, "%d\n", frozen);
 }
 
 static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 435bea231cc6..f0235c1640af 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -530,7 +530,7 @@ static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	/* Unlink destination if it already exists */
 	if (new_dentry->d_inode) {
-		if (S_ISDIR(new_dentry->d_inode->i_mode))
+		if (d_is_dir(new_dentry))
 			res = hfsplus_rmdir(new_dir, new_dentry);
 		else
 			res = hfsplus_unlink(new_dir, new_dentry);
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index 5f2755117ce7..043ac9d77262 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -678,10 +678,10 @@ static struct inode *get_inode(struct super_block *sb, struct dentry *dentry)
 		return NULL;
 	}
 
-	if (S_ISDIR(dentry->d_inode->i_mode)) {
+	if (d_is_dir(dentry)) {
 		inode->i_op = &hppfs_dir_iops;
 		inode->i_fop = &hppfs_dir_fops;
-	} else if (S_ISLNK(dentry->d_inode->i_mode)) {
+	} else if (d_is_symlink(dentry)) {
 		inode->i_op = &hppfs_link_iops;
 		inode->i_fop = &hppfs_file_fops;
 	} else {
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 5eba47f593f8..c274aca8e8dc 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -62,12 +62,6 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
 	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
 }
 
-static struct backing_dev_info hugetlbfs_backing_dev_info = {
-	.name		= "hugetlbfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
 int sysctl_hugetlb_shm_group;
 
 enum {
@@ -498,7 +492,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
-		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inode->i_mapping->private_data = resv_map;
 		info = HUGETLBFS_I(inode);
@@ -1032,10 +1025,6 @@ static int __init init_hugetlbfs_fs(void)
 		return -ENOTSUPP;
 	}
 
-	error = bdi_init(&hugetlbfs_backing_dev_info);
-	if (error)
-		return error;
-
 	error = -ENOMEM;
 	hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
 					sizeof(struct hugetlbfs_inode_info),
@@ -1071,7 +1060,6 @@ static int __init init_hugetlbfs_fs(void)
  out:
 	kmem_cache_destroy(hugetlbfs_inode_cachep);
  out2:
-	bdi_destroy(&hugetlbfs_backing_dev_info);
 	return error;
 }
 
@@ -1091,7 +1079,6 @@ static void __exit exit_hugetlbfs_fs(void)
 	for_each_hstate(h)
 		kern_unmount(hugetlbfs_vfsmount[i++]);
 	unregister_filesystem(&hugetlbfs_fs_type);
-	bdi_destroy(&hugetlbfs_backing_dev_info);
 }
 
 module_init(init_hugetlbfs_fs)
diff --git a/fs/inode.c b/fs/inode.c
index aa149e7262ac..f00b16f45507 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -18,6 +18,7 @@
 #include <linux/buffer_head.h> /* for inode_has_buffers */
 #include <linux/ratelimit.h>
 #include <linux/list_lru.h>
+#include <trace/events/writeback.h>
 #include "internal.h"
 
 /*
@@ -30,7 +31,7 @@
  * inode_sb_list_lock protects:
  *   sb->s_inodes, inode->i_sb_list
  * bdi->wb.list_lock protects:
- *   bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list
+ *   bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_wb_list
  * inode_hash_lock protects:
  *   inode_hashtable, inode->i_hash
  *
@@ -170,20 +171,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	atomic_set(&mapping->i_mmap_writable, 0);
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
 	mapping->private_data = NULL;
-	mapping->backing_dev_info = &default_backing_dev_info;
 	mapping->writeback_index = 0;
-
-	/*
-	 * If the block_device provides a backing_dev_info for client
-	 * inodes then use that.  Otherwise the inode share the bdev's
-	 * backing_dev_info.
-	 */
-	if (sb->s_bdev) {
-		struct backing_dev_info *bdi;
-
-		bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
-		mapping->backing_dev_info = bdi;
-	}
 	inode->i_private = NULL;
 	inode->i_mapping = mapping;
 	INIT_HLIST_HEAD(&inode->i_dentry);	/* buggered by rcu freeing */
@@ -194,7 +182,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 #ifdef CONFIG_FSNOTIFY
 	inode->i_fsnotify_mask = 0;
 #endif
-
+	inode->i_flctx = NULL;
 	this_cpu_inc(nr_inodes);
 
 	return 0;
@@ -237,6 +225,7 @@ void __destroy_inode(struct inode *inode)
 	BUG_ON(inode_has_buffers(inode));
 	security_inode_free(inode);
 	fsnotify_inode_delete(inode);
+	locks_free_lock_context(inode->i_flctx);
 	if (!inode->i_nlink) {
 		WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0);
 		atomic_long_dec(&inode->i_sb->s_remove_count);
@@ -355,7 +344,6 @@ void address_space_init_once(struct address_space *mapping)
 	INIT_LIST_HEAD(&mapping->private_list);
 	spin_lock_init(&mapping->private_lock);
 	mapping->i_mmap = RB_ROOT;
-	INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
 }
 EXPORT_SYMBOL(address_space_init_once);
 
@@ -416,7 +404,8 @@ static void inode_lru_list_add(struct inode *inode)
  */
 void inode_add_lru(struct inode *inode)
 {
-	if (!(inode->i_state & (I_DIRTY | I_SYNC | I_FREEING | I_WILL_FREE)) &&
+	if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC |
+				I_FREEING | I_WILL_FREE)) &&
 	    !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE)
 		inode_lru_list_add(inode);
 }
@@ -647,7 +636,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 			spin_unlock(&inode->i_lock);
 			continue;
 		}
-		if (inode->i_state & I_DIRTY && !kill_dirty) {
+		if (inode->i_state & I_DIRTY_ALL && !kill_dirty) {
 			spin_unlock(&inode->i_lock);
 			busy = 1;
 			continue;
@@ -685,8 +674,8 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
  * LRU does not have strict ordering. Hence we don't want to reclaim inodes
  * with this flag set because they are the inodes that are out of order.
  */
-static enum lru_status
-inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
+static enum lru_status inode_lru_isolate(struct list_head *item,
+		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
 {
 	struct list_head *freeable = arg;
 	struct inode	*inode = container_of(item, struct inode, i_lru);
@@ -704,7 +693,7 @@ inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 	 */
 	if (atomic_read(&inode->i_count) ||
 	    (inode->i_state & ~I_REFERENCED)) {
-		list_del_init(&inode->i_lru);
+		list_lru_isolate(lru, &inode->i_lru);
 		spin_unlock(&inode->i_lock);
 		this_cpu_dec(nr_unused);
 		return LRU_REMOVED;
@@ -738,7 +727,7 @@ inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
 
 	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state |= I_FREEING;
-	list_move(&inode->i_lru, freeable);
+	list_lru_isolate_move(lru, &inode->i_lru, freeable);
 	spin_unlock(&inode->i_lock);
 
 	this_cpu_dec(nr_unused);
@@ -751,14 +740,13 @@ inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
  * to trim from the LRU. Inodes to be freed are moved to a temporary list and
  * then are freed outside inode_lock by dispose_list().
  */
-long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
-		     int nid)
+long prune_icache_sb(struct super_block *sb, struct shrink_control *sc)
 {
 	LIST_HEAD(freeable);
 	long freed;
 
-	freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate,
-				       &freeable, &nr_to_scan);
+	freed = list_lru_shrink_walk(&sb->s_inode_lru, sc,
+				     inode_lru_isolate, &freeable);
 	dispose_list(&freeable);
 	return freed;
 }
@@ -1282,6 +1270,56 @@ struct inode *ilookup(struct super_block *sb, unsigned long ino)
 }
 EXPORT_SYMBOL(ilookup);
 
+/**
+ * find_inode_nowait - find an inode in the inode cache
+ * @sb:		super block of file system to search
+ * @hashval:	hash value (usually inode number) to search for
+ * @match:	callback used for comparisons between inodes
+ * @data:	opaque data pointer to pass to @match
+ *
+ * Search for the inode specified by @hashval and @data in the inode
+ * cache, where the helper function @match will return 0 if the inode
+ * does not match, 1 if the inode does match, and -1 if the search
+ * should be stopped.  The @match function must be responsible for
+ * taking the i_lock spin_lock and checking i_state for an inode being
+ * freed or being initialized, and incrementing the reference count
+ * before returning 1.  It also must not sleep, since it is called with
+ * the inode_hash_lock spinlock held.
+ *
+ * This is a even more generalized version of ilookup5() when the
+ * function must never block --- find_inode() can block in
+ * __wait_on_freeing_inode() --- or when the caller can not increment
+ * the reference count because the resulting iput() might cause an
+ * inode eviction.  The tradeoff is that the @match funtion must be
+ * very carefully implemented.
+ */
+struct inode *find_inode_nowait(struct super_block *sb,
+				unsigned long hashval,
+				int (*match)(struct inode *, unsigned long,
+					     void *),
+				void *data)
+{
+	struct hlist_head *head = inode_hashtable + hash(sb, hashval);
+	struct inode *inode, *ret_inode = NULL;
+	int mval;
+
+	spin_lock(&inode_hash_lock);
+	hlist_for_each_entry(inode, head, i_hash) {
+		if (inode->i_sb != sb)
+			continue;
+		mval = match(inode, hashval, data);
+		if (mval == 0)
+			continue;
+		if (mval == 1)
+			ret_inode = inode;
+		goto out;
+	}
+out:
+	spin_unlock(&inode_hash_lock);
+	return ret_inode;
+}
+EXPORT_SYMBOL(find_inode_nowait);
+
 int insert_inode_locked(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
@@ -1432,11 +1470,20 @@ static void iput_final(struct inode *inode)
  */
 void iput(struct inode *inode)
 {
-	if (inode) {
-		BUG_ON(inode->i_state & I_CLEAR);
-
-		if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock))
-			iput_final(inode);
+	if (!inode)
+		return;
+	BUG_ON(inode->i_state & I_CLEAR);
+retry:
+	if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) {
+		if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) {
+			atomic_inc(&inode->i_count);
+			inode->i_state &= ~I_DIRTY_TIME;
+			spin_unlock(&inode->i_lock);
+			trace_writeback_lazytime_iput(inode);
+			mark_inode_dirty_sync(inode);
+			goto retry;
+		}
+		iput_final(inode);
 	}
 }
 EXPORT_SYMBOL(iput);
@@ -1495,14 +1542,9 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
 	return 0;
 }
 
-/*
- * This does the actual work of updating an inodes time or version.  Must have
- * had called mnt_want_write() before calling this.
- */
-static int update_time(struct inode *inode, struct timespec *time, int flags)
+int generic_update_time(struct inode *inode, struct timespec *time, int flags)
 {
-	if (inode->i_op->update_time)
-		return inode->i_op->update_time(inode, time, flags);
+	int iflags = I_DIRTY_TIME;
 
 	if (flags & S_ATIME)
 		inode->i_atime = *time;
@@ -1512,9 +1554,27 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
 		inode->i_ctime = *time;
 	if (flags & S_MTIME)
 		inode->i_mtime = *time;
-	mark_inode_dirty_sync(inode);
+
+	if (!(inode->i_sb->s_flags & MS_LAZYTIME) || (flags & S_VERSION))
+		iflags |= I_DIRTY_SYNC;
+	__mark_inode_dirty(inode, iflags);
 	return 0;
 }
+EXPORT_SYMBOL(generic_update_time);
+
+/*
+ * This does the actual work of updating an inodes time or version.  Must have
+ * had called mnt_want_write() before calling this.
+ */
+static int update_time(struct inode *inode, struct timespec *time, int flags)
+{
+	int (*update_time)(struct inode *, struct timespec *, int);
+
+	update_time = inode->i_op->update_time ? inode->i_op->update_time :
+		generic_update_time;
+
+	return update_time(inode, time, flags);
+}
 
 /**
  *	touch_atime	-	update the access time
diff --git a/fs/internal.h b/fs/internal.h
index e9a61fe67575..01dce1d1476b 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -14,6 +14,7 @@ struct file_system_type;
 struct linux_binprm;
 struct path;
 struct mount;
+struct shrink_control;
 
 /*
  * block_dev.c
@@ -83,7 +84,7 @@ extern struct file *get_empty_filp(void);
  * super.c
  */
 extern int do_remount_sb(struct super_block *, int, void *, int);
-extern bool grab_super_passive(struct super_block *sb);
+extern bool trylock_super(struct super_block *sb);
 extern struct dentry *mount_fs(struct file_system_type *,
 			       int, const char *, void *);
 extern struct super_block *user_get_super(dev_t);
@@ -111,8 +112,7 @@ extern int open_check_o_direct(struct file *f);
  * inode.c
  */
 extern spinlock_t inode_sb_list_lock;
-extern long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
-			    int nid);
+extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc);
 extern void inode_add_lru(struct inode *inode);
 
 /*
@@ -129,8 +129,7 @@ extern int invalidate_inodes(struct super_block *, bool);
  */
 extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
 extern int d_set_mounted(struct dentry *dentry);
-extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
-			    int nid);
+extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
 
 /*
  * read_write.c
@@ -145,7 +144,7 @@ extern const struct file_operations pipefifo_fops;
 /*
  * fs_pin.c
  */
-extern void sb_pin_kill(struct super_block *sb);
+extern void group_pin_kill(struct hlist_head *p);
 extern void mnt_pin_kill(struct mount *m);
 
 /*
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 214c3c11fbc2..5d01d2638ca5 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -379,6 +379,11 @@ int __generic_block_fiemap(struct inode *inode,
 				past_eof = true;
 		}
 		cond_resched();
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+
 	} while (1);
 
 	/* If ret is 1 then we just hit the end of the extent array */
diff --git a/fs/isofs/util.c b/fs/isofs/util.c
index 01e1ee7a998b..005a15cfd30a 100644
--- a/fs/isofs/util.c
+++ b/fs/isofs/util.c
@@ -2,6 +2,7 @@
  *  linux/fs/isofs/util.c
  */
 
+#include <linux/time.h>
 #include "isofs.h"
 
 /* 
@@ -17,9 +18,9 @@
 int iso_date(char * p, int flag)
 {
 	int year, month, day, hour, minute, second, tz;
-	int crtime, days, i;
+	int crtime;
 
-	year = p[0] - 70;
+	year = p[0];
 	month = p[1];
 	day = p[2];
 	hour = p[3];
@@ -31,18 +32,7 @@ int iso_date(char * p, int flag)
 	if (year < 0) {
 		crtime = 0;
 	} else {
-		int monlen[12] = {31,28,31,30,31,30,31,31,30,31,30,31};
-
-		days = year * 365;
-		if (year > 2)
-			days += (year+1) / 4;
-		for (i = 1; i < month; i++)
-			days += monlen[i-1];
-		if (((year+2) % 4) == 0 && month > 2)
-			days++;
-		days += day - 1;
-		crtime = ((((days * 24) + hour) * 60 + minute) * 60)
-			+ second;
+		crtime = mktime64(year+1900, month, day, hour, minute, second);
 
 		/* sign extend */
 		if (tz & 0x80)
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index bcbef08a4d8f..b5128c6e63ad 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -524,6 +524,9 @@ static int do_one_pass(journal_t *journal,
 			if (descr_csum_size > 0 &&
 			    !jbd2_descr_block_csum_verify(journal,
 							  bh->b_data)) {
+				printk(KERN_ERR "JBD2: Invalid checksum "
+				       "recovering block %lu in log\n",
+				       next_log_block);
 				err = -EIO;
 				brelse(bh);
 				goto failed;
diff --git a/fs/jffs2/compr_rubin.c b/fs/jffs2/compr_rubin.c
index 92e0644bf867..556de100ebd5 100644
--- a/fs/jffs2/compr_rubin.c
+++ b/fs/jffs2/compr_rubin.c
@@ -84,11 +84,6 @@ static inline int pullbit(struct pushpull *pp)
 	return bit;
 }
 
-static inline int pulledbits(struct pushpull *pp)
-{
-	return pp->ofs;
-}
-
 
 static void init_rubin(struct rubin_state *rs, int div, int *bits)
 {
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 938556025d64..f21b6fb5e4c4 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -252,7 +252,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de
 	if (!f->inocache)
 		return -EIO;
 
-	if (S_ISDIR(old_dentry->d_inode->i_mode))
+	if (d_is_dir(old_dentry))
 		return -EPERM;
 
 	/* XXX: This is ugly */
@@ -772,7 +772,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 	 */
 	if (new_dentry->d_inode) {
 		victim_f = JFFS2_INODE_INFO(new_dentry->d_inode);
-		if (S_ISDIR(new_dentry->d_inode->i_mode)) {
+		if (d_is_dir(new_dentry)) {
 			struct jffs2_full_dirent *fd;
 
 			mutex_lock(&victim_f->sem);
@@ -807,7 +807,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 
 	if (victim_f) {
 		/* There was a victim. Kill it off nicely */
-		if (S_ISDIR(new_dentry->d_inode->i_mode))
+		if (d_is_dir(new_dentry))
 			clear_nlink(new_dentry->d_inode);
 		else
 			drop_nlink(new_dentry->d_inode);
@@ -815,7 +815,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 		   inode which didn't exist. */
 		if (victim_f->inocache) {
 			mutex_lock(&victim_f->sem);
-			if (S_ISDIR(new_dentry->d_inode->i_mode))
+			if (d_is_dir(new_dentry))
 				victim_f->inocache->pino_nlink = 0;
 			else
 				victim_f->inocache->pino_nlink--;
@@ -825,7 +825,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 
 	/* If it was a directory we moved, and there was no victim,
 	   increase i_nlink on its new parent */
-	if (S_ISDIR(old_dentry->d_inode->i_mode) && !victim_f)
+	if (d_is_dir(old_dentry) && !victim_f)
 		inc_nlink(new_dir_i);
 
 	/* Unlink the original */
@@ -839,7 +839,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 		struct jffs2_inode_info *f = JFFS2_INODE_INFO(old_dentry->d_inode);
 		mutex_lock(&f->sem);
 		inc_nlink(old_dentry->d_inode);
-		if (f->inocache && !S_ISDIR(old_dentry->d_inode->i_mode))
+		if (f->inocache && !d_is_dir(old_dentry))
 			f->inocache->pino_nlink++;
 		mutex_unlock(&f->sem);
 
@@ -852,7 +852,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 		return ret;
 	}
 
-	if (S_ISDIR(old_dentry->d_inode->i_mode))
+	if (d_is_dir(old_dentry))
 		drop_nlink(old_dir_i);
 
 	new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = ITIME(now);
diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c
index 7654e87b0428..9ad5ba4b299b 100644
--- a/fs/jffs2/scan.c
+++ b/fs/jffs2/scan.c
@@ -510,6 +510,10 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo
 				sumlen = c->sector_size - je32_to_cpu(sm->offset);
 				sumptr = buf + buf_size - sumlen;
 
+				/* sm->offset maybe wrong but MAGIC maybe right */
+				if (sumlen > c->sector_size)
+					goto full_scan;
+
 				/* Now, make sure the summary itself is available */
 				if (sumlen > buf_size) {
 					/* Need to kmalloc for this. */
@@ -544,6 +548,7 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo
 		}
 	}
 
+full_scan:
 	buf_ofs = jeb->offset;
 
 	if (!buf_size) {
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 0918f0e2e266..3d76f28a2ba9 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -138,7 +138,7 @@ static struct dentry *jffs2_get_parent(struct dentry *child)
 	struct jffs2_inode_info *f;
 	uint32_t pino;
 
-	BUG_ON(!S_ISDIR(child->d_inode->i_mode));
+	BUG_ON(!d_is_dir(child));
 
 	f = JFFS2_INODE_INFO(child->d_inode);
 
diff --git a/fs/jfs/endian24.h b/fs/jfs/endian24.h
deleted file mode 100644
index fa92f7f1d0d0..000000000000
--- a/fs/jfs/endian24.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- *   Copyright (C) International Business Machines Corp., 2001
- *
- *   This program is free software;  you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   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;  if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-#ifndef _H_ENDIAN24
-#define	_H_ENDIAN24
-
-/*
- *	endian24.h:
- *
- * Endian conversion for 24-byte data
- *
- */
-#define __swab24(x) \
-({ \
-	__u32 __x = (x); \
-	((__u32)( \
-		((__x & (__u32)0x000000ffUL) << 16) | \
-		 (__x & (__u32)0x0000ff00UL)	    | \
-		((__x & (__u32)0x00ff0000UL) >> 16) )); \
-})
-
-#if (defined(__KERNEL__) && defined(__LITTLE_ENDIAN)) || (defined(__BYTE_ORDER) && (__BYTE_ORDER == __LITTLE_ENDIAN))
-	#define __cpu_to_le24(x) ((__u32)(x))
-	#define __le24_to_cpu(x) ((__u32)(x))
-#else
-	#define __cpu_to_le24(x) __swab24(x)
-	#define __le24_to_cpu(x) __swab24(x)
-#endif
-
-#ifdef __KERNEL__
-	#define cpu_to_le24 __cpu_to_le24
-	#define le24_to_cpu __le24_to_cpu
-#endif
-
-#endif				/* !_H_ENDIAN24 */
diff --git a/fs/jfs/file.c b/fs/jfs/file.c
index 33aa0cc1f8b8..10815f8dfd8b 100644
--- a/fs/jfs/file.c
+++ b/fs/jfs/file.c
@@ -39,7 +39,7 @@ int jfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		return rc;
 
 	mutex_lock(&inode->i_mutex);
-	if (!(inode->i_state & I_DIRTY) ||
+	if (!(inode->i_state & I_DIRTY_ALL) ||
 	    (datasync && !(inode->i_state & I_DIRTY_DATASYNC))) {
 		/* Make sure committed changes hit the disk */
 		jfs_flush_journal(JFS_SBI(inode->i_sb)->log, 1);
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index 984c2bbf4f61..d88576e23fe4 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -1040,8 +1040,8 @@ static int dtSplitUp(tid_t tid,
 		pxdlist.maxnpxd = 1;
 		pxdlist.npxd = 0;
 		pxd = &pxdlist.pxd[0];
-		PXDaddress(pxd, nxaddr)
-		    PXDlength(pxd, xlen + n);
+		PXDaddress(pxd, nxaddr);
+		PXDlength(pxd, xlen + n);
 		split->pxdlist = &pxdlist;
 		if ((rc = dtExtendPage(tid, ip, split, btstack))) {
 			nxaddr = addressPXD(pxd);
diff --git a/fs/jfs/jfs_types.h b/fs/jfs/jfs_types.h
index 43ea3713c083..8f602dcb51fa 100644
--- a/fs/jfs/jfs_types.h
+++ b/fs/jfs/jfs_types.h
@@ -30,8 +30,6 @@
 #include <linux/types.h>
 #include <linux/nls.h>
 
-#include "endian24.h"
-
 /*
  * transaction and lock id's
  *
@@ -59,26 +57,42 @@ struct timestruc_t {
 
 /*
  *	physical xd (pxd)
+ *
+ *	The leftmost 24 bits of len_addr are the extent length.
+ *	The rightmost 8 bits of len_addr are the most signficant bits of
+ *	the extent address
  */
 typedef struct {
-	unsigned len:24;
-	unsigned addr1:8;
+	__le32 len_addr;
 	__le32 addr2;
 } pxd_t;
 
 /* xd_t field construction */
 
-#define	PXDlength(pxd, length32)	((pxd)->len = __cpu_to_le24(length32))
-#define	PXDaddress(pxd, address64)\
-{\
-	(pxd)->addr1 = ((s64)address64) >> 32;\
-	(pxd)->addr2 = __cpu_to_le32((address64) & 0xffffffff);\
+static inline void PXDlength(pxd_t *pxd, __u32 len)
+{
+	pxd->len_addr = (pxd->len_addr & cpu_to_le32(~0xffffff)) |
+			cpu_to_le32(len & 0xffffff);
+}
+
+static inline void PXDaddress(pxd_t *pxd, __u64 addr)
+{
+	pxd->len_addr = (pxd->len_addr & cpu_to_le32(0xffffff)) |
+			cpu_to_le32((addr >> 32)<<24);
+	pxd->addr2 = cpu_to_le32(addr & 0xffffffff);
 }
 
 /* xd_t field extraction */
-#define	lengthPXD(pxd)	__le24_to_cpu((pxd)->len)
-#define	addressPXD(pxd)\
-	( ((s64)((pxd)->addr1)) << 32 | __le32_to_cpu((pxd)->addr2))
+static inline __u32 lengthPXD(pxd_t *pxd)
+{
+	return le32_to_cpu((pxd)->len_addr) & 0xffffff;
+}
+
+static inline __u64 addressPXD(pxd_t *pxd)
+{
+	__u64 n = le32_to_cpu(pxd->len_addr) & ~0xffffff;
+	return (n << 8) + le32_to_cpu(pxd->addr2);
+}
 
 #define MAXTREEHEIGHT 8
 /* pxd list */
@@ -93,12 +107,10 @@ struct pxdlist {
  *	data extent descriptor (dxd)
  */
 typedef struct {
-	unsigned flag:8;	/* 1: flags */
-	unsigned rsrvd:24;
+	__u8 flag;	/* 1: flags */
+	__u8 rsrvd[3];
 	__le32 size;		/* 4: size in byte */
-	unsigned len:24;	/* 3: length in unit of fsblksize */
-	unsigned addr1:8;	/* 1: address in unit of fsblksize */
-	__le32 addr2;		/* 4: address in unit of fsblksize */
+	pxd_t loc;		/* 8: address and length in unit of fsblksize */
 } dxd_t;			/* - 16 - */
 
 /* dxd_t flags */
@@ -109,12 +121,11 @@ typedef struct {
 #define DXD_CORRUPT	0x08	/* Inconsistency detected */
 
 /* dxd_t field construction
- *	Conveniently, the PXD macros work for DXD
  */
-#define	DXDlength	PXDlength
-#define	DXDaddress	PXDaddress
-#define	lengthDXD	lengthPXD
-#define	addressDXD	addressPXD
+#define	DXDlength(dxd, len)	PXDlength(&(dxd)->loc, len)
+#define	DXDaddress(dxd, addr)	PXDaddress(&(dxd)->loc, addr)
+#define	lengthDXD(dxd)	lengthPXD(&(dxd)->loc)
+#define	addressDXD(dxd)	addressPXD(&(dxd)->loc)
 #define DXDsize(dxd, size32) ((dxd)->size = cpu_to_le32(size32))
 #define sizeDXD(dxd)	le32_to_cpu((dxd)->size)
 
diff --git a/fs/jfs/jfs_xtree.h b/fs/jfs/jfs_xtree.h
index 08c0c749b986..1e0987986d5f 100644
--- a/fs/jfs/jfs_xtree.h
+++ b/fs/jfs/jfs_xtree.h
@@ -29,13 +29,11 @@
  *	extent allocation descriptor (xad)
  */
 typedef struct xad {
-	unsigned flag:8;	/* 1: flag */
-	unsigned rsvrd:16;	/* 2: reserved */
-	unsigned off1:8;	/* 1: offset in unit of fsblksize */
-	__le32 off2;		/* 4: offset in unit of fsblksize */
-	unsigned len:24;	/* 3: length in unit of fsblksize */
-	unsigned addr1:8;	/* 1: address in unit of fsblksize */
-	__le32 addr2;		/* 4: address in unit of fsblksize */
+	__u8 flag;	/* 1: flag */
+	__u8 rsvrd[2];	/* 2: reserved */
+	__u8 off1;	/* 1: offset in unit of fsblksize */
+	__le32 off2;	/* 4: offset in unit of fsblksize */
+	pxd_t loc;	/* 8: length and address in unit of fsblksize */
 } xad_t;			/* (16) */
 
 #define MAXXLEN		((1 << 24) - 1)
@@ -49,19 +47,14 @@ typedef struct xad {
 	(xad)->off1 = ((u64)offset64) >> 32;\
 	(xad)->off2 = __cpu_to_le32((offset64) & 0xffffffff);\
 }
-#define XADaddress(xad, address64)\
-{\
-	(xad)->addr1 = ((u64)address64) >> 32;\
-	(xad)->addr2 = __cpu_to_le32((address64) & 0xffffffff);\
-}
-#define XADlength(xad, length32)	(xad)->len = __cpu_to_le24(length32)
+#define XADaddress(xad, address64) PXDaddress(&(xad)->loc, address64)
+#define XADlength(xad, length32) PXDlength(&(xad)->loc, length32)
 
 /* xad_t field extraction */
 #define offsetXAD(xad)\
 	( ((s64)((xad)->off1)) << 32 | __le32_to_cpu((xad)->off2))
-#define addressXAD(xad)\
-	( ((s64)((xad)->addr1)) << 32 | __le32_to_cpu((xad)->addr2))
-#define lengthXAD(xad)	__le24_to_cpu((xad)->len)
+#define addressXAD(xad) addressPXD(&(xad)->loc)
+#define lengthXAD(xad) lengthPXD(&(xad)->loc)
 
 /* xad list */
 struct xadlist {
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 16c3a9556634..5d30c56ae075 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -619,8 +619,7 @@ out_mount_failed:
 	iput(sbi->direct_inode);
 	sbi->direct_inode = NULL;
 out_unload:
-	if (sbi->nls_tab)
-		unload_nls(sbi->nls_tab);
+	unload_nls(sbi->nls_tab);
 out_kfree:
 	kfree(sbi);
 	return ret;
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 2d881b381d2b..6acc9648f986 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -411,8 +411,9 @@ void kernfs_put(struct kernfs_node *kn)
 
 	if (kernfs_type(kn) == KERNFS_LINK)
 		kernfs_put(kn->symlink.target_kn);
-	if (!(kn->flags & KERNFS_STATIC_NAME))
-		kfree(kn->name);
+
+	kfree_const(kn->name);
+
 	if (kn->iattr) {
 		if (kn->iattr->ia_secdata)
 			security_release_secctx(kn->iattr->ia_secdata,
@@ -506,15 +507,12 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 					     const char *name, umode_t mode,
 					     unsigned flags)
 {
-	char *dup_name = NULL;
 	struct kernfs_node *kn;
 	int ret;
 
-	if (!(flags & KERNFS_STATIC_NAME)) {
-		name = dup_name = kstrdup(name, GFP_KERNEL);
-		if (!name)
-			return NULL;
-	}
+	name = kstrdup_const(name, GFP_KERNEL);
+	if (!name)
+		return NULL;
 
 	kn = kmem_cache_zalloc(kernfs_node_cache, GFP_KERNEL);
 	if (!kn)
@@ -538,7 +536,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
  err_out2:
 	kmem_cache_free(kernfs_node_cache, kn);
  err_out1:
-	kfree(dup_name);
+	kfree_const(name);
 	return NULL;
 }
 
@@ -1264,7 +1262,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	/* rename kernfs_node */
 	if (strcmp(kn->name, new_name) != 0) {
 		error = -ENOMEM;
-		new_name = kstrdup(new_name, GFP_KERNEL);
+		new_name = kstrdup_const(new_name, GFP_KERNEL);
 		if (!new_name)
 			goto out;
 	} else {
@@ -1285,9 +1283,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 
 	kn->ns = new_ns;
 	if (new_name) {
-		if (!(kn->flags & KERNFS_STATIC_NAME))
-			old_name = kn->name;
-		kn->flags &= ~KERNFS_STATIC_NAME;
+		old_name = kn->name;
 		kn->name = new_name;
 	}
 
@@ -1297,7 +1293,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	kernfs_link_sibling(kn);
 
 	kernfs_put(old_parent);
-	kfree(old_name);
+	kfree_const(old_name);
 
 	error = 0;
  out:
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index ddc9f9612f16..2bacb9988566 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -207,6 +207,7 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
 		goto out_free;
 	}
 
+	of->event = atomic_read(&of->kn->attr.open->event);
 	ops = kernfs_ops(of->kn);
 	if (ops->read)
 		len = ops->read(of, buf, len, *ppos);
@@ -901,7 +902,6 @@ const struct file_operations kernfs_file_fops = {
  * @ops: kernfs operations for the file
  * @priv: private data for the file
  * @ns: optional namespace tag of the file
- * @name_is_static: don't copy file name
  * @key: lockdep key for the file's active_ref, %NULL to disable lockdep
  *
  * Returns the created node on success, ERR_PTR() value on error.
@@ -911,7 +911,6 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 					 umode_t mode, loff_t size,
 					 const struct kernfs_ops *ops,
 					 void *priv, const void *ns,
-					 bool name_is_static,
 					 struct lock_class_key *key)
 {
 	struct kernfs_node *kn;
@@ -919,8 +918,6 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 	int rc;
 
 	flags = KERNFS_FILE;
-	if (name_is_static)
-		flags |= KERNFS_STATIC_NAME;
 
 	kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, flags);
 	if (!kn)
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 985217626e66..9000874a945b 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -24,12 +24,6 @@ static const struct address_space_operations kernfs_aops = {
 	.write_end	= simple_write_end,
 };
 
-static struct backing_dev_info kernfs_bdi = {
-	.name		= "kernfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
 static const struct inode_operations kernfs_iops = {
 	.permission	= kernfs_iop_permission,
 	.setattr	= kernfs_iop_setattr,
@@ -40,12 +34,6 @@ static const struct inode_operations kernfs_iops = {
 	.listxattr	= kernfs_iop_listxattr,
 };
 
-void __init kernfs_inode_init(void)
-{
-	if (bdi_init(&kernfs_bdi))
-		panic("failed to init kernfs_bdi");
-}
-
 static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
 {
 	static DEFINE_MUTEX(iattr_mutex);
@@ -298,7 +286,6 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
 	kernfs_get(kn);
 	inode->i_private = kn;
 	inode->i_mapping->a_ops = &kernfs_aops;
-	inode->i_mapping->backing_dev_info = &kernfs_bdi;
 	inode->i_op = &kernfs_iops;
 
 	set_default_inode_attr(inode, kn->mode);
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index dc84a3ef9ca2..af9fa7499919 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -88,7 +88,6 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name);
 ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
 			    size_t size);
 ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
-void kernfs_inode_init(void);
 
 /*
  * dir.c
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index f973ae9b05f1..8eaf417187f1 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -246,5 +246,4 @@ void __init kernfs_init(void)
 	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
 					      sizeof(struct kernfs_node),
 					      0, SLAB_PANIC, NULL);
-	kernfs_inode_init();
 }
diff --git a/fs/libfs.c b/fs/libfs.c
index 005843ce5dbd..0ab65122ee45 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -329,7 +329,7 @@ int simple_rename(struct inode *old_dir, struct dentry *old_dentry,
 		struct inode *new_dir, struct dentry *new_dentry)
 {
 	struct inode *inode = old_dentry->d_inode;
-	int they_are_dirs = S_ISDIR(old_dentry->d_inode->i_mode);
+	int they_are_dirs = d_is_dir(old_dentry);
 
 	if (!simple_empty(new_dentry))
 		return -ENOTEMPTY;
@@ -948,7 +948,7 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end,
 
 	mutex_lock(&inode->i_mutex);
 	ret = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY))
+	if (!(inode->i_state & I_DIRTY_ALL))
 		goto out;
 	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
 		goto out;
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 1cc6ec51e6b1..47a32b6d9b90 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -65,7 +65,7 @@ static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm)
 	return (struct sockaddr *)&nsm->sm_addr;
 }
 
-static struct rpc_clnt *nsm_create(struct net *net)
+static struct rpc_clnt *nsm_create(struct net *net, const char *nodename)
 {
 	struct sockaddr_in sin = {
 		.sin_family		= AF_INET,
@@ -77,6 +77,7 @@ static struct rpc_clnt *nsm_create(struct net *net)
 		.address		= (struct sockaddr *)&sin,
 		.addrsize		= sizeof(sin),
 		.servername		= "rpc.statd",
+		.nodename		= nodename,
 		.program		= &nsm_program,
 		.version		= NSM_VERSION,
 		.authflavor		= RPC_AUTH_NULL,
@@ -102,7 +103,7 @@ out:
 	return clnt;
 }
 
-static struct rpc_clnt *nsm_client_get(struct net *net)
+static struct rpc_clnt *nsm_client_get(struct net *net, const char *nodename)
 {
 	struct rpc_clnt	*clnt, *new;
 	struct lockd_net *ln = net_generic(net, lockd_net_id);
@@ -111,7 +112,7 @@ static struct rpc_clnt *nsm_client_get(struct net *net)
 	if (clnt != NULL)
 		goto out;
 
-	clnt = new = nsm_create(net);
+	clnt = new = nsm_create(net, nodename);
 	if (IS_ERR(clnt))
 		goto out;
 
@@ -190,19 +191,23 @@ int nsm_monitor(const struct nlm_host *host)
 	struct nsm_res	res;
 	int		status;
 	struct rpc_clnt *clnt;
+	const char *nodename = NULL;
 
 	dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name);
 
 	if (nsm->sm_monitored)
 		return 0;
 
+	if (host->h_rpcclnt)
+		nodename = host->h_rpcclnt->cl_nodename;
+
 	/*
 	 * Choose whether to record the caller_name or IP address of
 	 * this peer in the local rpc.statd's database.
 	 */
 	nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
 
-	clnt = nsm_client_get(host->net);
+	clnt = nsm_client_get(host->net, nodename);
 	if (IS_ERR(clnt)) {
 		status = PTR_ERR(clnt);
 		dprintk("lockd: failed to create NSM upcall transport, "
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 56598742dde4..5581e020644b 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -57,8 +57,8 @@ static DEFINE_SPINLOCK(nlm_blocked_lock);
 static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie)
 {
 	/*
-	 * We can get away with a static buffer because we're only
-	 * called with BKL held.
+	 * We can get away with a static buffer because this is only called
+	 * from lockd, which is single-threaded.
 	 */
 	static char buf[2*NLM_MAXCOOKIELEN+1];
 	unsigned int i, len = sizeof(buf);
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index d12ff4e2dbe7..665ef5a05183 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -164,12 +164,15 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file,
 {
 	struct inode	 *inode = nlmsvc_file_inode(file);
 	struct file_lock *fl;
+	struct file_lock_context *flctx = inode->i_flctx;
 	struct nlm_host	 *lockhost;
 
+	if (!flctx || list_empty_careful(&flctx->flc_posix))
+		return 0;
 again:
 	file->f_locks = 0;
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl; fl = fl->fl_next) {
+	spin_lock(&flctx->flc_lock);
+	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
 		if (fl->fl_lmops != &nlmsvc_lock_operations)
 			continue;
 
@@ -180,7 +183,7 @@ again:
 		if (match(lockhost, host)) {
 			struct file_lock lock = *fl;
 
-			spin_unlock(&inode->i_lock);
+			spin_unlock(&flctx->flc_lock);
 			lock.fl_type  = F_UNLCK;
 			lock.fl_start = 0;
 			lock.fl_end   = OFFSET_MAX;
@@ -192,7 +195,7 @@ again:
 			goto again;
 		}
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 
 	return 0;
 }
@@ -223,18 +226,21 @@ nlm_file_inuse(struct nlm_file *file)
 {
 	struct inode	 *inode = nlmsvc_file_inode(file);
 	struct file_lock *fl;
+	struct file_lock_context *flctx = inode->i_flctx;
 
 	if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares)
 		return 1;
 
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl; fl = fl->fl_next) {
-		if (fl->fl_lmops == &nlmsvc_lock_operations) {
-			spin_unlock(&inode->i_lock);
-			return 1;
+	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
+		spin_lock(&flctx->flc_lock);
+		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+			if (fl->fl_lmops == &nlmsvc_lock_operations) {
+				spin_unlock(&flctx->flc_lock);
+				return 1;
+			}
 		}
+		spin_unlock(&flctx->flc_lock);
 	}
-	spin_unlock(&inode->i_lock);
 	file->f_locks = 0;
 	return 0;
 }
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 9340e7e10ef6..5b651daad518 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -95,14 +95,6 @@ nlm_decode_fh(__be32 *p, struct nfs_fh *f)
 	return p + XDR_QUADLEN(NFS2_FHSIZE);
 }
 
-static inline __be32 *
-nlm_encode_fh(__be32 *p, struct nfs_fh *f)
-{
-	*p++ = htonl(NFS2_FHSIZE);
-	memcpy(p, f->data, NFS2_FHSIZE);
-	return p + XDR_QUADLEN(NFS2_FHSIZE);
-}
-
 /*
  * Encode and decode owner handle
  */
diff --git a/fs/locks.c b/fs/locks.c
index 59e2f905e4ff..528fedfda15e 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -137,7 +137,7 @@
 
 #define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
 #define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
-#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG))
+#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
 #define IS_OFDLCK(fl)	(fl->fl_flags & FL_OFDLCK)
 
 static bool lease_breaking(struct file_lock *fl)
@@ -157,14 +157,11 @@ static int target_leasetype(struct file_lock *fl)
 int leases_enable = 1;
 int lease_break_time = 45;
 
-#define for_each_lock(inode, lockp) \
-	for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next)
-
 /*
  * The global file_lock_list is only used for displaying /proc/locks, so we
  * keep a list on each CPU, with each list protected by its own spinlock via
  * the file_lock_lglock. Note that alterations to the list also require that
- * the relevant i_lock is held.
+ * the relevant flc_lock is held.
  */
 DEFINE_STATIC_LGLOCK(file_lock_lglock);
 static DEFINE_PER_CPU(struct hlist_head, file_lock_list);
@@ -192,21 +189,68 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS);
  * contrast to those that are acting as records of acquired locks).
  *
  * Note that when we acquire this lock in order to change the above fields,
- * we often hold the i_lock as well. In certain cases, when reading the fields
+ * we often hold the flc_lock as well. In certain cases, when reading the fields
  * protected by this lock, we can skip acquiring it iff we already hold the
- * i_lock.
+ * flc_lock.
  *
  * In particular, adding an entry to the fl_block list requires that you hold
- * both the i_lock and the blocked_lock_lock (acquired in that order). Deleting
- * an entry from the list however only requires the file_lock_lock.
+ * both the flc_lock and the blocked_lock_lock (acquired in that order).
+ * Deleting an entry from the list however only requires the file_lock_lock.
  */
 static DEFINE_SPINLOCK(blocked_lock_lock);
 
+static struct kmem_cache *flctx_cache __read_mostly;
 static struct kmem_cache *filelock_cache __read_mostly;
 
+static struct file_lock_context *
+locks_get_lock_context(struct inode *inode)
+{
+	struct file_lock_context *new;
+
+	if (likely(inode->i_flctx))
+		goto out;
+
+	new = kmem_cache_alloc(flctx_cache, GFP_KERNEL);
+	if (!new)
+		goto out;
+
+	spin_lock_init(&new->flc_lock);
+	INIT_LIST_HEAD(&new->flc_flock);
+	INIT_LIST_HEAD(&new->flc_posix);
+	INIT_LIST_HEAD(&new->flc_lease);
+
+	/*
+	 * Assign the pointer if it's not already assigned. If it is, then
+	 * free the context we just allocated.
+	 */
+	spin_lock(&inode->i_lock);
+	if (likely(!inode->i_flctx)) {
+		inode->i_flctx = new;
+		new = NULL;
+	}
+	spin_unlock(&inode->i_lock);
+
+	if (new)
+		kmem_cache_free(flctx_cache, new);
+out:
+	return inode->i_flctx;
+}
+
+void
+locks_free_lock_context(struct file_lock_context *ctx)
+{
+	if (ctx) {
+		WARN_ON_ONCE(!list_empty(&ctx->flc_flock));
+		WARN_ON_ONCE(!list_empty(&ctx->flc_posix));
+		WARN_ON_ONCE(!list_empty(&ctx->flc_lease));
+		kmem_cache_free(flctx_cache, ctx);
+	}
+}
+
 static void locks_init_lock_heads(struct file_lock *fl)
 {
 	INIT_HLIST_NODE(&fl->fl_link);
+	INIT_LIST_HEAD(&fl->fl_list);
 	INIT_LIST_HEAD(&fl->fl_block);
 	init_waitqueue_head(&fl->fl_wait);
 }
@@ -243,6 +287,7 @@ EXPORT_SYMBOL_GPL(locks_release_private);
 void locks_free_lock(struct file_lock *fl)
 {
 	BUG_ON(waitqueue_active(&fl->fl_wait));
+	BUG_ON(!list_empty(&fl->fl_list));
 	BUG_ON(!list_empty(&fl->fl_block));
 	BUG_ON(!hlist_unhashed(&fl->fl_link));
 
@@ -257,8 +302,8 @@ locks_dispose_list(struct list_head *dispose)
 	struct file_lock *fl;
 
 	while (!list_empty(dispose)) {
-		fl = list_first_entry(dispose, struct file_lock, fl_block);
-		list_del_init(&fl->fl_block);
+		fl = list_first_entry(dispose, struct file_lock, fl_list);
+		list_del_init(&fl->fl_list);
 		locks_free_lock(fl);
 	}
 }
@@ -513,7 +558,7 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
 	return fl1->fl_owner == fl2->fl_owner;
 }
 
-/* Must be called with the i_lock held! */
+/* Must be called with the flc_lock held! */
 static void locks_insert_global_locks(struct file_lock *fl)
 {
 	lg_local_lock(&file_lock_lglock);
@@ -522,12 +567,12 @@ static void locks_insert_global_locks(struct file_lock *fl)
 	lg_local_unlock(&file_lock_lglock);
 }
 
-/* Must be called with the i_lock held! */
+/* Must be called with the flc_lock held! */
 static void locks_delete_global_locks(struct file_lock *fl)
 {
 	/*
 	 * Avoid taking lock if already unhashed. This is safe since this check
-	 * is done while holding the i_lock, and new insertions into the list
+	 * is done while holding the flc_lock, and new insertions into the list
 	 * also require that it be held.
 	 */
 	if (hlist_unhashed(&fl->fl_link))
@@ -579,10 +624,10 @@ static void locks_delete_block(struct file_lock *waiter)
  * the order they blocked. The documentation doesn't require this but
  * it seems like the reasonable thing to do.
  *
- * Must be called with both the i_lock and blocked_lock_lock held. The fl_block
- * list itself is protected by the blocked_lock_lock, but by ensuring that the
- * i_lock is also held on insertions we can avoid taking the blocked_lock_lock
- * in some cases when we see that the fl_block list is empty.
+ * Must be called with both the flc_lock and blocked_lock_lock held. The
+ * fl_block list itself is protected by the blocked_lock_lock, but by ensuring
+ * that the flc_lock is also held on insertions we can avoid taking the
+ * blocked_lock_lock in some cases when we see that the fl_block list is empty.
  */
 static void __locks_insert_block(struct file_lock *blocker,
 					struct file_lock *waiter)
@@ -594,7 +639,7 @@ static void __locks_insert_block(struct file_lock *blocker,
 		locks_insert_global_blocked(waiter);
 }
 
-/* Must be called with i_lock held. */
+/* Must be called with flc_lock held. */
 static void locks_insert_block(struct file_lock *blocker,
 					struct file_lock *waiter)
 {
@@ -606,15 +651,15 @@ static void locks_insert_block(struct file_lock *blocker,
 /*
  * Wake up processes blocked waiting for blocker.
  *
- * Must be called with the inode->i_lock held!
+ * Must be called with the inode->flc_lock held!
  */
 static void locks_wake_up_blocks(struct file_lock *blocker)
 {
 	/*
 	 * Avoid taking global lock if list is empty. This is safe since new
-	 * blocked requests are only added to the list under the i_lock, and
-	 * the i_lock is always held here. Note that removal from the fl_block
-	 * list does not require the i_lock, so we must recheck list_empty()
+	 * blocked requests are only added to the list under the flc_lock, and
+	 * the flc_lock is always held here. Note that removal from the fl_block
+	 * list does not require the flc_lock, so we must recheck list_empty()
 	 * after acquiring the blocked_lock_lock.
 	 */
 	if (list_empty(&blocker->fl_block))
@@ -635,63 +680,32 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 	spin_unlock(&blocked_lock_lock);
 }
 
-/* Insert file lock fl into an inode's lock list at the position indicated
- * by pos. At the same time add the lock to the global file lock list.
- *
- * Must be called with the i_lock held!
- */
-static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
+static void
+locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before)
 {
 	fl->fl_nspid = get_pid(task_tgid(current));
-
-	/* insert into file's list */
-	fl->fl_next = *pos;
-	*pos = fl;
-
+	list_add_tail(&fl->fl_list, before);
 	locks_insert_global_locks(fl);
 }
 
-/**
- * locks_delete_lock - Delete a lock and then free it.
- * @thisfl_p: pointer that points to the fl_next field of the previous
- * 	      inode->i_flock list entry
- *
- * Unlink a lock from all lists and free the namespace reference, but don't
- * free it yet. Wake up processes that are blocked waiting for this lock and
- * notify the FS that the lock has been cleared.
- *
- * Must be called with the i_lock held!
- */
-static void locks_unlink_lock(struct file_lock **thisfl_p)
+static void
+locks_unlink_lock_ctx(struct file_lock *fl)
 {
-	struct file_lock *fl = *thisfl_p;
-
 	locks_delete_global_locks(fl);
-
-	*thisfl_p = fl->fl_next;
-	fl->fl_next = NULL;
-
+	list_del_init(&fl->fl_list);
 	if (fl->fl_nspid) {
 		put_pid(fl->fl_nspid);
 		fl->fl_nspid = NULL;
 	}
-
 	locks_wake_up_blocks(fl);
 }
 
-/*
- * Unlink a lock from all lists and free it.
- *
- * Must be called with i_lock held!
- */
-static void locks_delete_lock(struct file_lock **thisfl_p,
-			      struct list_head *dispose)
+static void
+locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose)
 {
-	struct file_lock *fl = *thisfl_p;
-
-	locks_unlink_lock(thisfl_p);
+	locks_unlink_lock_ctx(fl);
 	if (dispose)
-		list_add(&fl->fl_block, dispose);
+		list_add(&fl->fl_list, dispose);
 	else
 		locks_free_lock(fl);
 }
@@ -746,22 +760,27 @@ void
 posix_test_lock(struct file *filp, struct file_lock *fl)
 {
 	struct file_lock *cfl;
+	struct file_lock_context *ctx;
 	struct inode *inode = file_inode(filp);
 
-	spin_lock(&inode->i_lock);
-	for (cfl = file_inode(filp)->i_flock; cfl; cfl = cfl->fl_next) {
-		if (!IS_POSIX(cfl))
-			continue;
-		if (posix_locks_conflict(fl, cfl))
-			break;
-	}
-	if (cfl) {
-		locks_copy_conflock(fl, cfl);
-		if (cfl->fl_nspid)
-			fl->fl_pid = pid_vnr(cfl->fl_nspid);
-	} else
+	ctx = inode->i_flctx;
+	if (!ctx || list_empty_careful(&ctx->flc_posix)) {
 		fl->fl_type = F_UNLCK;
-	spin_unlock(&inode->i_lock);
+		return;
+	}
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
+		if (posix_locks_conflict(fl, cfl)) {
+			locks_copy_conflock(fl, cfl);
+			if (cfl->fl_nspid)
+				fl->fl_pid = pid_vnr(cfl->fl_nspid);
+			goto out;
+		}
+	}
+	fl->fl_type = F_UNLCK;
+out:
+	spin_unlock(&ctx->flc_lock);
 	return;
 }
 EXPORT_SYMBOL(posix_test_lock);
@@ -845,34 +864,34 @@ static int posix_locks_deadlock(struct file_lock *caller_fl,
 static int flock_lock_file(struct file *filp, struct file_lock *request)
 {
 	struct file_lock *new_fl = NULL;
-	struct file_lock **before;
-	struct inode * inode = file_inode(filp);
+	struct file_lock *fl;
+	struct file_lock_context *ctx;
+	struct inode *inode = file_inode(filp);
 	int error = 0;
-	int found = 0;
+	bool found = false;
 	LIST_HEAD(dispose);
 
+	ctx = locks_get_lock_context(inode);
+	if (!ctx)
+		return -ENOMEM;
+
 	if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) {
 		new_fl = locks_alloc_lock();
 		if (!new_fl)
 			return -ENOMEM;
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	if (request->fl_flags & FL_ACCESS)
 		goto find_conflict;
 
-	for_each_lock(inode, before) {
-		struct file_lock *fl = *before;
-		if (IS_POSIX(fl))
-			break;
-		if (IS_LEASE(fl))
-			continue;
+	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
 		if (filp != fl->fl_file)
 			continue;
 		if (request->fl_type == fl->fl_type)
 			goto out;
-		found = 1;
-		locks_delete_lock(before, &dispose);
+		found = true;
+		locks_delete_lock_ctx(fl, &dispose);
 		break;
 	}
 
@@ -882,23 +901,8 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
 		goto out;
 	}
 
-	/*
-	 * If a higher-priority process was blocked on the old file lock,
-	 * give it the opportunity to lock the file.
-	 */
-	if (found) {
-		spin_unlock(&inode->i_lock);
-		cond_resched();
-		spin_lock(&inode->i_lock);
-	}
-
 find_conflict:
-	for_each_lock(inode, before) {
-		struct file_lock *fl = *before;
-		if (IS_POSIX(fl))
-			break;
-		if (IS_LEASE(fl))
-			continue;
+	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
 		if (!flock_locks_conflict(request, fl))
 			continue;
 		error = -EAGAIN;
@@ -911,12 +915,12 @@ find_conflict:
 	if (request->fl_flags & FL_ACCESS)
 		goto out;
 	locks_copy_lock(new_fl, request);
-	locks_insert_lock(before, new_fl);
+	locks_insert_lock_ctx(new_fl, &ctx->flc_flock);
 	new_fl = NULL;
 	error = 0;
 
 out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	if (new_fl)
 		locks_free_lock(new_fl);
 	locks_dispose_list(&dispose);
@@ -925,16 +929,20 @@ out:
 
 static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock)
 {
-	struct file_lock *fl;
+	struct file_lock *fl, *tmp;
 	struct file_lock *new_fl = NULL;
 	struct file_lock *new_fl2 = NULL;
 	struct file_lock *left = NULL;
 	struct file_lock *right = NULL;
-	struct file_lock **before;
+	struct file_lock_context *ctx;
 	int error;
 	bool added = false;
 	LIST_HEAD(dispose);
 
+	ctx = locks_get_lock_context(inode);
+	if (!ctx)
+		return -ENOMEM;
+
 	/*
 	 * We may need two file_lock structures for this operation,
 	 * so we get them in advance to avoid races.
@@ -948,15 +956,14 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 		new_fl2 = locks_alloc_lock();
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	/*
 	 * New lock request. Walk all POSIX locks and look for conflicts. If
 	 * there are any, either return error or put the request on the
 	 * blocker's list of waiters and the global blocked_hash.
 	 */
 	if (request->fl_type != F_UNLCK) {
-		for_each_lock(inode, before) {
-			fl = *before;
+		list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
 			if (!IS_POSIX(fl))
 				continue;
 			if (!posix_locks_conflict(request, fl))
@@ -986,29 +993,25 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 	if (request->fl_flags & FL_ACCESS)
 		goto out;
 
-	/*
-	 * Find the first old lock with the same owner as the new lock.
-	 */
-	
-	before = &inode->i_flock;
-
-	/* First skip locks owned by other processes.  */
-	while ((fl = *before) && (!IS_POSIX(fl) ||
-				  !posix_same_owner(request, fl))) {
-		before = &fl->fl_next;
+	/* Find the first old lock with the same owner as the new lock */
+	list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
+		if (posix_same_owner(request, fl))
+			break;
 	}
 
 	/* Process locks with this owner. */
-	while ((fl = *before) && posix_same_owner(request, fl)) {
-		/* Detect adjacent or overlapping regions (if same lock type)
-		 */
+	list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) {
+		if (!posix_same_owner(request, fl))
+			break;
+
+		/* Detect adjacent or overlapping regions (if same lock type) */
 		if (request->fl_type == fl->fl_type) {
 			/* In all comparisons of start vs end, use
 			 * "start - 1" rather than "end + 1". If end
 			 * is OFFSET_MAX, end + 1 will become negative.
 			 */
 			if (fl->fl_end < request->fl_start - 1)
-				goto next_lock;
+				continue;
 			/* If the next lock in the list has entirely bigger
 			 * addresses than the new one, insert the lock here.
 			 */
@@ -1029,18 +1032,17 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			else
 				request->fl_end = fl->fl_end;
 			if (added) {
-				locks_delete_lock(before, &dispose);
+				locks_delete_lock_ctx(fl, &dispose);
 				continue;
 			}
 			request = fl;
 			added = true;
-		}
-		else {
+		} else {
 			/* Processing for different lock types is a bit
 			 * more complex.
 			 */
 			if (fl->fl_end < request->fl_start)
-				goto next_lock;
+				continue;
 			if (fl->fl_start > request->fl_end)
 				break;
 			if (request->fl_type == F_UNLCK)
@@ -1059,7 +1061,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 				 * one (This may happen several times).
 				 */
 				if (added) {
-					locks_delete_lock(before, &dispose);
+					locks_delete_lock_ctx(fl, &dispose);
 					continue;
 				}
 				/*
@@ -1075,15 +1077,11 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 				locks_copy_lock(new_fl, request);
 				request = new_fl;
 				new_fl = NULL;
-				locks_delete_lock(before, &dispose);
-				locks_insert_lock(before, request);
+				locks_insert_lock_ctx(request, &fl->fl_list);
+				locks_delete_lock_ctx(fl, &dispose);
 				added = true;
 			}
 		}
-		/* Go on to next lock.
-		 */
-	next_lock:
-		before = &fl->fl_next;
 	}
 
 	/*
@@ -1108,7 +1106,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			goto out;
 		}
 		locks_copy_lock(new_fl, request);
-		locks_insert_lock(before, new_fl);
+		locks_insert_lock_ctx(new_fl, &fl->fl_list);
+		fl = new_fl;
 		new_fl = NULL;
 	}
 	if (right) {
@@ -1119,7 +1118,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			left = new_fl2;
 			new_fl2 = NULL;
 			locks_copy_lock(left, right);
-			locks_insert_lock(before, left);
+			locks_insert_lock_ctx(left, &fl->fl_list);
 		}
 		right->fl_start = request->fl_end + 1;
 		locks_wake_up_blocks(right);
@@ -1129,7 +1128,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 		locks_wake_up_blocks(left);
 	}
  out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	/*
 	 * Free any unused locks.
 	 */
@@ -1199,22 +1198,29 @@ EXPORT_SYMBOL(posix_lock_file_wait);
  */
 int locks_mandatory_locked(struct file *file)
 {
+	int ret;
 	struct inode *inode = file_inode(file);
+	struct file_lock_context *ctx;
 	struct file_lock *fl;
 
+	ctx = inode->i_flctx;
+	if (!ctx || list_empty_careful(&ctx->flc_posix))
+		return 0;
+
 	/*
 	 * Search the lock list for this inode for any POSIX locks.
 	 */
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (!IS_POSIX(fl))
-			continue;
+	spin_lock(&ctx->flc_lock);
+	ret = 0;
+	list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
 		if (fl->fl_owner != current->files &&
-		    fl->fl_owner != file)
+		    fl->fl_owner != file) {
+			ret = -EAGAIN;
 			break;
+		}
 	}
-	spin_unlock(&inode->i_lock);
-	return fl ? -EAGAIN : 0;
+	spin_unlock(&ctx->flc_lock);
+	return ret;
 }
 
 /**
@@ -1294,9 +1300,8 @@ static void lease_clear_pending(struct file_lock *fl, int arg)
 }
 
 /* We already had a lease on this file; just change its type */
-int lease_modify(struct file_lock **before, int arg, struct list_head *dispose)
+int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose)
 {
-	struct file_lock *fl = *before;
 	int error = assign_type(fl, arg);
 
 	if (error)
@@ -1313,7 +1318,7 @@ int lease_modify(struct file_lock **before, int arg, struct list_head *dispose)
 			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
 			fl->fl_fasync = NULL;
 		}
-		locks_delete_lock(before, dispose);
+		locks_delete_lock_ctx(fl, dispose);
 	}
 	return 0;
 }
@@ -1329,25 +1334,24 @@ static bool past_time(unsigned long then)
 
 static void time_out_leases(struct inode *inode, struct list_head *dispose)
 {
-	struct file_lock **before;
-	struct file_lock *fl;
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl, *tmp;
 
-	lockdep_assert_held(&inode->i_lock);
+	lockdep_assert_held(&ctx->flc_lock);
 
-	before = &inode->i_flock;
-	while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) {
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
 		trace_time_out_leases(inode, fl);
 		if (past_time(fl->fl_downgrade_time))
-			lease_modify(before, F_RDLCK, dispose);
+			lease_modify(fl, F_RDLCK, dispose);
 		if (past_time(fl->fl_break_time))
-			lease_modify(before, F_UNLCK, dispose);
-		if (fl == *before)	/* lease_modify may have freed fl */
-			before = &fl->fl_next;
+			lease_modify(fl, F_UNLCK, dispose);
 	}
 }
 
 static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 {
+	if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT))
+		return false;
 	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE))
 		return false;
 	return locks_conflict(breaker, lease);
@@ -1356,11 +1360,12 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 static bool
 any_leases_conflict(struct inode *inode, struct file_lock *breaker)
 {
+	struct file_lock_context *ctx = inode->i_flctx;
 	struct file_lock *fl;
 
-	lockdep_assert_held(&inode->i_lock);
+	lockdep_assert_held(&ctx->flc_lock);
 
-	for (fl = inode->i_flock ; fl && IS_LEASE(fl); fl = fl->fl_next) {
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (leases_conflict(fl, breaker))
 			return true;
 	}
@@ -1384,7 +1389,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
 	struct file_lock *new_fl;
-	struct file_lock *fl, **before;
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl;
 	unsigned long break_time;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 	LIST_HEAD(dispose);
@@ -1394,7 +1400,13 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 		return PTR_ERR(new_fl);
 	new_fl->fl_flags = type;
 
-	spin_lock(&inode->i_lock);
+	/* typically we will check that ctx is non-NULL before calling */
+	if (!ctx) {
+		WARN_ON_ONCE(1);
+		return error;
+	}
+
+	spin_lock(&ctx->flc_lock);
 
 	time_out_leases(inode, &dispose);
 
@@ -1408,9 +1420,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			break_time++;	/* so that 0 means no break time */
 	}
 
-	for (before = &inode->i_flock;
-			((fl = *before) != NULL) && IS_LEASE(fl);
-			before = &fl->fl_next) {
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (!leases_conflict(fl, new_fl))
 			continue;
 		if (want_write) {
@@ -1419,17 +1429,16 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			fl->fl_flags |= FL_UNLOCK_PENDING;
 			fl->fl_break_time = break_time;
 		} else {
-			if (lease_breaking(inode->i_flock))
+			if (lease_breaking(fl))
 				continue;
 			fl->fl_flags |= FL_DOWNGRADE_PENDING;
 			fl->fl_downgrade_time = break_time;
 		}
 		if (fl->fl_lmops->lm_break(fl))
-			locks_delete_lock(before, &dispose);
+			locks_delete_lock_ctx(fl, &dispose);
 	}
 
-	fl = inode->i_flock;
-	if (!fl || !IS_LEASE(fl))
+	if (list_empty(&ctx->flc_lease))
 		goto out;
 
 	if (mode & O_NONBLOCK) {
@@ -1439,18 +1448,19 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 	}
 
 restart:
-	break_time = inode->i_flock->fl_break_time;
+	fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list);
+	break_time = fl->fl_break_time;
 	if (break_time != 0)
 		break_time -= jiffies;
 	if (break_time == 0)
 		break_time++;
-	locks_insert_block(inode->i_flock, new_fl);
+	locks_insert_block(fl, new_fl);
 	trace_break_lease_block(inode, new_fl);
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
 						!new_fl->fl_next, break_time);
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	trace_break_lease_unblock(inode, new_fl);
 	locks_delete_block(new_fl);
 	if (error >= 0) {
@@ -1462,12 +1472,10 @@ restart:
 			time_out_leases(inode, &dispose);
 		if (any_leases_conflict(inode, new_fl))
 			goto restart;
-
 		error = 0;
 	}
-
 out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	locks_free_lock(new_fl);
 	return error;
@@ -1487,14 +1495,18 @@ EXPORT_SYMBOL(__break_lease);
 void lease_get_mtime(struct inode *inode, struct timespec *time)
 {
 	bool has_lease = false;
-	struct file_lock *flock;
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl;
 
-	if (inode->i_flock) {
-		spin_lock(&inode->i_lock);
-		flock = inode->i_flock;
-		if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK))
-			has_lease = true;
-		spin_unlock(&inode->i_lock);
+	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
+		spin_lock(&ctx->flc_lock);
+		if (!list_empty(&ctx->flc_lease)) {
+			fl = list_first_entry(&ctx->flc_lease,
+						struct file_lock, fl_list);
+			if (fl->fl_type == F_WRLCK)
+				has_lease = true;
+		}
+		spin_unlock(&ctx->flc_lock);
 	}
 
 	if (has_lease)
@@ -1532,20 +1544,22 @@ int fcntl_getlease(struct file *filp)
 {
 	struct file_lock *fl;
 	struct inode *inode = file_inode(filp);
+	struct file_lock_context *ctx = inode->i_flctx;
 	int type = F_UNLCK;
 	LIST_HEAD(dispose);
 
-	spin_lock(&inode->i_lock);
-	time_out_leases(file_inode(filp), &dispose);
-	for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl);
-			fl = fl->fl_next) {
-		if (fl->fl_file == filp) {
+	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
+		spin_lock(&ctx->flc_lock);
+		time_out_leases(file_inode(filp), &dispose);
+		list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
+			if (fl->fl_file != filp)
+				continue;
 			type = target_leasetype(fl);
 			break;
 		}
+		spin_unlock(&ctx->flc_lock);
+		locks_dispose_list(&dispose);
 	}
-	spin_unlock(&inode->i_lock);
-	locks_dispose_list(&dispose);
 	return type;
 }
 
@@ -1560,11 +1574,14 @@ int fcntl_getlease(struct file *filp)
  * conflict with the lease we're trying to set.
  */
 static int
-check_conflicting_open(const struct dentry *dentry, const long arg)
+check_conflicting_open(const struct dentry *dentry, const long arg, int flags)
 {
 	int ret = 0;
 	struct inode *inode = dentry->d_inode;
 
+	if (flags & FL_LAYOUT)
+		return 0;
+
 	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
 		return -EAGAIN;
 
@@ -1578,9 +1595,10 @@ check_conflicting_open(const struct dentry *dentry, const long arg)
 static int
 generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv)
 {
-	struct file_lock *fl, **before, **my_before = NULL, *lease;
+	struct file_lock *fl, *my_fl = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	struct file_lock_context *ctx;
 	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
 	LIST_HEAD(dispose);
@@ -1588,6 +1606,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	lease = *flp;
 	trace_generic_add_lease(inode, lease);
 
+	ctx = locks_get_lock_context(inode);
+	if (!ctx)
+		return -ENOMEM;
+
 	/*
 	 * In the delegation case we need mutual exclusion with
 	 * a number of operations that take the i_mutex.  We trylock
@@ -1606,9 +1628,9 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 		return -EINVAL;
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	time_out_leases(inode, &dispose);
-	error = check_conflicting_open(dentry, arg);
+	error = check_conflicting_open(dentry, arg, lease->fl_flags);
 	if (error)
 		goto out;
 
@@ -1621,13 +1643,13 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 * except for this filp.
 	 */
 	error = -EAGAIN;
-	for (before = &inode->i_flock;
-			((fl = *before) != NULL) && IS_LEASE(fl);
-			before = &fl->fl_next) {
-		if (fl->fl_file == filp) {
-			my_before = before;
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
+		if (fl->fl_file == filp &&
+		    fl->fl_owner == lease->fl_owner) {
+			my_fl = fl;
 			continue;
 		}
+
 		/*
 		 * No exclusive leases if someone else has a lease on
 		 * this file:
@@ -1642,9 +1664,9 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 			goto out;
 	}
 
-	if (my_before != NULL) {
-		lease = *my_before;
-		error = lease->fl_lmops->lm_change(my_before, arg, &dispose);
+	if (my_fl != NULL) {
+		lease = my_fl;
+		error = lease->fl_lmops->lm_change(lease, arg, &dispose);
 		if (error)
 			goto out;
 		goto out_setup;
@@ -1654,7 +1676,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	if (!leases_enable)
 		goto out;
 
-	locks_insert_lock(before, lease);
+	locks_insert_lock_ctx(lease, &ctx->flc_lease);
 	/*
 	 * The check in break_lease() is lockless. It's possible for another
 	 * open to race in after we did the earlier check for a conflicting
@@ -1665,46 +1687,51 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 * precedes these checks.
 	 */
 	smp_mb();
-	error = check_conflicting_open(dentry, arg);
-	if (error)
-		goto out_unlink;
+	error = check_conflicting_open(dentry, arg, lease->fl_flags);
+	if (error) {
+		locks_unlink_lock_ctx(lease);
+		goto out;
+	}
 
 out_setup:
 	if (lease->fl_lmops->lm_setup)
 		lease->fl_lmops->lm_setup(lease, priv);
 out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
-	if (!error && !my_before)
+	if (!error && !my_fl)
 		*flp = NULL;
 	return error;
-out_unlink:
-	locks_unlink_lock(before);
-	goto out;
 }
 
-static int generic_delete_lease(struct file *filp)
+static int generic_delete_lease(struct file *filp, void *owner)
 {
 	int error = -EAGAIN;
-	struct file_lock *fl, **before;
+	struct file_lock *fl, *victim = NULL;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	struct file_lock_context *ctx = inode->i_flctx;
 	LIST_HEAD(dispose);
 
-	spin_lock(&inode->i_lock);
-	time_out_leases(inode, &dispose);
-	for (before = &inode->i_flock;
-			((fl = *before) != NULL) && IS_LEASE(fl);
-			before = &fl->fl_next) {
-		if (fl->fl_file == filp)
+	if (!ctx) {
+		trace_generic_delete_lease(inode, NULL);
+		return error;
+	}
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
+		if (fl->fl_file == filp &&
+		    fl->fl_owner == owner) {
+			victim = fl;
 			break;
+		}
 	}
-	trace_generic_delete_lease(inode, fl);
-	if (fl && IS_LEASE(fl))
-		error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose);
-	spin_unlock(&inode->i_lock);
+	trace_generic_delete_lease(inode, victim);
+	if (victim)
+		error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	return error;
 }
@@ -1737,13 +1764,14 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
 
 	switch (arg) {
 	case F_UNLCK:
-		return generic_delete_lease(filp);
+		return generic_delete_lease(filp, *priv);
 	case F_RDLCK:
 	case F_WRLCK:
 		if (!(*flp)->fl_lmops->lm_break) {
 			WARN_ON_ONCE(1);
 			return -ENOLCK;
 		}
+
 		return generic_add_lease(filp, arg, flp, priv);
 	default:
 		return -EINVAL;
@@ -1816,7 +1844,7 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
 	if (arg == F_UNLCK)
-		return vfs_setlease(filp, F_UNLCK, NULL, NULL);
+		return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp);
 	return do_fcntl_add_lease(fd, filp, arg);
 }
 
@@ -2171,7 +2199,7 @@ again:
 	 */
 	/*
 	 * we need that spin_lock here - it prevents reordering between
-	 * update of inode->i_flock and check for it done in close().
+	 * update of i_flctx->flc_posix and check for it done in close().
 	 * rcu_read_lock() wouldn't do.
 	 */
 	spin_lock(&current->files->file_lock);
@@ -2331,13 +2359,14 @@ out:
 void locks_remove_posix(struct file *filp, fl_owner_t owner)
 {
 	struct file_lock lock;
+	struct file_lock_context *ctx = file_inode(filp)->i_flctx;
 
 	/*
 	 * If there are no locks held on this file, we don't need to call
 	 * posix_lock_file().  Another process could be setting a lock on this
 	 * file at the same time, but we wouldn't remove that lock anyway.
 	 */
-	if (!file_inode(filp)->i_flock)
+	if (!ctx || list_empty(&ctx->flc_posix))
 		return;
 
 	lock.fl_type = F_UNLCK;
@@ -2358,67 +2387,68 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner)
 
 EXPORT_SYMBOL(locks_remove_posix);
 
+/* The i_flctx must be valid when calling into here */
+static void
+locks_remove_flock(struct file *filp)
+{
+	struct file_lock fl = {
+		.fl_owner = filp,
+		.fl_pid = current->tgid,
+		.fl_file = filp,
+		.fl_flags = FL_FLOCK,
+		.fl_type = F_UNLCK,
+		.fl_end = OFFSET_MAX,
+	};
+	struct file_lock_context *flctx = file_inode(filp)->i_flctx;
+
+	if (list_empty(&flctx->flc_flock))
+		return;
+
+	if (filp->f_op->flock)
+		filp->f_op->flock(filp, F_SETLKW, &fl);
+	else
+		flock_lock_file(filp, &fl);
+
+	if (fl.fl_ops && fl.fl_ops->fl_release_private)
+		fl.fl_ops->fl_release_private(&fl);
+}
+
+/* The i_flctx must be valid when calling into here */
+static void
+locks_remove_lease(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl, *tmp;
+	LIST_HEAD(dispose);
+
+	if (list_empty(&ctx->flc_lease))
+		return;
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
+		if (filp == fl->fl_file)
+			lease_modify(fl, F_UNLCK, &dispose);
+	spin_unlock(&ctx->flc_lock);
+	locks_dispose_list(&dispose);
+}
+
 /*
  * This function is called on the last close of an open file.
  */
 void locks_remove_file(struct file *filp)
 {
-	struct inode * inode = file_inode(filp);
-	struct file_lock *fl;
-	struct file_lock **before;
-	LIST_HEAD(dispose);
-
-	if (!inode->i_flock)
+	if (!file_inode(filp)->i_flctx)
 		return;
 
+	/* remove any OFD locks */
 	locks_remove_posix(filp, filp);
 
-	if (filp->f_op->flock) {
-		struct file_lock fl = {
-			.fl_owner = filp,
-			.fl_pid = current->tgid,
-			.fl_file = filp,
-			.fl_flags = FL_FLOCK,
-			.fl_type = F_UNLCK,
-			.fl_end = OFFSET_MAX,
-		};
-		filp->f_op->flock(filp, F_SETLKW, &fl);
-		if (fl.fl_ops && fl.fl_ops->fl_release_private)
-			fl.fl_ops->fl_release_private(&fl);
-	}
-
-	spin_lock(&inode->i_lock);
-	before = &inode->i_flock;
+	/* remove flock locks */
+	locks_remove_flock(filp);
 
-	while ((fl = *before) != NULL) {
-		if (fl->fl_file == filp) {
-			if (IS_LEASE(fl)) {
-				lease_modify(before, F_UNLCK, &dispose);
-				continue;
-			}
-
-			/*
-			 * There's a leftover lock on the list of a type that
-			 * we didn't expect to see. Most likely a classic
-			 * POSIX lock that ended up not getting released
-			 * properly, or that raced onto the list somehow. Log
-			 * some info about it and then just remove it from
-			 * the list.
-			 */
-			WARN(!IS_FLOCK(fl),
-				"leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n",
-				MAJOR(inode->i_sb->s_dev),
-				MINOR(inode->i_sb->s_dev), inode->i_ino,
-				fl->fl_type, fl->fl_flags,
-				fl->fl_start, fl->fl_end);
-
-			locks_delete_lock(before, &dispose);
-			continue;
- 		}
-		before = &fl->fl_next;
-	}
-	spin_unlock(&inode->i_lock);
-	locks_dispose_list(&dispose);
+	/* remove any leases */
+	locks_remove_lease(filp);
 }
 
 /**
@@ -2621,6 +2651,9 @@ static int __init filelock_init(void)
 {
 	int i;
 
+	flctx_cache = kmem_cache_create("file_lock_ctx",
+			sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL);
+
 	filelock_cache = kmem_cache_create("file_lock_cache",
 			sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
 
diff --git a/fs/mount.h b/fs/mount.h
index 0ad6f760ce52..6a61c2b3e385 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -2,6 +2,7 @@
 #include <linux/seq_file.h>
 #include <linux/poll.h>
 #include <linux/ns_common.h>
+#include <linux/fs_pin.h>
 
 struct mnt_namespace {
 	atomic_t		count;
@@ -62,7 +63,8 @@ struct mount {
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	struct hlist_head mnt_pins;
-	struct path mnt_ex_mountpoint;
+	struct fs_pin mnt_umount;
+	struct dentry *mnt_ex_mountpoint;
 };
 
 #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
diff --git a/fs/namei.c b/fs/namei.c
index bc35b02883bb..c83145af4bfc 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -118,15 +118,6 @@
  * POSIX.1 2.4: an empty pathname is invalid (ENOENT).
  * PATH_MAX includes the nul terminator --RR.
  */
-void final_putname(struct filename *name)
-{
-	if (name->separate) {
-		__putname(name->name);
-		kfree(name);
-	} else {
-		__putname(name);
-	}
-}
 
 #define EMBEDDED_NAME_MAX	(PATH_MAX - sizeof(struct filename))
 
@@ -145,6 +136,7 @@ getname_flags(const char __user *filename, int flags, int *empty)
 	result = __getname();
 	if (unlikely(!result))
 		return ERR_PTR(-ENOMEM);
+	result->refcnt = 1;
 
 	/*
 	 * First, try to embed the struct filename inside the names_cache
@@ -179,6 +171,7 @@ recopy:
 		}
 		result->name = kname;
 		result->separate = true;
+		result->refcnt = 1;
 		max = PATH_MAX;
 		goto recopy;
 	}
@@ -202,7 +195,7 @@ recopy:
 	return result;
 
 error:
-	final_putname(result);
+	putname(result);
 	return err;
 }
 
@@ -212,43 +205,56 @@ getname(const char __user * filename)
 	return getname_flags(filename, 0, NULL);
 }
 
-/*
- * The "getname_kernel()" interface doesn't do pathnames longer
- * than EMBEDDED_NAME_MAX. Deal with it - you're a kernel user.
- */
 struct filename *
 getname_kernel(const char * filename)
 {
 	struct filename *result;
-	char *kname;
-	int len;
-
-	len = strlen(filename);
-	if (len >= EMBEDDED_NAME_MAX)
-		return ERR_PTR(-ENAMETOOLONG);
+	int len = strlen(filename) + 1;
 
 	result = __getname();
 	if (unlikely(!result))
 		return ERR_PTR(-ENOMEM);
 
-	kname = (char *)result + sizeof(*result);
-	result->name = kname;
+	if (len <= EMBEDDED_NAME_MAX) {
+		result->name = (char *)(result) + sizeof(*result);
+		result->separate = false;
+	} else if (len <= PATH_MAX) {
+		struct filename *tmp;
+
+		tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+		if (unlikely(!tmp)) {
+			__putname(result);
+			return ERR_PTR(-ENOMEM);
+		}
+		tmp->name = (char *)result;
+		tmp->separate = true;
+		result = tmp;
+	} else {
+		__putname(result);
+		return ERR_PTR(-ENAMETOOLONG);
+	}
+	memcpy((char *)result->name, filename, len);
 	result->uptr = NULL;
 	result->aname = NULL;
-	result->separate = false;
+	result->refcnt = 1;
+	audit_getname(result);
 
-	strlcpy(kname, filename, EMBEDDED_NAME_MAX);
 	return result;
 }
 
-#ifdef CONFIG_AUDITSYSCALL
 void putname(struct filename *name)
 {
-	if (unlikely(!audit_dummy_context()))
-		return audit_putname(name);
-	final_putname(name);
+	BUG_ON(name->refcnt <= 0);
+
+	if (--name->refcnt > 0)
+		return;
+
+	if (name->separate) {
+		__putname(name->name);
+		kfree(name);
+	} else
+		__putname(name);
 }
-#endif
 
 static int check_acl(struct inode *inode, int mask)
 {
@@ -2036,31 +2042,47 @@ static int filename_lookup(int dfd, struct filename *name,
 static int do_path_lookup(int dfd, const char *name,
 				unsigned int flags, struct nameidata *nd)
 {
-	struct filename filename = { .name = name };
+	struct filename *filename = getname_kernel(name);
+	int retval = PTR_ERR(filename);
 
-	return filename_lookup(dfd, &filename, flags, nd);
+	if (!IS_ERR(filename)) {
+		retval = filename_lookup(dfd, filename, flags, nd);
+		putname(filename);
+	}
+	return retval;
 }
 
 /* does lookup, returns the object with parent locked */
 struct dentry *kern_path_locked(const char *name, struct path *path)
 {
+	struct filename *filename = getname_kernel(name);
 	struct nameidata nd;
 	struct dentry *d;
-	int err = do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, &nd);
-	if (err)
-		return ERR_PTR(err);
+	int err;
+
+	if (IS_ERR(filename))
+		return ERR_CAST(filename);
+
+	err = filename_lookup(AT_FDCWD, filename, LOOKUP_PARENT, &nd);
+	if (err) {
+		d = ERR_PTR(err);
+		goto out;
+	}
 	if (nd.last_type != LAST_NORM) {
 		path_put(&nd.path);
-		return ERR_PTR(-EINVAL);
+		d = ERR_PTR(-EINVAL);
+		goto out;
 	}
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
 	d = __lookup_hash(&nd.last, nd.path.dentry, 0);
 	if (IS_ERR(d)) {
 		mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 		path_put(&nd.path);
-		return d;
+		goto out;
 	}
 	*path = nd.path;
+out:
+	putname(filename);
 	return d;
 }
 
@@ -2351,13 +2373,17 @@ static int
 filename_mountpoint(int dfd, struct filename *s, struct path *path,
 			unsigned int flags)
 {
-	int error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_RCU);
+	int error;
+	if (IS_ERR(s))
+		return PTR_ERR(s);
+	error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_RCU);
 	if (unlikely(error == -ECHILD))
 		error = path_mountpoint(dfd, s->name, path, flags);
 	if (unlikely(error == -ESTALE))
 		error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_REVAL);
 	if (likely(!error))
 		audit_inode(s, path->dentry, 0);
+	putname(s);
 	return error;
 }
 
@@ -2379,21 +2405,14 @@ int
 user_path_mountpoint_at(int dfd, const char __user *name, unsigned int flags,
 			struct path *path)
 {
-	struct filename *s = getname(name);
-	int error;
-	if (IS_ERR(s))
-		return PTR_ERR(s);
-	error = filename_mountpoint(dfd, s, path, flags);
-	putname(s);
-	return error;
+	return filename_mountpoint(dfd, getname(name), path, flags);
 }
 
 int
 kern_path_mountpoint(int dfd, const char *name, struct path *path,
 			unsigned int flags)
 {
-	struct filename s = {.name = name};
-	return filename_mountpoint(dfd, &s, path, flags);
+	return filename_mountpoint(dfd, getname_kernel(name), path, flags);
 }
 EXPORT_SYMBOL(kern_path_mountpoint);
 
@@ -2795,7 +2814,7 @@ no_open:
 			} else if (!dentry->d_inode) {
 				goto out;
 			} else if ((open_flag & O_TRUNC) &&
-				   S_ISREG(dentry->d_inode->i_mode)) {
+				   d_is_reg(dentry)) {
 				goto out;
 			}
 			/* will fail later, go on to get the right error */
@@ -3273,7 +3292,7 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 {
 	struct nameidata nd;
 	struct file *file;
-	struct filename filename = { .name = name };
+	struct filename *filename;
 	int flags = op->lookup_flags | LOOKUP_ROOT;
 
 	nd.root.mnt = mnt;
@@ -3282,15 +3301,20 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 	if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN)
 		return ERR_PTR(-ELOOP);
 
-	file = path_openat(-1, &filename, &nd, op, flags | LOOKUP_RCU);
+	filename = getname_kernel(name);
+	if (unlikely(IS_ERR(filename)))
+		return ERR_CAST(filename);
+
+	file = path_openat(-1, filename, &nd, op, flags | LOOKUP_RCU);
 	if (unlikely(file == ERR_PTR(-ECHILD)))
-		file = path_openat(-1, &filename, &nd, op, flags);
+		file = path_openat(-1, filename, &nd, op, flags);
 	if (unlikely(file == ERR_PTR(-ESTALE)))
-		file = path_openat(-1, &filename, &nd, op, flags | LOOKUP_REVAL);
+		file = path_openat(-1, filename, &nd, op, flags | LOOKUP_REVAL);
+	putname(filename);
 	return file;
 }
 
-struct dentry *kern_path_create(int dfd, const char *pathname,
+static struct dentry *filename_create(int dfd, struct filename *name,
 				struct path *path, unsigned int lookup_flags)
 {
 	struct dentry *dentry = ERR_PTR(-EEXIST);
@@ -3305,7 +3329,7 @@ struct dentry *kern_path_create(int dfd, const char *pathname,
 	 */
 	lookup_flags &= LOOKUP_REVAL;
 
-	error = do_path_lookup(dfd, pathname, LOOKUP_PARENT|lookup_flags, &nd);
+	error = filename_lookup(dfd, name, LOOKUP_PARENT|lookup_flags, &nd);
 	if (error)
 		return ERR_PTR(error);
 
@@ -3359,6 +3383,19 @@ out:
 	path_put(&nd.path);
 	return dentry;
 }
+
+struct dentry *kern_path_create(int dfd, const char *pathname,
+				struct path *path, unsigned int lookup_flags)
+{
+	struct filename *filename = getname_kernel(pathname);
+	struct dentry *res;
+
+	if (IS_ERR(filename))
+		return ERR_CAST(filename);
+	res = filename_create(dfd, filename, path, lookup_flags);
+	putname(filename);
+	return res;
+}
 EXPORT_SYMBOL(kern_path_create);
 
 void done_path_create(struct path *path, struct dentry *dentry)
@@ -3377,7 +3414,7 @@ struct dentry *user_path_create(int dfd, const char __user *pathname,
 	struct dentry *res;
 	if (IS_ERR(tmp))
 		return ERR_CAST(tmp);
-	res = kern_path_create(dfd, tmp->name, path, lookup_flags);
+	res = filename_create(dfd, tmp, path, lookup_flags);
 	putname(tmp);
 	return res;
 }
diff --git a/fs/namespace.c b/fs/namespace.c
index cd1e9681a0cf..82ef1405260e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -190,6 +190,14 @@ unsigned int mnt_get_count(struct mount *mnt)
 #endif
 }
 
+static void drop_mountpoint(struct fs_pin *p)
+{
+	struct mount *m = container_of(p, struct mount, mnt_umount);
+	dput(m->mnt_ex_mountpoint);
+	pin_remove(p);
+	mntput(&m->mnt);
+}
+
 static struct mount *alloc_vfsmnt(const char *name)
 {
 	struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
@@ -201,7 +209,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 			goto out_free_cache;
 
 		if (name) {
-			mnt->mnt_devname = kstrdup(name, GFP_KERNEL);
+			mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL);
 			if (!mnt->mnt_devname)
 				goto out_free_id;
 		}
@@ -229,12 +237,13 @@ static struct mount *alloc_vfsmnt(const char *name)
 #ifdef CONFIG_FSNOTIFY
 		INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
 #endif
+		init_fs_pin(&mnt->mnt_umount, drop_mountpoint);
 	}
 	return mnt;
 
 #ifdef CONFIG_SMP
 out_free_devname:
-	kfree(mnt->mnt_devname);
+	kfree_const(mnt->mnt_devname);
 #endif
 out_free_id:
 	mnt_free_id(mnt);
@@ -568,7 +577,7 @@ int sb_prepare_remount_readonly(struct super_block *sb)
 
 static void free_vfsmnt(struct mount *mnt)
 {
-	kfree(mnt->mnt_devname);
+	kfree_const(mnt->mnt_devname);
 #ifdef CONFIG_SMP
 	free_percpu(mnt->mnt_pcp);
 #endif
@@ -1289,7 +1298,6 @@ static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
 
 static void namespace_unlock(void)
 {
-	struct mount *mnt;
 	struct hlist_head head = unmounted;
 
 	if (likely(hlist_empty(&head))) {
@@ -1299,23 +1307,11 @@ static void namespace_unlock(void)
 
 	head.first->pprev = &head.first;
 	INIT_HLIST_HEAD(&unmounted);
-
-	/* undo decrements we'd done in umount_tree() */
-	hlist_for_each_entry(mnt, &head, mnt_hash)
-		if (mnt->mnt_ex_mountpoint.mnt)
-			mntget(mnt->mnt_ex_mountpoint.mnt);
-
 	up_write(&namespace_sem);
 
 	synchronize_rcu();
 
-	while (!hlist_empty(&head)) {
-		mnt = hlist_entry(head.first, struct mount, mnt_hash);
-		hlist_del_init(&mnt->mnt_hash);
-		if (mnt->mnt_ex_mountpoint.mnt)
-			path_put(&mnt->mnt_ex_mountpoint);
-		mntput(&mnt->mnt);
-	}
+	group_pin_kill(&head);
 }
 
 static inline void namespace_lock(void)
@@ -1334,7 +1330,6 @@ void umount_tree(struct mount *mnt, int how)
 {
 	HLIST_HEAD(tmp_list);
 	struct mount *p;
-	struct mount *last = NULL;
 
 	for (p = mnt; p; p = next_mnt(p, mnt)) {
 		hlist_del_init_rcu(&p->mnt_hash);
@@ -1347,33 +1342,28 @@ void umount_tree(struct mount *mnt, int how)
 	if (how)
 		propagate_umount(&tmp_list);
 
-	hlist_for_each_entry(p, &tmp_list, mnt_hash) {
+	while (!hlist_empty(&tmp_list)) {
+		p = hlist_entry(tmp_list.first, struct mount, mnt_hash);
+		hlist_del_init_rcu(&p->mnt_hash);
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
 		p->mnt_ns = NULL;
 		if (how < 2)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
+
+		pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt, &unmounted);
 		if (mnt_has_parent(p)) {
 			hlist_del_init(&p->mnt_mp_list);
 			put_mountpoint(p->mnt_mp);
 			mnt_add_count(p->mnt_parent, -1);
-			/* move the reference to mountpoint into ->mnt_ex_mountpoint */
-			p->mnt_ex_mountpoint.dentry = p->mnt_mountpoint;
-			p->mnt_ex_mountpoint.mnt = &p->mnt_parent->mnt;
+			/* old mountpoint will be dropped when we can do that */
+			p->mnt_ex_mountpoint = p->mnt_mountpoint;
 			p->mnt_mountpoint = p->mnt.mnt_root;
 			p->mnt_parent = p;
 			p->mnt_mp = NULL;
 		}
 		change_mnt_propagation(p, MS_PRIVATE);
-		last = p;
-	}
-	if (last) {
-		last->mnt_hash.next = unmounted.first;
-		if (unmounted.first)
-			unmounted.first->pprev = &last->mnt_hash.next;
-		unmounted.first = tmp_list.first;
-		unmounted.first->pprev = &unmounted.first;
 	}
 }
 
@@ -1917,8 +1907,8 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
 	if (mnt->mnt.mnt_sb->s_flags & MS_NOUSER)
 		return -EINVAL;
 
-	if (S_ISDIR(mp->m_dentry->d_inode->i_mode) !=
-	      S_ISDIR(mnt->mnt.mnt_root->d_inode->i_mode))
+	if (d_is_dir(mp->m_dentry) !=
+	      d_is_dir(mnt->mnt.mnt_root))
 		return -ENOTDIR;
 
 	return attach_recursive_mnt(mnt, p, mp, NULL);
@@ -2190,8 +2180,8 @@ static int do_move_mount(struct path *path, const char *old_name)
 	if (!mnt_has_parent(old))
 		goto out1;
 
-	if (S_ISDIR(path->dentry->d_inode->i_mode) !=
-	      S_ISDIR(old_path.dentry->d_inode->i_mode))
+	if (d_is_dir(path->dentry) !=
+	      d_is_dir(old_path.dentry))
 		goto out1;
 	/*
 	 * Don't move a mount residing in a shared parent.
@@ -2281,7 +2271,7 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
 		goto unlock;
 
 	err = -EINVAL;
-	if (S_ISLNK(newmnt->mnt.mnt_root->d_inode->i_mode))
+	if (d_is_symlink(newmnt->mnt.mnt_root))
 		goto unlock;
 
 	newmnt->mnt.mnt_flags = mnt_flags;
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 008960101520..e7ca827d7694 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -77,6 +77,7 @@ static int ncp_hash_dentry(const struct dentry *, struct qstr *);
 static int ncp_compare_dentry(const struct dentry *, const struct dentry *,
 		unsigned int, const char *, const struct qstr *);
 static int ncp_delete_dentry(const struct dentry *);
+static void ncp_d_prune(struct dentry *dentry);
 
 const struct dentry_operations ncp_dentry_operations =
 {
@@ -84,6 +85,7 @@ const struct dentry_operations ncp_dentry_operations =
 	.d_hash		= ncp_hash_dentry,
 	.d_compare	= ncp_compare_dentry,
 	.d_delete	= ncp_delete_dentry,
+	.d_prune	= ncp_d_prune,
 };
 
 #define ncp_namespace(i)	(NCP_SERVER(i)->name_space[NCP_FINFO(i)->volNumber])
@@ -384,42 +386,6 @@ finished:
 	return val;
 }
 
-static struct dentry *
-ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
-{
-	struct dentry *dent = dentry;
-
-	if (d_validate(dent, parent)) {
-		if (dent->d_name.len <= NCP_MAXPATHLEN &&
-		    (unsigned long)dent->d_fsdata == fpos) {
-			if (!dent->d_inode) {
-				dput(dent);
-				dent = NULL;
-			}
-			return dent;
-		}
-		dput(dent);
-	}
-
-	/* If a pointer is invalid, we search the dentry. */
-	spin_lock(&parent->d_lock);
-	list_for_each_entry(dent, &parent->d_subdirs, d_child) {
-		if ((unsigned long)dent->d_fsdata == fpos) {
-			if (dent->d_inode)
-				dget(dent);
-			else
-				dent = NULL;
-			spin_unlock(&parent->d_lock);
-			goto out;
-		}
-	}
-	spin_unlock(&parent->d_lock);
-	return NULL;
-
-out:
-	return dent;
-}
-
 static time_t ncp_obtain_mtime(struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
@@ -435,6 +401,20 @@ static time_t ncp_obtain_mtime(struct dentry *dentry)
 	return ncp_date_dos2unix(i.modifyTime, i.modifyDate);
 }
 
+static inline void
+ncp_invalidate_dircache_entries(struct dentry *parent)
+{
+	struct ncp_server *server = NCP_SERVER(parent->d_inode);
+	struct dentry *dentry;
+
+	spin_lock(&parent->d_lock);
+	list_for_each_entry(dentry, &parent->d_subdirs, d_child) {
+		dentry->d_fsdata = NULL;
+		ncp_age_dentry(server, dentry);
+	}
+	spin_unlock(&parent->d_lock);
+}
+
 static int ncp_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct dentry *dentry = file->f_path.dentry;
@@ -500,10 +480,21 @@ static int ncp_readdir(struct file *file, struct dir_context *ctx)
 			struct dentry *dent;
 			bool over;
 
-			dent = ncp_dget_fpos(ctl.cache->dentry[ctl.idx],
-						dentry, ctx->pos);
-			if (!dent)
+			spin_lock(&dentry->d_lock);
+			if (!(NCP_FINFO(inode)->flags & NCPI_DIR_CACHE)) { 
+				spin_unlock(&dentry->d_lock);
+				goto invalid_cache;
+			}
+			dent = ctl.cache->dentry[ctl.idx];
+			if (unlikely(!lockref_get_not_dead(&dent->d_lockref))) {
+				spin_unlock(&dentry->d_lock);
+				goto invalid_cache;
+			}
+			spin_unlock(&dentry->d_lock);
+			if (!dent->d_inode) {
+				dput(dent);
 				goto invalid_cache;
+			}
 			over = !dir_emit(ctx, dent->d_name.name,
 					dent->d_name.len,
 					dent->d_inode->i_ino, DT_UNKNOWN);
@@ -548,6 +539,9 @@ init_cache:
 	ctl.filled = 0;
 	ctl.valid  = 1;
 read_really:
+	spin_lock(&dentry->d_lock);
+	NCP_FINFO(inode)->flags |= NCPI_DIR_CACHE;
+	spin_unlock(&dentry->d_lock);
 	if (ncp_is_server_root(inode)) {
 		ncp_read_volume_list(file, ctx, &ctl);
 	} else {
@@ -573,6 +567,13 @@ out:
 	return result;
 }
 
+static void ncp_d_prune(struct dentry *dentry)
+{
+	if (!dentry->d_fsdata)	/* not referenced from page cache */
+		return;
+	NCP_FINFO(dentry->d_parent->d_inode)->flags &= ~NCPI_DIR_CACHE;
+}
+
 static int
 ncp_fill_cache(struct file *file, struct dir_context *ctx,
 		struct ncp_cache_control *ctrl, struct ncp_entry_info *entry,
@@ -630,6 +631,10 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx,
 			d_instantiate(newdent, inode);
 			if (!hashed)
 				d_rehash(newdent);
+		} else {
+			spin_lock(&dentry->d_lock);
+			NCP_FINFO(inode)->flags &= ~NCPI_DIR_CACHE;
+			spin_unlock(&dentry->d_lock);
 		}
 	} else {
 		struct inode *inode = newdent->d_inode;
@@ -639,12 +644,6 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx,
 		mutex_unlock(&inode->i_mutex);
 	}
 
-	if (newdent->d_inode) {
-		ino = newdent->d_inode->i_ino;
-		newdent->d_fsdata = (void *) ctl.fpos;
-		ncp_new_dentry(newdent);
-	}
-
 	if (ctl.idx >= NCP_DIRCACHE_SIZE) {
 		if (ctl.page) {
 			kunmap(ctl.page);
@@ -660,8 +659,13 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx,
 			ctl.cache = kmap(ctl.page);
 	}
 	if (ctl.cache) {
-		ctl.cache->dentry[ctl.idx] = newdent;
-		valid = 1;
+		if (newdent->d_inode) {
+			newdent->d_fsdata = newdent;
+			ctl.cache->dentry[ctl.idx] = newdent;
+			ino = newdent->d_inode->i_ino;
+			ncp_new_dentry(newdent);
+		}
+ 		valid = 1;
 	}
 	dput(newdent);
 end_advance:
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index e31e589369a4..01a9e16e9782 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -267,7 +267,6 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
 	if (inode) {
 		atomic_set(&NCP_FINFO(inode)->opened, info->opened);
 
-		inode->i_mapping->backing_dev_info = sb->s_bdi;
 		inode->i_ino = info->ino;
 		ncp_set_attr(inode, info);
 		if (S_ISREG(inode->i_mode)) {
@@ -560,7 +559,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	server = NCP_SBP(sb);
 	memset(server, 0, sizeof(*server));
 
-	error = bdi_setup_and_register(&server->bdi, "ncpfs", BDI_CAP_MAP_COPY);
+	error = bdi_setup_and_register(&server->bdi, "ncpfs");
 	if (error)
 		goto out_fput;
 
diff --git a/fs/ncpfs/ncp_fs_i.h b/fs/ncpfs/ncp_fs_i.h
index 4b0bec477846..c4794504f843 100644
--- a/fs/ncpfs/ncp_fs_i.h
+++ b/fs/ncpfs/ncp_fs_i.h
@@ -22,6 +22,7 @@ struct ncp_inode_info {
 	int	access;
 	int	flags;
 #define NCPI_KLUDGE_SYMLINK	0x0001
+#define NCPI_DIR_CACHE		0x0002
 	__u8	file_handle[6];
 	struct inode vfs_inode;
 };
diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h
index b785f74bfe3c..250e443a07f3 100644
--- a/fs/ncpfs/ncplib_kernel.h
+++ b/fs/ncpfs/ncplib_kernel.h
@@ -184,36 +184,6 @@ ncp_new_dentry(struct dentry* dentry)
 	dentry->d_time = jiffies;
 }
 
-static inline void
-ncp_renew_dentries(struct dentry *parent)
-{
-	struct ncp_server *server = NCP_SERVER(parent->d_inode);
-	struct dentry *dentry;
-
-	spin_lock(&parent->d_lock);
-	list_for_each_entry(dentry, &parent->d_subdirs, d_child) {
-		if (dentry->d_fsdata == NULL)
-			ncp_age_dentry(server, dentry);
-		else
-			ncp_new_dentry(dentry);
-	}
-	spin_unlock(&parent->d_lock);
-}
-
-static inline void
-ncp_invalidate_dircache_entries(struct dentry *parent)
-{
-	struct ncp_server *server = NCP_SERVER(parent->d_inode);
-	struct dentry *dentry;
-
-	spin_lock(&parent->d_lock);
-	list_for_each_entry(dentry, &parent->d_subdirs, d_child) {
-		dentry->d_fsdata = NULL;
-		ncp_age_dentry(server, dentry);
-	}
-	spin_unlock(&parent->d_lock);
-}
-
 struct ncp_cache_head {
 	time_t		mtime;
 	unsigned long	time;	/* cache age */
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 3dece03f2fc8..c7abc10279af 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -128,6 +128,11 @@ config PNFS_OBJLAYOUT
 	depends on NFS_V4_1 && SCSI_OSD_ULD
 	default NFS_V4
 
+config PNFS_FLEXFILE_LAYOUT
+	tristate
+	depends on NFS_V4_1 && NFS_V3
+	default m
+
 config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
 	string "NFSv4.1 Implementation ID Domain"
 	depends on NFS_V4_1
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 04cb830fa09f..1e987acf20c9 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -27,9 +27,10 @@ nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o
 	  dns_resolve.o nfs4trace.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
 nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
-nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
+nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o pnfs_nfs.o
 nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
 obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
 obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
+obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 77fec6a55f57..1cac3c175d18 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -860,12 +860,14 @@ static const struct nfs_pageio_ops bl_pg_read_ops = {
 	.pg_init = bl_pg_init_read,
 	.pg_test = bl_pg_test_read,
 	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static const struct nfs_pageio_ops bl_pg_write_ops = {
 	.pg_init = bl_pg_init_write,
 	.pg_test = bl_pg_test_write,
 	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static struct pnfs_layoutdriver_type blocklayout_type = {
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index b8fb3a4ef649..351be9205bf8 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -128,22 +128,24 @@ nfs41_callback_svc(void *vrqstp)
 		if (try_to_freeze())
 			continue;
 
-		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
+		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE);
 		spin_lock_bh(&serv->sv_cb_lock);
 		if (!list_empty(&serv->sv_cb_list)) {
 			req = list_first_entry(&serv->sv_cb_list,
 					struct rpc_rqst, rq_bc_list);
 			list_del(&req->rq_bc_list);
 			spin_unlock_bh(&serv->sv_cb_lock);
+			finish_wait(&serv->sv_cb_waitq, &wq);
 			dprintk("Invoking bc_svc_process()\n");
 			error = bc_svc_process(serv, req, rqstp);
 			dprintk("bc_svc_process() returned w/ error code= %d\n",
 				error);
 		} else {
 			spin_unlock_bh(&serv->sv_cb_lock);
-			schedule();
+			/* schedule_timeout to game the hung task watchdog */
+			schedule_timeout(60 * HZ);
+			finish_wait(&serv->sv_cb_waitq, &wq);
 		}
-		finish_wait(&serv->sv_cb_waitq, &wq);
 	}
 	return 0;
 }
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index e36a9d78ea49..197806fb87ff 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -427,6 +427,8 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 	if (clp == NULL)
 		goto out;
 
+	if (!(clp->cl_session->flags & SESSION4_BACK_CHAN))
+		goto out;
 	tbl = &clp->cl_session->bc_slot_table;
 
 	spin_lock(&tbl->slot_tbl_lock);
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index f4ccfe6521ec..19ca95cdfd9b 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -313,7 +313,7 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp,
 		goto out;
 	}
 
-	args->devs = kmalloc(n * sizeof(*args->devs), GFP_KERNEL);
+	args->devs = kmalloc_array(n, sizeof(*args->devs), GFP_KERNEL);
 	if (!args->devs) {
 		status = htonl(NFS4ERR_DELAY);
 		goto out;
@@ -415,7 +415,7 @@ static __be32 decode_rc_list(struct xdr_stream *xdr,
 			     rc_list->rcl_nrefcalls * 2 * sizeof(uint32_t));
 		if (unlikely(p == NULL))
 			goto out;
-		rc_list->rcl_refcalls = kmalloc(rc_list->rcl_nrefcalls *
+		rc_list->rcl_refcalls = kmalloc_array(rc_list->rcl_nrefcalls,
 						sizeof(*rc_list->rcl_refcalls),
 						GFP_KERNEL);
 		if (unlikely(rc_list->rcl_refcalls == NULL))
@@ -464,8 +464,10 @@ static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp,
 
 		for (i = 0; i < args->csa_nrclists; i++) {
 			status = decode_rc_list(xdr, &args->csa_rclists[i]);
-			if (status)
+			if (status) {
+				args->csa_nrclists = i;
 				goto out_free;
+			}
 		}
 	}
 	status = 0;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index f9f4845db989..19874151e95c 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -433,7 +433,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 
 static bool nfs_client_init_is_complete(const struct nfs_client *clp)
 {
-	return clp->cl_cons_state != NFS_CS_INITING;
+	return clp->cl_cons_state <= NFS_CS_READY;
 }
 
 int nfs_wait_client_init_complete(const struct nfs_client *clp)
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 7f3f60641344..a6ad68865880 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -85,25 +85,30 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 {
 	struct inode *inode = state->inode;
 	struct file_lock *fl;
+	struct file_lock_context *flctx = inode->i_flctx;
+	struct list_head *list;
 	int status = 0;
 
-	if (inode->i_flock == NULL)
+	if (flctx == NULL)
 		goto out;
 
-	/* Protect inode->i_flock using the i_lock */
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
-			continue;
+	list = &flctx->flc_posix;
+	spin_lock(&flctx->flc_lock);
+restart:
+	list_for_each_entry(fl, list, fl_list) {
 		if (nfs_file_open_context(fl->fl_file) != ctx)
 			continue;
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&flctx->flc_lock);
 		status = nfs4_lock_delegation_recall(fl, state, stateid);
 		if (status < 0)
 			goto out;
-		spin_lock(&inode->i_lock);
+		spin_lock(&flctx->flc_lock);
 	}
-	spin_unlock(&inode->i_lock);
+	if (list == &flctx->flc_posix) {
+		list = &flctx->flc_flock;
+		goto restart;
+	}
+	spin_unlock(&flctx->flc_lock);
 out:
 	return status;
 }
@@ -175,10 +180,9 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
 			delegation->cred = get_rpccred(cred);
 			clear_bit(NFS_DELEGATION_NEED_RECLAIM,
 				  &delegation->flags);
-			NFS_I(inode)->delegation_state = delegation->type;
 			spin_unlock(&delegation->lock);
-			put_rpccred(oldcred);
 			rcu_read_unlock();
+			put_rpccred(oldcred);
 			trace_nfs4_reclaim_delegation(inode, res->delegation_type);
 		} else {
 			/* We appear to have raced with a delegation return. */
@@ -270,7 +274,6 @@ nfs_detach_delegation_locked(struct nfs_inode *nfsi,
 	set_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
 	list_del_rcu(&delegation->super_list);
 	delegation->inode = NULL;
-	nfsi->delegation_state = 0;
 	rcu_assign_pointer(nfsi->delegation, NULL);
 	spin_unlock(&delegation->lock);
 	return delegation;
@@ -301,6 +304,17 @@ nfs_inode_detach_delegation(struct inode *inode)
 	return nfs_detach_delegation(nfsi, delegation, server);
 }
 
+static void
+nfs_update_inplace_delegation(struct nfs_delegation *delegation,
+		const struct nfs_delegation *update)
+{
+	if (nfs4_stateid_is_newer(&update->stateid, &delegation->stateid)) {
+		delegation->stateid.seqid = update->stateid.seqid;
+		smp_wmb();
+		delegation->type = update->type;
+	}
+}
+
 /**
  * nfs_inode_set_delegation - set up a delegation on an inode
  * @inode: inode to which delegation applies
@@ -334,9 +348,11 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 	old_delegation = rcu_dereference_protected(nfsi->delegation,
 					lockdep_is_held(&clp->cl_lock));
 	if (old_delegation != NULL) {
-		if (nfs4_stateid_match(&delegation->stateid,
-					&old_delegation->stateid) &&
-				delegation->type == old_delegation->type) {
+		/* Is this an update of the existing delegation? */
+		if (nfs4_stateid_match_other(&old_delegation->stateid,
+					&delegation->stateid)) {
+			nfs_update_inplace_delegation(old_delegation,
+					delegation);
 			goto out;
 		}
 		/*
@@ -354,13 +370,15 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 			delegation = NULL;
 			goto out;
 		}
-		freeme = nfs_detach_delegation_locked(nfsi, 
+		if (test_and_set_bit(NFS_DELEGATION_RETURNING,
+					&old_delegation->flags))
+			goto out;
+		freeme = nfs_detach_delegation_locked(nfsi,
 				old_delegation, clp);
 		if (freeme == NULL)
 			goto out;
 	}
 	list_add_rcu(&delegation->super_list, &server->delegations);
-	nfsi->delegation_state = delegation->type;
 	rcu_assign_pointer(nfsi->delegation, delegation);
 	delegation = NULL;
 
@@ -418,6 +436,8 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 {
 	bool ret = false;
 
+	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
+		goto out;
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
 		ret = true;
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) && !ret) {
@@ -429,6 +449,7 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 			ret = true;
 		spin_unlock(&delegation->lock);
 	}
+out:
 	return ret;
 }
 
@@ -456,14 +477,20 @@ restart:
 								super_list) {
 			if (!nfs_delegation_need_return(delegation))
 				continue;
-			inode = nfs_delegation_grab_inode(delegation);
-			if (inode == NULL)
+			if (!nfs_sb_active(server->super))
 				continue;
+			inode = nfs_delegation_grab_inode(delegation);
+			if (inode == NULL) {
+				rcu_read_unlock();
+				nfs_sb_deactive(server->super);
+				goto restart;
+			}
 			delegation = nfs_start_delegation_return_locked(NFS_I(inode));
 			rcu_read_unlock();
 
 			err = nfs_end_delegation_return(inode, delegation, 0);
 			iput(inode);
+			nfs_sb_deactive(server->super);
 			if (!err)
 				goto restart;
 			set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
@@ -794,19 +821,30 @@ restart:
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
 		list_for_each_entry_rcu(delegation, &server->delegations,
 								super_list) {
+			if (test_bit(NFS_DELEGATION_RETURNING,
+						&delegation->flags))
+				continue;
 			if (test_bit(NFS_DELEGATION_NEED_RECLAIM,
 						&delegation->flags) == 0)
 				continue;
-			inode = nfs_delegation_grab_inode(delegation);
-			if (inode == NULL)
+			if (!nfs_sb_active(server->super))
 				continue;
-			delegation = nfs_detach_delegation(NFS_I(inode),
-					delegation, server);
+			inode = nfs_delegation_grab_inode(delegation);
+			if (inode == NULL) {
+				rcu_read_unlock();
+				nfs_sb_deactive(server->super);
+				goto restart;
+			}
+			delegation = nfs_start_delegation_return_locked(NFS_I(inode));
 			rcu_read_unlock();
-
-			if (delegation != NULL)
-				nfs_free_delegation(delegation);
+			if (delegation != NULL) {
+				delegation = nfs_detach_delegation(NFS_I(inode),
+					delegation, server);
+				if (delegation != NULL)
+					nfs_free_delegation(delegation);
+			}
 			iput(inode);
+			nfs_sb_deactive(server->super);
 			goto restart;
 		}
 	}
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 9b0c55cb2a2e..c19e16f0b2d0 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -408,14 +408,22 @@ static int xdr_decode(nfs_readdir_descriptor_t *desc,
 	return 0;
 }
 
+/* Match file and dirent using either filehandle or fileid
+ * Note: caller is responsible for checking the fsid
+ */
 static
 int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
 {
+	struct nfs_inode *nfsi;
+
 	if (dentry->d_inode == NULL)
 		goto different;
-	if (nfs_compare_fh(entry->fh, NFS_FH(dentry->d_inode)) != 0)
-		goto different;
-	return 1;
+
+	nfsi = NFS_I(dentry->d_inode);
+	if (entry->fattr->fileid == nfsi->fileid)
+		return 1;
+	if (nfs_compare_fh(entry->fh, &nfsi->fh) == 0)
+		return 1;
 different:
 	return 0;
 }
@@ -469,6 +477,10 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 	struct inode *inode;
 	int status;
 
+	if (!(entry->fattr->valid & NFS_ATTR_FATTR_FILEID))
+		return;
+	if (!(entry->fattr->valid & NFS_ATTR_FATTR_FSID))
+		return;
 	if (filename.name[0] == '.') {
 		if (filename.len == 1)
 			return;
@@ -479,6 +491,10 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 
 	dentry = d_lookup(parent, &filename);
 	if (dentry != NULL) {
+		/* Is there a mountpoint here? If so, just exit */
+		if (!nfs_fsid_equal(&NFS_SB(dentry->d_sb)->fsid,
+					&entry->fattr->fsid))
+			goto out;
 		if (nfs_same_file(dentry, entry)) {
 			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 			status = nfs_refresh_inode(dentry->d_inode, entry->fattr);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 294692ff83b1..e907c8cf732e 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -66,6 +66,10 @@ static struct kmem_cache *nfs_direct_cachep;
 /*
  * This represents a set of asynchronous requests that we're waiting on
  */
+struct nfs_direct_mirror {
+	ssize_t count;
+};
+
 struct nfs_direct_req {
 	struct kref		kref;		/* release manager */
 
@@ -78,8 +82,13 @@ struct nfs_direct_req {
 	/* completion state */
 	atomic_t		io_count;	/* i/os we're waiting for */
 	spinlock_t		lock;		/* protect completion state */
+
+	struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX];
+	int			mirror_count;
+
 	ssize_t			count,		/* bytes actually processed */
 				bytes_left,	/* bytes left to be sent */
+				io_start,	/* start of IO */
 				error;		/* any reported error */
 	struct completion	completion;	/* wait for i/o completion */
 
@@ -108,26 +117,56 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
 	return atomic_dec_and_test(&dreq->io_count);
 }
 
+void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq)
+{
+	dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+}
+EXPORT_SYMBOL_GPL(nfs_direct_set_resched_writes);
+
+static void
+nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
+{
+	int i;
+	ssize_t count;
+
+	WARN_ON_ONCE(hdr->pgio_mirror_idx >= dreq->mirror_count);
+
+	count = dreq->mirrors[hdr->pgio_mirror_idx].count;
+	if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
+		count = hdr->io_start + hdr->good_bytes - dreq->io_start;
+		dreq->mirrors[hdr->pgio_mirror_idx].count = count;
+	}
+
+	/* update the dreq->count by finding the minimum agreed count from all
+	 * mirrors */
+	count = dreq->mirrors[0].count;
+
+	for (i = 1; i < dreq->mirror_count; i++)
+		count = min(count, dreq->mirrors[i].count);
+
+	dreq->count = count;
+}
+
 /*
  * nfs_direct_select_verf - select the right verifier
  * @dreq - direct request possibly spanning multiple servers
  * @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs
- * @ds_idx - index of data server in data server list, only valid if ds_clp set
+ * @commit_idx - commit bucket index for the DS
  *
  * returns the correct verifier to use given the role of the server
  */
 static struct nfs_writeverf *
 nfs_direct_select_verf(struct nfs_direct_req *dreq,
 		       struct nfs_client *ds_clp,
-		       int ds_idx)
+		       int commit_idx)
 {
 	struct nfs_writeverf *verfp = &dreq->verf;
 
 #ifdef CONFIG_NFS_V4_1
 	if (ds_clp) {
 		/* pNFS is in use, use the DS verf */
-		if (ds_idx >= 0 && ds_idx < dreq->ds_cinfo.nbuckets)
-			verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf;
+		if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets)
+			verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf;
 		else
 			WARN_ON_ONCE(1);
 	}
@@ -148,8 +187,7 @@ static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq,
 {
 	struct nfs_writeverf *verfp;
 
-	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp,
-				      hdr->ds_idx);
+	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx);
 	WARN_ON_ONCE(verfp->committed >= 0);
 	memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
 	WARN_ON_ONCE(verfp->committed < 0);
@@ -169,8 +207,7 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
 {
 	struct nfs_writeverf *verfp;
 
-	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp,
-					 hdr->ds_idx);
+	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx);
 	if (verfp->committed < 0) {
 		nfs_direct_set_hdr_verf(dreq, hdr);
 		return 0;
@@ -193,7 +230,11 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
 
 	verfp = nfs_direct_select_verf(dreq, data->ds_clp,
 					 data->ds_commit_index);
-	WARN_ON_ONCE(verfp->committed < 0);
+
+	/* verifier not set so always fail */
+	if (verfp->committed < 0)
+		return 1;
+
 	return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf));
 }
 
@@ -242,13 +283,25 @@ static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
 void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 			      struct nfs_direct_req *dreq)
 {
-	cinfo->lock = &dreq->lock;
+	cinfo->lock = &dreq->inode->i_lock;
 	cinfo->mds = &dreq->mds_cinfo;
 	cinfo->ds = &dreq->ds_cinfo;
 	cinfo->dreq = dreq;
 	cinfo->completion_ops = &nfs_direct_commit_completion_ops;
 }
 
+static inline void nfs_direct_setup_mirroring(struct nfs_direct_req *dreq,
+					     struct nfs_pageio_descriptor *pgio,
+					     struct nfs_page *req)
+{
+	int mirror_count = 1;
+
+	if (pgio->pg_ops->pg_get_mirror_count)
+		mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req);
+
+	dreq->mirror_count = mirror_count;
+}
+
 static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 {
 	struct nfs_direct_req *dreq;
@@ -263,6 +316,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 	INIT_LIST_HEAD(&dreq->mds_cinfo.list);
 	dreq->verf.committed = NFS_INVALID_STABLE_HOW;	/* not set yet */
 	INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
+	dreq->mirror_count = 1;
 	spin_lock_init(&dreq->lock);
 
 	return dreq;
@@ -369,7 +423,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0))
 		dreq->error = hdr->error;
 	else
-		dreq->count += hdr->good_bytes;
+		nfs_direct_good_bytes(dreq, hdr);
+
 	spin_unlock(&dreq->lock);
 
 	while (!list_empty(&hdr->pages)) {
@@ -547,6 +602,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 
 	dreq->inode = inode;
 	dreq->bytes_left = count;
+	dreq->io_start = pos;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
 	if (IS_ERR(l_ctx)) {
@@ -579,6 +635,20 @@ out:
 	return result;
 }
 
+static void
+nfs_direct_write_scan_commit_list(struct inode *inode,
+				  struct list_head *list,
+				  struct nfs_commit_info *cinfo)
+{
+	spin_lock(cinfo->lock);
+#ifdef CONFIG_NFS_V4_1
+	if (cinfo->ds != NULL && cinfo->ds->nwritten != 0)
+		NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
+#endif
+	nfs_scan_commit_list(&cinfo->mds->list, list, cinfo, 0);
+	spin_unlock(cinfo->lock);
+}
+
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 {
 	struct nfs_pageio_descriptor desc;
@@ -586,20 +656,23 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	LIST_HEAD(reqs);
 	struct nfs_commit_info cinfo;
 	LIST_HEAD(failed);
+	int i;
 
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
-	pnfs_recover_commit_reqs(dreq->inode, &reqs, &cinfo);
-	spin_lock(cinfo.lock);
-	nfs_scan_commit_list(&cinfo.mds->list, &reqs, &cinfo, 0);
-	spin_unlock(cinfo.lock);
+	nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
 
 	dreq->count = 0;
+	for (i = 0; i < dreq->mirror_count; i++)
+		dreq->mirrors[i].count = 0;
 	get_dreq(dreq);
 
 	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 
+	req = nfs_list_entry(reqs.next);
+	nfs_direct_setup_mirroring(dreq, &desc, req);
+
 	list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
 		if (!nfs_pageio_add_request(&desc, req)) {
 			nfs_list_remove_request(req);
@@ -646,7 +719,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 		nfs_list_remove_request(req);
 		if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) {
 			/* Note the rewrite will go through mds */
-			nfs_mark_request_commit(req, NULL, &cinfo);
+			nfs_mark_request_commit(req, NULL, &cinfo, 0);
 		} else
 			nfs_release_request(req);
 		nfs_unlock_and_release_request(req);
@@ -721,7 +794,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 		dreq->error = hdr->error;
 	}
 	if (dreq->error == 0) {
-		dreq->count += hdr->good_bytes;
+		nfs_direct_good_bytes(dreq, hdr);
 		if (nfs_write_need_commit(hdr)) {
 			if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
 				request_commit = true;
@@ -745,7 +818,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 		nfs_list_remove_request(req);
 		if (request_commit) {
 			kref_get(&req->wb_kref);
-			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+			nfs_mark_request_commit(req, hdr->lseg, &cinfo,
+				hdr->ds_commit_idx);
 		}
 		nfs_unlock_and_release_request(req);
 	}
@@ -826,6 +900,9 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 				result = PTR_ERR(req);
 				break;
 			}
+
+			nfs_direct_setup_mirroring(dreq, &desc, req);
+
 			nfs_lock_request(req);
 			req->wb_index = pos >> PAGE_SHIFT;
 			req->wb_offset = pos & ~PAGE_MASK;
@@ -934,6 +1011,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
 
 	dreq->inode = inode;
 	dreq->bytes_left = count;
+	dreq->io_start = pos;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
 	if (IS_ERR(l_ctx)) {
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 2ab6f00dba5b..e679d24c39d3 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -178,7 +178,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 		iocb->ki_filp,
 		iov_iter_count(to), (unsigned long) iocb->ki_pos);
 
-	result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
+	result = nfs_revalidate_mapping_protected(inode, iocb->ki_filp->f_mapping);
 	if (!result) {
 		result = generic_file_read_iter(iocb, to);
 		if (result > 0)
@@ -199,7 +199,7 @@ nfs_file_splice_read(struct file *filp, loff_t *ppos,
 	dprintk("NFS: splice_read(%pD2, %lu@%Lu)\n",
 		filp, (unsigned long) count, (unsigned long long) *ppos);
 
-	res = nfs_revalidate_mapping(inode, filp->f_mapping);
+	res = nfs_revalidate_mapping_protected(inode, filp->f_mapping);
 	if (!res) {
 		res = generic_file_splice_read(filp, ppos, pipe, count, flags);
 		if (res > 0)
@@ -372,6 +372,10 @@ start:
 				 nfs_wait_bit_killable, TASK_KILLABLE);
 	if (ret)
 		return ret;
+	/*
+	 * Wait for O_DIRECT to complete
+	 */
+	nfs_inode_dio_wait(mapping->host);
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
@@ -619,6 +623,9 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	/* make sure the cache has finished storing the page */
 	nfs_fscache_wait_on_page_write(NFS_I(inode), page);
 
+	wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING,
+			nfs_wait_bit_killable, TASK_KILLABLE);
+
 	lock_page(page);
 	mapping = page_file_mapping(page);
 	if (mapping != inode->i_mapping)
@@ -646,7 +653,6 @@ static const struct vm_operations_struct nfs_file_vm_ops = {
 	.fault = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = nfs_vm_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 static int nfs_need_sync_write(struct file *filp, struct inode *inode)
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 7afb52f6a25a..91e88a7ecef0 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -118,13 +118,6 @@ static void filelayout_reset_read(struct nfs_pgio_header *hdr)
 	}
 }
 
-static void filelayout_fenceme(struct inode *inode, struct pnfs_layout_hdr *lo)
-{
-	if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
-		return;
-	pnfs_return_layout(inode);
-}
-
 static int filelayout_async_handle_error(struct rpc_task *task,
 					 struct nfs4_state *state,
 					 struct nfs_client *clp,
@@ -207,7 +200,7 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
 		nfs4_mark_deviceid_unavailable(devid);
-		set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
+		pnfs_error_mark_layout_for_return(inode, lseg);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		/* fall through */
 	default:
@@ -339,16 +332,6 @@ static void filelayout_read_count_stats(struct rpc_task *task, void *data)
 	rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics);
 }
 
-static void filelayout_read_release(void *data)
-{
-	struct nfs_pgio_header *hdr = data;
-	struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout;
-
-	filelayout_fenceme(lo->plh_inode, lo);
-	nfs_put_client(hdr->ds_clp);
-	hdr->mds_ops->rpc_release(data);
-}
-
 static int filelayout_write_done_cb(struct rpc_task *task,
 				struct nfs_pgio_header *hdr)
 {
@@ -371,17 +354,6 @@ static int filelayout_write_done_cb(struct rpc_task *task,
 	return 0;
 }
 
-/* Fake up some data that will cause nfs_commit_release to retry the writes. */
-static void prepare_to_resend_writes(struct nfs_commit_data *data)
-{
-	struct nfs_page *first = nfs_list_entry(data->pages.next);
-
-	data->task.tk_status = 0;
-	memcpy(&data->verf.verifier, &first->wb_verf,
-	       sizeof(data->verf.verifier));
-	data->verf.verifier.data[0]++; /* ensure verifier mismatch */
-}
-
 static int filelayout_commit_done_cb(struct rpc_task *task,
 				     struct nfs_commit_data *data)
 {
@@ -393,7 +365,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 
 	switch (err) {
 	case -NFS4ERR_RESET_TO_MDS:
-		prepare_to_resend_writes(data);
+		pnfs_generic_prepare_to_resend_writes(data);
 		return -EAGAIN;
 	case -EAGAIN:
 		rpc_restart_call_prepare(task);
@@ -451,16 +423,6 @@ static void filelayout_write_count_stats(struct rpc_task *task, void *data)
 	rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics);
 }
 
-static void filelayout_write_release(void *data)
-{
-	struct nfs_pgio_header *hdr = data;
-	struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout;
-
-	filelayout_fenceme(lo->plh_inode, lo);
-	nfs_put_client(hdr->ds_clp);
-	hdr->mds_ops->rpc_release(data);
-}
-
 static void filelayout_commit_prepare(struct rpc_task *task, void *data)
 {
 	struct nfs_commit_data *wdata = data;
@@ -471,14 +433,6 @@ static void filelayout_commit_prepare(struct rpc_task *task, void *data)
 			task);
 }
 
-static void filelayout_write_commit_done(struct rpc_task *task, void *data)
-{
-	struct nfs_commit_data *wdata = data;
-
-	/* Note this may cause RPC to be resent */
-	wdata->mds_ops->rpc_call_done(task, data);
-}
-
 static void filelayout_commit_count_stats(struct rpc_task *task, void *data)
 {
 	struct nfs_commit_data *cdata = data;
@@ -486,35 +440,25 @@ static void filelayout_commit_count_stats(struct rpc_task *task, void *data)
 	rpc_count_iostats(task, NFS_SERVER(cdata->inode)->client->cl_metrics);
 }
 
-static void filelayout_commit_release(void *calldata)
-{
-	struct nfs_commit_data *data = calldata;
-
-	data->completion_ops->completion(data);
-	pnfs_put_lseg(data->lseg);
-	nfs_put_client(data->ds_clp);
-	nfs_commitdata_release(data);
-}
-
 static const struct rpc_call_ops filelayout_read_call_ops = {
 	.rpc_call_prepare = filelayout_read_prepare,
 	.rpc_call_done = filelayout_read_call_done,
 	.rpc_count_stats = filelayout_read_count_stats,
-	.rpc_release = filelayout_read_release,
+	.rpc_release = pnfs_generic_rw_release,
 };
 
 static const struct rpc_call_ops filelayout_write_call_ops = {
 	.rpc_call_prepare = filelayout_write_prepare,
 	.rpc_call_done = filelayout_write_call_done,
 	.rpc_count_stats = filelayout_write_count_stats,
-	.rpc_release = filelayout_write_release,
+	.rpc_release = pnfs_generic_rw_release,
 };
 
 static const struct rpc_call_ops filelayout_commit_call_ops = {
 	.rpc_call_prepare = filelayout_commit_prepare,
-	.rpc_call_done = filelayout_write_commit_done,
+	.rpc_call_done = pnfs_generic_write_commit_done,
 	.rpc_count_stats = filelayout_commit_count_stats,
-	.rpc_release = filelayout_commit_release,
+	.rpc_release = pnfs_generic_commit_release,
 };
 
 static enum pnfs_try_status
@@ -548,7 +492,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
 	/* No multipath support. Use first DS */
 	atomic_inc(&ds->ds_clp->cl_count);
 	hdr->ds_clp = ds->ds_clp;
-	hdr->ds_idx = idx;
+	hdr->ds_commit_idx = idx;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
 	if (fh)
 		hdr->args.fh = fh;
@@ -557,8 +501,9 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
 	hdr->mds_offset = offset;
 
 	/* Perform an asynchronous read to ds */
-	nfs_initiate_pgio(ds_clnt, hdr,
-			    &filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN);
+	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
+			  NFS_PROTO(hdr->inode), &filelayout_read_call_ops,
+			  0, RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
 }
 
@@ -591,16 +536,16 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	hdr->pgio_done_cb = filelayout_write_done_cb;
 	atomic_inc(&ds->ds_clp->cl_count);
 	hdr->ds_clp = ds->ds_clp;
-	hdr->ds_idx = idx;
+	hdr->ds_commit_idx = idx;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
 	if (fh)
 		hdr->args.fh = fh;
 	hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
 
 	/* Perform an asynchronous write */
-	nfs_initiate_pgio(ds_clnt, hdr,
-				    &filelayout_write_call_ops, sync,
-				    RPC_TASK_SOFTCONN);
+	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
+			  NFS_PROTO(hdr->inode), &filelayout_write_call_ops,
+			  sync, RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
 }
 
@@ -988,12 +933,14 @@ static const struct nfs_pageio_ops filelayout_pg_read_ops = {
 	.pg_init = filelayout_pg_init_read,
 	.pg_test = filelayout_pg_test,
 	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static const struct nfs_pageio_ops filelayout_pg_write_ops = {
 	.pg_init = filelayout_pg_init_write,
 	.pg_test = filelayout_pg_test,
 	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
@@ -1004,87 +951,28 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
 		return j;
 }
 
-/* The generic layer is about to remove the req from the commit list.
- * If this will make the bucket empty, it will need to put the lseg reference.
- * Note this is must be called holding the inode (/cinfo) lock
- */
-static void
-filelayout_clear_request_commit(struct nfs_page *req,
-				struct nfs_commit_info *cinfo)
-{
-	struct pnfs_layout_segment *freeme = NULL;
-
-	if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
-		goto out;
-	cinfo->ds->nwritten--;
-	if (list_is_singular(&req->wb_list)) {
-		struct pnfs_commit_bucket *bucket;
-
-		bucket = list_first_entry(&req->wb_list,
-					  struct pnfs_commit_bucket,
-					  written);
-		freeme = bucket->wlseg;
-		bucket->wlseg = NULL;
-	}
-out:
-	nfs_request_remove_commit_list(req, cinfo);
-	pnfs_put_lseg_locked(freeme);
-}
-
 static void
 filelayout_mark_request_commit(struct nfs_page *req,
 			       struct pnfs_layout_segment *lseg,
-			       struct nfs_commit_info *cinfo)
+			       struct nfs_commit_info *cinfo,
+			       u32 ds_commit_idx)
 
 {
 	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
 	u32 i, j;
-	struct list_head *list;
-	struct pnfs_commit_bucket *buckets;
 
 	if (fl->commit_through_mds) {
-		list = &cinfo->mds->list;
-		spin_lock(cinfo->lock);
-		goto mds_commit;
-	}
-
-	/* Note that we are calling nfs4_fl_calc_j_index on each page
-	 * that ends up being committed to a data server.  An attractive
-	 * alternative is to add a field to nfs_write_data and nfs_page
-	 * to store the value calculated in filelayout_write_pagelist
-	 * and just use that here.
-	 */
-	j = nfs4_fl_calc_j_index(lseg, req_offset(req));
-	i = select_bucket_index(fl, j);
-	spin_lock(cinfo->lock);
-	buckets = cinfo->ds->buckets;
-	list = &buckets[i].written;
-	if (list_empty(list)) {
-		/* Non-empty buckets hold a reference on the lseg.  That ref
-		 * is normally transferred to the COMMIT call and released
-		 * there.  It could also be released if the last req is pulled
-		 * off due to a rewrite, in which case it will be done in
-		 * filelayout_clear_request_commit
+		nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo);
+	} else {
+		/* Note that we are calling nfs4_fl_calc_j_index on each page
+		 * that ends up being committed to a data server.  An attractive
+		 * alternative is to add a field to nfs_write_data and nfs_page
+		 * to store the value calculated in filelayout_write_pagelist
+		 * and just use that here.
 		 */
-		buckets[i].wlseg = pnfs_get_lseg(lseg);
-	}
-	set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
-	cinfo->ds->nwritten++;
-
-mds_commit:
-	/* nfs_request_add_commit_list(). We need to add req to list without
-	 * dropping cinfo lock.
-	 */
-	set_bit(PG_CLEAN, &(req)->wb_flags);
-	nfs_list_add_request(req, list);
-	cinfo->mds->ncommit++;
-	spin_unlock(cinfo->lock);
-	if (!cinfo->dreq) {
-		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
-			     BDI_RECLAIMABLE);
-		__mark_inode_dirty(req->wb_context->dentry->d_inode,
-				   I_DIRTY_DATASYNC);
+		j = nfs4_fl_calc_j_index(lseg, req_offset(req));
+		i = select_bucket_index(fl, j);
+		pnfs_layout_mark_request_commit(req, lseg, cinfo, i);
 	}
 }
 
@@ -1138,101 +1026,15 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
 	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
 	if (fh)
 		data->args.fh = fh;
-	return nfs_initiate_commit(ds_clnt, data,
+	return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode),
 				   &filelayout_commit_call_ops, how,
 				   RPC_TASK_SOFTCONN);
 out_err:
-	prepare_to_resend_writes(data);
-	filelayout_commit_release(data);
+	pnfs_generic_prepare_to_resend_writes(data);
+	pnfs_generic_commit_release(data);
 	return -EAGAIN;
 }
 
-static int
-transfer_commit_list(struct list_head *src, struct list_head *dst,
-		     struct nfs_commit_info *cinfo, int max)
-{
-	struct nfs_page *req, *tmp;
-	int ret = 0;
-
-	list_for_each_entry_safe(req, tmp, src, wb_list) {
-		if (!nfs_lock_request(req))
-			continue;
-		kref_get(&req->wb_kref);
-		if (cond_resched_lock(cinfo->lock))
-			list_safe_reset_next(req, tmp, wb_list);
-		nfs_request_remove_commit_list(req, cinfo);
-		clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
-		nfs_list_add_request(req, dst);
-		ret++;
-		if ((ret == max) && !cinfo->dreq)
-			break;
-	}
-	return ret;
-}
-
-/* Note called with cinfo->lock held. */
-static int
-filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
-			       struct nfs_commit_info *cinfo,
-			       int max)
-{
-	struct list_head *src = &bucket->written;
-	struct list_head *dst = &bucket->committing;
-	int ret;
-
-	ret = transfer_commit_list(src, dst, cinfo, max);
-	if (ret) {
-		cinfo->ds->nwritten -= ret;
-		cinfo->ds->ncommitting += ret;
-		bucket->clseg = bucket->wlseg;
-		if (list_empty(src))
-			bucket->wlseg = NULL;
-		else
-			pnfs_get_lseg(bucket->clseg);
-	}
-	return ret;
-}
-
-/* Move reqs from written to committing lists, returning count of number moved.
- * Note called with cinfo->lock held.
- */
-static int filelayout_scan_commit_lists(struct nfs_commit_info *cinfo,
-					int max)
-{
-	int i, rv = 0, cnt;
-
-	for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) {
-		cnt = filelayout_scan_ds_commit_list(&cinfo->ds->buckets[i],
-						     cinfo, max);
-		max -= cnt;
-		rv += cnt;
-	}
-	return rv;
-}
-
-/* Pull everything off the committing lists and dump into @dst */
-static void filelayout_recover_commit_reqs(struct list_head *dst,
-					   struct nfs_commit_info *cinfo)
-{
-	struct pnfs_commit_bucket *b;
-	struct pnfs_layout_segment *freeme;
-	int i;
-
-restart:
-	spin_lock(cinfo->lock);
-	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
-		if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
-			freeme = b->wlseg;
-			b->wlseg = NULL;
-			spin_unlock(cinfo->lock);
-			pnfs_put_lseg(freeme);
-			goto restart;
-		}
-	}
-	cinfo->ds->nwritten = 0;
-	spin_unlock(cinfo->lock);
-}
-
 /* filelayout_search_commit_reqs - Search lists in @cinfo for the head reqest
  *				   for @page
  * @cinfo - commit info for current inode
@@ -1263,108 +1065,14 @@ filelayout_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page)
 	return NULL;
 }
 
-static void filelayout_retry_commit(struct nfs_commit_info *cinfo, int idx)
-{
-	struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
-	struct pnfs_commit_bucket *bucket;
-	struct pnfs_layout_segment *freeme;
-	int i;
-
-	for (i = idx; i < fl_cinfo->nbuckets; i++) {
-		bucket = &fl_cinfo->buckets[i];
-		if (list_empty(&bucket->committing))
-			continue;
-		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
-		spin_lock(cinfo->lock);
-		freeme = bucket->clseg;
-		bucket->clseg = NULL;
-		spin_unlock(cinfo->lock);
-		pnfs_put_lseg(freeme);
-	}
-}
-
-static unsigned int
-alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
-{
-	struct pnfs_ds_commit_info *fl_cinfo;
-	struct pnfs_commit_bucket *bucket;
-	struct nfs_commit_data *data;
-	int i;
-	unsigned int nreq = 0;
-
-	fl_cinfo = cinfo->ds;
-	bucket = fl_cinfo->buckets;
-	for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) {
-		if (list_empty(&bucket->committing))
-			continue;
-		data = nfs_commitdata_alloc();
-		if (!data)
-			break;
-		data->ds_commit_index = i;
-		spin_lock(cinfo->lock);
-		data->lseg = bucket->clseg;
-		bucket->clseg = NULL;
-		spin_unlock(cinfo->lock);
-		list_add(&data->pages, list);
-		nreq++;
-	}
-
-	/* Clean up on error */
-	filelayout_retry_commit(cinfo, i);
-	/* Caller will clean up entries put on list */
-	return nreq;
-}
-
-/* This follows nfs_commit_list pretty closely */
 static int
 filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 			   int how, struct nfs_commit_info *cinfo)
 {
-	struct nfs_commit_data *data, *tmp;
-	LIST_HEAD(list);
-	unsigned int nreq = 0;
-
-	if (!list_empty(mds_pages)) {
-		data = nfs_commitdata_alloc();
-		if (data != NULL) {
-			data->lseg = NULL;
-			list_add(&data->pages, &list);
-			nreq++;
-		} else {
-			nfs_retry_commit(mds_pages, NULL, cinfo);
-			filelayout_retry_commit(cinfo, 0);
-			cinfo->completion_ops->error_cleanup(NFS_I(inode));
-			return -ENOMEM;
-		}
-	}
-
-	nreq += alloc_ds_commits(cinfo, &list);
-
-	if (nreq == 0) {
-		cinfo->completion_ops->error_cleanup(NFS_I(inode));
-		goto out;
-	}
-
-	atomic_add(nreq, &cinfo->mds->rpcs_out);
-
-	list_for_each_entry_safe(data, tmp, &list, pages) {
-		list_del_init(&data->pages);
-		if (!data->lseg) {
-			nfs_init_commit(data, mds_pages, NULL, cinfo);
-			nfs_initiate_commit(NFS_CLIENT(inode), data,
-					    data->mds_ops, how, 0);
-		} else {
-			struct pnfs_commit_bucket *buckets;
-
-			buckets = cinfo->ds->buckets;
-			nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg, cinfo);
-			filelayout_initiate_commit(data, how);
-		}
-	}
-out:
-	cinfo->ds->ncommitting = 0;
-	return PNFS_ATTEMPTED;
+	return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo,
+					    filelayout_initiate_commit);
 }
+
 static struct nfs4_deviceid_node *
 filelayout_alloc_deviceid_node(struct nfs_server *server,
 		struct pnfs_device *pdev, gfp_t gfp_flags)
@@ -1421,9 +1129,9 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.pg_write_ops		= &filelayout_pg_write_ops,
 	.get_ds_info		= &filelayout_get_ds_info,
 	.mark_request_commit	= filelayout_mark_request_commit,
-	.clear_request_commit	= filelayout_clear_request_commit,
-	.scan_commit_lists	= filelayout_scan_commit_lists,
-	.recover_commit_reqs	= filelayout_recover_commit_reqs,
+	.clear_request_commit	= pnfs_generic_clear_request_commit,
+	.scan_commit_lists	= pnfs_generic_scan_commit_lists,
+	.recover_commit_reqs	= pnfs_generic_recover_commit_reqs,
 	.search_commit_reqs	= filelayout_search_commit_reqs,
 	.commit_pagelist	= filelayout_commit_pagelist,
 	.read_pagelist		= filelayout_read_pagelist,
diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h
index 7c9f800c49d7..2896cb833a11 100644
--- a/fs/nfs/filelayout/filelayout.h
+++ b/fs/nfs/filelayout/filelayout.h
@@ -33,13 +33,6 @@
 #include "../pnfs.h"
 
 /*
- * Default data server connection timeout and retrans vaules.
- * Set by module paramters dataserver_timeo and dataserver_retrans.
- */
-#define NFS4_DEF_DS_TIMEO   600 /* in tenths of a second */
-#define NFS4_DEF_DS_RETRANS 5
-
-/*
  * Field testing shows we need to support up to 4096 stripe indices.
  * We store each index as a u8 (u32 on the wire) to keep the memory footprint
  * reasonable. This in turn means we support a maximum of 256
@@ -48,32 +41,11 @@
 #define NFS4_PNFS_MAX_STRIPE_CNT 4096
 #define NFS4_PNFS_MAX_MULTI_CNT  256 /* 256 fit into a u8 stripe_index */
 
-/* error codes for internal use */
-#define NFS4ERR_RESET_TO_MDS   12001
-
 enum stripetype4 {
 	STRIPE_SPARSE = 1,
 	STRIPE_DENSE = 2
 };
 
-/* Individual ip address */
-struct nfs4_pnfs_ds_addr {
-	struct sockaddr_storage	da_addr;
-	size_t			da_addrlen;
-	struct list_head	da_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
-	char			*da_remotestr;	/* human readable addr+port */
-};
-
-struct nfs4_pnfs_ds {
-	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
-	char			*ds_remotestr;	/* comma sep list of addrs */
-	struct list_head	ds_addrs;
-	struct nfs_client	*ds_clp;
-	atomic_t		ds_count;
-	unsigned long		ds_state;
-#define NFS4DS_CONNECTING	0	/* ds is establishing connection */
-};
-
 struct nfs4_file_layout_dsaddr {
 	struct nfs4_deviceid_node	id_node;
 	u32				stripe_count;
@@ -119,17 +91,6 @@ FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg)
 	return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node;
 }
 
-static inline void
-filelayout_mark_devid_invalid(struct nfs4_deviceid_node *node)
-{
-	u32 *p = (u32 *)&node->deviceid;
-
-	printk(KERN_WARNING "NFS: Deviceid [%x%x%x%x] marked out of use.\n",
-		p[0], p[1], p[2], p[3]);
-
-	set_bit(NFS_DEVICEID_INVALID, &node->flags);
-}
-
 static inline bool
 filelayout_test_devid_invalid(struct nfs4_deviceid_node *node)
 {
@@ -142,7 +103,6 @@ filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node);
 extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
 
-extern void print_ds(struct nfs4_pnfs_ds *ds);
 u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
 u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
 struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index bfecac781f19..4f372e224603 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -31,7 +31,6 @@
 #include <linux/nfs_fs.h>
 #include <linux/vmalloc.h>
 #include <linux/module.h>
-#include <linux/sunrpc/addr.h>
 
 #include "../internal.h"
 #include "../nfs4session.h"
@@ -42,183 +41,6 @@
 static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
 static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
 
-/*
- * Data server cache
- *
- * Data servers can be mapped to different device ids.
- * nfs4_pnfs_ds reference counting
- *   - set to 1 on allocation
- *   - incremented when a device id maps a data server already in the cache.
- *   - decremented when deviceid is removed from the cache.
- */
-static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
-static LIST_HEAD(nfs4_data_server_cache);
-
-/* Debug routines */
-void
-print_ds(struct nfs4_pnfs_ds *ds)
-{
-	if (ds == NULL) {
-		printk("%s NULL device\n", __func__);
-		return;
-	}
-	printk("        ds %s\n"
-		"        ref count %d\n"
-		"        client %p\n"
-		"        cl_exchange_flags %x\n",
-		ds->ds_remotestr,
-		atomic_read(&ds->ds_count), ds->ds_clp,
-		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
-}
-
-static bool
-same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
-{
-	struct sockaddr_in *a, *b;
-	struct sockaddr_in6 *a6, *b6;
-
-	if (addr1->sa_family != addr2->sa_family)
-		return false;
-
-	switch (addr1->sa_family) {
-	case AF_INET:
-		a = (struct sockaddr_in *)addr1;
-		b = (struct sockaddr_in *)addr2;
-
-		if (a->sin_addr.s_addr == b->sin_addr.s_addr &&
-		    a->sin_port == b->sin_port)
-			return true;
-		break;
-
-	case AF_INET6:
-		a6 = (struct sockaddr_in6 *)addr1;
-		b6 = (struct sockaddr_in6 *)addr2;
-
-		/* LINKLOCAL addresses must have matching scope_id */
-		if (ipv6_addr_src_scope(&a6->sin6_addr) ==
-		    IPV6_ADDR_SCOPE_LINKLOCAL &&
-		    a6->sin6_scope_id != b6->sin6_scope_id)
-			return false;
-
-		if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) &&
-		    a6->sin6_port == b6->sin6_port)
-			return true;
-		break;
-
-	default:
-		dprintk("%s: unhandled address family: %u\n",
-			__func__, addr1->sa_family);
-		return false;
-	}
-
-	return false;
-}
-
-static bool
-_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
-			       const struct list_head *dsaddrs2)
-{
-	struct nfs4_pnfs_ds_addr *da1, *da2;
-
-	/* step through both lists, comparing as we go */
-	for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
-	     da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
-	     da1 != NULL && da2 != NULL;
-	     da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
-	     da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
-		if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
-				   (struct sockaddr *)&da2->da_addr))
-			return false;
-	}
-	if (da1 == NULL && da2 == NULL)
-		return true;
-
-	return false;
-}
-
-/*
- * Lookup DS by addresses.  nfs4_ds_cache_lock is held
- */
-static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(const struct list_head *dsaddrs)
-{
-	struct nfs4_pnfs_ds *ds;
-
-	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
-		if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
-			return ds;
-	return NULL;
-}
-
-/*
- * Create an rpc connection to the nfs4_pnfs_ds data server
- * Currently only supports IPv4 and IPv6 addresses
- */
-static int
-nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
-{
-	struct nfs_client *clp = ERR_PTR(-EIO);
-	struct nfs4_pnfs_ds_addr *da;
-	int status = 0;
-
-	dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
-		mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor);
-
-	list_for_each_entry(da, &ds->ds_addrs, da_node) {
-		dprintk("%s: DS %s: trying address %s\n",
-			__func__, ds->ds_remotestr, da->da_remotestr);
-
-		clp = nfs4_set_ds_client(mds_srv->nfs_client,
-					(struct sockaddr *)&da->da_addr,
-					da->da_addrlen, IPPROTO_TCP,
-					dataserver_timeo, dataserver_retrans);
-		if (!IS_ERR(clp))
-			break;
-	}
-
-	if (IS_ERR(clp)) {
-		status = PTR_ERR(clp);
-		goto out;
-	}
-
-	status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time);
-	if (status)
-		goto out_put;
-
-	smp_wmb();
-	ds->ds_clp = clp;
-	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
-out:
-	return status;
-out_put:
-	nfs_put_client(clp);
-	goto out;
-}
-
-static void
-destroy_ds(struct nfs4_pnfs_ds *ds)
-{
-	struct nfs4_pnfs_ds_addr *da;
-
-	dprintk("--> %s\n", __func__);
-	ifdebug(FACILITY)
-		print_ds(ds);
-
-	nfs_put_client(ds->ds_clp);
-
-	while (!list_empty(&ds->ds_addrs)) {
-		da = list_first_entry(&ds->ds_addrs,
-				      struct nfs4_pnfs_ds_addr,
-				      da_node);
-		list_del_init(&da->da_node);
-		kfree(da->da_remotestr);
-		kfree(da);
-	}
-
-	kfree(ds->ds_remotestr);
-	kfree(ds);
-}
-
 void
 nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
@@ -229,259 +51,13 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 
 	for (i = 0; i < dsaddr->ds_num; i++) {
 		ds = dsaddr->ds_list[i];
-		if (ds != NULL) {
-			if (atomic_dec_and_lock(&ds->ds_count,
-						&nfs4_ds_cache_lock)) {
-				list_del_init(&ds->ds_node);
-				spin_unlock(&nfs4_ds_cache_lock);
-				destroy_ds(ds);
-			}
-		}
+		if (ds != NULL)
+			nfs4_pnfs_ds_put(ds);
 	}
 	kfree(dsaddr->stripe_indices);
 	kfree(dsaddr);
 }
 
-/*
- * Create a string with a human readable address and port to avoid
- * complicated setup around many dprinks.
- */
-static char *
-nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
-{
-	struct nfs4_pnfs_ds_addr *da;
-	char *remotestr;
-	size_t len;
-	char *p;
-
-	len = 3;        /* '{', '}' and eol */
-	list_for_each_entry(da, dsaddrs, da_node) {
-		len += strlen(da->da_remotestr) + 1;    /* string plus comma */
-	}
-
-	remotestr = kzalloc(len, gfp_flags);
-	if (!remotestr)
-		return NULL;
-
-	p = remotestr;
-	*(p++) = '{';
-	len--;
-	list_for_each_entry(da, dsaddrs, da_node) {
-		size_t ll = strlen(da->da_remotestr);
-
-		if (ll > len)
-			goto out_err;
-
-		memcpy(p, da->da_remotestr, ll);
-		p += ll;
-		len -= ll;
-
-		if (len < 1)
-			goto out_err;
-		(*p++) = ',';
-		len--;
-	}
-	if (len < 2)
-		goto out_err;
-	*(p++) = '}';
-	*p = '\0';
-	return remotestr;
-out_err:
-	kfree(remotestr);
-	return NULL;
-}
-
-static struct nfs4_pnfs_ds *
-nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
-{
-	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
-	char *remotestr;
-
-	if (list_empty(dsaddrs)) {
-		dprintk("%s: no addresses defined\n", __func__);
-		goto out;
-	}
-
-	ds = kzalloc(sizeof(*ds), gfp_flags);
-	if (!ds)
-		goto out;
-
-	/* this is only used for debugging, so it's ok if its NULL */
-	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
-
-	spin_lock(&nfs4_ds_cache_lock);
-	tmp_ds = _data_server_lookup_locked(dsaddrs);
-	if (tmp_ds == NULL) {
-		INIT_LIST_HEAD(&ds->ds_addrs);
-		list_splice_init(dsaddrs, &ds->ds_addrs);
-		ds->ds_remotestr = remotestr;
-		atomic_set(&ds->ds_count, 1);
-		INIT_LIST_HEAD(&ds->ds_node);
-		ds->ds_clp = NULL;
-		list_add(&ds->ds_node, &nfs4_data_server_cache);
-		dprintk("%s add new data server %s\n", __func__,
-			ds->ds_remotestr);
-	} else {
-		kfree(remotestr);
-		kfree(ds);
-		atomic_inc(&tmp_ds->ds_count);
-		dprintk("%s data server %s found, inc'ed ds_count to %d\n",
-			__func__, tmp_ds->ds_remotestr,
-			atomic_read(&tmp_ds->ds_count));
-		ds = tmp_ds;
-	}
-	spin_unlock(&nfs4_ds_cache_lock);
-out:
-	return ds;
-}
-
-/*
- * Currently only supports ipv4, ipv6 and one multi-path address.
- */
-static struct nfs4_pnfs_ds_addr *
-decode_ds_addr(struct net *net, struct xdr_stream *streamp, gfp_t gfp_flags)
-{
-	struct nfs4_pnfs_ds_addr *da = NULL;
-	char *buf, *portstr;
-	__be16 port;
-	int nlen, rlen;
-	int tmp[2];
-	__be32 *p;
-	char *netid, *match_netid;
-	size_t len, match_netid_len;
-	char *startsep = "";
-	char *endsep = "";
-
-
-	/* r_netid */
-	p = xdr_inline_decode(streamp, 4);
-	if (unlikely(!p))
-		goto out_err;
-	nlen = be32_to_cpup(p++);
-
-	p = xdr_inline_decode(streamp, nlen);
-	if (unlikely(!p))
-		goto out_err;
-
-	netid = kmalloc(nlen+1, gfp_flags);
-	if (unlikely(!netid))
-		goto out_err;
-
-	netid[nlen] = '\0';
-	memcpy(netid, p, nlen);
-
-	/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
-	p = xdr_inline_decode(streamp, 4);
-	if (unlikely(!p))
-		goto out_free_netid;
-	rlen = be32_to_cpup(p);
-
-	p = xdr_inline_decode(streamp, rlen);
-	if (unlikely(!p))
-		goto out_free_netid;
-
-	/* port is ".ABC.DEF", 8 chars max */
-	if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) {
-		dprintk("%s: Invalid address, length %d\n", __func__,
-			rlen);
-		goto out_free_netid;
-	}
-	buf = kmalloc(rlen + 1, gfp_flags);
-	if (!buf) {
-		dprintk("%s: Not enough memory\n", __func__);
-		goto out_free_netid;
-	}
-	buf[rlen] = '\0';
-	memcpy(buf, p, rlen);
-
-	/* replace port '.' with '-' */
-	portstr = strrchr(buf, '.');
-	if (!portstr) {
-		dprintk("%s: Failed finding expected dot in port\n",
-			__func__);
-		goto out_free_buf;
-	}
-	*portstr = '-';
-
-	/* find '.' between address and port */
-	portstr = strrchr(buf, '.');
-	if (!portstr) {
-		dprintk("%s: Failed finding expected dot between address and "
-			"port\n", __func__);
-		goto out_free_buf;
-	}
-	*portstr = '\0';
-
-	da = kzalloc(sizeof(*da), gfp_flags);
-	if (unlikely(!da))
-		goto out_free_buf;
-
-	INIT_LIST_HEAD(&da->da_node);
-
-	if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
-		      sizeof(da->da_addr))) {
-		dprintk("%s: error parsing address %s\n", __func__, buf);
-		goto out_free_da;
-	}
-
-	portstr++;
-	sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]);
-	port = htons((tmp[0] << 8) | (tmp[1]));
-
-	switch (da->da_addr.ss_family) {
-	case AF_INET:
-		((struct sockaddr_in *)&da->da_addr)->sin_port = port;
-		da->da_addrlen = sizeof(struct sockaddr_in);
-		match_netid = "tcp";
-		match_netid_len = 3;
-		break;
-
-	case AF_INET6:
-		((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port;
-		da->da_addrlen = sizeof(struct sockaddr_in6);
-		match_netid = "tcp6";
-		match_netid_len = 4;
-		startsep = "[";
-		endsep = "]";
-		break;
-
-	default:
-		dprintk("%s: unsupported address family: %u\n",
-			__func__, da->da_addr.ss_family);
-		goto out_free_da;
-	}
-
-	if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) {
-		dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n",
-			__func__, netid, match_netid);
-		goto out_free_da;
-	}
-
-	/* save human readable address */
-	len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7;
-	da->da_remotestr = kzalloc(len, gfp_flags);
-
-	/* NULL is ok, only used for dprintk */
-	if (da->da_remotestr)
-		snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep,
-			 buf, endsep, ntohs(port));
-
-	dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr);
-	kfree(buf);
-	kfree(netid);
-	return da;
-
-out_free_da:
-	kfree(da);
-out_free_buf:
-	dprintk("%s: Error parsing DS addr: %s\n", __func__, buf);
-	kfree(buf);
-out_free_netid:
-	kfree(netid);
-out_err:
-	return NULL;
-}
-
 /* Decode opaque device data and return the result */
 struct nfs4_file_layout_dsaddr *
 nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
@@ -584,8 +160,8 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 
 		mp_count = be32_to_cpup(p); /* multipath count */
 		for (j = 0; j < mp_count; j++) {
-			da = decode_ds_addr(server->nfs_client->cl_net,
-					    &stream, gfp_flags);
+			da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
+						    &stream, gfp_flags);
 			if (da)
 				list_add_tail(&da->da_node, &dsaddrs);
 		}
@@ -681,22 +257,7 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
 	return flseg->fh_array[i];
 }
 
-static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
-{
-	might_sleep();
-	wait_on_bit_action(&ds->ds_state, NFS4DS_CONNECTING,
-			   nfs_wait_bit_killable, TASK_KILLABLE);
-}
-
-static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
-{
-	smp_mb__before_atomic();
-	clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
-	smp_mb__after_atomic();
-	wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
-}
-
-
+/* Upon return, either ds is connected, or ds is NULL */
 struct nfs4_pnfs_ds *
 nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 {
@@ -704,29 +265,23 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
 	struct nfs4_pnfs_ds *ret = ds;
+	struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
 
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
 			__func__, ds_idx);
-		filelayout_mark_devid_invalid(devid);
+		pnfs_generic_mark_devid_invalid(devid);
 		goto out;
 	}
 	smp_rmb();
 	if (ds->ds_clp)
 		goto out_test_devid;
 
-	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
-		struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
-		int err;
-
-		err = nfs4_ds_connect(s, ds);
-		if (err)
-			nfs4_mark_deviceid_unavailable(devid);
-		nfs4_clear_ds_conn_bit(ds);
-	} else {
-		/* Either ds is connected, or ds is NULL */
-		nfs4_wait_ds_connect(ds);
-	}
+	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+			     dataserver_retrans, 4,
+			     s->nfs_client->cl_minorversion,
+			     s->nfs_client->cl_rpcclient->cl_auth->au_flavor);
+
 out_test_devid:
 	if (filelayout_test_devid_unavailable(devid))
 		ret = NULL;
diff --git a/fs/nfs/flexfilelayout/Makefile b/fs/nfs/flexfilelayout/Makefile
new file mode 100644
index 000000000000..1d2c9f6bbcd4
--- /dev/null
+++ b/fs/nfs/flexfilelayout/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the pNFS Flexfile Layout Driver kernel module
+#
+obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += nfs_layout_flexfiles.o
+nfs_layout_flexfiles-y := flexfilelayout.o flexfilelayoutdev.o
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
new file mode 100644
index 000000000000..315cc68945b9
--- /dev/null
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -0,0 +1,1533 @@
+/*
+ * Module for pnfs flexfile layout driver.
+ *
+ * Copyright (c) 2014, Primary Data, Inc. All rights reserved.
+ *
+ * Tao Peng <bergwolf@primarydata.com>
+ */
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
+#include <linux/module.h>
+
+#include <linux/sunrpc/metrics.h>
+#include <linux/nfs_idmap.h>
+
+#include "flexfilelayout.h"
+#include "../nfs4session.h"
+#include "../internal.h"
+#include "../delegation.h"
+#include "../nfs4trace.h"
+#include "../iostat.h"
+#include "../nfs.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+#define FF_LAYOUT_POLL_RETRY_MAX     (15*HZ)
+
+static struct pnfs_layout_hdr *
+ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
+{
+	struct nfs4_flexfile_layout *ffl;
+
+	ffl = kzalloc(sizeof(*ffl), gfp_flags);
+	if (ffl) {
+		INIT_LIST_HEAD(&ffl->error_list);
+		return &ffl->generic_hdr;
+	} else
+		return NULL;
+}
+
+static void
+ff_layout_free_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	struct nfs4_ff_layout_ds_err *err, *n;
+
+	list_for_each_entry_safe(err, n, &FF_LAYOUT_FROM_HDR(lo)->error_list,
+				 list) {
+		list_del(&err->list);
+		kfree(err);
+	}
+	kfree(FF_LAYOUT_FROM_HDR(lo));
+}
+
+static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, NFS4_STATEID_SIZE);
+	if (unlikely(p == NULL))
+		return -ENOBUFS;
+	memcpy(stateid, p, NFS4_STATEID_SIZE);
+	dprintk("%s: stateid id= [%x%x%x%x]\n", __func__,
+		p[0], p[1], p[2], p[3]);
+	return 0;
+}
+
+static int decode_deviceid(struct xdr_stream *xdr, struct nfs4_deviceid *devid)
+{
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, NFS4_DEVICEID4_SIZE);
+	if (unlikely(!p))
+		return -ENOBUFS;
+	memcpy(devid, p, NFS4_DEVICEID4_SIZE);
+	nfs4_print_deviceid(devid);
+	return 0;
+}
+
+static int decode_nfs_fh(struct xdr_stream *xdr, struct nfs_fh *fh)
+{
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -ENOBUFS;
+	fh->size = be32_to_cpup(p++);
+	if (fh->size > sizeof(struct nfs_fh)) {
+		printk(KERN_ERR "NFS flexfiles: Too big fh received %d\n",
+		       fh->size);
+		return -EOVERFLOW;
+	}
+	/* fh.data */
+	p = xdr_inline_decode(xdr, fh->size);
+	if (unlikely(!p))
+		return -ENOBUFS;
+	memcpy(&fh->data, p, fh->size);
+	dprintk("%s: fh len %d\n", __func__, fh->size);
+
+	return 0;
+}
+
+/*
+ * Currently only stringified uids and gids are accepted.
+ * I.e., kerberos is not supported to the DSes, so no pricipals.
+ *
+ * That means that one common function will suffice, but when
+ * principals are added, this should be split to accomodate
+ * calls to both nfs_map_name_to_uid() and nfs_map_group_to_gid().
+ */
+static int
+decode_name(struct xdr_stream *xdr, u32 *id)
+{
+	__be32 *p;
+	int len;
+
+	/* opaque_length(4)*/
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -ENOBUFS;
+	len = be32_to_cpup(p++);
+	if (len < 0)
+		return -EINVAL;
+
+	dprintk("%s: len %u\n", __func__, len);
+
+	/* opaque body */
+	p = xdr_inline_decode(xdr, len);
+	if (unlikely(!p))
+		return -ENOBUFS;
+
+	if (!nfs_map_string_to_numeric((char *)p, len, id))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void ff_layout_free_mirror_array(struct nfs4_ff_layout_segment *fls)
+{
+	int i;
+
+	if (fls->mirror_array) {
+		for (i = 0; i < fls->mirror_array_cnt; i++) {
+			/* normally mirror_ds is freed in
+			 * .free_deviceid_node but we still do it here
+			 * for .alloc_lseg error path */
+			if (fls->mirror_array[i]) {
+				kfree(fls->mirror_array[i]->fh_versions);
+				nfs4_ff_layout_put_deviceid(fls->mirror_array[i]->mirror_ds);
+				kfree(fls->mirror_array[i]);
+			}
+		}
+		kfree(fls->mirror_array);
+		fls->mirror_array = NULL;
+	}
+}
+
+static int ff_layout_check_layout(struct nfs4_layoutget_res *lgr)
+{
+	int ret = 0;
+
+	dprintk("--> %s\n", __func__);
+
+	/* FIXME: remove this check when layout segment support is added */
+	if (lgr->range.offset != 0 ||
+	    lgr->range.length != NFS4_MAX_UINT64) {
+		dprintk("%s Only whole file layouts supported. Use MDS i/o\n",
+			__func__);
+		ret = -EINVAL;
+	}
+
+	dprintk("--> %s returns %d\n", __func__, ret);
+	return ret;
+}
+
+static void _ff_layout_free_lseg(struct nfs4_ff_layout_segment *fls)
+{
+	if (fls) {
+		ff_layout_free_mirror_array(fls);
+		kfree(fls);
+	}
+}
+
+static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls)
+{
+	struct nfs4_ff_layout_mirror *tmp;
+	int i, j;
+
+	for (i = 0; i < fls->mirror_array_cnt - 1; i++) {
+		for (j = i + 1; j < fls->mirror_array_cnt; j++)
+			if (fls->mirror_array[i]->efficiency <
+			    fls->mirror_array[j]->efficiency) {
+				tmp = fls->mirror_array[i];
+				fls->mirror_array[i] = fls->mirror_array[j];
+				fls->mirror_array[j] = tmp;
+			}
+	}
+}
+
+static struct pnfs_layout_segment *
+ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
+		     struct nfs4_layoutget_res *lgr,
+		     gfp_t gfp_flags)
+{
+	struct pnfs_layout_segment *ret;
+	struct nfs4_ff_layout_segment *fls = NULL;
+	struct xdr_stream stream;
+	struct xdr_buf buf;
+	struct page *scratch;
+	u64 stripe_unit;
+	u32 mirror_array_cnt;
+	__be32 *p;
+	int i, rc;
+
+	dprintk("--> %s\n", __func__);
+	scratch = alloc_page(gfp_flags);
+	if (!scratch)
+		return ERR_PTR(-ENOMEM);
+
+	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages,
+			      lgr->layoutp->len);
+	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+
+	/* stripe unit and mirror_array_cnt */
+	rc = -EIO;
+	p = xdr_inline_decode(&stream, 8 + 4);
+	if (!p)
+		goto out_err_free;
+
+	p = xdr_decode_hyper(p, &stripe_unit);
+	mirror_array_cnt = be32_to_cpup(p++);
+	dprintk("%s: stripe_unit=%llu mirror_array_cnt=%u\n", __func__,
+		stripe_unit, mirror_array_cnt);
+
+	if (mirror_array_cnt > NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT ||
+	    mirror_array_cnt == 0)
+		goto out_err_free;
+
+	rc = -ENOMEM;
+	fls = kzalloc(sizeof(*fls), gfp_flags);
+	if (!fls)
+		goto out_err_free;
+
+	fls->mirror_array_cnt = mirror_array_cnt;
+	fls->stripe_unit = stripe_unit;
+	fls->mirror_array = kcalloc(fls->mirror_array_cnt,
+				    sizeof(fls->mirror_array[0]), gfp_flags);
+	if (fls->mirror_array == NULL)
+		goto out_err_free;
+
+	for (i = 0; i < fls->mirror_array_cnt; i++) {
+		struct nfs4_deviceid devid;
+		struct nfs4_deviceid_node *idnode;
+		u32 ds_count;
+		u32 fh_count;
+		int j;
+
+		rc = -EIO;
+		p = xdr_inline_decode(&stream, 4);
+		if (!p)
+			goto out_err_free;
+		ds_count = be32_to_cpup(p);
+
+		/* FIXME: allow for striping? */
+		if (ds_count != 1)
+			goto out_err_free;
+
+		fls->mirror_array[i] =
+			kzalloc(sizeof(struct nfs4_ff_layout_mirror),
+				gfp_flags);
+		if (fls->mirror_array[i] == NULL) {
+			rc = -ENOMEM;
+			goto out_err_free;
+		}
+
+		spin_lock_init(&fls->mirror_array[i]->lock);
+		fls->mirror_array[i]->ds_count = ds_count;
+
+		/* deviceid */
+		rc = decode_deviceid(&stream, &devid);
+		if (rc)
+			goto out_err_free;
+
+		idnode = nfs4_find_get_deviceid(NFS_SERVER(lh->plh_inode),
+						&devid, lh->plh_lc_cred,
+						gfp_flags);
+		/*
+		 * upon success, mirror_ds is allocated by previous
+		 * getdeviceinfo, or newly by .alloc_deviceid_node
+		 * nfs4_find_get_deviceid failure is indeed getdeviceinfo falure
+		 */
+		if (idnode)
+			fls->mirror_array[i]->mirror_ds =
+				FF_LAYOUT_MIRROR_DS(idnode);
+		else
+			goto out_err_free;
+
+		/* efficiency */
+		rc = -EIO;
+		p = xdr_inline_decode(&stream, 4);
+		if (!p)
+			goto out_err_free;
+		fls->mirror_array[i]->efficiency = be32_to_cpup(p);
+
+		/* stateid */
+		rc = decode_stateid(&stream, &fls->mirror_array[i]->stateid);
+		if (rc)
+			goto out_err_free;
+
+		/* fh */
+		p = xdr_inline_decode(&stream, 4);
+		if (!p)
+			goto out_err_free;
+		fh_count = be32_to_cpup(p);
+
+		fls->mirror_array[i]->fh_versions =
+			kzalloc(fh_count * sizeof(struct nfs_fh),
+				gfp_flags);
+		if (fls->mirror_array[i]->fh_versions == NULL) {
+			rc = -ENOMEM;
+			goto out_err_free;
+		}
+
+		for (j = 0; j < fh_count; j++) {
+			rc = decode_nfs_fh(&stream,
+					   &fls->mirror_array[i]->fh_versions[j]);
+			if (rc)
+				goto out_err_free;
+		}
+
+		fls->mirror_array[i]->fh_versions_cnt = fh_count;
+
+		/* user */
+		rc = decode_name(&stream, &fls->mirror_array[i]->uid);
+		if (rc)
+			goto out_err_free;
+
+		/* group */
+		rc = decode_name(&stream, &fls->mirror_array[i]->gid);
+		if (rc)
+			goto out_err_free;
+
+		dprintk("%s: uid %d gid %d\n", __func__,
+			fls->mirror_array[i]->uid,
+			fls->mirror_array[i]->gid);
+	}
+
+	ff_layout_sort_mirrors(fls);
+	rc = ff_layout_check_layout(lgr);
+	if (rc)
+		goto out_err_free;
+
+	ret = &fls->generic_hdr;
+	dprintk("<-- %s (success)\n", __func__);
+out_free_page:
+	__free_page(scratch);
+	return ret;
+out_err_free:
+	_ff_layout_free_lseg(fls);
+	ret = ERR_PTR(rc);
+	dprintk("<-- %s (%d)\n", __func__, rc);
+	goto out_free_page;
+}
+
+static bool ff_layout_has_rw_segments(struct pnfs_layout_hdr *layout)
+{
+	struct pnfs_layout_segment *lseg;
+
+	list_for_each_entry(lseg, &layout->plh_segs, pls_list)
+		if (lseg->pls_range.iomode == IOMODE_RW)
+			return true;
+
+	return false;
+}
+
+static void
+ff_layout_free_lseg(struct pnfs_layout_segment *lseg)
+{
+	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
+	int i;
+
+	dprintk("--> %s\n", __func__);
+
+	for (i = 0; i < fls->mirror_array_cnt; i++) {
+		if (fls->mirror_array[i]) {
+			nfs4_ff_layout_put_deviceid(fls->mirror_array[i]->mirror_ds);
+			fls->mirror_array[i]->mirror_ds = NULL;
+			if (fls->mirror_array[i]->cred) {
+				put_rpccred(fls->mirror_array[i]->cred);
+				fls->mirror_array[i]->cred = NULL;
+			}
+		}
+	}
+
+	if (lseg->pls_range.iomode == IOMODE_RW) {
+		struct nfs4_flexfile_layout *ffl;
+		struct inode *inode;
+
+		ffl = FF_LAYOUT_FROM_HDR(lseg->pls_layout);
+		inode = ffl->generic_hdr.plh_inode;
+		spin_lock(&inode->i_lock);
+		if (!ff_layout_has_rw_segments(lseg->pls_layout)) {
+			ffl->commit_info.nbuckets = 0;
+			kfree(ffl->commit_info.buckets);
+			ffl->commit_info.buckets = NULL;
+		}
+		spin_unlock(&inode->i_lock);
+	}
+	_ff_layout_free_lseg(fls);
+}
+
+/* Return 1 until we have multiple lsegs support */
+static int
+ff_layout_get_lseg_count(struct nfs4_ff_layout_segment *fls)
+{
+	return 1;
+}
+
+static int
+ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg,
+			    struct nfs_commit_info *cinfo,
+			    gfp_t gfp_flags)
+{
+	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
+	struct pnfs_commit_bucket *buckets;
+	int size;
+
+	if (cinfo->ds->nbuckets != 0) {
+		/* This assumes there is only one RW lseg per file.
+		 * To support multiple lseg per file, we need to
+		 * change struct pnfs_commit_bucket to allow dynamic
+		 * increasing nbuckets.
+		 */
+		return 0;
+	}
+
+	size = ff_layout_get_lseg_count(fls) * FF_LAYOUT_MIRROR_COUNT(lseg);
+
+	buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket),
+			  gfp_flags);
+	if (!buckets)
+		return -ENOMEM;
+	else {
+		int i;
+
+		spin_lock(cinfo->lock);
+		if (cinfo->ds->nbuckets != 0)
+			kfree(buckets);
+		else {
+			cinfo->ds->buckets = buckets;
+			cinfo->ds->nbuckets = size;
+			for (i = 0; i < size; i++) {
+				INIT_LIST_HEAD(&buckets[i].written);
+				INIT_LIST_HEAD(&buckets[i].committing);
+				/* mark direct verifier as unset */
+				buckets[i].direct_verf.committed =
+					NFS_INVALID_STABLE_HOW;
+			}
+		}
+		spin_unlock(cinfo->lock);
+		return 0;
+	}
+}
+
+static struct nfs4_pnfs_ds *
+ff_layout_choose_best_ds_for_read(struct nfs_pageio_descriptor *pgio,
+				  int *best_idx)
+{
+	struct nfs4_ff_layout_segment *fls;
+	struct nfs4_pnfs_ds *ds;
+	int idx;
+
+	fls = FF_LAYOUT_LSEG(pgio->pg_lseg);
+	/* mirrors are sorted by efficiency */
+	for (idx = 0; idx < fls->mirror_array_cnt; idx++) {
+		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, idx, false);
+		if (ds) {
+			*best_idx = idx;
+			return ds;
+		}
+	}
+
+	return NULL;
+}
+
+static void
+ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
+			struct nfs_page *req)
+{
+	struct nfs_pgio_mirror *pgm;
+	struct nfs4_ff_layout_mirror *mirror;
+	struct nfs4_pnfs_ds *ds;
+	int ds_idx;
+
+	/* Use full layout for now */
+	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 no lseg, fall back to read through mds */
+	if (pgio->pg_lseg == NULL)
+		goto out_mds;
+
+	ds = ff_layout_choose_best_ds_for_read(pgio, &ds_idx);
+	if (!ds)
+		goto out_mds;
+	mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
+
+	pgio->pg_mirror_idx = ds_idx;
+
+	/* read always uses only one mirror - idx 0 for pgio layer */
+	pgm = &pgio->pg_mirrors[0];
+	pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
+
+	return;
+out_mds:
+	pnfs_put_lseg(pgio->pg_lseg);
+	pgio->pg_lseg = NULL;
+	nfs_pageio_reset_read_mds(pgio);
+}
+
+static void
+ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			struct nfs_page *req)
+{
+	struct nfs4_ff_layout_mirror *mirror;
+	struct nfs_pgio_mirror *pgm;
+	struct nfs_commit_info cinfo;
+	struct nfs4_pnfs_ds *ds;
+	int i;
+	int status;
+
+	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 no lseg, fall back to write through mds */
+	if (pgio->pg_lseg == NULL)
+		goto out_mds;
+
+	nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq);
+	status = ff_layout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS);
+	if (status < 0)
+		goto out_mds;
+
+	/* Use a direct mapping of ds_idx to pgio mirror_idx */
+	if (WARN_ON_ONCE(pgio->pg_mirror_count !=
+	    FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg)))
+		goto out_mds;
+
+	for (i = 0; i < pgio->pg_mirror_count; i++) {
+		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
+		if (!ds)
+			goto out_mds;
+		pgm = &pgio->pg_mirrors[i];
+		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
+		pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize;
+	}
+
+	return;
+
+out_mds:
+	pnfs_put_lseg(pgio->pg_lseg);
+	pgio->pg_lseg = NULL;
+	nfs_pageio_reset_write_mds(pgio);
+}
+
+static unsigned int
+ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
+				    struct nfs_page *req)
+{
+	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 (pgio->pg_lseg)
+		return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg);
+
+	/* no lseg means that pnfs is not in use, so no mirroring here */
+	pnfs_put_lseg(pgio->pg_lseg);
+	pgio->pg_lseg = NULL;
+	nfs_pageio_reset_write_mds(pgio);
+	return 1;
+}
+
+static const struct nfs_pageio_ops ff_layout_pg_read_ops = {
+	.pg_init = ff_layout_pg_init_read,
+	.pg_test = pnfs_generic_pg_test,
+	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
+};
+
+static const struct nfs_pageio_ops ff_layout_pg_write_ops = {
+	.pg_init = ff_layout_pg_init_write,
+	.pg_test = pnfs_generic_pg_test,
+	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_get_mirror_count = ff_layout_pg_get_mirror_count_write,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
+};
+
+static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
+{
+	struct rpc_task *task = &hdr->task;
+
+	pnfs_layoutcommit_inode(hdr->inode, false);
+
+	if (retry_pnfs) {
+		dprintk("%s Reset task %5u for i/o through pNFS "
+			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
+			hdr->task.tk_pid,
+			hdr->inode->i_sb->s_id,
+			(unsigned long long)NFS_FILEID(hdr->inode),
+			hdr->args.count,
+			(unsigned long long)hdr->args.offset);
+
+		if (!hdr->dreq) {
+			struct nfs_open_context *ctx;
+
+			ctx = nfs_list_entry(hdr->pages.next)->wb_context;
+			set_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
+			hdr->completion_ops->error_cleanup(&hdr->pages);
+		} else {
+			nfs_direct_set_resched_writes(hdr->dreq);
+			/* fake unstable write to let common nfs resend pages */
+			hdr->verf.committed = NFS_UNSTABLE;
+			hdr->good_bytes = 0;
+		}
+		return;
+	}
+
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		dprintk("%s Reset task %5u for i/o through MDS "
+			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
+			hdr->task.tk_pid,
+			hdr->inode->i_sb->s_id,
+			(unsigned long long)NFS_FILEID(hdr->inode),
+			hdr->args.count,
+			(unsigned long long)hdr->args.offset);
+
+		task->tk_status = pnfs_write_done_resend_to_mds(hdr);
+	}
+}
+
+static void ff_layout_reset_read(struct nfs_pgio_header *hdr)
+{
+	struct rpc_task *task = &hdr->task;
+
+	pnfs_layoutcommit_inode(hdr->inode, false);
+
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		dprintk("%s Reset task %5u for i/o through MDS "
+			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
+			hdr->task.tk_pid,
+			hdr->inode->i_sb->s_id,
+			(unsigned long long)NFS_FILEID(hdr->inode),
+			hdr->args.count,
+			(unsigned long long)hdr->args.offset);
+
+		task->tk_status = pnfs_read_done_resend_to_mds(hdr);
+	}
+}
+
+static int ff_layout_async_handle_error_v4(struct rpc_task *task,
+					   struct nfs4_state *state,
+					   struct nfs_client *clp,
+					   struct pnfs_layout_segment *lseg,
+					   int idx)
+{
+	struct pnfs_layout_hdr *lo = lseg->pls_layout;
+	struct inode *inode = lo->plh_inode;
+	struct nfs_server *mds_server = NFS_SERVER(inode);
+
+	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
+	struct nfs_client *mds_client = mds_server->nfs_client;
+	struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table;
+
+	if (task->tk_status >= 0)
+		return 0;
+
+	switch (task->tk_status) {
+	/* MDS state errors */
+	case -NFS4ERR_DELEG_REVOKED:
+	case -NFS4ERR_ADMIN_REVOKED:
+	case -NFS4ERR_BAD_STATEID:
+		if (state == NULL)
+			break;
+		nfs_remove_bad_delegation(state->inode);
+	case -NFS4ERR_OPENMODE:
+		if (state == NULL)
+			break;
+		if (nfs4_schedule_stateid_recovery(mds_server, state) < 0)
+			goto out_bad_stateid;
+		goto wait_on_recovery;
+	case -NFS4ERR_EXPIRED:
+		if (state != NULL) {
+			if (nfs4_schedule_stateid_recovery(mds_server, state) < 0)
+				goto out_bad_stateid;
+		}
+		nfs4_schedule_lease_recovery(mds_client);
+		goto wait_on_recovery;
+	/* DS session errors */
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_BADSLOT:
+	case -NFS4ERR_BAD_HIGH_SLOT:
+	case -NFS4ERR_DEADSESSION:
+	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+	case -NFS4ERR_SEQ_FALSE_RETRY:
+	case -NFS4ERR_SEQ_MISORDERED:
+		dprintk("%s ERROR %d, Reset session. Exchangeid "
+			"flags 0x%x\n", __func__, task->tk_status,
+			clp->cl_exchange_flags);
+		nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
+		break;
+	case -NFS4ERR_DELAY:
+	case -NFS4ERR_GRACE:
+		rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX);
+		break;
+	case -NFS4ERR_RETRY_UNCACHED_REP:
+		break;
+	/* Invalidate Layout errors */
+	case -NFS4ERR_PNFS_NO_LAYOUT:
+	case -ESTALE:           /* mapped NFS4ERR_STALE */
+	case -EBADHANDLE:       /* mapped NFS4ERR_BADHANDLE */
+	case -EISDIR:           /* mapped NFS4ERR_ISDIR */
+	case -NFS4ERR_FHEXPIRED:
+	case -NFS4ERR_WRONG_TYPE:
+		dprintk("%s Invalid layout error %d\n", __func__,
+			task->tk_status);
+		/*
+		 * Destroy layout so new i/o will get a new layout.
+		 * Layout will not be destroyed until all current lseg
+		 * references are put. Mark layout as invalid to resend failed
+		 * i/o and all i/o waiting on the slot table to the MDS until
+		 * layout is destroyed and a new valid layout is obtained.
+		 */
+		pnfs_destroy_layout(NFS_I(inode));
+		rpc_wake_up(&tbl->slot_tbl_waitq);
+		goto reset;
+	/* RPC connection errors */
+	case -ECONNREFUSED:
+	case -EHOSTDOWN:
+	case -EHOSTUNREACH:
+	case -ENETUNREACH:
+	case -EIO:
+	case -ETIMEDOUT:
+	case -EPIPE:
+		dprintk("%s DS connection error %d\n", __func__,
+			task->tk_status);
+		nfs4_mark_deviceid_unavailable(devid);
+		rpc_wake_up(&tbl->slot_tbl_waitq);
+		/* fall through */
+	default:
+		if (ff_layout_has_available_ds(lseg))
+			return -NFS4ERR_RESET_TO_PNFS;
+reset:
+		dprintk("%s Retry through MDS. Error %d\n", __func__,
+			task->tk_status);
+		return -NFS4ERR_RESET_TO_MDS;
+	}
+out:
+	task->tk_status = 0;
+	return -EAGAIN;
+out_bad_stateid:
+	task->tk_status = -EIO;
+	return 0;
+wait_on_recovery:
+	rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL);
+	if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0)
+		rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task);
+	goto out;
+}
+
+/* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
+static int ff_layout_async_handle_error_v3(struct rpc_task *task,
+					   struct pnfs_layout_segment *lseg,
+					   int idx)
+{
+	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
+
+	if (task->tk_status >= 0)
+		return 0;
+
+	if (task->tk_status != -EJUKEBOX) {
+		dprintk("%s DS connection error %d\n", __func__,
+			task->tk_status);
+		nfs4_mark_deviceid_unavailable(devid);
+		if (ff_layout_has_available_ds(lseg))
+			return -NFS4ERR_RESET_TO_PNFS;
+		else
+			return -NFS4ERR_RESET_TO_MDS;
+	}
+
+	if (task->tk_status == -EJUKEBOX)
+		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
+	task->tk_status = 0;
+	rpc_restart_call(task);
+	rpc_delay(task, NFS_JUKEBOX_RETRY_TIME);
+	return -EAGAIN;
+}
+
+static int ff_layout_async_handle_error(struct rpc_task *task,
+					struct nfs4_state *state,
+					struct nfs_client *clp,
+					struct pnfs_layout_segment *lseg,
+					int idx)
+{
+	int vers = clp->cl_nfs_mod->rpc_vers->number;
+
+	switch (vers) {
+	case 3:
+		return ff_layout_async_handle_error_v3(task, lseg, idx);
+	case 4:
+		return ff_layout_async_handle_error_v4(task, state, clp,
+						       lseg, idx);
+	default:
+		/* should never happen */
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+}
+
+static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
+					int idx, u64 offset, u64 length,
+					u32 status, int opnum)
+{
+	struct nfs4_ff_layout_mirror *mirror;
+	int err;
+
+	mirror = FF_LAYOUT_COMP(lseg, idx);
+	err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
+				       mirror, offset, length, status, opnum,
+				       GFP_NOIO);
+	dprintk("%s: err %d op %d status %u\n", __func__, err, opnum, status);
+}
+
+/* NFS_PROTO call done callback routines */
+
+static int ff_layout_read_done_cb(struct rpc_task *task,
+				struct nfs_pgio_header *hdr)
+{
+	struct inode *inode;
+	int err;
+
+	trace_nfs4_pnfs_read(hdr, task->tk_status);
+	if (task->tk_status == -ETIMEDOUT && !hdr->res.op_status)
+		hdr->res.op_status = NFS4ERR_NXIO;
+	if (task->tk_status < 0 && hdr->res.op_status)
+		ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx,
+					    hdr->args.offset, hdr->args.count,
+					    hdr->res.op_status, OP_READ);
+	err = ff_layout_async_handle_error(task, hdr->args.context->state,
+					   hdr->ds_clp, hdr->lseg,
+					   hdr->pgio_mirror_idx);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_PNFS:
+		set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+			&hdr->lseg->pls_layout->plh_flags);
+		pnfs_read_resend_pnfs(hdr);
+		return task->tk_status;
+	case -NFS4ERR_RESET_TO_MDS:
+		inode = hdr->lseg->pls_layout->plh_inode;
+		pnfs_error_mark_layout_for_return(inode, hdr->lseg);
+		ff_layout_reset_read(hdr);
+		return task->tk_status;
+	case -EAGAIN:
+		rpc_restart_call_prepare(task);
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+
+/*
+ * We reference the rpc_cred of the first WRITE that triggers the need for
+ * a LAYOUTCOMMIT, and use it to send the layoutcommit compound.
+ * rfc5661 is not clear about which credential should be used.
+ *
+ * Flexlayout client should treat DS replied FILE_SYNC as DATA_SYNC, so
+ * to follow http://www.rfc-editor.org/errata_search.php?rfc=5661&eid=2751
+ * we always send layoutcommit after DS writes.
+ */
+static void
+ff_layout_set_layoutcommit(struct nfs_pgio_header *hdr)
+{
+	pnfs_set_layoutcommit(hdr);
+	dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
+		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
+}
+
+static bool
+ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx)
+{
+	/* No mirroring for now */
+	struct nfs4_deviceid_node *node = FF_LAYOUT_DEVID_NODE(lseg, idx);
+
+	return ff_layout_test_devid_unavailable(node);
+}
+
+static int ff_layout_read_prepare_common(struct rpc_task *task,
+					 struct nfs_pgio_header *hdr)
+{
+	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
+		rpc_exit(task, -EIO);
+		return -EIO;
+	}
+	if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) {
+		dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
+		if (ff_layout_has_available_ds(hdr->lseg))
+			pnfs_read_resend_pnfs(hdr);
+		else
+			ff_layout_reset_read(hdr);
+		rpc_exit(task, 0);
+		return -EAGAIN;
+	}
+	hdr->pgio_done_cb = ff_layout_read_done_cb;
+
+	return 0;
+}
+
+/*
+ * Call ops for the async read/write cases
+ * In the case of dense layouts, the offset needs to be reset to its
+ * original value.
+ */
+static void ff_layout_read_prepare_v3(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (ff_layout_read_prepare_common(task, hdr))
+		return;
+
+	rpc_call_start(task);
+}
+
+static int ff_layout_setup_sequence(struct nfs_client *ds_clp,
+				    struct nfs4_sequence_args *args,
+				    struct nfs4_sequence_res *res,
+				    struct rpc_task *task)
+{
+	if (ds_clp->cl_session)
+		return nfs41_setup_sequence(ds_clp->cl_session,
+					   args,
+					   res,
+					   task);
+	return nfs40_setup_sequence(ds_clp->cl_slot_tbl,
+				   args,
+				   res,
+				   task);
+}
+
+static void ff_layout_read_prepare_v4(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (ff_layout_read_prepare_common(task, hdr))
+		return;
+
+	if (ff_layout_setup_sequence(hdr->ds_clp,
+				     &hdr->args.seq_args,
+				     &hdr->res.seq_res,
+				     task))
+		return;
+
+	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
+			hdr->args.lock_context, FMODE_READ) == -EIO)
+		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
+}
+
+static void ff_layout_read_call_done(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
+	    task->tk_status == 0) {
+		nfs4_sequence_done(task, &hdr->res.seq_res);
+		return;
+	}
+
+	/* Note this may cause RPC to be resent */
+	hdr->mds_ops->rpc_call_done(task, hdr);
+}
+
+static void ff_layout_read_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	rpc_count_iostats_metrics(task,
+	    &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_READ]);
+}
+
+static int ff_layout_write_done_cb(struct rpc_task *task,
+				struct nfs_pgio_header *hdr)
+{
+	struct inode *inode;
+	int err;
+
+	trace_nfs4_pnfs_write(hdr, task->tk_status);
+	if (task->tk_status == -ETIMEDOUT && !hdr->res.op_status)
+		hdr->res.op_status = NFS4ERR_NXIO;
+	if (task->tk_status < 0 && hdr->res.op_status)
+		ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx,
+					    hdr->args.offset, hdr->args.count,
+					    hdr->res.op_status, OP_WRITE);
+	err = ff_layout_async_handle_error(task, hdr->args.context->state,
+					   hdr->ds_clp, hdr->lseg,
+					   hdr->pgio_mirror_idx);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_PNFS:
+	case -NFS4ERR_RESET_TO_MDS:
+		inode = hdr->lseg->pls_layout->plh_inode;
+		pnfs_error_mark_layout_for_return(inode, hdr->lseg);
+		if (err == -NFS4ERR_RESET_TO_PNFS) {
+			pnfs_set_retry_layoutget(hdr->lseg->pls_layout);
+			ff_layout_reset_write(hdr, true);
+		} else {
+			pnfs_clear_retry_layoutget(hdr->lseg->pls_layout);
+			ff_layout_reset_write(hdr, false);
+		}
+		return task->tk_status;
+	case -EAGAIN:
+		rpc_restart_call_prepare(task);
+		return -EAGAIN;
+	}
+
+	if (hdr->res.verf->committed == NFS_FILE_SYNC ||
+	    hdr->res.verf->committed == NFS_DATA_SYNC)
+		ff_layout_set_layoutcommit(hdr);
+
+	return 0;
+}
+
+static int ff_layout_commit_done_cb(struct rpc_task *task,
+				     struct nfs_commit_data *data)
+{
+	struct inode *inode;
+	int err;
+
+	trace_nfs4_pnfs_commit_ds(data, task->tk_status);
+	if (task->tk_status == -ETIMEDOUT && !data->res.op_status)
+		data->res.op_status = NFS4ERR_NXIO;
+	if (task->tk_status < 0 && data->res.op_status)
+		ff_layout_io_track_ds_error(data->lseg, data->ds_commit_index,
+					    data->args.offset, data->args.count,
+					    data->res.op_status, OP_COMMIT);
+	err = ff_layout_async_handle_error(task, NULL, data->ds_clp,
+					   data->lseg, data->ds_commit_index);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_PNFS:
+	case -NFS4ERR_RESET_TO_MDS:
+		inode = data->lseg->pls_layout->plh_inode;
+		pnfs_error_mark_layout_for_return(inode, data->lseg);
+		if (err == -NFS4ERR_RESET_TO_PNFS)
+			pnfs_set_retry_layoutget(data->lseg->pls_layout);
+		else
+			pnfs_clear_retry_layoutget(data->lseg->pls_layout);
+		pnfs_generic_prepare_to_resend_writes(data);
+		return -EAGAIN;
+	case -EAGAIN:
+		rpc_restart_call_prepare(task);
+		return -EAGAIN;
+	}
+
+	if (data->verf.committed == NFS_UNSTABLE)
+		pnfs_commit_set_layoutcommit(data);
+
+	return 0;
+}
+
+static int ff_layout_write_prepare_common(struct rpc_task *task,
+					  struct nfs_pgio_header *hdr)
+{
+	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
+		rpc_exit(task, -EIO);
+		return -EIO;
+	}
+
+	if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) {
+		bool retry_pnfs;
+
+		retry_pnfs = ff_layout_has_available_ds(hdr->lseg);
+		dprintk("%s task %u reset io to %s\n", __func__,
+			task->tk_pid, retry_pnfs ? "pNFS" : "MDS");
+		ff_layout_reset_write(hdr, retry_pnfs);
+		rpc_exit(task, 0);
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+
+static void ff_layout_write_prepare_v3(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (ff_layout_write_prepare_common(task, hdr))
+		return;
+
+	rpc_call_start(task);
+}
+
+static void ff_layout_write_prepare_v4(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (ff_layout_write_prepare_common(task, hdr))
+		return;
+
+	if (ff_layout_setup_sequence(hdr->ds_clp,
+				     &hdr->args.seq_args,
+				     &hdr->res.seq_res,
+				     task))
+		return;
+
+	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
+			hdr->args.lock_context, FMODE_WRITE) == -EIO)
+		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
+}
+
+static void ff_layout_write_call_done(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
+	    task->tk_status == 0) {
+		nfs4_sequence_done(task, &hdr->res.seq_res);
+		return;
+	}
+
+	/* Note this may cause RPC to be resent */
+	hdr->mds_ops->rpc_call_done(task, hdr);
+}
+
+static void ff_layout_write_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	rpc_count_iostats_metrics(task,
+	    &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]);
+}
+
+static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data)
+{
+	rpc_call_start(task);
+}
+
+static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *wdata = data;
+
+	ff_layout_setup_sequence(wdata->ds_clp,
+				 &wdata->args.seq_args,
+				 &wdata->res.seq_res,
+				 task);
+}
+
+static void ff_layout_commit_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *cdata = data;
+
+	rpc_count_iostats_metrics(task,
+	    &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]);
+}
+
+static const struct rpc_call_ops ff_layout_read_call_ops_v3 = {
+	.rpc_call_prepare = ff_layout_read_prepare_v3,
+	.rpc_call_done = ff_layout_read_call_done,
+	.rpc_count_stats = ff_layout_read_count_stats,
+	.rpc_release = pnfs_generic_rw_release,
+};
+
+static const struct rpc_call_ops ff_layout_read_call_ops_v4 = {
+	.rpc_call_prepare = ff_layout_read_prepare_v4,
+	.rpc_call_done = ff_layout_read_call_done,
+	.rpc_count_stats = ff_layout_read_count_stats,
+	.rpc_release = pnfs_generic_rw_release,
+};
+
+static const struct rpc_call_ops ff_layout_write_call_ops_v3 = {
+	.rpc_call_prepare = ff_layout_write_prepare_v3,
+	.rpc_call_done = ff_layout_write_call_done,
+	.rpc_count_stats = ff_layout_write_count_stats,
+	.rpc_release = pnfs_generic_rw_release,
+};
+
+static const struct rpc_call_ops ff_layout_write_call_ops_v4 = {
+	.rpc_call_prepare = ff_layout_write_prepare_v4,
+	.rpc_call_done = ff_layout_write_call_done,
+	.rpc_count_stats = ff_layout_write_count_stats,
+	.rpc_release = pnfs_generic_rw_release,
+};
+
+static const struct rpc_call_ops ff_layout_commit_call_ops_v3 = {
+	.rpc_call_prepare = ff_layout_commit_prepare_v3,
+	.rpc_call_done = pnfs_generic_write_commit_done,
+	.rpc_count_stats = ff_layout_commit_count_stats,
+	.rpc_release = pnfs_generic_commit_release,
+};
+
+static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = {
+	.rpc_call_prepare = ff_layout_commit_prepare_v4,
+	.rpc_call_done = pnfs_generic_write_commit_done,
+	.rpc_count_stats = ff_layout_commit_count_stats,
+	.rpc_release = pnfs_generic_commit_release,
+};
+
+static enum pnfs_try_status
+ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
+{
+	struct pnfs_layout_segment *lseg = hdr->lseg;
+	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
+	struct rpc_cred *ds_cred;
+	loff_t offset = hdr->args.offset;
+	u32 idx = hdr->pgio_mirror_idx;
+	int vers;
+	struct nfs_fh *fh;
+
+	dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n",
+		__func__, hdr->inode->i_ino,
+		hdr->args.pgbase, (size_t)hdr->args.count, offset);
+
+	ds = nfs4_ff_layout_prepare_ds(lseg, idx, false);
+	if (!ds)
+		goto out_failed;
+
+	ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
+						   hdr->inode);
+	if (IS_ERR(ds_clnt))
+		goto out_failed;
+
+	ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
+	if (IS_ERR(ds_cred))
+		goto out_failed;
+
+	vers = nfs4_ff_layout_ds_version(lseg, idx);
+
+	dprintk("%s USE DS: %s cl_count %d vers %d\n", __func__,
+		ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), vers);
+
+	atomic_inc(&ds->ds_clp->cl_count);
+	hdr->ds_clp = ds->ds_clp;
+	fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
+	if (fh)
+		hdr->args.fh = fh;
+
+	/*
+	 * Note that if we ever decide to split across DSes,
+	 * then we may need to handle dense-like offsets.
+	 */
+	hdr->args.offset = offset;
+	hdr->mds_offset = offset;
+
+	/* Perform an asynchronous read to ds */
+	nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
+			  vers == 3 ? &ff_layout_read_call_ops_v3 :
+				      &ff_layout_read_call_ops_v4,
+			  0, RPC_TASK_SOFTCONN);
+
+	return PNFS_ATTEMPTED;
+
+out_failed:
+	if (ff_layout_has_available_ds(lseg))
+		return PNFS_TRY_AGAIN;
+	return PNFS_NOT_ATTEMPTED;
+}
+
+/* Perform async writes. */
+static enum pnfs_try_status
+ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
+{
+	struct pnfs_layout_segment *lseg = hdr->lseg;
+	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
+	struct rpc_cred *ds_cred;
+	loff_t offset = hdr->args.offset;
+	int vers;
+	struct nfs_fh *fh;
+	int idx = hdr->pgio_mirror_idx;
+
+	ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
+	if (!ds)
+		return PNFS_NOT_ATTEMPTED;
+
+	ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
+						   hdr->inode);
+	if (IS_ERR(ds_clnt))
+		return PNFS_NOT_ATTEMPTED;
+
+	ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
+	if (IS_ERR(ds_cred))
+		return PNFS_NOT_ATTEMPTED;
+
+	vers = nfs4_ff_layout_ds_version(lseg, idx);
+
+	dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d vers %d\n",
+		__func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
+		offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count),
+		vers);
+
+	hdr->pgio_done_cb = ff_layout_write_done_cb;
+	atomic_inc(&ds->ds_clp->cl_count);
+	hdr->ds_clp = ds->ds_clp;
+	hdr->ds_commit_idx = idx;
+	fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
+	if (fh)
+		hdr->args.fh = fh;
+
+	/*
+	 * Note that if we ever decide to split across DSes,
+	 * then we may need to handle dense-like offsets.
+	 */
+	hdr->args.offset = offset;
+
+	/* Perform an asynchronous write */
+	nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
+			  vers == 3 ? &ff_layout_write_call_ops_v3 :
+				      &ff_layout_write_call_ops_v4,
+			  sync, RPC_TASK_SOFTCONN);
+	return PNFS_ATTEMPTED;
+}
+
+static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i)
+{
+	return i;
+}
+
+static struct nfs_fh *
+select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i)
+{
+	struct nfs4_ff_layout_segment *flseg = FF_LAYOUT_LSEG(lseg);
+
+	/* FIXME: Assume that there is only one NFS version available
+	 * for the DS.
+	 */
+	return &flseg->mirror_array[i]->fh_versions[0];
+}
+
+static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
+{
+	struct pnfs_layout_segment *lseg = data->lseg;
+	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
+	struct rpc_cred *ds_cred;
+	u32 idx;
+	int vers;
+	struct nfs_fh *fh;
+
+	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
+	ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
+	if (!ds)
+		goto out_err;
+
+	ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
+						   data->inode);
+	if (IS_ERR(ds_clnt))
+		goto out_err;
+
+	ds_cred = ff_layout_get_ds_cred(lseg, idx, data->cred);
+	if (IS_ERR(ds_cred))
+		goto out_err;
+
+	vers = nfs4_ff_layout_ds_version(lseg, idx);
+
+	dprintk("%s ino %lu, how %d cl_count %d vers %d\n", __func__,
+		data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count),
+		vers);
+	data->commit_done_cb = ff_layout_commit_done_cb;
+	data->cred = ds_cred;
+	atomic_inc(&ds->ds_clp->cl_count);
+	data->ds_clp = ds->ds_clp;
+	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
+	if (fh)
+		data->args.fh = fh;
+	return nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
+				   vers == 3 ? &ff_layout_commit_call_ops_v3 :
+					       &ff_layout_commit_call_ops_v4,
+				   how, RPC_TASK_SOFTCONN);
+out_err:
+	pnfs_generic_prepare_to_resend_writes(data);
+	pnfs_generic_commit_release(data);
+	return -EAGAIN;
+}
+
+static int
+ff_layout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
+			   int how, struct nfs_commit_info *cinfo)
+{
+	return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo,
+					    ff_layout_initiate_commit);
+}
+
+static struct pnfs_ds_commit_info *
+ff_layout_get_ds_info(struct inode *inode)
+{
+	struct pnfs_layout_hdr *layout = NFS_I(inode)->layout;
+
+	if (layout == NULL)
+		return NULL;
+
+	return &FF_LAYOUT_FROM_HDR(layout)->commit_info;
+}
+
+static void
+ff_layout_free_deveiceid_node(struct nfs4_deviceid_node *d)
+{
+	nfs4_ff_layout_free_deviceid(container_of(d, struct nfs4_ff_layout_ds,
+						  id_node));
+}
+
+static int ff_layout_encode_ioerr(struct nfs4_flexfile_layout *flo,
+				  struct xdr_stream *xdr,
+				  const struct nfs4_layoutreturn_args *args)
+{
+	struct pnfs_layout_hdr *hdr = &flo->generic_hdr;
+	__be32 *start;
+	int count = 0, ret = 0;
+
+	start = xdr_reserve_space(xdr, 4);
+	if (unlikely(!start))
+		return -E2BIG;
+
+	/* This assume we always return _ALL_ layouts */
+	spin_lock(&hdr->plh_inode->i_lock);
+	ret = ff_layout_encode_ds_ioerr(flo, xdr, &count, &args->range);
+	spin_unlock(&hdr->plh_inode->i_lock);
+
+	*start = cpu_to_be32(count);
+
+	return ret;
+}
+
+/* report nothing for now */
+static void ff_layout_encode_iostats(struct nfs4_flexfile_layout *flo,
+				     struct xdr_stream *xdr,
+				     const struct nfs4_layoutreturn_args *args)
+{
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (likely(p))
+		*p = cpu_to_be32(0);
+}
+
+static struct nfs4_deviceid_node *
+ff_layout_alloc_deviceid_node(struct nfs_server *server,
+			      struct pnfs_device *pdev, gfp_t gfp_flags)
+{
+	struct nfs4_ff_layout_ds *dsaddr;
+
+	dsaddr = nfs4_ff_alloc_deviceid_node(server, pdev, gfp_flags);
+	if (!dsaddr)
+		return NULL;
+	return &dsaddr->id_node;
+}
+
+static void
+ff_layout_encode_layoutreturn(struct pnfs_layout_hdr *lo,
+			      struct xdr_stream *xdr,
+			      const struct nfs4_layoutreturn_args *args)
+{
+	struct nfs4_flexfile_layout *flo = FF_LAYOUT_FROM_HDR(lo);
+	__be32 *start;
+
+	dprintk("%s: Begin\n", __func__);
+	start = xdr_reserve_space(xdr, 4);
+	BUG_ON(!start);
+
+	if (ff_layout_encode_ioerr(flo, xdr, args))
+		goto out;
+
+	ff_layout_encode_iostats(flo, xdr, args);
+out:
+	*start = cpu_to_be32((xdr->p - start - 1) * 4);
+	dprintk("%s: Return\n", __func__);
+}
+
+static struct pnfs_layoutdriver_type flexfilelayout_type = {
+	.id			= LAYOUT_FLEX_FILES,
+	.name			= "LAYOUT_FLEX_FILES",
+	.owner			= THIS_MODULE,
+	.alloc_layout_hdr	= ff_layout_alloc_layout_hdr,
+	.free_layout_hdr	= ff_layout_free_layout_hdr,
+	.alloc_lseg		= ff_layout_alloc_lseg,
+	.free_lseg		= ff_layout_free_lseg,
+	.pg_read_ops		= &ff_layout_pg_read_ops,
+	.pg_write_ops		= &ff_layout_pg_write_ops,
+	.get_ds_info		= ff_layout_get_ds_info,
+	.free_deviceid_node	= ff_layout_free_deveiceid_node,
+	.mark_request_commit	= pnfs_layout_mark_request_commit,
+	.clear_request_commit	= pnfs_generic_clear_request_commit,
+	.scan_commit_lists	= pnfs_generic_scan_commit_lists,
+	.recover_commit_reqs	= pnfs_generic_recover_commit_reqs,
+	.commit_pagelist	= ff_layout_commit_pagelist,
+	.read_pagelist		= ff_layout_read_pagelist,
+	.write_pagelist		= ff_layout_write_pagelist,
+	.alloc_deviceid_node    = ff_layout_alloc_deviceid_node,
+	.encode_layoutreturn    = ff_layout_encode_layoutreturn,
+};
+
+static int __init nfs4flexfilelayout_init(void)
+{
+	printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Registering...\n",
+	       __func__);
+	return pnfs_register_layoutdriver(&flexfilelayout_type);
+}
+
+static void __exit nfs4flexfilelayout_exit(void)
+{
+	printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Unregistering...\n",
+	       __func__);
+	pnfs_unregister_layoutdriver(&flexfilelayout_type);
+}
+
+MODULE_ALIAS("nfs-layouttype4-4");
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("The NFSv4 flexfile layout driver");
+
+module_init(nfs4flexfilelayout_init);
+module_exit(nfs4flexfilelayout_exit);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
new file mode 100644
index 000000000000..070f20445b2d
--- /dev/null
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -0,0 +1,155 @@
+/*
+ * NFSv4 flexfile layout driver data structures.
+ *
+ * Copyright (c) 2014, Primary Data, Inc. All rights reserved.
+ *
+ * Tao Peng <bergwolf@primarydata.com>
+ */
+
+#ifndef FS_NFS_NFS4FLEXFILELAYOUT_H
+#define FS_NFS_NFS4FLEXFILELAYOUT_H
+
+#include "../pnfs.h"
+
+/* XXX: Let's filter out insanely large mirror count for now to avoid oom
+ * due to network error etc. */
+#define NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT 4096
+
+struct nfs4_ff_ds_version {
+	u32				version;
+	u32				minor_version;
+	u32				rsize;
+	u32				wsize;
+	bool				tightly_coupled;
+};
+
+/* chained in global deviceid hlist */
+struct nfs4_ff_layout_ds {
+	struct nfs4_deviceid_node	id_node;
+	u32				ds_versions_cnt;
+	struct nfs4_ff_ds_version	*ds_versions;
+	struct nfs4_pnfs_ds		*ds;
+};
+
+struct nfs4_ff_layout_ds_err {
+	struct list_head		list; /* linked in mirror error_list */
+	u64				offset;
+	u64				length;
+	int				status;
+	enum nfs_opnum4			opnum;
+	nfs4_stateid			stateid;
+	struct nfs4_deviceid		deviceid;
+};
+
+struct nfs4_ff_layout_mirror {
+	u32				ds_count;
+	u32				efficiency;
+	struct nfs4_ff_layout_ds	*mirror_ds;
+	u32				fh_versions_cnt;
+	struct nfs_fh			*fh_versions;
+	nfs4_stateid			stateid;
+	struct nfs4_string		user_name;
+	struct nfs4_string		group_name;
+	u32				uid;
+	u32				gid;
+	struct rpc_cred			*cred;
+	spinlock_t			lock;
+};
+
+struct nfs4_ff_layout_segment {
+	struct pnfs_layout_segment	generic_hdr;
+	u64				stripe_unit;
+	u32				mirror_array_cnt;
+	struct nfs4_ff_layout_mirror	**mirror_array;
+};
+
+struct nfs4_flexfile_layout {
+	struct pnfs_layout_hdr generic_hdr;
+	struct pnfs_ds_commit_info commit_info;
+	struct list_head	error_list; /* nfs4_ff_layout_ds_err */
+};
+
+static inline struct nfs4_flexfile_layout *
+FF_LAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo)
+{
+	return container_of(lo, struct nfs4_flexfile_layout, generic_hdr);
+}
+
+static inline struct nfs4_ff_layout_segment *
+FF_LAYOUT_LSEG(struct pnfs_layout_segment *lseg)
+{
+	return container_of(lseg,
+			    struct nfs4_ff_layout_segment,
+			    generic_hdr);
+}
+
+static inline struct nfs4_deviceid_node *
+FF_LAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg, u32 idx)
+{
+	if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt ||
+	    FF_LAYOUT_LSEG(lseg)->mirror_array[idx] == NULL ||
+	    FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds == NULL)
+		return NULL;
+	return &FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds->id_node;
+}
+
+static inline struct nfs4_ff_layout_ds *
+FF_LAYOUT_MIRROR_DS(struct nfs4_deviceid_node *node)
+{
+	return container_of(node, struct nfs4_ff_layout_ds, id_node);
+}
+
+static inline struct nfs4_ff_layout_mirror *
+FF_LAYOUT_COMP(struct pnfs_layout_segment *lseg, u32 idx)
+{
+	if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt)
+		return NULL;
+	return FF_LAYOUT_LSEG(lseg)->mirror_array[idx];
+}
+
+static inline u32
+FF_LAYOUT_MIRROR_COUNT(struct pnfs_layout_segment *lseg)
+{
+	return FF_LAYOUT_LSEG(lseg)->mirror_array_cnt;
+}
+
+static inline bool
+ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
+{
+	return nfs4_test_deviceid_unavailable(node);
+}
+
+static inline int
+nfs4_ff_layout_ds_version(struct pnfs_layout_segment *lseg, u32 ds_idx)
+{
+	return FF_LAYOUT_COMP(lseg, ds_idx)->mirror_ds->ds_versions[0].version;
+}
+
+struct nfs4_ff_layout_ds *
+nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+			    gfp_t gfp_flags);
+void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds);
+void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds);
+int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
+			     struct nfs4_ff_layout_mirror *mirror, u64 offset,
+			     u64 length, int status, enum nfs_opnum4 opnum,
+			     gfp_t gfp_flags);
+int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo,
+			      struct xdr_stream *xdr, int *count,
+			      const struct pnfs_layout_range *range);
+struct nfs_fh *
+nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx);
+
+struct nfs4_pnfs_ds *
+nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
+			  bool fail_return);
+
+struct rpc_clnt *
+nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg,
+				 u32 ds_idx,
+				 struct nfs_client *ds_clp,
+				 struct inode *inode);
+struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg,
+				       u32 ds_idx, struct rpc_cred *mdscred);
+bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg);
+#endif /* FS_NFS_NFS4FLEXFILELAYOUT_H */
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
new file mode 100644
index 000000000000..e2c01f204a95
--- /dev/null
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -0,0 +1,552 @@
+/*
+ * Device operations for the pnfs nfs4 file layout driver.
+ *
+ * Copyright (c) 2014, Primary Data, Inc. All rights reserved.
+ *
+ * Tao Peng <bergwolf@primarydata.com>
+ */
+
+#include <linux/nfs_fs.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+#include <linux/sunrpc/addr.h>
+
+#include "../internal.h"
+#include "../nfs4session.h"
+#include "flexfilelayout.h"
+
+#define NFSDBG_FACILITY		NFSDBG_PNFS_LD
+
+static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
+static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
+
+void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
+{
+	if (mirror_ds)
+		nfs4_put_deviceid_node(&mirror_ds->id_node);
+}
+
+void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
+{
+	nfs4_print_deviceid(&mirror_ds->id_node.deviceid);
+	nfs4_pnfs_ds_put(mirror_ds->ds);
+	kfree(mirror_ds);
+}
+
+/* Decode opaque device data and construct new_ds using it */
+struct nfs4_ff_layout_ds *
+nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+			    gfp_t gfp_flags)
+{
+	struct xdr_stream stream;
+	struct xdr_buf buf;
+	struct page *scratch;
+	struct list_head dsaddrs;
+	struct nfs4_pnfs_ds_addr *da;
+	struct nfs4_ff_layout_ds *new_ds = NULL;
+	struct nfs4_ff_ds_version *ds_versions = NULL;
+	u32 mp_count;
+	u32 version_count;
+	__be32 *p;
+	int i, ret = -ENOMEM;
+
+	/* set up xdr stream */
+	scratch = alloc_page(gfp_flags);
+	if (!scratch)
+		goto out_err;
+
+	new_ds = kzalloc(sizeof(struct nfs4_ff_layout_ds), gfp_flags);
+	if (!new_ds)
+		goto out_scratch;
+
+	nfs4_init_deviceid_node(&new_ds->id_node,
+				server,
+				&pdev->dev_id);
+	INIT_LIST_HEAD(&dsaddrs);
+
+	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
+	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+
+	/* multipath count */
+	p = xdr_inline_decode(&stream, 4);
+	if (unlikely(!p))
+		goto out_err_drain_dsaddrs;
+	mp_count = be32_to_cpup(p);
+	dprintk("%s: multipath ds count %d\n", __func__, mp_count);
+
+	for (i = 0; i < mp_count; i++) {
+		/* multipath ds */
+		da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
+					    &stream, gfp_flags);
+		if (da)
+			list_add_tail(&da->da_node, &dsaddrs);
+	}
+	if (list_empty(&dsaddrs)) {
+		dprintk("%s: no suitable DS addresses found\n",
+			__func__);
+		ret = -ENOMEDIUM;
+		goto out_err_drain_dsaddrs;
+	}
+
+	/* version count */
+	p = xdr_inline_decode(&stream, 4);
+	if (unlikely(!p))
+		goto out_err_drain_dsaddrs;
+	version_count = be32_to_cpup(p);
+	dprintk("%s: version count %d\n", __func__, version_count);
+
+	ds_versions = kzalloc(version_count * sizeof(struct nfs4_ff_ds_version),
+			      gfp_flags);
+	if (!ds_versions)
+		goto out_scratch;
+
+	for (i = 0; i < version_count; i++) {
+		/* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) +
+		 * tightly_coupled(4) */
+		p = xdr_inline_decode(&stream, 20);
+		if (unlikely(!p))
+			goto out_err_drain_dsaddrs;
+		ds_versions[i].version = be32_to_cpup(p++);
+		ds_versions[i].minor_version = be32_to_cpup(p++);
+		ds_versions[i].rsize = nfs_block_size(be32_to_cpup(p++), NULL);
+		ds_versions[i].wsize = nfs_block_size(be32_to_cpup(p++), NULL);
+		ds_versions[i].tightly_coupled = be32_to_cpup(p);
+
+		if (ds_versions[i].rsize > NFS_MAX_FILE_IO_SIZE)
+			ds_versions[i].rsize = NFS_MAX_FILE_IO_SIZE;
+		if (ds_versions[i].wsize > NFS_MAX_FILE_IO_SIZE)
+			ds_versions[i].wsize = NFS_MAX_FILE_IO_SIZE;
+
+		if (ds_versions[i].version != 3 || ds_versions[i].minor_version != 0) {
+			dprintk("%s: [%d] unsupported ds version %d-%d\n", __func__,
+				i, ds_versions[i].version,
+				ds_versions[i].minor_version);
+			ret = -EPROTONOSUPPORT;
+			goto out_err_drain_dsaddrs;
+		}
+
+		dprintk("%s: [%d] vers %u minor_ver %u rsize %u wsize %u coupled %d\n",
+			__func__, i, ds_versions[i].version,
+			ds_versions[i].minor_version,
+			ds_versions[i].rsize,
+			ds_versions[i].wsize,
+			ds_versions[i].tightly_coupled);
+	}
+
+	new_ds->ds_versions = ds_versions;
+	new_ds->ds_versions_cnt = version_count;
+
+	new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+	if (!new_ds->ds)
+		goto out_err_drain_dsaddrs;
+
+	/* If DS was already in cache, free ds addrs */
+	while (!list_empty(&dsaddrs)) {
+		da = list_first_entry(&dsaddrs,
+				      struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+
+	__free_page(scratch);
+	return new_ds;
+
+out_err_drain_dsaddrs:
+	while (!list_empty(&dsaddrs)) {
+		da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+
+	kfree(ds_versions);
+out_scratch:
+	__free_page(scratch);
+out_err:
+	kfree(new_ds);
+
+	dprintk("%s ERROR: returning %d\n", __func__, ret);
+	return NULL;
+}
+
+static u64
+end_offset(u64 start, u64 len)
+{
+	u64 end;
+
+	end = start + len;
+	return end >= start ? end : NFS4_MAX_UINT64;
+}
+
+static void extend_ds_error(struct nfs4_ff_layout_ds_err *err,
+			    u64 offset, u64 length)
+{
+	u64 end;
+
+	end = max_t(u64, end_offset(err->offset, err->length),
+		    end_offset(offset, length));
+	err->offset = min_t(u64, err->offset, offset);
+	err->length = end - err->offset;
+}
+
+static bool ds_error_can_merge(struct nfs4_ff_layout_ds_err *err,  u64 offset,
+			       u64 length, int status, enum nfs_opnum4 opnum,
+			       nfs4_stateid *stateid,
+			       struct nfs4_deviceid *deviceid)
+{
+	return err->status == status && err->opnum == opnum &&
+	       nfs4_stateid_match(&err->stateid, stateid) &&
+	       !memcmp(&err->deviceid, deviceid, sizeof(*deviceid)) &&
+	       end_offset(err->offset, err->length) >= offset &&
+	       err->offset <= end_offset(offset, length);
+}
+
+static bool merge_ds_error(struct nfs4_ff_layout_ds_err *old,
+			   struct nfs4_ff_layout_ds_err *new)
+{
+	if (!ds_error_can_merge(old, new->offset, new->length, new->status,
+				new->opnum, &new->stateid, &new->deviceid))
+		return false;
+
+	extend_ds_error(old, new->offset, new->length);
+	return true;
+}
+
+static bool
+ff_layout_add_ds_error_locked(struct nfs4_flexfile_layout *flo,
+			      struct nfs4_ff_layout_ds_err *dserr)
+{
+	struct nfs4_ff_layout_ds_err *err;
+
+	list_for_each_entry(err, &flo->error_list, list) {
+		if (merge_ds_error(err, dserr)) {
+			return true;
+		}
+	}
+
+	list_add(&dserr->list, &flo->error_list);
+	return false;
+}
+
+static bool
+ff_layout_update_ds_error(struct nfs4_flexfile_layout *flo, u64 offset,
+			  u64 length, int status, enum nfs_opnum4 opnum,
+			  nfs4_stateid *stateid, struct nfs4_deviceid *deviceid)
+{
+	bool found = false;
+	struct nfs4_ff_layout_ds_err *err;
+
+	list_for_each_entry(err, &flo->error_list, list) {
+		if (ds_error_can_merge(err, offset, length, status, opnum,
+				       stateid, deviceid)) {
+			found = true;
+			extend_ds_error(err, offset, length);
+			break;
+		}
+	}
+
+	return found;
+}
+
+int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
+			     struct nfs4_ff_layout_mirror *mirror, u64 offset,
+			     u64 length, int status, enum nfs_opnum4 opnum,
+			     gfp_t gfp_flags)
+{
+	struct nfs4_ff_layout_ds_err *dserr;
+	bool needfree;
+
+	if (status == 0)
+		return 0;
+
+	if (mirror->mirror_ds == NULL)
+		return -EINVAL;
+
+	spin_lock(&flo->generic_hdr.plh_inode->i_lock);
+	if (ff_layout_update_ds_error(flo, offset, length, status, opnum,
+				      &mirror->stateid,
+				      &mirror->mirror_ds->id_node.deviceid)) {
+		spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
+		return 0;
+	}
+	spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
+	dserr = kmalloc(sizeof(*dserr), gfp_flags);
+	if (!dserr)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&dserr->list);
+	dserr->offset = offset;
+	dserr->length = length;
+	dserr->status = status;
+	dserr->opnum = opnum;
+	nfs4_stateid_copy(&dserr->stateid, &mirror->stateid);
+	memcpy(&dserr->deviceid, &mirror->mirror_ds->id_node.deviceid,
+	       NFS4_DEVICEID4_SIZE);
+
+	spin_lock(&flo->generic_hdr.plh_inode->i_lock);
+	needfree = ff_layout_add_ds_error_locked(flo, dserr);
+	spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
+	if (needfree)
+		kfree(dserr);
+
+	return 0;
+}
+
+/* currently we only support AUTH_NONE and AUTH_SYS */
+static rpc_authflavor_t
+nfs4_ff_layout_choose_authflavor(struct nfs4_ff_layout_mirror *mirror)
+{
+	if (mirror->uid == (u32)-1)
+		return RPC_AUTH_NULL;
+	return RPC_AUTH_UNIX;
+}
+
+/* fetch cred for NFSv3 DS */
+static int ff_layout_update_mirror_cred(struct nfs4_ff_layout_mirror *mirror,
+				      struct nfs4_pnfs_ds *ds)
+{
+	if (ds->ds_clp && !mirror->cred &&
+	    mirror->mirror_ds->ds_versions[0].version == 3) {
+		struct rpc_auth *auth = ds->ds_clp->cl_rpcclient->cl_auth;
+		struct rpc_cred *cred;
+		struct auth_cred acred = {
+			.uid = make_kuid(&init_user_ns, mirror->uid),
+			.gid = make_kgid(&init_user_ns, mirror->gid),
+		};
+
+		/* AUTH_NULL ignores acred */
+		cred = auth->au_ops->lookup_cred(auth, &acred, 0);
+		if (IS_ERR(cred)) {
+			dprintk("%s: lookup_cred failed with %ld\n",
+				__func__, PTR_ERR(cred));
+			return PTR_ERR(cred);
+		} else {
+			mirror->cred = cred;
+		}
+	}
+	return 0;
+}
+
+struct nfs_fh *
+nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx)
+{
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, mirror_idx);
+	struct nfs_fh *fh = NULL;
+	struct nfs4_deviceid_node *devid;
+
+	if (mirror == NULL || mirror->mirror_ds == NULL ||
+	    mirror->mirror_ds->ds == NULL) {
+		printk(KERN_ERR "NFS: %s: No data server for mirror offset index %d\n",
+			__func__, mirror_idx);
+		if (mirror && mirror->mirror_ds) {
+			devid = &mirror->mirror_ds->id_node;
+			pnfs_generic_mark_devid_invalid(devid);
+		}
+		goto out;
+	}
+
+	/* FIXME: For now assume there is only 1 version available for the DS */
+	fh = &mirror->fh_versions[0];
+out:
+	return fh;
+}
+
+/* Upon return, either ds is connected, or ds is NULL */
+struct nfs4_pnfs_ds *
+nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
+			  bool fail_return)
+{
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
+	struct nfs4_pnfs_ds *ds = NULL;
+	struct nfs4_deviceid_node *devid;
+	struct inode *ino = lseg->pls_layout->plh_inode;
+	struct nfs_server *s = NFS_SERVER(ino);
+	unsigned int max_payload;
+	rpc_authflavor_t flavor;
+
+	if (mirror == NULL || mirror->mirror_ds == NULL ||
+	    mirror->mirror_ds->ds == NULL) {
+		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
+			__func__, ds_idx);
+		if (mirror && mirror->mirror_ds) {
+			devid = &mirror->mirror_ds->id_node;
+			pnfs_generic_mark_devid_invalid(devid);
+		}
+		goto out;
+	}
+
+	devid = &mirror->mirror_ds->id_node;
+	if (ff_layout_test_devid_unavailable(devid))
+		goto out;
+
+	ds = mirror->mirror_ds->ds;
+	/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
+	smp_rmb();
+	if (ds->ds_clp)
+		goto out;
+
+	flavor = nfs4_ff_layout_choose_authflavor(mirror);
+
+	/* FIXME: For now we assume the server sent only one version of NFS
+	 * to use for the DS.
+	 */
+	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+			     dataserver_retrans,
+			     mirror->mirror_ds->ds_versions[0].version,
+			     mirror->mirror_ds->ds_versions[0].minor_version,
+			     flavor);
+
+	/* connect success, check rsize/wsize limit */
+	if (ds->ds_clp) {
+		max_payload =
+			nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
+				       NULL);
+		if (mirror->mirror_ds->ds_versions[0].rsize > max_payload)
+			mirror->mirror_ds->ds_versions[0].rsize = max_payload;
+		if (mirror->mirror_ds->ds_versions[0].wsize > max_payload)
+			mirror->mirror_ds->ds_versions[0].wsize = max_payload;
+	} else {
+		ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
+					 mirror, lseg->pls_range.offset,
+					 lseg->pls_range.length, NFS4ERR_NXIO,
+					 OP_ILLEGAL, GFP_NOIO);
+		if (fail_return) {
+			pnfs_error_mark_layout_for_return(ino, lseg);
+			if (ff_layout_has_available_ds(lseg))
+				pnfs_set_retry_layoutget(lseg->pls_layout);
+			else
+				pnfs_clear_retry_layoutget(lseg->pls_layout);
+
+		} else {
+			if (ff_layout_has_available_ds(lseg))
+				set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					&lseg->pls_layout->plh_flags);
+			else {
+				pnfs_error_mark_layout_for_return(ino, lseg);
+				pnfs_clear_retry_layoutget(lseg->pls_layout);
+			}
+		}
+	}
+
+	if (ff_layout_update_mirror_cred(mirror, ds))
+		ds = NULL;
+out:
+	return ds;
+}
+
+struct rpc_cred *
+ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx,
+		      struct rpc_cred *mdscred)
+{
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
+	struct rpc_cred *cred = ERR_PTR(-EINVAL);
+
+	if (!nfs4_ff_layout_prepare_ds(lseg, ds_idx, true))
+		goto out;
+
+	if (mirror && mirror->cred)
+		cred = mirror->cred;
+	else
+		cred = mdscred;
+out:
+	return cred;
+}
+
+/**
+* Find or create a DS rpc client with th MDS server rpc client auth flavor
+* in the nfs_client cl_ds_clients list.
+*/
+struct rpc_clnt *
+nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, u32 ds_idx,
+				 struct nfs_client *ds_clp, struct inode *inode)
+{
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
+
+	switch (mirror->mirror_ds->ds_versions[0].version) {
+	case 3:
+		/* For NFSv3 DS, flavor is set when creating DS connections */
+		return ds_clp->cl_rpcclient;
+	case 4:
+		return nfs4_find_or_create_ds_client(ds_clp, inode);
+	default:
+		BUG();
+	}
+}
+
+static bool is_range_intersecting(u64 offset1, u64 length1,
+				  u64 offset2, u64 length2)
+{
+	u64 end1 = end_offset(offset1, length1);
+	u64 end2 = end_offset(offset2, length2);
+
+	return (end1 == NFS4_MAX_UINT64 || end1 > offset2) &&
+	       (end2 == NFS4_MAX_UINT64 || end2 > offset1);
+}
+
+/* called with inode i_lock held */
+int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo,
+			      struct xdr_stream *xdr, int *count,
+			      const struct pnfs_layout_range *range)
+{
+	struct nfs4_ff_layout_ds_err *err, *n;
+	__be32 *p;
+
+	list_for_each_entry_safe(err, n, &flo->error_list, list) {
+		if (!is_range_intersecting(err->offset, err->length,
+					   range->offset, range->length))
+			continue;
+		/* offset(8) + length(8) + stateid(NFS4_STATEID_SIZE)
+		 * + deviceid(NFS4_DEVICEID4_SIZE) + status(4) + opnum(4)
+		 */
+		p = xdr_reserve_space(xdr,
+				24 + NFS4_STATEID_SIZE + NFS4_DEVICEID4_SIZE);
+		if (unlikely(!p))
+			return -ENOBUFS;
+		p = xdr_encode_hyper(p, err->offset);
+		p = xdr_encode_hyper(p, err->length);
+		p = xdr_encode_opaque_fixed(p, &err->stateid,
+					    NFS4_STATEID_SIZE);
+		p = xdr_encode_opaque_fixed(p, &err->deviceid,
+					    NFS4_DEVICEID4_SIZE);
+		*p++ = cpu_to_be32(err->status);
+		*p++ = cpu_to_be32(err->opnum);
+		*count += 1;
+		list_del(&err->list);
+		dprintk("%s: offset %llu length %llu status %d op %d count %d\n",
+			__func__, err->offset, err->length, err->status,
+			err->opnum, *count);
+		kfree(err);
+	}
+
+	return 0;
+}
+
+bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg)
+{
+	struct nfs4_ff_layout_mirror *mirror;
+	struct nfs4_deviceid_node *devid;
+	int idx;
+
+	for (idx = 0; idx < FF_LAYOUT_MIRROR_COUNT(lseg); idx++) {
+		mirror = FF_LAYOUT_COMP(lseg, idx);
+		if (mirror && mirror->mirror_ds) {
+			devid = &mirror->mirror_ds->id_node;
+			if (!ff_layout_test_devid_unavailable(devid))
+				return true;
+		}
+	}
+
+	return false;
+}
+
+module_param(dataserver_retrans, uint, 0644);
+MODULE_PARM_DESC(dataserver_retrans, "The  number of times the NFSv4.1 client "
+			"retries a request before it attempts further "
+			" recovery  action.");
+module_param(dataserver_timeo, uint, 0644);
+MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the "
+			"NFSv4.1  client  waits for a response from a "
+			" data server before it retries an NFS request.");
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index 2f5db844c172..857e2a99acc8 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -152,7 +152,7 @@ void nfs_fattr_map_and_free_names(struct nfs_server *server, struct nfs_fattr *f
 		nfs_fattr_free_group_name(fattr);
 }
 
-static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res)
+int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res)
 {
 	unsigned long val;
 	char buf[16];
@@ -166,6 +166,7 @@ static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *re
 	*res = val;
 	return 1;
 }
+EXPORT_SYMBOL_GPL(nfs_map_string_to_numeric);
 
 static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen)
 {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 2211f6ba8736..d42dff6d5e98 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -388,7 +388,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		if (S_ISREG(inode->i_mode)) {
 			inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
 			inode->i_data.a_ops = &nfs_file_aops;
-			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
 		} else if (S_ISDIR(inode->i_mode)) {
 			inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
 			inode->i_fop = &nfs_dir_operations;
@@ -507,10 +506,15 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 		attr->ia_valid &= ~ATTR_MODE;
 
 	if (attr->ia_valid & ATTR_SIZE) {
+		loff_t i_size;
+
 		BUG_ON(!S_ISREG(inode->i_mode));
 
-		if (attr->ia_size == i_size_read(inode))
+		i_size = i_size_read(inode);
+		if (attr->ia_size == i_size)
 			attr->ia_valid &= ~ATTR_SIZE;
+		else if (attr->ia_size < i_size && IS_SWAPFILE(inode))
+			return -ETXTBSY;
 	}
 
 	/* Optimization: if the end result is no change, don't RPC */
@@ -552,6 +556,7 @@ EXPORT_SYMBOL_GPL(nfs_setattr);
  * This is a copy of the common vmtruncate, but with the locking
  * corrected to take into account the fact that NFS requires
  * inode->i_size to be updated under the inode->i_lock.
+ * Note: must be called with inode->i_lock held!
  */
 static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 {
@@ -561,14 +566,14 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 	if (err)
 		goto out;
 
-	spin_lock(&inode->i_lock);
 	i_size_write(inode, offset);
 	/* Optimisation */
 	if (offset == 0)
 		NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA;
-	spin_unlock(&inode->i_lock);
 
+	spin_unlock(&inode->i_lock);
 	truncate_pagecache(inode, offset);
+	spin_lock(&inode->i_lock);
 out:
 	return err;
 }
@@ -581,10 +586,15 @@ out:
  * Note: we do this in the *proc.c in order to ensure that
  *       it works for things like exclusive creates too.
  */
-void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
+void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
+		struct nfs_fattr *fattr)
 {
+	/* Barrier: bump the attribute generation count. */
+	nfs_fattr_set_barrier(fattr);
+
+	spin_lock(&inode->i_lock);
+	NFS_I(inode)->attr_gencount = fattr->gencount;
 	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
-		spin_lock(&inode->i_lock);
 		if ((attr->ia_valid & ATTR_MODE) != 0) {
 			int mode = attr->ia_mode & S_IALLUGO;
 			mode |= inode->i_mode & ~S_IALLUGO;
@@ -596,12 +606,13 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
 			inode->i_gid = attr->ia_gid;
 		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL);
-		spin_unlock(&inode->i_lock);
 	}
 	if ((attr->ia_valid & ATTR_SIZE) != 0) {
 		nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
 		nfs_vmtruncate(inode, attr->ia_size);
 	}
+	nfs_update_inode(inode, fattr);
+	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
 
@@ -1024,6 +1035,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 
 	if (mapping->nrpages != 0) {
 		if (S_ISREG(inode->i_mode)) {
+			unmap_mapping_range(mapping, 0, 0, 0);
 			ret = nfs_sync_mapping(mapping);
 			if (ret < 0)
 				return ret;
@@ -1056,11 +1068,14 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
 }
 
 /**
- * nfs_revalidate_mapping - Revalidate the pagecache
+ * __nfs_revalidate_mapping - Revalidate the pagecache
  * @inode - pointer to host inode
  * @mapping - pointer to mapping
+ * @may_lock - take inode->i_mutex?
  */
-int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
+static int __nfs_revalidate_mapping(struct inode *inode,
+		struct address_space *mapping,
+		bool may_lock)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	unsigned long *bitlock = &nfsi->flags;
@@ -1109,7 +1124,12 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
 	spin_unlock(&inode->i_lock);
 	trace_nfs_invalidate_mapping_enter(inode);
-	ret = nfs_invalidate_mapping(inode, mapping);
+	if (may_lock) {
+		mutex_lock(&inode->i_mutex);
+		ret = nfs_invalidate_mapping(inode, mapping);
+		mutex_unlock(&inode->i_mutex);
+	} else
+		ret = nfs_invalidate_mapping(inode, mapping);
 	trace_nfs_invalidate_mapping_exit(inode, ret);
 
 	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
@@ -1119,6 +1139,29 @@ out:
 	return ret;
 }
 
+/**
+ * nfs_revalidate_mapping - Revalidate the pagecache
+ * @inode - pointer to host inode
+ * @mapping - pointer to mapping
+ */
+int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
+{
+	return __nfs_revalidate_mapping(inode, mapping, false);
+}
+
+/**
+ * nfs_revalidate_mapping_protected - Revalidate the pagecache
+ * @inode - pointer to host inode
+ * @mapping - pointer to mapping
+ *
+ * Differs from nfs_revalidate_mapping() in that it grabs the inode->i_mutex
+ * while invalidating the mapping.
+ */
+int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping)
+{
+	return __nfs_revalidate_mapping(inode, mapping, true);
+}
+
 static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -1227,13 +1270,6 @@ static int nfs_ctime_need_update(const struct inode *inode, const struct nfs_fat
 	return timespec_compare(&fattr->ctime, &inode->i_ctime) > 0;
 }
 
-static int nfs_size_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
-{
-	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
-		return 0;
-	return nfs_size_to_loff_t(fattr->size) > i_size_read(inode);
-}
-
 static atomic_long_t nfs_attr_generation_counter;
 
 static unsigned long nfs_read_attr_generation_counter(void)
@@ -1245,6 +1281,7 @@ unsigned long nfs_inc_attr_generation_counter(void)
 {
 	return atomic_long_inc_return(&nfs_attr_generation_counter);
 }
+EXPORT_SYMBOL_GPL(nfs_inc_attr_generation_counter);
 
 void nfs_fattr_init(struct nfs_fattr *fattr)
 {
@@ -1256,6 +1293,22 @@ void nfs_fattr_init(struct nfs_fattr *fattr)
 }
 EXPORT_SYMBOL_GPL(nfs_fattr_init);
 
+/**
+ * nfs_fattr_set_barrier
+ * @fattr: attributes
+ *
+ * Used to set a barrier after an attribute was updated. This
+ * barrier ensures that older attributes from RPC calls that may
+ * have raced with our update cannot clobber these new values.
+ * Note that you are still responsible for ensuring that other
+ * operations which change the attribute on the server do not
+ * collide.
+ */
+void nfs_fattr_set_barrier(struct nfs_fattr *fattr)
+{
+	fattr->gencount = nfs_inc_attr_generation_counter();
+}
+
 struct nfs_fattr *nfs_alloc_fattr(void)
 {
 	struct nfs_fattr *fattr;
@@ -1366,7 +1419,6 @@ static int nfs_inode_attrs_need_update(const struct inode *inode, const struct n
 
 	return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 ||
 		nfs_ctime_need_update(inode, fattr) ||
-		nfs_size_need_update(inode, fattr) ||
 		((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
 }
 
@@ -1456,6 +1508,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	int status;
 
 	spin_lock(&inode->i_lock);
+	nfs_fattr_set_barrier(fattr);
 	status = nfs_post_op_update_inode_locked(inode, fattr);
 	spin_unlock(&inode->i_lock);
 
@@ -1464,7 +1517,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
 
 /**
- * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
+ * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache
  * @inode - pointer to inode
  * @fattr - updated attributes
  *
@@ -1474,11 +1527,10 @@ EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
  *
  * This function is mainly designed to be used by the ->write_done() functions.
  */
-int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
+int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
 	int status;
 
-	spin_lock(&inode->i_lock);
 	/* Don't do a WCC update if these attributes are already stale */
 	if ((fattr->valid & NFS_ATTR_FATTR) == 0 ||
 			!nfs_inode_attrs_need_update(inode, fattr)) {
@@ -1510,6 +1562,27 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa
 	}
 out_noforce:
 	status = nfs_post_op_update_inode_locked(inode, fattr);
+	return status;
+}
+
+/**
+ * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
+ * @inode - pointer to inode
+ * @fattr - updated attributes
+ *
+ * After an operation that has changed the inode metadata, mark the
+ * attribute cache as being invalid, then try to update it. Fake up
+ * weak cache consistency data, if none exist.
+ *
+ * This function is mainly designed to be used by the ->write_done() functions.
+ */
+int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
+{
+	int status;
+
+	spin_lock(&inode->i_lock);
+	nfs_fattr_set_barrier(fattr);
+	status = nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
 	spin_unlock(&inode->i_lock);
 	return status;
 }
@@ -1711,6 +1784,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 		nfsi->attrtimeo_timestamp = now;
+		/* Set barrier to be more recent than all outstanding updates */
 		nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	} else {
 		if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
@@ -1718,6 +1792,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
 			nfsi->attrtimeo_timestamp = now;
 		}
+		/* Set the barrier to be more recent than this fattr */
+		if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0)
+			nfsi->attr_gencount = fattr->gencount;
 	}
 	invalid &= ~NFS_INO_INVALID_ATTR;
 	/* Don't invalidate the data if we were to blame */
@@ -1771,7 +1848,6 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi)
 #if IS_ENABLED(CONFIG_NFS_V4)
 	INIT_LIST_HEAD(&nfsi->open_states);
 	nfsi->delegation = NULL;
-	nfsi->delegation_state = 0;
 	init_rwsem(&nfsi->rwsem);
 	nfsi->layout = NULL;
 #endif
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b6f34bfa6fe8..9e6475bc5ba2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -6,6 +6,7 @@
 #include <linux/mount.h>
 #include <linux/security.h>
 #include <linux/crc32.h>
+#include <linux/nfs_page.h>
 
 #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
 
@@ -187,9 +188,15 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 					     const struct sockaddr *ds_addr,
 					     int ds_addrlen, int ds_proto,
 					     unsigned int ds_timeo,
-					     unsigned int ds_retrans);
+					     unsigned int ds_retrans,
+					     u32 minor_version,
+					     rpc_authflavor_t au_flavor);
 extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *,
 						struct inode *);
+extern struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
+			const struct sockaddr *ds_addr, int ds_addrlen,
+			int ds_proto, unsigned int ds_timeo,
+			unsigned int ds_retrans, rpc_authflavor_t au_flavor);
 #ifdef CONFIG_PROC_FS
 extern int __init nfs_fs_proc_init(void);
 extern void nfs_fs_proc_exit(void);
@@ -242,9 +249,12 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
 void nfs_pgio_header_free(struct nfs_pgio_header *);
 void nfs_pgio_data_destroy(struct nfs_pgio_header *);
 int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
-int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_header *,
-		      const struct rpc_call_ops *, int, int);
+int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
+		      struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
+		      const struct rpc_call_ops *call_ops, int how, int flags);
 void nfs_free_request(struct nfs_page *req);
+struct nfs_pgio_mirror *
+nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc);
 
 static inline void nfs_iocounter_init(struct nfs_io_counter *c)
 {
@@ -252,6 +262,12 @@ static inline void nfs_iocounter_init(struct nfs_io_counter *c)
 	atomic_set(&c->io_count, 0);
 }
 
+static inline bool nfs_pgio_has_mirroring(struct nfs_pageio_descriptor *desc)
+{
+	WARN_ON_ONCE(desc->pg_mirror_count < 1);
+	return desc->pg_mirror_count > 1;
+}
+
 /* nfs2xdr.c */
 extern struct rpc_procinfo nfs_procedures[];
 extern int nfs2_decode_dirent(struct xdr_stream *,
@@ -375,7 +391,7 @@ extern struct rpc_stat nfs_rpcstat;
 
 extern int __init register_nfs_fs(void);
 extern void __exit unregister_nfs_fs(void);
-extern void nfs_sb_active(struct super_block *sb);
+extern bool nfs_sb_active(struct super_block *sb);
 extern void nfs_sb_deactive(struct super_block *sb);
 
 /* namespace.c */
@@ -414,7 +430,6 @@ int  nfs_show_options(struct seq_file *, struct dentry *);
 int  nfs_show_devname(struct seq_file *, struct dentry *);
 int  nfs_show_path(struct seq_file *, struct dentry *);
 int  nfs_show_stats(struct seq_file *, struct dentry *);
-void nfs_put_super(struct super_block *);
 int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
 
 /* write.c */
@@ -427,6 +442,7 @@ extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
 extern void nfs_commit_prepare(struct rpc_task *task, void *calldata);
 extern int nfs_initiate_commit(struct rpc_clnt *clnt,
 			       struct nfs_commit_data *data,
+			       const struct nfs_rpc_ops *nfs_ops,
 			       const struct rpc_call_ops *call_ops,
 			       int how, int flags);
 extern void nfs_init_commit(struct nfs_commit_data *data,
@@ -440,13 +456,16 @@ int nfs_scan_commit(struct inode *inode, struct list_head *dst,
 		    struct nfs_commit_info *cinfo);
 void nfs_mark_request_commit(struct nfs_page *req,
 			     struct pnfs_layout_segment *lseg,
-			     struct nfs_commit_info *cinfo);
+			     struct nfs_commit_info *cinfo,
+			     u32 ds_commit_idx);
 int nfs_write_need_commit(struct nfs_pgio_header *);
+void nfs_writeback_update_inode(struct nfs_pgio_header *hdr);
 int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
 			    int how, struct nfs_commit_info *cinfo);
 void nfs_retry_commit(struct list_head *page_list,
 		      struct pnfs_layout_segment *lseg,
-		      struct nfs_commit_info *cinfo);
+		      struct nfs_commit_info *cinfo,
+		      u32 ds_commit_idx);
 void nfs_commitdata_release(struct nfs_commit_data *data);
 void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
 				 struct nfs_commit_info *cinfo);
@@ -457,6 +476,7 @@ void nfs_init_cinfo(struct nfs_commit_info *cinfo,
 		    struct nfs_direct_req *dreq);
 int nfs_key_timeout_notify(struct file *filp, struct inode *inode);
 bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx);
+void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio);
 
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,
@@ -480,6 +500,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode)
 	inode_dio_wait(inode);
 }
 extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
+extern void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq);
 
 /* nfs4proc.c */
 extern void __nfs4_read_done_cb(struct nfs_pgio_header *);
@@ -493,6 +514,26 @@ extern int nfs41_walk_client_list(struct nfs_client *clp,
 				struct nfs_client **result,
 				struct rpc_cred *cred);
 
+static inline struct inode *nfs_igrab_and_active(struct inode *inode)
+{
+	inode = igrab(inode);
+	if (inode != NULL && !nfs_sb_active(inode->i_sb)) {
+		iput(inode);
+		inode = NULL;
+	}
+	return inode;
+}
+
+static inline void nfs_iput_and_deactive(struct inode *inode)
+{
+	if (inode != NULL) {
+		struct super_block *sb = inode->i_sb;
+
+		iput(inode);
+		nfs_sb_deactive(sb);
+	}
+}
+
 /*
  * Determine the device name as a string
  */
@@ -558,6 +599,19 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
 }
 
 /*
+ * Record the page as unstable and mark its inode as dirty.
+ */
+static inline
+void nfs_mark_page_unstable(struct page *page)
+{
+	struct inode *inode = page_file_mapping(page)->host;
+
+	inc_zone_page_state(page, NR_UNSTABLE_NFS);
+	inc_bdi_stat(inode_to_bdi(inode), BDI_RECLAIMABLE);
+	 __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+}
+
+/*
  * Determine the number of bytes of data the page contains
  */
 static inline
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 5f61b83f4a1c..b4e03ed8599d 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -481,7 +481,8 @@ out_overflow:
  *		void;
  *	};
  */
-static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result)
+static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result,
+			   __u32 *op_status)
 {
 	enum nfs_stat status;
 	int error;
@@ -489,6 +490,8 @@ static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result)
 	error = decode_stat(xdr, &status);
 	if (unlikely(error))
 		goto out;
+	if (op_status)
+		*op_status = status;
 	if (status != NFS_OK)
 		goto out_default;
 	error = decode_fattr(xdr, result);
@@ -808,7 +811,7 @@ out_default:
 static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr,
 				 struct nfs_fattr *result)
 {
-	return decode_attrstat(xdr, result);
+	return decode_attrstat(xdr, result, NULL);
 }
 
 static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr,
@@ -865,6 +868,7 @@ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr,
 	error = decode_stat(xdr, &status);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS_OK)
 		goto out_default;
 	error = decode_fattr(xdr, result->fattr);
@@ -882,7 +886,7 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr,
 {
 	/* All NFSv2 writes are "file sync" writes */
 	result->verf->committed = NFS_FILE_SYNC;
-	return decode_attrstat(xdr, result->fattr);
+	return decode_attrstat(xdr, result->fattr, &result->op_status);
 }
 
 /**
diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h
index 333ae4068506..e134d6548ab7 100644
--- a/fs/nfs/nfs3_fs.h
+++ b/fs/nfs/nfs3_fs.h
@@ -30,5 +30,7 @@ struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subver
 struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
 				     struct nfs_fattr *, rpc_authflavor_t);
 
+/* nfs3super.c */
+extern struct nfs_subversion nfs_v3;
 
 #endif /* __LINUX_FS_NFS_NFS3_FS_H */
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index 8c1b437c5403..9e9fa347a948 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -1,5 +1,6 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
+#include <linux/sunrpc/addr.h>
 #include "internal.h"
 #include "nfs3_fs.h"
 
@@ -64,3 +65,43 @@ struct nfs_server *nfs3_clone_server(struct nfs_server *source,
 		nfs_init_server_aclclient(server);
 	return server;
 }
+
+/*
+ * Set up a pNFS Data Server client over NFSv3.
+ *
+ * Return any existing nfs_client that matches server address,port,version
+ * and minorversion.
+ *
+ * For a new nfs_client, use a soft mount (default), a low retrans and a
+ * low timeout interval so that if a connection is lost, we retry through
+ * the MDS.
+ */
+struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
+		const struct sockaddr *ds_addr, int ds_addrlen,
+		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
+		rpc_authflavor_t au_flavor)
+{
+	struct nfs_client_initdata cl_init = {
+		.addr = ds_addr,
+		.addrlen = ds_addrlen,
+		.nfs_mod = &nfs_v3,
+		.proto = ds_proto,
+		.net = mds_clp->cl_net,
+	};
+	struct rpc_timeout ds_timeout;
+	struct nfs_client *clp;
+	char buf[INET6_ADDRSTRLEN + 1];
+
+	/* fake a hostname because lockd wants it */
+	if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0)
+		return ERR_PTR(-EINVAL);
+	cl_init.hostname = buf;
+
+	/* Use the MDS nfs_client cl_ipaddr. */
+	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
+	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
+			     au_flavor);
+
+	return clp;
+}
+EXPORT_SYMBOL_GPL(nfs3_set_ds_client);
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 524f9f837408..1f11d2533ee4 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -138,7 +138,7 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	nfs_fattr_init(fattr);
 	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	if (status == 0)
-		nfs_setattr_update_inode(inode, sattr);
+		nfs_setattr_update_inode(inode, sattr, fattr);
 	dprintk("NFS reply setattr: %d\n", status);
 	return status;
 }
@@ -800,6 +800,9 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
 	struct inode *inode = hdr->inode;
 
+	if (hdr->pgio_done_cb != NULL)
+		return hdr->pgio_done_cb(task, hdr);
+
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 
@@ -825,10 +828,13 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
 	struct inode *inode = hdr->inode;
 
+	if (hdr->pgio_done_cb != NULL)
+		return hdr->pgio_done_cb(task, hdr);
+
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(inode, hdr->res.fattr);
+		nfs_writeback_update_inode(hdr);
 	return 0;
 }
 
@@ -845,6 +851,9 @@ static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commi
 
 static int nfs3_commit_done(struct rpc_task *task, struct nfs_commit_data *data)
 {
+	if (data->commit_done_cb != NULL)
+		return data->commit_done_cb(task, data);
+
 	if (nfs3_async_handle_jukebox(task, data->inode))
 		return -EAGAIN;
 	nfs_refresh_inode(data->inode, data->res.fattr);
diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c
index 6af29c2da352..5c4394e4656b 100644
--- a/fs/nfs/nfs3super.c
+++ b/fs/nfs/nfs3super.c
@@ -7,7 +7,7 @@
 #include "nfs3_fs.h"
 #include "nfs.h"
 
-static struct nfs_subversion nfs_v3 = {
+struct nfs_subversion nfs_v3 = {
 	.owner = THIS_MODULE,
 	.nfs_fs   = &nfs_fs_type,
 	.rpc_vers = &nfs_version3,
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 8f4cbe7f4aa8..53852a4bd88b 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1636,6 +1636,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 	error = decode_post_op_attr(xdr, result->fattr);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
 	error = decode_read3resok(xdr, result);
@@ -1708,6 +1709,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 	error = decode_wcc_data(xdr, result->fattr);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
 	error = decode_write3resok(xdr, result);
@@ -1985,6 +1987,11 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		if (entry->fattr->valid & NFS_ATTR_FATTR_V3)
 			entry->d_type = nfs_umode_to_dtype(entry->fattr->mode);
 
+		if (entry->fattr->fileid != entry->ino) {
+			entry->fattr->mounted_on_fileid = entry->ino;
+			entry->fattr->valid |= NFS_ATTR_FATTR_MOUNTED_ON_FILEID;
+		}
+
 		/* In fact, a post_op_fh3: */
 		p = xdr_inline_decode(xdr, 4);
 		if (unlikely(p == NULL))
@@ -2323,6 +2330,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 	error = decode_wcc_data(xdr, result->fattr);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
 	error = decode_writeverf3(xdr, &result->verf->verifier);
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index a08178764cf9..fdef424b0cd3 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -44,6 +44,7 @@ enum nfs4_client_state {
 #define NFS4_RENEW_TIMEOUT		0x01
 #define NFS4_RENEW_DELEGATION_CB	0x02
 
+struct nfs_seqid_counter;
 struct nfs4_minor_version_ops {
 	u32	minor_version;
 	unsigned init_caps;
@@ -56,6 +57,8 @@ struct nfs4_minor_version_ops {
 			struct nfs_fsinfo *);
 	void	(*free_lock_state)(struct nfs_server *,
 			struct nfs4_lock_state *);
+	struct nfs_seqid *
+		(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
 	const struct rpc_call_ops *call_sync_ops;
 	const struct nfs4_state_recovery_ops *reboot_recovery_ops;
 	const struct nfs4_state_recovery_ops *nograce_recovery_ops;
@@ -443,6 +446,12 @@ extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_release_seqid(struct nfs_seqid *seqid);
 extern void nfs_free_seqid(struct nfs_seqid *seqid);
+extern int nfs40_setup_sequence(struct nfs4_slot_table *tbl,
+				struct nfs4_sequence_args *args,
+				struct nfs4_sequence_res *res,
+				struct rpc_task *task);
+extern int nfs4_sequence_done(struct rpc_task *task,
+			      struct nfs4_sequence_res *res);
 
 extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp);
 
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 706ad10b8186..86d6214ea022 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -621,6 +621,9 @@ int nfs41_walk_client_list(struct nfs_client *new,
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
 
+		if (pos == new)
+			goto found;
+
 		if (pos->rpc_ops != new->rpc_ops)
 			continue;
 
@@ -639,10 +642,6 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			prev = pos;
 
 			status = nfs_wait_client_init_complete(pos);
-			if (pos->cl_cons_state == NFS_CS_SESSION_INITING) {
-				nfs4_schedule_lease_recovery(pos);
-				status = nfs4_wait_clnt_recover(pos);
-			}
 			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
 				break;
@@ -668,7 +667,7 @@ int nfs41_walk_client_list(struct nfs_client *new,
 		 */
 		if (!nfs4_match_client_owner_id(pos, new))
 			continue;
-
+found:
 		atomic_inc(&pos->cl_count);
 		*result = pos;
 		status = 0;
@@ -849,14 +848,15 @@ error:
  */
 struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 		const struct sockaddr *ds_addr, int ds_addrlen,
-		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
+		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
+		u32 minor_version, rpc_authflavor_t au_flavor)
 {
 	struct nfs_client_initdata cl_init = {
 		.addr = ds_addr,
 		.addrlen = ds_addrlen,
 		.nfs_mod = &nfs_v4,
 		.proto = ds_proto,
-		.minorversion = mds_clp->cl_minorversion,
+		.minorversion = minor_version,
 		.net = mds_clp->cl_net,
 	};
 	struct rpc_timeout ds_timeout;
@@ -874,7 +874,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 	 */
 	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
 	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
-			     mds_clp->cl_rpcclient->cl_auth->au_flavor);
+			     au_flavor);
 
 	dprintk("<-- %s %p\n", __func__, clp);
 	return clp;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c347705b0161..627f37c44456 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -495,12 +495,11 @@ static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args)
 	args->sa_privileged = 1;
 }
 
-static int nfs40_setup_sequence(const struct nfs_server *server,
-				struct nfs4_sequence_args *args,
-				struct nfs4_sequence_res *res,
-				struct rpc_task *task)
+int nfs40_setup_sequence(struct nfs4_slot_table *tbl,
+			 struct nfs4_sequence_args *args,
+			 struct nfs4_sequence_res *res,
+			 struct rpc_task *task)
 {
-	struct nfs4_slot_table *tbl = server->nfs_client->cl_slot_tbl;
 	struct nfs4_slot *slot;
 
 	/* slot already allocated? */
@@ -535,6 +534,7 @@ out_sleep:
 	spin_unlock(&tbl->slot_tbl_lock);
 	return -EAGAIN;
 }
+EXPORT_SYMBOL_GPL(nfs40_setup_sequence);
 
 static int nfs40_sequence_done(struct rpc_task *task,
 			       struct nfs4_sequence_res *res)
@@ -694,8 +694,7 @@ out_retry:
 }
 EXPORT_SYMBOL_GPL(nfs41_sequence_done);
 
-static int nfs4_sequence_done(struct rpc_task *task,
-			       struct nfs4_sequence_res *res)
+int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
 	if (res->sr_slot == NULL)
 		return 1;
@@ -703,6 +702,7 @@ static int nfs4_sequence_done(struct rpc_task *task,
 		return nfs40_sequence_done(task, res);
 	return nfs41_sequence_done(task, res);
 }
+EXPORT_SYMBOL_GPL(nfs4_sequence_done);
 
 int nfs41_setup_sequence(struct nfs4_session *session,
 				struct nfs4_sequence_args *args,
@@ -777,7 +777,8 @@ static int nfs4_setup_sequence(const struct nfs_server *server,
 	int ret = 0;
 
 	if (!session)
-		return nfs40_setup_sequence(server, args, res, task);
+		return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
+					    args, res, task);
 
 	dprintk("--> %s clp %p session %p sr_slot %u\n",
 		__func__, session->clp, session, res->sr_slot ?
@@ -818,14 +819,16 @@ static int nfs4_setup_sequence(const struct nfs_server *server,
 			       struct nfs4_sequence_res *res,
 			       struct rpc_task *task)
 {
-	return nfs40_setup_sequence(server, args, res, task);
+	return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
+				    args, res, task);
 }
 
-static int nfs4_sequence_done(struct rpc_task *task,
-			       struct nfs4_sequence_res *res)
+int nfs4_sequence_done(struct rpc_task *task,
+		       struct nfs4_sequence_res *res)
 {
 	return nfs40_sequence_done(task, res);
 }
+EXPORT_SYMBOL_GPL(nfs4_sequence_done);
 
 #endif	/* !CONFIG_NFS_V4_1 */
 
@@ -898,6 +901,7 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
 	if (!cinfo->atomic || cinfo->before != dir->i_version)
 		nfs_force_lookup_revalidate(dir);
 	dir->i_version = cinfo->after;
+	nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	nfs_fscache_invalidate(dir);
 	spin_unlock(&dir->i_lock);
 }
@@ -937,6 +941,31 @@ static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server,
 	return true;
 }
 
+static u32
+nfs4_map_atomic_open_share(struct nfs_server *server,
+		fmode_t fmode, int openflags)
+{
+	u32 res = 0;
+
+	switch (fmode & (FMODE_READ | FMODE_WRITE)) {
+	case FMODE_READ:
+		res = NFS4_SHARE_ACCESS_READ;
+		break;
+	case FMODE_WRITE:
+		res = NFS4_SHARE_ACCESS_WRITE;
+		break;
+	case FMODE_READ|FMODE_WRITE:
+		res = NFS4_SHARE_ACCESS_BOTH;
+	}
+	if (!(server->caps & NFS_CAP_ATOMIC_OPEN_V1))
+		goto out;
+	/* Want no delegation if we're using O_DIRECT */
+	if (openflags & O_DIRECT)
+		res |= NFS4_SHARE_WANT_NO_DELEG;
+out:
+	return res;
+}
+
 static enum open_claim_type4
 nfs4_map_atomic_open_claim(struct nfs_server *server,
 		enum open_claim_type4 claim)
@@ -977,6 +1006,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	struct dentry *parent = dget_parent(dentry);
 	struct inode *dir = parent->d_inode;
 	struct nfs_server *server = NFS_SERVER(dir);
+	struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
 	struct nfs4_opendata *p;
 
 	p = kzalloc(sizeof(*p), gfp_mask);
@@ -987,8 +1017,9 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	if (IS_ERR(p->f_label))
 		goto err_free_p;
 
-	p->o_arg.seqid = nfs_alloc_seqid(&sp->so_seqid, gfp_mask);
-	if (p->o_arg.seqid == NULL)
+	alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid;
+	p->o_arg.seqid = alloc_seqid(&sp->so_seqid, gfp_mask);
+	if (IS_ERR(p->o_arg.seqid))
 		goto err_free_label;
 	nfs_sb_active(dentry->d_sb);
 	p->dentry = dget(dentry);
@@ -997,6 +1028,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	atomic_inc(&sp->so_count);
 	p->o_arg.open_flags = flags;
 	p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE);
+	p->o_arg.share_access = nfs4_map_atomic_open_share(server,
+			fmode, flags);
 	/* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS
 	 * will return permission denied for all bits until close */
 	if (!(flags & O_EXCL)) {
@@ -1167,6 +1200,16 @@ static bool nfs_need_update_open_stateid(struct nfs4_state *state,
 	return false;
 }
 
+static void nfs_resync_open_stateid_locked(struct nfs4_state *state)
+{
+	if (state->n_wronly)
+		set_bit(NFS_O_WRONLY_STATE, &state->flags);
+	if (state->n_rdonly)
+		set_bit(NFS_O_RDONLY_STATE, &state->flags);
+	if (state->n_rdwr)
+		set_bit(NFS_O_RDWR_STATE, &state->flags);
+}
+
 static void nfs_clear_open_stateid_locked(struct nfs4_state *state,
 		nfs4_stateid *stateid, fmode_t fmode)
 {
@@ -1185,8 +1228,12 @@ static void nfs_clear_open_stateid_locked(struct nfs4_state *state,
 	}
 	if (stateid == NULL)
 		return;
-	if (!nfs_need_update_open_stateid(state, stateid))
+	/* Handle races with OPEN */
+	if (!nfs4_stateid_match_other(stateid, &state->open_stateid) ||
+	    !nfs4_stateid_is_newer(stateid, &state->open_stateid)) {
+		nfs_resync_open_stateid_locked(state);
 		return;
+	}
 	if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
 		nfs4_stateid_copy(&state->stateid, stateid);
 	nfs4_stateid_copy(&state->open_stateid, stateid);
@@ -1281,6 +1328,23 @@ no_delegation:
 	return ret;
 }
 
+static bool nfs4_update_lock_stateid(struct nfs4_lock_state *lsp,
+		const nfs4_stateid *stateid)
+{
+	struct nfs4_state *state = lsp->ls_state;
+	bool ret = false;
+
+	spin_lock(&state->state_lock);
+	if (!nfs4_stateid_match_other(stateid, &lsp->ls_stateid))
+		goto out_noupdate;
+	if (!nfs4_stateid_is_newer(stateid, &lsp->ls_stateid))
+		goto out_noupdate;
+	nfs4_stateid_copy(&lsp->ls_stateid, stateid);
+	ret = true;
+out_noupdate:
+	spin_unlock(&state->state_lock);
+	return ret;
+}
 
 static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmode)
 {
@@ -1489,6 +1553,9 @@ static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmod
 
 	opendata->o_arg.open_flags = 0;
 	opendata->o_arg.fmode = fmode;
+	opendata->o_arg.share_access = nfs4_map_atomic_open_share(
+			NFS_SB(opendata->dentry->d_sb),
+			fmode, 0);
 	memset(&opendata->o_res, 0, sizeof(opendata->o_res));
 	memset(&opendata->c_res, 0, sizeof(opendata->c_res));
 	nfs4_init_opendata_res(opendata);
@@ -1679,8 +1746,8 @@ static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_opendata *data = calldata;
 
-	nfs40_setup_sequence(data->o_arg.server, &data->c_arg.seq_args,
-				&data->c_res.seq_res, task);
+	nfs40_setup_sequence(data->o_arg.server->nfs_client->cl_slot_tbl,
+			     &data->c_arg.seq_args, &data->c_res.seq_res, task);
 }
 
 static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
@@ -2350,8 +2417,8 @@ static int _nfs4_do_open(struct inode *dir,
 				opendata->o_res.f_attr, sattr,
 				state, label, olabel);
 		if (status == 0) {
-			nfs_setattr_update_inode(state->inode, sattr);
-			nfs_post_op_update_inode(state->inode, opendata->o_res.f_attr);
+			nfs_setattr_update_inode(state->inode, sattr,
+					opendata->o_res.f_attr);
 			nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel);
 		}
 	}
@@ -2587,6 +2654,11 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 		case -NFS4ERR_OLD_STATEID:
 		case -NFS4ERR_BAD_STATEID:
 		case -NFS4ERR_EXPIRED:
+			if (!nfs4_stateid_match(&calldata->arg.stateid,
+						&state->open_stateid)) {
+				rpc_restart_call_prepare(task);
+				goto out_release;
+			}
 			if (calldata->arg.fmode == 0)
 				break;
 		default:
@@ -2619,6 +2691,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
 	is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
 	is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
+	nfs4_stateid_copy(&calldata->arg.stateid, &state->open_stateid);
 	/* Calculate the change in open mode */
 	calldata->arg.fmode = 0;
 	if (state->n_rdwr == 0) {
@@ -2653,6 +2726,9 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 			goto out_wait;
 		    }
 	}
+	calldata->arg.share_access =
+		nfs4_map_atomic_open_share(NFS_SERVER(inode),
+				calldata->arg.fmode, 0);
 
 	nfs_fattr_init(calldata->res.fattr);
 	calldata->timestamp = jiffies;
@@ -2675,45 +2751,10 @@ static const struct rpc_call_ops nfs4_close_ops = {
 	.rpc_release = nfs4_free_closedata,
 };
 
-static bool nfs4_state_has_opener(struct nfs4_state *state)
-{
-	/* first check existing openers */
-	if (test_bit(NFS_O_RDONLY_STATE, &state->flags) != 0 &&
-	    state->n_rdonly != 0)
-		return true;
-
-	if (test_bit(NFS_O_WRONLY_STATE, &state->flags) != 0 &&
-	    state->n_wronly != 0)
-		return true;
-
-	if (test_bit(NFS_O_RDWR_STATE, &state->flags) != 0 &&
-	    state->n_rdwr != 0)
-		return true;
-
-	return false;
-}
-
 static bool nfs4_roc(struct inode *inode)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
-	struct nfs_open_context *ctx;
-	struct nfs4_state *state;
-
-	spin_lock(&inode->i_lock);
-	list_for_each_entry(ctx, &nfsi->open_files, list) {
-		state = ctx->state;
-		if (state == NULL)
-			continue;
-		if (nfs4_state_has_opener(state)) {
-			spin_unlock(&inode->i_lock);
-			return false;
-		}
-	}
-	spin_unlock(&inode->i_lock);
-
-	if (nfs4_check_delegation(inode, FMODE_READ))
+	if (!nfs_have_layout(inode))
 		return false;
-
 	return pnfs_roc(inode);
 }
 
@@ -2731,6 +2772,7 @@ static bool nfs4_roc(struct inode *inode)
 int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
+	struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
 	struct nfs4_closedata *calldata;
 	struct nfs4_state_owner *sp = state->owner;
 	struct rpc_task *task;
@@ -2757,10 +2799,10 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait)
 	calldata->inode = state->inode;
 	calldata->state = state;
 	calldata->arg.fh = NFS_FH(state->inode);
-	calldata->arg.stateid = &state->open_stateid;
 	/* Serialization for the sequence id */
-	calldata->arg.seqid = nfs_alloc_seqid(&state->owner->so_seqid, gfp_mask);
-	if (calldata->arg.seqid == NULL)
+	alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid;
+	calldata->arg.seqid = alloc_seqid(&state->owner->so_seqid, gfp_mask);
+	if (IS_ERR(calldata->arg.seqid))
 		goto out_free_calldata;
 	calldata->arg.fmode = 0;
 	calldata->arg.bitmask = server->cache_consistency_bitmask;
@@ -3250,7 +3292,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 
 	status = nfs4_do_setattr(inode, cred, fattr, sattr, state, NULL, label);
 	if (status == 0) {
-		nfs_setattr_update_inode(inode, sattr);
+		nfs_setattr_update_inode(inode, sattr, fattr);
 		nfs_setsecurity(inode, fattr, label);
 	}
 	nfs4_label_free(label);
@@ -4196,7 +4238,7 @@ static int nfs4_write_done_cb(struct rpc_task *task,
 	}
 	if (task->tk_status >= 0) {
 		renew_lease(NFS_SERVER(inode), hdr->timestamp);
-		nfs_post_op_update_inode_force_wcc(inode, &hdr->fattr);
+		nfs_writeback_update_inode(hdr);
 	}
 	return 0;
 }
@@ -5137,9 +5179,13 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 static void nfs4_delegreturn_release(void *calldata)
 {
 	struct nfs4_delegreturndata *data = calldata;
+	struct inode *inode = data->inode;
 
-	if (data->roc)
-		pnfs_roc_release(data->inode);
+	if (inode) {
+		if (data->roc)
+			pnfs_roc_release(inode);
+		nfs_iput_and_deactive(inode);
+	}
 	kfree(calldata);
 }
 
@@ -5196,9 +5242,9 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 	nfs_fattr_init(data->res.fattr);
 	data->timestamp = jiffies;
 	data->rpc_status = 0;
-	data->inode = inode;
-	data->roc = list_empty(&NFS_I(inode)->open_files) ?
-		    pnfs_roc(inode) : false;
+	data->inode = nfs_igrab_and_active(inode);
+	if (data->inode)
+		data->roc = nfs4_roc(inode);
 
 	task_setup_data.callback_data = data;
 	msg.rpc_argp = &data->args;
@@ -5353,7 +5399,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	p->arg.fl = &p->fl;
 	p->arg.seqid = seqid;
 	p->res.seqid = seqid;
-	p->arg.stateid = &lsp->ls_stateid;
 	p->lsp = lsp;
 	atomic_inc(&lsp->ls_count);
 	/* Ensure we don't close file until we're done freeing locks! */
@@ -5380,14 +5425,18 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 		return;
 	switch (task->tk_status) {
 		case 0:
-			nfs4_stateid_copy(&calldata->lsp->ls_stateid,
-					&calldata->res.stateid);
 			renew_lease(calldata->server, calldata->timestamp);
-			break;
+			do_vfs_lock(calldata->fl.fl_file, &calldata->fl);
+			if (nfs4_update_lock_stateid(calldata->lsp,
+					&calldata->res.stateid))
+				break;
 		case -NFS4ERR_BAD_STATEID:
 		case -NFS4ERR_OLD_STATEID:
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_EXPIRED:
+			if (!nfs4_stateid_match(&calldata->arg.stateid,
+						&calldata->lsp->ls_stateid))
+				rpc_restart_call_prepare(task);
 			break;
 		default:
 			if (nfs4_async_handle_error(task, calldata->server,
@@ -5403,6 +5452,7 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
 
 	if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
 		goto out_wait;
+	nfs4_stateid_copy(&calldata->arg.stateid, &calldata->lsp->ls_stateid);
 	if (test_bit(NFS_LOCK_INITIALIZED, &calldata->lsp->ls_flags) == 0) {
 		/* Note: exit _without_ running nfs4_locku_done */
 		goto out_no_action;
@@ -5473,6 +5523,7 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *
 	struct nfs_seqid *seqid;
 	struct nfs4_lock_state *lsp;
 	struct rpc_task *task;
+	struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
 	int status = 0;
 	unsigned char fl_flags = request->fl_flags;
 
@@ -5496,9 +5547,10 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *
 	lsp = request->fl_u.nfs4_fl.owner;
 	if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) == 0)
 		goto out;
-	seqid = nfs_alloc_seqid(&lsp->ls_seqid, GFP_KERNEL);
+	alloc_seqid = NFS_SERVER(inode)->nfs_client->cl_mvops->alloc_seqid;
+	seqid = alloc_seqid(&lsp->ls_seqid, GFP_KERNEL);
 	status = -ENOMEM;
-	if (seqid == NULL)
+	if (IS_ERR(seqid))
 		goto out;
 	task = nfs4_do_unlck(request, nfs_file_open_context(request->fl_file), lsp, seqid);
 	status = PTR_ERR(task);
@@ -5531,6 +5583,7 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	struct nfs4_lockdata *p;
 	struct inode *inode = lsp->ls_state->inode;
 	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
 
 	p = kzalloc(sizeof(*p), gfp_mask);
 	if (p == NULL)
@@ -5539,12 +5592,12 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	p->arg.fh = NFS_FH(inode);
 	p->arg.fl = &p->fl;
 	p->arg.open_seqid = nfs_alloc_seqid(&lsp->ls_state->owner->so_seqid, gfp_mask);
-	if (p->arg.open_seqid == NULL)
+	if (IS_ERR(p->arg.open_seqid))
 		goto out_free;
-	p->arg.lock_seqid = nfs_alloc_seqid(&lsp->ls_seqid, gfp_mask);
-	if (p->arg.lock_seqid == NULL)
+	alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid;
+	p->arg.lock_seqid = alloc_seqid(&lsp->ls_seqid, gfp_mask);
+	if (IS_ERR(p->arg.lock_seqid))
 		goto out_free_seqid;
-	p->arg.lock_stateid = &lsp->ls_stateid;
 	p->arg.lock_owner.clientid = server->nfs_client->cl_clientid;
 	p->arg.lock_owner.id = lsp->ls_seqid.owner_id;
 	p->arg.lock_owner.s_dev = server->s_dev;
@@ -5571,15 +5624,19 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
 	if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0)
 		goto out_wait;
 	/* Do we need to do an open_to_lock_owner? */
-	if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) {
+	if (!test_bit(NFS_LOCK_INITIALIZED, &data->lsp->ls_flags)) {
 		if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) {
 			goto out_release_lock_seqid;
 		}
-		data->arg.open_stateid = &state->open_stateid;
+		nfs4_stateid_copy(&data->arg.open_stateid,
+				&state->open_stateid);
 		data->arg.new_lock_owner = 1;
 		data->res.open_seqid = data->arg.open_seqid;
-	} else
+	} else {
 		data->arg.new_lock_owner = 0;
+		nfs4_stateid_copy(&data->arg.lock_stateid,
+				&data->lsp->ls_stateid);
+	}
 	if (!nfs4_valid_open_stateid(state)) {
 		data->rpc_status = -EBADF;
 		task->tk_action = NULL;
@@ -5603,6 +5660,7 @@ out_wait:
 static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_lockdata *data = calldata;
+	struct nfs4_lock_state *lsp = data->lsp;
 
 	dprintk("%s: begin!\n", __func__);
 
@@ -5610,18 +5668,36 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 		return;
 
 	data->rpc_status = task->tk_status;
-	if (data->arg.new_lock_owner != 0) {
-		if (data->rpc_status == 0)
-			nfs_confirm_seqid(&data->lsp->ls_seqid, 0);
-		else
-			goto out;
-	}
-	if (data->rpc_status == 0) {
-		nfs4_stateid_copy(&data->lsp->ls_stateid, &data->res.stateid);
-		set_bit(NFS_LOCK_INITIALIZED, &data->lsp->ls_flags);
-		renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), data->timestamp);
+	switch (task->tk_status) {
+	case 0:
+		renew_lease(NFS_SERVER(data->ctx->dentry->d_inode),
+				data->timestamp);
+		if (data->arg.new_lock) {
+			data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS);
+			if (do_vfs_lock(data->fl.fl_file, &data->fl) < 0) {
+				rpc_restart_call_prepare(task);
+				break;
+			}
+		}
+		if (data->arg.new_lock_owner != 0) {
+			nfs_confirm_seqid(&lsp->ls_seqid, 0);
+			nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid);
+			set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags);
+		} else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid))
+			rpc_restart_call_prepare(task);
+		break;
+	case -NFS4ERR_BAD_STATEID:
+	case -NFS4ERR_OLD_STATEID:
+	case -NFS4ERR_STALE_STATEID:
+	case -NFS4ERR_EXPIRED:
+		if (data->arg.new_lock_owner != 0) {
+			if (!nfs4_stateid_match(&data->arg.open_stateid,
+						&lsp->ls_state->open_stateid))
+				rpc_restart_call_prepare(task);
+		} else if (!nfs4_stateid_match(&data->arg.lock_stateid,
+						&lsp->ls_stateid))
+				rpc_restart_call_prepare(task);
 	}
-out:
 	dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status);
 }
 
@@ -5702,7 +5778,8 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 		if (recovery_type == NFS_LOCK_RECLAIM)
 			data->arg.reclaim = NFS_LOCK_RECLAIM;
 		nfs4_set_sequence_privileged(&data->arg.seq_args);
-	}
+	} else
+		data->arg.new_lock = 1;
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
@@ -5826,10 +5903,8 @@ static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *reques
 
 static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 {
-	struct nfs4_state_owner *sp = state->owner;
 	struct nfs_inode *nfsi = NFS_I(state->inode);
 	unsigned char fl_flags = request->fl_flags;
-	unsigned int seq;
 	int status = -ENOLCK;
 
 	if ((fl_flags & FL_POSIX) &&
@@ -5849,25 +5924,11 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
 		/* ...but avoid races with delegation recall... */
 		request->fl_flags = fl_flags & ~FL_SLEEP;
 		status = do_vfs_lock(request->fl_file, request);
-		goto out_unlock;
-	}
-	seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
-	up_read(&nfsi->rwsem);
-	status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW);
-	if (status != 0)
+		up_read(&nfsi->rwsem);
 		goto out;
-	down_read(&nfsi->rwsem);
-	if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) {
-		status = -NFS4ERR_DELAY;
-		goto out_unlock;
 	}
-	/* Note: we always want to sleep here! */
-	request->fl_flags = fl_flags | FL_SLEEP;
-	if (do_vfs_lock(request->fl_file, request) < 0)
-		printk(KERN_WARNING "NFS: %s: VFS is out of sync with lock "
-			"manager!\n", __func__);
-out_unlock:
 	up_read(&nfsi->rwsem);
+	status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW);
 out:
 	request->fl_flags = fl_flags;
 	return status;
@@ -5974,8 +6035,8 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata
 {
 	struct nfs_release_lockowner_data *data = calldata;
 	struct nfs_server *server = data->server;
-	nfs40_setup_sequence(server, &data->args.seq_args,
-				&data->res.seq_res, task);
+	nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
+			     &data->args.seq_args, &data->res.seq_res, task);
 	data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
 	data->timestamp = jiffies;
 }
@@ -6591,47 +6652,47 @@ nfs41_same_server_scope(struct nfs41_server_scope *a,
 int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	int status;
+	struct nfs41_bind_conn_to_session_args args = {
+		.client = clp,
+		.dir = NFS4_CDFC4_FORE_OR_BOTH,
+	};
 	struct nfs41_bind_conn_to_session_res res;
 	struct rpc_message msg = {
 		.rpc_proc =
 			&nfs4_procedures[NFSPROC4_CLNT_BIND_CONN_TO_SESSION],
-		.rpc_argp = clp,
+		.rpc_argp = &args,
 		.rpc_resp = &res,
 		.rpc_cred = cred,
 	};
 
 	dprintk("--> %s\n", __func__);
 
-	res.session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS);
-	if (unlikely(res.session == NULL)) {
-		status = -ENOMEM;
-		goto out;
-	}
+	nfs4_copy_sessionid(&args.sessionid, &clp->cl_session->sess_id);
+	if (!(clp->cl_session->flags & SESSION4_BACK_CHAN))
+		args.dir = NFS4_CDFC4_FORE;
 
 	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	trace_nfs4_bind_conn_to_session(clp, status);
 	if (status == 0) {
-		if (memcmp(res.session->sess_id.data,
+		if (memcmp(res.sessionid.data,
 		    clp->cl_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) {
 			dprintk("NFS: %s: Session ID mismatch\n", __func__);
 			status = -EIO;
-			goto out_session;
+			goto out;
 		}
-		if (res.dir != NFS4_CDFS4_BOTH) {
+		if ((res.dir & args.dir) != res.dir || res.dir == 0) {
 			dprintk("NFS: %s: Unexpected direction from server\n",
 				__func__);
 			status = -EIO;
-			goto out_session;
+			goto out;
 		}
-		if (res.use_conn_in_rdma_mode) {
+		if (res.use_conn_in_rdma_mode != args.use_conn_in_rdma_mode) {
 			dprintk("NFS: %s: Server returned RDMA mode = true\n",
 				__func__);
 			status = -EIO;
-			goto out_session;
+			goto out;
 		}
 	}
-out_session:
-	kfree(res.session);
 out:
 	dprintk("<-- %s status= %d\n", __func__, status);
 	return status;
@@ -6836,9 +6897,13 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 
 	if (status == 0) {
 		clp->cl_clientid = res.clientid;
-		clp->cl_exchange_flags = (res.flags & ~EXCHGID4_FLAG_CONFIRMED_R);
-		if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R))
+		clp->cl_exchange_flags = res.flags;
+		/* Client ID is not confirmed */
+		if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R)) {
+			clear_bit(NFS4_SESSION_ESTABLISHED,
+					&clp->cl_session->session_state);
 			clp->cl_seqid = res.seqid;
+		}
 
 		kfree(clp->cl_serverowner);
 		clp->cl_serverowner = res.server_owner;
@@ -7109,10 +7174,11 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
 		args->bc_attrs.max_reqs);
 }
 
-static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args, struct nfs4_session *session)
+static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args,
+		struct nfs41_create_session_res *res)
 {
 	struct nfs4_channel_attrs *sent = &args->fc_attrs;
-	struct nfs4_channel_attrs *rcvd = &session->fc_attrs;
+	struct nfs4_channel_attrs *rcvd = &res->fc_attrs;
 
 	if (rcvd->max_resp_sz > sent->max_resp_sz)
 		return -EINVAL;
@@ -7131,11 +7197,14 @@ static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args
 	return 0;
 }
 
-static int nfs4_verify_back_channel_attrs(struct nfs41_create_session_args *args, struct nfs4_session *session)
+static int nfs4_verify_back_channel_attrs(struct nfs41_create_session_args *args,
+		struct nfs41_create_session_res *res)
 {
 	struct nfs4_channel_attrs *sent = &args->bc_attrs;
-	struct nfs4_channel_attrs *rcvd = &session->bc_attrs;
+	struct nfs4_channel_attrs *rcvd = &res->bc_attrs;
 
+	if (!(res->flags & SESSION4_BACK_CHAN))
+		goto out;
 	if (rcvd->max_rqst_sz > sent->max_rqst_sz)
 		return -EINVAL;
 	if (rcvd->max_resp_sz < sent->max_resp_sz)
@@ -7147,18 +7216,33 @@ static int nfs4_verify_back_channel_attrs(struct nfs41_create_session_args *args
 		return -EINVAL;
 	if (rcvd->max_reqs != sent->max_reqs)
 		return -EINVAL;
+out:
 	return 0;
 }
 
 static int nfs4_verify_channel_attrs(struct nfs41_create_session_args *args,
-				     struct nfs4_session *session)
+				     struct nfs41_create_session_res *res)
 {
 	int ret;
 
-	ret = nfs4_verify_fore_channel_attrs(args, session);
+	ret = nfs4_verify_fore_channel_attrs(args, res);
 	if (ret)
 		return ret;
-	return nfs4_verify_back_channel_attrs(args, session);
+	return nfs4_verify_back_channel_attrs(args, res);
+}
+
+static void nfs4_update_session(struct nfs4_session *session,
+		struct nfs41_create_session_res *res)
+{
+	nfs4_copy_sessionid(&session->sess_id, &res->sessionid);
+	/* Mark client id and session as being confirmed */
+	session->clp->cl_exchange_flags |= EXCHGID4_FLAG_CONFIRMED_R;
+	set_bit(NFS4_SESSION_ESTABLISHED, &session->session_state);
+	session->flags = res->flags;
+	memcpy(&session->fc_attrs, &res->fc_attrs, sizeof(session->fc_attrs));
+	if (res->flags & SESSION4_BACK_CHAN)
+		memcpy(&session->bc_attrs, &res->bc_attrs,
+				sizeof(session->bc_attrs));
 }
 
 static int _nfs4_proc_create_session(struct nfs_client *clp,
@@ -7167,11 +7251,12 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
 	struct nfs4_session *session = clp->cl_session;
 	struct nfs41_create_session_args args = {
 		.client = clp,
+		.clientid = clp->cl_clientid,
+		.seqid = clp->cl_seqid,
 		.cb_program = NFS4_CALLBACK,
 	};
-	struct nfs41_create_session_res res = {
-		.client = clp,
-	};
+	struct nfs41_create_session_res res;
+
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE_SESSION],
 		.rpc_argp = &args,
@@ -7188,11 +7273,15 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
 
 	if (!status) {
 		/* Verify the session's negotiated channel_attrs values */
-		status = nfs4_verify_channel_attrs(&args, session);
+		status = nfs4_verify_channel_attrs(&args, &res);
 		/* Increment the clientid slot sequence id */
-		clp->cl_seqid++;
+		if (clp->cl_seqid == res.seqid)
+			clp->cl_seqid++;
+		if (status)
+			goto out;
+		nfs4_update_session(session, &res);
 	}
-
+out:
 	return status;
 }
 
@@ -7244,8 +7333,8 @@ int nfs4_proc_destroy_session(struct nfs4_session *session,
 	dprintk("--> nfs4_proc_destroy_session\n");
 
 	/* session is still being setup */
-	if (session->clp->cl_cons_state != NFS_CS_READY)
-		return status;
+	if (!test_and_clear_bit(NFS4_SESSION_ESTABLISHED, &session->session_state))
+		return 0;
 
 	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	trace_nfs4_destroy_session(session->clp, status);
@@ -7537,6 +7626,7 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 		return;
 	if (pnfs_choose_layoutget_stateid(&lgp->args.stateid,
 					  NFS_I(lgp->args.inode)->layout,
+					  &lgp->args.range,
 					  lgp->args.ctx->state)) {
 		rpc_exit(task, NFS4_OK);
 	}
@@ -7792,9 +7882,13 @@ static void nfs4_layoutreturn_release(void *calldata)
 	spin_lock(&lo->plh_inode->i_lock);
 	if (lrp->res.lrs_present)
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+	pnfs_clear_layoutreturn_waitbit(lo);
+	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
+	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 	lo->plh_block_lgets--;
 	spin_unlock(&lo->plh_inode->i_lock);
 	pnfs_put_layout_hdr(lrp->args.layout);
+	nfs_iput_and_deactive(lrp->inode);
 	kfree(calldata);
 	dprintk("<-- %s\n", __func__);
 }
@@ -7805,7 +7899,7 @@ static const struct rpc_call_ops nfs4_layoutreturn_call_ops = {
 	.rpc_release = nfs4_layoutreturn_release,
 };
 
-int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
+int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync)
 {
 	struct rpc_task *task;
 	struct rpc_message msg = {
@@ -7820,14 +7914,23 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
 		.callback_ops = &nfs4_layoutreturn_call_ops,
 		.callback_data = lrp,
 	};
-	int status;
+	int status = 0;
 
 	dprintk("--> %s\n", __func__);
+	if (!sync) {
+		lrp->inode = nfs_igrab_and_active(lrp->args.inode);
+		if (!lrp->inode) {
+			nfs4_layoutreturn_release(lrp);
+			return -EAGAIN;
+		}
+		task_setup_data.flags |= RPC_TASK_ASYNC;
+	}
 	nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1);
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
-	status = task->tk_status;
+	if (sync)
+		status = task->tk_status;
 	trace_nfs4_layoutreturn(lrp->args.inode, status);
 	dprintk("<-- %s status=%d\n", __func__, status);
 	rpc_put_task(task);
@@ -7921,6 +8024,7 @@ static void nfs4_layoutcommit_release(void *calldata)
 	nfs_post_op_update_inode_force_wcc(data->args.inode,
 					   data->res.fattr);
 	put_rpccred(data->cred);
+	nfs_iput_and_deactive(data->inode);
 	kfree(data);
 }
 
@@ -7945,7 +8049,6 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync)
 		.rpc_message = &msg,
 		.callback_ops = &nfs4_layoutcommit_ops,
 		.callback_data = data,
-		.flags = RPC_TASK_ASYNC,
 	};
 	struct rpc_task *task;
 	int status = 0;
@@ -7956,18 +8059,21 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync)
 		data->args.lastbytewritten,
 		data->args.inode->i_ino);
 
+	if (!sync) {
+		data->inode = nfs_igrab_and_active(data->args.inode);
+		if (data->inode == NULL) {
+			nfs4_layoutcommit_release(data);
+			return -EAGAIN;
+		}
+		task_setup_data.flags = RPC_TASK_ASYNC;
+	}
 	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
-	if (sync == false)
-		goto out;
-	status = nfs4_wait_for_completion_rpc_task(task);
-	if (status != 0)
-		goto out;
-	status = task->tk_status;
+	if (sync)
+		status = task->tk_status;
 	trace_nfs4_layoutcommit(data->args.inode, status);
-out:
 	dprintk("%s: status %d\n", __func__, status);
 	rpc_put_task(task);
 	return status;
@@ -8395,6 +8501,7 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
 	.match_stateid = nfs4_match_stateid,
 	.find_root_sec = nfs4_find_root_sec,
 	.free_lock_state = nfs4_release_lockowner,
+	.alloc_seqid = nfs_alloc_seqid,
 	.call_sync_ops = &nfs40_call_sync_ops,
 	.reboot_recovery_ops = &nfs40_reboot_recovery_ops,
 	.nograce_recovery_ops = &nfs40_nograce_recovery_ops,
@@ -8403,6 +8510,12 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
 };
 
 #if defined(CONFIG_NFS_V4_1)
+static struct nfs_seqid *
+nfs_alloc_no_seqid(struct nfs_seqid_counter *arg1, gfp_t arg2)
+{
+	return NULL;
+}
+
 static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 	.minor_version = 1,
 	.init_caps = NFS_CAP_READDIRPLUS
@@ -8416,6 +8529,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 	.match_stateid = nfs41_match_stateid,
 	.find_root_sec = nfs41_find_root_sec,
 	.free_lock_state = nfs41_free_lock_state,
+	.alloc_seqid = nfs_alloc_no_seqid,
 	.call_sync_ops = &nfs41_call_sync_ops,
 	.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
 	.nograce_recovery_ops = &nfs41_nograce_recovery_ops,
@@ -8442,6 +8556,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 	.find_root_sec = nfs41_find_root_sec,
 	.free_lock_state = nfs41_free_lock_state,
 	.call_sync_ops = &nfs41_call_sync_ops,
+	.alloc_seqid = nfs_alloc_no_seqid,
 	.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
 	.nograce_recovery_ops = &nfs41_nograce_recovery_ops,
 	.state_renewal_ops = &nfs41_state_renewal_ops,
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index e799dc3c3b1d..e23366effcfb 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -450,7 +450,7 @@ int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
 	tbl = &ses->fc_slot_table;
 	tbl->session = ses;
 	status = nfs4_realloc_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
-	if (status) /* -ENOMEM */
+	if (status || !(ses->flags & SESSION4_BACK_CHAN)) /* -ENOMEM */
 		return status;
 	/* Back channel */
 	tbl = &ses->bc_slot_table;
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index b34ada9bc6a2..e3ea2c5324d6 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -70,6 +70,7 @@ struct nfs4_session {
 
 enum nfs4_session_state {
 	NFS4_SESSION_INITING,
+	NFS4_SESSION_ESTABLISHED,
 };
 
 extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
@@ -118,6 +119,12 @@ static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
 	return 0;
 }
 
+static inline void nfs4_copy_sessionid(struct nfs4_sessionid *dst,
+		const struct nfs4_sessionid *src)
+{
+	memcpy(dst->data, src->data, NFS4_MAX_SESSIONID_LEN);
+}
+
 #ifdef CONFIG_CRC32
 /*
  * nfs_session_id_hash - calculate the crc32 hash for the session id
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 5194933ed419..f95e3b58bbc3 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -346,9 +346,23 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
 	status = nfs4_proc_exchange_id(clp, cred);
 	if (status != NFS4_OK)
 		return status;
-	set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 
-	return nfs41_walk_client_list(clp, result, cred);
+	status = nfs41_walk_client_list(clp, result, cred);
+	if (status < 0)
+		return status;
+	if (clp != *result)
+		return 0;
+
+	/* Purge state if the client id was established in a prior instance */
+	if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)
+		set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+	else
+		set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	nfs4_schedule_state_manager(clp);
+	status = nfs_wait_client_init_complete(clp);
+	if (status < 0)
+		nfs_put_client(clp);
+	return status;
 }
 
 #endif /* CONFIG_NFS_V4_1 */
@@ -1003,11 +1017,11 @@ struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_m
 	struct nfs_seqid *new;
 
 	new = kmalloc(sizeof(*new), gfp_mask);
-	if (new != NULL) {
-		new->sequence = counter;
-		INIT_LIST_HEAD(&new->list);
-		new->task = NULL;
-	}
+	if (new == NULL)
+		return ERR_PTR(-ENOMEM);
+	new->sequence = counter;
+	INIT_LIST_HEAD(&new->list);
+	new->task = NULL;
 	return new;
 }
 
@@ -1015,7 +1029,7 @@ void nfs_release_seqid(struct nfs_seqid *seqid)
 {
 	struct nfs_seqid_counter *sequence;
 
-	if (list_empty(&seqid->list))
+	if (seqid == NULL || list_empty(&seqid->list))
 		return;
 	sequence = seqid->sequence;
 	spin_lock(&sequence->lock);
@@ -1071,13 +1085,15 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
 
 void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid)
 {
-	struct nfs4_state_owner *sp = container_of(seqid->sequence,
-					struct nfs4_state_owner, so_seqid);
-	struct nfs_server *server = sp->so_server;
+	struct nfs4_state_owner *sp;
 
+	if (seqid == NULL)
+		return;
+
+	sp = container_of(seqid->sequence, struct nfs4_state_owner, so_seqid);
 	if (status == -NFS4ERR_BAD_SEQID)
 		nfs4_drop_state_owner(sp);
-	if (!nfs4_has_session(server->nfs_client))
+	if (!nfs4_has_session(sp->so_server->nfs_client))
 		nfs_increment_seqid(status, seqid);
 }
 
@@ -1088,14 +1104,18 @@ void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid)
  */
 void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid)
 {
-	nfs_increment_seqid(status, seqid);
+	if (seqid != NULL)
+		nfs_increment_seqid(status, seqid);
 }
 
 int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task)
 {
-	struct nfs_seqid_counter *sequence = seqid->sequence;
+	struct nfs_seqid_counter *sequence;
 	int status = 0;
 
+	if (seqid == NULL)
+		goto out;
+	sequence = seqid->sequence;
 	spin_lock(&sequence->lock);
 	seqid->task = task;
 	if (list_empty(&seqid->list))
@@ -1106,6 +1126,7 @@ int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task)
 	status = -EAGAIN;
 unlock:
 	spin_unlock(&sequence->lock);
+out:
 	return status;
 }
 
@@ -1366,49 +1387,55 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct file_lock *fl;
 	int status = 0;
+	struct file_lock_context *flctx = inode->i_flctx;
+	struct list_head *list;
 
-	if (inode->i_flock == NULL)
+	if (flctx == NULL)
 		return 0;
 
+	list = &flctx->flc_posix;
+
 	/* Guard against delegation returns and new lock/unlock calls */
 	down_write(&nfsi->rwsem);
-	/* Protect inode->i_flock using the BKL */
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
-			continue;
+	spin_lock(&flctx->flc_lock);
+restart:
+	list_for_each_entry(fl, list, fl_list) {
 		if (nfs_file_open_context(fl->fl_file)->state != state)
 			continue;
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&flctx->flc_lock);
 		status = ops->recover_lock(state, fl);
 		switch (status) {
-			case 0:
-				break;
-			case -ESTALE:
-			case -NFS4ERR_ADMIN_REVOKED:
-			case -NFS4ERR_STALE_STATEID:
-			case -NFS4ERR_BAD_STATEID:
-			case -NFS4ERR_EXPIRED:
-			case -NFS4ERR_NO_GRACE:
-			case -NFS4ERR_STALE_CLIENTID:
-			case -NFS4ERR_BADSESSION:
-			case -NFS4ERR_BADSLOT:
-			case -NFS4ERR_BAD_HIGH_SLOT:
-			case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-				goto out;
-			default:
-				printk(KERN_ERR "NFS: %s: unhandled error %d\n",
-					 __func__, status);
-			case -ENOMEM:
-			case -NFS4ERR_DENIED:
-			case -NFS4ERR_RECLAIM_BAD:
-			case -NFS4ERR_RECLAIM_CONFLICT:
-				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
-				status = 0;
+		case 0:
+			break;
+		case -ESTALE:
+		case -NFS4ERR_ADMIN_REVOKED:
+		case -NFS4ERR_STALE_STATEID:
+		case -NFS4ERR_BAD_STATEID:
+		case -NFS4ERR_EXPIRED:
+		case -NFS4ERR_NO_GRACE:
+		case -NFS4ERR_STALE_CLIENTID:
+		case -NFS4ERR_BADSESSION:
+		case -NFS4ERR_BADSLOT:
+		case -NFS4ERR_BAD_HIGH_SLOT:
+		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+			goto out;
+		default:
+			pr_err("NFS: %s: unhandled error %d\n",
+					__func__, status);
+		case -ENOMEM:
+		case -NFS4ERR_DENIED:
+		case -NFS4ERR_RECLAIM_BAD:
+		case -NFS4ERR_RECLAIM_CONFLICT:
+			/* kill_proc(fl->fl_pid, SIGLOST, 1); */
+			status = 0;
 		}
-		spin_lock(&inode->i_lock);
+		spin_lock(&flctx->flc_lock);
 	}
-	spin_unlock(&inode->i_lock);
+	if (list == &flctx->flc_posix) {
+		list = &flctx->flc_flock;
+		goto restart;
+	}
+	spin_unlock(&flctx->flc_lock);
 out:
 	up_write(&nfsi->rwsem);
 	return status;
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 6f340f02f2ba..75090feeafad 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -53,7 +53,6 @@ static const struct super_operations nfs4_sops = {
 	.destroy_inode	= nfs_destroy_inode,
 	.write_inode	= nfs4_write_inode,
 	.drop_inode	= nfs_drop_inode,
-	.put_super	= nfs_put_super,
 	.statfs		= nfs_statfs,
 	.evict_inode	= nfs4_evict_inode,
 	.umount_begin	= nfs_umount_begin,
@@ -346,6 +345,9 @@ out:
 
 static void __exit exit_nfs_v4(void)
 {
+	/* Not called in the _init(), conditionally loaded */
+	nfs4_pnfs_v3_ds_connect_unload();
+
 	unregister_nfs_version(&nfs_v4);
 	nfs4_unregister_sysctl();
 	nfs_idmap_quit();
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index cb4376b78ed9..5c399ec41079 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -946,7 +946,10 @@ static void encode_uint64(struct xdr_stream *xdr, u64 n)
 static void encode_nfs4_seqid(struct xdr_stream *xdr,
 		const struct nfs_seqid *seqid)
 {
-	encode_uint32(xdr, seqid->sequence->counter);
+	if (seqid != NULL)
+		encode_uint32(xdr, seqid->sequence->counter);
+	else
+		encode_uint32(xdr, 0);
 }
 
 static void encode_compound_hdr(struct xdr_stream *xdr,
@@ -1125,7 +1128,7 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg
 {
 	encode_op_hdr(xdr, OP_CLOSE, decode_close_maxsz, hdr);
 	encode_nfs4_seqid(xdr, arg->seqid);
-	encode_nfs4_stateid(xdr, arg->stateid);
+	encode_nfs4_stateid(xdr, &arg->stateid);
 }
 
 static void encode_commit(struct xdr_stream *xdr, const struct nfs_commitargs *args, struct compound_hdr *hdr)
@@ -1301,12 +1304,12 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args
 	*p = cpu_to_be32(args->new_lock_owner);
 	if (args->new_lock_owner){
 		encode_nfs4_seqid(xdr, args->open_seqid);
-		encode_nfs4_stateid(xdr, args->open_stateid);
+		encode_nfs4_stateid(xdr, &args->open_stateid);
 		encode_nfs4_seqid(xdr, args->lock_seqid);
 		encode_lockowner(xdr, &args->lock_owner);
 	}
 	else {
-		encode_nfs4_stateid(xdr, args->lock_stateid);
+		encode_nfs4_stateid(xdr, &args->lock_stateid);
 		encode_nfs4_seqid(xdr, args->lock_seqid);
 	}
 }
@@ -1330,7 +1333,7 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar
 	encode_op_hdr(xdr, OP_LOCKU, decode_locku_maxsz, hdr);
 	encode_uint32(xdr, nfs4_lock_type(args->fl, 0));
 	encode_nfs4_seqid(xdr, args->seqid);
-	encode_nfs4_stateid(xdr, args->stateid);
+	encode_nfs4_stateid(xdr, &args->stateid);
 	p = reserve_space(xdr, 16);
 	p = xdr_encode_hyper(p, args->fl->fl_start);
 	xdr_encode_hyper(p, nfs4_lock_length(args->fl));
@@ -1348,24 +1351,12 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc
 	encode_string(xdr, name->len, name->name);
 }
 
-static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode)
+static void encode_share_access(struct xdr_stream *xdr, u32 share_access)
 {
 	__be32 *p;
 
 	p = reserve_space(xdr, 8);
-	switch (fmode & (FMODE_READ|FMODE_WRITE)) {
-	case FMODE_READ:
-		*p++ = cpu_to_be32(NFS4_SHARE_ACCESS_READ);
-		break;
-	case FMODE_WRITE:
-		*p++ = cpu_to_be32(NFS4_SHARE_ACCESS_WRITE);
-		break;
-	case FMODE_READ|FMODE_WRITE:
-		*p++ = cpu_to_be32(NFS4_SHARE_ACCESS_BOTH);
-		break;
-	default:
-		*p++ = cpu_to_be32(0);
-	}
+	*p++ = cpu_to_be32(share_access);
 	*p = cpu_to_be32(0);		/* for linux, share_deny = 0 always */
 }
 
@@ -1377,7 +1368,7 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena
  * owner 4 = 32
  */
 	encode_nfs4_seqid(xdr, arg->seqid);
-	encode_share_access(xdr, arg->fmode);
+	encode_share_access(xdr, arg->share_access);
 	p = reserve_space(xdr, 36);
 	p = xdr_encode_hyper(p, arg->clientid);
 	*p++ = cpu_to_be32(24);
@@ -1530,9 +1521,9 @@ static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_co
 static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr)
 {
 	encode_op_hdr(xdr, OP_OPEN_DOWNGRADE, decode_open_downgrade_maxsz, hdr);
-	encode_nfs4_stateid(xdr, arg->stateid);
+	encode_nfs4_stateid(xdr, &arg->stateid);
 	encode_nfs4_seqid(xdr, arg->seqid);
-	encode_share_access(xdr, arg->fmode);
+	encode_share_access(xdr, arg->share_access);
 }
 
 static void
@@ -1724,17 +1715,17 @@ static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, stru
 #if defined(CONFIG_NFS_V4_1)
 /* NFSv4.1 operations */
 static void encode_bind_conn_to_session(struct xdr_stream *xdr,
-				   struct nfs4_session *session,
+				   struct nfs41_bind_conn_to_session_args *args,
 				   struct compound_hdr *hdr)
 {
 	__be32 *p;
 
 	encode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION,
 		decode_bind_conn_to_session_maxsz, hdr);
-	encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
+	encode_opaque_fixed(xdr, args->sessionid.data, NFS4_MAX_SESSIONID_LEN);
 	p = xdr_reserve_space(xdr, 8);
-	*p++ = cpu_to_be32(NFS4_CDFC4_BACK_OR_BOTH);
-	*p = 0;	/* use_conn_in_rdma_mode = False */
+	*p++ = cpu_to_be32(args->dir);
+	*p = (args->use_conn_in_rdma_mode) ? cpu_to_be32(1) : cpu_to_be32(0);
 }
 
 static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map)
@@ -1801,9 +1792,8 @@ static void encode_create_session(struct xdr_stream *xdr,
 				  struct compound_hdr *hdr)
 {
 	__be32 *p;
-	char machine_name[NFS4_MAX_MACHINE_NAME_LEN];
-	uint32_t len;
 	struct nfs_client *clp = args->client;
+	struct rpc_clnt *clnt = clp->cl_rpcclient;
 	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
 	u32 max_resp_sz_cached;
 
@@ -1814,13 +1804,10 @@ static void encode_create_session(struct xdr_stream *xdr,
 	max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE +
 			      RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT;
 
-	len = scnprintf(machine_name, sizeof(machine_name), "%s",
-			clp->cl_ipaddr);
-
 	encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr);
-	p = reserve_space(xdr, 16 + 2*28 + 20 + len + 12);
-	p = xdr_encode_hyper(p, clp->cl_clientid);
-	*p++ = cpu_to_be32(clp->cl_seqid);			/*Sequence id */
+	p = reserve_space(xdr, 16 + 2*28 + 20 + clnt->cl_nodelen + 12);
+	p = xdr_encode_hyper(p, args->clientid);
+	*p++ = cpu_to_be32(args->seqid);			/*Sequence id */
 	*p++ = cpu_to_be32(args->flags);			/*flags */
 
 	/* Fore Channel */
@@ -1847,7 +1834,7 @@ static void encode_create_session(struct xdr_stream *xdr,
 
 	/* authsys_parms rfc1831 */
 	*p++ = cpu_to_be32(nn->boot_time.tv_nsec);	/* stamp */
-	p = xdr_encode_opaque(p, machine_name, len);
+	p = xdr_encode_array(p, clnt->cl_nodename, clnt->cl_nodelen);
 	*p++ = cpu_to_be32(0);				/* UID */
 	*p++ = cpu_to_be32(0);				/* GID */
 	*p = cpu_to_be32(0);				/* No more gids */
@@ -2012,11 +1999,11 @@ encode_layoutreturn(struct xdr_stream *xdr,
 	p = reserve_space(xdr, 16);
 	*p++ = cpu_to_be32(0);		/* reclaim. always 0 for now */
 	*p++ = cpu_to_be32(args->layout_type);
-	*p++ = cpu_to_be32(IOMODE_ANY);
+	*p++ = cpu_to_be32(args->range.iomode);
 	*p = cpu_to_be32(RETURN_FILE);
 	p = reserve_space(xdr, 16);
-	p = xdr_encode_hyper(p, 0);
-	p = xdr_encode_hyper(p, NFS4_MAX_UINT64);
+	p = xdr_encode_hyper(p, args->range.offset);
+	p = xdr_encode_hyper(p, args->range.length);
 	spin_lock(&args->inode->i_lock);
 	encode_nfs4_stateid(xdr, &args->stateid);
 	spin_unlock(&args->inode->i_lock);
@@ -2747,14 +2734,14 @@ static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req,
 				struct xdr_stream *xdr,
-				struct nfs_client *clp)
+				struct nfs41_bind_conn_to_session_args *args)
 {
 	struct compound_hdr hdr = {
-		.minorversion = clp->cl_mvops->minor_version,
+		.minorversion = args->client->cl_mvops->minor_version,
 	};
 
 	encode_compound_hdr(xdr, req, &hdr);
-	encode_bind_conn_to_session(xdr, clp->cl_session, &hdr);
+	encode_bind_conn_to_session(xdr, args, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -4936,20 +4923,13 @@ out_overflow:
 	return -EIO;
 }
 
-static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res)
+static int decode_rw_delegation(struct xdr_stream *xdr,
+		uint32_t delegation_type,
+		struct nfs_openres *res)
 {
 	__be32 *p;
-	uint32_t delegation_type;
 	int status;
 
-	p = xdr_inline_decode(xdr, 4);
-	if (unlikely(!p))
-		goto out_overflow;
-	delegation_type = be32_to_cpup(p);
-	if (delegation_type == NFS4_OPEN_DELEGATE_NONE) {
-		res->delegation_type = 0;
-		return 0;
-	}
 	status = decode_stateid(xdr, &res->delegation);
 	if (unlikely(status))
 		return status;
@@ -4973,6 +4953,52 @@ out_overflow:
 	return -EIO;
 }
 
+static int decode_no_delegation(struct xdr_stream *xdr, struct nfs_openres *res)
+{
+	__be32 *p;
+	uint32_t why_no_delegation;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	why_no_delegation = be32_to_cpup(p);
+	switch (why_no_delegation) {
+		case WND4_CONTENTION:
+		case WND4_RESOURCE:
+			xdr_inline_decode(xdr, 4);
+			/* Ignore for now */
+	}
+	return 0;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
+static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res)
+{
+	__be32 *p;
+	uint32_t delegation_type;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	delegation_type = be32_to_cpup(p);
+	res->delegation_type = 0;
+	switch (delegation_type) {
+	case NFS4_OPEN_DELEGATE_NONE:
+		return 0;
+	case NFS4_OPEN_DELEGATE_READ:
+	case NFS4_OPEN_DELEGATE_WRITE:
+		return decode_rw_delegation(xdr, delegation_type, res);
+	case NFS4_OPEN_DELEGATE_NONE_EXT:
+		return decode_no_delegation(xdr, res);
+	}
+	return -EIO;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
 static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
 {
 	__be32 *p;
@@ -5587,7 +5613,7 @@ static int decode_bind_conn_to_session(struct xdr_stream *xdr,
 
 	status = decode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION);
 	if (!status)
-		status = decode_sessionid(xdr, &res->session->sess_id);
+		status = decode_sessionid(xdr, &res->sessionid);
 	if (unlikely(status))
 		return status;
 
@@ -5615,12 +5641,10 @@ static int decode_create_session(struct xdr_stream *xdr,
 {
 	__be32 *p;
 	int status;
-	struct nfs_client *clp = res->client;
-	struct nfs4_session *session = clp->cl_session;
 
 	status = decode_op_hdr(xdr, OP_CREATE_SESSION);
 	if (!status)
-		status = decode_sessionid(xdr, &session->sess_id);
+		status = decode_sessionid(xdr, &res->sessionid);
 	if (unlikely(status))
 		return status;
 
@@ -5628,13 +5652,13 @@ static int decode_create_session(struct xdr_stream *xdr,
 	p = xdr_inline_decode(xdr, 8);
 	if (unlikely(!p))
 		goto out_overflow;
-	clp->cl_seqid = be32_to_cpup(p++);
-	session->flags = be32_to_cpup(p);
+	res->seqid = be32_to_cpup(p++);
+	res->flags = be32_to_cpup(p);
 
 	/* Channel attributes */
-	status = decode_chan_attrs(xdr, &session->fc_attrs);
+	status = decode_chan_attrs(xdr, &res->fc_attrs);
 	if (!status)
-		status = decode_chan_attrs(xdr, &session->bc_attrs);
+		status = decode_chan_attrs(xdr, &res->bc_attrs);
 	return status;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -6567,6 +6591,7 @@ static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	int status;
 
 	status = decode_compound_hdr(xdr, &hdr);
+	res->op_status = hdr.status;
 	if (status)
 		goto out;
 	status = decode_sequence(xdr, &res->seq_res, rqstp);
@@ -6592,6 +6617,7 @@ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	int status;
 
 	status = decode_compound_hdr(xdr, &hdr);
+	res->op_status = hdr.status;
 	if (status)
 		goto out;
 	status = decode_sequence(xdr, &res->seq_res, rqstp);
@@ -6621,6 +6647,7 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	int status;
 
 	status = decode_compound_hdr(xdr, &hdr);
+	res->op_status = hdr.status;
 	if (status)
 		goto out;
 	status = decode_sequence(xdr, &res->seq_res, rqstp);
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index cd3c910d2d12..9bc9f04fb7f6 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -261,11 +261,11 @@ static int __init root_nfs_data(char *cmdline)
 	 */
 	len = snprintf(nfs_export_path, sizeof(nfs_export_path),
 				tmp, utsname()->nodename);
-	if (len > (int)sizeof(nfs_export_path))
+	if (len >= (int)sizeof(nfs_export_path))
 		goto out_devnametoolong;
 	len = snprintf(nfs_root_device, sizeof(nfs_root_device),
 				"%pI4:%s", &servaddr, nfs_export_path);
-	if (len > (int)sizeof(nfs_root_device))
+	if (len >= (int)sizeof(nfs_root_device))
 		goto out_devnametoolong;
 
 	retval = 0;
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 9e5bc42180e4..24e1d7403c0b 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -537,11 +537,12 @@ int objio_write_pagelist(struct nfs_pgio_header *hdr, int how)
 static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio,
 			  struct nfs_page *prev, struct nfs_page *req)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(pgio);
 	unsigned int size;
 
 	size = pnfs_generic_pg_test(pgio, prev, req);
 
-	if (!size || pgio->pg_count + req->wb_bytes >
+	if (!size || mirror->pg_count + req->wb_bytes >
 	    (unsigned long)pgio->pg_layout_private)
 		return 0;
 
@@ -607,12 +608,14 @@ static const struct nfs_pageio_ops objio_pg_read_ops = {
 	.pg_init = objio_init_read,
 	.pg_test = objio_pg_test,
 	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static const struct nfs_pageio_ops objio_pg_write_ops = {
 	.pg_init = objio_init_write,
 	.pg_test = objio_pg_test,
 	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static struct pnfs_layoutdriver_type objlayout_type = {
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 2b5e769beb16..d57190a0d533 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -42,21 +42,35 @@ static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
 	return p->pagevec != NULL;
 }
 
+struct nfs_pgio_mirror *
+nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc)
+{
+	return nfs_pgio_has_mirroring(desc) ?
+		&desc->pg_mirrors[desc->pg_mirror_idx] :
+		&desc->pg_mirrors[0];
+}
+EXPORT_SYMBOL_GPL(nfs_pgio_current_mirror);
+
 void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 		       struct nfs_pgio_header *hdr,
 		       void (*release)(struct nfs_pgio_header *hdr))
 {
-	hdr->req = nfs_list_entry(desc->pg_list.next);
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
+
+	hdr->req = nfs_list_entry(mirror->pg_list.next);
 	hdr->inode = desc->pg_inode;
 	hdr->cred = hdr->req->wb_context->cred;
 	hdr->io_start = req_offset(hdr->req);
-	hdr->good_bytes = desc->pg_count;
+	hdr->good_bytes = mirror->pg_count;
 	hdr->dreq = desc->pg_dreq;
 	hdr->layout_private = desc->pg_layout_private;
 	hdr->release = release;
 	hdr->completion_ops = desc->pg_completion_ops;
 	if (hdr->completion_ops->init_hdr)
 		hdr->completion_ops->init_hdr(hdr);
+
+	hdr->pgio_mirror_idx = desc->pg_mirror_idx;
 }
 EXPORT_SYMBOL_GPL(nfs_pgheader_init);
 
@@ -480,7 +494,10 @@ nfs_wait_on_request(struct nfs_page *req)
 size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 			   struct nfs_page *prev, struct nfs_page *req)
 {
-	if (desc->pg_count > desc->pg_bsize) {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
+
+	if (mirror->pg_count > mirror->pg_bsize) {
 		/* should never happen */
 		WARN_ON_ONCE(1);
 		return 0;
@@ -490,11 +507,11 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 	 * Limit the request size so that we can still allocate a page array
 	 * for it without upsetting the slab allocator.
 	 */
-	if (((desc->pg_count + req->wb_bytes) >> PAGE_SHIFT) *
+	if (((mirror->pg_count + req->wb_bytes) >> PAGE_SHIFT) *
 			sizeof(struct page) > PAGE_SIZE)
 		return 0;
 
-	return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes);
+	return min(mirror->pg_bsize - mirror->pg_count, (size_t)req->wb_bytes);
 }
 EXPORT_SYMBOL_GPL(nfs_generic_pg_test);
 
@@ -597,13 +614,14 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata)
 }
 
 int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
+		      struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
 		      const struct rpc_call_ops *call_ops, int how, int flags)
 {
 	struct rpc_task *task;
 	struct rpc_message msg = {
 		.rpc_argp = &hdr->args,
 		.rpc_resp = &hdr->res,
-		.rpc_cred = hdr->cred,
+		.rpc_cred = cred,
 	};
 	struct rpc_task_setup task_setup_data = {
 		.rpc_client = clnt,
@@ -616,7 +634,7 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
 	};
 	int ret = 0;
 
-	hdr->rw_ops->rw_initiate(hdr, &msg, &task_setup_data, how);
+	hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how);
 
 	dprintk("NFS: %5u initiated pgio call "
 		"(req %s/%llu, %u bytes @ offset %llu)\n",
@@ -650,10 +668,18 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio);
 static int nfs_pgio_error(struct nfs_pageio_descriptor *desc,
 			  struct nfs_pgio_header *hdr)
 {
+	struct nfs_pgio_mirror *mirror;
+	u32 midx;
+
 	set_bit(NFS_IOHDR_REDO, &hdr->flags);
 	nfs_pgio_data_destroy(hdr);
 	hdr->completion_ops->completion(hdr);
-	desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+	/* TODO: Make sure it's right to clean up all mirrors here
+	 *       and not just hdr->pgio_mirror_idx */
+	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
+		mirror = &desc->pg_mirrors[midx];
+		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
+	}
 	return -ENOMEM;
 }
 
@@ -670,6 +696,17 @@ static void nfs_pgio_release(void *calldata)
 	hdr->completion_ops->completion(hdr);
 }
 
+static void nfs_pageio_mirror_init(struct nfs_pgio_mirror *mirror,
+				   unsigned int bsize)
+{
+	INIT_LIST_HEAD(&mirror->pg_list);
+	mirror->pg_bytes_written = 0;
+	mirror->pg_count = 0;
+	mirror->pg_bsize = bsize;
+	mirror->pg_base = 0;
+	mirror->pg_recoalesce = 0;
+}
+
 /**
  * nfs_pageio_init - initialise a page io descriptor
  * @desc: pointer to descriptor
@@ -686,13 +723,10 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 		     size_t bsize,
 		     int io_flags)
 {
-	INIT_LIST_HEAD(&desc->pg_list);
-	desc->pg_bytes_written = 0;
-	desc->pg_count = 0;
-	desc->pg_bsize = bsize;
-	desc->pg_base = 0;
+	struct nfs_pgio_mirror *new;
+	int i;
+
 	desc->pg_moreio = 0;
-	desc->pg_recoalesce = 0;
 	desc->pg_inode = inode;
 	desc->pg_ops = pg_ops;
 	desc->pg_completion_ops = compl_ops;
@@ -702,6 +736,26 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_lseg = NULL;
 	desc->pg_dreq = NULL;
 	desc->pg_layout_private = NULL;
+	desc->pg_bsize = bsize;
+
+	desc->pg_mirror_count = 1;
+	desc->pg_mirror_idx = 0;
+
+	if (pg_ops->pg_get_mirror_count) {
+		/* until we have a request, we don't have an lseg and no
+		 * idea how many mirrors there will be */
+		new = kcalloc(NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX,
+			      sizeof(struct nfs_pgio_mirror), GFP_KERNEL);
+		desc->pg_mirrors_dynamic = new;
+		desc->pg_mirrors = new;
+
+		for (i = 0; i < NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX; i++)
+			nfs_pageio_mirror_init(&desc->pg_mirrors[i], bsize);
+	} else {
+		desc->pg_mirrors_dynamic = NULL;
+		desc->pg_mirrors = desc->pg_mirrors_static;
+		nfs_pageio_mirror_init(&desc->pg_mirrors[0], bsize);
+	}
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_init);
 
@@ -737,14 +791,16 @@ static void nfs_pgio_result(struct rpc_task *task, void *calldata)
 int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 		     struct nfs_pgio_header *hdr)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	struct nfs_page		*req;
 	struct page		**pages,
 				*last_page;
-	struct list_head *head = &desc->pg_list;
+	struct list_head *head = &mirror->pg_list;
 	struct nfs_commit_info cinfo;
 	unsigned int pagecount, pageused;
 
-	pagecount = nfs_page_array_len(desc->pg_base, desc->pg_count);
+	pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count);
 	if (!nfs_pgarray_set(&hdr->page_array, pagecount))
 		return nfs_pgio_error(desc, hdr);
 
@@ -772,7 +828,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
 
 	/* Set up the argument struct */
-	nfs_pgio_rpcsetup(hdr, desc->pg_count, 0, desc->pg_ioflags, &cinfo);
+	nfs_pgio_rpcsetup(hdr, mirror->pg_count, 0, desc->pg_ioflags, &cinfo);
 	desc->pg_rpc_callops = &nfs_pgio_common_ops;
 	return 0;
 }
@@ -780,23 +836,74 @@ EXPORT_SYMBOL_GPL(nfs_generic_pgio);
 
 static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
 {
+	struct nfs_pgio_mirror *mirror;
 	struct nfs_pgio_header *hdr;
 	int ret;
 
+	mirror = nfs_pgio_current_mirror(desc);
+
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
-		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+		/* TODO: make sure this is right with mirroring - or
+		 *       should it back out all mirrors? */
+		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
 		return -ENOMEM;
 	}
 	nfs_pgheader_init(desc, hdr, nfs_pgio_header_free);
 	ret = nfs_generic_pgio(desc, hdr);
 	if (ret == 0)
 		ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode),
-					hdr, desc->pg_rpc_callops,
+					hdr,
+					hdr->cred,
+					NFS_PROTO(hdr->inode),
+					desc->pg_rpc_callops,
 					desc->pg_ioflags, 0);
 	return ret;
 }
 
+/*
+ * nfs_pageio_setup_mirroring - determine if mirroring is to be used
+ *				by calling the pg_get_mirror_count op
+ */
+static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio,
+				       struct nfs_page *req)
+{
+	int mirror_count = 1;
+
+	if (!pgio->pg_ops->pg_get_mirror_count)
+		return 0;
+
+	mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req);
+
+	if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX)
+		return -EINVAL;
+
+	if (WARN_ON_ONCE(!pgio->pg_mirrors_dynamic))
+		return -EINVAL;
+
+	pgio->pg_mirror_count = mirror_count;
+
+	return 0;
+}
+
+/*
+ * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1)
+ */
+void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio)
+{
+	pgio->pg_mirror_count = 1;
+	pgio->pg_mirror_idx = 0;
+}
+
+static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio)
+{
+	pgio->pg_mirror_count = 1;
+	pgio->pg_mirror_idx = 0;
+	pgio->pg_mirrors = pgio->pg_mirrors_static;
+	kfree(pgio->pg_mirrors_dynamic);
+	pgio->pg_mirrors_dynamic = NULL;
+}
+
 static bool nfs_match_open_context(const struct nfs_open_context *ctx1,
 		const struct nfs_open_context *ctx2)
 {
@@ -826,11 +933,15 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 				      struct nfs_pageio_descriptor *pgio)
 {
 	size_t size;
+	struct file_lock_context *flctx;
 
 	if (prev) {
 		if (!nfs_match_open_context(req->wb_context, prev->wb_context))
 			return false;
-		if (req->wb_context->dentry->d_inode->i_flock != NULL &&
+		flctx = req->wb_context->dentry->d_inode->i_flctx;
+		if (flctx != NULL &&
+		    !(list_empty_careful(&flctx->flc_posix) &&
+		      list_empty_careful(&flctx->flc_flock)) &&
 		    !nfs_match_lock_context(req->wb_lock_context,
 					    prev->wb_lock_context))
 			return false;
@@ -863,19 +974,22 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
 				     struct nfs_page *req)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	struct nfs_page *prev = NULL;
-	if (desc->pg_count != 0) {
-		prev = nfs_list_entry(desc->pg_list.prev);
+
+	if (mirror->pg_count != 0) {
+		prev = nfs_list_entry(mirror->pg_list.prev);
 	} else {
 		if (desc->pg_ops->pg_init)
 			desc->pg_ops->pg_init(desc, req);
-		desc->pg_base = req->wb_pgbase;
+		mirror->pg_base = req->wb_pgbase;
 	}
 	if (!nfs_can_coalesce_requests(prev, req, desc))
 		return 0;
 	nfs_list_remove_request(req);
-	nfs_list_add_request(req, &desc->pg_list);
-	desc->pg_count += req->wb_bytes;
+	nfs_list_add_request(req, &mirror->pg_list);
+	mirror->pg_count += req->wb_bytes;
 	return 1;
 }
 
@@ -884,16 +998,19 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
  */
 static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
 {
-	if (!list_empty(&desc->pg_list)) {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
+
+	if (!list_empty(&mirror->pg_list)) {
 		int error = desc->pg_ops->pg_doio(desc);
 		if (error < 0)
 			desc->pg_error = error;
 		else
-			desc->pg_bytes_written += desc->pg_count;
+			mirror->pg_bytes_written += mirror->pg_count;
 	}
-	if (list_empty(&desc->pg_list)) {
-		desc->pg_count = 0;
-		desc->pg_base = 0;
+	if (list_empty(&mirror->pg_list)) {
+		mirror->pg_count = 0;
+		mirror->pg_base = 0;
 	}
 }
 
@@ -911,6 +1028,8 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
 static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			   struct nfs_page *req)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	struct nfs_page *subreq;
 	unsigned int bytes_left = 0;
 	unsigned int offset, pgbase;
@@ -934,7 +1053,7 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			nfs_pageio_doio(desc);
 			if (desc->pg_error < 0)
 				return 0;
-			if (desc->pg_recoalesce)
+			if (mirror->pg_recoalesce)
 				return 0;
 			/* retry add_request for this subreq */
 			nfs_page_group_lock(req, false);
@@ -972,14 +1091,16 @@ err_ptr:
 
 static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
 	LIST_HEAD(head);
 
 	do {
-		list_splice_init(&desc->pg_list, &head);
-		desc->pg_bytes_written -= desc->pg_count;
-		desc->pg_count = 0;
-		desc->pg_base = 0;
-		desc->pg_recoalesce = 0;
+		list_splice_init(&mirror->pg_list, &head);
+		mirror->pg_bytes_written -= mirror->pg_count;
+		mirror->pg_count = 0;
+		mirror->pg_base = 0;
+		mirror->pg_recoalesce = 0;
+
 		desc->pg_moreio = 0;
 
 		while (!list_empty(&head)) {
@@ -993,11 +1114,11 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
 				return 0;
 			break;
 		}
-	} while (desc->pg_recoalesce);
+	} while (mirror->pg_recoalesce);
 	return 1;
 }
 
-int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
+static int nfs_pageio_add_request_mirror(struct nfs_pageio_descriptor *desc,
 		struct nfs_page *req)
 {
 	int ret;
@@ -1010,9 +1131,80 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			break;
 		ret = nfs_do_recoalesce(desc);
 	} while (ret);
+
 	return ret;
 }
 
+int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
+			   struct nfs_page *req)
+{
+	u32 midx;
+	unsigned int pgbase, offset, bytes;
+	struct nfs_page *dupreq, *lastreq;
+
+	pgbase = req->wb_pgbase;
+	offset = req->wb_offset;
+	bytes = req->wb_bytes;
+
+	nfs_pageio_setup_mirroring(desc, req);
+
+	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
+		if (midx) {
+			nfs_page_group_lock(req, false);
+
+			/* find the last request */
+			for (lastreq = req->wb_head;
+			     lastreq->wb_this_page != req->wb_head;
+			     lastreq = lastreq->wb_this_page)
+				;
+
+			dupreq = nfs_create_request(req->wb_context,
+					req->wb_page, lastreq, pgbase, bytes);
+
+			if (IS_ERR(dupreq)) {
+				nfs_page_group_unlock(req);
+				return 0;
+			}
+
+			nfs_lock_request(dupreq);
+			nfs_page_group_unlock(req);
+			dupreq->wb_offset = offset;
+			dupreq->wb_index = req->wb_index;
+		} else
+			dupreq = req;
+
+		if (nfs_pgio_has_mirroring(desc))
+			desc->pg_mirror_idx = midx;
+		if (!nfs_pageio_add_request_mirror(desc, dupreq))
+			return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * nfs_pageio_complete_mirror - Complete I/O on the current mirror of an
+ *				nfs_pageio_descriptor
+ * @desc: pointer to io descriptor
+ */
+static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc,
+				       u32 mirror_idx)
+{
+	struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx];
+	u32 restore_idx = desc->pg_mirror_idx;
+
+	if (nfs_pgio_has_mirroring(desc))
+		desc->pg_mirror_idx = mirror_idx;
+	for (;;) {
+		nfs_pageio_doio(desc);
+		if (!mirror->pg_recoalesce)
+			break;
+		if (!nfs_do_recoalesce(desc))
+			break;
+	}
+	desc->pg_mirror_idx = restore_idx;
+}
+
 /*
  * nfs_pageio_resend - Transfer requests to new descriptor and resend
  * @hdr - the pgio header to move request from
@@ -1046,18 +1238,19 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
 EXPORT_SYMBOL_GPL(nfs_pageio_resend);
 
 /**
- * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor
+ * nfs_pageio_complete - Complete I/O then cleanup an nfs_pageio_descriptor
  * @desc: pointer to io descriptor
  */
 void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
 {
-	for (;;) {
-		nfs_pageio_doio(desc);
-		if (!desc->pg_recoalesce)
-			break;
-		if (!nfs_do_recoalesce(desc))
-			break;
-	}
+	u32 midx;
+
+	for (midx = 0; midx < desc->pg_mirror_count; midx++)
+		nfs_pageio_complete_mirror(desc, midx);
+
+	if (desc->pg_ops->pg_cleanup)
+		desc->pg_ops->pg_cleanup(desc);
+	nfs_pageio_cleanup_mirroring(desc);
 }
 
 /**
@@ -1073,10 +1266,17 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
  */
 void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
 {
-	if (!list_empty(&desc->pg_list)) {
-		struct nfs_page *prev = nfs_list_entry(desc->pg_list.prev);
-		if (index != prev->wb_index + 1)
-			nfs_pageio_complete(desc);
+	struct nfs_pgio_mirror *mirror;
+	struct nfs_page *prev;
+	u32 midx;
+
+	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
+		mirror = &desc->pg_mirrors[midx];
+		if (!list_empty(&mirror->pg_list)) {
+			prev = nfs_list_entry(mirror->pg_list.prev);
+			if (index != prev->wb_index + 1)
+				nfs_pageio_complete_mirror(desc, midx);
+		}
 	}
 }
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 0a5dda4d85c2..4f802b02fbb9 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -34,6 +34,7 @@
 #include "pnfs.h"
 #include "iostat.h"
 #include "nfs4trace.h"
+#include "delegation.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS
 #define PNFS_LAYOUTGET_RETRY_TIMEOUT (120*HZ)
@@ -50,6 +51,10 @@ static DEFINE_SPINLOCK(pnfs_spinlock);
  */
 static LIST_HEAD(pnfs_modules_tbl);
 
+static int
+pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
+		       enum pnfs_iomode iomode, bool sync);
+
 /* Return the registered pnfs layout driver module matching given id */
 static struct pnfs_layoutdriver_type *
 find_pnfs_driver_locked(u32 id)
@@ -238,6 +243,8 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 	struct inode *inode = lo->plh_inode;
 
 	if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
+		if (!list_empty(&lo->plh_segs))
+			WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n");
 		pnfs_detach_layout_hdr(lo);
 		spin_unlock(&inode->i_lock);
 		pnfs_free_layout_hdr(lo);
@@ -337,6 +344,48 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
 	rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
 }
 
+/* Return true if layoutreturn is needed */
+static bool
+pnfs_layout_need_return(struct pnfs_layout_hdr *lo,
+			struct pnfs_layout_segment *lseg)
+{
+	struct pnfs_layout_segment *s;
+
+	if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+		return false;
+
+	list_for_each_entry(s, &lo->plh_segs, pls_list)
+		if (s != lseg && test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
+			return false;
+
+	return true;
+}
+
+static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg,
+		struct pnfs_layout_hdr *lo, struct inode *inode)
+{
+	lo = lseg->pls_layout;
+	inode = lo->plh_inode;
+
+	spin_lock(&inode->i_lock);
+	if (pnfs_layout_need_return(lo, lseg)) {
+		nfs4_stateid stateid;
+		enum pnfs_iomode iomode;
+
+		stateid = lo->plh_stateid;
+		iomode = lo->plh_return_iomode;
+		/* decreased in pnfs_send_layoutreturn() */
+		lo->plh_block_lgets++;
+		lo->plh_return_iomode = 0;
+		spin_unlock(&inode->i_lock);
+		pnfs_get_layout_hdr(lo);
+
+		/* Send an async layoutreturn so we dont deadlock */
+		pnfs_send_layoutreturn(lo, stateid, iomode, false);
+	} else
+		spin_unlock(&inode->i_lock);
+}
+
 void
 pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {
@@ -349,8 +398,17 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 	dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg,
 		atomic_read(&lseg->pls_refcount),
 		test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
+
+	/* Handle the case where refcount != 1 */
+	if (atomic_add_unless(&lseg->pls_refcount, -1, 1))
+		return;
+
 	lo = lseg->pls_layout;
 	inode = lo->plh_inode;
+	/* Do we need a layoutreturn? */
+	if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+		pnfs_layoutreturn_before_put_lseg(lseg, lo, inode);
+
 	if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
 		pnfs_get_layout_hdr(lo);
 		pnfs_layout_remove_lseg(lo, lseg);
@@ -543,6 +601,7 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 		pnfs_get_layout_hdr(lo);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
+		pnfs_clear_retry_layoutget(lo);
 		spin_unlock(&nfsi->vfs_inode.i_lock);
 		pnfs_free_lseg_list(&tmp_list);
 		pnfs_put_layout_hdr(lo);
@@ -740,25 +799,37 @@ pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo,
 	return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
 }
 
+static bool
+pnfs_layout_returning(const struct pnfs_layout_hdr *lo,
+		      struct pnfs_layout_range *range)
+{
+	return test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) &&
+		(lo->plh_return_iomode == IOMODE_ANY ||
+		 lo->plh_return_iomode == range->iomode);
+}
+
 /* lget is set to 1 if called from inside send_layoutget call chain */
 static bool
-pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo, int lget)
+pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo,
+			struct pnfs_layout_range *range, int lget)
 {
 	return lo->plh_block_lgets ||
 		test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
 		(list_empty(&lo->plh_segs) &&
-		 (atomic_read(&lo->plh_outstanding) > lget));
+		 (atomic_read(&lo->plh_outstanding) > lget)) ||
+		pnfs_layout_returning(lo, range);
 }
 
 int
 pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
+			      struct pnfs_layout_range *range,
 			      struct nfs4_state *open_state)
 {
 	int status = 0;
 
 	dprintk("--> %s\n", __func__);
 	spin_lock(&lo->plh_inode->i_lock);
-	if (pnfs_layoutgets_blocked(lo, 1)) {
+	if (pnfs_layoutgets_blocked(lo, range, 1)) {
 		status = -EAGAIN;
 	} else if (!nfs4_valid_open_stateid(open_state)) {
 		status = -EBADF;
@@ -825,7 +896,9 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 			pnfs_layout_io_set_failed(lo, range->iomode);
 		}
 		return NULL;
-	}
+	} else
+		pnfs_layout_clear_fail_bit(lo,
+				pnfs_iomode_to_fail_bit(range->iomode));
 
 	return lseg;
 }
@@ -845,6 +918,49 @@ static void pnfs_clear_layoutcommit(struct inode *inode,
 	}
 }
 
+void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
+{
+	clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
+}
+
+static int
+pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
+		       enum pnfs_iomode iomode, bool sync)
+{
+	struct inode *ino = lo->plh_inode;
+	struct nfs4_layoutreturn *lrp;
+	int status = 0;
+
+	lrp = kzalloc(sizeof(*lrp), GFP_NOFS);
+	if (unlikely(lrp == NULL)) {
+		status = -ENOMEM;
+		spin_lock(&ino->i_lock);
+		lo->plh_block_lgets--;
+		pnfs_clear_layoutreturn_waitbit(lo);
+		rpc_wake_up(&NFS_SERVER(ino)->roc_rpcwaitq);
+		spin_unlock(&ino->i_lock);
+		pnfs_put_layout_hdr(lo);
+		goto out;
+	}
+
+	lrp->args.stateid = stateid;
+	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
+	lrp->args.inode = ino;
+	lrp->args.range.iomode = iomode;
+	lrp->args.range.offset = 0;
+	lrp->args.range.length = NFS4_MAX_UINT64;
+	lrp->args.layout = lo;
+	lrp->clp = NFS_SERVER(ino)->nfs_client;
+	lrp->cred = lo->plh_lc_cred;
+
+	status = nfs4_proc_layoutreturn(lrp, sync);
+out:
+	dprintk("<-- %s status: %d\n", __func__, status);
+	return status;
+}
+
 /*
  * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
  * when the layout segment list is empty.
@@ -859,7 +975,6 @@ _pnfs_return_layout(struct inode *ino)
 	struct pnfs_layout_hdr *lo = NULL;
 	struct nfs_inode *nfsi = NFS_I(ino);
 	LIST_HEAD(tmp_list);
-	struct nfs4_layoutreturn *lrp;
 	nfs4_stateid stateid;
 	int status = 0, empty;
 
@@ -901,24 +1016,7 @@ _pnfs_return_layout(struct inode *ino)
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 
-	lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
-	if (unlikely(lrp == NULL)) {
-		status = -ENOMEM;
-		spin_lock(&ino->i_lock);
-		lo->plh_block_lgets--;
-		spin_unlock(&ino->i_lock);
-		pnfs_put_layout_hdr(lo);
-		goto out;
-	}
-
-	lrp->args.stateid = stateid;
-	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
-	lrp->args.inode = ino;
-	lrp->args.layout = lo;
-	lrp->clp = NFS_SERVER(ino)->nfs_client;
-	lrp->cred = lo->plh_lc_cred;
-
-	status = nfs4_proc_layoutreturn(lrp);
+	status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
 out:
 	dprintk("<-- %s status: %d\n", __func__, status);
 	return status;
@@ -954,31 +1052,60 @@ pnfs_commit_and_return_layout(struct inode *inode)
 
 bool pnfs_roc(struct inode *ino)
 {
+	struct nfs_inode *nfsi = NFS_I(ino);
+	struct nfs_open_context *ctx;
+	struct nfs4_state *state;
 	struct pnfs_layout_hdr *lo;
 	struct pnfs_layout_segment *lseg, *tmp;
+	nfs4_stateid stateid;
 	LIST_HEAD(tmp_list);
-	bool found = false;
+	bool found = false, layoutreturn = false;
 
 	spin_lock(&ino->i_lock);
-	lo = NFS_I(ino)->layout;
+	lo = nfsi->layout;
 	if (!lo || !test_and_clear_bit(NFS_LAYOUT_ROC, &lo->plh_flags) ||
 	    test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags))
-		goto out_nolayout;
+		goto out_noroc;
+
+	/* Don't return layout if we hold a delegation */
+	if (nfs4_check_delegation(ino, FMODE_READ))
+		goto out_noroc;
+
+	list_for_each_entry(ctx, &nfsi->open_files, list) {
+		state = ctx->state;
+		/* Don't return layout if there is open file state */
+		if (state != NULL && state->state != 0)
+			goto out_noroc;
+	}
+
+	pnfs_clear_retry_layoutget(lo);
 	list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list)
 		if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
 			mark_lseg_invalid(lseg, &tmp_list);
 			found = true;
 		}
 	if (!found)
-		goto out_nolayout;
+		goto out_noroc;
 	lo->plh_block_lgets++;
 	pnfs_get_layout_hdr(lo); /* matched in pnfs_roc_release */
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 	return true;
 
-out_nolayout:
+out_noroc:
+	if (lo) {
+		stateid = lo->plh_stateid;
+		layoutreturn =
+			test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					   &lo->plh_flags);
+		if (layoutreturn) {
+			lo->plh_block_lgets++;
+			pnfs_get_layout_hdr(lo);
+		}
+	}
 	spin_unlock(&ino->i_lock);
+	if (layoutreturn)
+		pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
 	return false;
 }
 
@@ -1013,8 +1140,9 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 	struct nfs_inode *nfsi = NFS_I(ino);
 	struct pnfs_layout_hdr *lo;
 	struct pnfs_layout_segment *lseg;
+	nfs4_stateid stateid;
 	u32 current_seqid;
-	bool found = false;
+	bool found = false, layoutreturn = false;
 
 	spin_lock(&ino->i_lock);
 	list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list)
@@ -1031,7 +1159,21 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 	 */
 	*barrier = current_seqid + atomic_read(&lo->plh_outstanding);
 out:
+	if (!found) {
+		stateid = lo->plh_stateid;
+		layoutreturn =
+			test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					   &lo->plh_flags);
+		if (layoutreturn) {
+			lo->plh_block_lgets++;
+			pnfs_get_layout_hdr(lo);
+		}
+	}
 	spin_unlock(&ino->i_lock);
+	if (layoutreturn) {
+		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+		pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, false);
+	}
 	return found;
 }
 
@@ -1178,6 +1320,7 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
 
 	list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
 		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
+		    !test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags) &&
 		    pnfs_lseg_range_match(&lseg->pls_range, range)) {
 			ret = pnfs_get_lseg(lseg);
 			break;
@@ -1266,6 +1409,35 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx,
 	return ret;
 }
 
+/* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */
+static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key)
+{
+	if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags))
+		return 1;
+	return nfs_wait_bit_killable(key);
+}
+
+static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
+{
+	/*
+	 * send layoutcommit as it can hold up layoutreturn due to lseg
+	 * reference
+	 */
+	pnfs_layoutcommit_inode(lo->plh_inode, false);
+	return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN,
+				   pnfs_layoutget_retry_bit_wait,
+				   TASK_UNINTERRUPTIBLE);
+}
+
+static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo)
+{
+	unsigned long *bitlock = &lo->plh_flags;
+
+	clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock);
+	smp_mb__after_atomic();
+	wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET);
+}
+
 /*
  * Layout segment is retreived from the server if not cached.
  * The appropriate layout segment is referenced and returned to the caller.
@@ -1296,6 +1468,8 @@ pnfs_update_layout(struct inode *ino,
 	if (pnfs_within_mdsthreshold(ctx, ino, iomode))
 		goto out;
 
+lookup_again:
+	first = false;
 	spin_lock(&ino->i_lock);
 	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
 	if (lo == NULL) {
@@ -1310,27 +1484,62 @@ pnfs_update_layout(struct inode *ino,
 	}
 
 	/* if LAYOUTGET already failed once we don't try again */
-	if (pnfs_layout_io_test_failed(lo, iomode))
+	if (pnfs_layout_io_test_failed(lo, iomode) &&
+	    !pnfs_should_retry_layoutget(lo))
 		goto out_unlock;
 
-	/* Check to see if the layout for the given range already exists */
-	lseg = pnfs_find_lseg(lo, &arg);
-	if (lseg)
-		goto out_unlock;
+	first = list_empty(&lo->plh_segs);
+	if (first) {
+		/* The first layoutget for the file. Need to serialize per
+		 * RFC 5661 Errata 3208.
+		 */
+		if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET,
+				     &lo->plh_flags)) {
+			spin_unlock(&ino->i_lock);
+			wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET,
+				    TASK_UNINTERRUPTIBLE);
+			pnfs_put_layout_hdr(lo);
+			goto lookup_again;
+		}
+	} else {
+		/* Check to see if the layout for the given range
+		 * already exists
+		 */
+		lseg = pnfs_find_lseg(lo, &arg);
+		if (lseg)
+			goto out_unlock;
+	}
+
+	/*
+	 * Because we free lsegs before sending LAYOUTRETURN, we need to wait
+	 * for LAYOUTRETURN even if first is true.
+	 */
+	if (!lseg && pnfs_should_retry_layoutget(lo) &&
+	    test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
+		spin_unlock(&ino->i_lock);
+		dprintk("%s wait for layoutreturn\n", __func__);
+		if (pnfs_prepare_to_retry_layoutget(lo)) {
+			if (first)
+				pnfs_clear_first_layoutget(lo);
+			pnfs_put_layout_hdr(lo);
+			dprintk("%s retrying\n", __func__);
+			goto lookup_again;
+		}
+		goto out_put_layout_hdr;
+	}
 
-	if (pnfs_layoutgets_blocked(lo, 0))
+	if (pnfs_layoutgets_blocked(lo, &arg, 0))
 		goto out_unlock;
 	atomic_inc(&lo->plh_outstanding);
-
-	first = list_empty(&lo->plh_layouts) ? true : false;
 	spin_unlock(&ino->i_lock);
 
-	if (first) {
+	if (list_empty(&lo->plh_layouts)) {
 		/* The lo must be on the clp list if there is any
 		 * chance of a CB_LAYOUTRECALL(FILE) coming in.
 		 */
 		spin_lock(&clp->cl_lock);
-		list_add_tail(&lo->plh_layouts, &server->layouts);
+		if (list_empty(&lo->plh_layouts))
+			list_add_tail(&lo->plh_layouts, &server->layouts);
 		spin_unlock(&clp->cl_lock);
 	}
 
@@ -1343,8 +1552,11 @@ pnfs_update_layout(struct inode *ino,
 		arg.length = PAGE_CACHE_ALIGN(arg.length);
 
 	lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
+	pnfs_clear_retry_layoutget(lo);
 	atomic_dec(&lo->plh_outstanding);
 out_put_layout_hdr:
+	if (first)
+		pnfs_clear_first_layoutget(lo);
 	pnfs_put_layout_hdr(lo);
 out:
 	dprintk("%s: inode %s/%llu pNFS layout segment %s for "
@@ -1393,7 +1605,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		goto out_forget_reply;
 	}
 
-	if (pnfs_layoutgets_blocked(lo, 1)) {
+	if (pnfs_layoutgets_blocked(lo, &lgp->args.range, 1)) {
 		dprintk("%s forget reply due to state\n", __func__);
 		goto out_forget_reply;
 	}
@@ -1440,24 +1652,79 @@ out_forget_reply:
 	goto out;
 }
 
+static void
+pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
+				struct list_head *tmp_list,
+				struct pnfs_layout_range *return_range)
+{
+	struct pnfs_layout_segment *lseg, *next;
+
+	dprintk("%s:Begin lo %p\n", __func__, lo);
+
+	if (list_empty(&lo->plh_segs))
+		return;
+
+	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
+		if (should_free_lseg(&lseg->pls_range, return_range)) {
+			dprintk("%s: marking lseg %p iomode %d "
+				"offset %llu length %llu\n", __func__,
+				lseg, lseg->pls_range.iomode,
+				lseg->pls_range.offset,
+				lseg->pls_range.length);
+			set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
+			mark_lseg_invalid(lseg, tmp_list);
+		}
+}
+
+void pnfs_error_mark_layout_for_return(struct inode *inode,
+				       struct pnfs_layout_segment *lseg)
+{
+	struct pnfs_layout_hdr *lo = NFS_I(inode)->layout;
+	int iomode = pnfs_iomode_to_fail_bit(lseg->pls_range.iomode);
+	struct pnfs_layout_range range = {
+		.iomode = lseg->pls_range.iomode,
+		.offset = 0,
+		.length = NFS4_MAX_UINT64,
+	};
+	LIST_HEAD(free_me);
+
+	spin_lock(&inode->i_lock);
+	/* set failure bit so that pnfs path will be retried later */
+	pnfs_layout_set_fail_bit(lo, iomode);
+	set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
+	if (lo->plh_return_iomode == 0)
+		lo->plh_return_iomode = range.iomode;
+	else if (lo->plh_return_iomode != range.iomode)
+		lo->plh_return_iomode = IOMODE_ANY;
+	/*
+	 * mark all matching lsegs so that we are sure to have no live
+	 * segments at hand when sending layoutreturn. See pnfs_put_lseg()
+	 * for how it works.
+	 */
+	pnfs_mark_matching_lsegs_return(lo, &free_me, &range);
+	spin_unlock(&inode->i_lock);
+	pnfs_free_lseg_list(&free_me);
+}
+EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return);
+
 void
 pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
 	u64 rd_size = req->wb_bytes;
 
-	WARN_ON_ONCE(pgio->pg_lseg != NULL);
-
-	if (pgio->pg_dreq == NULL)
-		rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
-	else
-		rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
-
-	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
-					   req->wb_context,
-					   req_offset(req),
-					   rd_size,
-					   IOMODE_READ,
-					   GFP_KERNEL);
+	if (pgio->pg_lseg == NULL) {
+		if (pgio->pg_dreq == NULL)
+			rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
+		else
+			rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
+		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+						   req->wb_context,
+						   req_offset(req),
+						   rd_size,
+						   IOMODE_READ,
+						   GFP_KERNEL);
+	}
 	/* If no lseg, fall back to read through mds */
 	if (pgio->pg_lseg == NULL)
 		nfs_pageio_reset_read_mds(pgio);
@@ -1469,27 +1736,36 @@ void
 pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			   struct nfs_page *req, u64 wb_size)
 {
-	WARN_ON_ONCE(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 (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 no lseg, fall back to write through mds */
 	if (pgio->pg_lseg == NULL)
 		nfs_pageio_reset_write_mds(pgio);
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
 
+void
+pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *desc)
+{
+	if (desc->pg_lseg) {
+		pnfs_put_lseg(desc->pg_lseg);
+		desc->pg_lseg = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_cleanup);
+
 /*
  * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
  * of bytes (maximum @req->wb_bytes) that can be coalesced.
  */
 size_t
-pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
-		     struct nfs_page *req)
+pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
+		     struct nfs_page *prev, struct nfs_page *req)
 {
 	unsigned int size;
 	u64 seg_end, req_start, seg_left;
@@ -1513,10 +1789,16 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		seg_end = end_offset(pgio->pg_lseg->pls_range.offset,
 				     pgio->pg_lseg->pls_range.length);
 		req_start = req_offset(req);
-		WARN_ON_ONCE(req_start > seg_end);
+		WARN_ON_ONCE(req_start >= seg_end);
 		/* start of request is past the last byte of this segment */
-		if (req_start >= seg_end)
+		if (req_start >= seg_end) {
+			/* reference the new lseg */
+			if (pgio->pg_ops->pg_cleanup)
+				pgio->pg_ops->pg_cleanup(pgio);
+			if (pgio->pg_ops->pg_init)
+				pgio->pg_ops->pg_init(pgio, req);
 			return 0;
+		}
 
 		/* adjust 'size' iff there are fewer bytes left in the
 		 * segment than what nfs_generic_pg_test returned */
@@ -1571,10 +1853,12 @@ static void
 pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
 		struct nfs_pgio_header *hdr)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
-		list_splice_tail_init(&hdr->pages, &desc->pg_list);
+		list_splice_tail_init(&hdr->pages, &mirror->pg_list);
 		nfs_pageio_reset_write_mds(desc);
-		desc->pg_recoalesce = 1;
+		mirror->pg_recoalesce = 1;
 	}
 	nfs_pgio_data_destroy(hdr);
 }
@@ -1608,11 +1892,9 @@ pnfs_do_write(struct nfs_pageio_descriptor *desc,
 	struct pnfs_layout_segment *lseg = desc->pg_lseg;
 	enum pnfs_try_status trypnfs;
 
-	desc->pg_lseg = NULL;
 	trypnfs = pnfs_try_to_write_data(hdr, call_ops, lseg, how);
 	if (trypnfs == PNFS_NOT_ATTEMPTED)
 		pnfs_write_through_mds(desc, hdr);
-	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
@@ -1625,24 +1907,23 @@ EXPORT_SYMBOL_GPL(pnfs_writehdr_free);
 int
 pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	struct nfs_pgio_header *hdr;
 	int ret;
 
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
-		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
+		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
 		return -ENOMEM;
 	}
 	nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
+
 	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	ret = nfs_generic_pgio(desc, hdr);
-	if (ret != 0) {
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
-	} else
+	if (!ret)
 		pnfs_do_write(desc, hdr, desc->pg_ioflags);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
@@ -1687,10 +1968,12 @@ static void
 pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
 		struct nfs_pgio_header *hdr)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
-		list_splice_tail_init(&hdr->pages, &desc->pg_list);
+		list_splice_tail_init(&hdr->pages, &mirror->pg_list);
 		nfs_pageio_reset_read_mds(desc);
-		desc->pg_recoalesce = 1;
+		mirror->pg_recoalesce = 1;
 	}
 	nfs_pgio_data_destroy(hdr);
 }
@@ -1719,18 +2002,29 @@ pnfs_try_to_read_data(struct nfs_pgio_header *hdr,
 	return trypnfs;
 }
 
+/* Resend all requests through pnfs. */
+int pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr)
+{
+	struct nfs_pageio_descriptor pgio;
+
+	nfs_pageio_init_read(&pgio, hdr->inode, false, hdr->completion_ops);
+	return nfs_pageio_resend(&pgio, hdr);
+}
+EXPORT_SYMBOL_GPL(pnfs_read_resend_pnfs);
+
 static void
 pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
 {
 	const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
 	struct pnfs_layout_segment *lseg = desc->pg_lseg;
 	enum pnfs_try_status trypnfs;
+	int err = 0;
 
-	desc->pg_lseg = NULL;
 	trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg);
-	if (trypnfs == PNFS_NOT_ATTEMPTED)
+	if (trypnfs == PNFS_TRY_AGAIN)
+		err = pnfs_read_resend_pnfs(hdr);
+	if (trypnfs == PNFS_NOT_ATTEMPTED || err)
 		pnfs_read_through_mds(desc, hdr);
-	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
@@ -1743,24 +2037,20 @@ EXPORT_SYMBOL_GPL(pnfs_readhdr_free);
 int
 pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 {
+	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+
 	struct nfs_pgio_header *hdr;
 	int ret;
 
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
-		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-		ret = -ENOMEM;
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
-		return ret;
+		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
+		return -ENOMEM;
 	}
 	nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
 	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	ret = nfs_generic_pgio(desc, hdr);
-	if (ret != 0) {
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
-	} else
+	if (!ret)
 		pnfs_do_read(desc, hdr);
 	return ret;
 }
@@ -1966,6 +2256,7 @@ clear_layoutcommitting:
 	pnfs_clear_layoutcommitting(inode);
 	goto out;
 }
+EXPORT_SYMBOL_GPL(pnfs_layoutcommit_inode);
 
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
 {
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 9ae5b765b073..635f0865671c 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -38,6 +38,25 @@ enum {
 	NFS_LSEG_VALID = 0,	/* cleared when lseg is recalled/returned */
 	NFS_LSEG_ROC,		/* roc bit received from server */
 	NFS_LSEG_LAYOUTCOMMIT,	/* layoutcommit bit set for layoutcommit */
+	NFS_LSEG_LAYOUTRETURN,	/* layoutreturn bit set for layoutreturn */
+};
+
+/* Individual ip address */
+struct nfs4_pnfs_ds_addr {
+	struct sockaddr_storage	da_addr;
+	size_t			da_addrlen;
+	struct list_head	da_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
+	char			*da_remotestr;	/* human readable addr+port */
+};
+
+struct nfs4_pnfs_ds {
+	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
+	char			*ds_remotestr;	/* comma sep list of addrs */
+	struct list_head	ds_addrs;
+	struct nfs_client	*ds_clp;
+	atomic_t		ds_count;
+	unsigned long		ds_state;
+#define NFS4DS_CONNECTING	0	/* ds is establishing connection */
 };
 
 struct pnfs_layout_segment {
@@ -53,19 +72,34 @@ struct pnfs_layout_segment {
 enum pnfs_try_status {
 	PNFS_ATTEMPTED     = 0,
 	PNFS_NOT_ATTEMPTED = 1,
+	PNFS_TRY_AGAIN     = 2,
 };
 
 #ifdef CONFIG_NFS_V4_1
 
 #define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4"
 
+/*
+ * Default data server connection timeout and retrans vaules.
+ * Set by module parameters dataserver_timeo and dataserver_retrans.
+ */
+#define NFS4_DEF_DS_TIMEO   600 /* in tenths of a second */
+#define NFS4_DEF_DS_RETRANS 5
+
+/* error codes for internal use */
+#define NFS4ERR_RESET_TO_MDS   12001
+#define NFS4ERR_RESET_TO_PNFS  12002
+
 enum {
 	NFS_LAYOUT_RO_FAILED = 0,	/* get ro layout failed stop trying */
 	NFS_LAYOUT_RW_FAILED,		/* get rw layout failed stop trying */
 	NFS_LAYOUT_BULK_RECALL,		/* bulk recall affecting layout */
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
 	NFS_LAYOUT_RETURN,		/* Return this layout ASAP */
+	NFS_LAYOUT_RETURN_BEFORE_CLOSE,	/* Return this layout before close */
 	NFS_LAYOUT_INVALID_STID,	/* layout stateid id is invalid */
+	NFS_LAYOUT_FIRST_LAYOUTGET,	/* Serialize first layoutget */
+	NFS_LAYOUT_RETRY_LAYOUTGET,	/* Retry layoutget */
 };
 
 enum layoutdriver_policy_flags {
@@ -106,7 +140,8 @@ struct pnfs_layoutdriver_type {
 	struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode);
 	void (*mark_request_commit) (struct nfs_page *req,
 				     struct pnfs_layout_segment *lseg,
-				     struct nfs_commit_info *cinfo);
+				     struct nfs_commit_info *cinfo,
+				     u32 ds_commit_idx);
 	void (*clear_request_commit) (struct nfs_page *req,
 				      struct nfs_commit_info *cinfo);
 	int (*scan_commit_lists) (struct nfs_commit_info *cinfo,
@@ -154,6 +189,7 @@ struct pnfs_layout_hdr {
 	u32			plh_barrier; /* ignore lower seqids */
 	unsigned long		plh_retry_timestamp;
 	unsigned long		plh_flags;
+	enum pnfs_iomode	plh_return_iomode;
 	loff_t			plh_lwb; /* last write byte for layoutcommit */
 	struct rpc_cred		*plh_lc_cred; /* layoutcommit cred */
 	struct inode		*plh_inode;
@@ -185,7 +221,7 @@ extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev,
 				   struct rpc_cred *cred);
 extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags);
-extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
+extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync);
 
 /* pnfs.c */
 void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo);
@@ -198,6 +234,7 @@ void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *
 int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
 void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			        struct nfs_page *req, u64 wb_size);
+void pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *);
 int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
 size_t pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
 			    struct nfs_page *prev, struct nfs_page *req);
@@ -217,6 +254,7 @@ void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
 			     bool update_barrier);
 int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
 				  struct pnfs_layout_hdr *lo,
+				  struct pnfs_layout_range *range,
 				  struct nfs4_state *open_state);
 int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
@@ -233,17 +271,21 @@ int _pnfs_return_layout(struct inode *);
 int pnfs_commit_and_return_layout(struct inode *);
 void pnfs_ld_write_done(struct nfs_pgio_header *);
 void pnfs_ld_read_done(struct nfs_pgio_header *);
+int pnfs_read_resend_pnfs(struct nfs_pgio_header *);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       struct nfs_open_context *ctx,
 					       loff_t pos,
 					       u64 count,
 					       enum pnfs_iomode iomode,
 					       gfp_t gfp_flags);
+void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo);
 
 void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
 int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *);
 int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *);
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
+void pnfs_error_mark_layout_for_return(struct inode *inode,
+				       struct pnfs_layout_segment *lseg);
 
 /* nfs4_deviceid_flags */
 enum {
@@ -275,6 +317,43 @@ void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
 bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
 void nfs4_deviceid_purge_client(const struct nfs_client *);
 
+/* pnfs_nfs.c */
+void pnfs_generic_clear_request_commit(struct nfs_page *req,
+				       struct nfs_commit_info *cinfo);
+void pnfs_generic_commit_release(void *calldata);
+void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data);
+void pnfs_generic_rw_release(void *data);
+void pnfs_generic_recover_commit_reqs(struct list_head *dst,
+				      struct nfs_commit_info *cinfo);
+int pnfs_generic_commit_pagelist(struct inode *inode,
+				 struct list_head *mds_pages,
+				 int how,
+				 struct nfs_commit_info *cinfo,
+				 int (*initiate_commit)(struct nfs_commit_data *data,
+							int how));
+int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max);
+void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
+void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
+struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
+				      gfp_t gfp_flags);
+void nfs4_pnfs_v3_ds_connect_unload(void);
+void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+			  struct nfs4_deviceid_node *devid, unsigned int timeo,
+			  unsigned int retrans, u32 version, u32 minor_version,
+			  rpc_authflavor_t au_flavor);
+struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net,
+						 struct xdr_stream *xdr,
+						 gfp_t gfp_flags);
+void pnfs_layout_mark_request_commit(struct nfs_page *req,
+				     struct pnfs_layout_segment *lseg,
+				     struct nfs_commit_info *cinfo,
+				     u32 ds_commit_idx);
+
+static inline bool nfs_have_layout(struct inode *inode)
+{
+	return NFS_I(inode)->layout != NULL;
+}
+
 static inline struct nfs4_deviceid_node *
 nfs4_get_deviceid(struct nfs4_deviceid_node *d)
 {
@@ -282,6 +361,26 @@ nfs4_get_deviceid(struct nfs4_deviceid_node *d)
 	return d;
 }
 
+static inline void pnfs_set_retry_layoutget(struct pnfs_layout_hdr *lo)
+{
+	if (!test_and_set_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags))
+		atomic_inc(&lo->plh_refcount);
+}
+
+static inline void pnfs_clear_retry_layoutget(struct pnfs_layout_hdr *lo)
+{
+	if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) {
+		atomic_dec(&lo->plh_refcount);
+		/* wake up waiters for LAYOUTRETURN as that is not needed */
+		wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
+	}
+}
+
+static inline bool pnfs_should_retry_layoutget(struct pnfs_layout_hdr *lo)
+{
+	return test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags);
+}
+
 static inline struct pnfs_layout_segment *
 pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
@@ -317,16 +416,22 @@ pnfs_get_ds_info(struct inode *inode)
 	return ld->get_ds_info(inode);
 }
 
+static inline void
+pnfs_generic_mark_devid_invalid(struct nfs4_deviceid_node *node)
+{
+	set_bit(NFS_DEVICEID_INVALID, &node->flags);
+}
+
 static inline bool
 pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			 struct nfs_commit_info *cinfo)
+			 struct nfs_commit_info *cinfo, u32 ds_commit_idx)
 {
 	struct inode *inode = req->wb_context->dentry->d_inode;
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 
 	if (lseg == NULL || ld->mark_request_commit == NULL)
 		return false;
-	ld->mark_request_commit(req, lseg, cinfo);
+	ld->mark_request_commit(req, lseg, cinfo, ds_commit_idx);
 	return true;
 }
 
@@ -352,15 +457,6 @@ pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
 		return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max);
 }
 
-static inline void
-pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
-			 struct nfs_commit_info *cinfo)
-{
-	if (cinfo->ds == NULL || cinfo->ds->nwritten == 0)
-		return;
-	NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
-}
-
 static inline struct nfs_page *
 pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo,
 			struct page *page)
@@ -427,6 +523,11 @@ static inline void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id)
 #endif /* NFS_DEBUG */
 #else  /* CONFIG_NFS_V4_1 */
 
+static inline bool nfs_have_layout(struct inode *inode)
+{
+	return false;
+}
+
 static inline void pnfs_destroy_all_layouts(struct nfs_client *clp)
 {
 }
@@ -513,7 +614,7 @@ pnfs_get_ds_info(struct inode *inode)
 
 static inline bool
 pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			 struct nfs_commit_info *cinfo)
+			 struct nfs_commit_info *cinfo, u32 ds_commit_idx)
 {
 	return false;
 }
@@ -531,12 +632,6 @@ pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
 	return 0;
 }
 
-static inline void
-pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
-			 struct nfs_commit_info *cinfo)
-{
-}
-
 static inline struct nfs_page *
 pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo,
 			struct page *page)
@@ -568,6 +663,10 @@ static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
 	return NULL;
 }
 
+static inline void nfs4_pnfs_v3_ds_connect_unload(void)
+{
+}
+
 #endif /* CONFIG_NFS_V4_1 */
 
 #endif /* FS_NFS_PNFS_H */
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
new file mode 100644
index 000000000000..54e36b38fb5f
--- /dev/null
+++ b/fs/nfs/pnfs_nfs.c
@@ -0,0 +1,870 @@
+/*
+ * Common NFS I/O  operations for the pnfs file based
+ * layout drivers.
+ *
+ * Copyright (c) 2014, Primary Data, Inc. All rights reserved.
+ *
+ * Tom Haynes <loghyr@primarydata.com>
+ */
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/module.h>
+
+#include "nfs4session.h"
+#include "internal.h"
+#include "pnfs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_PNFS
+
+void pnfs_generic_rw_release(void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	nfs_put_client(hdr->ds_clp);
+	hdr->mds_ops->rpc_release(data);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_rw_release);
+
+/* Fake up some data that will cause nfs_commit_release to retry the writes. */
+void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data)
+{
+	struct nfs_page *first = nfs_list_entry(data->pages.next);
+
+	data->task.tk_status = 0;
+	memcpy(&data->verf.verifier, &first->wb_verf,
+	       sizeof(data->verf.verifier));
+	data->verf.verifier.data[0]++; /* ensure verifier mismatch */
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_prepare_to_resend_writes);
+
+void pnfs_generic_write_commit_done(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *wdata = data;
+
+	/* Note this may cause RPC to be resent */
+	wdata->mds_ops->rpc_call_done(task, data);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_write_commit_done);
+
+void pnfs_generic_commit_release(void *calldata)
+{
+	struct nfs_commit_data *data = calldata;
+
+	data->completion_ops->completion(data);
+	pnfs_put_lseg(data->lseg);
+	nfs_put_client(data->ds_clp);
+	nfs_commitdata_release(data);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_commit_release);
+
+/* The generic layer is about to remove the req from the commit list.
+ * If this will make the bucket empty, it will need to put the lseg reference.
+ * Note this must be called holding the inode (/cinfo) lock
+ */
+void
+pnfs_generic_clear_request_commit(struct nfs_page *req,
+				  struct nfs_commit_info *cinfo)
+{
+	struct pnfs_layout_segment *freeme = NULL;
+
+	if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
+		goto out;
+	cinfo->ds->nwritten--;
+	if (list_is_singular(&req->wb_list)) {
+		struct pnfs_commit_bucket *bucket;
+
+		bucket = list_first_entry(&req->wb_list,
+					  struct pnfs_commit_bucket,
+					  written);
+		freeme = bucket->wlseg;
+		bucket->wlseg = NULL;
+	}
+out:
+	nfs_request_remove_commit_list(req, cinfo);
+	pnfs_put_lseg_locked(freeme);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit);
+
+static int
+pnfs_generic_transfer_commit_list(struct list_head *src, struct list_head *dst,
+				  struct nfs_commit_info *cinfo, int max)
+{
+	struct nfs_page *req, *tmp;
+	int ret = 0;
+
+	list_for_each_entry_safe(req, tmp, src, wb_list) {
+		if (!nfs_lock_request(req))
+			continue;
+		kref_get(&req->wb_kref);
+		if (cond_resched_lock(cinfo->lock))
+			list_safe_reset_next(req, tmp, wb_list);
+		nfs_request_remove_commit_list(req, cinfo);
+		clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
+		nfs_list_add_request(req, dst);
+		ret++;
+		if ((ret == max) && !cinfo->dreq)
+			break;
+	}
+	return ret;
+}
+
+static int
+pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
+				 struct nfs_commit_info *cinfo,
+				 int max)
+{
+	struct list_head *src = &bucket->written;
+	struct list_head *dst = &bucket->committing;
+	int ret;
+
+	lockdep_assert_held(cinfo->lock);
+	ret = pnfs_generic_transfer_commit_list(src, dst, cinfo, max);
+	if (ret) {
+		cinfo->ds->nwritten -= ret;
+		cinfo->ds->ncommitting += ret;
+		bucket->clseg = bucket->wlseg;
+		if (list_empty(src))
+			bucket->wlseg = NULL;
+		else
+			pnfs_get_lseg(bucket->clseg);
+	}
+	return ret;
+}
+
+/* Move reqs from written to committing lists, returning count
+ * of number moved.
+ */
+int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo,
+				   int max)
+{
+	int i, rv = 0, cnt;
+
+	lockdep_assert_held(cinfo->lock);
+	for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) {
+		cnt = pnfs_generic_scan_ds_commit_list(&cinfo->ds->buckets[i],
+						       cinfo, max);
+		max -= cnt;
+		rv += cnt;
+	}
+	return rv;
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_scan_commit_lists);
+
+/* Pull everything off the committing lists and dump into @dst.  */
+void pnfs_generic_recover_commit_reqs(struct list_head *dst,
+				      struct nfs_commit_info *cinfo)
+{
+	struct pnfs_commit_bucket *b;
+	struct pnfs_layout_segment *freeme;
+	int i;
+
+	lockdep_assert_held(cinfo->lock);
+restart:
+	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
+		if (pnfs_generic_transfer_commit_list(&b->written, dst,
+						      cinfo, 0)) {
+			freeme = b->wlseg;
+			b->wlseg = NULL;
+			spin_unlock(cinfo->lock);
+			pnfs_put_lseg(freeme);
+			spin_lock(cinfo->lock);
+			goto restart;
+		}
+	}
+	cinfo->ds->nwritten = 0;
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs);
+
+static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
+{
+	struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
+	struct pnfs_commit_bucket *bucket;
+	struct pnfs_layout_segment *freeme;
+	int i;
+
+	for (i = idx; i < fl_cinfo->nbuckets; i++) {
+		bucket = &fl_cinfo->buckets[i];
+		if (list_empty(&bucket->committing))
+			continue;
+		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo, i);
+		spin_lock(cinfo->lock);
+		freeme = bucket->clseg;
+		bucket->clseg = NULL;
+		spin_unlock(cinfo->lock);
+		pnfs_put_lseg(freeme);
+	}
+}
+
+static unsigned int
+pnfs_generic_alloc_ds_commits(struct nfs_commit_info *cinfo,
+			      struct list_head *list)
+{
+	struct pnfs_ds_commit_info *fl_cinfo;
+	struct pnfs_commit_bucket *bucket;
+	struct nfs_commit_data *data;
+	int i;
+	unsigned int nreq = 0;
+
+	fl_cinfo = cinfo->ds;
+	bucket = fl_cinfo->buckets;
+	for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) {
+		if (list_empty(&bucket->committing))
+			continue;
+		data = nfs_commitdata_alloc();
+		if (!data)
+			break;
+		data->ds_commit_index = i;
+		spin_lock(cinfo->lock);
+		data->lseg = bucket->clseg;
+		bucket->clseg = NULL;
+		spin_unlock(cinfo->lock);
+		list_add(&data->pages, list);
+		nreq++;
+	}
+
+	/* Clean up on error */
+	pnfs_generic_retry_commit(cinfo, i);
+	return nreq;
+}
+
+/* This follows nfs_commit_list pretty closely */
+int
+pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
+			     int how, struct nfs_commit_info *cinfo,
+			     int (*initiate_commit)(struct nfs_commit_data *data,
+						    int how))
+{
+	struct nfs_commit_data *data, *tmp;
+	LIST_HEAD(list);
+	unsigned int nreq = 0;
+
+	if (!list_empty(mds_pages)) {
+		data = nfs_commitdata_alloc();
+		if (data != NULL) {
+			data->lseg = NULL;
+			list_add(&data->pages, &list);
+			nreq++;
+		} else {
+			nfs_retry_commit(mds_pages, NULL, cinfo, 0);
+			pnfs_generic_retry_commit(cinfo, 0);
+			cinfo->completion_ops->error_cleanup(NFS_I(inode));
+			return -ENOMEM;
+		}
+	}
+
+	nreq += pnfs_generic_alloc_ds_commits(cinfo, &list);
+
+	if (nreq == 0) {
+		cinfo->completion_ops->error_cleanup(NFS_I(inode));
+		goto out;
+	}
+
+	atomic_add(nreq, &cinfo->mds->rpcs_out);
+
+	list_for_each_entry_safe(data, tmp, &list, pages) {
+		list_del_init(&data->pages);
+		if (!data->lseg) {
+			nfs_init_commit(data, mds_pages, NULL, cinfo);
+			nfs_initiate_commit(NFS_CLIENT(inode), data,
+					    NFS_PROTO(data->inode),
+					    data->mds_ops, how, 0);
+		} else {
+			struct pnfs_commit_bucket *buckets;
+
+			buckets = cinfo->ds->buckets;
+			nfs_init_commit(data,
+					&buckets[data->ds_commit_index].committing,
+					data->lseg,
+					cinfo);
+			initiate_commit(data, how);
+		}
+	}
+out:
+	cinfo->ds->ncommitting = 0;
+	return PNFS_ATTEMPTED;
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist);
+
+/*
+ * Data server cache
+ *
+ * Data servers can be mapped to different device ids.
+ * nfs4_pnfs_ds reference counting
+ *   - set to 1 on allocation
+ *   - incremented when a device id maps a data server already in the cache.
+ *   - decremented when deviceid is removed from the cache.
+ */
+static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
+static LIST_HEAD(nfs4_data_server_cache);
+
+/* Debug routines */
+static void
+print_ds(struct nfs4_pnfs_ds *ds)
+{
+	if (ds == NULL) {
+		printk(KERN_WARNING "%s NULL device\n", __func__);
+		return;
+	}
+	printk(KERN_WARNING "        ds %s\n"
+		"        ref count %d\n"
+		"        client %p\n"
+		"        cl_exchange_flags %x\n",
+		ds->ds_remotestr,
+		atomic_read(&ds->ds_count), ds->ds_clp,
+		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
+}
+
+static bool
+same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
+{
+	struct sockaddr_in *a, *b;
+	struct sockaddr_in6 *a6, *b6;
+
+	if (addr1->sa_family != addr2->sa_family)
+		return false;
+
+	switch (addr1->sa_family) {
+	case AF_INET:
+		a = (struct sockaddr_in *)addr1;
+		b = (struct sockaddr_in *)addr2;
+
+		if (a->sin_addr.s_addr == b->sin_addr.s_addr &&
+		    a->sin_port == b->sin_port)
+			return true;
+		break;
+
+	case AF_INET6:
+		a6 = (struct sockaddr_in6 *)addr1;
+		b6 = (struct sockaddr_in6 *)addr2;
+
+		/* LINKLOCAL addresses must have matching scope_id */
+		if (ipv6_addr_src_scope(&a6->sin6_addr) ==
+		    IPV6_ADDR_SCOPE_LINKLOCAL &&
+		    a6->sin6_scope_id != b6->sin6_scope_id)
+			return false;
+
+		if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) &&
+		    a6->sin6_port == b6->sin6_port)
+			return true;
+		break;
+
+	default:
+		dprintk("%s: unhandled address family: %u\n",
+			__func__, addr1->sa_family);
+		return false;
+	}
+
+	return false;
+}
+
+static bool
+_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
+			       const struct list_head *dsaddrs2)
+{
+	struct nfs4_pnfs_ds_addr *da1, *da2;
+
+	/* step through both lists, comparing as we go */
+	for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
+	     da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
+	     da1 != NULL && da2 != NULL;
+	     da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
+	     da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
+		if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
+				   (struct sockaddr *)&da2->da_addr))
+			return false;
+	}
+	if (da1 == NULL && da2 == NULL)
+		return true;
+
+	return false;
+}
+
+/*
+ * Lookup DS by addresses.  nfs4_ds_cache_lock is held
+ */
+static struct nfs4_pnfs_ds *
+_data_server_lookup_locked(const struct list_head *dsaddrs)
+{
+	struct nfs4_pnfs_ds *ds;
+
+	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
+		if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
+			return ds;
+	return NULL;
+}
+
+static void destroy_ds(struct nfs4_pnfs_ds *ds)
+{
+	struct nfs4_pnfs_ds_addr *da;
+
+	dprintk("--> %s\n", __func__);
+	ifdebug(FACILITY)
+		print_ds(ds);
+
+	nfs_put_client(ds->ds_clp);
+
+	while (!list_empty(&ds->ds_addrs)) {
+		da = list_first_entry(&ds->ds_addrs,
+				      struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+
+	kfree(ds->ds_remotestr);
+	kfree(ds);
+}
+
+void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds)
+{
+	if (atomic_dec_and_lock(&ds->ds_count,
+				&nfs4_ds_cache_lock)) {
+		list_del_init(&ds->ds_node);
+		spin_unlock(&nfs4_ds_cache_lock);
+		destroy_ds(ds);
+	}
+}
+EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_put);
+
+/*
+ * Create a string with a human readable address and port to avoid
+ * complicated setup around many dprinks.
+ */
+static char *
+nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
+{
+	struct nfs4_pnfs_ds_addr *da;
+	char *remotestr;
+	size_t len;
+	char *p;
+
+	len = 3;        /* '{', '}' and eol */
+	list_for_each_entry(da, dsaddrs, da_node) {
+		len += strlen(da->da_remotestr) + 1;    /* string plus comma */
+	}
+
+	remotestr = kzalloc(len, gfp_flags);
+	if (!remotestr)
+		return NULL;
+
+	p = remotestr;
+	*(p++) = '{';
+	len--;
+	list_for_each_entry(da, dsaddrs, da_node) {
+		size_t ll = strlen(da->da_remotestr);
+
+		if (ll > len)
+			goto out_err;
+
+		memcpy(p, da->da_remotestr, ll);
+		p += ll;
+		len -= ll;
+
+		if (len < 1)
+			goto out_err;
+		(*p++) = ',';
+		len--;
+	}
+	if (len < 2)
+		goto out_err;
+	*(p++) = '}';
+	*p = '\0';
+	return remotestr;
+out_err:
+	kfree(remotestr);
+	return NULL;
+}
+
+/*
+ * Given a list of multipath struct nfs4_pnfs_ds_addr, add it to ds cache if
+ * uncached and return cached struct nfs4_pnfs_ds.
+ */
+struct nfs4_pnfs_ds *
+nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
+{
+	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
+	char *remotestr;
+
+	if (list_empty(dsaddrs)) {
+		dprintk("%s: no addresses defined\n", __func__);
+		goto out;
+	}
+
+	ds = kzalloc(sizeof(*ds), gfp_flags);
+	if (!ds)
+		goto out;
+
+	/* this is only used for debugging, so it's ok if its NULL */
+	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
+
+	spin_lock(&nfs4_ds_cache_lock);
+	tmp_ds = _data_server_lookup_locked(dsaddrs);
+	if (tmp_ds == NULL) {
+		INIT_LIST_HEAD(&ds->ds_addrs);
+		list_splice_init(dsaddrs, &ds->ds_addrs);
+		ds->ds_remotestr = remotestr;
+		atomic_set(&ds->ds_count, 1);
+		INIT_LIST_HEAD(&ds->ds_node);
+		ds->ds_clp = NULL;
+		list_add(&ds->ds_node, &nfs4_data_server_cache);
+		dprintk("%s add new data server %s\n", __func__,
+			ds->ds_remotestr);
+	} else {
+		kfree(remotestr);
+		kfree(ds);
+		atomic_inc(&tmp_ds->ds_count);
+		dprintk("%s data server %s found, inc'ed ds_count to %d\n",
+			__func__, tmp_ds->ds_remotestr,
+			atomic_read(&tmp_ds->ds_count));
+		ds = tmp_ds;
+	}
+	spin_unlock(&nfs4_ds_cache_lock);
+out:
+	return ds;
+}
+EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_add);
+
+static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
+{
+	might_sleep();
+	wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING,
+			TASK_KILLABLE);
+}
+
+static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
+{
+	smp_mb__before_atomic();
+	clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
+	smp_mb__after_atomic();
+	wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
+}
+
+static struct nfs_client *(*get_v3_ds_connect)(
+			struct nfs_client *mds_clp,
+			const struct sockaddr *ds_addr,
+			int ds_addrlen,
+			int ds_proto,
+			unsigned int ds_timeo,
+			unsigned int ds_retrans,
+			rpc_authflavor_t au_flavor);
+
+static bool load_v3_ds_connect(void)
+{
+	if (!get_v3_ds_connect) {
+		get_v3_ds_connect = symbol_request(nfs3_set_ds_client);
+		WARN_ON_ONCE(!get_v3_ds_connect);
+	}
+
+	return(get_v3_ds_connect != NULL);
+}
+
+void __exit nfs4_pnfs_v3_ds_connect_unload(void)
+{
+	if (get_v3_ds_connect) {
+		symbol_put(nfs3_set_ds_client);
+		get_v3_ds_connect = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(nfs4_pnfs_v3_ds_connect_unload);
+
+static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
+				 struct nfs4_pnfs_ds *ds,
+				 unsigned int timeo,
+				 unsigned int retrans,
+				 rpc_authflavor_t au_flavor)
+{
+	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs4_pnfs_ds_addr *da;
+	int status = 0;
+
+	dprintk("--> %s DS %s au_flavor %d\n", __func__,
+		ds->ds_remotestr, au_flavor);
+
+	if (!load_v3_ds_connect())
+		goto out;
+
+	list_for_each_entry(da, &ds->ds_addrs, da_node) {
+		dprintk("%s: DS %s: trying address %s\n",
+			__func__, ds->ds_remotestr, da->da_remotestr);
+
+		clp = get_v3_ds_connect(mds_srv->nfs_client,
+					(struct sockaddr *)&da->da_addr,
+					da->da_addrlen, IPPROTO_TCP,
+					timeo, retrans, au_flavor);
+		if (!IS_ERR(clp))
+			break;
+	}
+
+	if (IS_ERR(clp)) {
+		status = PTR_ERR(clp);
+		goto out;
+	}
+
+	smp_wmb();
+	ds->ds_clp = clp;
+	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
+out:
+	return status;
+}
+
+static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
+				 struct nfs4_pnfs_ds *ds,
+				 unsigned int timeo,
+				 unsigned int retrans,
+				 u32 minor_version,
+				 rpc_authflavor_t au_flavor)
+{
+	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs4_pnfs_ds_addr *da;
+	int status = 0;
+
+	dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
+		au_flavor);
+
+	list_for_each_entry(da, &ds->ds_addrs, da_node) {
+		dprintk("%s: DS %s: trying address %s\n",
+			__func__, ds->ds_remotestr, da->da_remotestr);
+
+		clp = nfs4_set_ds_client(mds_srv->nfs_client,
+					(struct sockaddr *)&da->da_addr,
+					da->da_addrlen, IPPROTO_TCP,
+					timeo, retrans, minor_version,
+					au_flavor);
+		if (!IS_ERR(clp))
+			break;
+	}
+
+	if (IS_ERR(clp)) {
+		status = PTR_ERR(clp);
+		goto out;
+	}
+
+	status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time);
+	if (status)
+		goto out_put;
+
+	smp_wmb();
+	ds->ds_clp = clp;
+	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
+out:
+	return status;
+out_put:
+	nfs_put_client(clp);
+	goto out;
+}
+
+/*
+ * Create an rpc connection to the nfs4_pnfs_ds data server.
+ * Currently only supports IPv4 and IPv6 addresses.
+ * If connection fails, make devid unavailable.
+ */
+void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+			  struct nfs4_deviceid_node *devid, unsigned int timeo,
+			  unsigned int retrans, u32 version,
+			  u32 minor_version, rpc_authflavor_t au_flavor)
+{
+	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
+		int err = 0;
+
+		if (version == 3) {
+			err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo,
+						       retrans, au_flavor);
+		} else if (version == 4) {
+			err = _nfs4_pnfs_v4_ds_connect(mds_srv, ds, timeo,
+						       retrans, minor_version,
+						       au_flavor);
+		} else {
+			dprintk("%s: unsupported DS version %d\n", __func__,
+				version);
+			err = -EPROTONOSUPPORT;
+		}
+
+		if (err)
+			nfs4_mark_deviceid_unavailable(devid);
+		nfs4_clear_ds_conn_bit(ds);
+	} else {
+		nfs4_wait_ds_connect(ds);
+	}
+}
+EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect);
+
+/*
+ * Currently only supports ipv4, ipv6 and one multi-path address.
+ */
+struct nfs4_pnfs_ds_addr *
+nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags)
+{
+	struct nfs4_pnfs_ds_addr *da = NULL;
+	char *buf, *portstr;
+	__be16 port;
+	int nlen, rlen;
+	int tmp[2];
+	__be32 *p;
+	char *netid, *match_netid;
+	size_t len, match_netid_len;
+	char *startsep = "";
+	char *endsep = "";
+
+
+	/* r_netid */
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_err;
+	nlen = be32_to_cpup(p++);
+
+	p = xdr_inline_decode(xdr, nlen);
+	if (unlikely(!p))
+		goto out_err;
+
+	netid = kmalloc(nlen+1, gfp_flags);
+	if (unlikely(!netid))
+		goto out_err;
+
+	netid[nlen] = '\0';
+	memcpy(netid, p, nlen);
+
+	/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_free_netid;
+	rlen = be32_to_cpup(p);
+
+	p = xdr_inline_decode(xdr, rlen);
+	if (unlikely(!p))
+		goto out_free_netid;
+
+	/* port is ".ABC.DEF", 8 chars max */
+	if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) {
+		dprintk("%s: Invalid address, length %d\n", __func__,
+			rlen);
+		goto out_free_netid;
+	}
+	buf = kmalloc(rlen + 1, gfp_flags);
+	if (!buf) {
+		dprintk("%s: Not enough memory\n", __func__);
+		goto out_free_netid;
+	}
+	buf[rlen] = '\0';
+	memcpy(buf, p, rlen);
+
+	/* replace port '.' with '-' */
+	portstr = strrchr(buf, '.');
+	if (!portstr) {
+		dprintk("%s: Failed finding expected dot in port\n",
+			__func__);
+		goto out_free_buf;
+	}
+	*portstr = '-';
+
+	/* find '.' between address and port */
+	portstr = strrchr(buf, '.');
+	if (!portstr) {
+		dprintk("%s: Failed finding expected dot between address and "
+			"port\n", __func__);
+		goto out_free_buf;
+	}
+	*portstr = '\0';
+
+	da = kzalloc(sizeof(*da), gfp_flags);
+	if (unlikely(!da))
+		goto out_free_buf;
+
+	INIT_LIST_HEAD(&da->da_node);
+
+	if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
+		      sizeof(da->da_addr))) {
+		dprintk("%s: error parsing address %s\n", __func__, buf);
+		goto out_free_da;
+	}
+
+	portstr++;
+	sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]);
+	port = htons((tmp[0] << 8) | (tmp[1]));
+
+	switch (da->da_addr.ss_family) {
+	case AF_INET:
+		((struct sockaddr_in *)&da->da_addr)->sin_port = port;
+		da->da_addrlen = sizeof(struct sockaddr_in);
+		match_netid = "tcp";
+		match_netid_len = 3;
+		break;
+
+	case AF_INET6:
+		((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port;
+		da->da_addrlen = sizeof(struct sockaddr_in6);
+		match_netid = "tcp6";
+		match_netid_len = 4;
+		startsep = "[";
+		endsep = "]";
+		break;
+
+	default:
+		dprintk("%s: unsupported address family: %u\n",
+			__func__, da->da_addr.ss_family);
+		goto out_free_da;
+	}
+
+	if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) {
+		dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n",
+			__func__, netid, match_netid);
+		goto out_free_da;
+	}
+
+	/* save human readable address */
+	len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7;
+	da->da_remotestr = kzalloc(len, gfp_flags);
+
+	/* NULL is ok, only used for dprintk */
+	if (da->da_remotestr)
+		snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep,
+			 buf, endsep, ntohs(port));
+
+	dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr);
+	kfree(buf);
+	kfree(netid);
+	return da;
+
+out_free_da:
+	kfree(da);
+out_free_buf:
+	dprintk("%s: Error parsing DS addr: %s\n", __func__, buf);
+	kfree(buf);
+out_free_netid:
+	kfree(netid);
+out_err:
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(nfs4_decode_mp_ds_addr);
+
+void
+pnfs_layout_mark_request_commit(struct nfs_page *req,
+				struct pnfs_layout_segment *lseg,
+				struct nfs_commit_info *cinfo,
+				u32 ds_commit_idx)
+{
+	struct list_head *list;
+	struct pnfs_commit_bucket *buckets;
+
+	spin_lock(cinfo->lock);
+	buckets = cinfo->ds->buckets;
+	list = &buckets[ds_commit_idx].written;
+	if (list_empty(list)) {
+		/* Non-empty buckets hold a reference on the lseg.  That ref
+		 * is normally transferred to the COMMIT call and released
+		 * there.  It could also be released if the last req is pulled
+		 * off due to a rewrite, in which case it will be done in
+		 * pnfs_common_clear_request_commit
+		 */
+		WARN_ON_ONCE(buckets[ds_commit_idx].wlseg != NULL);
+		buckets[ds_commit_idx].wlseg = pnfs_get_lseg(lseg);
+	}
+	set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
+	cinfo->ds->nwritten++;
+	spin_unlock(cinfo->lock);
+
+	nfs_request_add_commit_list(req, list, cinfo);
+}
+EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit);
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index b09cc23d6f43..c63189acd052 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -139,7 +139,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	nfs_fattr_init(fattr);
 	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	if (status == 0)
-		nfs_setattr_update_inode(inode, sattr);
+		nfs_setattr_update_inode(inode, sattr, fattr);
 	dprintk("NFS reply setattr: %d\n", status);
 	return status;
 }
@@ -609,10 +609,8 @@ static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task,
 
 static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	struct inode *inode = hdr->inode;
-
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(inode, hdr->res.fattr);
+		nfs_writeback_update_inode(hdr);
 	return 0;
 }
 
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index c91a4799c562..568ecf0a880f 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -70,8 +70,15 @@ EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
 
 void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 {
+	struct nfs_pgio_mirror *mirror;
+
 	pgio->pg_ops = &nfs_pgio_rw_ops;
-	pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
+
+	/* read path should never have more than one mirror */
+	WARN_ON_ONCE(pgio->pg_mirror_count != 1);
+
+	mirror = &pgio->pg_mirrors[0];
+	mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
 
@@ -81,6 +88,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 	struct nfs_page	*new;
 	unsigned int len;
 	struct nfs_pageio_descriptor pgio;
+	struct nfs_pgio_mirror *pgm;
 
 	len = nfs_page_length(page);
 	if (len == 0)
@@ -97,7 +105,13 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 			     &nfs_async_read_completion_ops);
 	nfs_pageio_add_request(&pgio, new);
 	nfs_pageio_complete(&pgio);
-	NFS_I(inode)->read_io += pgio.pg_bytes_written;
+
+	/* It doesn't make sense to do mirrored reads! */
+	WARN_ON_ONCE(pgio.pg_mirror_count != 1);
+
+	pgm = &pgio.pg_mirrors[0];
+	NFS_I(inode)->read_io += pgm->pg_bytes_written;
+
 	return 0;
 }
 
@@ -168,13 +182,14 @@ out:
 
 static void nfs_initiate_read(struct nfs_pgio_header *hdr,
 			      struct rpc_message *msg,
+			      const struct nfs_rpc_ops *rpc_ops,
 			      struct rpc_task_setup *task_setup_data, int how)
 {
 	struct inode *inode = hdr->inode;
 	int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
 
 	task_setup_data->flags |= swap_flags;
-	NFS_PROTO(inode)->read_setup(hdr, msg);
+	rpc_ops->read_setup(hdr, msg);
 }
 
 static void
@@ -351,6 +366,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 		struct list_head *pages, unsigned nr_pages)
 {
 	struct nfs_pageio_descriptor pgio;
+	struct nfs_pgio_mirror *pgm;
 	struct nfs_readdesc desc = {
 		.pgio = &pgio,
 	};
@@ -386,10 +402,15 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 			     &nfs_async_read_completion_ops);
 
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
-
 	nfs_pageio_complete(&pgio);
-	NFS_I(inode)->read_io += pgio.pg_bytes_written;
-	npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+	/* It doesn't make sense to do mirrored reads! */
+	WARN_ON_ONCE(pgio.pg_mirror_count != 1);
+
+	pgm = &pgio.pg_mirrors[0];
+	NFS_I(inode)->read_io += pgm->pg_bytes_written;
+	npages = (pgm->pg_bytes_written + PAGE_CACHE_SIZE - 1) >>
+		 PAGE_CACHE_SHIFT;
 	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
 read_complete:
 	put_nfs_open_context(desc.ctx);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 31a11b0e885d..322b2de02988 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -311,7 +311,6 @@ const struct super_operations nfs_sops = {
 	.destroy_inode	= nfs_destroy_inode,
 	.write_inode	= nfs_write_inode,
 	.drop_inode	= nfs_drop_inode,
-	.put_super	= nfs_put_super,
 	.statfs		= nfs_statfs,
 	.evict_inode	= nfs_evict_inode,
 	.umount_begin	= nfs_umount_begin,
@@ -405,12 +404,15 @@ void __exit unregister_nfs_fs(void)
 	unregister_filesystem(&nfs_fs_type);
 }
 
-void nfs_sb_active(struct super_block *sb)
+bool nfs_sb_active(struct super_block *sb)
 {
 	struct nfs_server *server = NFS_SB(sb);
 
-	if (atomic_inc_return(&server->active) == 1)
-		atomic_inc(&sb->s_active);
+	if (!atomic_inc_not_zero(&sb->s_active))
+		return false;
+	if (atomic_inc_return(&server->active) != 1)
+		atomic_dec(&sb->s_active);
+	return true;
 }
 EXPORT_SYMBOL_GPL(nfs_sb_active);
 
@@ -2569,7 +2571,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
 		error = nfs_bdi_register(server);
 		if (error) {
 			mntroot = ERR_PTR(error);
-			goto error_splat_bdi;
+			goto error_splat_super;
 		}
 		server->super = s;
 	}
@@ -2601,9 +2603,6 @@ error_splat_root:
 	dput(mntroot);
 	mntroot = ERR_PTR(error);
 error_splat_super:
-	if (server && !s->s_root)
-		bdi_unregister(&server->backing_dev_info);
-error_splat_bdi:
 	deactivate_locked_super(s);
 	goto out;
 }
@@ -2651,27 +2650,19 @@ out:
 EXPORT_SYMBOL_GPL(nfs_fs_mount);
 
 /*
- * Ensure that we unregister the bdi before kill_anon_super
- * releases the device name
- */
-void nfs_put_super(struct super_block *s)
-{
-	struct nfs_server *server = NFS_SB(s);
-
-	bdi_unregister(&server->backing_dev_info);
-}
-EXPORT_SYMBOL_GPL(nfs_put_super);
-
-/*
  * Destroy an NFS2/3 superblock
  */
 void nfs_kill_super(struct super_block *s)
 {
 	struct nfs_server *server = NFS_SB(s);
+	dev_t dev = s->s_dev;
+
+	generic_shutdown_super(s);
 
-	kill_anon_super(s);
 	nfs_fscache_release_super_cookie(s);
+
 	nfs_free_server(server);
+	free_anon_bdev(dev);
 }
 EXPORT_SYMBOL_GPL(nfs_kill_super);
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index af3af685a9e3..849ed784d6ac 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -473,13 +473,18 @@ try_again:
 	do {
 		/*
 		 * Subrequests are always contiguous, non overlapping
-		 * and in order. If not, it's a programming error.
+		 * and in order - but may be repeated (mirrored writes).
 		 */
-		WARN_ON_ONCE(subreq->wb_offset !=
-		     (head->wb_offset + total_bytes));
-
-		/* keep track of how many bytes this group covers */
-		total_bytes += subreq->wb_bytes;
+		if (subreq->wb_offset == (head->wb_offset + total_bytes)) {
+			/* keep track of how many bytes this group covers */
+			total_bytes += subreq->wb_bytes;
+		} else if (WARN_ON_ONCE(subreq->wb_offset < head->wb_offset ||
+			    ((subreq->wb_offset + subreq->wb_bytes) >
+			     (head->wb_offset + total_bytes)))) {
+			nfs_page_group_unlock(head);
+			spin_unlock(&inode->i_lock);
+			return ERR_PTR(-EIO);
+		}
 
 		if (!nfs_lock_request(subreq)) {
 			/* releases page group bit lock and
@@ -784,13 +789,8 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
 	nfs_list_add_request(req, dst);
 	cinfo->mds->ncommit++;
 	spin_unlock(cinfo->lock);
-	if (!cinfo->dreq) {
-		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
-			     BDI_RECLAIMABLE);
-		__mark_inode_dirty(req->wb_context->dentry->d_inode,
-				   I_DIRTY_DATASYNC);
-	}
+	if (!cinfo->dreq)
+		nfs_mark_page_unstable(req->wb_page);
 }
 EXPORT_SYMBOL_GPL(nfs_request_add_commit_list);
 
@@ -842,9 +842,9 @@ EXPORT_SYMBOL_GPL(nfs_init_cinfo);
  */
 void
 nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			struct nfs_commit_info *cinfo)
+			struct nfs_commit_info *cinfo, u32 ds_commit_idx)
 {
-	if (pnfs_mark_request_commit(req, lseg, cinfo))
+	if (pnfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx))
 		return;
 	nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo);
 }
@@ -853,7 +853,7 @@ static void
 nfs_clear_page_commit(struct page *page)
 {
 	dec_zone_page_state(page, NR_UNSTABLE_NFS);
-	dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE);
+	dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE);
 }
 
 /* Called holding inode (/cinfo) lock */
@@ -900,7 +900,8 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
 		}
 		if (nfs_write_need_commit(hdr)) {
 			memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf));
-			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+			nfs_mark_request_commit(req, hdr->lseg, &cinfo,
+				hdr->pgio_mirror_idx);
 			goto next;
 		}
 remove_req:
@@ -1091,6 +1092,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct nfs_lock_context *l_ctx;
+	struct file_lock_context *flctx = file_inode(file)->i_flctx;
 	struct nfs_page	*req;
 	int do_flush, status;
 	/*
@@ -1109,7 +1111,9 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 		do_flush = req->wb_page != page || req->wb_context != ctx;
 		/* for now, flush if more than 1 request in page_group */
 		do_flush |= req->wb_this_page != req;
-		if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) {
+		if (l_ctx && flctx &&
+		    !(list_empty_careful(&flctx->flc_posix) &&
+		      list_empty_careful(&flctx->flc_flock))) {
 			do_flush |= l_ctx->lockowner.l_owner != current->files
 				|| l_ctx->lockowner.l_pid != current->tgid;
 		}
@@ -1170,6 +1174,13 @@ out:
 	return PageUptodate(page) != 0;
 }
 
+static bool
+is_whole_file_wrlock(struct file_lock *fl)
+{
+	return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX &&
+			fl->fl_type == F_WRLCK;
+}
+
 /* If we know the page is up to date, and we're not using byte range locks (or
  * if we have the whole file locked for writing), it may be more efficient to
  * extend the write to cover the entire page in order to avoid fragmentation
@@ -1180,17 +1191,36 @@ out:
  */
 static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode)
 {
+	int ret;
+	struct file_lock_context *flctx = inode->i_flctx;
+	struct file_lock *fl;
+
 	if (file->f_flags & O_DSYNC)
 		return 0;
 	if (!nfs_write_pageuptodate(page, inode))
 		return 0;
 	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		return 1;
-	if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 &&
-			inode->i_flock->fl_end == OFFSET_MAX &&
-			inode->i_flock->fl_type != F_RDLCK))
-		return 1;
-	return 0;
+	if (!flctx || (list_empty_careful(&flctx->flc_flock) &&
+		       list_empty_careful(&flctx->flc_posix)))
+		return 0;
+
+	/* Check to see if there are whole file write locks */
+	ret = 0;
+	spin_lock(&flctx->flc_lock);
+	if (!list_empty(&flctx->flc_posix)) {
+		fl = list_first_entry(&flctx->flc_posix, struct file_lock,
+					fl_list);
+		if (is_whole_file_wrlock(fl))
+			ret = 1;
+	} else if (!list_empty(&flctx->flc_flock)) {
+		fl = list_first_entry(&flctx->flc_flock, struct file_lock,
+					fl_list);
+		if (fl->fl_type == F_WRLCK)
+			ret = 1;
+	}
+	spin_unlock(&flctx->flc_lock);
+	return ret;
 }
 
 /*
@@ -1240,15 +1270,15 @@ static int flush_task_priority(int how)
 
 static void nfs_initiate_write(struct nfs_pgio_header *hdr,
 			       struct rpc_message *msg,
+			       const struct nfs_rpc_ops *rpc_ops,
 			       struct rpc_task_setup *task_setup_data, int how)
 {
-	struct inode *inode = hdr->inode;
 	int priority = flush_task_priority(how);
 
 	task_setup_data->priority = priority;
-	NFS_PROTO(inode)->write_setup(hdr, msg);
+	rpc_ops->write_setup(hdr, msg);
 
-	nfs4_state_protect_write(NFS_SERVER(inode)->nfs_client,
+	nfs4_state_protect_write(NFS_SERVER(hdr->inode)->nfs_client,
 				 &task_setup_data->rpc_client, msg, hdr);
 }
 
@@ -1298,8 +1328,14 @@ EXPORT_SYMBOL_GPL(nfs_pageio_init_write);
 
 void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 {
+	struct nfs_pgio_mirror *mirror;
+
 	pgio->pg_ops = &nfs_pgio_rw_ops;
-	pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize;
+
+	nfs_pageio_stop_mirroring(pgio);
+
+	mirror = &pgio->pg_mirrors[0];
+	mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize;
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
 
@@ -1341,6 +1377,36 @@ static int nfs_should_remove_suid(const struct inode *inode)
 	return 0;
 }
 
+static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr,
+		struct nfs_fattr *fattr)
+{
+	struct nfs_pgio_args *argp = &hdr->args;
+	struct nfs_pgio_res *resp = &hdr->res;
+
+	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
+		return;
+	if (argp->offset + resp->count != fattr->size)
+		return;
+	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode))
+		return;
+	/* Set attribute barrier */
+	nfs_fattr_set_barrier(fattr);
+}
+
+void nfs_writeback_update_inode(struct nfs_pgio_header *hdr)
+{
+	struct nfs_fattr *fattr = hdr->res.fattr;
+	struct inode *inode = hdr->inode;
+
+	if (fattr == NULL)
+		return;
+	spin_lock(&inode->i_lock);
+	nfs_writeback_check_extend(hdr, fattr);
+	nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
+	spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL_GPL(nfs_writeback_update_inode);
+
 /*
  * This function is called when the WRITE call is complete.
  */
@@ -1465,6 +1531,7 @@ void nfs_commitdata_release(struct nfs_commit_data *data)
 EXPORT_SYMBOL_GPL(nfs_commitdata_release);
 
 int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
+			const struct nfs_rpc_ops *nfs_ops,
 			const struct rpc_call_ops *call_ops,
 			int how, int flags)
 {
@@ -1486,7 +1553,7 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 		.priority = priority,
 	};
 	/* Set up the initial task struct.  */
-	NFS_PROTO(data->inode)->commit_setup(data, &msg);
+	nfs_ops->commit_setup(data, &msg);
 
 	dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid);
 
@@ -1554,19 +1621,17 @@ EXPORT_SYMBOL_GPL(nfs_init_commit);
 
 void nfs_retry_commit(struct list_head *page_list,
 		      struct pnfs_layout_segment *lseg,
-		      struct nfs_commit_info *cinfo)
+		      struct nfs_commit_info *cinfo,
+		      u32 ds_commit_idx)
 {
 	struct nfs_page *req;
 
 	while (!list_empty(page_list)) {
 		req = nfs_list_entry(page_list->next);
 		nfs_list_remove_request(req);
-		nfs_mark_request_commit(req, lseg, cinfo);
-		if (!cinfo->dreq) {
-			dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-			dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
-				     BDI_RECLAIMABLE);
-		}
+		nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx);
+		if (!cinfo->dreq)
+			nfs_clear_page_commit(req->wb_page);
 		nfs_unlock_and_release_request(req);
 	}
 }
@@ -1589,10 +1654,10 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 	/* Set up the argument struct */
 	nfs_init_commit(data, head, NULL, cinfo);
 	atomic_inc(&cinfo->mds->rpcs_out);
-	return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops,
-				   how, 0);
+	return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
+				   data->mds_ops, how, 0);
  out_bad:
-	nfs_retry_commit(head, NULL, cinfo);
+	nfs_retry_commit(head, NULL, cinfo, 0);
 	cinfo->completion_ops->error_cleanup(NFS_I(inode));
 	return -ENOMEM;
 }
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 73395156bdb4..683bf718aead 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -82,6 +82,16 @@ config NFSD_V4
 
 	  If unsure, say N.
 
+config NFSD_PNFS
+	bool "NFSv4.1 server support for Parallel NFS (pNFS)"
+	depends on NFSD_V4
+	help
+	  This option enables support for the parallel NFS features of the
+	  minor version 1 of the NFSv4 protocol (RFC5661) in the kernel's NFS
+	  server.
+
+	  If unsure, say N.
+
 config NFSD_V4_SECURITY_LABEL
 	bool "Provide Security Label support for NFSv4 server"
 	depends on NFSD_V4 && SECURITY
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index af32ef06b4fe..9a6028e120c6 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -2,9 +2,14 @@
 # Makefile for the Linux nfs server
 #
 
+ccflags-y += -I$(src)			# needed for trace events
+
 obj-$(CONFIG_NFSD)	+= nfsd.o
 
-nfsd-y 			:= nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
+# this one should be compiled first, as the tracing macros can easily blow up
+nfsd-y			+= trace.o
+
+nfsd-y 			+= nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
 			   export.o auth.o lockd.o nfscache.o nfsxdr.o stats.o
 nfsd-$(CONFIG_NFSD_FAULT_INJECTION) += fault_inject.o
 nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o
@@ -12,3 +17,4 @@ nfsd-$(CONFIG_NFSD_V3)	+= nfs3proc.o nfs3xdr.o
 nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
 nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
 			   nfs4acl.o nfs4callback.o nfs4recover.o
+nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o blocklayout.o blocklayoutxdr.o
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
new file mode 100644
index 000000000000..cdbc78c72542
--- /dev/null
+++ b/fs/nfsd/blocklayout.c
@@ -0,0 +1,189 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/exportfs.h>
+#include <linux/genhd.h>
+#include <linux/slab.h>
+
+#include <linux/nfsd/debug.h>
+
+#include "blocklayoutxdr.h"
+#include "pnfs.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+
+static int
+nfsd4_block_get_device_info_simple(struct super_block *sb,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev;
+	struct pnfs_block_volume *b;
+
+	dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
+		      sizeof(struct pnfs_block_volume), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+	gdp->gd_device = dev;
+
+	dev->nr_volumes = 1;
+	b = &dev->volumes[0];
+
+	b->type = PNFS_BLOCK_VOLUME_SIMPLE;
+	b->simple.sig_len = PNFS_BLOCK_UUID_LEN;
+	return sb->s_export_op->get_uuid(sb, b->simple.sig, &b->simple.sig_len,
+			&b->simple.offset);
+}
+
+static __be32
+nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	if (sb->s_bdev != sb->s_bdev->bd_contains)
+		return nfserr_inval;
+	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
+}
+
+static __be32
+nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
+		struct nfsd4_layoutget *args)
+{
+	struct nfsd4_layout_seg *seg = &args->lg_seg;
+	struct super_block *sb = inode->i_sb;
+	u32 block_size = (1 << inode->i_blkbits);
+	struct pnfs_block_extent *bex;
+	struct iomap iomap;
+	u32 device_generation = 0;
+	int error;
+
+	/*
+	 * We do not attempt to support I/O smaller than the fs block size,
+	 * or not aligned to it.
+	 */
+	if (args->lg_minlength < block_size) {
+		dprintk("pnfsd: I/O too small\n");
+		goto out_layoutunavailable;
+	}
+	if (seg->offset & (block_size - 1)) {
+		dprintk("pnfsd: I/O misaligned\n");
+		goto out_layoutunavailable;
+	}
+
+	/*
+	 * Some clients barf on non-zero block numbers for NONE or INVALID
+	 * layouts, so make sure to zero the whole structure.
+	 */
+	error = -ENOMEM;
+	bex = kzalloc(sizeof(*bex), GFP_KERNEL);
+	if (!bex)
+		goto out_error;
+	args->lg_content = bex;
+
+	error = sb->s_export_op->map_blocks(inode, seg->offset, seg->length,
+					    &iomap, seg->iomode != IOMODE_READ,
+					    &device_generation);
+	if (error) {
+		if (error == -ENXIO)
+			goto out_layoutunavailable;
+		goto out_error;
+	}
+
+	if (iomap.length < args->lg_minlength) {
+		dprintk("pnfsd: extent smaller than minlength\n");
+		goto out_layoutunavailable;
+	}
+
+	switch (iomap.type) {
+	case IOMAP_MAPPED:
+		if (seg->iomode == IOMODE_READ)
+			bex->es = PNFS_BLOCK_READ_DATA;
+		else
+			bex->es = PNFS_BLOCK_READWRITE_DATA;
+		bex->soff = (iomap.blkno << 9);
+		break;
+	case IOMAP_UNWRITTEN:
+		if (seg->iomode & IOMODE_RW) {
+			/*
+			 * Crack monkey special case from section 2.3.1.
+			 */
+			if (args->lg_minlength == 0) {
+				dprintk("pnfsd: no soup for you!\n");
+				goto out_layoutunavailable;
+			}
+
+			bex->es = PNFS_BLOCK_INVALID_DATA;
+			bex->soff = (iomap.blkno << 9);
+			break;
+		}
+		/*FALLTHRU*/
+	case IOMAP_HOLE:
+		if (seg->iomode == IOMODE_READ) {
+			bex->es = PNFS_BLOCK_NONE_DATA;
+			break;
+		}
+		/*FALLTHRU*/
+	case IOMAP_DELALLOC:
+	default:
+		WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type);
+		goto out_layoutunavailable;
+	}
+
+	error = nfsd4_set_deviceid(&bex->vol_id, fhp, device_generation);
+	if (error)
+		goto out_error;
+	bex->foff = iomap.offset;
+	bex->len = iomap.length;
+
+	seg->offset = iomap.offset;
+	seg->length = iomap.length;
+
+	dprintk("GET: %lld:%lld %d\n", bex->foff, bex->len, bex->es);
+	return 0;
+
+out_error:
+	seg->length = 0;
+	return nfserrno(error);
+out_layoutunavailable:
+	seg->length = 0;
+	return nfserr_layoutunavailable;
+}
+
+static __be32
+nfsd4_block_proc_layoutcommit(struct inode *inode,
+		struct nfsd4_layoutcommit *lcp)
+{
+	loff_t new_size = lcp->lc_last_wr + 1;
+	struct iattr iattr = { .ia_valid = 0 };
+	struct iomap *iomaps;
+	int nr_iomaps;
+	int error;
+
+	nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
+			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+	if (nr_iomaps < 0)
+		return nfserrno(nr_iomaps);
+
+	if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
+	    timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
+		lcp->lc_mtime = current_fs_time(inode->i_sb);
+	iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
+	iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
+
+	if (new_size > i_size_read(inode)) {
+		iattr.ia_valid |= ATTR_SIZE;
+		iattr.ia_size = new_size;
+	}
+
+	error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps,
+			nr_iomaps, &iattr);
+	kfree(iomaps);
+	return nfserrno(error);
+}
+
+const struct nfsd4_layout_ops bl_layout_ops = {
+	.proc_getdeviceinfo	= nfsd4_block_proc_getdeviceinfo,
+	.encode_getdeviceinfo	= nfsd4_block_encode_getdeviceinfo,
+	.proc_layoutget		= nfsd4_block_proc_layoutget,
+	.encode_layoutget	= nfsd4_block_encode_layoutget,
+	.proc_layoutcommit	= nfsd4_block_proc_layoutcommit,
+};
diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c
new file mode 100644
index 000000000000..9da89fddab33
--- /dev/null
+++ b/fs/nfsd/blocklayoutxdr.c
@@ -0,0 +1,157 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/sunrpc/svc.h>
+#include <linux/exportfs.h>
+#include <linux/nfs4.h>
+
+#include "nfsd.h"
+#include "blocklayoutxdr.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+
+__be32
+nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
+		struct nfsd4_layoutget *lgp)
+{
+	struct pnfs_block_extent *b = lgp->lg_content;
+	int len = sizeof(__be32) + 5 * sizeof(__be64) + sizeof(__be32);
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, sizeof(__be32) + len);
+	if (!p)
+		return nfserr_toosmall;
+
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(1);		/* we always return a single extent */
+
+	p = xdr_encode_opaque_fixed(p, &b->vol_id,
+			sizeof(struct nfsd4_deviceid));
+	p = xdr_encode_hyper(p, b->foff);
+	p = xdr_encode_hyper(p, b->len);
+	p = xdr_encode_hyper(p, b->soff);
+	*p++ = cpu_to_be32(b->es);
+	return 0;
+}
+
+static int
+nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
+{
+	__be32 *p;
+	int len;
+
+	switch (b->type) {
+	case PNFS_BLOCK_VOLUME_SIMPLE:
+		len = 4 + 4 + 8 + 4 + b->simple.sig_len;
+		p = xdr_reserve_space(xdr, len);
+		if (!p)
+			return -ETOOSMALL;
+
+		*p++ = cpu_to_be32(b->type);
+		*p++ = cpu_to_be32(1);	/* single signature */
+		p = xdr_encode_hyper(p, b->simple.offset);
+		p = xdr_encode_opaque(p, b->simple.sig, b->simple.sig_len);
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return len;
+}
+
+__be32
+nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev = gdp->gd_device;
+	int len = sizeof(__be32), ret, i;
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, len + sizeof(__be32));
+	if (!p)
+		return nfserr_resource;
+
+	for (i = 0; i < dev->nr_volumes; i++) {
+		ret = nfsd4_block_encode_volume(xdr, &dev->volumes[i]);
+		if (ret < 0)
+			return nfserrno(ret);
+		len += ret;
+	}
+
+	/*
+	 * Fill in the overall length and number of volumes at the beginning
+	 * of the layout.
+	 */
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(dev->nr_volumes);
+	return 0;
+}
+
+int
+nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+		u32 block_size)
+{
+	struct iomap *iomaps;
+	u32 nr_iomaps, expected, i;
+
+	if (len < sizeof(u32)) {
+		dprintk("%s: extent array too small: %u\n", __func__, len);
+		return -EINVAL;
+	}
+
+	nr_iomaps = be32_to_cpup(p++);
+	expected = sizeof(__be32) + nr_iomaps * NFS4_BLOCK_EXTENT_SIZE;
+	if (len != expected) {
+		dprintk("%s: extent array size mismatch: %u/%u\n",
+			__func__, len, expected);
+		return -EINVAL;
+	}
+
+	iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL);
+	if (!iomaps) {
+		dprintk("%s: failed to allocate extent array\n", __func__);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < nr_iomaps; i++) {
+		struct pnfs_block_extent bex;
+
+		memcpy(&bex.vol_id, p, sizeof(struct nfsd4_deviceid));
+		p += XDR_QUADLEN(sizeof(struct nfsd4_deviceid));
+
+		p = xdr_decode_hyper(p, &bex.foff);
+		if (bex.foff & (block_size - 1)) {
+			dprintk("%s: unaligned offset %lld\n",
+				__func__, bex.foff);
+			goto fail;
+		}
+		p = xdr_decode_hyper(p, &bex.len);
+		if (bex.len & (block_size - 1)) {
+			dprintk("%s: unaligned length %lld\n",
+				__func__, bex.foff);
+			goto fail;
+		}
+		p = xdr_decode_hyper(p, &bex.soff);
+		if (bex.soff & (block_size - 1)) {
+			dprintk("%s: unaligned disk offset %lld\n",
+				__func__, bex.soff);
+			goto fail;
+		}
+		bex.es = be32_to_cpup(p++);
+		if (bex.es != PNFS_BLOCK_READWRITE_DATA) {
+			dprintk("%s: incorrect extent state %d\n",
+				__func__, bex.es);
+			goto fail;
+		}
+
+		iomaps[i].offset = bex.foff;
+		iomaps[i].length = bex.len;
+	}
+
+	*iomapp = iomaps;
+	return nr_iomaps;
+fail:
+	kfree(iomaps);
+	return -EINVAL;
+}
diff --git a/fs/nfsd/blocklayoutxdr.h b/fs/nfsd/blocklayoutxdr.h
new file mode 100644
index 000000000000..fdc79037c0e7
--- /dev/null
+++ b/fs/nfsd/blocklayoutxdr.h
@@ -0,0 +1,62 @@
+#ifndef _NFSD_BLOCKLAYOUTXDR_H
+#define _NFSD_BLOCKLAYOUTXDR_H 1
+
+#include <linux/blkdev.h>
+#include "xdr4.h"
+
+struct iomap;
+struct xdr_stream;
+
+enum pnfs_block_extent_state {
+	PNFS_BLOCK_READWRITE_DATA	= 0,
+	PNFS_BLOCK_READ_DATA		= 1,
+	PNFS_BLOCK_INVALID_DATA		= 2,
+	PNFS_BLOCK_NONE_DATA		= 3,
+};
+
+struct pnfs_block_extent {
+	struct nfsd4_deviceid		vol_id;
+	u64				foff;
+	u64				len;
+	u64				soff;
+	enum pnfs_block_extent_state	es;
+};
+#define NFS4_BLOCK_EXTENT_SIZE		44
+
+enum pnfs_block_volume_type {
+	PNFS_BLOCK_VOLUME_SIMPLE	= 0,
+	PNFS_BLOCK_VOLUME_SLICE		= 1,
+	PNFS_BLOCK_VOLUME_CONCAT	= 2,
+	PNFS_BLOCK_VOLUME_STRIPE	= 3,
+};
+
+/*
+ * Random upper cap for the uuid length to avoid unbounded allocation.
+ * Not actually limited by the protocol.
+ */
+#define PNFS_BLOCK_UUID_LEN	128
+
+struct pnfs_block_volume {
+	enum pnfs_block_volume_type	type;
+	union {
+		struct {
+			u64		offset;
+			u32		sig_len;
+			u8		sig[PNFS_BLOCK_UUID_LEN];
+		} simple;
+	};
+};
+
+struct pnfs_block_deviceaddr {
+	u32				nr_volumes;
+	struct pnfs_block_volume	volumes[];
+};
+
+__be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
+		struct nfsd4_getdeviceinfo *gdp);
+__be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
+		struct nfsd4_layoutget *lgp);
+int nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+		u32 block_size);
+
+#endif /* _NFSD_BLOCKLAYOUTXDR_H */
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 30a739d896ff..c3e3b6e55ae2 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -20,6 +20,7 @@
 #include "nfsd.h"
 #include "nfsfh.h"
 #include "netns.h"
+#include "pnfs.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT
 
@@ -545,6 +546,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 
 	exp.ex_client = dom;
 	exp.cd = cd;
+	exp.ex_devid_map = NULL;
 
 	/* expiry */
 	err = -EINVAL;
@@ -621,6 +623,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 		if (!gid_valid(exp.ex_anon_gid))
 			goto out4;
 		err = 0;
+
+		nfsd4_setup_layout_type(&exp);
 	}
 
 	expp = svc_export_lookup(&exp);
@@ -703,6 +707,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_fslocs.locations = NULL;
 	new->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = 0;
+	new->ex_layout_type = 0;
 	new->ex_uuid = NULL;
 	new->cd = item->cd;
 }
@@ -717,6 +722,8 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_anon_uid = item->ex_anon_uid;
 	new->ex_anon_gid = item->ex_anon_gid;
 	new->ex_fsid = item->ex_fsid;
+	new->ex_devid_map = item->ex_devid_map;
+	item->ex_devid_map = NULL;
 	new->ex_uuid = item->ex_uuid;
 	item->ex_uuid = NULL;
 	new->ex_fslocs.locations = item->ex_fslocs.locations;
@@ -725,6 +732,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	item->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = item->ex_fslocs.migrated;
 	item->ex_fslocs.migrated = 0;
+	new->ex_layout_type = item->ex_layout_type;
 	new->ex_nflavors = item->ex_nflavors;
 	for (i = 0; i < MAX_SECINFO_LIST; i++) {
 		new->ex_flavors[i] = item->ex_flavors[i];
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index 04dc8c167b0c..1f52bfcc436f 100644
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -56,6 +56,8 @@ struct svc_export {
 	struct nfsd4_fs_locations ex_fslocs;
 	uint32_t		ex_nflavors;
 	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
+	enum pnfs_layouttype	ex_layout_type;
+	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
 };
 
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7cbdf1b2e4ab..58277859a467 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -546,6 +546,102 @@ out:
 	return status;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+/*
+ * CB_LAYOUTRECALL4args
+ *
+ *	struct layoutrecall_file4 {
+ *		nfs_fh4         lor_fh;
+ *		offset4         lor_offset;
+ *		length4         lor_length;
+ *		stateid4        lor_stateid;
+ *	};
+ *
+ *	union layoutrecall4 switch(layoutrecall_type4 lor_recalltype) {
+ *	case LAYOUTRECALL4_FILE:
+ *		layoutrecall_file4 lor_layout;
+ *	case LAYOUTRECALL4_FSID:
+ *		fsid4              lor_fsid;
+ *	case LAYOUTRECALL4_ALL:
+ *		void;
+ *	};
+ *
+ *	struct CB_LAYOUTRECALL4args {
+ *		layouttype4             clora_type;
+ *		layoutiomode4           clora_iomode;
+ *		bool                    clora_changed;
+ *		layoutrecall4           clora_recall;
+ *	};
+ */
+static void encode_cb_layout4args(struct xdr_stream *xdr,
+				  const struct nfs4_layout_stateid *ls,
+				  struct nfs4_cb_compound_hdr *hdr)
+{
+	__be32 *p;
+
+	BUG_ON(hdr->minorversion == 0);
+
+	p = xdr_reserve_space(xdr, 5 * 4);
+	*p++ = cpu_to_be32(OP_CB_LAYOUTRECALL);
+	*p++ = cpu_to_be32(ls->ls_layout_type);
+	*p++ = cpu_to_be32(IOMODE_ANY);
+	*p++ = cpu_to_be32(1);
+	*p = cpu_to_be32(RETURN_FILE);
+
+	encode_nfs_fh4(xdr, &ls->ls_stid.sc_file->fi_fhandle);
+
+	p = xdr_reserve_space(xdr, 2 * 8);
+	p = xdr_encode_hyper(p, 0);
+	xdr_encode_hyper(p, NFS4_MAX_UINT64);
+
+	encode_stateid4(xdr, &ls->ls_recall_sid);
+
+	hdr->nops++;
+}
+
+static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   const struct nfsd4_callback *cb)
+{
+	const struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	struct nfs4_cb_compound_hdr hdr = {
+		.ident = 0,
+		.minorversion = cb->cb_minorversion,
+	};
+
+	encode_cb_compound4args(xdr, &hdr);
+	encode_cb_sequence4args(xdr, cb, &hdr);
+	encode_cb_layout4args(xdr, ls, &hdr);
+	encode_cb_nops(&hdr);
+}
+
+static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  struct nfsd4_callback *cb)
+{
+	struct nfs4_cb_compound_hdr hdr;
+	enum nfsstat4 nfserr;
+	int status;
+
+	status = decode_cb_compound4res(xdr, &hdr);
+	if (unlikely(status))
+		goto out;
+	if (cb) {
+		status = decode_cb_sequence4res(xdr, cb);
+		if (unlikely(status))
+			goto out;
+	}
+	status = decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &nfserr);
+	if (unlikely(status))
+		goto out;
+	if (unlikely(nfserr != NFS4_OK))
+		status = nfs_cb_stat_to_errno(nfserr);
+out:
+	return status;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 /*
  * RPC procedure tables
  */
@@ -563,6 +659,9 @@ out:
 static struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NULL,	NULL,		cb_null,	cb_null),
 	PROC(CB_RECALL,	COMPOUND,	cb_recall,	cb_recall),
+#ifdef CONFIG_NFSD_PNFS
+	PROC(CB_LAYOUT,	COMPOUND,	cb_layout,	cb_layout),
+#endif
 };
 
 static struct rpc_version nfs_cb_version4 = {
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
new file mode 100644
index 000000000000..1028a0629543
--- /dev/null
+++ b/fs/nfsd/nfs4layouts.c
@@ -0,0 +1,719 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/kmod.h>
+#include <linux/file.h>
+#include <linux/jhash.h>
+#include <linux/sched.h>
+#include <linux/sunrpc/addr.h>
+
+#include "pnfs.h"
+#include "netns.h"
+#include "trace.h"
+
+#define NFSDDBG_FACILITY                NFSDDBG_PNFS
+
+struct nfs4_layout {
+	struct list_head		lo_perstate;
+	struct nfs4_layout_stateid	*lo_state;
+	struct nfsd4_layout_seg		lo_seg;
+};
+
+static struct kmem_cache *nfs4_layout_cache;
+static struct kmem_cache *nfs4_layout_stateid_cache;
+
+static struct nfsd4_callback_ops nfsd4_cb_layout_ops;
+static const struct lock_manager_operations nfsd4_layouts_lm_ops;
+
+const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
+	[LAYOUT_BLOCK_VOLUME]	= &bl_layout_ops,
+};
+
+/* pNFS device ID to export fsid mapping */
+#define DEVID_HASH_BITS	8
+#define DEVID_HASH_SIZE	(1 << DEVID_HASH_BITS)
+#define DEVID_HASH_MASK	(DEVID_HASH_SIZE - 1)
+static u64 nfsd_devid_seq = 1;
+static struct list_head nfsd_devid_hash[DEVID_HASH_SIZE];
+static DEFINE_SPINLOCK(nfsd_devid_lock);
+
+static inline u32 devid_hashfn(u64 idx)
+{
+	return jhash_2words(idx, idx >> 32, 0) & DEVID_HASH_MASK;
+}
+
+static void
+nfsd4_alloc_devid_map(const struct svc_fh *fhp)
+{
+	const struct knfsd_fh *fh = &fhp->fh_handle;
+	size_t fsid_len = key_len(fh->fh_fsid_type);
+	struct nfsd4_deviceid_map *map, *old;
+	int i;
+
+	map = kzalloc(sizeof(*map) + fsid_len, GFP_KERNEL);
+	if (!map)
+		return;
+
+	map->fsid_type = fh->fh_fsid_type;
+	memcpy(&map->fsid, fh->fh_fsid, fsid_len);
+
+	spin_lock(&nfsd_devid_lock);
+	if (fhp->fh_export->ex_devid_map)
+		goto out_unlock;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		list_for_each_entry(old, &nfsd_devid_hash[i], hash) {
+			if (old->fsid_type != fh->fh_fsid_type)
+				continue;
+			if (memcmp(old->fsid, fh->fh_fsid,
+					key_len(old->fsid_type)))
+				continue;
+
+			fhp->fh_export->ex_devid_map = old;
+			goto out_unlock;
+		}
+	}
+
+	map->idx = nfsd_devid_seq++;
+	list_add_tail_rcu(&map->hash, &nfsd_devid_hash[devid_hashfn(map->idx)]);
+	fhp->fh_export->ex_devid_map = map;
+	map = NULL;
+
+out_unlock:
+	spin_unlock(&nfsd_devid_lock);
+	kfree(map);
+}
+
+struct nfsd4_deviceid_map *
+nfsd4_find_devid_map(int idx)
+{
+	struct nfsd4_deviceid_map *map, *ret = NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(map, &nfsd_devid_hash[devid_hashfn(idx)], hash)
+		if (map->idx == idx)
+			ret = map;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+int
+nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation)
+{
+	if (!fhp->fh_export->ex_devid_map) {
+		nfsd4_alloc_devid_map(fhp);
+		if (!fhp->fh_export->ex_devid_map)
+			return -ENOMEM;
+	}
+
+	id->fsid_idx = fhp->fh_export->ex_devid_map->idx;
+	id->generation = device_generation;
+	id->pad = 0;
+	return 0;
+}
+
+void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+	struct super_block *sb = exp->ex_path.mnt->mnt_sb;
+
+	if (exp->ex_flags & NFSEXP_NOPNFS)
+		return;
+
+	if (sb->s_export_op->get_uuid &&
+	    sb->s_export_op->map_blocks &&
+	    sb->s_export_op->commit_blocks)
+		exp->ex_layout_type = LAYOUT_BLOCK_VOLUME;
+}
+
+static void
+nfsd4_free_layout_stateid(struct nfs4_stid *stid)
+{
+	struct nfs4_layout_stateid *ls = layoutstateid(stid);
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+
+	trace_layoutstate_free(&ls->ls_stid.sc_stateid);
+
+	spin_lock(&clp->cl_lock);
+	list_del_init(&ls->ls_perclnt);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_del_init(&ls->ls_perfile);
+	spin_unlock(&fp->fi_lock);
+
+	vfs_setlease(ls->ls_file, F_UNLCK, NULL, (void **)&ls);
+	fput(ls->ls_file);
+
+	if (ls->ls_recalled)
+		atomic_dec(&ls->ls_stid.sc_file->fi_lo_recalls);
+
+	kmem_cache_free(nfs4_layout_stateid_cache, ls);
+}
+
+static int
+nfsd4_layout_setlease(struct nfs4_layout_stateid *ls)
+{
+	struct file_lock *fl;
+	int status;
+
+	fl = locks_alloc_lock();
+	if (!fl)
+		return -ENOMEM;
+	locks_init_lock(fl);
+	fl->fl_lmops = &nfsd4_layouts_lm_ops;
+	fl->fl_flags = FL_LAYOUT;
+	fl->fl_type = F_RDLCK;
+	fl->fl_end = OFFSET_MAX;
+	fl->fl_owner = ls;
+	fl->fl_pid = current->tgid;
+	fl->fl_file = ls->ls_file;
+
+	status = vfs_setlease(fl->fl_file, fl->fl_type, &fl, NULL);
+	if (status) {
+		locks_free_lock(fl);
+		return status;
+	}
+	BUG_ON(fl != NULL);
+	return 0;
+}
+
+static struct nfs4_layout_stateid *
+nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
+		struct nfs4_stid *parent, u32 layout_type)
+{
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_file *fp = parent->sc_file;
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stp;
+
+	stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache);
+	if (!stp)
+		return NULL;
+	stp->sc_free = nfsd4_free_layout_stateid;
+	get_nfs4_file(fp);
+	stp->sc_file = fp;
+
+	ls = layoutstateid(stp);
+	INIT_LIST_HEAD(&ls->ls_perclnt);
+	INIT_LIST_HEAD(&ls->ls_perfile);
+	spin_lock_init(&ls->ls_lock);
+	INIT_LIST_HEAD(&ls->ls_layouts);
+	ls->ls_layout_type = layout_type;
+	nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops,
+			NFSPROC4_CLNT_CB_LAYOUT);
+
+	if (parent->sc_type == NFS4_DELEG_STID)
+		ls->ls_file = get_file(fp->fi_deleg_file);
+	else
+		ls->ls_file = find_any_file(fp);
+	BUG_ON(!ls->ls_file);
+
+	if (nfsd4_layout_setlease(ls)) {
+		put_nfs4_file(fp);
+		kmem_cache_free(nfs4_layout_stateid_cache, ls);
+		return NULL;
+	}
+
+	spin_lock(&clp->cl_lock);
+	stp->sc_type = NFS4_LAYOUT_STID;
+	list_add(&ls->ls_perclnt, &clp->cl_lo_states);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_add(&ls->ls_perfile, &fp->fi_lo_states);
+	spin_unlock(&fp->fi_lock);
+
+	trace_layoutstate_alloc(&ls->ls_stid.sc_stateid);
+	return ls;
+}
+
+__be32
+nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stid;
+	unsigned char typemask = NFS4_LAYOUT_STID;
+	__be32 status;
+
+	if (create)
+		typemask |= (NFS4_OPEN_STID | NFS4_LOCK_STID | NFS4_DELEG_STID);
+
+	status = nfsd4_lookup_stateid(cstate, stateid, typemask, &stid,
+			net_generic(SVC_NET(rqstp), nfsd_net_id));
+	if (status)
+		goto out;
+
+	if (!fh_match(&cstate->current_fh.fh_handle,
+		      &stid->sc_file->fi_fhandle)) {
+		status = nfserr_bad_stateid;
+		goto out_put_stid;
+	}
+
+	if (stid->sc_type != NFS4_LAYOUT_STID) {
+		ls = nfsd4_alloc_layout_stateid(cstate, stid, layout_type);
+		nfs4_put_stid(stid);
+
+		status = nfserr_jukebox;
+		if (!ls)
+			goto out;
+	} else {
+		ls = container_of(stid, struct nfs4_layout_stateid, ls_stid);
+
+		status = nfserr_bad_stateid;
+		if (stateid->si_generation > stid->sc_stateid.si_generation)
+			goto out_put_stid;
+		if (layout_type != ls->ls_layout_type)
+			goto out_put_stid;
+	}
+
+	*lsp = ls;
+	return 0;
+
+out_put_stid:
+	nfs4_put_stid(stid);
+out:
+	return status;
+}
+
+static void
+nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls)
+{
+	spin_lock(&ls->ls_lock);
+	if (ls->ls_recalled)
+		goto out_unlock;
+
+	ls->ls_recalled = true;
+	atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls);
+	if (list_empty(&ls->ls_layouts))
+		goto out_unlock;
+
+	trace_layout_recall(&ls->ls_stid.sc_stateid);
+
+	atomic_inc(&ls->ls_stid.sc_count);
+	update_stateid(&ls->ls_stid.sc_stateid);
+	memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
+	nfsd4_run_cb(&ls->ls_recall);
+
+out_unlock:
+	spin_unlock(&ls->ls_lock);
+}
+
+static inline u64
+layout_end(struct nfsd4_layout_seg *seg)
+{
+	u64 end = seg->offset + seg->length;
+	return end >= seg->offset ? end : NFS4_MAX_UINT64;
+}
+
+static void
+layout_update_len(struct nfsd4_layout_seg *lo, u64 end)
+{
+	if (end == NFS4_MAX_UINT64)
+		lo->length = NFS4_MAX_UINT64;
+	else
+		lo->length = end - lo->offset;
+}
+
+static bool
+layouts_overlapping(struct nfs4_layout *lo, struct nfsd4_layout_seg *s)
+{
+	if (s->iomode != IOMODE_ANY && s->iomode != lo->lo_seg.iomode)
+		return false;
+	if (layout_end(&lo->lo_seg) <= s->offset)
+		return false;
+	if (layout_end(s) <= lo->lo_seg.offset)
+		return false;
+	return true;
+}
+
+static bool
+layouts_try_merge(struct nfsd4_layout_seg *lo, struct nfsd4_layout_seg *new)
+{
+	if (lo->iomode != new->iomode)
+		return false;
+	if (layout_end(new) < lo->offset)
+		return false;
+	if (layout_end(lo) < new->offset)
+		return false;
+
+	lo->offset = min(lo->offset, new->offset);
+	layout_update_len(lo, max(layout_end(lo), layout_end(new)));
+	return true;
+}
+
+static __be32
+nfsd4_recall_conflict(struct nfs4_layout_stateid *ls)
+{
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+	struct nfs4_layout_stateid *l, *n;
+	__be32 nfserr = nfs_ok;
+
+	assert_spin_locked(&fp->fi_lock);
+
+	list_for_each_entry_safe(l, n, &fp->fi_lo_states, ls_perfile) {
+		if (l != ls) {
+			nfsd4_recall_file_layout(l);
+			nfserr = nfserr_recallconflict;
+		}
+	}
+
+	return nfserr;
+}
+
+__be32
+nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls)
+{
+	struct nfsd4_layout_seg *seg = &lgp->lg_seg;
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+	struct nfs4_layout *lp, *new = NULL;
+	__be32 nfserr;
+
+	spin_lock(&fp->fi_lock);
+	nfserr = nfsd4_recall_conflict(ls);
+	if (nfserr)
+		goto out;
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+	spin_unlock(&ls->ls_lock);
+	spin_unlock(&fp->fi_lock);
+
+	new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL);
+	if (!new)
+		return nfserr_jukebox;
+	memcpy(&new->lo_seg, seg, sizeof(lp->lo_seg));
+	new->lo_state = ls;
+
+	spin_lock(&fp->fi_lock);
+	nfserr = nfsd4_recall_conflict(ls);
+	if (nfserr)
+		goto out;
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+
+	atomic_inc(&ls->ls_stid.sc_count);
+	list_add_tail(&new->lo_perstate, &ls->ls_layouts);
+	new = NULL;
+done:
+	update_stateid(&ls->ls_stid.sc_stateid);
+	memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
+	spin_unlock(&ls->ls_lock);
+out:
+	spin_unlock(&fp->fi_lock);
+	if (new)
+		kmem_cache_free(nfs4_layout_cache, new);
+	return nfserr;
+}
+
+static void
+nfsd4_free_layouts(struct list_head *reaplist)
+{
+	while (!list_empty(reaplist)) {
+		struct nfs4_layout *lp = list_first_entry(reaplist,
+				struct nfs4_layout, lo_perstate);
+
+		list_del(&lp->lo_perstate);
+		nfs4_put_stid(&lp->lo_state->ls_stid);
+		kmem_cache_free(nfs4_layout_cache, lp);
+	}
+}
+
+static void
+nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg,
+		struct list_head *reaplist)
+{
+	struct nfsd4_layout_seg *lo = &lp->lo_seg;
+	u64 end = layout_end(lo);
+
+	if (seg->offset <= lo->offset) {
+		if (layout_end(seg) >= end) {
+			list_move_tail(&lp->lo_perstate, reaplist);
+			return;
+		}
+		end = seg->offset;
+	} else {
+		/* retain the whole layout segment on a split. */
+		if (layout_end(seg) < end) {
+			dprintk("%s: split not supported\n", __func__);
+			return;
+		}
+
+		lo->offset = layout_end(seg);
+	}
+
+	layout_update_len(lo, end);
+}
+
+__be32
+nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_layout *lp, *n;
+	LIST_HEAD(reaplist);
+	__be32 nfserr;
+	int found = 0;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lrp->lr_sid,
+						false, lrp->lr_layout_type,
+						&ls);
+	if (nfserr) {
+		trace_layout_return_lookup_fail(&lrp->lr_sid);
+		return nfserr;
+	}
+
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry_safe(lp, n, &ls->ls_layouts, lo_perstate) {
+		if (layouts_overlapping(lp, &lrp->lr_seg)) {
+			nfsd4_return_file_layout(lp, &lrp->lr_seg, &reaplist);
+			found++;
+		}
+	}
+	if (!list_empty(&ls->ls_layouts)) {
+		if (found) {
+			update_stateid(&ls->ls_stid.sc_stateid);
+			memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid,
+				sizeof(stateid_t));
+		}
+		lrp->lrs_present = 1;
+	} else {
+		trace_layoutstate_unhash(&ls->ls_stid.sc_stateid);
+		nfs4_unhash_stid(&ls->ls_stid);
+		lrp->lrs_present = 0;
+	}
+	spin_unlock(&ls->ls_lock);
+
+	nfs4_put_stid(&ls->ls_stid);
+	nfsd4_free_layouts(&reaplist);
+	return nfs_ok;
+}
+
+__be32
+nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_layout *lp, *t;
+	LIST_HEAD(reaplist);
+
+	lrp->lrs_present = 0;
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) {
+		if (lrp->lr_return_type == RETURN_FSID &&
+		    !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle,
+				   &cstate->current_fh.fh_handle))
+			continue;
+
+		spin_lock(&ls->ls_lock);
+		list_for_each_entry_safe(lp, t, &ls->ls_layouts, lo_perstate) {
+			if (lrp->lr_seg.iomode == IOMODE_ANY ||
+			    lrp->lr_seg.iomode == lp->lo_seg.iomode)
+				list_move_tail(&lp->lo_perstate, &reaplist);
+		}
+		spin_unlock(&ls->ls_lock);
+	}
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+	return 0;
+}
+
+static void
+nfsd4_return_all_layouts(struct nfs4_layout_stateid *ls,
+		struct list_head *reaplist)
+{
+	spin_lock(&ls->ls_lock);
+	list_splice_init(&ls->ls_layouts, reaplist);
+	spin_unlock(&ls->ls_lock);
+}
+
+void
+nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt)
+		nfsd4_return_all_layouts(ls, &reaplist);
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+void
+nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&fp->fi_lock);
+	list_for_each_entry_safe(ls, n, &fp->fi_lo_states, ls_perfile) {
+		if (ls->ls_stid.sc_client == clp)
+			nfsd4_return_all_layouts(ls, &reaplist);
+	}
+	spin_unlock(&fp->fi_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+static void
+nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
+{
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	char addr_str[INET6_ADDRSTRLEN];
+	static char *envp[] = {
+		"HOME=/",
+		"TERM=linux",
+		"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+		NULL
+	};
+	char *argv[8];
+	int error;
+
+	rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str));
+
+	printk(KERN_WARNING
+		"nfsd: client %s failed to respond to layout recall. "
+		"  Fencing..\n", addr_str);
+
+	argv[0] = "/sbin/nfsd-recall-failed";
+	argv[1] = addr_str;
+	argv[2] = ls->ls_file->f_path.mnt->mnt_sb->s_id;
+	argv[3] = NULL;
+
+	error = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+	if (error) {
+		printk(KERN_ERR "nfsd: fence failed for client %s: %d!\n",
+			addr_str, error);
+	}
+}
+
+static int
+nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
+{
+	struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	LIST_HEAD(reaplist);
+
+	switch (task->tk_status) {
+	case 0:
+		return 1;
+	case -NFS4ERR_NOMATCHING_LAYOUT:
+		trace_layout_recall_done(&ls->ls_stid.sc_stateid);
+		task->tk_status = 0;
+		return 1;
+	case -NFS4ERR_DELAY:
+		/* Poll the client until it's done with the layout */
+		/* FIXME: cap number of retries.
+		 * The pnfs standard states that we need to only expire
+		 * the client after at-least "lease time" .eg lease-time * 2
+		 * when failing to communicate a recall
+		 */
+		rpc_delay(task, HZ/100); /* 10 mili-seconds */
+		return 0;
+	default:
+		/*
+		 * Unknown error or non-responding client, we'll need to fence.
+		 */
+		nfsd4_cb_layout_fail(ls);
+		return -1;
+	}
+}
+
+static void
+nfsd4_cb_layout_release(struct nfsd4_callback *cb)
+{
+	struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	LIST_HEAD(reaplist);
+
+	trace_layout_recall_release(&ls->ls_stid.sc_stateid);
+
+	nfsd4_return_all_layouts(ls, &reaplist);
+	nfsd4_free_layouts(&reaplist);
+	nfs4_put_stid(&ls->ls_stid);
+}
+
+static struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
+	.done		= nfsd4_cb_layout_done,
+	.release	= nfsd4_cb_layout_release,
+};
+
+static bool
+nfsd4_layout_lm_break(struct file_lock *fl)
+{
+	/*
+	 * We don't want the locks code to timeout the lease for us;
+	 * we'll remove it ourself if a layout isn't returned
+	 * in time:
+	 */
+	fl->fl_break_time = 0;
+	nfsd4_recall_file_layout(fl->fl_owner);
+	return false;
+}
+
+static int
+nfsd4_layout_lm_change(struct file_lock *onlist, int arg,
+		struct list_head *dispose)
+{
+	BUG_ON(!(arg & F_UNLCK));
+	return lease_modify(onlist, arg, dispose);
+}
+
+static const struct lock_manager_operations nfsd4_layouts_lm_ops = {
+	.lm_break	= nfsd4_layout_lm_break,
+	.lm_change	= nfsd4_layout_lm_change,
+};
+
+int
+nfsd4_init_pnfs(void)
+{
+	int i;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++)
+		INIT_LIST_HEAD(&nfsd_devid_hash[i]);
+
+	nfs4_layout_cache = kmem_cache_create("nfs4_layout",
+			sizeof(struct nfs4_layout), 0, 0, NULL);
+	if (!nfs4_layout_cache)
+		return -ENOMEM;
+
+	nfs4_layout_stateid_cache = kmem_cache_create("nfs4_layout_stateid",
+			sizeof(struct nfs4_layout_stateid), 0, 0, NULL);
+	if (!nfs4_layout_stateid_cache) {
+		kmem_cache_destroy(nfs4_layout_cache);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void
+nfsd4_exit_pnfs(void)
+{
+	int i;
+
+	kmem_cache_destroy(nfs4_layout_cache);
+	kmem_cache_destroy(nfs4_layout_stateid_cache);
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		struct nfsd4_deviceid_map *map, *n;
+
+		list_for_each_entry_safe(map, n, &nfsd_devid_hash[i], hash)
+			kfree(map);
+	}
+}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index ac71d13c69ef..d30bea8d0277 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -43,6 +43,8 @@
 #include "current_stateid.h"
 #include "netns.h"
 #include "acl.h"
+#include "pnfs.h"
+#include "trace.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -1178,6 +1180,259 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status == nfserr_same ? nfs_ok : status;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static const struct nfsd4_layout_ops *
+nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
+{
+	if (!exp->ex_layout_type) {
+		dprintk("%s: export does not support pNFS\n", __func__);
+		return NULL;
+	}
+
+	if (exp->ex_layout_type != layout_type) {
+		dprintk("%s: layout type %d not supported\n",
+			__func__, layout_type);
+		return NULL;
+	}
+
+	return nfsd4_layout_ops[layout_type];
+}
+
+static __be32
+nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	const struct nfsd4_layout_ops *ops;
+	struct nfsd4_deviceid_map *map;
+	struct svc_export *exp;
+	__be32 nfserr;
+
+	dprintk("%s: layout_type %u dev_id [0x%llx:0x%x] maxcnt %u\n",
+	       __func__,
+	       gdp->gd_layout_type,
+	       gdp->gd_devid.fsid_idx, gdp->gd_devid.generation,
+	       gdp->gd_maxcount);
+
+	map = nfsd4_find_devid_map(gdp->gd_devid.fsid_idx);
+	if (!map) {
+		dprintk("%s: couldn't find device ID to export mapping!\n",
+			__func__);
+		return nfserr_noent;
+	}
+
+	exp = rqst_exp_find(rqstp, map->fsid_type, map->fsid);
+	if (IS_ERR(exp)) {
+		dprintk("%s: could not find device id\n", __func__);
+		return nfserr_noent;
+	}
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(exp, gdp->gd_layout_type);
+	if (!ops)
+		goto out;
+
+	nfserr = nfs_ok;
+	if (gdp->gd_maxcount != 0)
+		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp);
+
+	gdp->gd_notify_types &= ops->notify_types;
+	exp_put(exp);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutget(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutget *lgp)
+{
+	struct svc_fh *current_fh = &cstate->current_fh;
+	const struct nfsd4_layout_ops *ops;
+	struct nfs4_layout_stateid *ls;
+	__be32 nfserr;
+	int accmode;
+
+	switch (lgp->lg_seg.iomode) {
+	case IOMODE_READ:
+		accmode = NFSD_MAY_READ;
+		break;
+	case IOMODE_RW:
+		accmode = NFSD_MAY_READ | NFSD_MAY_WRITE;
+		break;
+	default:
+		dprintk("%s: invalid iomode %d\n",
+			__func__, lgp->lg_seg.iomode);
+		nfserr = nfserr_badiomode;
+		goto out;
+	}
+
+	nfserr = fh_verify(rqstp, current_fh, 0, accmode);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(current_fh->fh_export, lgp->lg_layout_type);
+	if (!ops)
+		goto out;
+
+	/*
+	 * Verify minlength and range as per RFC5661:
+	 *  o  If loga_length is less than loga_minlength,
+	 *     the metadata server MUST return NFS4ERR_INVAL.
+	 *  o  If the sum of loga_offset and loga_minlength exceeds
+	 *     NFS4_UINT64_MAX, and loga_minlength is not
+	 *     NFS4_UINT64_MAX, the error NFS4ERR_INVAL MUST result.
+	 *  o  If the sum of loga_offset and loga_length exceeds
+	 *     NFS4_UINT64_MAX, and loga_length is not NFS4_UINT64_MAX,
+	 *     the error NFS4ERR_INVAL MUST result.
+	 */
+	nfserr = nfserr_inval;
+	if (lgp->lg_seg.length < lgp->lg_minlength ||
+	    (lgp->lg_minlength != NFS4_MAX_UINT64 &&
+	     lgp->lg_minlength > NFS4_MAX_UINT64 - lgp->lg_seg.offset) ||
+	    (lgp->lg_seg.length != NFS4_MAX_UINT64 &&
+	     lgp->lg_seg.length > NFS4_MAX_UINT64 - lgp->lg_seg.offset))
+		goto out;
+	if (lgp->lg_seg.length == 0)
+		goto out;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid,
+						true, lgp->lg_layout_type, &ls);
+	if (nfserr) {
+		trace_layout_get_lookup_fail(&lgp->lg_sid);
+		goto out;
+	}
+
+	nfserr = nfserr_recallconflict;
+	if (atomic_read(&ls->ls_stid.sc_file->fi_lo_recalls))
+		goto out_put_stid;
+
+	nfserr = ops->proc_layoutget(current_fh->fh_dentry->d_inode,
+				     current_fh, lgp);
+	if (nfserr)
+		goto out_put_stid;
+
+	nfserr = nfsd4_insert_layout(lgp, ls);
+
+out_put_stid:
+	nfs4_put_stid(&ls->ls_stid);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutcommit(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutcommit *lcp)
+{
+	const struct nfsd4_layout_seg *seg = &lcp->lc_seg;
+	struct svc_fh *current_fh = &cstate->current_fh;
+	const struct nfsd4_layout_ops *ops;
+	loff_t new_size = lcp->lc_last_wr + 1;
+	struct inode *inode;
+	struct nfs4_layout_stateid *ls;
+	__be32 nfserr;
+
+	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(current_fh->fh_export, lcp->lc_layout_type);
+	if (!ops)
+		goto out;
+	inode = current_fh->fh_dentry->d_inode;
+
+	nfserr = nfserr_inval;
+	if (new_size <= seg->offset) {
+		dprintk("pnfsd: last write before layout segment\n");
+		goto out;
+	}
+	if (new_size > seg->offset + seg->length) {
+		dprintk("pnfsd: last write beyond layout segment\n");
+		goto out;
+	}
+	if (!lcp->lc_newoffset && new_size > i_size_read(inode)) {
+		dprintk("pnfsd: layoutcommit beyond EOF\n");
+		goto out;
+	}
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid,
+						false, lcp->lc_layout_type,
+						&ls);
+	if (nfserr) {
+		trace_layout_commit_lookup_fail(&lcp->lc_sid);
+		/* fixup error code as per RFC5661 */
+		if (nfserr == nfserr_bad_stateid)
+			nfserr = nfserr_badlayout;
+		goto out;
+	}
+
+	nfserr = ops->proc_layoutcommit(inode, lcp);
+	if (nfserr)
+		goto out_put_stid;
+
+	if (new_size > i_size_read(inode)) {
+		lcp->lc_size_chg = 1;
+		lcp->lc_newsize = new_size;
+	} else {
+		lcp->lc_size_chg = 0;
+	}
+
+out_put_stid:
+	nfs4_put_stid(&ls->ls_stid);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutreturn(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct svc_fh *current_fh = &cstate->current_fh;
+	__be32 nfserr;
+
+	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_NOP);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	if (!nfsd4_layout_verify(current_fh->fh_export, lrp->lr_layout_type))
+		goto out;
+
+	switch (lrp->lr_seg.iomode) {
+	case IOMODE_READ:
+	case IOMODE_RW:
+	case IOMODE_ANY:
+		break;
+	default:
+		dprintk("%s: invalid iomode %d\n", __func__,
+			lrp->lr_seg.iomode);
+		nfserr = nfserr_inval;
+		goto out;
+	}
+
+	switch (lrp->lr_return_type) {
+	case RETURN_FILE:
+		nfserr = nfsd4_return_file_layouts(rqstp, cstate, lrp);
+		break;
+	case RETURN_FSID:
+	case RETURN_ALL:
+		nfserr = nfsd4_return_client_layouts(rqstp, cstate, lrp);
+		break;
+	default:
+		dprintk("%s: invalid return_type %d\n", __func__,
+			lrp->lr_return_type);
+		nfserr = nfserr_inval;
+		break;
+	}
+out:
+	return nfserr;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 /*
  * NULL call.
  */
@@ -1679,6 +1934,36 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd
 		op_encode_channel_attrs_maxsz) * sizeof(__be32);
 }
 
+#ifdef CONFIG_NFSD_PNFS
+/*
+ * At this stage we don't really know what layout driver will handle the request,
+ * so we need to define an arbitrary upper bound here.
+ */
+#define MAX_LAYOUT_SIZE		128
+static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* logr_return_on_close */ +
+		op_encode_stateid_maxsz +
+		1 /* nr of layouts */ +
+		MAX_LAYOUT_SIZE) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* locr_newsize */ +
+		2 /* ns_size */) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* lrs_stateid */ +
+		op_encode_stateid_maxsz) * sizeof(__be32);
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static struct nfsd4_operation nfsd4_ops[] = {
 	[OP_ACCESS] = {
 		.op_func = (nfsd4op_func)nfsd4_access,
@@ -1966,6 +2251,31 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO] = {
+		.op_func = (nfsd4op_func)nfsd4_getdeviceinfo,
+		.op_flags = ALLOWED_WITHOUT_FH,
+		.op_name = "OP_GETDEVICEINFO",
+	},
+	[OP_LAYOUTGET] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutget,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTGET",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize,
+	},
+	[OP_LAYOUTCOMMIT] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutcommit,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTCOMMIT",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize,
+	},
+	[OP_LAYOUTRETURN] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutreturn,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTRETURN",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize,
+	},
+#endif /* CONFIG_NFSD_PNFS */
 
 	/* NFSv4.2 operations */
 	[OP_ALLOCATE] = {
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index cc6a76072009..1c307f02baa8 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -583,7 +583,7 @@ nfs4_reset_recoverydir(char *recdir)
 	if (status)
 		return status;
 	status = -ENOTDIR;
-	if (S_ISDIR(path.dentry->d_inode->i_mode)) {
+	if (d_is_dir(path.dentry)) {
 		strcpy(user_recovery_dirname, recdir);
 		status = 0;
 	}
@@ -1426,7 +1426,7 @@ nfsd4_client_tracking_init(struct net *net)
 	nn->client_tracking_ops = &nfsd4_legacy_tracking_ops;
 	status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
 	if (!status) {
-		status = S_ISDIR(path.dentry->d_inode->i_mode);
+		status = d_is_dir(path.dentry);
 		path_put(&path);
 		if (status)
 			goto do_init;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c06a1ba80d73..d2f2c37dc2db 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -48,6 +48,7 @@
 #include "current_stateid.h"
 
 #include "netns.h"
+#include "pnfs.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
@@ -150,16 +151,6 @@ renew_client_locked(struct nfs4_client *clp)
 	clp->cl_time = get_seconds();
 }
 
-static inline void
-renew_client(struct nfs4_client *clp)
-{
-	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
-
-	spin_lock(&nn->client_lock);
-	renew_client_locked(clp);
-	spin_unlock(&nn->client_lock);
-}
-
 static void put_client_renew_locked(struct nfs4_client *clp)
 {
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
@@ -282,7 +273,7 @@ static void nfsd4_free_file_rcu(struct rcu_head *rcu)
 	kmem_cache_free(file_slab, fp);
 }
 
-static inline void
+void
 put_nfs4_file(struct nfs4_file *fi)
 {
 	might_lock(&state_lock);
@@ -295,12 +286,6 @@ put_nfs4_file(struct nfs4_file *fi)
 	}
 }
 
-static inline void
-get_nfs4_file(struct nfs4_file *fi)
-{
-	atomic_inc(&fi->fi_ref);
-}
-
 static struct file *
 __nfs4_get_fd(struct nfs4_file *f, int oflag)
 {
@@ -358,7 +343,7 @@ find_readable_file(struct nfs4_file *f)
 	return ret;
 }
 
-static struct file *
+struct file *
 find_any_file(struct nfs4_file *f)
 {
 	struct file *ret;
@@ -408,14 +393,6 @@ static unsigned int file_hashval(struct knfsd_fh *fh)
 	return nfsd_fh_hashval(fh) & (FILE_HASH_SIZE - 1);
 }
 
-static bool nfsd_fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
-{
-	return fh1->fh_size == fh2->fh_size &&
-		!memcmp(fh1->fh_base.fh_pad,
-				fh2->fh_base.fh_pad,
-				fh1->fh_size);
-}
-
 static struct hlist_head file_hashtbl[FILE_HASH_SIZE];
 
 static void
@@ -494,7 +471,7 @@ static void nfs4_file_put_access(struct nfs4_file *fp, u32 access)
 		__nfs4_file_put_access(fp, O_RDONLY);
 }
 
-static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
 					 struct kmem_cache *slab)
 {
 	struct nfs4_stid *stid;
@@ -688,17 +665,17 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 	struct file *filp = NULL;
 
 	spin_lock(&fp->fi_lock);
-	if (fp->fi_deleg_file && atomic_dec_and_test(&fp->fi_delegees))
+	if (fp->fi_deleg_file && --fp->fi_delegees == 0)
 		swap(filp, fp->fi_deleg_file);
 	spin_unlock(&fp->fi_lock);
 
 	if (filp) {
-		vfs_setlease(filp, F_UNLCK, NULL, NULL);
+		vfs_setlease(filp, F_UNLCK, NULL, (void **)&fp);
 		fput(filp);
 	}
 }
 
-static void unhash_stid(struct nfs4_stid *s)
+void nfs4_unhash_stid(struct nfs4_stid *s)
 {
 	s->sc_type = 0;
 }
@@ -1006,7 +983,7 @@ static void unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 
 	list_del_init(&stp->st_locks);
 	unhash_ol_stateid(stp);
-	unhash_stid(&stp->st_stid);
+	nfs4_unhash_stid(&stp->st_stid);
 }
 
 static void release_lock_stateid(struct nfs4_ol_stateid *stp)
@@ -1518,7 +1495,12 @@ unhash_session(struct nfsd4_session *ses)
 static int
 STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
 {
-	if (clid->cl_boot == nn->boot_time)
+	/*
+	 * We're assuming the clid was not given out from a boot
+	 * precisely 2^32 (about 136 years) before this one.  That seems
+	 * a safe assumption:
+	 */
+	if (clid->cl_boot == (u32)nn->boot_time)
 		return 0;
 	dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n",
 		clid->cl_boot, clid->cl_id, nn->boot_time);
@@ -1558,6 +1540,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 	INIT_LIST_HEAD(&clp->cl_lru);
 	INIT_LIST_HEAD(&clp->cl_callbacks);
 	INIT_LIST_HEAD(&clp->cl_revoked);
+#ifdef CONFIG_NFSD_PNFS
+	INIT_LIST_HEAD(&clp->cl_lo_states);
+#endif
 	spin_lock_init(&clp->cl_lock);
 	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	return clp;
@@ -1653,7 +1638,7 @@ __destroy_client(struct nfs4_client *clp)
 		nfs4_put_stid(&dp->dl_stid);
 	}
 	while (!list_empty(&clp->cl_revoked)) {
-		dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
+		dp = list_entry(clp->cl_revoked.next, struct nfs4_delegation, dl_recall_lru);
 		list_del_init(&dp->dl_recall_lru);
 		nfs4_put_stid(&dp->dl_stid);
 	}
@@ -1662,6 +1647,7 @@ __destroy_client(struct nfs4_client *clp)
 		nfs4_get_stateowner(&oo->oo_owner);
 		release_openowner(oo);
 	}
+	nfsd4_return_all_client_layouts(clp);
 	nfsd4_shutdown_callback(clp);
 	if (clp->cl_cb_conn.cb_xprt)
 		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
@@ -2145,8 +2131,11 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
 static void
 nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid)
 {
-	/* pNFS is not supported */
+#ifdef CONFIG_NFSD_PNFS
+	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS;
+#else
 	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS;
+#endif
 
 	/* Referrals are supported, Migration is not. */
 	new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER;
@@ -3074,6 +3063,10 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
 	fp->fi_share_deny = 0;
 	memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
 	memset(fp->fi_access, 0, sizeof(fp->fi_access));
+#ifdef CONFIG_NFSD_PNFS
+	INIT_LIST_HEAD(&fp->fi_lo_states);
+	atomic_set(&fp->fi_lo_recalls, 0);
+#endif
 	hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]);
 }
 
@@ -3300,7 +3293,7 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
 	struct nfs4_file *fp;
 
 	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash) {
-		if (nfsd_fh_match(&fp->fi_fhandle, fh)) {
+		if (fh_match(&fp->fi_fhandle, fh)) {
 			if (atomic_inc_not_zero(&fp->fi_ref))
 				return fp;
 		}
@@ -3308,7 +3301,7 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
 	return NULL;
 }
 
-static struct nfs4_file *
+struct nfs4_file *
 find_file(struct knfsd_fh *fh)
 {
 	struct nfs4_file *fp;
@@ -3477,7 +3470,8 @@ nfsd_break_deleg_cb(struct file_lock *fl)
 }
 
 static int
-nfsd_change_deleg_cb(struct file_lock **onlist, int arg, struct list_head *dispose)
+nfsd_change_deleg_cb(struct file_lock *onlist, int arg,
+		     struct list_head *dispose)
 {
 	if (arg & F_UNLCK)
 		return lease_modify(onlist, arg, dispose);
@@ -3855,12 +3849,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 	/* Race breaker */
 	if (fp->fi_deleg_file) {
 		status = 0;
-		atomic_inc(&fp->fi_delegees);
+		++fp->fi_delegees;
 		hash_delegation_locked(dp, fp);
 		goto out_unlock;
 	}
 	fp->fi_deleg_file = filp;
-	atomic_set(&fp->fi_delegees, 1);
+	fp->fi_delegees = 1;
 	hash_delegation_locked(dp, fp);
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&state_lock);
@@ -3901,7 +3895,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 		status = -EAGAIN;
 		goto out_unlock;
 	}
-	atomic_inc(&fp->fi_delegees);
+	++fp->fi_delegees;
 	hash_delegation_locked(dp, fp);
 	status = 0;
 out_unlock:
@@ -4294,7 +4288,7 @@ laundromat_main(struct work_struct *laundry)
 
 static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp)
 {
-	if (!nfsd_fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle))
+	if (!fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle))
 		return nfserr_bad_stateid;
 	return nfs_ok;
 }
@@ -4445,7 +4439,7 @@ out_unlock:
 	return status;
 }
 
-static __be32
+__be32
 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn)
@@ -4859,6 +4853,9 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
 
+	nfsd4_return_all_file_layouts(stp->st_stateowner->so_client,
+				      stp->st_stid.sc_file);
+
 	nfsd4_close_open_stateid(stp);
 
 	/* put reference from nfs4_preprocess_seqid_op */
@@ -5556,10 +5553,11 @@ out_nfserr:
 static bool
 check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 {
-	struct file_lock **flpp;
+	struct file_lock *fl;
 	int status = false;
 	struct file *filp = find_any_file(fp);
 	struct inode *inode;
+	struct file_lock_context *flctx;
 
 	if (!filp) {
 		/* Any valid lock stateid should have some sort of access */
@@ -5568,15 +5566,18 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 	}
 
 	inode = file_inode(filp);
+	flctx = inode->i_flctx;
 
-	spin_lock(&inode->i_lock);
-	for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) {
-		if ((*flpp)->fl_owner == (fl_owner_t)lowner) {
-			status = true;
-			break;
+	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
+		spin_lock(&flctx->flc_lock);
+		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+			if (fl->fl_owner == (fl_owner_t)lowner) {
+				status = true;
+				break;
+			}
 		}
+		spin_unlock(&flctx->flc_lock);
 	}
-	spin_unlock(&inode->i_lock);
 	fput(filp);
 	return status;
 }
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 15f7b73e0c0f..df5e66caf100 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -47,6 +47,7 @@
 #include "state.h"
 #include "cache.h"
 #include "netns.h"
+#include "pnfs.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -234,6 +235,26 @@ static char *savemem(struct nfsd4_compoundargs *argp, __be32 *p, int nbytes)
 	return ret;
 }
 
+/*
+ * We require the high 32 bits of 'seconds' to be 0, and
+ * we ignore all 32 bits of 'nseconds'.
+ */
+static __be32
+nfsd4_decode_time(struct nfsd4_compoundargs *argp, struct timespec *tv)
+{
+	DECODE_HEAD;
+	u64 sec;
+
+	READ_BUF(12);
+	p = xdr_decode_hyper(p, &sec);
+	tv->tv_sec = sec;
+	tv->tv_nsec = be32_to_cpup(p++);
+	if (tv->tv_nsec >= (u32)1000000000)
+		return nfserr_inval;
+
+	DECODE_TAIL;
+}
+
 static __be32
 nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval)
 {
@@ -267,7 +288,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 {
 	int expected_len, len = 0;
 	u32 dummy32;
-	u64 sec;
 	char *buf;
 
 	DECODE_HEAD;
@@ -358,15 +378,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		dummy32 = be32_to_cpup(p++);
 		switch (dummy32) {
 		case NFS4_SET_TO_CLIENT_TIME:
-			/* We require the high 32 bits of 'seconds' to be 0, and we ignore
-			   all 32 bits of 'nseconds'. */
-			READ_BUF(12);
 			len += 12;
-			p = xdr_decode_hyper(p, &sec);
-			iattr->ia_atime.tv_sec = (time_t)sec;
-			iattr->ia_atime.tv_nsec = be32_to_cpup(p++);
-			if (iattr->ia_atime.tv_nsec >= (u32)1000000000)
-				return nfserr_inval;
+			status = nfsd4_decode_time(argp, &iattr->ia_atime);
+			if (status)
+				return status;
 			iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET);
 			break;
 		case NFS4_SET_TO_SERVER_TIME:
@@ -382,15 +397,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		dummy32 = be32_to_cpup(p++);
 		switch (dummy32) {
 		case NFS4_SET_TO_CLIENT_TIME:
-			/* We require the high 32 bits of 'seconds' to be 0, and we ignore
-			   all 32 bits of 'nseconds'. */
-			READ_BUF(12);
 			len += 12;
-			p = xdr_decode_hyper(p, &sec);
-			iattr->ia_mtime.tv_sec = sec;
-			iattr->ia_mtime.tv_nsec = be32_to_cpup(p++);
-			if (iattr->ia_mtime.tv_nsec >= (u32)1000000000)
-				return nfserr_inval;
+			status = nfsd4_decode_time(argp, &iattr->ia_mtime);
+			if (status)
+				return status;
 			iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET);
 			break;
 		case NFS4_SET_TO_SERVER_TIME:
@@ -1513,6 +1523,127 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
 	DECODE_TAIL;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static __be32
+nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp,
+		struct nfsd4_getdeviceinfo *gdev)
+{
+	DECODE_HEAD;
+	u32 num, i;
+
+	READ_BUF(sizeof(struct nfsd4_deviceid) + 3 * 4);
+	COPYMEM(&gdev->gd_devid, sizeof(struct nfsd4_deviceid));
+	gdev->gd_layout_type = be32_to_cpup(p++);
+	gdev->gd_maxcount = be32_to_cpup(p++);
+	num = be32_to_cpup(p++);
+	if (num) {
+		READ_BUF(4 * num);
+		gdev->gd_notify_types = be32_to_cpup(p++);
+		for (i = 1; i < num; i++) {
+			if (be32_to_cpup(p++)) {
+				status = nfserr_inval;
+				goto out;
+			}
+		}
+	}
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutget *lgp)
+{
+	DECODE_HEAD;
+
+	READ_BUF(36);
+	lgp->lg_signal = be32_to_cpup(p++);
+	lgp->lg_layout_type = be32_to_cpup(p++);
+	lgp->lg_seg.iomode = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &lgp->lg_seg.offset);
+	p = xdr_decode_hyper(p, &lgp->lg_seg.length);
+	p = xdr_decode_hyper(p, &lgp->lg_minlength);
+	nfsd4_decode_stateid(argp, &lgp->lg_sid);
+	READ_BUF(4);
+	lgp->lg_maxcount = be32_to_cpup(p++);
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutcommit *lcp)
+{
+	DECODE_HEAD;
+	u32 timechange;
+
+	READ_BUF(20);
+	p = xdr_decode_hyper(p, &lcp->lc_seg.offset);
+	p = xdr_decode_hyper(p, &lcp->lc_seg.length);
+	lcp->lc_reclaim = be32_to_cpup(p++);
+	nfsd4_decode_stateid(argp, &lcp->lc_sid);
+	READ_BUF(4);
+	lcp->lc_newoffset = be32_to_cpup(p++);
+	if (lcp->lc_newoffset) {
+		READ_BUF(8);
+		p = xdr_decode_hyper(p, &lcp->lc_last_wr);
+	} else
+		lcp->lc_last_wr = 0;
+	READ_BUF(4);
+	timechange = be32_to_cpup(p++);
+	if (timechange) {
+		status = nfsd4_decode_time(argp, &lcp->lc_mtime);
+		if (status)
+			return status;
+	} else {
+		lcp->lc_mtime.tv_nsec = UTIME_NOW;
+	}
+	READ_BUF(8);
+	lcp->lc_layout_type = be32_to_cpup(p++);
+
+	/*
+	 * Save the layout update in XDR format and let the layout driver deal
+	 * with it later.
+	 */
+	lcp->lc_up_len = be32_to_cpup(p++);
+	if (lcp->lc_up_len > 0) {
+		READ_BUF(lcp->lc_up_len);
+		READMEM(lcp->lc_up_layout, lcp->lc_up_len);
+	}
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutreturn *lrp)
+{
+	DECODE_HEAD;
+
+	READ_BUF(16);
+	lrp->lr_reclaim = be32_to_cpup(p++);
+	lrp->lr_layout_type = be32_to_cpup(p++);
+	lrp->lr_seg.iomode = be32_to_cpup(p++);
+	lrp->lr_return_type = be32_to_cpup(p++);
+	if (lrp->lr_return_type == RETURN_FILE) {
+		READ_BUF(16);
+		p = xdr_decode_hyper(p, &lrp->lr_seg.offset);
+		p = xdr_decode_hyper(p, &lrp->lr_seg.length);
+		nfsd4_decode_stateid(argp, &lrp->lr_sid);
+		READ_BUF(4);
+		lrp->lrf_body_len = be32_to_cpup(p++);
+		if (lrp->lrf_body_len > 0) {
+			READ_BUF(lrp->lrf_body_len);
+			READMEM(lrp->lrf_body, lrp->lrf_body_len);
+		}
+	} else {
+		lrp->lr_seg.offset = 0;
+		lrp->lr_seg.length = NFS4_MAX_UINT64;
+	}
+
+	DECODE_TAIL;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static __be32
 nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp,
 		       struct nfsd4_fallocate *fallocate)
@@ -1607,11 +1738,19 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_DESTROY_SESSION]	= (nfsd4_dec)nfsd4_decode_destroy_session,
 	[OP_FREE_STATEID]	= (nfsd4_dec)nfsd4_decode_free_stateid,
 	[OP_GET_DIR_DELEGATION]	= (nfsd4_dec)nfsd4_decode_notsupp,
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO]	= (nfsd4_dec)nfsd4_decode_getdeviceinfo,
+	[OP_GETDEVICELIST]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_LAYOUTCOMMIT]	= (nfsd4_dec)nfsd4_decode_layoutcommit,
+	[OP_LAYOUTGET]		= (nfsd4_dec)nfsd4_decode_layoutget,
+	[OP_LAYOUTRETURN]	= (nfsd4_dec)nfsd4_decode_layoutreturn,
+#else
 	[OP_GETDEVICEINFO]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_GETDEVICELIST]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTCOMMIT]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTGET]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTRETURN]	= (nfsd4_dec)nfsd4_decode_notsupp,
+#endif
 	[OP_SECINFO_NO_NAME]	= (nfsd4_dec)nfsd4_decode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_dec)nfsd4_decode_sequence,
 	[OP_SET_SSV]		= (nfsd4_dec)nfsd4_decode_notsupp,
@@ -2539,6 +2678,30 @@ out_acl:
 			get_parent_attributes(exp, &stat);
 		p = xdr_encode_hyper(p, stat.ino);
 	}
+#ifdef CONFIG_NFSD_PNFS
+	if ((bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) ||
+	    (bmval2 & FATTR4_WORD2_LAYOUT_TYPES)) {
+		if (exp->ex_layout_type) {
+			p = xdr_reserve_space(xdr, 8);
+			if (!p)
+				goto out_resource;
+			*p++ = cpu_to_be32(1);
+			*p++ = cpu_to_be32(exp->ex_layout_type);
+		} else {
+			p = xdr_reserve_space(xdr, 4);
+			if (!p)
+				goto out_resource;
+			*p++ = cpu_to_be32(0);
+		}
+	}
+
+	if (bmval2 & FATTR4_WORD2_LAYOUT_BLKSIZE) {
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			goto out_resource;
+		*p++ = cpu_to_be32(stat.blksize);
+	}
+#endif /* CONFIG_NFSD_PNFS */
 	if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
 		status = nfsd4_encode_security_label(xdr, rqstp, context,
 								contextlen);
@@ -2768,16 +2931,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
 	if (entry_bytes > cd->rd_maxcount)
 		goto fail;
 	cd->rd_maxcount -= entry_bytes;
-	if (!cd->rd_dircount)
-		goto fail;
 	/*
 	 * RFC 3530 14.2.24 describes rd_dircount as only a "hint", so
 	 * let's always let through the first entry, at least:
 	 */
-	name_and_cookie = 4 * XDR_QUADLEN(namlen) + 8;
+	if (!cd->rd_dircount)
+		goto fail;
+	name_and_cookie = 4 + 4 * XDR_QUADLEN(namlen) + 8;
 	if (name_and_cookie > cd->rd_dircount && cd->cookie_offset)
 		goto fail;
 	cd->rd_dircount -= min(cd->rd_dircount, name_and_cookie);
+
 	cd->cookie_offset = cookie_offset;
 skip_entry:
 	cd->common.err = nfs_ok;
@@ -3814,6 +3978,156 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
 	return nfserr;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static __be32
+nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_getdeviceinfo *gdev)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	const struct nfsd4_layout_ops *ops =
+		nfsd4_layout_ops[gdev->gd_layout_type];
+	u32 starting_len = xdr->buf->len, needed_len;
+	__be32 *p;
+
+	dprintk("%s: err %d\n", __func__, nfserr);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_resource;
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		goto out;
+
+	*p++ = cpu_to_be32(gdev->gd_layout_type);
+
+	/* If maxcount is 0 then just update notifications */
+	if (gdev->gd_maxcount != 0) {
+		nfserr = ops->encode_getdeviceinfo(xdr, gdev);
+		if (nfserr) {
+			/*
+			 * We don't bother to burden the layout drivers with
+			 * enforcing gd_maxcount, just tell the client to
+			 * come back with a bigger buffer if it's not enough.
+			 */
+			if (xdr->buf->len + 4 > gdev->gd_maxcount)
+				goto toosmall;
+			goto out;
+		}
+	}
+
+	nfserr = nfserr_resource;
+	if (gdev->gd_notify_types) {
+		p = xdr_reserve_space(xdr, 4 + 4);
+		if (!p)
+			goto out;
+		*p++ = cpu_to_be32(1);			/* bitmap length */
+		*p++ = cpu_to_be32(gdev->gd_notify_types);
+	} else {
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			goto out;
+		*p++ = 0;
+	}
+
+	nfserr = 0;
+out:
+	kfree(gdev->gd_device);
+	dprintk("%s: done: %d\n", __func__, be32_to_cpu(nfserr));
+	return nfserr;
+
+toosmall:
+	dprintk("%s: maxcount too small\n", __func__);
+	needed_len = xdr->buf->len + 4 /* notifications */;
+	xdr_truncate_encode(xdr, starting_len);
+	p = xdr_reserve_space(xdr, 4);
+	if (!p) {
+		nfserr = nfserr_resource;
+	} else {
+		*p++ = cpu_to_be32(needed_len);
+		nfserr = nfserr_toosmall;
+	}
+	goto out;
+}
+
+static __be32
+nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_layoutget *lgp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	const struct nfsd4_layout_ops *ops =
+		nfsd4_layout_ops[lgp->lg_layout_type];
+	__be32 *p;
+
+	dprintk("%s: err %d\n", __func__, nfserr);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_resource;
+	p = xdr_reserve_space(xdr, 36 + sizeof(stateid_opaque_t));
+	if (!p)
+		goto out;
+
+	*p++ = cpu_to_be32(1);	/* we always set return-on-close */
+	*p++ = cpu_to_be32(lgp->lg_sid.si_generation);
+	p = xdr_encode_opaque_fixed(p, &lgp->lg_sid.si_opaque,
+				    sizeof(stateid_opaque_t));
+
+	*p++ = cpu_to_be32(1);	/* we always return a single layout */
+	p = xdr_encode_hyper(p, lgp->lg_seg.offset);
+	p = xdr_encode_hyper(p, lgp->lg_seg.length);
+	*p++ = cpu_to_be32(lgp->lg_seg.iomode);
+	*p++ = cpu_to_be32(lgp->lg_layout_type);
+
+	nfserr = ops->encode_layoutget(xdr, lgp);
+out:
+	kfree(lgp->lg_content);
+	return nfserr;
+}
+
+static __be32
+nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr,
+			  struct nfsd4_layoutcommit *lcp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(lcp->lc_size_chg);
+	if (lcp->lc_size_chg) {
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_hyper(p, lcp->lc_newsize);
+	}
+
+	return nfs_ok;
+}
+
+static __be32
+nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(lrp->lrs_present);
+	if (lrp->lrs_present)
+		nfsd4_encode_stateid(xdr, &lrp->lr_sid);
+	return nfs_ok;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static __be32
 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_seek *seek)
@@ -3890,11 +4204,19 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_DESTROY_SESSION]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_FREE_STATEID]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_GET_DIR_DELEGATION]	= (nfsd4_enc)nfsd4_encode_noop,
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO]	= (nfsd4_enc)nfsd4_encode_getdeviceinfo,
+	[OP_GETDEVICELIST]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_LAYOUTCOMMIT]	= (nfsd4_enc)nfsd4_encode_layoutcommit,
+	[OP_LAYOUTGET]		= (nfsd4_enc)nfsd4_encode_layoutget,
+	[OP_LAYOUTRETURN]	= (nfsd4_enc)nfsd4_encode_layoutreturn,
+#else
 	[OP_GETDEVICEINFO]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_GETDEVICELIST]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTCOMMIT]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTGET]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTRETURN]	= (nfsd4_enc)nfsd4_encode_noop,
+#endif
 	[OP_SECINFO_NO_NAME]	= (nfsd4_enc)nfsd4_encode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_enc)nfsd4_encode_sequence,
 	[OP_SET_SSV]		= (nfsd4_enc)nfsd4_encode_noop,
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 19ace74d35f6..aa47d75ddb26 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -21,6 +21,7 @@
 #include "cache.h"
 #include "state.h"
 #include "netns.h"
+#include "pnfs.h"
 
 /*
  *	We have a single directory with several nodes in it.
@@ -1258,9 +1259,12 @@ static int __init init_nfsd(void)
 	retval = nfsd4_init_slabs();
 	if (retval)
 		goto out_unregister_pernet;
-	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
+	retval = nfsd4_init_pnfs();
 	if (retval)
 		goto out_free_slabs;
+	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
+	if (retval)
+		goto out_exit_pnfs;
 	nfsd_stat_init();	/* Statistics */
 	retval = nfsd_reply_cache_init();
 	if (retval)
@@ -1282,6 +1286,8 @@ out_free_lockd:
 out_free_stat:
 	nfsd_stat_shutdown();
 	nfsd_fault_inject_cleanup();
+out_exit_pnfs:
+	nfsd4_exit_pnfs();
 out_free_slabs:
 	nfsd4_free_slabs();
 out_unregister_pernet:
@@ -1299,6 +1305,7 @@ static void __exit exit_nfsd(void)
 	nfsd_stat_shutdown();
 	nfsd_lockd_shutdown();
 	nfsd4_free_slabs();
+	nfsd4_exit_pnfs();
 	nfsd_fault_inject_cleanup();
 	unregister_filesystem(&nfsd_fs_type);
 	unregister_pernet_subsys(&nfsd_net_ops);
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 33a46a8dfaf7..565c4da1a9eb 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -325,15 +325,27 @@ void		nfsd_lockd_shutdown(void);
 
 #define NFSD4_SUPPORTED_ATTRS_WORD2 0
 
+/* 4.1 */
+#ifdef CONFIG_NFSD_PNFS
+#define PNFSD_SUPPORTED_ATTRS_WORD1	FATTR4_WORD1_FS_LAYOUT_TYPES
+#define PNFSD_SUPPORTED_ATTRS_WORD2 \
+(FATTR4_WORD2_LAYOUT_BLKSIZE	| FATTR4_WORD2_LAYOUT_TYPES)
+#else
+#define PNFSD_SUPPORTED_ATTRS_WORD1	0
+#define PNFSD_SUPPORTED_ATTRS_WORD2	0
+#endif /* CONFIG_NFSD_PNFS */
+
 #define NFSD4_1_SUPPORTED_ATTRS_WORD0 \
 	NFSD4_SUPPORTED_ATTRS_WORD0
 
 #define NFSD4_1_SUPPORTED_ATTRS_WORD1 \
-	NFSD4_SUPPORTED_ATTRS_WORD1
+	(NFSD4_SUPPORTED_ATTRS_WORD1	| PNFSD_SUPPORTED_ATTRS_WORD1)
 
 #define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
-	(NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT)
+	(NFSD4_SUPPORTED_ATTRS_WORD2	| PNFSD_SUPPORTED_ATTRS_WORD2 | \
+	 FATTR4_WORD2_SUPPATTR_EXCLCREAT)
 
+/* 4.2 */
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #define NFSD4_2_SECURITY_ATTRS		FATTR4_WORD2_SECURITY_LABEL
 #else
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 965b478d50fc..e9fa966fc37f 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -114,8 +114,8 @@ static inline __be32 check_pseudo_root(struct svc_rqst *rqstp,
 	 * We're exposing only the directories and symlinks that have to be
 	 * traversed on the way to real exports:
 	 */
-	if (unlikely(!S_ISDIR(dentry->d_inode->i_mode) &&
-		     !S_ISLNK(dentry->d_inode->i_mode)))
+	if (unlikely(!d_is_dir(dentry) &&
+		     !d_is_symlink(dentry)))
 		return nfserr_stale;
 	/*
 	 * A pseudoroot export gives permission to access only one
@@ -259,7 +259,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 		goto out;
 	}
 
-	if (S_ISDIR(dentry->d_inode->i_mode) &&
+	if (d_is_dir(dentry) &&
 			(dentry->d_flags & DCACHE_DISCONNECTED)) {
 		printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %pd2\n",
 				dentry);
@@ -414,7 +414,7 @@ static inline void _fh_update_old(struct dentry *dentry,
 {
 	fh->ofh_ino = ino_t_to_u32(dentry->d_inode->i_ino);
 	fh->ofh_generation = dentry->d_inode->i_generation;
-	if (S_ISDIR(dentry->d_inode->i_mode) ||
+	if (d_is_dir(dentry) ||
 	    (exp->ex_flags & NFSEXP_NOSUBTREECHECK))
 		fh->ofh_dirino = 0;
 }
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 08236d70c667..f22920442172 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -187,6 +187,24 @@ fh_init(struct svc_fh *fhp, int maxsize)
 	return fhp;
 }
 
+static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
+{
+	if (fh1->fh_size != fh2->fh_size)
+		return false;
+	if (memcmp(fh1->fh_base.fh_pad, fh2->fh_base.fh_pad, fh1->fh_size) != 0)
+		return false;
+	return true;
+}
+
+static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
+{
+	if (fh1->fh_fsid_type != fh2->fh_fsid_type)
+		return false;
+	if (memcmp(fh1->fh_fsid, fh2->fh_fsid, key_len(fh1->fh_fsid_type)) != 0)
+		return false;
+	return true;
+}
+
 #ifdef CONFIG_NFSD_V3
 /*
  * The wcc data stored in current_fh should be cleared
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 314f5c8f8f1a..9277cc91c21b 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -119,6 +119,7 @@ struct svc_program		nfsd_program = {
 static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = {
 	[0] = 1,
 	[1] = 1,
+	[2] = 1,
 };
 
 int nfsd_vers(int vers, enum vers_op change)
diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
new file mode 100644
index 000000000000..d4c4453674c6
--- /dev/null
+++ b/fs/nfsd/pnfs.h
@@ -0,0 +1,86 @@
+#ifndef _FS_NFSD_PNFS_H
+#define _FS_NFSD_PNFS_H 1
+
+#ifdef CONFIG_NFSD_V4
+#include <linux/exportfs.h>
+#include <linux/nfsd/export.h>
+
+#include "state.h"
+#include "xdr4.h"
+
+struct xdr_stream;
+
+struct nfsd4_deviceid_map {
+	struct list_head	hash;
+	u64			idx;
+	int			fsid_type;
+	u32			fsid[];
+};
+
+struct nfsd4_layout_ops {
+	u32		notify_types;
+
+	__be32 (*proc_getdeviceinfo)(struct super_block *sb,
+			struct nfsd4_getdeviceinfo *gdevp);
+	__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
+			struct nfsd4_getdeviceinfo *gdevp);
+
+	__be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp,
+			struct nfsd4_layoutget *lgp);
+	__be32 (*encode_layoutget)(struct xdr_stream *,
+			struct nfsd4_layoutget *lgp);
+
+	__be32 (*proc_layoutcommit)(struct inode *inode,
+			struct nfsd4_layoutcommit *lcp);
+};
+
+extern const struct nfsd4_layout_ops *nfsd4_layout_ops[];
+extern const struct nfsd4_layout_ops bl_layout_ops;
+
+__be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp);
+__be32 nfsd4_insert_layout(struct nfsd4_layoutget *lgp,
+		struct nfs4_layout_stateid *ls);
+__be32 nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp);
+__be32 nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp);
+int nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation);
+struct nfsd4_deviceid_map *nfsd4_find_devid_map(int idx);
+#endif /* CONFIG_NFSD_V4 */
+
+#ifdef CONFIG_NFSD_PNFS
+void nfsd4_setup_layout_type(struct svc_export *exp);
+void nfsd4_return_all_client_layouts(struct nfs4_client *);
+void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
+		struct nfs4_file *fp);
+int nfsd4_init_pnfs(void);
+void nfsd4_exit_pnfs(void);
+#else
+struct nfs4_client;
+struct nfs4_file;
+
+static inline void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+}
+
+static inline void nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+}
+static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
+		struct nfs4_file *fp)
+{
+}
+static inline void nfsd4_exit_pnfs(void)
+{
+}
+static inline int nfsd4_init_pnfs(void)
+{
+	return 0;
+}
+#endif /* CONFIG_NFSD_PNFS */
+#endif /* _FS_NFSD_PNFS_H */
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 9d3be371240a..4f3bfeb11766 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -92,6 +92,7 @@ struct nfs4_stid {
 /* For a deleg stateid kept around only to process free_stateid's: */
 #define NFS4_REVOKED_DELEG_STID 16
 #define NFS4_CLOSED_DELEG_STID 32
+#define NFS4_LAYOUT_STID 64
 	unsigned char sc_type;
 	stateid_t sc_stateid;
 	struct nfs4_client *sc_client;
@@ -297,6 +298,9 @@ struct nfs4_client {
 	struct list_head	cl_delegations;
 	struct list_head	cl_revoked;	/* unacknowledged, revoked 4.1 state */
 	struct list_head        cl_lru;         /* tail queue */
+#ifdef CONFIG_NFSD_PNFS
+	struct list_head	cl_lo_states;	/* outstanding layout states */
+#endif
 	struct xdr_netobj	cl_name; 	/* id generated by client */
 	nfs4_verifier		cl_verifier; 	/* generated by client */
 	time_t                  cl_time;        /* time of last lease renewal */
@@ -493,9 +497,13 @@ struct nfs4_file {
 	atomic_t		fi_access[2];
 	u32			fi_share_deny;
 	struct file		*fi_deleg_file;
-	atomic_t		fi_delegees;
+	int			fi_delegees;
 	struct knfsd_fh		fi_fhandle;
 	bool			fi_had_conflict;
+#ifdef CONFIG_NFSD_PNFS
+	struct list_head	fi_lo_states;
+	atomic_t		fi_lo_recalls;
+#endif
 };
 
 /*
@@ -528,6 +536,24 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
 	return container_of(s, struct nfs4_ol_stateid, st_stid);
 }
 
+struct nfs4_layout_stateid {
+	struct nfs4_stid		ls_stid;
+	struct list_head		ls_perclnt;
+	struct list_head		ls_perfile;
+	spinlock_t			ls_lock;
+	struct list_head		ls_layouts;
+	u32				ls_layout_type;
+	struct file			*ls_file;
+	struct nfsd4_callback		ls_recall;
+	stateid_t			ls_recall_sid;
+	bool				ls_recalled;
+};
+
+static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s)
+{
+	return container_of(s, struct nfs4_layout_stateid, ls_stid);
+}
+
 /* flags for preprocess_seqid_op() */
 #define RD_STATE	        0x00000010
 #define WR_STATE	        0x00000020
@@ -535,6 +561,7 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
 enum nfsd4_cb_op {
 	NFSPROC4_CLNT_CB_NULL = 0,
 	NFSPROC4_CLNT_CB_RECALL,
+	NFSPROC4_CLNT_CB_LAYOUT,
 	NFSPROC4_CLNT_CB_SEQUENCE,
 };
 
@@ -545,6 +572,12 @@ struct nfsd_net;
 extern __be32 nfs4_preprocess_stateid_op(struct net *net,
 		struct nfsd4_compound_state *cstate,
 		stateid_t *stateid, int flags, struct file **filp);
+__be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
+		     stateid_t *stateid, unsigned char typemask,
+		     struct nfs4_stid **s, struct nfsd_net *nn);
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
+		struct kmem_cache *slab);
+void nfs4_unhash_stid(struct nfs4_stid *s);
 void nfs4_put_stid(struct nfs4_stid *s);
 void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *);
 extern void nfs4_release_reclaim(struct nfsd_net *);
@@ -567,6 +600,14 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
 							struct nfsd_net *nn);
 extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn);
 
+struct nfs4_file *find_file(struct knfsd_fh *fh);
+void put_nfs4_file(struct nfs4_file *fi);
+static inline void get_nfs4_file(struct nfs4_file *fi)
+{
+	atomic_inc(&fi->fi_ref);
+}
+struct file *find_any_file(struct nfs4_file *f);
+
 /* grace period management */
 void nfsd4_end_grace(struct nfsd_net *nn);
 
diff --git a/fs/nfsd/trace.c b/fs/nfsd/trace.c
new file mode 100644
index 000000000000..82f89070594c
--- /dev/null
+++ b/fs/nfsd/trace.c
@@ -0,0 +1,5 @@
+
+#include "state.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
new file mode 100644
index 000000000000..c668520c344b
--- /dev/null
+++ b/fs/nfsd/trace.h
@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM nfsd
+
+#if !defined(_NFSD_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _NFSD_TRACE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(nfsd_stateid_class,
+	TP_PROTO(stateid_t *stp),
+	TP_ARGS(stp),
+	TP_STRUCT__entry(
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(u32, si_id)
+		__field(u32, si_generation)
+	),
+	TP_fast_assign(
+		__entry->cl_boot = stp->si_opaque.so_clid.cl_boot;
+		__entry->cl_id = stp->si_opaque.so_clid.cl_id;
+		__entry->si_id = stp->si_opaque.so_id;
+		__entry->si_generation = stp->si_generation;
+	),
+	TP_printk("client %08x:%08x stateid %08x:%08x",
+		__entry->cl_boot,
+		__entry->cl_id,
+		__entry->si_id,
+		__entry->si_generation)
+)
+
+#define DEFINE_STATEID_EVENT(name) \
+DEFINE_EVENT(nfsd_stateid_class, name, \
+	TP_PROTO(stateid_t *stp), \
+	TP_ARGS(stp))
+DEFINE_STATEID_EVENT(layoutstate_alloc);
+DEFINE_STATEID_EVENT(layoutstate_unhash);
+DEFINE_STATEID_EVENT(layoutstate_free);
+DEFINE_STATEID_EVENT(layout_get_lookup_fail);
+DEFINE_STATEID_EVENT(layout_commit_lookup_fail);
+DEFINE_STATEID_EVENT(layout_return_lookup_fail);
+DEFINE_STATEID_EVENT(layout_recall);
+DEFINE_STATEID_EVENT(layout_recall_done);
+DEFINE_STATEID_EVENT(layout_recall_fail);
+DEFINE_STATEID_EVENT(layout_recall_release);
+
+#endif /* _NFSD_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 5685c679dd93..368526582429 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -615,9 +615,9 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor
 	export = fhp->fh_export;
 	dentry = fhp->fh_dentry;
 
-	if (S_ISREG(dentry->d_inode->i_mode))
+	if (d_is_reg(dentry))
 		map = nfs3_regaccess;
-	else if (S_ISDIR(dentry->d_inode->i_mode))
+	else if (d_is_dir(dentry))
 		map = nfs3_diraccess;
 	else
 		map = nfs3_anyaccess;
@@ -1402,7 +1402,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 
 		switch (createmode) {
 		case NFS3_CREATE_UNCHECKED:
-			if (! S_ISREG(dchild->d_inode->i_mode))
+			if (! d_is_reg(dchild))
 				goto out;
 			else if (truncp) {
 				/* in nfsv4, we need to treat this case a little
@@ -1615,7 +1615,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 	if (err)
 		goto out;
 	err = nfserr_isdir;
-	if (S_ISDIR(tfhp->fh_dentry->d_inode->i_mode))
+	if (d_is_dir(tfhp->fh_dentry))
 		goto out;
 	err = nfserr_perm;
 	if (!len)
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 90a5925bd6ab..0bda93e58e1b 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -428,6 +428,61 @@ struct nfsd4_reclaim_complete {
 	u32 rca_one_fs;
 };
 
+struct nfsd4_deviceid {
+	u64			fsid_idx;
+	u32			generation;
+	u32			pad;
+};
+
+struct nfsd4_layout_seg {
+	u32			iomode;
+	u64			offset;
+	u64			length;
+};
+
+struct nfsd4_getdeviceinfo {
+	struct nfsd4_deviceid	gd_devid;	/* request */
+	u32			gd_layout_type;	/* request */
+	u32			gd_maxcount;	/* request */
+	u32			gd_notify_types;/* request - response */
+	void			*gd_device;	/* response */
+};
+
+struct nfsd4_layoutget {
+	u64			lg_minlength;	/* request */
+	u32			lg_signal;	/* request */
+	u32			lg_layout_type;	/* request */
+	u32			lg_maxcount;	/* request */
+	stateid_t		lg_sid;		/* request/response */
+	struct nfsd4_layout_seg	lg_seg;		/* request/response */
+	void			*lg_content;	/* response */
+};
+
+struct nfsd4_layoutcommit {
+	stateid_t		lc_sid;		/* request */
+	struct nfsd4_layout_seg	lc_seg;		/* request */
+	u32			lc_reclaim;	/* request */
+	u32			lc_newoffset;	/* request */
+	u64			lc_last_wr;	/* request */
+	struct timespec		lc_mtime;	/* request */
+	u32			lc_layout_type;	/* request */
+	u32			lc_up_len;	/* layout length */
+	void			*lc_up_layout;	/* decoded by callback */
+	u32			lc_size_chg;	/* boolean for response */
+	u64			lc_newsize;	/* response */
+};
+
+struct nfsd4_layoutreturn {
+	u32			lr_return_type;	/* request */
+	u32			lr_layout_type;	/* request */
+	struct nfsd4_layout_seg	lr_seg;		/* request */
+	u32			lr_reclaim;	/* request */
+	u32			lrf_body_len;	/* request */
+	void			*lrf_body;	/* request */
+	stateid_t		lr_sid;		/* request/response */
+	u32			lrs_present;	/* response */
+};
+
 struct nfsd4_fallocate {
 	/* request */
 	stateid_t	falloc_stateid;
@@ -491,6 +546,10 @@ struct nfsd4_op {
 		struct nfsd4_reclaim_complete	reclaim_complete;
 		struct nfsd4_test_stateid	test_stateid;
 		struct nfsd4_free_stateid	free_stateid;
+		struct nfsd4_getdeviceinfo	getdeviceinfo;
+		struct nfsd4_layoutget		layoutget;
+		struct nfsd4_layoutcommit	layoutcommit;
+		struct nfsd4_layoutreturn	layoutreturn;
 
 		/* NFSv4.2 */
 		struct nfsd4_fallocate		allocate;
diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h
index c5c55dfb91a9..c47f6fdb111a 100644
--- a/fs/nfsd/xdr4cb.h
+++ b/fs/nfsd/xdr4cb.h
@@ -21,3 +21,10 @@
 #define NFS4_dec_cb_recall_sz		(cb_compound_dec_hdr_sz  +      \
 					cb_sequence_dec_sz +            \
 					op_dec_sz)
+#define NFS4_enc_cb_layout_sz		(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + 3 +                         \
+					enc_nfs4_fh_sz + 4)
+#define NFS4_dec_cb_layout_sz		(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index b2e3ff347620..ecdbae19a766 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -31,6 +31,8 @@
 #include "alloc.h"
 #include "dat.h"
 
+static void __nilfs_btree_init(struct nilfs_bmap *bmap);
+
 static struct nilfs_btree_path *nilfs_btree_alloc_path(void)
 {
 	struct nilfs_btree_path *path;
@@ -368,6 +370,34 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
 	return ret;
 }
 
+/**
+ * nilfs_btree_root_broken - verify consistency of btree root node
+ * @node: btree root node to be examined
+ * @ino: inode number
+ *
+ * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned.
+ */
+static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
+				   unsigned long ino)
+{
+	int level, flags, nchildren;
+	int ret = 0;
+
+	level = nilfs_btree_node_get_level(node);
+	flags = nilfs_btree_node_get_flags(node);
+	nchildren = nilfs_btree_node_get_nchildren(node);
+
+	if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN ||
+		     level > NILFS_BTREE_LEVEL_MAX ||
+		     nchildren < 0 ||
+		     nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) {
+		pr_crit("NILFS: bad btree root (inode number=%lu): level = %d, flags = 0x%x, nchildren = %d\n",
+			ino, level, flags, nchildren);
+		ret = 1;
+	}
+	return ret;
+}
+
 int nilfs_btree_broken_node_block(struct buffer_head *bh)
 {
 	int ret;
@@ -1713,7 +1743,7 @@ nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree,
 
 	/* convert and insert */
 	dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL;
-	nilfs_btree_init(btree);
+	__nilfs_btree_init(btree);
 	if (nreq != NULL) {
 		nilfs_bmap_commit_alloc_ptr(btree, dreq, dat);
 		nilfs_bmap_commit_alloc_ptr(btree, nreq, dat);
@@ -2294,12 +2324,23 @@ static const struct nilfs_bmap_operations nilfs_btree_ops_gc = {
 	.bop_gather_data	=	NULL,
 };
 
-int nilfs_btree_init(struct nilfs_bmap *bmap)
+static void __nilfs_btree_init(struct nilfs_bmap *bmap)
 {
 	bmap->b_ops = &nilfs_btree_ops;
 	bmap->b_nchildren_per_block =
 		NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap));
-	return 0;
+}
+
+int nilfs_btree_init(struct nilfs_bmap *bmap)
+{
+	int ret = 0;
+
+	__nilfs_btree_init(bmap);
+
+	if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap),
+				    bmap->b_inode->i_ino))
+		ret = -EIO;
+	return ret;
 }
 
 void nilfs_btree_init_gc(struct nilfs_bmap *bmap)
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 3a03e0aea1fb..a8c728acb7a8 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -128,7 +128,6 @@ static const struct vm_operations_struct nilfs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= nilfs_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 57ceaf33d177..748ca238915a 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -172,7 +172,6 @@ int nilfs_init_gcinode(struct inode *inode)
 	inode->i_mode = S_IFREG;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 	inode->i_mapping->a_ops = &empty_aops;
-	inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
 
 	ii->i_flags = 0;
 	nilfs_bmap_init_gc(ii->i_bmap);
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index c4dcd1db57ee..892cf5ffdb8e 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -429,7 +429,6 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz)
 
 	inode->i_mode = S_IFREG;
 	mapping_set_gfp_mask(inode->i_mapping, gfp_mask);
-	inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
 
 	inode->i_op = &def_mdt_iops;
 	inode->i_fop = &def_mdt_fops;
@@ -457,13 +456,12 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode,
 			       struct nilfs_shadow_map *shadow)
 {
 	struct nilfs_mdt_info *mi = NILFS_MDT(inode);
-	struct backing_dev_info *bdi = inode->i_sb->s_bdi;
 
 	INIT_LIST_HEAD(&shadow->frozen_buffers);
 	address_space_init_once(&shadow->frozen_data);
-	nilfs_mapping_init(&shadow->frozen_data, inode, bdi);
+	nilfs_mapping_init(&shadow->frozen_data, inode);
 	address_space_init_once(&shadow->frozen_btnodes);
-	nilfs_mapping_init(&shadow->frozen_btnodes, inode, bdi);
+	nilfs_mapping_init(&shadow->frozen_btnodes, inode);
 	mi->mi_shadow = shadow;
 	return 0;
 }
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index da276640f776..700ecbcca55d 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -461,14 +461,12 @@ unsigned nilfs_page_count_clean_buffers(struct page *page,
 	return nc;
 }
 
-void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
-			struct backing_dev_info *bdi)
+void nilfs_mapping_init(struct address_space *mapping, struct inode *inode)
 {
 	mapping->host = inode;
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
 	mapping->private_data = NULL;
-	mapping->backing_dev_info = bdi;
 	mapping->a_ops = &empty_aops;
 }
 
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index ef30c5c2426f..a43b8287d012 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -57,8 +57,7 @@ int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
 void nilfs_copy_back_pages(struct address_space *, struct address_space *);
 void nilfs_clear_dirty_page(struct page *, bool);
 void nilfs_clear_dirty_pages(struct address_space *, bool);
-void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
-			struct backing_dev_info *bdi);
+void nilfs_mapping_init(struct address_space *mapping, struct inode *inode);
 unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);
 unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
 					    sector_t start_blk,
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 469086b9f99b..0c3f303baf32 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1907,6 +1907,7 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
 					     struct the_nilfs *nilfs)
 {
 	struct nilfs_inode_info *ii, *n;
+	int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE);
 	int defer_iput = false;
 
 	spin_lock(&nilfs->ns_inode_lock);
@@ -1919,10 +1920,10 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
 		brelse(ii->i_bh);
 		ii->i_bh = NULL;
 		list_del_init(&ii->i_dirty);
-		if (!ii->vfs_inode.i_nlink) {
+		if (!ii->vfs_inode.i_nlink || during_mount) {
 			/*
-			 * Defer calling iput() to avoid a deadlock
-			 * over I_SYNC flag for inodes with i_nlink == 0
+			 * Defer calling iput() to avoid deadlocks if
+			 * i_nlink == 0 or mount is not yet finished.
 			 */
 			list_add_tail(&ii->i_dirty, &sci->sc_iput_queue);
 			defer_iput = true;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 2e5b3ec85b8f..5bc2a1cf73c3 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -166,7 +166,7 @@ struct inode *nilfs_alloc_inode(struct super_block *sb)
 	ii->i_state = 0;
 	ii->i_cno = 0;
 	ii->vfs_inode.i_version = 1;
-	nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode, sb->s_bdi);
+	nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode);
 	return &ii->vfs_inode;
 }
 
@@ -1057,7 +1057,6 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct the_nilfs *nilfs;
 	struct nilfs_root *fsroot;
-	struct backing_dev_info *bdi;
 	__u64 cno;
 	int err;
 
@@ -1077,8 +1076,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_time_gran = 1;
 	sb->s_max_links = NILFS_LINK_MAX;
 
-	bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
-	sb->s_bdi = bdi ? : &default_backing_dev_info;
+	sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info;
 
 	err = load_nilfs(nilfs, sb);
 	if (err)
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 30d3addfad75..d2f97ecca6a5 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -115,8 +115,8 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
 		return false;
 
 	/* sorry, fanotify only gives a damn about files and dirs */
-	if (!S_ISREG(path->dentry->d_inode->i_mode) &&
-	    !S_ISDIR(path->dentry->d_inode->i_mode))
+	if (!d_is_reg(path->dentry) &&
+	    !d_can_lookup(path->dentry))
 		return false;
 
 	if (inode_mark && vfsmnt_mark) {
@@ -139,11 +139,12 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
 		BUG();
 	}
 
-	if (S_ISDIR(path->dentry->d_inode->i_mode) &&
-	    (marks_ignored_mask & FS_ISDIR))
+	if (d_is_dir(path->dentry) &&
+	    !(marks_mask & FS_ISDIR & ~marks_ignored_mask))
 		return false;
 
-	if (event_mask & marks_mask & ~marks_ignored_mask)
+	if (event_mask & FAN_ALL_OUTGOING_EVENTS & marks_mask &
+				 ~marks_ignored_mask)
 		return true;
 
 	return false;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index bff8567aa42d..cf275500a665 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -487,20 +487,27 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
 					    unsigned int flags,
 					    int *destroy)
 {
-	__u32 oldmask;
+	__u32 oldmask = 0;
 
 	spin_lock(&fsn_mark->lock);
 	if (!(flags & FAN_MARK_IGNORED_MASK)) {
+		__u32 tmask = fsn_mark->mask & ~mask;
+
+		if (flags & FAN_MARK_ONDIR)
+			tmask &= ~FAN_ONDIR;
+
 		oldmask = fsn_mark->mask;
-		fsnotify_set_mark_mask_locked(fsn_mark, (oldmask & ~mask));
+		fsnotify_set_mark_mask_locked(fsn_mark, tmask);
 	} else {
-		oldmask = fsn_mark->ignored_mask;
-		fsnotify_set_mark_ignored_mask_locked(fsn_mark, (oldmask & ~mask));
+		__u32 tmask = fsn_mark->ignored_mask & ~mask;
+		if (flags & FAN_MARK_ONDIR)
+			tmask &= ~FAN_ONDIR;
+
+		fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
 	}
+	*destroy = !(fsn_mark->mask | fsn_mark->ignored_mask);
 	spin_unlock(&fsn_mark->lock);
 
-	*destroy = !(oldmask & ~mask);
-
 	return mask & oldmask;
 }
 
@@ -569,20 +576,22 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
 
 	spin_lock(&fsn_mark->lock);
 	if (!(flags & FAN_MARK_IGNORED_MASK)) {
+		__u32 tmask = fsn_mark->mask | mask;
+
+		if (flags & FAN_MARK_ONDIR)
+			tmask |= FAN_ONDIR;
+
 		oldmask = fsn_mark->mask;
-		fsnotify_set_mark_mask_locked(fsn_mark, (oldmask | mask));
+		fsnotify_set_mark_mask_locked(fsn_mark, tmask);
 	} else {
 		__u32 tmask = fsn_mark->ignored_mask | mask;
+		if (flags & FAN_MARK_ONDIR)
+			tmask |= FAN_ONDIR;
+
 		fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
 		if (flags & FAN_MARK_IGNORED_SURV_MODIFY)
 			fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
 	}
-
-	if (!(flags & FAN_MARK_ONDIR)) {
-		__u32 tmask = fsn_mark->ignored_mask | FAN_ONDIR;
-		fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
-	}
-
 	spin_unlock(&fsn_mark->lock);
 
 	return mask & ~oldmask;
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 643faa44f22b..1da9b2d184dc 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -19,6 +19,7 @@
  * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
 #include <linux/gfp.h>
 #include <linux/pagemap.h>
@@ -2091,7 +2092,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
 	count = iov_length(iov, nr_segs);
 	pos = *ppos;
 	/* We can write back this queue in page reclaim. */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 	written = 0;
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 7e8282dcea2a..c58a1bcfda0f 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -245,16 +245,14 @@ int ocfs2_set_acl(handle_t *handle,
 			ret = posix_acl_equiv_mode(acl, &mode);
 			if (ret < 0)
 				return ret;
-			else {
-				if (ret == 0)
-					acl = NULL;
 
-				ret = ocfs2_acl_set_mode(inode, di_bh,
-							 handle, mode);
-				if (ret)
-					return ret;
+			if (ret == 0)
+				acl = NULL;
 
-			}
+			ret = ocfs2_acl_set_mode(inode, di_bh,
+						 handle, mode);
+			if (ret)
+				return ret;
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index fcae9ef1a328..044158bd22be 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6873,7 +6873,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
 		mlog_errno(ret);
-		goto out_unlock;
+		goto out;
 	}
 
 	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
@@ -6931,7 +6931,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 		if (ret) {
 			mlog_errno(ret);
 			need_free = 1;
-			goto out_commit;
+			goto out_unlock;
 		}
 
 		page_end = PAGE_CACHE_SIZE;
@@ -6964,12 +6964,16 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 		if (ret) {
 			mlog_errno(ret);
 			need_free = 1;
-			goto out_commit;
+			goto out_unlock;
 		}
 
 		inode->i_blocks = ocfs2_inode_sector_count(inode);
 	}
 
+out_unlock:
+	if (pages)
+		ocfs2_unlock_and_free_pages(pages, num_pages);
+
 out_commit:
 	if (ret < 0 && did_quota)
 		dquot_free_space_nodirty(inode,
@@ -6989,15 +6993,11 @@ out_commit:
 
 	ocfs2_commit_trans(osb, handle);
 
-out_unlock:
+out:
 	if (data_ac)
 		ocfs2_free_alloc_context(data_ac);
-
-out:
-	if (pages) {
-		ocfs2_unlock_and_free_pages(pages, num_pages);
+	if (pages)
 		kfree(pages);
-	}
 
 	return ret;
 }
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 46d93e941f3d..44db1808cdb5 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -28,6 +28,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/mpage.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
 
 #include <cluster/masklog.h>
 
@@ -47,6 +48,9 @@
 #include "ocfs2_trace.h"
 
 #include "buffer_head_io.h"
+#include "dir.h"
+#include "namei.h"
+#include "sysfile.h"
 
 static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
@@ -506,18 +510,21 @@ bail:
  *
  * called like this: dio->get_blocks(dio->inode, fs_startblk,
  * 					fs_count, map_bh, dio->rw == WRITE);
- *
- * Note that we never bother to allocate blocks here, and thus ignore the
- * create argument.
  */
 static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 				     struct buffer_head *bh_result, int create)
 {
 	int ret;
+	u32 cpos = 0;
+	int alloc_locked = 0;
 	u64 p_blkno, inode_blocks, contig_blocks;
 	unsigned int ext_flags;
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
 	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+	unsigned long len = bh_result->b_size;
+	unsigned int clusters_to_alloc = 0;
+
+	cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock);
 
 	/* This function won't even be called if the request isn't all
 	 * nicely aligned and of the right size, so there's no need
@@ -539,6 +546,40 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 	/* We should already CoW the refcounted extent in case of create. */
 	BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
 
+	/* allocate blocks if no p_blkno is found, and create == 1 */
+	if (!p_blkno && create) {
+		ret = ocfs2_inode_lock(inode, NULL, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		alloc_locked = 1;
+
+		/* fill hole, allocate blocks can't be larger than the size
+		 * of the hole */
+		clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
+		if (clusters_to_alloc > contig_blocks)
+			clusters_to_alloc = contig_blocks;
+
+		/* allocate extent and insert them into the extent tree */
+		ret = ocfs2_extend_allocation(inode, cpos,
+				clusters_to_alloc, 0);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
+				&contig_blocks, &ext_flags);
+		if (ret < 0) {
+			mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
+					(unsigned long long)iblock);
+			ret = -EIO;
+			goto bail;
+		}
+	}
+
 	/*
 	 * get_more_blocks() expects us to describe a hole by clearing
 	 * the mapped bit on bh_result().
@@ -556,6 +597,8 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 		contig_blocks = max_blocks;
 	bh_result->b_size = contig_blocks << blocksize_bits;
 bail:
+	if (alloc_locked)
+		ocfs2_inode_unlock(inode, 1);
 	return ret;
 }
 
@@ -597,6 +640,184 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int ocfs2_is_overwrite(struct ocfs2_super *osb,
+		struct inode *inode, loff_t offset)
+{
+	int ret = 0;
+	u32 v_cpos = 0;
+	u32 p_cpos = 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
+	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+			&num_clusters, &ext_flags);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN))
+		return 1;
+
+	return 0;
+}
+
+static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
+		struct iov_iter *iter,
+		loff_t offset)
+{
+	ssize_t ret = 0;
+	ssize_t written = 0;
+	bool orphaned = false;
+	int is_overwrite = 0;
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct buffer_head *di_bh = NULL;
+	size_t count = iter->count;
+	journal_t *journal = osb->journal->j_journal;
+	u32 zero_len;
+	int cluster_align;
+	loff_t final_size = offset + count;
+	int append_write = offset >= i_size_read(inode) ? 1 : 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	{
+		u64 o = offset;
+
+		zero_len = do_div(o, 1 << osb->s_clustersize_bits);
+		cluster_align = !zero_len;
+	}
+
+	/*
+	 * when final_size > inode->i_size, inode->i_size will be
+	 * updated after direct write, so add the inode to orphan
+	 * dir first.
+	 */
+	if (final_size > i_size_read(inode)) {
+		ret = ocfs2_add_inode_to_orphan(osb, inode);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+		orphaned = true;
+	}
+
+	if (append_write) {
+		ret = ocfs2_inode_lock(inode, &di_bh, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+			ret = ocfs2_zero_extend(inode, di_bh, offset);
+		else
+			ret = ocfs2_extend_no_holes(inode, di_bh, offset,
+					offset);
+		if (ret < 0) {
+			mlog_errno(ret);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
+		if (is_overwrite < 0) {
+			mlog_errno(is_overwrite);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+		di_bh = NULL;
+	}
+
+	written = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
+			iter, offset,
+			ocfs2_direct_IO_get_blocks,
+			ocfs2_dio_end_io, NULL, 0);
+	if (unlikely(written < 0)) {
+		loff_t i_size = i_size_read(inode);
+
+		if (offset + count > i_size) {
+			ret = ocfs2_inode_lock(inode, &di_bh, 1);
+			if (ret < 0) {
+				mlog_errno(ret);
+				goto clean_orphan;
+			}
+
+			if (i_size == i_size_read(inode)) {
+				ret = ocfs2_truncate_file(inode, di_bh,
+						i_size);
+				if (ret < 0) {
+					if (ret != -ENOSPC)
+						mlog_errno(ret);
+
+					ocfs2_inode_unlock(inode, 1);
+					brelse(di_bh);
+					goto clean_orphan;
+				}
+			}
+
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+
+			ret = jbd2_journal_force_commit(journal);
+			if (ret < 0)
+				mlog_errno(ret);
+		}
+	} else if (written < 0 && append_write && !is_overwrite &&
+			!cluster_align) {
+		u32 p_cpos = 0;
+		u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
+
+		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+				&num_clusters, &ext_flags);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
+
+		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
+				p_cpos << (osb->s_clustersize_bits - 9),
+				zero_len >> 9, GFP_KERNEL, false);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+clean_orphan:
+	if (orphaned) {
+		int tmp_ret;
+		int update_isize = written > 0 ? 1 : 0;
+		loff_t end = update_isize ? offset + written : 0;
+
+		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode,
+				update_isize, end);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			goto out;
+		}
+
+		tmp_ret = jbd2_journal_force_commit(journal);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			mlog_errno(tmp_ret);
+		}
+	}
+
+out:
+	if (ret >= 0)
+		ret = written;
+	return ret;
+}
+
 static ssize_t ocfs2_direct_IO(int rw,
 			       struct kiocb *iocb,
 			       struct iov_iter *iter,
@@ -604,6 +825,9 @@ static ssize_t ocfs2_direct_IO(int rw,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+			OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * Fallback to buffered I/O if we see an inode without
@@ -612,14 +836,20 @@ static ssize_t ocfs2_direct_IO(int rw,
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return 0;
 
-	/* Fallback to buffered I/O if we are appending. */
-	if (i_size_read(inode) <= offset)
+	/* Fallback to buffered I/O if we are appending and
+	 * concurrent O_DIRECT writes are allowed.
+	 */
+	if (i_size_read(inode) <= offset && !full_coherency)
 		return 0;
 
-	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
+	if (rw == READ)
+		return __blockdev_direct_IO(rw, iocb, inode,
+				    inode->i_sb->s_bdev,
 				    iter, offset,
 				    ocfs2_direct_IO_get_blocks,
 				    ocfs2_dio_end_io, NULL, 0);
+	else
+		return ocfs2_direct_IO_write(iocb, iter, offset);
 }
 
 static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 2e355e0f8335..56c403a563bc 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1016,7 +1016,8 @@ void o2net_fill_node_map(unsigned long *map, unsigned bytes)
 
 	memset(map, 0, bytes);
 	for (node = 0; node < O2NM_MAX_NODES; ++node) {
-		o2net_tx_can_proceed(o2net_nn_from_num(node), &sc, &ret);
+		if (!o2net_tx_can_proceed(o2net_nn_from_num(node), &sc, &ret))
+			continue;
 		if (!ret) {
 			set_bit(node, map);
 			sc_put(sc);
diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h
index dc024367110a..b95e7df5b76a 100644
--- a/fs/ocfs2/cluster/tcp_internal.h
+++ b/fs/ocfs2/cluster/tcp_internal.h
@@ -107,12 +107,12 @@ struct o2net_node {
 	struct list_head		nn_status_list;
 
 	/* connects are attempted from when heartbeat comes up until either hb
-	 * goes down, the node is unconfigured, no connect attempts succeed
-	 * before O2NET_CONN_IDLE_DELAY, or a connect succeeds.  connect_work
-	 * is queued from set_nn_state both from hb up and from itself if a
-	 * connect attempt fails and so can be self-arming.  shutdown is
-	 * careful to first mark the nn such that no connects will be attempted
-	 * before canceling delayed connect work and flushing the queue. */
+	 * goes down, the node is unconfigured, or a connect succeeds.
+	 * connect_work is queued from set_nn_state both from hb up and from
+	 * itself if a connect attempt fails and so can be self-arming.
+	 * shutdown is careful to first mark the nn such that no connects will
+	 * be attempted before canceling delayed connect work and flushing the
+	 * queue. */
 	struct delayed_work		nn_connect_work;
 	unsigned long			nn_last_connect_attempt;
 
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 319e786175af..b08050bd3f2e 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -3456,10 +3456,8 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name,
 	int blocksize = dir->i_sb->s_blocksize;
 
 	status = ocfs2_read_dir_block(dir, 0, &bh, 0);
-	if (status) {
-		mlog_errno(status);
+	if (status)
 		goto bail;
-	}
 
 	rec_len = OCFS2_DIR_REC_LEN(namelen);
 	offset = 0;
@@ -3480,10 +3478,9 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name,
 			status = ocfs2_read_dir_block(dir,
 					     offset >> sb->s_blocksize_bits,
 					     &bh, 0);
-			if (status) {
-				mlog_errno(status);
+			if (status)
 				goto bail;
-			}
+
 			/* move to next block */
 			de = (struct ocfs2_dir_entry *) bh->b_data;
 		}
@@ -3513,7 +3510,6 @@ next:
 		de = (struct ocfs2_dir_entry *)((char *) de + le16_to_cpu(de->rec_len));
 	}
 
-	status = 0;
 bail:
 	brelse(bh);
 	if (status)
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index b46278f9ae44..fd6bbbbd7d78 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -385,8 +385,12 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 		head = &res->granted;
 
 	list_for_each_entry(lock, head, list) {
-		if (lock->ml.cookie == cookie)
+		/* if lock is found but unlock is pending ignore the bast */
+		if (lock->ml.cookie == cookie) {
+			if (lock->unlock_pending)
+				break;
 			goto do_ast;
+		}
 	}
 
 	mlog(0, "Got %sast for unknown lock! cookie=%u:%llu, name=%.*s, "
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 149eb556b8c6..825136070d2c 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -406,7 +406,7 @@ static int debug_purgelist_print(struct dlm_ctxt *dlm, char *buf, int len)
 	}
 	spin_unlock(&dlm->spinlock);
 
-	out += snprintf(buf + out, len - out, "Total on list: %ld\n", total);
+	out += snprintf(buf + out, len - out, "Total on list: %lu\n", total);
 
 	return out;
 }
@@ -464,7 +464,7 @@ static int debug_mle_print(struct dlm_ctxt *dlm, char *buf, int len)
 	spin_unlock(&dlm->master_lock);
 
 	out += snprintf(buf + out, len - out,
-			"Total: %ld, Longest: %ld\n", total, longest);
+			"Total: %lu, Longest: %lu\n", total, longest);
 	return out;
 }
 
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 50a59d2337b2..7df88a6dd626 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -674,20 +674,6 @@ static void dlm_leave_domain(struct dlm_ctxt *dlm)
 	spin_unlock(&dlm->spinlock);
 }
 
-int dlm_joined(struct dlm_ctxt *dlm)
-{
-	int ret = 0;
-
-	spin_lock(&dlm_domain_lock);
-
-	if (dlm->dlm_state == DLM_CTXT_JOINED)
-		ret = 1;
-
-	spin_unlock(&dlm_domain_lock);
-
-	return ret;
-}
-
 int dlm_shutting_down(struct dlm_ctxt *dlm)
 {
 	int ret = 0;
diff --git a/fs/ocfs2/dlm/dlmdomain.h b/fs/ocfs2/dlm/dlmdomain.h
index 2f7f60bfeb3b..fd6122a38dbd 100644
--- a/fs/ocfs2/dlm/dlmdomain.h
+++ b/fs/ocfs2/dlm/dlmdomain.h
@@ -28,7 +28,6 @@
 extern spinlock_t dlm_domain_lock;
 extern struct list_head dlm_domains;
 
-int dlm_joined(struct dlm_ctxt *dlm);
 int dlm_shutting_down(struct dlm_ctxt *dlm);
 void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm,
 					int node_num);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index cecd875653e4..ce12e0b1a31f 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1070,6 +1070,9 @@ static void dlm_move_reco_locks_to_list(struct dlm_ctxt *dlm,
 					     dead_node, dlm->name);
 					list_del_init(&lock->list);
 					dlm_lock_put(lock);
+					/* Can't schedule DLM_UNLOCK_FREE_LOCK
+					 * - do manually */
+					dlm_lock_put(lock);
 					break;
 				}
 			}
@@ -2346,6 +2349,10 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 						     dead_node, dlm->name);
 						list_del_init(&lock->list);
 						dlm_lock_put(lock);
+						/* Can't schedule
+						 * DLM_UNLOCK_FREE_LOCK
+						 * - do manually */
+						dlm_lock_put(lock);
 						break;
 					}
 				}
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 57c40e34f56f..061ba6a91bf2 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -390,12 +390,6 @@ clear_fields:
 	ip->ip_conn = NULL;
 }
 
-static struct backing_dev_info dlmfs_backing_dev_info = {
-	.name		= "ocfs2-dlmfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
 static struct inode *dlmfs_get_root_inode(struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
@@ -404,7 +398,6 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb)
 	if (inode) {
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, NULL, mode);
-		inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inc_nlink(inode);
 
@@ -428,7 +421,6 @@ static struct inode *dlmfs_get_inode(struct inode *parent,
 
 	inode->i_ino = get_next_ino();
 	inode_init_owner(inode, parent, mode);
-	inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 
 	ip = DLMFS_I(inode);
@@ -643,10 +635,6 @@ static int __init init_dlmfs_fs(void)
 	int status;
 	int cleanup_inode = 0, cleanup_worker = 0;
 
-	status = bdi_init(&dlmfs_backing_dev_info);
-	if (status)
-		return status;
-
 	dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache",
 				sizeof(struct dlmfs_inode_private),
 				0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
@@ -673,7 +661,6 @@ bail:
 			kmem_cache_destroy(dlmfs_inode_cache);
 		if (cleanup_worker)
 			destroy_workqueue(user_dlm_worker);
-		bdi_destroy(&dlmfs_backing_dev_info);
 	} else
 		printk("OCFS2 User DLM kernel interface loaded\n");
 	return status;
@@ -693,7 +680,6 @@ static void __exit exit_dlmfs_fs(void)
 	rcu_barrier();
 	kmem_cache_destroy(dlmfs_inode_cache);
 
-	bdi_destroy(&dlmfs_backing_dev_info);
 }
 
 MODULE_AUTHOR("Oracle");
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 1c423af04c69..11849a44dc5a 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3750,6 +3750,9 @@ static int ocfs2_dentry_convert_worker(struct ocfs2_lock_res *lockres,
 			break;
 		spin_unlock(&dentry_attach_lock);
 
+		if (S_ISDIR(dl->dl_inode->i_mode))
+			shrink_dcache_parent(dentry);
+
 		mlog(0, "d_delete(%pd);\n", dentry);
 
 		/*
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 3950693dd0f6..46e0d4e857c7 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -295,7 +295,7 @@ out:
 	return ret;
 }
 
-static int ocfs2_set_inode_size(handle_t *handle,
+int ocfs2_set_inode_size(handle_t *handle,
 				struct inode *inode,
 				struct buffer_head *fe_bh,
 				u64 new_i_size)
@@ -441,7 +441,7 @@ out:
 	return status;
 }
 
-static int ocfs2_truncate_file(struct inode *inode,
+int ocfs2_truncate_file(struct inode *inode,
 			       struct buffer_head *di_bh,
 			       u64 new_i_size)
 {
@@ -569,7 +569,7 @@ static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
 	handle_t *handle = NULL;
 	struct ocfs2_alloc_context *data_ac = NULL;
 	struct ocfs2_alloc_context *meta_ac = NULL;
-	enum ocfs2_alloc_restarted why;
+	enum ocfs2_alloc_restarted why = RESTART_NONE;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct ocfs2_extent_tree et;
 	int did_quota = 0;
@@ -709,6 +709,13 @@ leave:
 	return status;
 }
 
+int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten)
+{
+	return __ocfs2_extend_allocation(inode, logical_start,
+			clusters_to_add, mark_unwritten);
+}
+
 /*
  * While a write will already be ordering the data, a truncate will not.
  * Thus, we need to explicitly order the zeroed pages.
@@ -2109,6 +2116,9 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	loff_t saved_pos = 0, end;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+		OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * We start with a read level meta lock and only jump to an ex
@@ -2197,7 +2207,16 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 * one node could wind up truncating another
 		 * nodes writes.
 		 */
-		if (end > i_size_read(inode)) {
+		if (end > i_size_read(inode) && !full_coherency) {
+			*direct_io = 0;
+			break;
+		}
+
+		/*
+		 * Fallback to old way if the feature bit is not set.
+		 */
+		if (end > i_size_read(inode) &&
+				!ocfs2_supports_append_dio(osb)) {
 			*direct_io = 0;
 			break;
 		}
@@ -2210,7 +2229,13 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 */
 		ret = ocfs2_check_range_for_holes(inode, saved_pos, count);
 		if (ret == 1) {
-			*direct_io = 0;
+			/*
+			 * Fallback to old way if the feature bit is not set.
+			 * Otherwise try dio first and then complete the rest
+			 * request through buffer io.
+			 */
+			if (!ocfs2_supports_append_dio(osb))
+				*direct_io = 0;
 			ret = 0;
 		} else if (ret < 0)
 			mlog_errno(ret);
@@ -2243,6 +2268,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	u32 old_clusters;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int full_coherency = !(osb->s_mount_opt &
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
@@ -2357,13 +2383,53 @@ relock:
 
 	iov_iter_truncate(from, count);
 	if (direct_io) {
+		loff_t endbyte;
+		ssize_t written_buffered;
 		written = generic_file_direct_write(iocb, from, *ppos);
-		if (written < 0) {
+		if (written < 0 || written == count) {
 			ret = written;
 			goto out_dio;
 		}
+
+		/*
+		 * for completing the rest of the request.
+		 */
+		*ppos += written;
+		count -= written;
+		written_buffered = generic_perform_write(file, from, *ppos);
+		/*
+		 * If generic_file_buffered_write() returned a synchronous error
+		 * then we want to return the number of bytes which were
+		 * direct-written, or the error code if that was zero. Note
+		 * that this differs from normal direct-io semantics, which
+		 * will return -EFOO even if some bytes were written.
+		 */
+		if (written_buffered < 0) {
+			ret = written_buffered;
+			goto out_dio;
+		}
+
+		iocb->ki_pos = *ppos + written_buffered;
+		/* We need to ensure that the page cache pages are written to
+		 * disk and invalidated to preserve the expected O_DIRECT
+		 * semantics.
+		 */
+		endbyte = *ppos + written_buffered - 1;
+		ret = filemap_write_and_wait_range(file->f_mapping, *ppos,
+				endbyte);
+		if (ret == 0) {
+			written += written_buffered;
+			invalidate_mapping_pages(mapping,
+					*ppos >> PAGE_CACHE_SHIFT,
+					endbyte >> PAGE_CACHE_SHIFT);
+		} else {
+			/*
+			 * We don't know how much we wrote, so just return
+			 * the number of bytes which were direct-written
+			 */
+		}
 	} else {
-		current->backing_dev_info = file->f_mapping->backing_dev_info;
+		current->backing_dev_info = inode_to_bdi(inode);
 		written = generic_perform_write(file, from, *ppos);
 		if (likely(written >= 0))
 			iocb->ki_pos = *ppos + written;
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 97bf761c9e7c..e8c62f22215c 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -51,13 +51,22 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb,
 			 struct ocfs2_alloc_context *data_ac,
 			 struct ocfs2_alloc_context *meta_ac,
 			 enum ocfs2_alloc_restarted *reason_ret);
+int ocfs2_set_inode_size(handle_t *handle,
+		struct inode *inode,
+		struct buffer_head *fe_bh,
+		u64 new_i_size);
 int ocfs2_simple_size_update(struct inode *inode,
 			     struct buffer_head *di_bh,
 			     u64 new_i_size);
+int ocfs2_truncate_file(struct inode *inode,
+		struct buffer_head *di_bh,
+		u64 new_i_size);
 int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh,
 			  u64 new_i_size, u64 zero_to);
 int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
 		      loff_t zero_to);
+int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index c8b25de9efbb..3025c0da6b8a 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -648,7 +648,7 @@ static int ocfs2_remove_inode(struct inode *inode,
 
 	if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
 		status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode,
-					  orphan_dir_bh);
+					  orphan_dir_bh, false);
 		if (status < 0) {
 			mlog_errno(status);
 			goto bail_commit;
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index ca3431ee7f24..5e86b247c821 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -81,6 +81,8 @@ struct ocfs2_inode_info
 	tid_t i_sync_tid;
 	tid_t i_datasync_tid;
 
+	wait_queue_head_t append_dio_wq;
+
 	struct dquot *i_dquot[MAXQUOTAS];
 };
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 4f502382180f..ff531928269e 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -50,6 +50,8 @@
 #include "sysfile.h"
 #include "uptodate.h"
 #include "quota.h"
+#include "file.h"
+#include "namei.h"
 
 #include "buffer_head_io.h"
 #include "ocfs2_trace.h"
@@ -69,13 +71,15 @@ static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
 static int ocfs2_trylock_journal(struct ocfs2_super *osb,
 				 int slot_num);
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot);
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type);
 static int ocfs2_commit_thread(void *arg);
 static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 					    int slot_num,
 					    struct ocfs2_dinode *la_dinode,
 					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec);
+					    struct ocfs2_quota_recovery *qrec,
+					    enum ocfs2_orphan_reco_type orphan_reco_type);
 
 static inline int ocfs2_wait_on_mount(struct ocfs2_super *osb)
 {
@@ -149,7 +153,8 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb)
 	return 0;
 }
 
-void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
+void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
+		enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_replay_map *replay_map = osb->replay_map;
 	int i;
@@ -163,7 +168,8 @@ void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
 	for (i = 0; i < replay_map->rm_slots; i++)
 		if (replay_map->rm_replay_slots[i])
 			ocfs2_queue_recovery_completion(osb->journal, i, NULL,
-							NULL, NULL);
+							NULL, NULL,
+							orphan_reco_type);
 	replay_map->rm_state = REPLAY_DONE;
 }
 
@@ -1174,6 +1180,7 @@ struct ocfs2_la_recovery_item {
 	struct ocfs2_dinode	*lri_la_dinode;
 	struct ocfs2_dinode	*lri_tl_dinode;
 	struct ocfs2_quota_recovery *lri_qrec;
+	enum ocfs2_orphan_reco_type  lri_orphan_reco_type;
 };
 
 /* Does the second half of the recovery process. By this point, the
@@ -1195,6 +1202,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 	struct ocfs2_dinode *la_dinode, *tl_dinode;
 	struct ocfs2_la_recovery_item *item, *n;
 	struct ocfs2_quota_recovery *qrec;
+	enum ocfs2_orphan_reco_type orphan_reco_type;
 	LIST_HEAD(tmp_la_list);
 
 	trace_ocfs2_complete_recovery(
@@ -1212,6 +1220,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 		la_dinode = item->lri_la_dinode;
 		tl_dinode = item->lri_tl_dinode;
 		qrec = item->lri_qrec;
+		orphan_reco_type = item->lri_orphan_reco_type;
 
 		trace_ocfs2_complete_recovery_slot(item->lri_slot,
 			la_dinode ? le64_to_cpu(la_dinode->i_blkno) : 0,
@@ -1236,7 +1245,8 @@ void ocfs2_complete_recovery(struct work_struct *work)
 			kfree(tl_dinode);
 		}
 
-		ret = ocfs2_recover_orphans(osb, item->lri_slot);
+		ret = ocfs2_recover_orphans(osb, item->lri_slot,
+				orphan_reco_type);
 		if (ret < 0)
 			mlog_errno(ret);
 
@@ -1261,7 +1271,8 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 					    int slot_num,
 					    struct ocfs2_dinode *la_dinode,
 					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec)
+					    struct ocfs2_quota_recovery *qrec,
+					    enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_la_recovery_item *item;
 
@@ -1285,6 +1296,7 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 	item->lri_slot = slot_num;
 	item->lri_tl_dinode = tl_dinode;
 	item->lri_qrec = qrec;
+	item->lri_orphan_reco_type = orphan_reco_type;
 
 	spin_lock(&journal->j_lock);
 	list_add_tail(&item->lri_list, &journal->j_la_cleanups);
@@ -1304,7 +1316,8 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 	/* No need to queue up our truncate_log as regular cleanup will catch
 	 * that */
 	ocfs2_queue_recovery_completion(journal, osb->slot_num,
-					osb->local_alloc_copy, NULL, NULL);
+					osb->local_alloc_copy, NULL, NULL,
+					ORPHAN_NEED_TRUNCATE);
 	ocfs2_schedule_truncate_log_flush(osb, 0);
 
 	osb->local_alloc_copy = NULL;
@@ -1312,7 +1325,7 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 
 	/* queue to recover orphan slots for all offline slots */
 	ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 	ocfs2_free_replay_slots(osb);
 }
 
@@ -1323,7 +1336,8 @@ void ocfs2_complete_quota_recovery(struct ocfs2_super *osb)
 						osb->slot_num,
 						NULL,
 						NULL,
-						osb->quota_rec);
+						osb->quota_rec,
+						ORPHAN_NEED_TRUNCATE);
 		osb->quota_rec = NULL;
 	}
 }
@@ -1360,7 +1374,7 @@ restart:
 
 	/* queue recovery for our own slot */
 	ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL,
-					NULL, NULL);
+					NULL, NULL, ORPHAN_NO_NEED_TRUNCATE);
 
 	spin_lock(&osb->osb_lock);
 	while (rm->rm_used) {
@@ -1419,13 +1433,14 @@ skip_recovery:
 			continue;
 		}
 		ocfs2_queue_recovery_completion(osb->journal, rm_quota[i],
-						NULL, NULL, qrec);
+						NULL, NULL, qrec,
+						ORPHAN_NEED_TRUNCATE);
 	}
 
 	ocfs2_super_unlock(osb, 1);
 
 	/* queue recovery for offline slots */
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 
 bail:
 	mutex_lock(&osb->recovery_lock);
@@ -1447,7 +1462,6 @@ bail:
 	 * requires that we call do_exit().  And it isn't exported, but
 	 * complete_and_exit() seems to be a minimal wrapper around it. */
 	complete_and_exit(NULL, status);
-	return status;
 }
 
 void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
@@ -1712,7 +1726,7 @@ static int ocfs2_recover_node(struct ocfs2_super *osb,
 
 	/* This will kfree the memory pointed to by la_copy and tl_copy */
 	ocfs2_queue_recovery_completion(osb->journal, slot_num, la_copy,
-					tl_copy, NULL);
+					tl_copy, NULL, ORPHAN_NEED_TRUNCATE);
 
 	status = 0;
 done:
@@ -1902,7 +1916,7 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 
 	for (i = 0; i < osb->max_slots; i++)
 		ocfs2_queue_recovery_completion(osb->journal, i, NULL, NULL,
-						NULL);
+						NULL, ORPHAN_NO_NEED_TRUNCATE);
 	/*
 	 * We queued a recovery on orphan slots, increment the sequence
 	 * number and update LVB so other node will skip the scan for a while
@@ -2001,6 +2015,13 @@ static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
 	if (IS_ERR(iter))
 		return 0;
 
+	/* Skip inodes which are already added to recover list, since dio may
+	 * happen concurrently with unlink/rename */
+	if (OCFS2_I(iter)->ip_next_orphan) {
+		iput(iter);
+		return 0;
+	}
+
 	trace_ocfs2_orphan_filldir((unsigned long long)OCFS2_I(iter)->ip_blkno);
 	/* No locking is required for the next_orphan queue as there
 	 * is only ever a single process doing orphan recovery. */
@@ -2109,7 +2130,8 @@ static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb,
  *   advertising our state to ocfs2_delete_inode().
  */
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot)
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	int ret = 0;
 	struct inode *inode = NULL;
@@ -2133,13 +2155,60 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 					(unsigned long long)oi->ip_blkno);
 
 		iter = oi->ip_next_orphan;
+		oi->ip_next_orphan = NULL;
+
+		/*
+		 * We need to take and drop the inode lock to
+		 * force read inode from disk.
+		 */
+		ret = ocfs2_inode_lock(inode, NULL, 0);
+		if (ret) {
+			mlog_errno(ret);
+			goto next;
+		}
+		ocfs2_inode_unlock(inode, 0);
+
+		if (inode->i_nlink == 0) {
+			spin_lock(&oi->ip_lock);
+			/* Set the proper information to get us going into
+			 * ocfs2_delete_inode. */
+			oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
+			spin_unlock(&oi->ip_lock);
+		} else if (orphan_reco_type == ORPHAN_NEED_TRUNCATE) {
+			struct buffer_head *di_bh = NULL;
+
+			ret = ocfs2_rw_lock(inode, 1);
+			if (ret) {
+				mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_inode_lock(inode, &di_bh, 1);
+			if (ret < 0) {
+				ocfs2_rw_unlock(inode, 1);
+				mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_truncate_file(inode, di_bh,
+					i_size_read(inode));
+			ocfs2_inode_unlock(inode, 1);
+			ocfs2_rw_unlock(inode, 1);
+			brelse(di_bh);
+			if (ret < 0) {
+				if (ret != -ENOSPC)
+					mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_del_inode_from_orphan(osb, inode, 0, 0);
+			if (ret)
+				mlog_errno(ret);
 
-		spin_lock(&oi->ip_lock);
-		/* Set the proper information to get us going into
-		 * ocfs2_delete_inode. */
-		oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
-		spin_unlock(&oi->ip_lock);
+			wake_up(&OCFS2_I(inode)->append_dio_wq);
+		} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
 
+next:
 		iput(inode);
 
 		inode = iter;
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 7f8cde94abfe..f4cd3c3e9fb7 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -472,6 +472,11 @@ static inline int ocfs2_unlink_credits(struct super_block *sb)
  * orphan dir index leaf */
 #define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 4)
 
+/* dinode + orphan dir dinode + extent tree leaf block + orphan dir entry +
+ * orphan dir index root + orphan dir index leaf */
+#define OCFS2_INODE_ADD_TO_ORPHAN_CREDITS  (2 * OCFS2_INODE_UPDATE_CREDITS + 4)
+#define OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS  OCFS2_INODE_ADD_TO_ORPHAN_CREDITS
+
 /* dinode update, old dir dinode update, new dir dinode update, old
  * dir dir entry, new dir dir entry, dir entry update for renaming
  * directory + target unlink + 3 x dir index leaves */
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 10d66c75cecb..9581d190f6e1 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -173,7 +173,6 @@ out:
 static const struct vm_operations_struct ocfs2_file_vm_ops = {
 	.fault		= ocfs2_fault,
 	.page_mkwrite	= ocfs2_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 int ocfs2_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 914c121ec890..b5c3a5ea3ee6 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -79,7 +79,8 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 				    struct inode **ret_orphan_dir,
 				    u64 blkno,
 				    char *name,
-				    struct ocfs2_dir_lookup_result *lookup);
+				    struct ocfs2_dir_lookup_result *lookup,
+				    bool dio);
 
 static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    handle_t *handle,
@@ -87,7 +88,8 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    struct buffer_head *fe_bh,
 			    char *name,
 			    struct ocfs2_dir_lookup_result *lookup,
-			    struct inode *orphan_dir_inode);
+			    struct inode *orphan_dir_inode,
+			    bool dio);
 
 static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
 				     handle_t *handle,
@@ -104,6 +106,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2);
 /* An orphan dir name is an 8 byte value, printed as a hex string */
 #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
+#define OCFS2_DIO_ORPHAN_PREFIX "dio-"
+#define OCFS2_DIO_ORPHAN_PREFIX_LEN 4
 
 static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
 				   unsigned int flags)
@@ -952,7 +956,8 @@ static int ocfs2_unlink(struct inode *dir,
 	if (ocfs2_inode_is_unlinkable(inode)) {
 		status = ocfs2_prepare_orphan_dir(osb, &orphan_dir,
 						  OCFS2_I(inode)->ip_blkno,
-						  orphan_name, &orphan_insert);
+						  orphan_name, &orphan_insert,
+						  false);
 		if (status < 0) {
 			mlog_errno(status);
 			goto leave;
@@ -1004,7 +1009,7 @@ static int ocfs2_unlink(struct inode *dir,
 
 	if (is_unlinkable) {
 		status = ocfs2_orphan_add(osb, handle, inode, fe_bh,
-				orphan_name, &orphan_insert, orphan_dir);
+				orphan_name, &orphan_insert, orphan_dir, false);
 		if (status < 0)
 			mlog_errno(status);
 	}
@@ -1440,7 +1445,8 @@ static int ocfs2_rename(struct inode *old_dir,
 		if (S_ISDIR(new_inode->i_mode) || (new_inode->i_nlink == 1)) {
 			status = ocfs2_prepare_orphan_dir(osb, &orphan_dir,
 						OCFS2_I(new_inode)->ip_blkno,
-						orphan_name, &orphan_insert);
+						orphan_name, &orphan_insert,
+						false);
 			if (status < 0) {
 				mlog_errno(status);
 				goto bail;
@@ -1507,7 +1513,7 @@ static int ocfs2_rename(struct inode *old_dir,
 		if (should_add_orphan) {
 			status = ocfs2_orphan_add(osb, handle, new_inode,
 					newfe_bh, orphan_name,
-					&orphan_insert, orphan_dir);
+					&orphan_insert, orphan_dir, false);
 			if (status < 0) {
 				mlog_errno(status);
 				goto bail;
@@ -2088,12 +2094,28 @@ static int __ocfs2_prepare_orphan_dir(struct inode *orphan_dir_inode,
 				      struct buffer_head *orphan_dir_bh,
 				      u64 blkno,
 				      char *name,
-				      struct ocfs2_dir_lookup_result *lookup)
+				      struct ocfs2_dir_lookup_result *lookup,
+				      bool dio)
 {
 	int ret;
 	struct ocfs2_super *osb = OCFS2_SB(orphan_dir_inode->i_sb);
+	int namelen = dio ?
+			(OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN) :
+			OCFS2_ORPHAN_NAMELEN;
+
+	if (dio) {
+		ret = snprintf(name, OCFS2_DIO_ORPHAN_PREFIX_LEN + 1, "%s",
+				OCFS2_DIO_ORPHAN_PREFIX);
+		if (ret != OCFS2_DIO_ORPHAN_PREFIX_LEN) {
+			ret = -EINVAL;
+			mlog_errno(ret);
+			return ret;
+		}
 
-	ret = ocfs2_blkno_stringify(blkno, name);
+		ret = ocfs2_blkno_stringify(blkno,
+				name + OCFS2_DIO_ORPHAN_PREFIX_LEN);
+	} else
+		ret = ocfs2_blkno_stringify(blkno, name);
 	if (ret < 0) {
 		mlog_errno(ret);
 		return ret;
@@ -2101,7 +2123,7 @@ static int __ocfs2_prepare_orphan_dir(struct inode *orphan_dir_inode,
 
 	ret = ocfs2_prepare_dir_for_insert(osb, orphan_dir_inode,
 					   orphan_dir_bh, name,
-					   OCFS2_ORPHAN_NAMELEN, lookup);
+					   namelen, lookup);
 	if (ret < 0) {
 		mlog_errno(ret);
 		return ret;
@@ -2128,7 +2150,8 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 				    struct inode **ret_orphan_dir,
 				    u64 blkno,
 				    char *name,
-				    struct ocfs2_dir_lookup_result *lookup)
+				    struct ocfs2_dir_lookup_result *lookup,
+				    bool dio)
 {
 	struct inode *orphan_dir_inode = NULL;
 	struct buffer_head *orphan_dir_bh = NULL;
@@ -2142,7 +2165,7 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 	}
 
 	ret = __ocfs2_prepare_orphan_dir(orphan_dir_inode, orphan_dir_bh,
-					 blkno, name, lookup);
+					 blkno, name, lookup, dio);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out;
@@ -2170,12 +2193,16 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    struct buffer_head *fe_bh,
 			    char *name,
 			    struct ocfs2_dir_lookup_result *lookup,
-			    struct inode *orphan_dir_inode)
+			    struct inode *orphan_dir_inode,
+			    bool dio)
 {
 	struct buffer_head *orphan_dir_bh = NULL;
 	int status = 0;
 	struct ocfs2_dinode *orphan_fe;
 	struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data;
+	int namelen = dio ?
+			(OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN) :
+			OCFS2_ORPHAN_NAMELEN;
 
 	trace_ocfs2_orphan_add_begin(
 				(unsigned long long)OCFS2_I(inode)->ip_blkno);
@@ -2219,7 +2246,7 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 	ocfs2_journal_dirty(handle, orphan_dir_bh);
 
 	status = __ocfs2_add_entry(handle, orphan_dir_inode, name,
-				   OCFS2_ORPHAN_NAMELEN, inode,
+				   namelen, inode,
 				   OCFS2_I(inode)->ip_blkno,
 				   orphan_dir_bh, lookup);
 	if (status < 0) {
@@ -2227,13 +2254,21 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 		goto rollback;
 	}
 
-	fe->i_flags |= cpu_to_le32(OCFS2_ORPHANED_FL);
-	OCFS2_I(inode)->ip_flags &= ~OCFS2_INODE_SKIP_ORPHAN_DIR;
+	if (dio) {
+		/* Update flag OCFS2_DIO_ORPHANED_FL and record the orphan
+		 * slot.
+		 */
+		fe->i_flags |= cpu_to_le32(OCFS2_DIO_ORPHANED_FL);
+		fe->i_dio_orphaned_slot = cpu_to_le16(osb->slot_num);
+	} else {
+		fe->i_flags |= cpu_to_le32(OCFS2_ORPHANED_FL);
+		OCFS2_I(inode)->ip_flags &= ~OCFS2_INODE_SKIP_ORPHAN_DIR;
 
-	/* Record which orphan dir our inode now resides
-	 * in. delete_inode will use this to determine which orphan
-	 * dir to lock. */
-	fe->i_orphaned_slot = cpu_to_le16(osb->slot_num);
+		/* Record which orphan dir our inode now resides
+		 * in. delete_inode will use this to determine which orphan
+		 * dir to lock. */
+		fe->i_orphaned_slot = cpu_to_le16(osb->slot_num);
+	}
 
 	ocfs2_journal_dirty(handle, fe_bh);
 
@@ -2258,14 +2293,28 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 		     handle_t *handle,
 		     struct inode *orphan_dir_inode,
 		     struct inode *inode,
-		     struct buffer_head *orphan_dir_bh)
+		     struct buffer_head *orphan_dir_bh,
+		     bool dio)
 {
-	char name[OCFS2_ORPHAN_NAMELEN + 1];
+	const int namelen = OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN;
+	char name[namelen + 1];
 	struct ocfs2_dinode *orphan_fe;
 	int status = 0;
 	struct ocfs2_dir_lookup_result lookup = { NULL, };
 
-	status = ocfs2_blkno_stringify(OCFS2_I(inode)->ip_blkno, name);
+	if (dio) {
+		status = snprintf(name, OCFS2_DIO_ORPHAN_PREFIX_LEN + 1, "%s",
+				OCFS2_DIO_ORPHAN_PREFIX);
+		if (status != OCFS2_DIO_ORPHAN_PREFIX_LEN) {
+			status = -EINVAL;
+			mlog_errno(status);
+			return status;
+		}
+
+		status = ocfs2_blkno_stringify(OCFS2_I(inode)->ip_blkno,
+				name + OCFS2_DIO_ORPHAN_PREFIX_LEN);
+	} else
+		status = ocfs2_blkno_stringify(OCFS2_I(inode)->ip_blkno, name);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -2273,10 +2322,10 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 
 	trace_ocfs2_orphan_del(
 	     (unsigned long long)OCFS2_I(orphan_dir_inode)->ip_blkno,
-	     name, OCFS2_ORPHAN_NAMELEN);
+	     name, namelen);
 
 	/* find it's spot in the orphan directory */
-	status = ocfs2_find_entry(name, OCFS2_ORPHAN_NAMELEN, orphan_dir_inode,
+	status = ocfs2_find_entry(name, namelen, orphan_dir_inode,
 				  &lookup);
 	if (status) {
 		mlog_errno(status);
@@ -2376,7 +2425,8 @@ static int ocfs2_prep_new_orphaned_file(struct inode *dir,
 	}
 
 	ret = __ocfs2_prepare_orphan_dir(orphan_dir, orphan_dir_bh,
-					 di_blkno, orphan_name, orphan_insert);
+					 di_blkno, orphan_name, orphan_insert,
+					 false);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out;
@@ -2482,7 +2532,7 @@ int ocfs2_create_inode_in_orphan(struct inode *dir,
 
 	di = (struct ocfs2_dinode *)new_di_bh->b_data;
 	status = ocfs2_orphan_add(osb, handle, inode, new_di_bh, orphan_name,
-				  &orphan_insert, orphan_dir);
+				  &orphan_insert, orphan_dir, false);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -2527,6 +2577,186 @@ leave:
 	return status;
 }
 
+static int ocfs2_dio_orphan_recovered(struct inode *inode)
+{
+	int ret;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return 0;
+	}
+
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+	ret = !(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL));
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+	return ret;
+}
+
+#define OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL 10000
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+	struct inode *inode)
+{
+	char orphan_name[OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN + 1];
+	struct inode *orphan_dir_inode = NULL;
+	struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
+	struct buffer_head *di_bh = NULL;
+	int status = 0;
+	handle_t *handle = NULL;
+	struct ocfs2_dinode *di = NULL;
+
+restart:
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+	/*
+	 * Another append dio crashed?
+	 * If so, wait for recovery first.
+	 */
+	if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+		wait_event_interruptible_timeout(OCFS2_I(inode)->append_dio_wq,
+				ocfs2_dio_orphan_recovered(inode),
+				msecs_to_jiffies(OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL));
+		goto restart;
+	}
+
+	status = ocfs2_prepare_orphan_dir(osb, &orphan_dir_inode,
+			OCFS2_I(inode)->ip_blkno,
+			orphan_name,
+			&orphan_insert,
+			true);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	handle = ocfs2_start_trans(osb,
+			OCFS2_INODE_ADD_TO_ORPHAN_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		goto bail_unlock_orphan;
+	}
+
+	status = ocfs2_orphan_add(osb, handle, inode, di_bh, orphan_name,
+			&orphan_insert, orphan_dir_inode, true);
+	if (status)
+		mlog_errno(status);
+
+	ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+	ocfs2_inode_unlock(orphan_dir_inode, 1);
+	mutex_unlock(&orphan_dir_inode->i_mutex);
+	iput(orphan_dir_inode);
+
+	ocfs2_free_dir_lookup_result(&orphan_insert);
+
+bail_unlock_inode:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+bail:
+	return status;
+}
+
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end)
+{
+	struct inode *orphan_dir_inode = NULL;
+	struct buffer_head *orphan_dir_bh = NULL;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
+	handle_t *handle = NULL;
+	int status = 0;
+
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+
+	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
+			ORPHAN_DIR_SYSTEM_INODE,
+			le16_to_cpu(di->i_dio_orphaned_slot));
+	if (!orphan_dir_inode) {
+		status = -ENOENT;
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	mutex_lock(&orphan_dir_inode->i_mutex);
+	status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
+	if (status < 0) {
+		mutex_unlock(&orphan_dir_inode->i_mutex);
+		iput(orphan_dir_inode);
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	handle = ocfs2_start_trans(osb,
+			OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		goto bail_unlock_orphan;
+	}
+
+	BUG_ON(!(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL)));
+
+	status = ocfs2_orphan_del(osb, handle, orphan_dir_inode,
+				inode, orphan_dir_bh, true);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_commit;
+	}
+
+	status = ocfs2_journal_access_di(handle,
+			INODE_CACHE(inode),
+			di_bh,
+			OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_commit;
+	}
+
+	di->i_flags &= ~cpu_to_le32(OCFS2_DIO_ORPHANED_FL);
+	di->i_dio_orphaned_slot = 0;
+
+	if (update_isize) {
+		status = ocfs2_set_inode_size(handle, inode, di_bh, end);
+		if (status)
+			mlog_errno(status);
+	} else
+		ocfs2_journal_dirty(handle, di_bh);
+
+bail_commit:
+	ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+	ocfs2_inode_unlock(orphan_dir_inode, 1);
+	mutex_unlock(&orphan_dir_inode->i_mutex);
+	brelse(orphan_dir_bh);
+	iput(orphan_dir_inode);
+
+bail_unlock_inode:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+bail:
+	return status;
+}
+
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *inode,
 				   struct dentry *dentry)
@@ -2615,7 +2845,7 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 	}
 
 	status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode,
-				  orphan_dir_bh);
+				  orphan_dir_bh, false);
 	if (status < 0) {
 		mlog_errno(status);
 		goto out_commit;
diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h
index e5d059d4f115..5ddecce172fa 100644
--- a/fs/ocfs2/namei.h
+++ b/fs/ocfs2/namei.h
@@ -34,10 +34,16 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 		     handle_t *handle,
 		     struct inode *orphan_dir_inode,
 		     struct inode *inode,
-		     struct buffer_head *orphan_dir_bh);
+		     struct buffer_head *orphan_dir_bh,
+		     bool dio);
 int ocfs2_create_inode_in_orphan(struct inode *dir,
 				 int mode,
 				 struct inode **new_inode);
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+		struct inode *inode);
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end);
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *new_inode,
 				   struct dentry *new_dentry);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7d6b7d090452..460c6c37e683 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -209,6 +209,11 @@ struct ocfs2_lock_res {
 #endif
 };
 
+enum ocfs2_orphan_reco_type {
+	ORPHAN_NO_NEED_TRUNCATE = 0,
+	ORPHAN_NEED_TRUNCATE,
+};
+
 enum ocfs2_orphan_scan_state {
 	ORPHAN_SCAN_ACTIVE,
 	ORPHAN_SCAN_INACTIVE
@@ -279,6 +284,8 @@ enum ocfs2_mount_options
 						     writes */
 	OCFS2_MOUNT_HB_NONE = 1 << 13, /* No heartbeat */
 	OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */
+
+	OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15,  /* Journal Async Commit */
 };
 
 #define OCFS2_OSB_SOFT_RO	0x0001
@@ -493,6 +500,14 @@ static inline int ocfs2_writes_unwritten_extents(struct ocfs2_super *osb)
 	return 0;
 }
 
+static inline int ocfs2_supports_append_dio(struct ocfs2_super *osb)
+{
+	if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_APPEND_DIO)
+		return 1;
+	return 0;
+}
+
+
 static inline int ocfs2_supports_inline_data(struct ocfs2_super *osb)
 {
 	if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INLINE_DATA)
@@ -724,6 +739,16 @@ static inline unsigned int ocfs2_clusters_for_bytes(struct super_block *sb,
 	return clusters;
 }
 
+static inline unsigned int ocfs2_bytes_to_clusters(struct super_block *sb,
+		u64 bytes)
+{
+	int cl_bits = OCFS2_SB(sb)->s_clustersize_bits;
+	unsigned int clusters;
+
+	clusters = (unsigned int)(bytes >> cl_bits);
+	return clusters;
+}
+
 static inline u64 ocfs2_blocks_for_bytes(struct super_block *sb,
 					 u64 bytes)
 {
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 938387a10d5d..db64ce2d4667 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -102,7 +102,8 @@
 					 | OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS \
 					 | OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE \
 					 | OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG	\
-					 | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO)
+					 | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO \
+					 | OCFS2_FEATURE_INCOMPAT_APPEND_DIO)
 #define OCFS2_FEATURE_RO_COMPAT_SUPP	(OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \
 					 | OCFS2_FEATURE_RO_COMPAT_USRQUOTA \
 					 | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)
@@ -178,6 +179,11 @@
 #define OCFS2_FEATURE_INCOMPAT_CLUSTERINFO	0x4000
 
 /*
+ * Append Direct IO support
+ */
+#define OCFS2_FEATURE_INCOMPAT_APPEND_DIO	0x8000
+
+/*
  * backup superblock flag is used to indicate that this volume
  * has backup superblocks.
  */
@@ -199,6 +205,7 @@
 #define OCFS2_FEATURE_RO_COMPAT_USRQUOTA	0x0002
 #define OCFS2_FEATURE_RO_COMPAT_GRPQUOTA	0x0004
 
+
 /* The byte offset of the first backup block will be 1G.
  * The following will be 4G, 16G, 64G, 256G and 1T.
  */
@@ -229,6 +236,8 @@
 #define OCFS2_CHAIN_FL		(0x00000400)	/* Chain allocator */
 #define OCFS2_DEALLOC_FL	(0x00000800)	/* Truncate log */
 #define OCFS2_QUOTA_FL		(0x00001000)	/* Quota file */
+#define OCFS2_DIO_ORPHANED_FL	(0X00002000)	/* On the orphan list especially
+						 * for dio */
 
 /*
  * Flags on ocfs2_dinode.i_dyn_features
@@ -729,7 +738,9 @@ struct ocfs2_dinode {
 					   inode belongs to.  Only valid
 					   if allocated from a
 					   discontiguous block group */
-/*A0*/	__le64 i_reserved2[3];
+/*A0*/	__le16 i_dio_orphaned_slot;	/* only used for append dio write */
+	__le16 i_reserved1[3];
+	__le64 i_reserved2[2];
 /*B8*/	union {
 		__le64 i_pad1;		/* Generic way to refer to this
 					   64bit union */
diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h
index 1eae330193a6..b6d51333ad02 100644
--- a/fs/ocfs2/quota.h
+++ b/fs/ocfs2/quota.h
@@ -48,6 +48,7 @@ struct ocfs2_quota_recovery {
 /* In-memory structure with quota header information */
 struct ocfs2_mem_dqinfo {
 	unsigned int dqi_type;		/* Quota type this structure describes */
+	unsigned int dqi_flags;		/* Flags OLQF_* */
 	unsigned int dqi_chunks;	/* Number of chunks in local quota file */
 	unsigned int dqi_blocks;	/* Number of blocks allocated for local quota file */
 	unsigned int dqi_syncms;	/* How often should we sync with other nodes */
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 10b653930ee2..3d0b63d34225 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -73,12 +73,6 @@ static loff_t ol_dqblk_off(struct super_block *sb, int c, int off)
 	       ol_dqblk_block_off(sb, c, off);
 }
 
-/* Compute block number from given offset */
-static inline unsigned int ol_dqblk_file_block(struct super_block *sb, loff_t off)
-{
-	return off >> sb->s_blocksize_bits;
-}
-
 static inline unsigned int ol_dqblk_block_offset(struct super_block *sb, loff_t off)
 {
 	return off & ((1 << sb->s_blocksize_bits) - 1);
@@ -292,7 +286,7 @@ static void olq_update_info(struct buffer_head *bh, void *private)
 	ldinfo = (struct ocfs2_local_disk_dqinfo *)(bh->b_data +
 						OCFS2_LOCAL_INFO_OFF);
 	spin_lock(&dq_data_lock);
-	ldinfo->dqi_flags = cpu_to_le32(info->dqi_flags & DQF_MASK);
+	ldinfo->dqi_flags = cpu_to_le32(oinfo->dqi_flags);
 	ldinfo->dqi_chunks = cpu_to_le32(oinfo->dqi_chunks);
 	ldinfo->dqi_blocks = cpu_to_le32(oinfo->dqi_blocks);
 	spin_unlock(&dq_data_lock);
@@ -701,8 +695,8 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 	/* We don't need the lock and we have to acquire quota file locks
 	 * which will later depend on this lock */
 	mutex_unlock(&sb_dqopt(sb)->dqio_mutex);
-	info->dqi_maxblimit = 0x7fffffffffffffffLL;
-	info->dqi_maxilimit = 0x7fffffffffffffffLL;
+	info->dqi_max_spc_limit = 0x7fffffffffffffffLL;
+	info->dqi_max_ino_limit = 0x7fffffffffffffffLL;
 	oinfo = kmalloc(sizeof(struct ocfs2_mem_dqinfo), GFP_NOFS);
 	if (!oinfo) {
 		mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota"
@@ -737,13 +731,13 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 	}
 	ldinfo = (struct ocfs2_local_disk_dqinfo *)(bh->b_data +
 						OCFS2_LOCAL_INFO_OFF);
-	info->dqi_flags = le32_to_cpu(ldinfo->dqi_flags);
+	oinfo->dqi_flags = le32_to_cpu(ldinfo->dqi_flags);
 	oinfo->dqi_chunks = le32_to_cpu(ldinfo->dqi_chunks);
 	oinfo->dqi_blocks = le32_to_cpu(ldinfo->dqi_blocks);
 	oinfo->dqi_libh = bh;
 
 	/* We crashed when using local quota file? */
-	if (!(info->dqi_flags & OLQF_CLEAN)) {
+	if (!(oinfo->dqi_flags & OLQF_CLEAN)) {
 		rec = OCFS2_SB(sb)->quota_rec;
 		if (!rec) {
 			rec = ocfs2_alloc_quota_recovery();
@@ -772,7 +766,7 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 	}
 
 	/* Now mark quota file as used */
-	info->dqi_flags &= ~OLQF_CLEAN;
+	oinfo->dqi_flags &= ~OLQF_CLEAN;
 	status = ocfs2_modify_bh(lqinode, bh, olq_update_info, info);
 	if (status < 0) {
 		mlog_errno(status);
@@ -857,7 +851,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type)
 		goto out;
 
 	/* Mark local file as clean */
-	info->dqi_flags |= OLQF_CLEAN;
+	oinfo->dqi_flags |= OLQF_CLEAN;
 	status = ocfs2_modify_bh(sb_dqopt(sb)->files[type],
 				 oinfo->dqi_libh,
 				 olq_update_info,
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index d81f6e2a97f5..ee541f92dab4 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2428,8 +2428,6 @@ static int ocfs2_calc_refcount_meta_credits(struct super_block *sb,
 			get_bh(prev_bh);
 		}
 
-		rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data;
-
 		trace_ocfs2_calc_refcount_meta_credits_iterate(
 				recs_add, (unsigned long long)cpos, clusters,
 				(unsigned long long)le64_to_cpu(rec.r_cpos),
diff --git a/fs/ocfs2/reservations.c b/fs/ocfs2/reservations.c
index 41ffd36c689c..6a348b0294ab 100644
--- a/fs/ocfs2/reservations.c
+++ b/fs/ocfs2/reservations.c
@@ -39,7 +39,7 @@
 #define OCFS2_CHECK_RESERVATIONS
 #endif
 
-DEFINE_SPINLOCK(resv_lock);
+static DEFINE_SPINLOCK(resv_lock);
 
 #define	OCFS2_MIN_RESV_WINDOW_BITS	8
 #define	OCFS2_MAX_RESV_WINDOW_BITS	1024
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 83723179e1ec..26675185b886 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -191,6 +191,7 @@ enum {
 	Opt_coherency_full,
 	Opt_resv_level,
 	Opt_dir_resv_level,
+	Opt_journal_async_commit,
 	Opt_err,
 };
 
@@ -222,6 +223,7 @@ static const match_table_t tokens = {
 	{Opt_coherency_full, "coherency=full"},
 	{Opt_resv_level, "resv_level=%u"},
 	{Opt_dir_resv_level, "dir_resv_level=%u"},
+	{Opt_journal_async_commit, "journal_async_commit"},
 	{Opt_err, NULL}
 };
 
@@ -1000,36 +1002,6 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb)
 	}
 }
 
-/* Handle quota on quotactl */
-static int ocfs2_quota_on(struct super_block *sb, int type, int format_id)
-{
-	unsigned int feature[OCFS2_MAXQUOTAS] = {
-					OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
-					OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
-
-	if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type]))
-		return -EINVAL;
-
-	return dquot_enable(sb_dqopt(sb)->files[type], type,
-			    format_id, DQUOT_LIMITS_ENABLED);
-}
-
-/* Handle quota off quotactl */
-static int ocfs2_quota_off(struct super_block *sb, int type)
-{
-	return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED);
-}
-
-static const struct quotactl_ops ocfs2_quotactl_ops = {
-	.quota_on_meta	= ocfs2_quota_on,
-	.quota_off	= ocfs2_quota_off,
-	.quota_sync	= dquot_quota_sync,
-	.get_info	= dquot_get_dqinfo,
-	.set_info	= dquot_set_dqinfo,
-	.get_dqblk	= dquot_get_dqblk,
-	.set_dqblk	= dquot_set_dqblk,
-};
-
 static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct dentry *root;
@@ -1500,6 +1472,9 @@ static int ocfs2_parse_options(struct super_block *sb,
 			    option < OCFS2_MAX_RESV_LEVEL)
 				mopt->dir_resv_level = option;
 			break;
+		case Opt_journal_async_commit:
+			mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT;
+			break;
 		default:
 			mlog(ML_ERROR,
 			     "Unrecognized mount option \"%s\" "
@@ -1606,6 +1581,9 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
 	if (osb->osb_dir_resv_level != osb->osb_resv_level)
 		seq_printf(s, ",dir_resv_level=%d", osb->osb_resv_level);
 
+	if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT)
+		seq_printf(s, ",journal_async_commit");
+
 	return 0;
 }
 
@@ -1768,6 +1746,8 @@ static void ocfs2_inode_init_once(void *data)
 	ocfs2_lock_res_init_once(&oi->ip_inode_lockres);
 	ocfs2_lock_res_init_once(&oi->ip_open_lockres);
 
+	init_waitqueue_head(&oi->append_dio_wq);
+
 	ocfs2_metadata_cache_init(INODE_CACHE(&oi->vfs_inode),
 				  &ocfs2_inode_caching_ops);
 
@@ -2079,7 +2059,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	sb->s_op = &ocfs2_sops;
 	sb->s_d_op = &ocfs2_dentry_ops;
 	sb->s_export_op = &ocfs2_export_ops;
-	sb->s_qcop = &ocfs2_quotactl_ops;
+	sb->s_qcop = &dquot_quotactl_sysfile_ops;
 	sb->dq_op = &ocfs2_quota_operations;
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
 	sb->s_xattr = ocfs2_xattr_handlers;
@@ -2475,6 +2455,15 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
 		goto finally;
 	}
 
+	if (osb->s_mount_opt & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT)
+		jbd2_journal_set_features(osb->journal->j_journal,
+				JBD2_FEATURE_COMPAT_CHECKSUM, 0,
+				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+	else
+		jbd2_journal_clear_features(osb->journal->j_journal,
+				JBD2_FEATURE_COMPAT_CHECKSUM, 0,
+				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+
 	if (dirty) {
 		/* recover my local alloc if we didn't unmount cleanly. */
 		status = ocfs2_begin_local_alloc_recovery(osb,
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 662f8dee149f..85b190dc132f 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -5334,16 +5334,6 @@ out:
 	return ret;
 }
 
-static inline char *ocfs2_xattr_bucket_get_val(struct inode *inode,
-					struct ocfs2_xattr_bucket *bucket,
-					int offs)
-{
-	int block_off = offs >> inode->i_sb->s_blocksize_bits;
-
-	offs = offs % inode->i_sb->s_blocksize;
-	return bucket_block(bucket, block_off) + offs;
-}
-
 /*
  * Truncate the specified xe_off entry in xattr bucket.
  * bucket is indicated by header_bh and len is the new length.
diff --git a/fs/open.c b/fs/open.c
index 813be037b412..33f9cbf2610b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -667,11 +667,8 @@ int open_check_o_direct(struct file *f)
 {
 	/* NB: we're sure to have correct a_ops only after f_op->open */
 	if (f->f_flags & O_DIRECT) {
-		if (!f->f_mapping->a_ops ||
-		    ((!f->f_mapping->a_ops->direct_IO) &&
-		    (!f->f_mapping->a_ops->get_xip_mem))) {
+		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
 			return -EINVAL;
-		}
 	}
 	return 0;
 }
@@ -971,8 +968,14 @@ struct file *file_open_name(struct filename *name, int flags, umode_t mode)
  */
 struct file *filp_open(const char *filename, int flags, umode_t mode)
 {
-	struct filename name = {.name = filename};
-	return file_open_name(&name, flags, mode);
+	struct filename *name = getname_kernel(filename);
+	struct file *file = ERR_CAST(name);
+	
+	if (!IS_ERR(name)) {
+		file = file_open_name(name, flags, mode);
+		putname(name);
+	}
+	return file;
 }
 EXPORT_SYMBOL(filp_open);
 
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index ea10a8719107..24f640441bd9 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -191,7 +191,6 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 		ovl_set_timestamps(upperdentry, stat);
 
 	return err;
-
 }
 
 static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
@@ -385,7 +384,7 @@ int ovl_copy_up(struct dentry *dentry)
 		struct kstat stat;
 		enum ovl_path_type type = ovl_path_type(dentry);
 
-		if (type != OVL_PATH_LOWER)
+		if (OVL_TYPE_UPPER(type))
 			break;
 
 		next = dget(dentry);
@@ -394,7 +393,7 @@ int ovl_copy_up(struct dentry *dentry)
 			parent = dget_parent(next);
 
 			type = ovl_path_type(parent);
-			if (type != OVL_PATH_LOWER)
+			if (OVL_TYPE_UPPER(type))
 				break;
 
 			dput(next);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 8ffc4b980f1b..d139405d2bfa 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -19,7 +19,7 @@ void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
 	int err;
 
 	dget(wdentry);
-	if (S_ISDIR(wdentry->d_inode->i_mode))
+	if (d_is_dir(wdentry))
 		err = ovl_do_rmdir(wdir, wdentry);
 	else
 		err = ovl_do_unlink(wdir, wdentry);
@@ -118,14 +118,14 @@ int ovl_create_real(struct inode *dir, struct dentry *newdentry,
 
 static int ovl_set_opaque(struct dentry *upperdentry)
 {
-	return ovl_do_setxattr(upperdentry, ovl_opaque_xattr, "y", 1, 0);
+	return ovl_do_setxattr(upperdentry, OVL_XATTR_OPAQUE, "y", 1, 0);
 }
 
 static void ovl_remove_opaque(struct dentry *upperdentry)
 {
 	int err;
 
-	err = ovl_do_removexattr(upperdentry, ovl_opaque_xattr);
+	err = ovl_do_removexattr(upperdentry, OVL_XATTR_OPAQUE);
 	if (err) {
 		pr_warn("overlayfs: failed to remove opaque from '%s' (%i)\n",
 			upperdentry->d_name.name, err);
@@ -152,7 +152,7 @@ static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	 * correct link count.  nlink=1 seems to pacify 'find' and
 	 * other utilities.
 	 */
-	if (type == OVL_PATH_MERGE)
+	if (OVL_TYPE_MERGE(type))
 		stat->nlink = 1;
 
 	return 0;
@@ -506,7 +506,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
 	struct dentry *opaquedir = NULL;
 	int err;
 
-	if (is_dir) {
+	if (is_dir && OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) {
 		opaquedir = ovl_check_empty_and_clear(dentry);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir))
@@ -630,7 +630,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 		goto out_drop_write;
 
 	type = ovl_path_type(dentry);
-	if (type == OVL_PATH_PURE_UPPER) {
+	if (OVL_TYPE_PURE_UPPER(type)) {
 		err = ovl_remove_upper(dentry, is_dir);
 	} else {
 		const struct cred *old_cred;
@@ -693,7 +693,7 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	bool new_create = false;
 	bool cleanup_whiteout = false;
 	bool overwrite = !(flags & RENAME_EXCHANGE);
-	bool is_dir = S_ISDIR(old->d_inode->i_mode);
+	bool is_dir = d_is_dir(old);
 	bool new_is_dir = false;
 	struct dentry *opaquedir = NULL;
 	const struct cred *old_cred = NULL;
@@ -712,7 +712,7 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	/* Don't copy up directory trees */
 	old_type = ovl_path_type(old);
 	err = -EXDEV;
-	if ((old_type == OVL_PATH_LOWER || old_type == OVL_PATH_MERGE) && is_dir)
+	if (OVL_TYPE_MERGE_OR_LOWER(old_type) && is_dir)
 		goto out;
 
 	if (new->d_inode) {
@@ -720,30 +720,30 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 		if (err)
 			goto out;
 
-		if (S_ISDIR(new->d_inode->i_mode))
+		if (d_is_dir(new))
 			new_is_dir = true;
 
 		new_type = ovl_path_type(new);
 		err = -EXDEV;
-		if (!overwrite && (new_type == OVL_PATH_LOWER || new_type == OVL_PATH_MERGE) && new_is_dir)
+		if (!overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir)
 			goto out;
 
 		err = 0;
-		if (new_type == OVL_PATH_LOWER && old_type == OVL_PATH_LOWER) {
+		if (!OVL_TYPE_UPPER(new_type) && !OVL_TYPE_UPPER(old_type)) {
 			if (ovl_dentry_lower(old)->d_inode ==
 			    ovl_dentry_lower(new)->d_inode)
 				goto out;
 		}
-		if (new_type != OVL_PATH_LOWER && old_type != OVL_PATH_LOWER) {
+		if (OVL_TYPE_UPPER(new_type) && OVL_TYPE_UPPER(old_type)) {
 			if (ovl_dentry_upper(old)->d_inode ==
 			    ovl_dentry_upper(new)->d_inode)
 				goto out;
 		}
 	} else {
 		if (ovl_dentry_is_opaque(new))
-			new_type = OVL_PATH_UPPER;
+			new_type = __OVL_PATH_UPPER;
 		else
-			new_type = OVL_PATH_PURE_UPPER;
+			new_type = __OVL_PATH_UPPER | __OVL_PATH_PURE;
 	}
 
 	err = ovl_want_write(old);
@@ -763,8 +763,8 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 			goto out_drop_write;
 	}
 
-	old_opaque = old_type != OVL_PATH_PURE_UPPER;
-	new_opaque = new_type != OVL_PATH_PURE_UPPER;
+	old_opaque = !OVL_TYPE_PURE_UPPER(old_type);
+	new_opaque = !OVL_TYPE_PURE_UPPER(new_type);
 
 	if (old_opaque || new_opaque) {
 		err = -ENOMEM;
@@ -787,7 +787,7 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 		old_cred = override_creds(override_cred);
 	}
 
-	if (overwrite && (new_type == OVL_PATH_LOWER || new_type == OVL_PATH_MERGE) && new_is_dir) {
+	if (overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) {
 		opaquedir = ovl_check_empty_and_clear(new);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir)) {
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 07d74b24913b..04f124884687 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -205,7 +205,7 @@ static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
 
 static bool ovl_is_private_xattr(const char *name)
 {
-	return strncmp(name, "trusted.overlay.", 14) == 0;
+	return strncmp(name, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 0;
 }
 
 int ovl_setxattr(struct dentry *dentry, const char *name,
@@ -238,7 +238,10 @@ out:
 static bool ovl_need_xattr_filter(struct dentry *dentry,
 				  enum ovl_path_type type)
 {
-	return type == OVL_PATH_UPPER && S_ISDIR(dentry->d_inode->i_mode);
+	if ((type & (__OVL_PATH_PURE | __OVL_PATH_UPPER)) == __OVL_PATH_UPPER)
+		return S_ISDIR(dentry->d_inode->i_mode);
+	else
+		return false;
 }
 
 ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
@@ -299,7 +302,7 @@ int ovl_removexattr(struct dentry *dentry, const char *name)
 	if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
 		goto out_drop_write;
 
-	if (type == OVL_PATH_LOWER) {
+	if (!OVL_TYPE_UPPER(type)) {
 		err = vfs_getxattr(realpath.dentry, name, NULL, 0);
 		if (err < 0)
 			goto out_drop_write;
@@ -321,7 +324,7 @@ out:
 static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type,
 				  struct dentry *realdentry)
 {
-	if (type != OVL_PATH_LOWER)
+	if (OVL_TYPE_UPPER(type))
 		return false;
 
 	if (special_file(realdentry->d_inode->i_mode))
@@ -430,5 +433,4 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
 	}
 
 	return inode;
-
 }
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 814bed33dd07..17ac5afc9ffb 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -12,13 +12,20 @@
 struct ovl_entry;
 
 enum ovl_path_type {
-	OVL_PATH_PURE_UPPER,
-	OVL_PATH_UPPER,
-	OVL_PATH_MERGE,
-	OVL_PATH_LOWER,
+	__OVL_PATH_PURE		= (1 << 0),
+	__OVL_PATH_UPPER	= (1 << 1),
+	__OVL_PATH_MERGE	= (1 << 2),
 };
 
-extern const char *ovl_opaque_xattr;
+#define OVL_TYPE_UPPER(type)	((type) & __OVL_PATH_UPPER)
+#define OVL_TYPE_MERGE(type)	((type) & __OVL_PATH_MERGE)
+#define OVL_TYPE_PURE_UPPER(type) ((type) & __OVL_PATH_PURE)
+#define OVL_TYPE_MERGE_OR_LOWER(type) \
+	(OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type))
+
+#define OVL_XATTR_PRE_NAME "trusted.overlay."
+#define OVL_XATTR_PRE_LEN  16
+#define OVL_XATTR_OPAQUE   OVL_XATTR_PRE_NAME"opaque"
 
 static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry)
 {
@@ -130,6 +137,7 @@ void ovl_dentry_version_inc(struct dentry *dentry);
 void ovl_path_upper(struct dentry *dentry, struct path *path);
 void ovl_path_lower(struct dentry *dentry, struct path *path);
 enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path);
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
 struct dentry *ovl_dentry_upper(struct dentry *dentry);
 struct dentry *ovl_dentry_lower(struct dentry *dentry);
 struct dentry *ovl_dentry_real(struct dentry *dentry);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index c0205990a9f5..907870e81a72 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -24,7 +24,6 @@ struct ovl_cache_entry {
 	struct list_head l_node;
 	struct rb_node node;
 	bool is_whiteout;
-	bool is_cursor;
 	char name[];
 };
 
@@ -40,6 +39,7 @@ struct ovl_readdir_data {
 	struct rb_root root;
 	struct list_head *list;
 	struct list_head middle;
+	struct dentry *dir;
 	int count;
 	int err;
 };
@@ -48,7 +48,7 @@ struct ovl_dir_file {
 	bool is_real;
 	bool is_upper;
 	struct ovl_dir_cache *cache;
-	struct ovl_cache_entry cursor;
+	struct list_head *cursor;
 	struct file *realfile;
 	struct file *upperfile;
 };
@@ -79,23 +79,49 @@ static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root,
 	return NULL;
 }
 
-static struct ovl_cache_entry *ovl_cache_entry_new(const char *name, int len,
+static struct ovl_cache_entry *ovl_cache_entry_new(struct dentry *dir,
+						   const char *name, int len,
 						   u64 ino, unsigned int d_type)
 {
 	struct ovl_cache_entry *p;
 	size_t size = offsetof(struct ovl_cache_entry, name[len + 1]);
 
 	p = kmalloc(size, GFP_KERNEL);
-	if (p) {
-		memcpy(p->name, name, len);
-		p->name[len] = '\0';
-		p->len = len;
-		p->type = d_type;
-		p->ino = ino;
-		p->is_whiteout = false;
-		p->is_cursor = false;
-	}
+	if (!p)
+		return NULL;
+
+	memcpy(p->name, name, len);
+	p->name[len] = '\0';
+	p->len = len;
+	p->type = d_type;
+	p->ino = ino;
+	p->is_whiteout = false;
+
+	if (d_type == DT_CHR) {
+		struct dentry *dentry;
+		const struct cred *old_cred;
+		struct cred *override_cred;
+
+		override_cred = prepare_creds();
+		if (!override_cred) {
+			kfree(p);
+			return NULL;
+		}
+
+		/*
+		 * CAP_DAC_OVERRIDE for lookup
+		 */
+		cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+		old_cred = override_creds(override_cred);
 
+		dentry = lookup_one_len(name, dir, len);
+		if (!IS_ERR(dentry)) {
+			p->is_whiteout = ovl_is_whiteout(dentry);
+			dput(dentry);
+		}
+		revert_creds(old_cred);
+		put_cred(override_cred);
+	}
 	return p;
 }
 
@@ -122,7 +148,7 @@ static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd,
 			return 0;
 	}
 
-	p = ovl_cache_entry_new(name, len, ino, d_type);
+	p = ovl_cache_entry_new(rdd->dir, name, len, ino, d_type);
 	if (p == NULL)
 		return -ENOMEM;
 
@@ -143,7 +169,7 @@ static int ovl_fill_lower(struct ovl_readdir_data *rdd,
 	if (p) {
 		list_move_tail(&p->l_node, &rdd->middle);
 	} else {
-		p = ovl_cache_entry_new(name, namelen, ino, d_type);
+		p = ovl_cache_entry_new(rdd->dir, name, namelen, ino, d_type);
 		if (p == NULL)
 			rdd->err = -ENOMEM;
 		else
@@ -168,7 +194,6 @@ static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry)
 {
 	struct ovl_dir_cache *cache = od->cache;
 
-	list_del_init(&od->cursor.l_node);
 	WARN_ON(cache->refcount <= 0);
 	cache->refcount--;
 	if (!cache->refcount) {
@@ -204,6 +229,7 @@ static inline int ovl_dir_read(struct path *realpath,
 	if (IS_ERR(realfile))
 		return PTR_ERR(realfile);
 
+	rdd->dir = realpath->dentry;
 	rdd->ctx.pos = 0;
 	do {
 		rdd->count = 0;
@@ -227,108 +253,58 @@ static void ovl_dir_reset(struct file *file)
 	if (cache && ovl_dentry_version_get(dentry) != cache->version) {
 		ovl_cache_put(od, dentry);
 		od->cache = NULL;
+		od->cursor = NULL;
 	}
-	WARN_ON(!od->is_real && type != OVL_PATH_MERGE);
-	if (od->is_real && type == OVL_PATH_MERGE)
+	WARN_ON(!od->is_real && !OVL_TYPE_MERGE(type));
+	if (od->is_real && OVL_TYPE_MERGE(type))
 		od->is_real = false;
 }
 
-static int ovl_dir_mark_whiteouts(struct dentry *dir,
-				  struct ovl_readdir_data *rdd)
-{
-	struct ovl_cache_entry *p;
-	struct dentry *dentry;
-	const struct cred *old_cred;
-	struct cred *override_cred;
-
-	override_cred = prepare_creds();
-	if (!override_cred) {
-		ovl_cache_free(rdd->list);
-		return -ENOMEM;
-	}
-
-	/*
-	 * CAP_DAC_OVERRIDE for lookup
-	 */
-	cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
-	old_cred = override_creds(override_cred);
-
-	mutex_lock(&dir->d_inode->i_mutex);
-	list_for_each_entry(p, rdd->list, l_node) {
-		if (p->is_cursor)
-			continue;
-
-		if (p->type != DT_CHR)
-			continue;
-
-		dentry = lookup_one_len(p->name, dir, p->len);
-		if (IS_ERR(dentry))
-			continue;
-
-		p->is_whiteout = ovl_is_whiteout(dentry);
-		dput(dentry);
-	}
-	mutex_unlock(&dir->d_inode->i_mutex);
-
-	revert_creds(old_cred);
-	put_cred(override_cred);
-
-	return 0;
-}
-
 static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
 {
 	int err;
-	struct path lowerpath;
-	struct path upperpath;
+	struct path realpath;
 	struct ovl_readdir_data rdd = {
 		.ctx.actor = ovl_fill_merge,
 		.list = list,
 		.root = RB_ROOT,
 		.is_merge = false,
 	};
+	int idx, next;
 
-	ovl_path_lower(dentry, &lowerpath);
-	ovl_path_upper(dentry, &upperpath);
+	for (idx = 0; idx != -1; idx = next) {
+		next = ovl_path_next(idx, dentry, &realpath);
 
-	if (upperpath.dentry) {
-		err = ovl_dir_read(&upperpath, &rdd);
-		if (err)
-			goto out;
-
-		if (lowerpath.dentry) {
-			err = ovl_dir_mark_whiteouts(upperpath.dentry, &rdd);
+		if (next != -1) {
+			err = ovl_dir_read(&realpath, &rdd);
 			if (err)
-				goto out;
+				break;
+		} else {
+			/*
+			 * Insert lowest layer entries before upper ones, this
+			 * allows offsets to be reasonably constant
+			 */
+			list_add(&rdd.middle, rdd.list);
+			rdd.is_merge = true;
+			err = ovl_dir_read(&realpath, &rdd);
+			list_del(&rdd.middle);
 		}
 	}
-	if (lowerpath.dentry) {
-		/*
-		 * Insert lowerpath entries before upperpath ones, this allows
-		 * offsets to be reasonably constant
-		 */
-		list_add(&rdd.middle, rdd.list);
-		rdd.is_merge = true;
-		err = ovl_dir_read(&lowerpath, &rdd);
-		list_del(&rdd.middle);
-	}
-out:
 	return err;
 }
 
 static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
 {
-	struct ovl_cache_entry *p;
+	struct list_head *p;
 	loff_t off = 0;
 
-	list_for_each_entry(p, &od->cache->entries, l_node) {
-		if (p->is_cursor)
-			continue;
+	list_for_each(p, &od->cache->entries) {
 		if (off >= pos)
 			break;
 		off++;
 	}
-	list_move_tail(&od->cursor.l_node, &p->l_node);
+	/* Cursor is safe since the cache is stable */
+	od->cursor = p;
 }
 
 static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry)
@@ -367,6 +343,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
 {
 	struct ovl_dir_file *od = file->private_data;
 	struct dentry *dentry = file->f_path.dentry;
+	struct ovl_cache_entry *p;
 
 	if (!ctx->pos)
 		ovl_dir_reset(file);
@@ -385,19 +362,13 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
 		ovl_seek_cursor(od, ctx->pos);
 	}
 
-	while (od->cursor.l_node.next != &od->cache->entries) {
-		struct ovl_cache_entry *p;
-
-		p = list_entry(od->cursor.l_node.next, struct ovl_cache_entry, l_node);
-		/* Skip cursors */
-		if (!p->is_cursor) {
-			if (!p->is_whiteout) {
-				if (!dir_emit(ctx, p->name, p->len, p->ino, p->type))
-					break;
-			}
-			ctx->pos++;
-		}
-		list_move(&od->cursor.l_node, &p->l_node);
+	while (od->cursor != &od->cache->entries) {
+		p = list_entry(od->cursor, struct ovl_cache_entry, l_node);
+		if (!p->is_whiteout)
+			if (!dir_emit(ctx, p->name, p->len, p->ino, p->type))
+				break;
+		od->cursor = p->l_node.next;
+		ctx->pos++;
 	}
 	return 0;
 }
@@ -452,7 +423,7 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
 	/*
 	 * Need to check if we started out being a lower dir, but got copied up
 	 */
-	if (!od->is_upper && ovl_path_type(dentry) != OVL_PATH_LOWER) {
+	if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) {
 		struct inode *inode = file_inode(file);
 
 		realfile = lockless_dereference(od->upperfile);
@@ -516,11 +487,9 @@ static int ovl_dir_open(struct inode *inode, struct file *file)
 		kfree(od);
 		return PTR_ERR(realfile);
 	}
-	INIT_LIST_HEAD(&od->cursor.l_node);
 	od->realfile = realfile;
-	od->is_real = (type != OVL_PATH_MERGE);
-	od->is_upper = (type != OVL_PATH_LOWER);
-	od->cursor.is_cursor = true;
+	od->is_real = !OVL_TYPE_MERGE(type);
+	od->is_upper = OVL_TYPE_UPPER(type);
 	file->private_data = od;
 
 	return 0;
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index f16d318b71f8..5f0d1993e6e3 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -35,7 +35,8 @@ struct ovl_config {
 /* private information held for overlayfs's superblock */
 struct ovl_fs {
 	struct vfsmount *upper_mnt;
-	struct vfsmount *lower_mnt;
+	unsigned numlower;
+	struct vfsmount **lower_mnt;
 	struct dentry *workdir;
 	long lower_namelen;
 	/* pathnames of lower and upper dirs, for show_options */
@@ -47,7 +48,6 @@ struct ovl_dir_cache;
 /* private information held for every overlayfs dentry */
 struct ovl_entry {
 	struct dentry *__upperdentry;
-	struct dentry *lowerdentry;
 	struct ovl_dir_cache *cache;
 	union {
 		struct {
@@ -56,30 +56,36 @@ struct ovl_entry {
 		};
 		struct rcu_head rcu;
 	};
+	unsigned numlower;
+	struct path lowerstack[];
 };
 
-const char *ovl_opaque_xattr = "trusted.overlay.opaque";
+#define OVL_MAX_STACK 500
 
+static struct dentry *__ovl_dentry_lower(struct ovl_entry *oe)
+{
+	return oe->numlower ? oe->lowerstack[0].dentry : NULL;
+}
 
 enum ovl_path_type ovl_path_type(struct dentry *dentry)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
+	enum ovl_path_type type = 0;
 
 	if (oe->__upperdentry) {
-		if (oe->lowerdentry) {
+		type = __OVL_PATH_UPPER;
+
+		if (oe->numlower) {
 			if (S_ISDIR(dentry->d_inode->i_mode))
-				return OVL_PATH_MERGE;
-			else
-				return OVL_PATH_UPPER;
-		} else {
-			if (oe->opaque)
-				return OVL_PATH_UPPER;
-			else
-				return OVL_PATH_PURE_UPPER;
+				type |= __OVL_PATH_MERGE;
+		} else if (!oe->opaque) {
+			type |= __OVL_PATH_PURE;
 		}
 	} else {
-		return OVL_PATH_LOWER;
+		if (oe->numlower > 1)
+			type |= __OVL_PATH_MERGE;
 	}
+	return type;
 }
 
 static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe)
@@ -98,10 +104,9 @@ void ovl_path_upper(struct dentry *dentry, struct path *path)
 
 enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
 {
-
 	enum ovl_path_type type = ovl_path_type(dentry);
 
-	if (type == OVL_PATH_LOWER)
+	if (!OVL_TYPE_UPPER(type))
 		ovl_path_lower(dentry, path);
 	else
 		ovl_path_upper(dentry, path);
@@ -120,7 +125,7 @@ struct dentry *ovl_dentry_lower(struct dentry *dentry)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
 
-	return oe->lowerdentry;
+	return __ovl_dentry_lower(oe);
 }
 
 struct dentry *ovl_dentry_real(struct dentry *dentry)
@@ -130,7 +135,7 @@ struct dentry *ovl_dentry_real(struct dentry *dentry)
 
 	realdentry = ovl_upperdentry_dereference(oe);
 	if (!realdentry)
-		realdentry = oe->lowerdentry;
+		realdentry = __ovl_dentry_lower(oe);
 
 	return realdentry;
 }
@@ -143,7 +148,7 @@ struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper)
 	if (realdentry) {
 		*is_upper = true;
 	} else {
-		realdentry = oe->lowerdentry;
+		realdentry = __ovl_dentry_lower(oe);
 		*is_upper = false;
 	}
 	return realdentry;
@@ -165,11 +170,9 @@ void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache)
 
 void ovl_path_lower(struct dentry *dentry, struct path *path)
 {
-	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
 	struct ovl_entry *oe = dentry->d_fsdata;
 
-	path->mnt = ofs->lower_mnt;
-	path->dentry = oe->lowerdentry;
+	*path = oe->numlower ? oe->lowerstack[0] : (struct path) { NULL, NULL };
 }
 
 int ovl_want_write(struct dentry *dentry)
@@ -249,7 +252,7 @@ static bool ovl_is_opaquedir(struct dentry *dentry)
 	if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr)
 		return false;
 
-	res = inode->i_op->getxattr(dentry, ovl_opaque_xattr, &val, 1);
+	res = inode->i_op->getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1);
 	if (res == 1 && val == 'y')
 		return true;
 
@@ -261,8 +264,11 @@ static void ovl_dentry_release(struct dentry *dentry)
 	struct ovl_entry *oe = dentry->d_fsdata;
 
 	if (oe) {
+		unsigned int i;
+
 		dput(oe->__upperdentry);
-		dput(oe->lowerdentry);
+		for (i = 0; i < oe->numlower; i++)
+			dput(oe->lowerstack[i].dentry);
 		kfree_rcu(oe, rcu);
 	}
 }
@@ -271,9 +277,15 @@ static const struct dentry_operations ovl_dentry_operations = {
 	.d_release = ovl_dentry_release,
 };
 
-static struct ovl_entry *ovl_alloc_entry(void)
+static struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
 {
-	return kzalloc(sizeof(struct ovl_entry), GFP_KERNEL);
+	size_t size = offsetof(struct ovl_entry, lowerstack[numlower]);
+	struct ovl_entry *oe = kzalloc(size, GFP_KERNEL);
+
+	if (oe)
+		oe->numlower = numlower;
+
+	return oe;
 }
 
 static inline struct dentry *ovl_lookup_real(struct dentry *dir,
@@ -295,82 +307,154 @@ static inline struct dentry *ovl_lookup_real(struct dentry *dir,
 	return dentry;
 }
 
+/*
+ * Returns next layer in stack starting from top.
+ * Returns -1 if this is the last layer.
+ */
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	BUG_ON(idx < 0);
+	if (idx == 0) {
+		ovl_path_upper(dentry, path);
+		if (path->dentry)
+			return oe->numlower ? 1 : -1;
+		idx++;
+	}
+	BUG_ON(idx > oe->numlower);
+	*path = oe->lowerstack[idx - 1];
+
+	return (idx < oe->numlower) ? idx + 1 : -1;
+}
+
 struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			  unsigned int flags)
 {
 	struct ovl_entry *oe;
-	struct dentry *upperdir;
-	struct dentry *lowerdir;
-	struct dentry *upperdentry = NULL;
-	struct dentry *lowerdentry = NULL;
+	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
+	struct path *stack = NULL;
+	struct dentry *upperdir, *upperdentry = NULL;
+	unsigned int ctr = 0;
 	struct inode *inode = NULL;
+	bool upperopaque = false;
+	struct dentry *this, *prev = NULL;
+	unsigned int i;
 	int err;
 
-	err = -ENOMEM;
-	oe = ovl_alloc_entry();
-	if (!oe)
-		goto out;
-
-	upperdir = ovl_dentry_upper(dentry->d_parent);
-	lowerdir = ovl_dentry_lower(dentry->d_parent);
-
+	upperdir = ovl_upperdentry_dereference(poe);
 	if (upperdir) {
-		upperdentry = ovl_lookup_real(upperdir, &dentry->d_name);
-		err = PTR_ERR(upperdentry);
-		if (IS_ERR(upperdentry))
-			goto out_put_dir;
-
-		if (lowerdir && upperdentry) {
-			if (ovl_is_whiteout(upperdentry)) {
-				dput(upperdentry);
-				upperdentry = NULL;
-				oe->opaque = true;
-			} else if (ovl_is_opaquedir(upperdentry)) {
-				oe->opaque = true;
+		this = ovl_lookup_real(upperdir, &dentry->d_name);
+		err = PTR_ERR(this);
+		if (IS_ERR(this))
+			goto out;
+
+		if (this) {
+			if (ovl_is_whiteout(this)) {
+				dput(this);
+				this = NULL;
+				upperopaque = true;
+			} else if (poe->numlower && ovl_is_opaquedir(this)) {
+				upperopaque = true;
 			}
 		}
+		upperdentry = prev = this;
 	}
-	if (lowerdir && !oe->opaque) {
-		lowerdentry = ovl_lookup_real(lowerdir, &dentry->d_name);
-		err = PTR_ERR(lowerdentry);
-		if (IS_ERR(lowerdentry))
-			goto out_dput_upper;
+
+	if (!upperopaque && poe->numlower) {
+		err = -ENOMEM;
+		stack = kcalloc(poe->numlower, sizeof(struct path), GFP_KERNEL);
+		if (!stack)
+			goto out_put_upper;
 	}
 
-	if (lowerdentry && upperdentry &&
-	    (!S_ISDIR(upperdentry->d_inode->i_mode) ||
-	     !S_ISDIR(lowerdentry->d_inode->i_mode))) {
-		dput(lowerdentry);
-		lowerdentry = NULL;
-		oe->opaque = true;
+	for (i = 0; !upperopaque && i < poe->numlower; i++) {
+		bool opaque = false;
+		struct path lowerpath = poe->lowerstack[i];
+
+		this = ovl_lookup_real(lowerpath.dentry, &dentry->d_name);
+		err = PTR_ERR(this);
+		if (IS_ERR(this)) {
+			/*
+			 * If it's positive, then treat ENAMETOOLONG as ENOENT.
+			 */
+			if (err == -ENAMETOOLONG && (upperdentry || ctr))
+				continue;
+			goto out_put;
+		}
+		if (!this)
+			continue;
+		if (ovl_is_whiteout(this)) {
+			dput(this);
+			break;
+		}
+		/*
+		 * Only makes sense to check opaque dir if this is not the
+		 * lowermost layer.
+		 */
+		if (i < poe->numlower - 1 && ovl_is_opaquedir(this))
+			opaque = true;
+
+		if (prev && (!S_ISDIR(prev->d_inode->i_mode) ||
+			     !S_ISDIR(this->d_inode->i_mode))) {
+			/*
+			 * FIXME: check for upper-opaqueness maybe better done
+			 * in remove code.
+			 */
+			if (prev == upperdentry)
+				upperopaque = true;
+			dput(this);
+			break;
+		}
+		/*
+		 * If this is a non-directory then stop here.
+		 */
+		if (!S_ISDIR(this->d_inode->i_mode))
+			opaque = true;
+
+		stack[ctr].dentry = this;
+		stack[ctr].mnt = lowerpath.mnt;
+		ctr++;
+		prev = this;
+		if (opaque)
+			break;
 	}
 
-	if (lowerdentry || upperdentry) {
+	oe = ovl_alloc_entry(ctr);
+	err = -ENOMEM;
+	if (!oe)
+		goto out_put;
+
+	if (upperdentry || ctr) {
 		struct dentry *realdentry;
 
-		realdentry = upperdentry ? upperdentry : lowerdentry;
+		realdentry = upperdentry ? upperdentry : stack[0].dentry;
+
 		err = -ENOMEM;
 		inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode,
 				      oe);
 		if (!inode)
-			goto out_dput;
+			goto out_free_oe;
 		ovl_copyattr(realdentry->d_inode, inode);
 	}
 
+	oe->opaque = upperopaque;
 	oe->__upperdentry = upperdentry;
-	oe->lowerdentry = lowerdentry;
-
+	memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
+	kfree(stack);
 	dentry->d_fsdata = oe;
 	d_add(dentry, inode);
 
 	return NULL;
 
-out_dput:
-	dput(lowerdentry);
-out_dput_upper:
-	dput(upperdentry);
-out_put_dir:
+out_free_oe:
 	kfree(oe);
+out_put:
+	for (i = 0; i < ctr; i++)
+		dput(stack[i].dentry);
+	kfree(stack);
+out_put_upper:
+	dput(upperdentry);
 out:
 	return ERR_PTR(err);
 }
@@ -383,10 +467,12 @@ struct file *ovl_path_open(struct path *path, int flags)
 static void ovl_put_super(struct super_block *sb)
 {
 	struct ovl_fs *ufs = sb->s_fs_info;
+	unsigned i;
 
 	dput(ufs->workdir);
 	mntput(ufs->upper_mnt);
-	mntput(ufs->lower_mnt);
+	for (i = 0; i < ufs->numlower; i++)
+		mntput(ufs->lower_mnt[i]);
 
 	kfree(ufs->config.lowerdir);
 	kfree(ufs->config.upperdir);
@@ -400,7 +486,7 @@ static void ovl_put_super(struct super_block *sb)
  * @buf: The struct kstatfs to fill in with stats
  *
  * Get the filesystem statistics.  As writes always target the upper layer
- * filesystem pass the statfs to the same filesystem.
+ * filesystem pass the statfs to the upper filesystem (if it exists)
  */
 static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
@@ -409,7 +495,7 @@ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct path path;
 	int err;
 
-	ovl_path_upper(root_dentry, &path);
+	ovl_path_real(root_dentry, &path);
 
 	err = vfs_statfs(&path, buf);
 	if (!err) {
@@ -432,8 +518,20 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
 	struct ovl_fs *ufs = sb->s_fs_info;
 
 	seq_printf(m, ",lowerdir=%s", ufs->config.lowerdir);
-	seq_printf(m, ",upperdir=%s", ufs->config.upperdir);
-	seq_printf(m, ",workdir=%s", ufs->config.workdir);
+	if (ufs->config.upperdir) {
+		seq_printf(m, ",upperdir=%s", ufs->config.upperdir);
+		seq_printf(m, ",workdir=%s", ufs->config.workdir);
+	}
+	return 0;
+}
+
+static int ovl_remount(struct super_block *sb, int *flags, char *data)
+{
+	struct ovl_fs *ufs = sb->s_fs_info;
+
+	if (!(*flags & MS_RDONLY) && !ufs->upper_mnt)
+		return -EROFS;
+
 	return 0;
 }
 
@@ -441,6 +539,7 @@ static const struct super_operations ovl_super_operations = {
 	.put_super	= ovl_put_super,
 	.statfs		= ovl_statfs,
 	.show_options	= ovl_show_options,
+	.remount_fs	= ovl_remount,
 };
 
 enum {
@@ -515,9 +614,19 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 			break;
 
 		default:
+			pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
 			return -EINVAL;
 		}
 	}
+
+	/* Workdir is useless in non-upper mount */
+	if (!config->upperdir && config->workdir) {
+		pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
+			config->workdir);
+		kfree(config->workdir);
+		config->workdir = NULL;
+	}
+
 	return 0;
 }
 
@@ -585,24 +694,6 @@ static void ovl_unescape(char *s)
 	}
 }
 
-static int ovl_mount_dir(const char *name, struct path *path)
-{
-	int err;
-	char *tmp = kstrdup(name, GFP_KERNEL);
-
-	if (!tmp)
-		return -ENOMEM;
-
-	ovl_unescape(tmp);
-	err = kern_path(tmp, LOOKUP_FOLLOW, path);
-	if (err) {
-		pr_err("overlayfs: failed to resolve '%s': %i\n", tmp, err);
-		err = -EINVAL;
-	}
-	kfree(tmp);
-	return err;
-}
-
 static bool ovl_is_allowed_fs_type(struct dentry *root)
 {
 	const struct dentry_operations *dop = root->d_op;
@@ -622,6 +713,75 @@ static bool ovl_is_allowed_fs_type(struct dentry *root)
 	return true;
 }
 
+static int ovl_mount_dir_noesc(const char *name, struct path *path)
+{
+	int err = -EINVAL;
+
+	if (!*name) {
+		pr_err("overlayfs: empty lowerdir\n");
+		goto out;
+	}
+	err = kern_path(name, LOOKUP_FOLLOW, path);
+	if (err) {
+		pr_err("overlayfs: failed to resolve '%s': %i\n", name, err);
+		goto out;
+	}
+	err = -EINVAL;
+	if (!ovl_is_allowed_fs_type(path->dentry)) {
+		pr_err("overlayfs: filesystem on '%s' not supported\n", name);
+		goto out_put;
+	}
+	if (!S_ISDIR(path->dentry->d_inode->i_mode)) {
+		pr_err("overlayfs: '%s' not a directory\n", name);
+		goto out_put;
+	}
+	return 0;
+
+out_put:
+	path_put(path);
+out:
+	return err;
+}
+
+static int ovl_mount_dir(const char *name, struct path *path)
+{
+	int err = -ENOMEM;
+	char *tmp = kstrdup(name, GFP_KERNEL);
+
+	if (tmp) {
+		ovl_unescape(tmp);
+		err = ovl_mount_dir_noesc(tmp, path);
+		kfree(tmp);
+	}
+	return err;
+}
+
+static int ovl_lower_dir(const char *name, struct path *path, long *namelen,
+			 int *stack_depth)
+{
+	int err;
+	struct kstatfs statfs;
+
+	err = ovl_mount_dir_noesc(name, path);
+	if (err)
+		goto out;
+
+	err = vfs_statfs(path, &statfs);
+	if (err) {
+		pr_err("overlayfs: statfs failed on '%s'\n", name);
+		goto out_put;
+	}
+	*namelen = max(*namelen, statfs.f_namelen);
+	*stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth);
+
+	return 0;
+
+out_put:
+	path_put(path);
+out:
+	return err;
+}
+
 /* Workdir should not be subdir of upperdir and vice versa */
 static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir)
 {
@@ -634,16 +794,39 @@ static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir)
 	return ok;
 }
 
+static unsigned int ovl_split_lowerdirs(char *str)
+{
+	unsigned int ctr = 1;
+	char *s, *d;
+
+	for (s = d = str;; s++, d++) {
+		if (*s == '\\') {
+			s++;
+		} else if (*s == ':') {
+			*d = '\0';
+			ctr++;
+			continue;
+		}
+		*d = *s;
+		if (!*s)
+			break;
+	}
+	return ctr;
+}
+
 static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 {
-	struct path lowerpath;
-	struct path upperpath;
-	struct path workpath;
-	struct inode *root_inode;
+	struct path upperpath = { NULL, NULL };
+	struct path workpath = { NULL, NULL };
 	struct dentry *root_dentry;
 	struct ovl_entry *oe;
 	struct ovl_fs *ufs;
-	struct kstatfs statfs;
+	struct path *stack = NULL;
+	char *lowertmp;
+	char *lower;
+	unsigned int numlower;
+	unsigned int stacklen = 0;
+	unsigned int i;
 	int err;
 
 	err = -ENOMEM;
@@ -655,123 +838,147 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	if (err)
 		goto out_free_config;
 
-	/* FIXME: workdir is not needed for a R/O mount */
 	err = -EINVAL;
-	if (!ufs->config.upperdir || !ufs->config.lowerdir ||
-	    !ufs->config.workdir) {
-		pr_err("overlayfs: missing upperdir or lowerdir or workdir\n");
+	if (!ufs->config.lowerdir) {
+		pr_err("overlayfs: missing 'lowerdir'\n");
 		goto out_free_config;
 	}
 
-	err = -ENOMEM;
-	oe = ovl_alloc_entry();
-	if (oe == NULL)
-		goto out_free_config;
-
-	err = ovl_mount_dir(ufs->config.upperdir, &upperpath);
-	if (err)
-		goto out_free_oe;
+	sb->s_stack_depth = 0;
+	if (ufs->config.upperdir) {
+		if (!ufs->config.workdir) {
+			pr_err("overlayfs: missing 'workdir'\n");
+			goto out_free_config;
+		}
 
-	err = ovl_mount_dir(ufs->config.lowerdir, &lowerpath);
-	if (err)
-		goto out_put_upperpath;
+		err = ovl_mount_dir(ufs->config.upperdir, &upperpath);
+		if (err)
+			goto out_free_config;
 
-	err = ovl_mount_dir(ufs->config.workdir, &workpath);
-	if (err)
-		goto out_put_lowerpath;
+		/* Upper fs should not be r/o */
+		if (upperpath.mnt->mnt_sb->s_flags & MS_RDONLY) {
+			pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n");
+			err = -EINVAL;
+			goto out_put_upperpath;
+		}
 
-	err = -EINVAL;
-	if (!S_ISDIR(upperpath.dentry->d_inode->i_mode) ||
-	    !S_ISDIR(lowerpath.dentry->d_inode->i_mode) ||
-	    !S_ISDIR(workpath.dentry->d_inode->i_mode)) {
-		pr_err("overlayfs: upperdir or lowerdir or workdir not a directory\n");
-		goto out_put_workpath;
-	}
+		err = ovl_mount_dir(ufs->config.workdir, &workpath);
+		if (err)
+			goto out_put_upperpath;
 
-	if (upperpath.mnt != workpath.mnt) {
-		pr_err("overlayfs: workdir and upperdir must reside under the same mount\n");
-		goto out_put_workpath;
+		err = -EINVAL;
+		if (upperpath.mnt != workpath.mnt) {
+			pr_err("overlayfs: workdir and upperdir must reside under the same mount\n");
+			goto out_put_workpath;
+		}
+		if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) {
+			pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
+			goto out_put_workpath;
+		}
+		sb->s_stack_depth = upperpath.mnt->mnt_sb->s_stack_depth;
 	}
-	if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) {
-		pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
+	err = -ENOMEM;
+	lowertmp = kstrdup(ufs->config.lowerdir, GFP_KERNEL);
+	if (!lowertmp)
 		goto out_put_workpath;
-	}
 
-	if (!ovl_is_allowed_fs_type(upperpath.dentry)) {
-		pr_err("overlayfs: filesystem of upperdir is not supported\n");
-		goto out_put_workpath;
+	err = -EINVAL;
+	stacklen = ovl_split_lowerdirs(lowertmp);
+	if (stacklen > OVL_MAX_STACK) {
+		pr_err("overlayfs: too many lower directries, limit is %d\n",
+		       OVL_MAX_STACK);
+		goto out_free_lowertmp;
+	} else if (!ufs->config.upperdir && stacklen == 1) {
+		pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n");
+		goto out_free_lowertmp;
 	}
 
-	if (!ovl_is_allowed_fs_type(lowerpath.dentry)) {
-		pr_err("overlayfs: filesystem of lowerdir is not supported\n");
-		goto out_put_workpath;
-	}
+	stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL);
+	if (!stack)
+		goto out_free_lowertmp;
 
-	err = vfs_statfs(&lowerpath, &statfs);
-	if (err) {
-		pr_err("overlayfs: statfs failed on lowerpath\n");
-		goto out_put_workpath;
-	}
-	ufs->lower_namelen = statfs.f_namelen;
+	lower = lowertmp;
+	for (numlower = 0; numlower < stacklen; numlower++) {
+		err = ovl_lower_dir(lower, &stack[numlower],
+				    &ufs->lower_namelen, &sb->s_stack_depth);
+		if (err)
+			goto out_put_lowerpath;
 
-	sb->s_stack_depth = max(upperpath.mnt->mnt_sb->s_stack_depth,
-				lowerpath.mnt->mnt_sb->s_stack_depth) + 1;
+		lower = strchr(lower, '\0') + 1;
+	}
 
 	err = -EINVAL;
+	sb->s_stack_depth++;
 	if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
 		pr_err("overlayfs: maximum fs stacking depth exceeded\n");
-		goto out_put_workpath;
+		goto out_put_lowerpath;
 	}
 
-	ufs->upper_mnt = clone_private_mount(&upperpath);
-	err = PTR_ERR(ufs->upper_mnt);
-	if (IS_ERR(ufs->upper_mnt)) {
-		pr_err("overlayfs: failed to clone upperpath\n");
-		goto out_put_workpath;
-	}
+	if (ufs->config.upperdir) {
+		ufs->upper_mnt = clone_private_mount(&upperpath);
+		err = PTR_ERR(ufs->upper_mnt);
+		if (IS_ERR(ufs->upper_mnt)) {
+			pr_err("overlayfs: failed to clone upperpath\n");
+			goto out_put_lowerpath;
+		}
 
-	ufs->lower_mnt = clone_private_mount(&lowerpath);
-	err = PTR_ERR(ufs->lower_mnt);
-	if (IS_ERR(ufs->lower_mnt)) {
-		pr_err("overlayfs: failed to clone lowerpath\n");
-		goto out_put_upper_mnt;
+		ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry);
+		err = PTR_ERR(ufs->workdir);
+		if (IS_ERR(ufs->workdir)) {
+			pr_err("overlayfs: failed to create directory %s/%s\n",
+			       ufs->config.workdir, OVL_WORKDIR_NAME);
+			goto out_put_upper_mnt;
+		}
 	}
 
-	ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry);
-	err = PTR_ERR(ufs->workdir);
-	if (IS_ERR(ufs->workdir)) {
-		pr_err("overlayfs: failed to create directory %s/%s\n",
-		       ufs->config.workdir, OVL_WORKDIR_NAME);
-		goto out_put_lower_mnt;
-	}
+	err = -ENOMEM;
+	ufs->lower_mnt = kcalloc(numlower, sizeof(struct vfsmount *), GFP_KERNEL);
+	if (ufs->lower_mnt == NULL)
+		goto out_put_workdir;
+	for (i = 0; i < numlower; i++) {
+		struct vfsmount *mnt = clone_private_mount(&stack[i]);
 
-	/*
-	 * Make lower_mnt R/O.  That way fchmod/fchown on lower file
-	 * will fail instead of modifying lower fs.
-	 */
-	ufs->lower_mnt->mnt_flags |= MNT_READONLY;
+		err = PTR_ERR(mnt);
+		if (IS_ERR(mnt)) {
+			pr_err("overlayfs: failed to clone lowerpath\n");
+			goto out_put_lower_mnt;
+		}
+		/*
+		 * Make lower_mnt R/O.  That way fchmod/fchown on lower file
+		 * will fail instead of modifying lower fs.
+		 */
+		mnt->mnt_flags |= MNT_READONLY;
+
+		ufs->lower_mnt[ufs->numlower] = mnt;
+		ufs->numlower++;
+	}
 
-	/* If the upper fs is r/o, we mark overlayfs r/o too */
-	if (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY)
+	/* If the upper fs is nonexistent, we mark overlayfs r/o too */
+	if (!ufs->upper_mnt)
 		sb->s_flags |= MS_RDONLY;
 
 	sb->s_d_op = &ovl_dentry_operations;
 
 	err = -ENOMEM;
-	root_inode = ovl_new_inode(sb, S_IFDIR, oe);
-	if (!root_inode)
-		goto out_put_workdir;
+	oe = ovl_alloc_entry(numlower);
+	if (!oe)
+		goto out_put_lower_mnt;
 
-	root_dentry = d_make_root(root_inode);
+	root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, oe));
 	if (!root_dentry)
-		goto out_put_workdir;
+		goto out_free_oe;
 
 	mntput(upperpath.mnt);
-	mntput(lowerpath.mnt);
+	for (i = 0; i < numlower; i++)
+		mntput(stack[i].mnt);
 	path_put(&workpath);
+	kfree(lowertmp);
 
 	oe->__upperdentry = upperpath.dentry;
-	oe->lowerdentry = lowerpath.dentry;
+	for (i = 0; i < numlower; i++) {
+		oe->lowerstack[i].dentry = stack[i].dentry;
+		oe->lowerstack[i].mnt = ufs->lower_mnt[i];
+	}
 
 	root_dentry->d_fsdata = oe;
 
@@ -782,20 +989,26 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 
 	return 0;
 
+out_free_oe:
+	kfree(oe);
+out_put_lower_mnt:
+	for (i = 0; i < ufs->numlower; i++)
+		mntput(ufs->lower_mnt[i]);
+	kfree(ufs->lower_mnt);
 out_put_workdir:
 	dput(ufs->workdir);
-out_put_lower_mnt:
-	mntput(ufs->lower_mnt);
 out_put_upper_mnt:
 	mntput(ufs->upper_mnt);
+out_put_lowerpath:
+	for (i = 0; i < numlower; i++)
+		path_put(&stack[i]);
+	kfree(stack);
+out_free_lowertmp:
+	kfree(lowertmp);
 out_put_workpath:
 	path_put(&workpath);
-out_put_lowerpath:
-	path_put(&lowerpath);
 out_put_upperpath:
 	path_put(&upperpath);
-out_free_oe:
-	kfree(oe);
 out_free_config:
 	kfree(ufs->config.lowerdir);
 	kfree(ufs->config.upperdir);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 0855f772cd41..3a48bb789c9f 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -564,13 +564,11 @@ posix_acl_create(struct inode *dir, umode_t *mode,
 
 	*acl = posix_acl_clone(p, GFP_NOFS);
 	if (!*acl)
-		return -ENOMEM;
+		goto no_mem;
 
 	ret = posix_acl_create_masq(*acl, mode);
-	if (ret < 0) {
-		posix_acl_release(*acl);
-		return -ENOMEM;
-	}
+	if (ret < 0)
+		goto no_mem_clone;
 
 	if (ret == 0) {
 		posix_acl_release(*acl);
@@ -591,6 +589,12 @@ no_acl:
 	*default_acl = NULL;
 	*acl = NULL;
 	return 0;
+
+no_mem_clone:
+	posix_acl_release(*acl);
+no_mem:
+	posix_acl_release(p);
+	return -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(posix_acl_create);
 
@@ -772,7 +776,7 @@ posix_acl_xattr_get(struct dentry *dentry, const char *name,
 
 	if (!IS_POSIXACL(dentry->d_inode))
 		return -EOPNOTSUPP;
-	if (S_ISLNK(dentry->d_inode->i_mode))
+	if (d_is_symlink(dentry))
 		return -EOPNOTSUPP;
 
 	acl = get_acl(dentry->d_inode, type);
@@ -832,7 +836,7 @@ posix_acl_xattr_list(struct dentry *dentry, char *list, size_t list_size,
 
 	if (!IS_POSIXACL(dentry->d_inode))
 		return -EOPNOTSUPP;
-	if (S_ISLNK(dentry->d_inode->i_mode))
+	if (d_is_symlink(dentry))
 		return -EOPNOTSUPP;
 
 	if (type == ACL_TYPE_ACCESS)
diff --git a/fs/proc/array.c b/fs/proc/array.c
index bd117d065b82..1295a00ca316 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -81,6 +81,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/ptrace.h>
 #include <linux/tracehook.h>
+#include <linux/string_helpers.h>
 #include <linux/user_namespace.h>
 
 #include <asm/pgtable.h>
@@ -89,39 +90,18 @@
 
 static inline void task_name(struct seq_file *m, struct task_struct *p)
 {
-	int i;
-	char *buf, *end;
-	char *name;
+	char *buf;
 	char tcomm[sizeof(p->comm)];
 
 	get_task_comm(tcomm, p);
 
 	seq_puts(m, "Name:\t");
-	end = m->buf + m->size;
 	buf = m->buf + m->count;
-	name = tcomm;
-	i = sizeof(tcomm);
-	while (i && (buf < end)) {
-		unsigned char c = *name;
-		name++;
-		i--;
-		*buf = c;
-		if (!c)
-			break;
-		if (c == '\\') {
-			buf++;
-			if (buf < end)
-				*buf++ = c;
-			continue;
-		}
-		if (c == '\n') {
-			*buf++ = '\\';
-			if (buf < end)
-				*buf++ = 'n';
-			continue;
-		}
-		buf++;
-	}
+
+	/* Ignore error for now */
+	string_escape_str(tcomm, &buf, m->size - m->count,
+			  ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+
 	m->count = buf - m->buf;
 	seq_putc(m, '\n');
 }
@@ -336,12 +316,10 @@ static inline void task_context_switch_counts(struct seq_file *m,
 
 static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
 {
-	seq_puts(m, "Cpus_allowed:\t");
-	seq_cpumask(m, &task->cpus_allowed);
-	seq_putc(m, '\n');
-	seq_puts(m, "Cpus_allowed_list:\t");
-	seq_cpumask_list(m, &task->cpus_allowed);
-	seq_putc(m, '\n');
+	seq_printf(m, "Cpus_allowed:\t%*pb\n",
+		   cpumask_pr_args(&task->cpus_allowed));
+	seq_printf(m, "Cpus_allowed_list:\t%*pbl\n",
+		   cpumask_pr_args(&task->cpus_allowed));
 }
 
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 7fea13229f33..be65b2082135 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -19,7 +19,6 @@
 #include <linux/mount.h>
 #include <linux/init.h>
 #include <linux/idr.h>
-#include <linux/namei.h>
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -122,7 +121,7 @@ static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
 			struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
-	struct proc_dir_entry *de = PROC_I(inode)->pde;
+	struct proc_dir_entry *de = PDE(inode);
 	if (de && de->nlink)
 		set_nlink(inode, de->nlink);
 
@@ -223,17 +222,6 @@ void proc_free_inum(unsigned int inum)
 	spin_unlock_irqrestore(&proc_inum_lock, flags);
 }
 
-static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	nd_set_link(nd, __PDE_DATA(dentry->d_inode));
-	return NULL;
-}
-
-static const struct inode_operations proc_link_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= proc_follow_link,
-};
-
 /*
  * Don't create negative dentries here, return -ENOENT by hand
  * instead.
@@ -350,29 +338,12 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
 	if (ret)
 		return ret;
 
-	if (S_ISDIR(dp->mode)) {
-		dp->proc_fops = &proc_dir_operations;
-		dp->proc_iops = &proc_dir_inode_operations;
-		dir->nlink++;
-	} else if (S_ISLNK(dp->mode)) {
-		dp->proc_iops = &proc_link_inode_operations;
-	} else if (S_ISREG(dp->mode)) {
-		BUG_ON(dp->proc_fops == NULL);
-		dp->proc_iops = &proc_file_inode_operations;
-	} else {
-		WARN_ON(1);
-		proc_free_inum(dp->low_ino);
-		return -EINVAL;
-	}
-
 	spin_lock(&proc_subdir_lock);
 	dp->parent = dir;
 	if (pde_subdir_insert(dir, dp) == false) {
 		WARN(1, "proc_dir_entry '%s/%s' already registered\n",
 		     dir->name, dp->name);
 		spin_unlock(&proc_subdir_lock);
-		if (S_ISDIR(dp->mode))
-			dir->nlink--;
 		proc_free_inum(dp->low_ino);
 		return -EEXIST;
 	}
@@ -431,6 +402,7 @@ struct proc_dir_entry *proc_symlink(const char *name,
 		ent->data = kmalloc((ent->size=strlen(dest))+1, GFP_KERNEL);
 		if (ent->data) {
 			strcpy((char*)ent->data,dest);
+			ent->proc_iops = &proc_link_inode_operations;
 			if (proc_register(parent, ent) < 0) {
 				kfree(ent->data);
 				kfree(ent);
@@ -456,8 +428,12 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
 	ent = __proc_create(&parent, name, S_IFDIR | mode, 2);
 	if (ent) {
 		ent->data = data;
+		ent->proc_fops = &proc_dir_operations;
+		ent->proc_iops = &proc_dir_inode_operations;
+		parent->nlink++;
 		if (proc_register(parent, ent) < 0) {
 			kfree(ent);
+			parent->nlink--;
 			ent = NULL;
 		}
 	}
@@ -493,6 +469,8 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 		return NULL;
 	}
 
+	BUG_ON(proc_fops == NULL);
+
 	if ((mode & S_IALLUGO) == 0)
 		mode |= S_IRUGO;
 	pde = __proc_create(&parent, name, mode, 1);
@@ -500,6 +478,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 		goto out;
 	pde->proc_fops = proc_fops;
 	pde->data = data;
+	pde->proc_iops = &proc_file_inode_operations;
 	if (proc_register(parent, pde) < 0)
 		goto out_free;
 	return pde;
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 8420a2f80811..7697b6621cfd 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/magic.h>
+#include <linux/namei.h>
 
 #include <asm/uaccess.h>
 
@@ -40,7 +41,7 @@ static void proc_evict_inode(struct inode *inode)
 	put_pid(PROC_I(inode)->pid);
 
 	/* Let go of any associated proc directory entry */
-	de = PROC_I(inode)->pde;
+	de = PDE(inode);
 	if (de)
 		pde_put(de);
 	head = PROC_I(inode)->sysctl;
@@ -393,6 +394,26 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
 };
 #endif
 
+static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct proc_dir_entry *pde = PDE(dentry->d_inode);
+	if (unlikely(!use_pde(pde)))
+		return ERR_PTR(-EINVAL);
+	nd_set_link(nd, pde->data);
+	return pde;
+}
+
+static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+{
+	unuse_pde(p);
+}
+
+const struct inode_operations proc_link_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= proc_follow_link,
+	.put_link	= proc_put_link,
+};
+
 struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 {
 	struct inode *inode = new_inode_pseudo(sb);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 6fcdba573e0f..c835b94c0cd3 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -200,6 +200,7 @@ struct pde_opener {
 	int closing;
 	struct completion *c;
 };
+extern const struct inode_operations proc_link_inode_operations;
 
 extern const struct inode_operations proc_pid_link_inode_operations;
 
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 1e3187da1fed..7eee2d8b97d9 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -5,6 +5,7 @@
 #include <linux/ksm.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
+#include <linux/huge_mm.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/hugetlb.h>
@@ -121,9 +122,18 @@ u64 stable_page_flags(struct page *page)
 	 * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
 	 * to make sure a given page is a thp, not a non-huge compound page.
 	 */
-	else if (PageTransCompound(page) && (PageLRU(compound_head(page)) ||
-					     PageAnon(compound_head(page))))
-		u |= 1 << KPF_THP;
+	else if (PageTransCompound(page)) {
+		struct page *head = compound_head(page);
+
+		if (PageLRU(head) || PageAnon(head))
+			u |= 1 << KPF_THP;
+		else if (is_huge_zero_page(head)) {
+			u |= 1 << KPF_ZERO_PAGE;
+			u |= 1 << KPF_THP;
+		}
+	} else if (is_zero_pfn(page_to_pfn(page)))
+		u |= 1 << KPF_ZERO_PAGE;
+
 
 	/*
 	 * Caveats on high order pages: page->_count will only be set
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 246eae84b13b..6dee68d013ff 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -21,7 +21,7 @@
 
 void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
-	unsigned long data, text, lib, swap;
+	unsigned long data, text, lib, swap, ptes, pmds;
 	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
 
 	/*
@@ -42,6 +42,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
 	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
 	swap = get_mm_counter(mm, MM_SWAPENTS);
+	ptes = PTRS_PER_PTE * sizeof(pte_t) * atomic_long_read(&mm->nr_ptes);
+	pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm);
 	seq_printf(m,
 		"VmPeak:\t%8lu kB\n"
 		"VmSize:\t%8lu kB\n"
@@ -54,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		"VmExe:\t%8lu kB\n"
 		"VmLib:\t%8lu kB\n"
 		"VmPTE:\t%8lu kB\n"
+		"VmPMD:\t%8lu kB\n"
 		"VmSwap:\t%8lu kB\n",
 		hiwater_vm << (PAGE_SHIFT-10),
 		total_vm << (PAGE_SHIFT-10),
@@ -63,8 +66,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		total_rss << (PAGE_SHIFT-10),
 		data << (PAGE_SHIFT-10),
 		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
-		(PTRS_PER_PTE * sizeof(pte_t) *
-		 atomic_long_read(&mm->nr_ptes)) >> 10,
+		ptes >> 10,
+		pmds >> 10,
 		swap << (PAGE_SHIFT-10));
 }
 
@@ -433,7 +436,6 @@ const struct file_operations proc_tid_maps_operations = {
 
 #ifdef CONFIG_PROC_PAGE_MONITOR
 struct mem_size_stats {
-	struct vm_area_struct *vma;
 	unsigned long resident;
 	unsigned long shared_clean;
 	unsigned long shared_dirty;
@@ -443,7 +445,6 @@ struct mem_size_stats {
 	unsigned long anonymous;
 	unsigned long anonymous_thp;
 	unsigned long swap;
-	unsigned long nonlinear;
 	u64 pss;
 };
 
@@ -483,8 +484,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 		struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
-	struct vm_area_struct *vma = mss->vma;
-	pgoff_t pgoff = linear_page_index(vma, addr);
+	struct vm_area_struct *vma = walk->vma;
 	struct page *page = NULL;
 
 	if (pte_present(*pte)) {
@@ -496,17 +496,10 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 			mss->swap += PAGE_SIZE;
 		else if (is_migration_entry(swpent))
 			page = migration_entry_to_page(swpent);
-	} else if (pte_file(*pte)) {
-		if (pte_to_pgoff(*pte) != pgoff)
-			mss->nonlinear += PAGE_SIZE;
 	}
 
 	if (!page)
 		return;
-
-	if (page->index != pgoff)
-		mss->nonlinear += PAGE_SIZE;
-
 	smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte));
 }
 
@@ -515,7 +508,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 		struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
-	struct vm_area_struct *vma = mss->vma;
+	struct vm_area_struct *vma = walk->vma;
 	struct page *page;
 
 	/* FOLL_DUMP will return -EFAULT on huge zero page */
@@ -536,8 +529,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			   struct mm_walk *walk)
 {
-	struct mem_size_stats *mss = walk->private;
-	struct vm_area_struct *vma = mss->vma;
+	struct vm_area_struct *vma = walk->vma;
 	pte_t *pte;
 	spinlock_t *ptl;
 
@@ -596,7 +588,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_ACCOUNT)]	= "ac",
 		[ilog2(VM_NORESERVE)]	= "nr",
 		[ilog2(VM_HUGETLB)]	= "ht",
-		[ilog2(VM_NONLINEAR)]	= "nl",
 		[ilog2(VM_ARCH_1)]	= "ar",
 		[ilog2(VM_DONTDUMP)]	= "dd",
 #ifdef CONFIG_MEM_SOFT_DIRTY
@@ -630,10 +621,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 	};
 
 	memset(&mss, 0, sizeof mss);
-	mss.vma = vma;
 	/* mmap_sem is held in m_start */
-	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
-		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
+	walk_page_vma(vma, &smaps_walk);
 
 	show_map_vma(m, vma, is_pid);
 
@@ -668,10 +657,6 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   (vma->vm_flags & VM_LOCKED) ?
 			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
 
-	if (vma->vm_flags & VM_NONLINEAR)
-		seq_printf(m, "Nonlinear:      %8lu kB\n",
-				mss.nonlinear >> 10);
-
 	show_smap_vma_flags(m, vma);
 	m_cache_vma(m, vma);
 	return 0;
@@ -747,18 +732,18 @@ enum clear_refs_types {
 	CLEAR_REFS_ANON,
 	CLEAR_REFS_MAPPED,
 	CLEAR_REFS_SOFT_DIRTY,
+	CLEAR_REFS_MM_HIWATER_RSS,
 	CLEAR_REFS_LAST,
 };
 
 struct clear_refs_private {
-	struct vm_area_struct *vma;
 	enum clear_refs_types type;
 };
 
+#ifdef CONFIG_MEM_SOFT_DIRTY
 static inline void clear_soft_dirty(struct vm_area_struct *vma,
 		unsigned long addr, pte_t *pte)
 {
-#ifdef CONFIG_MEM_SOFT_DIRTY
 	/*
 	 * The soft-dirty tracker uses #PF-s to catch writes
 	 * to pages, so write-protect the pte as well. See the
@@ -772,24 +757,63 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 		ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
 	} else if (is_swap_pte(ptent)) {
 		ptent = pte_swp_clear_soft_dirty(ptent);
-	} else if (pte_file(ptent)) {
-		ptent = pte_file_clear_soft_dirty(ptent);
 	}
 
 	set_pte_at(vma->vm_mm, addr, pte, ptent);
-#endif
 }
 
+static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t *pmdp)
+{
+	pmd_t pmd = *pmdp;
+
+	pmd = pmd_wrprotect(pmd);
+	pmd = pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY);
+
+	if (vma->vm_flags & VM_SOFTDIRTY)
+		vma->vm_flags &= ~VM_SOFTDIRTY;
+
+	set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
+}
+
+#else
+
+static inline void clear_soft_dirty(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *pte)
+{
+}
+
+static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t *pmdp)
+{
+}
+#endif
+
 static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {
 	struct clear_refs_private *cp = walk->private;
-	struct vm_area_struct *vma = cp->vma;
+	struct vm_area_struct *vma = walk->vma;
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
 	struct page *page;
 
-	split_huge_page_pmd(vma, addr, pmd);
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+			clear_soft_dirty_pmd(vma, addr, pmd);
+			goto out;
+		}
+
+		page = pmd_page(*pmd);
+
+		/* Clear accessed and referenced bits. */
+		pmdp_test_and_clear_young(vma, addr, pmd);
+		ClearPageReferenced(page);
+out:
+		spin_unlock(ptl);
+		return 0;
+	}
+
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
@@ -818,6 +842,28 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	return 0;
 }
 
+static int clear_refs_test_walk(unsigned long start, unsigned long end,
+				struct mm_walk *walk)
+{
+	struct clear_refs_private *cp = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+
+	if (vma->vm_flags & VM_PFNMAP)
+		return 1;
+
+	/*
+	 * Writing 1 to /proc/pid/clear_refs affects all pages.
+	 * Writing 2 to /proc/pid/clear_refs only affects anonymous pages.
+	 * Writing 3 to /proc/pid/clear_refs only affects file mapped pages.
+	 * Writing 4 to /proc/pid/clear_refs affects all pages.
+	 */
+	if (cp->type == CLEAR_REFS_ANON && vma->vm_file)
+		return 1;
+	if (cp->type == CLEAR_REFS_MAPPED && !vma->vm_file)
+		return 1;
+	return 0;
+}
+
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -858,9 +904,22 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		};
 		struct mm_walk clear_refs_walk = {
 			.pmd_entry = clear_refs_pte_range,
+			.test_walk = clear_refs_test_walk,
 			.mm = mm,
 			.private = &cp,
 		};
+
+		if (type == CLEAR_REFS_MM_HIWATER_RSS) {
+			/*
+			 * Writing 5 to /proc/pid/clear_refs resets the peak
+			 * resident set size to this mm's current rss value.
+			 */
+			down_write(&mm->mmap_sem);
+			reset_mm_hiwater_rss(mm);
+			up_write(&mm->mmap_sem);
+			goto out_mm;
+		}
+
 		down_read(&mm->mmap_sem);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			for (vma = mm->mmap; vma; vma = vma->vm_next) {
@@ -877,32 +936,12 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			}
 			mmu_notifier_invalidate_range_start(mm, 0, -1);
 		}
-		for (vma = mm->mmap; vma; vma = vma->vm_next) {
-			cp.vma = vma;
-			if (is_vm_hugetlb_page(vma))
-				continue;
-			/*
-			 * Writing 1 to /proc/pid/clear_refs affects all pages.
-			 *
-			 * Writing 2 to /proc/pid/clear_refs only affects
-			 * Anonymous pages.
-			 *
-			 * Writing 3 to /proc/pid/clear_refs only affects file
-			 * mapped pages.
-			 *
-			 * Writing 4 to /proc/pid/clear_refs affects all pages.
-			 */
-			if (type == CLEAR_REFS_ANON && vma->vm_file)
-				continue;
-			if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
-				continue;
-			walk_page_range(vma->vm_start, vma->vm_end,
-					&clear_refs_walk);
-		}
+		walk_page_range(0, ~0UL, &clear_refs_walk);
 		if (type == CLEAR_REFS_SOFT_DIRTY)
 			mmu_notifier_invalidate_range_end(mm, 0, -1);
 		flush_tlb_mm(mm);
 		up_read(&mm->mmap_sem);
+out_mm:
 		mmput(mm);
 	}
 	put_task_struct(task);
@@ -1066,15 +1105,13 @@ static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemap
 static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
 {
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma = walk->vma;
 	struct pagemapread *pm = walk->private;
 	spinlock_t *ptl;
-	pte_t *pte;
+	pte_t *pte, *orig_pte;
 	int err = 0;
 
-	/* find the first VMA at or above 'addr' */
-	vma = find_vma(walk->mm, addr);
-	if (vma && pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		int pmd_flags2;
 
 		if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
@@ -1100,51 +1137,20 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
-	while (1) {
-		/* End of address space hole, which we mark as non-present. */
-		unsigned long hole_end;
-
-		if (vma)
-			hole_end = min(end, vma->vm_start);
-		else
-			hole_end = end;
-
-		for (; addr < hole_end; addr += PAGE_SIZE) {
-			pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
-
-			err = add_to_pagemap(addr, &pme, pm);
-			if (err)
-				return err;
-		}
-
-		if (!vma || vma->vm_start >= end)
-			break;
-		/*
-		 * We can't possibly be in a hugetlb VMA. In general,
-		 * for a mm_walk with a pmd_entry and a hugetlb_entry,
-		 * the pmd_entry can only be called on addresses in a
-		 * hugetlb if the walk starts in a non-hugetlb VMA and
-		 * spans a hugepage VMA. Since pagemap_read walks are
-		 * PMD-sized and PMD-aligned, this will never be true.
-		 */
-		BUG_ON(is_vm_hugetlb_page(vma));
-
-		/* Addresses in the VMA. */
-		for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
-			pagemap_entry_t pme;
-			pte = pte_offset_map(pmd, addr);
-			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
-			pte_unmap(pte);
-			err = add_to_pagemap(addr, &pme, pm);
-			if (err)
-				return err;
-		}
+	/*
+	 * We can assume that @vma always points to a valid one and @end never
+	 * goes beyond vma->vm_end.
+	 */
+	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	for (; addr < end; pte++, addr += PAGE_SIZE) {
+		pagemap_entry_t pme;
 
-		if (addr == end)
+		pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
+		err = add_to_pagemap(addr, &pme, pm);
+		if (err)
 			break;
-
-		vma = find_vma(walk->mm, addr);
 	}
+	pte_unmap_unlock(orig_pte, ptl);
 
 	cond_resched();
 
@@ -1170,15 +1176,12 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
 				 struct mm_walk *walk)
 {
 	struct pagemapread *pm = walk->private;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma = walk->vma;
 	int err = 0;
 	int flags2;
 	pagemap_entry_t pme;
 
-	vma = find_vma(walk->mm, addr);
-	WARN_ON_ONCE(!vma);
-
-	if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+	if (vma->vm_flags & VM_SOFTDIRTY)
 		flags2 = __PM_SOFT_DIRTY;
 	else
 		flags2 = 0;
@@ -1322,6 +1325,9 @@ out:
 
 static int pagemap_open(struct inode *inode, struct file *file)
 {
+	/* do not disclose physical addresses: attack vector */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
 	pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
 			"to stop being page-shift some time soon. See the "
 			"linux/Documentation/vm/pagemap.txt for details.\n");
@@ -1338,7 +1344,6 @@ const struct file_operations proc_pagemap_operations = {
 #ifdef CONFIG_NUMA
 
 struct numa_maps {
-	struct vm_area_struct *vma;
 	unsigned long pages;
 	unsigned long anon;
 	unsigned long active;
@@ -1407,18 +1412,17 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
 static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		unsigned long end, struct mm_walk *walk)
 {
-	struct numa_maps *md;
+	struct numa_maps *md = walk->private;
+	struct vm_area_struct *vma = walk->vma;
 	spinlock_t *ptl;
 	pte_t *orig_pte;
 	pte_t *pte;
 
-	md = walk->private;
-
-	if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 
-		page = can_gather_numa_stats(huge_pte, md->vma, addr);
+		page = can_gather_numa_stats(huge_pte, vma, addr);
 		if (page)
 			gather_stats(page, md, pte_dirty(huge_pte),
 				     HPAGE_PMD_SIZE/PAGE_SIZE);
@@ -1430,7 +1434,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		return 0;
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
-		struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
+		struct page *page = can_gather_numa_stats(*pte, vma, addr);
 		if (!page)
 			continue;
 		gather_stats(page, md, pte_dirty(*pte), 1);
@@ -1440,7 +1444,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	return 0;
 }
 #ifdef CONFIG_HUGETLB_PAGE
-static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
 		unsigned long addr, unsigned long end, struct mm_walk *walk)
 {
 	struct numa_maps *md;
@@ -1459,7 +1463,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 }
 
 #else
-static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
 		unsigned long addr, unsigned long end, struct mm_walk *walk)
 {
 	return 0;
@@ -1477,7 +1481,12 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	struct numa_maps *md = &numa_priv->md;
 	struct file *file = vma->vm_file;
 	struct mm_struct *mm = vma->vm_mm;
-	struct mm_walk walk = {};
+	struct mm_walk walk = {
+		.hugetlb_entry = gather_hugetlb_stats,
+		.pmd_entry = gather_pte_stats,
+		.private = md,
+		.mm = mm,
+	};
 	struct mempolicy *pol;
 	char buffer[64];
 	int nid;
@@ -1488,13 +1497,6 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	/* Ensure we start with an empty set of numa_maps statistics. */
 	memset(md, 0, sizeof(*md));
 
-	md->vma = vma;
-
-	walk.hugetlb_entry = gather_hugetbl_stats;
-	walk.pmd_entry = gather_pte_stats;
-	walk.private = md;
-	walk.mm = mm;
-
 	pol = __get_vma_policy(vma, vma->vm_start);
 	if (pol) {
 		mpol_to_str(buffer, sizeof(buffer), pol);
@@ -1528,7 +1530,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	if (is_vm_hugetlb_page(vma))
 		seq_puts(m, " huge");
 
-	walk_page_range(vma->vm_start, vma->vm_end, &walk);
+	/* mmap_sem is held by m_start */
+	walk_page_vma(vma, &walk);
 
 	if (!md->pages)
 		goto out;
@@ -1557,6 +1560,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	for_each_node_state(nid, N_MEMORY)
 		if (md->node[nid])
 			seq_printf(m, " N%d=%lu", nid, md->node[nid]);
+
+	seq_printf(m, " kernelpagesize_kB=%lu", vma_kernel_pagesize(vma) >> 10);
 out:
 	seq_putc(m, '\n');
 	m_cache_vma(m, vma);
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index a90d6d354199..4e61388ec03d 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -546,8 +546,8 @@ static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr)
 		nhdr_ptr = notes_section;
 		while (nhdr_ptr->n_namesz != 0) {
 			sz = sizeof(Elf64_Nhdr) +
-				((nhdr_ptr->n_namesz + 3) & ~3) +
-				((nhdr_ptr->n_descsz + 3) & ~3);
+				(((u64)nhdr_ptr->n_namesz + 3) & ~3) +
+				(((u64)nhdr_ptr->n_descsz + 3) & ~3);
 			if ((real_sz + sz) > max_sz) {
 				pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
 					nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
@@ -732,8 +732,8 @@ static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr)
 		nhdr_ptr = notes_section;
 		while (nhdr_ptr->n_namesz != 0) {
 			sz = sizeof(Elf32_Nhdr) +
-				((nhdr_ptr->n_namesz + 3) & ~3) +
-				((nhdr_ptr->n_descsz + 3) & ~3);
+				(((u64)nhdr_ptr->n_namesz + 3) & ~3) +
+				(((u64)nhdr_ptr->n_descsz + 3) & ~3);
 			if ((real_sz + sz) > max_sz) {
 				pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
 					nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 0f96f71ab32b..8db932da4009 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -44,6 +44,7 @@ static int show_sb_opts(struct seq_file *m, struct super_block *sb)
 		{ MS_SYNCHRONOUS, ",sync" },
 		{ MS_DIRSYNC, ",dirsync" },
 		{ MS_MANDLOCK, ",mand" },
+		{ MS_LAZYTIME, ",lazytime" },
 		{ 0, NULL }
 	};
 	const struct proc_fs_info *fs_infop;
diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index 983d9510becc..916b8e23d968 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -21,6 +21,16 @@ config PSTORE_CONSOLE
 	  When the option is enabled, pstore will log all kernel
 	  messages, even if no oops or panic happened.
 
+config PSTORE_PMSG
+	bool "Log user space messages"
+	depends on PSTORE
+	help
+	  When the option is enabled, pstore will export a character
+	  interface /dev/pmsg0 to log user space messages. On reboot
+	  data can be retrieved from /sys/fs/pstore/pmsg-ramoops-[ID].
+
+	  If unsure, say N.
+
 config PSTORE_FTRACE
 	bool "Persistent function tracer"
 	depends on PSTORE
diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile
index 4c9095c2781e..e647d8e81712 100644
--- a/fs/pstore/Makefile
+++ b/fs/pstore/Makefile
@@ -7,5 +7,7 @@ obj-y += pstore.o
 pstore-objs += inode.o platform.o
 obj-$(CONFIG_PSTORE_FTRACE)	+= ftrace.o
 
+obj-$(CONFIG_PSTORE_PMSG)	+= pmsg.o
+
 ramoops-objs += ram.o ram_core.o
 obj-$(CONFIG_PSTORE_RAM)	+= ramoops.o
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 50416602774d..b32ce53d24ee 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -338,32 +338,38 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 
 	switch (type) {
 	case PSTORE_TYPE_DMESG:
-		sprintf(name, "dmesg-%s-%lld%s", psname, id,
-						compressed ? ".enc.z" : "");
+		scnprintf(name, sizeof(name), "dmesg-%s-%lld%s",
+			  psname, id, compressed ? ".enc.z" : "");
 		break;
 	case PSTORE_TYPE_CONSOLE:
-		sprintf(name, "console-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "console-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_FTRACE:
-		sprintf(name, "ftrace-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "ftrace-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_MCE:
-		sprintf(name, "mce-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "mce-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_PPC_RTAS:
-		sprintf(name, "rtas-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "rtas-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_PPC_OF:
-		sprintf(name, "powerpc-ofw-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "powerpc-ofw-%s-%lld",
+			  psname, id);
 		break;
 	case PSTORE_TYPE_PPC_COMMON:
-		sprintf(name, "powerpc-common-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "powerpc-common-%s-%lld",
+			  psname, id);
+		break;
+	case PSTORE_TYPE_PMSG:
+		scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_UNKNOWN:
-		sprintf(name, "unknown-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id);
 		break;
 	default:
-		sprintf(name, "type%d-%s-%lld", type, psname, id);
+		scnprintf(name, sizeof(name), "type%d-%s-%lld",
+			  type, psname, id);
 		break;
 	}
 
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index 3b3d305277c4..c36ba2cd0b5d 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -45,6 +45,12 @@ extern void pstore_register_ftrace(void);
 static inline void pstore_register_ftrace(void) {}
 #endif
 
+#ifdef CONFIG_PSTORE_PMSG
+extern void pstore_register_pmsg(void);
+#else
+static inline void pstore_register_pmsg(void) {}
+#endif
+
 extern struct pstore_info *psinfo;
 
 extern void	pstore_set_kmsg_bytes(int);
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 0a9b72cdfeca..c4c9a10c5760 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -301,7 +301,7 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 
 		if (big_oops_buf) {
 			dst = big_oops_buf;
-			hsize = sprintf(dst, "%s#%d Part%d\n", why,
+			hsize = sprintf(dst, "%s#%d Part%u\n", why,
 							oopscount, part);
 			size = big_oops_buf_sz - hsize;
 
@@ -321,7 +321,7 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 			}
 		} else {
 			dst = psinfo->buf;
-			hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount,
+			hsize = sprintf(dst, "%s#%d Part%u\n", why, oopscount,
 									part);
 			size = psinfo->bufsize - hsize;
 			dst += hsize;
@@ -447,6 +447,7 @@ int pstore_register(struct pstore_info *psi)
 	if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) {
 		pstore_register_console();
 		pstore_register_ftrace();
+		pstore_register_pmsg();
 	}
 
 	if (pstore_update_ms >= 0) {
diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c
new file mode 100644
index 000000000000..feb5dd2948b4
--- /dev/null
+++ b/fs/pstore/pmsg.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright 2014  Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * 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.
+ */
+
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include "internal.h"
+
+static DEFINE_MUTEX(pmsg_lock);
+#define PMSG_MAX_BOUNCE_BUFFER_SIZE (2*PAGE_SIZE)
+
+static ssize_t write_pmsg(struct file *file, const char __user *buf,
+			  size_t count, loff_t *ppos)
+{
+	size_t i, buffer_size;
+	char *buffer;
+
+	if (!count)
+		return 0;
+
+	if (!access_ok(VERIFY_READ, buf, count))
+		return -EFAULT;
+
+	buffer_size = count;
+	if (buffer_size > PMSG_MAX_BOUNCE_BUFFER_SIZE)
+		buffer_size = PMSG_MAX_BOUNCE_BUFFER_SIZE;
+	buffer = vmalloc(buffer_size);
+
+	mutex_lock(&pmsg_lock);
+	for (i = 0; i < count; ) {
+		size_t c = min(count - i, buffer_size);
+		u64 id;
+		long ret;
+
+		ret = __copy_from_user(buffer, buf + i, c);
+		if (unlikely(ret != 0)) {
+			mutex_unlock(&pmsg_lock);
+			vfree(buffer);
+			return -EFAULT;
+		}
+		psinfo->write_buf(PSTORE_TYPE_PMSG, 0, &id, 0, buffer, 0, c,
+				  psinfo);
+
+		i += c;
+	}
+
+	mutex_unlock(&pmsg_lock);
+	vfree(buffer);
+	return count;
+}
+
+static const struct file_operations pmsg_fops = {
+	.owner		= THIS_MODULE,
+	.llseek		= noop_llseek,
+	.write		= write_pmsg,
+};
+
+static struct class *pmsg_class;
+static int pmsg_major;
+#define PMSG_NAME "pmsg"
+#undef pr_fmt
+#define pr_fmt(fmt) PMSG_NAME ": " fmt
+
+static char *pmsg_devnode(struct device *dev, umode_t *mode)
+{
+	if (mode)
+		*mode = 0220;
+	return NULL;
+}
+
+void pstore_register_pmsg(void)
+{
+	struct device *pmsg_device;
+
+	pmsg_major = register_chrdev(0, PMSG_NAME, &pmsg_fops);
+	if (pmsg_major < 0) {
+		pr_err("register_chrdev failed\n");
+		goto err;
+	}
+
+	pmsg_class = class_create(THIS_MODULE, PMSG_NAME);
+	if (IS_ERR(pmsg_class)) {
+		pr_err("device class file already in use\n");
+		goto err_class;
+	}
+	pmsg_class->devnode = pmsg_devnode;
+
+	pmsg_device = device_create(pmsg_class, NULL, MKDEV(pmsg_major, 0),
+					NULL, "%s%d", PMSG_NAME, 0);
+	if (IS_ERR(pmsg_device)) {
+		pr_err("failed to create device\n");
+		goto err_device;
+	}
+	return;
+
+err_device:
+	class_destroy(pmsg_class);
+err_class:
+	unregister_chrdev(pmsg_major, PMSG_NAME);
+err:
+	return;
+}
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 8613e5b35c22..39d1373128e9 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -51,6 +51,10 @@ static ulong ramoops_ftrace_size = MIN_MEM_SIZE;
 module_param_named(ftrace_size, ramoops_ftrace_size, ulong, 0400);
 MODULE_PARM_DESC(ftrace_size, "size of ftrace log");
 
+static ulong ramoops_pmsg_size = MIN_MEM_SIZE;
+module_param_named(pmsg_size, ramoops_pmsg_size, ulong, 0400);
+MODULE_PARM_DESC(pmsg_size, "size of user space message log");
+
 static ulong mem_address;
 module_param(mem_address, ulong, 0400);
 MODULE_PARM_DESC(mem_address,
@@ -82,12 +86,14 @@ struct ramoops_context {
 	struct persistent_ram_zone **przs;
 	struct persistent_ram_zone *cprz;
 	struct persistent_ram_zone *fprz;
+	struct persistent_ram_zone *mprz;
 	phys_addr_t phys_addr;
 	unsigned long size;
 	unsigned int memtype;
 	size_t record_size;
 	size_t console_size;
 	size_t ftrace_size;
+	size_t pmsg_size;
 	int dump_oops;
 	struct persistent_ram_ecc_info ecc_info;
 	unsigned int max_dump_cnt;
@@ -96,6 +102,7 @@ struct ramoops_context {
 	unsigned int dump_read_cnt;
 	unsigned int console_read_cnt;
 	unsigned int ftrace_read_cnt;
+	unsigned int pmsg_read_cnt;
 	struct pstore_info pstore;
 };
 
@@ -109,6 +116,7 @@ static int ramoops_pstore_open(struct pstore_info *psi)
 	cxt->dump_read_cnt = 0;
 	cxt->console_read_cnt = 0;
 	cxt->ftrace_read_cnt = 0;
+	cxt->pmsg_read_cnt = 0;
 	return 0;
 }
 
@@ -164,6 +172,12 @@ static int ramoops_read_kmsg_hdr(char *buffer, struct timespec *time,
 	return header_length;
 }
 
+static bool prz_ok(struct persistent_ram_zone *prz)
+{
+	return !!prz && !!(persistent_ram_old_size(prz) +
+			   persistent_ram_ecc_string(prz, NULL, 0));
+}
+
 static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 				   int *count, struct timespec *time,
 				   char **buf, bool *compressed,
@@ -178,13 +192,16 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 	prz = ramoops_get_next_prz(cxt->przs, &cxt->dump_read_cnt,
 				   cxt->max_dump_cnt, id, type,
 				   PSTORE_TYPE_DMESG, 1);
-	if (!prz)
+	if (!prz_ok(prz))
 		prz = ramoops_get_next_prz(&cxt->cprz, &cxt->console_read_cnt,
 					   1, id, type, PSTORE_TYPE_CONSOLE, 0);
-	if (!prz)
+	if (!prz_ok(prz))
 		prz = ramoops_get_next_prz(&cxt->fprz, &cxt->ftrace_read_cnt,
 					   1, id, type, PSTORE_TYPE_FTRACE, 0);
-	if (!prz)
+	if (!prz_ok(prz))
+		prz = ramoops_get_next_prz(&cxt->mprz, &cxt->pmsg_read_cnt,
+					   1, id, type, PSTORE_TYPE_PMSG, 0);
+	if (!prz_ok(prz))
 		return 0;
 
 	if (!persistent_ram_old(prz))
@@ -252,6 +269,11 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
 			return -ENOMEM;
 		persistent_ram_write(cxt->fprz, buf, size);
 		return 0;
+	} else if (type == PSTORE_TYPE_PMSG) {
+		if (!cxt->mprz)
+			return -ENOMEM;
+		persistent_ram_write(cxt->mprz, buf, size);
+		return 0;
 	}
 
 	if (type != PSTORE_TYPE_DMESG)
@@ -309,6 +331,9 @@ static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, int count,
 	case PSTORE_TYPE_FTRACE:
 		prz = cxt->fprz;
 		break;
+	case PSTORE_TYPE_PMSG:
+		prz = cxt->mprz;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -435,7 +460,7 @@ static int ramoops_probe(struct platform_device *pdev)
 		goto fail_out;
 
 	if (!pdata->mem_size || (!pdata->record_size && !pdata->console_size &&
-			!pdata->ftrace_size)) {
+			!pdata->ftrace_size && !pdata->pmsg_size)) {
 		pr_err("The memory size and the record/console size must be "
 			"non-zero\n");
 		goto fail_out;
@@ -447,6 +472,8 @@ static int ramoops_probe(struct platform_device *pdev)
 		pdata->console_size = rounddown_pow_of_two(pdata->console_size);
 	if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size))
 		pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size);
+	if (pdata->pmsg_size && !is_power_of_2(pdata->pmsg_size))
+		pdata->pmsg_size = rounddown_pow_of_two(pdata->pmsg_size);
 
 	cxt->size = pdata->mem_size;
 	cxt->phys_addr = pdata->mem_address;
@@ -454,12 +481,14 @@ static int ramoops_probe(struct platform_device *pdev)
 	cxt->record_size = pdata->record_size;
 	cxt->console_size = pdata->console_size;
 	cxt->ftrace_size = pdata->ftrace_size;
+	cxt->pmsg_size = pdata->pmsg_size;
 	cxt->dump_oops = pdata->dump_oops;
 	cxt->ecc_info = pdata->ecc_info;
 
 	paddr = cxt->phys_addr;
 
-	dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size;
+	dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size
+			- cxt->pmsg_size;
 	err = ramoops_init_przs(dev, cxt, &paddr, dump_mem_sz);
 	if (err)
 		goto fail_out;
@@ -474,13 +503,9 @@ static int ramoops_probe(struct platform_device *pdev)
 	if (err)
 		goto fail_init_fprz;
 
-	if (!cxt->przs && !cxt->cprz && !cxt->fprz) {
-		pr_err("memory size too small, minimum is %zu\n",
-			cxt->console_size + cxt->record_size +
-			cxt->ftrace_size);
-		err = -EINVAL;
-		goto fail_cnt;
-	}
+	err = ramoops_init_prz(dev, cxt, &cxt->mprz, &paddr, cxt->pmsg_size, 0);
+	if (err)
+		goto fail_init_mprz;
 
 	cxt->pstore.data = cxt;
 	/*
@@ -525,7 +550,8 @@ fail_buf:
 	kfree(cxt->pstore.buf);
 fail_clear:
 	cxt->pstore.bufsize = 0;
-fail_cnt:
+	kfree(cxt->mprz);
+fail_init_mprz:
 	kfree(cxt->fprz);
 fail_init_fprz:
 	kfree(cxt->cprz);
@@ -583,6 +609,7 @@ static void ramoops_register_dummy(void)
 	dummy_data->record_size = record_size;
 	dummy_data->console_size = ramoops_console_size;
 	dummy_data->ftrace_size = ramoops_ftrace_size;
+	dummy_data->pmsg_size = ramoops_pmsg_size;
 	dummy_data->dump_oops = dump_oops;
 	/*
 	 * For backwards compatibility ramoops.ecc=1 means 16 bytes ECC
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 69df5b239844..0ccd4ba3a246 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1248,7 +1248,7 @@ static int ignore_hardlimit(struct dquot *dquot)
 
 	return capable(CAP_SYS_RESOURCE) &&
 	       (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD ||
-		!(info->dqi_flags & V1_DQF_RSQUASH));
+		!(info->dqi_flags & DQF_ROOT_SQUASH));
 }
 
 /* needs dq_data_lock */
@@ -2385,14 +2385,84 @@ out:
 }
 EXPORT_SYMBOL(dquot_quota_on_mount);
 
-static inline qsize_t qbtos(qsize_t blocks)
+static int dquot_quota_enable(struct super_block *sb, unsigned int flags)
 {
-	return blocks << QIF_DQBLKSIZE_BITS;
+	int ret;
+	int type;
+	struct quota_info *dqopt = sb_dqopt(sb);
+
+	if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE))
+		return -ENOSYS;
+	/* Accounting cannot be turned on while fs is mounted */
+	flags &= ~(FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT);
+	if (!flags)
+		return -EINVAL;
+	for (type = 0; type < MAXQUOTAS; type++) {
+		if (!(flags & qtype_enforce_flag(type)))
+			continue;
+		/* Can't enforce without accounting */
+		if (!sb_has_quota_usage_enabled(sb, type))
+			return -EINVAL;
+		ret = dquot_enable(dqopt->files[type], type,
+				   dqopt->info[type].dqi_fmt_id,
+				   DQUOT_LIMITS_ENABLED);
+		if (ret < 0)
+			goto out_err;
+	}
+	return 0;
+out_err:
+	/* Backout enforcement enablement we already did */
+	for (type--; type >= 0; type--)  {
+		if (flags & qtype_enforce_flag(type))
+			dquot_disable(sb, type, DQUOT_LIMITS_ENABLED);
+	}
+	/* Error code translation for better compatibility with XFS */
+	if (ret == -EBUSY)
+		ret = -EEXIST;
+	return ret;
 }
 
-static inline qsize_t stoqb(qsize_t space)
+static int dquot_quota_disable(struct super_block *sb, unsigned int flags)
 {
-	return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS;
+	int ret;
+	int type;
+	struct quota_info *dqopt = sb_dqopt(sb);
+
+	if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE))
+		return -ENOSYS;
+	/*
+	 * We don't support turning off accounting via quotactl. In principle
+	 * quota infrastructure can do this but filesystems don't expect
+	 * userspace to be able to do it.
+	 */
+	if (flags &
+		  (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT))
+		return -EOPNOTSUPP;
+
+	/* Filter out limits not enabled */
+	for (type = 0; type < MAXQUOTAS; type++)
+		if (!sb_has_quota_limits_enabled(sb, type))
+			flags &= ~qtype_enforce_flag(type);
+	/* Nothing left? */
+	if (!flags)
+		return -EEXIST;
+	for (type = 0; type < MAXQUOTAS; type++) {
+		if (flags & qtype_enforce_flag(type)) {
+			ret = dquot_disable(sb, type, DQUOT_LIMITS_ENABLED);
+			if (ret < 0)
+				goto out_err;
+		}
+	}
+	return 0;
+out_err:
+	/* Backout enforcement disabling we already did */
+	for (type--; type >= 0; type--)  {
+		if (flags & qtype_enforce_flag(type))
+			dquot_enable(dqopt->files[type], type,
+				     dqopt->info[type].dqi_fmt_id,
+				     DQUOT_LIMITS_ENABLED);
+	}
+	return ret;
 }
 
 /* Generic routine for getting common part of quota structure */
@@ -2444,13 +2514,13 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 		return -EINVAL;
 
 	if (((di->d_fieldmask & QC_SPC_SOFT) &&
-	     stoqb(di->d_spc_softlimit) > dqi->dqi_maxblimit) ||
+	     di->d_spc_softlimit > dqi->dqi_max_spc_limit) ||
 	    ((di->d_fieldmask & QC_SPC_HARD) &&
-	     stoqb(di->d_spc_hardlimit) > dqi->dqi_maxblimit) ||
+	     di->d_spc_hardlimit > dqi->dqi_max_spc_limit) ||
 	    ((di->d_fieldmask & QC_INO_SOFT) &&
-	     (di->d_ino_softlimit > dqi->dqi_maxilimit)) ||
+	     (di->d_ino_softlimit > dqi->dqi_max_ino_limit)) ||
 	    ((di->d_fieldmask & QC_INO_HARD) &&
-	     (di->d_ino_hardlimit > dqi->dqi_maxilimit)))
+	     (di->d_ino_hardlimit > dqi->dqi_max_ino_limit)))
 		return -ERANGE;
 
 	spin_lock(&dq_data_lock);
@@ -2577,6 +2647,14 @@ int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii)
 		goto out;
 	}
 	mi = sb_dqopt(sb)->info + type;
+	if (ii->dqi_valid & IIF_FLAGS) {
+		if (ii->dqi_flags & ~DQF_SETINFO_MASK ||
+		    (ii->dqi_flags & DQF_ROOT_SQUASH &&
+		     mi->dqi_format->qf_fmt_id != QFMT_VFS_OLD)) {
+			err = -EINVAL;
+			goto out;
+		}
+	}
 	spin_lock(&dq_data_lock);
 	if (ii->dqi_valid & IIF_BGRACE)
 		mi->dqi_bgrace = ii->dqi_bgrace;
@@ -2606,6 +2684,17 @@ const struct quotactl_ops dquot_quotactl_ops = {
 };
 EXPORT_SYMBOL(dquot_quotactl_ops);
 
+const struct quotactl_ops dquot_quotactl_sysfile_ops = {
+	.quota_enable	= dquot_quota_enable,
+	.quota_disable	= dquot_quota_disable,
+	.quota_sync	= dquot_quota_sync,
+	.get_info	= dquot_get_dqinfo,
+	.set_info	= dquot_set_dqinfo,
+	.get_dqblk	= dquot_get_dqblk,
+	.set_dqblk	= dquot_set_dqblk
+};
+EXPORT_SYMBOL(dquot_quotactl_sysfile_ops);
+
 static int do_proc_dqstats(struct ctl_table *table, int write,
 		     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 6f3856328eea..d14a799c7785 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -66,18 +66,40 @@ static int quota_sync_all(int type)
 	return ret;
 }
 
+unsigned int qtype_enforce_flag(int type)
+{
+	switch (type) {
+	case USRQUOTA:
+		return FS_QUOTA_UDQ_ENFD;
+	case GRPQUOTA:
+		return FS_QUOTA_GDQ_ENFD;
+	case PRJQUOTA:
+		return FS_QUOTA_PDQ_ENFD;
+	}
+	return 0;
+}
+
 static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id,
 		         struct path *path)
 {
-	if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta)
+	if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable)
 		return -ENOSYS;
-	if (sb->s_qcop->quota_on_meta)
-		return sb->s_qcop->quota_on_meta(sb, type, id);
+	if (sb->s_qcop->quota_enable)
+		return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type));
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 	return sb->s_qcop->quota_on(sb, type, id, path);
 }
 
+static int quota_quotaoff(struct super_block *sb, int type)
+{
+	if (!sb->s_qcop->quota_off && !sb->s_qcop->quota_disable)
+		return -ENOSYS;
+	if (sb->s_qcop->quota_disable)
+		return sb->s_qcop->quota_disable(sb, qtype_enforce_flag(type));
+	return sb->s_qcop->quota_off(sb, type);
+}
+
 static int quota_getfmt(struct super_block *sb, int type, void __user *addr)
 {
 	__u32 fmt;
@@ -208,15 +230,26 @@ static int quota_setquota(struct super_block *sb, int type, qid_t id,
 	return sb->s_qcop->set_dqblk(sb, qid, &fdq);
 }
 
-static int quota_setxstate(struct super_block *sb, int cmd, void __user *addr)
+static int quota_enable(struct super_block *sb, void __user *addr)
 {
 	__u32 flags;
 
 	if (copy_from_user(&flags, addr, sizeof(flags)))
 		return -EFAULT;
-	if (!sb->s_qcop->set_xstate)
+	if (!sb->s_qcop->quota_enable)
 		return -ENOSYS;
-	return sb->s_qcop->set_xstate(sb, flags, cmd);
+	return sb->s_qcop->quota_enable(sb, flags);
+}
+
+static int quota_disable(struct super_block *sb, void __user *addr)
+{
+	__u32 flags;
+
+	if (copy_from_user(&flags, addr, sizeof(flags)))
+		return -EFAULT;
+	if (!sb->s_qcop->quota_disable)
+		return -ENOSYS;
+	return sb->s_qcop->quota_disable(sb, flags);
 }
 
 static int quota_getxstate(struct super_block *sb, void __user *addr)
@@ -429,9 +462,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 	case Q_QUOTAON:
 		return quota_quotaon(sb, type, cmd, id, path);
 	case Q_QUOTAOFF:
-		if (!sb->s_qcop->quota_off)
-			return -ENOSYS;
-		return sb->s_qcop->quota_off(sb, type);
+		return quota_quotaoff(sb, type);
 	case Q_GETFMT:
 		return quota_getfmt(sb, type, addr);
 	case Q_GETINFO:
@@ -447,8 +478,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 			return -ENOSYS;
 		return sb->s_qcop->quota_sync(sb, type);
 	case Q_XQUOTAON:
+		return quota_enable(sb, addr);
 	case Q_XQUOTAOFF:
-		return quota_setxstate(sb, cmd, addr);
+		return quota_disable(sb, addr);
 	case Q_XQUOTARM:
 		return quota_rmxquota(sb, addr);
 	case Q_XGETQSTAT:
diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c
index 469c6848b322..8fe79beced5c 100644
--- a/fs/quota/quota_v1.c
+++ b/fs/quota/quota_v1.c
@@ -169,8 +169,8 @@ static int v1_read_file_info(struct super_block *sb, int type)
 	}
 	ret = 0;
 	/* limits are stored as unsigned 32-bit data */
-	dqopt->info[type].dqi_maxblimit = 0xffffffff;
-	dqopt->info[type].dqi_maxilimit = 0xffffffff;
+	dqopt->info[type].dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS;
+	dqopt->info[type].dqi_max_ino_limit = 0xffffffff;
 	dqopt->info[type].dqi_igrace =
 			dqblk.dqb_itime ? dqblk.dqb_itime : MAX_IQ_TIME;
 	dqopt->info[type].dqi_bgrace =
diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c
index 02751ec695c5..9cb10d7197f7 100644
--- a/fs/quota/quota_v2.c
+++ b/fs/quota/quota_v2.c
@@ -117,16 +117,17 @@ static int v2_read_file_info(struct super_block *sb, int type)
 	qinfo = info->dqi_priv;
 	if (version == 0) {
 		/* limits are stored as unsigned 32-bit data */
-		info->dqi_maxblimit = 0xffffffff;
-		info->dqi_maxilimit = 0xffffffff;
+		info->dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS;
+		info->dqi_max_ino_limit = 0xffffffff;
 	} else {
-		/* used space is stored as unsigned 64-bit value */
-		info->dqi_maxblimit = 0xffffffffffffffffULL;	/* 2^64-1 */
-		info->dqi_maxilimit = 0xffffffffffffffffULL;
+		/* used space is stored as unsigned 64-bit value in bytes */
+		info->dqi_max_spc_limit = 0xffffffffffffffffULL; /* 2^64-1 */
+		info->dqi_max_ino_limit = 0xffffffffffffffffULL;
 	}
 	info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace);
 	info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace);
-	info->dqi_flags = le32_to_cpu(dinfo.dqi_flags);
+	/* No flags currently supported */
+	info->dqi_flags = 0;
 	qinfo->dqi_sb = sb;
 	qinfo->dqi_type = type;
 	qinfo->dqi_blocks = le32_to_cpu(dinfo.dqi_blocks);
@@ -157,7 +158,8 @@ static int v2_write_file_info(struct super_block *sb, int type)
 	info->dqi_flags &= ~DQF_INFO_DIRTY;
 	dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace);
 	dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace);
-	dinfo.dqi_flags = cpu_to_le32(info->dqi_flags & DQF_MASK);
+	/* No flags currently supported */
+	dinfo.dqi_flags = cpu_to_le32(0);
 	spin_unlock(&dq_data_lock);
 	dinfo.dqi_blocks = cpu_to_le32(qinfo->dqi_blocks);
 	dinfo.dqi_free_blk = cpu_to_le32(qinfo->dqi_free_blk);
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index bbafbde3471a..f6ab41b39612 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -34,7 +34,14 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
 						   unsigned long flags);
 static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma);
 
+static unsigned ramfs_mmap_capabilities(struct file *file)
+{
+	return NOMMU_MAP_DIRECT | NOMMU_MAP_COPY | NOMMU_MAP_READ |
+		NOMMU_MAP_WRITE | NOMMU_MAP_EXEC;
+}
+
 const struct file_operations ramfs_file_operations = {
+	.mmap_capabilities	= ramfs_mmap_capabilities,
 	.mmap			= ramfs_nommu_mmap,
 	.get_unmapped_area	= ramfs_nommu_get_unmapped_area,
 	.read			= new_sync_read,
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index d365b1c4eb3c..889d558b4e05 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -50,14 +50,6 @@ static const struct address_space_operations ramfs_aops = {
 	.set_page_dirty	= __set_page_dirty_no_writeback,
 };
 
-static struct backing_dev_info ramfs_backing_dev_info = {
-	.name		= "ramfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK |
-			  BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY |
-			  BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP,
-};
-
 struct inode *ramfs_get_inode(struct super_block *sb,
 				const struct inode *dir, umode_t mode, dev_t dev)
 {
@@ -67,7 +59,6 @@ struct inode *ramfs_get_inode(struct super_block *sb,
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_mapping->a_ops = &ramfs_aops;
-		inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
 		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
 		mapping_set_unevictable(inode->i_mapping);
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
@@ -267,19 +258,9 @@ static struct file_system_type ramfs_fs_type = {
 int __init init_ramfs_fs(void)
 {
 	static unsigned long once;
-	int err;
 
 	if (test_and_set_bit(0, &once))
 		return 0;
-
-	err = bdi_init(&ramfs_backing_dev_info);
-	if (err)
-		return err;
-
-	err = register_filesystem(&ramfs_fs_type);
-	if (err)
-		bdi_destroy(&ramfs_backing_dev_info);
-
-	return err;
+	return register_filesystem(&ramfs_fs_type);
 }
 fs_initcall(init_ramfs_fs);
diff --git a/fs/read_write.c b/fs/read_write.c
index c0805c93b6fa..8e1b68786d66 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -333,6 +333,52 @@ out_putf:
 }
 #endif
 
+ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos)
+{
+	struct kiocb kiocb;
+	ssize_t ret;
+
+	if (!file->f_op->read_iter)
+		return -EINVAL;
+
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = *ppos;
+	kiocb.ki_nbytes = iov_iter_count(iter);
+
+	iter->type |= READ;
+	ret = file->f_op->read_iter(&kiocb, iter);
+	if (ret == -EIOCBQUEUED)
+		ret = wait_on_sync_kiocb(&kiocb);
+
+	if (ret > 0)
+		*ppos = kiocb.ki_pos;
+	return ret;
+}
+EXPORT_SYMBOL(vfs_iter_read);
+
+ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
+{
+	struct kiocb kiocb;
+	ssize_t ret;
+
+	if (!file->f_op->write_iter)
+		return -EINVAL;
+
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = *ppos;
+	kiocb.ki_nbytes = iov_iter_count(iter);
+
+	iter->type |= WRITE;
+	ret = file->f_op->write_iter(&kiocb, iter);
+	if (ret == -EIOCBQUEUED)
+		ret = wait_on_sync_kiocb(&kiocb);
+
+	if (ret > 0)
+		*ppos = kiocb.ki_pos;
+	return ret;
+}
+EXPORT_SYMBOL(vfs_iter_write);
+
 /*
  * rw_verify_area doesn't like huge counts. We limit
  * them to something that fits in "int" so that others
@@ -358,7 +404,7 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
 			return retval;
 	}
 
-	if (unlikely(inode->i_flock && mandatory_lock(inode))) {
+	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
 		retval = locks_mandatory_area(
 			read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
 			inode, file, pos, count);
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index a7eec9888f10..e72401e1f995 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2766,7 +2766,7 @@ static int reiserfs_write_begin(struct file *file,
 	int old_ref = 0;
 
  	inode = mapping->host;
-	*fsdata = 0;
+	*fsdata = NULL;
  	if (flags & AOP_FLAG_CONT_EXPAND &&
  	    (pos & (inode->i_sb->s_blocksize - 1)) == 0) {
  		pos ++;
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 04b06146bae2..4e781e697c90 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -266,7 +266,7 @@ static int reiserfs_for_each_xattr(struct inode *inode,
 		for (i = 0; !err && i < buf.count && buf.dentries[i]; i++) {
 			struct dentry *dentry = buf.dentries[i];
 
-			if (!S_ISDIR(dentry->d_inode->i_mode))
+			if (!d_is_dir(dentry))
 				err = action(dentry, data);
 
 			dput(dentry);
@@ -322,7 +322,7 @@ static int delete_one_xattr(struct dentry *dentry, void *data)
 	struct inode *dir = dentry->d_parent->d_inode;
 
 	/* This is the xattr dir, handle specially. */
-	if (S_ISDIR(dentry->d_inode->i_mode))
+	if (d_is_dir(dentry))
 		return xattr_rmdir(dir, dentry);
 
 	return xattr_unlink(dir, dentry);
diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c
index ea06c7554860..7da9e2153953 100644
--- a/fs/romfs/mmap-nommu.c
+++ b/fs/romfs/mmap-nommu.c
@@ -70,6 +70,15 @@ static int romfs_mmap(struct file *file, struct vm_area_struct *vma)
 	return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS;
 }
 
+static unsigned romfs_mmap_capabilities(struct file *file)
+{
+	struct mtd_info *mtd = file_inode(file)->i_sb->s_mtd;
+
+	if (!mtd)
+		return NOMMU_MAP_COPY;
+	return mtd_mmap_capabilities(mtd);
+}
+
 const struct file_operations romfs_ro_fops = {
 	.llseek			= generic_file_llseek,
 	.read			= new_sync_read,
@@ -77,4 +86,5 @@ const struct file_operations romfs_ro_fops = {
 	.splice_read		= generic_file_splice_read,
 	.mmap			= romfs_mmap,
 	.get_unmapped_area	= romfs_get_unmapped_area,
+	.mmap_capabilities	= romfs_mmap_capabilities,
 };
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index e98dd88197d5..268733cda397 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -355,9 +355,6 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos)
 	case ROMFH_REG:
 		i->i_fop = &romfs_ro_fops;
 		i->i_data.a_ops = &romfs_aops;
-		if (i->i_sb->s_mtd)
-			i->i_data.backing_dev_info =
-				i->i_sb->s_mtd->backing_dev_info;
 		if (nextfh & ROMFH_EXEC)
 			mode |= S_IXUGO;
 		break;
diff --git a/fs/select.c b/fs/select.c
index 467bb1cb3ea5..f684c750e08a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -971,7 +971,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
 	if (ret == -EINTR) {
 		struct restart_block *restart_block;
 
-		restart_block = &current_thread_info()->restart_block;
+		restart_block = &current->restart_block;
 		restart_block->fn = do_restart_poll;
 		restart_block->poll.ufds = ufds;
 		restart_block->poll.nfds = nfds;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index dbf3a59c86bb..555f82155be8 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -539,38 +539,6 @@ int seq_dentry(struct seq_file *m, struct dentry *dentry, const char *esc)
 	return res;
 }
 
-int seq_bitmap(struct seq_file *m, const unsigned long *bits,
-				   unsigned int nr_bits)
-{
-	if (m->count < m->size) {
-		int len = bitmap_scnprintf(m->buf + m->count,
-				m->size - m->count, bits, nr_bits);
-		if (m->count + len < m->size) {
-			m->count += len;
-			return 0;
-		}
-	}
-	seq_set_overflow(m);
-	return -1;
-}
-EXPORT_SYMBOL(seq_bitmap);
-
-int seq_bitmap_list(struct seq_file *m, const unsigned long *bits,
-		unsigned int nr_bits)
-{
-	if (m->count < m->size) {
-		int len = bitmap_scnlistprintf(m->buf + m->count,
-				m->size - m->count, bits, nr_bits);
-		if (m->count + len < m->size) {
-			m->count += len;
-			return 0;
-		}
-	}
-	seq_set_overflow(m);
-	return -1;
-}
-EXPORT_SYMBOL(seq_bitmap_list);
-
 static void *single_start(struct seq_file *p, loff_t *pos)
 {
 	return NULL + (*pos == 0);
diff --git a/fs/splice.c b/fs/splice.c
index 75c6058eabf2..7968da96bebb 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -961,7 +961,6 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 	splice_from_pipe_begin(&sd);
 	while (sd.total_len) {
 		struct iov_iter from;
-		struct kiocb kiocb;
 		size_t left;
 		int n, idx;
 
@@ -1005,29 +1004,15 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 			left -= this_len;
 		}
 
-		/* ... iov_iter */
-		from.type = ITER_BVEC | WRITE;
-		from.bvec = array;
-		from.nr_segs = n;
-		from.count = sd.total_len - left;
-		from.iov_offset = 0;
-
-		/* ... and iocb */
-		init_sync_kiocb(&kiocb, out);
-		kiocb.ki_pos = sd.pos;
-		kiocb.ki_nbytes = sd.total_len - left;
-
-		/* now, send it */
-		ret = out->f_op->write_iter(&kiocb, &from);
-		if (-EIOCBQUEUED == ret)
-			ret = wait_on_sync_kiocb(&kiocb);
-
+		iov_iter_bvec(&from, ITER_BVEC | WRITE, array, n,
+			      sd.total_len - left);
+		ret = vfs_iter_write(out, &from, &sd.pos);
 		if (ret <= 0)
 			break;
 
 		sd.num_spliced += ret;
 		sd.total_len -= ret;
-		*ppos = sd.pos = kiocb.ki_pos;
+		*ppos = sd.pos;
 
 		/* dismiss the fully eaten buffers, adjust the partial one */
 		while (ret) {
diff --git a/fs/super.c b/fs/super.c
index eae088f6aaae..2b7dc90ccdbb 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -36,8 +36,8 @@
 #include "internal.h"
 
 
-LIST_HEAD(super_blocks);
-DEFINE_SPINLOCK(sb_lock);
+static LIST_HEAD(super_blocks);
+static DEFINE_SPINLOCK(sb_lock);
 
 static char *sb_writers_name[SB_FREEZE_LEVELS] = {
 	"sb_writers",
@@ -71,14 +71,14 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
 	if (!(sc->gfp_mask & __GFP_FS))
 		return SHRINK_STOP;
 
-	if (!grab_super_passive(sb))
+	if (!trylock_super(sb))
 		return SHRINK_STOP;
 
 	if (sb->s_op->nr_cached_objects)
-		fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid);
+		fs_objects = sb->s_op->nr_cached_objects(sb, sc);
 
-	inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
-	dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
+	inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);
+	dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc);
 	total_objects = dentries + inodes + fs_objects + 1;
 	if (!total_objects)
 		total_objects = 1;
@@ -86,22 +86,26 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
 	/* proportion the scan between the caches */
 	dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
 	inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
+	fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects);
 
 	/*
 	 * prune the dcache first as the icache is pinned by it, then
 	 * prune the icache, followed by the filesystem specific caches
+	 *
+	 * Ensure that we always scan at least one object - memcg kmem
+	 * accounting uses this to fully empty the caches.
 	 */
-	freed = prune_dcache_sb(sb, dentries, sc->nid);
-	freed += prune_icache_sb(sb, inodes, sc->nid);
+	sc->nr_to_scan = dentries + 1;
+	freed = prune_dcache_sb(sb, sc);
+	sc->nr_to_scan = inodes + 1;
+	freed += prune_icache_sb(sb, sc);
 
 	if (fs_objects) {
-		fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
-								total_objects);
-		freed += sb->s_op->free_cached_objects(sb, fs_objects,
-						       sc->nid);
+		sc->nr_to_scan = fs_objects + 1;
+		freed += sb->s_op->free_cached_objects(sb, sc);
 	}
 
-	drop_super(sb);
+	up_read(&sb->s_umount);
 	return freed;
 }
 
@@ -114,21 +118,18 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 	sb = container_of(shrink, struct super_block, s_shrink);
 
 	/*
-	 * Don't call grab_super_passive as it is a potential
+	 * 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_count_node() and
+	 * ensures the safety of call to list_lru_shrink_count() and
 	 * s_op->nr_cached_objects().
 	 */
 	if (sb->s_op && sb->s_op->nr_cached_objects)
-		total_objects = sb->s_op->nr_cached_objects(sb,
-						 sc->nid);
+		total_objects = sb->s_op->nr_cached_objects(sb, sc);
 
-	total_objects += list_lru_count_node(&sb->s_dentry_lru,
-						 sc->nid);
-	total_objects += list_lru_count_node(&sb->s_inode_lru,
-						 sc->nid);
+	total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
+	total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc);
 
 	total_objects = vfs_pressure_ratio(total_objects);
 	return total_objects;
@@ -185,15 +186,15 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	}
 	init_waitqueue_head(&s->s_writers.wait);
 	init_waitqueue_head(&s->s_writers.wait_unfrozen);
+	s->s_bdi = &noop_backing_dev_info;
 	s->s_flags = flags;
-	s->s_bdi = &default_backing_dev_info;
 	INIT_HLIST_NODE(&s->s_instances);
 	INIT_HLIST_BL_HEAD(&s->s_anon);
 	INIT_LIST_HEAD(&s->s_inodes);
 
-	if (list_lru_init(&s->s_dentry_lru))
+	if (list_lru_init_memcg(&s->s_dentry_lru))
 		goto fail;
-	if (list_lru_init(&s->s_inode_lru))
+	if (list_lru_init_memcg(&s->s_inode_lru))
 		goto fail;
 
 	init_rwsem(&s->s_umount);
@@ -229,7 +230,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	s->s_shrink.scan_objects = super_cache_scan;
 	s->s_shrink.count_objects = super_cache_count;
 	s->s_shrink.batch = 1024;
-	s->s_shrink.flags = SHRINKER_NUMA_AWARE;
+	s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
 	return s;
 
 fail:
@@ -284,6 +285,14 @@ void deactivate_locked_super(struct super_block *s)
 		unregister_shrinker(&s->s_shrink);
 		fs->kill_sb(s);
 
+		/*
+		 * Since list_lru_destroy() may sleep, we cannot call it from
+		 * put_super(), where we hold the sb_lock. Therefore we destroy
+		 * the lru lists right now.
+		 */
+		list_lru_destroy(&s->s_dentry_lru);
+		list_lru_destroy(&s->s_inode_lru);
+
 		put_filesystem(fs);
 		put_super(s);
 	} else {
@@ -339,35 +348,31 @@ static int grab_super(struct super_block *s) __releases(sb_lock)
 }
 
 /*
- *	grab_super_passive - acquire a passive reference
+ *	trylock_super - try to grab ->s_umount shared
  *	@sb: reference we are trying to grab
  *
- *	Tries to acquire a passive reference. This is used in places where we
+ *	Try to prevent fs shutdown.  This is used in places where we
  *	cannot take an active reference but we need to ensure that the
- *	superblock does not go away while we are working on it. It returns
- *	false if a reference was not gained, and returns true with the s_umount
- *	lock held in read mode if a reference is gained. On successful return,
- *	the caller must drop the s_umount lock and the passive reference when
- *	done.
+ *	filesystem is not shut down while we are working on it. It returns
+ *	false if we cannot acquire s_umount or if we lose the race and
+ *	filesystem already got into shutdown, and returns true with the s_umount
+ *	lock held in read mode in case of success. On successful return,
+ *	the caller must drop the s_umount lock when done.
+ *
+ *	Note that unlike get_super() et.al. this one does *not* bump ->s_count.
+ *	The reason why it's safe is that we are OK with doing trylock instead
+ *	of down_read().  There's a couple of places that are OK with that, but
+ *	it's very much not a general-purpose interface.
  */
-bool grab_super_passive(struct super_block *sb)
+bool trylock_super(struct super_block *sb)
 {
-	spin_lock(&sb_lock);
-	if (hlist_unhashed(&sb->s_instances)) {
-		spin_unlock(&sb_lock);
-		return false;
-	}
-
-	sb->s_count++;
-	spin_unlock(&sb_lock);
-
 	if (down_read_trylock(&sb->s_umount)) {
-		if (sb->s_root && (sb->s_flags & MS_BORN))
+		if (!hlist_unhashed(&sb->s_instances) &&
+		    sb->s_root && (sb->s_flags & MS_BORN))
 			return true;
 		up_read(&sb->s_umount);
 	}
 
-	put_super(sb);
 	return false;
 }
 
@@ -706,9 +711,9 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 	remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY);
 
 	if (remount_ro) {
-		if (sb->s_pins.first) {
+		if (!hlist_empty(&sb->s_pins)) {
 			up_write(&sb->s_umount);
-			sb_pin_kill(sb);
+			group_pin_kill(&sb->s_pins);
 			down_write(&sb->s_umount);
 			if (!sb->s_root)
 				return 0;
@@ -863,10 +868,7 @@ EXPORT_SYMBOL(free_anon_bdev);
 
 int set_anon_super(struct super_block *s, void *data)
 {
-	int error = get_anon_bdev(&s->s_dev);
-	if (!error)
-		s->s_bdi = &noop_backing_dev_info;
-	return error;
+	return get_anon_bdev(&s->s_dev);
 }
 
 EXPORT_SYMBOL(set_anon_super);
@@ -1111,7 +1113,6 @@ 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);
-	WARN_ON(sb->s_bdi == &default_backing_dev_info);
 	sb->s_flags |= MS_BORN;
 
 	error = security_sb_kern_mount(sb, flags, secdata);
diff --git a/fs/sync.c b/fs/sync.c
index 01d9f18a70b5..fbc98ee62044 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -177,8 +177,16 @@ SYSCALL_DEFINE1(syncfs, int, fd)
  */
 int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync)
 {
+	struct inode *inode = file->f_mapping->host;
+
 	if (!file->f_op->fsync)
 		return -EINVAL;
+	if (!datasync && (inode->i_state & I_DIRTY_TIME)) {
+		spin_lock(&inode->i_lock);
+		inode->i_state &= ~I_DIRTY_TIME;
+		spin_unlock(&inode->i_lock);
+		mark_inode_dirty_sync(inode);
+	}
 	return file->f_op->fsync(file, start, end, datasync);
 }
 EXPORT_SYMBOL(vfs_fsync_range);
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index dfe928a9540f..7c2867b44141 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -295,7 +295,7 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 		key = attr->key ?: (struct lock_class_key *)&attr->skey;
 #endif
 	kn = __kernfs_create_file(parent, attr->name, mode & 0777, size, ops,
-				  (void *)attr, ns, true, key);
+				  (void *)attr, ns, key);
 	if (IS_ERR(kn)) {
 		if (PTR_ERR(kn) == -EEXIST)
 			sysfs_warn_dup(parent, attr->name);
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 7d2a860ba788..2554d8835b48 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -99,7 +99,7 @@ static int internal_create_group(struct kobject *kobj, int update,
 		return -EINVAL;
 	if (!grp->attrs && !grp->bin_attrs) {
 		WARN(1, "sysfs: (bin_)attrs not set by subsystem for group: %s/%s\n",
-			kobj->name, grp->name ? "" : grp->name);
+			kobj->name, grp->name ?: "");
 		return -EINVAL;
 	}
 	if (grp->name) {
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 7ed13e1e216a..4cfb3e82c56f 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -2032,6 +2032,8 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr,
 		long long blk_offs;
 		struct ubifs_data_node *dn = node;
 
+		ubifs_assert(zbr->len >= UBIFS_DATA_NODE_SZ);
+
 		/*
 		 * Search the inode node this data node belongs to and insert
 		 * it to the RB-tree of inodes.
@@ -2060,6 +2062,8 @@ static int check_leaf(struct ubifs_info *c, struct ubifs_zbranch *zbr,
 		struct ubifs_dent_node *dent = node;
 		struct fsck_inode *fscki1;
 
+		ubifs_assert(zbr->len >= UBIFS_DENT_NODE_SZ);
+
 		err = ubifs_validate_entry(c, dent);
 		if (err)
 			goto out_dump;
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index ea41649e4ca5..0fa6c803992e 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -108,8 +108,6 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir,
 	inode->i_mtime = inode->i_atime = inode->i_ctime =
 			 ubifs_current_time(inode);
 	inode->i_mapping->nrpages = 0;
-	/* Disable readahead */
-	inode->i_mapping->backing_dev_info = &c->bdi;
 
 	switch (mode & S_IFMT) {
 	case S_IFREG:
@@ -272,6 +270,10 @@ static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		goto out_budg;
 	}
 
+	err = ubifs_init_security(dir, inode, &dentry->d_name);
+	if (err)
+		goto out_cancel;
+
 	mutex_lock(&dir_ui->ui_mutex);
 	dir->i_size += sz_change;
 	dir_ui->ui_size = dir->i_size;
@@ -728,6 +730,10 @@ static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		goto out_budg;
 	}
 
+	err = ubifs_init_security(dir, inode, &dentry->d_name);
+	if (err)
+		goto out_cancel;
+
 	mutex_lock(&dir_ui->ui_mutex);
 	insert_inode_hash(inode);
 	inc_nlink(inode);
@@ -808,6 +814,10 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry,
 	ui->data = dev;
 	ui->data_len = devlen;
 
+	err = ubifs_init_security(dir, inode, &dentry->d_name);
+	if (err)
+		goto out_cancel;
+
 	mutex_lock(&dir_ui->ui_mutex);
 	dir->i_size += sz_change;
 	dir_ui->ui_size = dir->i_size;
@@ -884,6 +894,10 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry,
 	ui->data_len = len;
 	inode->i_size = ubifs_inode(inode)->ui_size = len;
 
+	err = ubifs_init_security(dir, inode, &dentry->d_name);
+	if (err)
+		goto out_cancel;
+
 	mutex_lock(&dir_ui->ui_mutex);
 	dir->i_size += sz_change;
 	dir_ui->ui_size = dir->i_size;
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 538519ee37d9..e627c0acf626 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1536,7 +1536,6 @@ static const struct vm_operations_struct ubifs_file_vm_ops = {
 	.fault        = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = ubifs_vm_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma)
@@ -1574,6 +1573,10 @@ const struct inode_operations ubifs_symlink_inode_operations = {
 	.follow_link = ubifs_follow_link,
 	.setattr     = ubifs_setattr,
 	.getattr     = ubifs_getattr,
+	.setxattr    = ubifs_setxattr,
+	.getxattr    = ubifs_getxattr,
+	.listxattr   = ubifs_listxattr,
+	.removexattr = ubifs_removexattr,
 };
 
 const struct file_operations ubifs_file_operations = {
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index 3187925e9879..9b40a1c5e160 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -1028,9 +1028,22 @@ int ubifs_replay_journal(struct ubifs_info *c)
 
 	do {
 		err = replay_log_leb(c, lnum, 0, c->sbuf);
-		if (err == 1)
-			/* We hit the end of the log */
-			break;
+		if (err == 1) {
+			if (lnum != c->lhead_lnum)
+				/* We hit the end of the log */
+				break;
+
+			/*
+			 * The head of the log must always start with the
+			 * "commit start" node on a properly formatted UBIFS.
+			 * But we found no nodes at all, which means that
+			 * someting went wrong and we cannot proceed mounting
+			 * the file-system.
+			 */
+			ubifs_err("no UBIFS nodes found at the log head LEB %d:%d, possibly corrupted",
+				  lnum, 0);
+			err = -EINVAL;
+		}
 		if (err)
 			goto out;
 		lnum = ubifs_next_log_lnum(c, lnum);
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 106bf20629ce..93e946561c5c 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -156,9 +156,6 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
 	if (err)
 		goto out_invalid;
 
-	/* Disable read-ahead */
-	inode->i_mapping->backing_dev_info = &c->bdi;
-
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_mapping->a_ops = &ubifs_file_address_operations;
@@ -2017,7 +2014,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	 * Read-ahead will be disabled because @c->bdi.ra_pages is 0.
 	 */
 	c->bdi.name = "ubifs",
-	c->bdi.capabilities = BDI_CAP_MAP_COPY;
+	c->bdi.capabilities = 0;
 	err  = bdi_init(&c->bdi);
 	if (err)
 		goto out_close;
@@ -2039,6 +2036,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	if (c->max_inode_sz > MAX_LFS_FILESIZE)
 		sb->s_maxbytes = c->max_inode_sz = MAX_LFS_FILESIZE;
 	sb->s_op = &ubifs_super_operations;
+	sb->s_xattr = ubifs_xattr_handlers;
 
 	mutex_lock(&c->umount_mutex);
 	err = mount_ubifs(c);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index c4fe900c67ab..bc04b9c69891 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -36,6 +36,7 @@
 #include <linux/mtd/ubi.h>
 #include <linux/pagemap.h>
 #include <linux/backing-dev.h>
+#include <linux/security.h>
 #include "ubifs-media.h"
 
 /* Version of this UBIFS implementation */
@@ -1465,6 +1466,7 @@ extern spinlock_t ubifs_infos_lock;
 extern atomic_long_t ubifs_clean_zn_cnt;
 extern struct kmem_cache *ubifs_inode_slab;
 extern const struct super_operations ubifs_super_operations;
+extern const struct xattr_handler *ubifs_xattr_handlers[];
 extern const struct address_space_operations ubifs_file_address_operations;
 extern const struct file_operations ubifs_file_operations;
 extern const struct inode_operations ubifs_file_inode_operations;
@@ -1754,6 +1756,8 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf,
 		       size_t size);
 ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size);
 int ubifs_removexattr(struct dentry *dentry, const char *name);
+int ubifs_init_security(struct inode *dentry, struct inode *inode,
+			const struct qstr *qstr);
 
 /* super.c */
 struct inode *ubifs_iget(struct super_block *sb, unsigned long inum);
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 5e0a63b1b0d5..a92be244a6fb 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -100,24 +100,30 @@ static const struct file_operations empty_fops;
 static int create_xattr(struct ubifs_info *c, struct inode *host,
 			const struct qstr *nm, const void *value, int size)
 {
-	int err;
+	int err, names_len;
 	struct inode *inode;
 	struct ubifs_inode *ui, *host_ui = ubifs_inode(host);
 	struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1,
 				.new_ino_d = ALIGN(size, 8), .dirtied_ino = 1,
 				.dirtied_ino_d = ALIGN(host_ui->data_len, 8) };
 
-	if (host_ui->xattr_cnt >= MAX_XATTRS_PER_INODE)
+	if (host_ui->xattr_cnt >= MAX_XATTRS_PER_INODE) {
+		ubifs_err("inode %lu already has too many xattrs (%d), cannot create more",
+			  host->i_ino, host_ui->xattr_cnt);
 		return -ENOSPC;
+	}
 	/*
 	 * Linux limits the maximum size of the extended attribute names list
 	 * to %XATTR_LIST_MAX. This means we should not allow creating more
 	 * extended attributes if the name list becomes larger. This limitation
 	 * is artificial for UBIFS, though.
 	 */
-	if (host_ui->xattr_names + host_ui->xattr_cnt +
-					nm->len + 1 > XATTR_LIST_MAX)
+	names_len = host_ui->xattr_names + host_ui->xattr_cnt + nm->len + 1;
+	if (names_len > XATTR_LIST_MAX) {
+		ubifs_err("cannot add one more xattr name to inode %lu, total names length would become %d, max. is %d",
+			  host->i_ino, names_len, XATTR_LIST_MAX);
 		return -ENOSPC;
+	}
 
 	err = ubifs_budget_space(c, &req);
 	if (err)
@@ -293,18 +299,16 @@ static struct inode *iget_xattr(struct ubifs_info *c, ino_t inum)
 	return ERR_PTR(-EINVAL);
 }
 
-int ubifs_setxattr(struct dentry *dentry, const char *name,
-		   const void *value, size_t size, int flags)
+static int setxattr(struct inode *host, const char *name, const void *value,
+		    size_t size, int flags)
 {
-	struct inode *inode, *host = dentry->d_inode;
+	struct inode *inode;
 	struct ubifs_info *c = host->i_sb->s_fs_info;
 	struct qstr nm = QSTR_INIT(name, strlen(name));
 	struct ubifs_dent_node *xent;
 	union ubifs_key key;
 	int err, type;
 
-	dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd", name,
-		host->i_ino, dentry, size);
 	ubifs_assert(mutex_is_locked(&host->i_mutex));
 
 	if (size > UBIFS_MAX_INO_DATA)
@@ -356,6 +360,15 @@ out_free:
 	return err;
 }
 
+int ubifs_setxattr(struct dentry *dentry, const char *name,
+		   const void *value, size_t size, int flags)
+{
+	dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd",
+		name, dentry->d_inode->i_ino, dentry, size);
+
+	return setxattr(dentry->d_inode, name, value, size, flags);
+}
+
 ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf,
 		       size_t size)
 {
@@ -568,3 +581,84 @@ out_free:
 	kfree(xent);
 	return err;
 }
+
+static size_t security_listxattr(struct dentry *d, char *list, size_t list_size,
+				 const char *name, size_t name_len, int flags)
+{
+	const int prefix_len = XATTR_SECURITY_PREFIX_LEN;
+	const size_t total_len = prefix_len + name_len + 1;
+
+	if (list && total_len <= list_size) {
+		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
+		memcpy(list + prefix_len, name, name_len);
+		list[prefix_len + name_len] = '\0';
+	}
+
+	return total_len;
+}
+
+static int security_getxattr(struct dentry *d, const char *name, void *buffer,
+		      size_t size, int flags)
+{
+	return ubifs_getxattr(d, name, buffer, size);
+}
+
+static int security_setxattr(struct dentry *d, const char *name,
+			     const void *value, size_t size, int flags,
+			     int handler_flags)
+{
+	return ubifs_setxattr(d, name, value, size, flags);
+}
+
+static const struct xattr_handler ubifs_xattr_security_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.list   = security_listxattr,
+	.get    = security_getxattr,
+	.set    = security_setxattr,
+};
+
+const struct xattr_handler *ubifs_xattr_handlers[] = {
+	&ubifs_xattr_security_handler,
+	NULL,
+};
+
+static int init_xattrs(struct inode *inode, const struct xattr *xattr_array,
+		      void *fs_info)
+{
+	const struct xattr *xattr;
+	char *name;
+	int err = 0;
+
+	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+		name = kmalloc(XATTR_SECURITY_PREFIX_LEN +
+			       strlen(xattr->name) + 1, GFP_NOFS);
+		if (!name) {
+			err = -ENOMEM;
+			break;
+		}
+		strcpy(name, XATTR_SECURITY_PREFIX);
+		strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name);
+		err = setxattr(inode, name, xattr->value, xattr->value_len, 0);
+		kfree(name);
+		if (err < 0)
+			break;
+	}
+
+	return err;
+}
+
+int ubifs_init_security(struct inode *dentry, struct inode *inode,
+			const struct qstr *qstr)
+{
+	int err;
+
+	mutex_lock(&inode->i_mutex);
+	err = security_inode_init_security(inode, dentry, qstr,
+					   &init_xattrs, 0);
+	mutex_unlock(&inode->i_mutex);
+
+	if (err)
+		ubifs_err("cannot initialize security for inode %lu, error %d",
+			  inode->i_ino, err);
+	return err;
+}
diff --git a/fs/udf/Kconfig b/fs/udf/Kconfig
index 0e0e99bd6bce..c6e17a744c3b 100644
--- a/fs/udf/Kconfig
+++ b/fs/udf/Kconfig
@@ -2,10 +2,12 @@ config UDF_FS
 	tristate "UDF file system support"
 	select CRC_ITU_T
 	help
-	  This is the new file system used on some CD-ROMs and DVDs. Say Y if
-	  you intend to mount DVD discs or CDRW's written in packet mode, or
-	  if written to by other UDF utilities, such as DirectCD.
-	  Please read <file:Documentation/filesystems/udf.txt>.
+	  This is a file system used on some CD-ROMs and DVDs. Since the
+	  file system is supported by multiple operating systems and is more
+	  compatible with standard unix file systems, it is also suitable for
+	  removable USB disks. Say Y if you intend to mount DVD discs or CDRW's
+	  written in packet mode, or if you want to use UDF for removable USB
+	  disks. Please read <file:Documentation/filesystems/udf.txt>.
 
 	  To compile this file system support as a module, choose M here: the
 	  module will be called udf.
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 5bc71d9a674a..a445d599098d 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -750,7 +750,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 	/* Are we beyond EOF? */
 	if (etype == -1) {
 		int ret;
-		isBeyondEOF = 1;
+		isBeyondEOF = true;
 		if (count) {
 			if (c)
 				laarr[0] = laarr[1];
@@ -792,7 +792,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 		endnum = c + 1;
 		lastblock = 1;
 	} else {
-		isBeyondEOF = 0;
+		isBeyondEOF = false;
 		endnum = startnum = ((count > 2) ? 2 : count);
 
 		/* if the current extent is in position 0,
@@ -1288,6 +1288,7 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode)
 	struct kernel_lb_addr *iloc = &iinfo->i_location;
 	unsigned int link_count;
 	unsigned int indirections = 0;
+	int bs = inode->i_sb->s_blocksize;
 	int ret = -EIO;
 
 reread:
@@ -1374,38 +1375,35 @@ reread:
 	if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_EFE)) {
 		iinfo->i_efe = 1;
 		iinfo->i_use = 0;
-		ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize -
+		ret = udf_alloc_i_data(inode, bs -
 					sizeof(struct extendedFileEntry));
 		if (ret)
 			goto out;
 		memcpy(iinfo->i_ext.i_data,
 		       bh->b_data + sizeof(struct extendedFileEntry),
-		       inode->i_sb->s_blocksize -
-					sizeof(struct extendedFileEntry));
+		       bs - sizeof(struct extendedFileEntry));
 	} else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_FE)) {
 		iinfo->i_efe = 0;
 		iinfo->i_use = 0;
-		ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize -
-						sizeof(struct fileEntry));
+		ret = udf_alloc_i_data(inode, bs - sizeof(struct fileEntry));
 		if (ret)
 			goto out;
 		memcpy(iinfo->i_ext.i_data,
 		       bh->b_data + sizeof(struct fileEntry),
-		       inode->i_sb->s_blocksize - sizeof(struct fileEntry));
+		       bs - sizeof(struct fileEntry));
 	} else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_USE)) {
 		iinfo->i_efe = 0;
 		iinfo->i_use = 1;
 		iinfo->i_lenAlloc = le32_to_cpu(
 				((struct unallocSpaceEntry *)bh->b_data)->
 				 lengthAllocDescs);
-		ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize -
+		ret = udf_alloc_i_data(inode, bs -
 					sizeof(struct unallocSpaceEntry));
 		if (ret)
 			goto out;
 		memcpy(iinfo->i_ext.i_data,
 		       bh->b_data + sizeof(struct unallocSpaceEntry),
-		       inode->i_sb->s_blocksize -
-					sizeof(struct unallocSpaceEntry));
+		       bs - sizeof(struct unallocSpaceEntry));
 		return 0;
 	}
 
@@ -1489,6 +1487,15 @@ reread:
 	}
 	inode->i_generation = iinfo->i_unique;
 
+	/*
+	 * Sanity check length of allocation descriptors and extended attrs to
+	 * avoid integer overflows
+	 */
+	if (iinfo->i_lenEAttr > bs || iinfo->i_lenAlloc > bs)
+		goto out;
+	/* Now do exact checks */
+	if (udf_file_entry_alloc_offset(inode) + iinfo->i_lenAlloc > bs)
+		goto out;
 	/* Sanity checks for files in ICB so that we don't get confused later */
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
 		/*
@@ -1498,8 +1505,7 @@ reread:
 		if (iinfo->i_lenAlloc != inode->i_size)
 			goto out;
 		/* File in ICB has to fit in there... */
-		if (inode->i_size > inode->i_sb->s_blocksize -
-					udf_file_entry_alloc_offset(inode))
+		if (inode->i_size > bs - udf_file_entry_alloc_offset(inode))
 			goto out;
 	}
 
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 3ccb2f11fc76..f169411c4ea0 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -1599,7 +1599,7 @@ static noinline int udf_process_sequence(
 	struct udf_vds_record *curr;
 	struct generic_desc *gd;
 	struct volDescPtr *vdp;
-	int done = 0;
+	bool done = false;
 	uint32_t vdsn;
 	uint16_t ident;
 	long next_s = 0, next_e = 0;
@@ -1680,7 +1680,7 @@ static noinline int udf_process_sequence(
 				lastblock = next_e;
 				next_s = next_e = 0;
 			} else
-				done = 1;
+				done = true;
 			break;
 		}
 		brelse(bh);
@@ -2300,6 +2300,7 @@ static void udf_put_super(struct super_block *sb)
 		udf_close_lvid(sb);
 	brelse(sbi->s_lvid_bh);
 	udf_sb_free_partitions(sb);
+	mutex_destroy(&sbi->s_alloc_mutex);
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;
 }
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index da73801301d5..8092d3759a5e 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -95,22 +95,18 @@
 
 void lock_ufs(struct super_block *sb)
 {
-#if defined(CONFIG_SMP) || defined (CONFIG_PREEMPT)
 	struct ufs_sb_info *sbi = UFS_SB(sb);
 
 	mutex_lock(&sbi->mutex);
 	sbi->mutex_owner = current;
-#endif
 }
 
 void unlock_ufs(struct super_block *sb)
 {
-#if defined(CONFIG_SMP) || defined (CONFIG_PREEMPT)
 	struct ufs_sb_info *sbi = UFS_SB(sb);
 
 	sbi->mutex_owner = NULL;
 	mutex_unlock(&sbi->mutex);
-#endif
 }
 
 static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation)
@@ -1415,9 +1411,11 @@ static struct kmem_cache * ufs_inode_cachep;
 static struct inode *ufs_alloc_inode(struct super_block *sb)
 {
 	struct ufs_inode_info *ei;
-	ei = (struct ufs_inode_info *)kmem_cache_alloc(ufs_inode_cachep, GFP_NOFS);
+
+	ei = kmem_cache_alloc(ufs_inode_cachep, GFP_NOFS);
 	if (!ei)
 		return NULL;
+
 	ei->vfs_inode.i_version = 1;
 	return &ei->vfs_inode;
 }
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index d61799949580..df6828570e87 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -121,3 +121,4 @@ xfs-$(CONFIG_XFS_POSIX_ACL)	+= xfs_acl.o
 xfs-$(CONFIG_PROC_FS)		+= xfs_stats.o
 xfs-$(CONFIG_SYSCTL)		+= xfs_sysctl.o
 xfs-$(CONFIG_COMPAT)		+= xfs_ioctl32.o
+xfs-$(CONFIG_NFSD_PNFS)		+= xfs_pnfs.o
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 53e95b2a1369..a7a3a63bb360 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -91,16 +91,6 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
 	return ptr;
 }
 
-void
-kmem_free(const void *ptr)
-{
-	if (!is_vmalloc_addr(ptr)) {
-		kfree(ptr);
-	} else {
-		vfree(ptr);
-	}
-}
-
 void *
 kmem_realloc(const void *ptr, size_t newsize, size_t oldsize,
 	     xfs_km_flags_t flags)
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index 64db0e53edea..cc6b768fc068 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -63,7 +63,10 @@ kmem_flags_convert(xfs_km_flags_t flags)
 extern void *kmem_alloc(size_t, xfs_km_flags_t);
 extern void *kmem_zalloc_large(size_t size, xfs_km_flags_t);
 extern void *kmem_realloc(const void *, size_t, size_t, xfs_km_flags_t);
-extern void  kmem_free(const void *);
+static inline void  kmem_free(const void *ptr)
+{
+	kvfree(ptr);
+}
 
 
 extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 5d38e8b8a913..15105dbc9e28 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -403,7 +403,7 @@ xfs_sbversion_add_attr2(xfs_mount_t *mp, xfs_trans_t *tp)
 		if (!xfs_sb_version_hasattr2(&mp->m_sb)) {
 			xfs_sb_version_addattr2(&mp->m_sb);
 			spin_unlock(&mp->m_sb_lock);
-			xfs_mod_sb(tp, XFS_SB_VERSIONNUM | XFS_SB_FEATURES2);
+			xfs_log_sb(tp);
 		} else
 			spin_unlock(&mp->m_sb_lock);
 	}
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index b5eb4743f75a..61ec015dca16 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -973,7 +973,11 @@ xfs_bmap_local_to_extents(
 	*firstblock = args.fsbno;
 	bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);
 
-	/* initialise the block and copy the data */
+	/*
+	 * Initialise the block and copy the data
+	 *
+	 * Note: init_fn must set the buffer log item type correctly!
+	 */
 	init_fn(tp, bp, ip, ifp);
 
 	/* account for the change in fork size and log everything */
@@ -1221,22 +1225,20 @@ xfs_bmap_add_attrfork(
 		goto bmap_cancel;
 	if (!xfs_sb_version_hasattr(&mp->m_sb) ||
 	   (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) {
-		__int64_t sbfields = 0;
+		bool log_sb = false;
 
 		spin_lock(&mp->m_sb_lock);
 		if (!xfs_sb_version_hasattr(&mp->m_sb)) {
 			xfs_sb_version_addattr(&mp->m_sb);
-			sbfields |= XFS_SB_VERSIONNUM;
+			log_sb = true;
 		}
 		if (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2) {
 			xfs_sb_version_addattr2(&mp->m_sb);
-			sbfields |= (XFS_SB_VERSIONNUM | XFS_SB_FEATURES2);
+			log_sb = true;
 		}
-		if (sbfields) {
-			spin_unlock(&mp->m_sb_lock);
-			xfs_mod_sb(tp, sbfields);
-		} else
-			spin_unlock(&mp->m_sb_lock);
+		spin_unlock(&mp->m_sb_lock);
+		if (log_sb)
+			xfs_log_sb(tp);
 	}
 
 	error = xfs_bmap_finish(&tp, &flist, &committed);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 44db6db86402..b9d8a499d2c4 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -28,6 +28,37 @@ struct xfs_trans;
 extern kmem_zone_t	*xfs_bmap_free_item_zone;
 
 /*
+ * Argument structure for xfs_bmap_alloc.
+ */
+struct xfs_bmalloca {
+	xfs_fsblock_t		*firstblock; /* i/o first block allocated */
+	struct xfs_bmap_free	*flist;	/* bmap freelist */
+	struct xfs_trans	*tp;	/* transaction pointer */
+	struct xfs_inode	*ip;	/* incore inode pointer */
+	struct xfs_bmbt_irec	prev;	/* extent before the new one */
+	struct xfs_bmbt_irec	got;	/* extent after, or delayed */
+
+	xfs_fileoff_t		offset;	/* offset in file filling in */
+	xfs_extlen_t		length;	/* i/o length asked/allocated */
+	xfs_fsblock_t		blkno;	/* starting block of new extent */
+
+	struct xfs_btree_cur	*cur;	/* btree cursor */
+	xfs_extnum_t		idx;	/* current extent index */
+	int			nallocs;/* number of extents alloc'd */
+	int			logflags;/* flags for transaction logging */
+
+	xfs_extlen_t		total;	/* total blocks needed for xaction */
+	xfs_extlen_t		minlen;	/* minimum allocation size (blocks) */
+	xfs_extlen_t		minleft; /* amount must be left after alloc */
+	bool			eof;	/* set if allocating past last extent */
+	bool			wasdel;	/* replacing a delayed allocation */
+	bool			userdata;/* set if is user data */
+	bool			aeof;	/* allocated space at eof */
+	bool			conv;	/* overwriting unwritten extents */
+	int			flags;
+};
+
+/*
  * List of extents to be free "later".
  * The list is kept sorted on xbf_startblock.
  */
@@ -149,6 +180,8 @@ void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
 void	xfs_bmap_add_free(xfs_fsblock_t bno, xfs_filblks_t len,
 		struct xfs_bmap_free *flist, struct xfs_mount *mp);
 void	xfs_bmap_cancel(struct xfs_bmap_free *flist);
+int	xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
+			int *committed);
 void	xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
 int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index fbd6da263571..8eb718979383 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -151,10 +151,13 @@ typedef struct xfs_sb {
 	__uint32_t	sb_features2;	/* additional feature bits */
 
 	/*
-	 * bad features2 field as a result of failing to pad the sb
-	 * structure to 64 bits. Some machines will be using this field
-	 * for features2 bits. Easiest just to mark it bad and not use
-	 * it for anything else.
+	 * bad features2 field as a result of failing to pad the sb structure to
+	 * 64 bits. Some machines will be using this field for features2 bits.
+	 * Easiest just to mark it bad and not use it for anything else.
+	 *
+	 * This is not kept up to date in memory; it is always overwritten by
+	 * the value in sb_features2 when formatting the incore superblock to
+	 * the disk buffer.
 	 */
 	__uint32_t	sb_bad_features2;
 
@@ -304,8 +307,8 @@ typedef enum {
 #define XFS_SB_ICOUNT		XFS_SB_MVAL(ICOUNT)
 #define XFS_SB_IFREE		XFS_SB_MVAL(IFREE)
 #define XFS_SB_FDBLOCKS		XFS_SB_MVAL(FDBLOCKS)
-#define XFS_SB_FEATURES2	XFS_SB_MVAL(FEATURES2)
-#define XFS_SB_BAD_FEATURES2	XFS_SB_MVAL(BAD_FEATURES2)
+#define XFS_SB_FEATURES2	(XFS_SB_MVAL(FEATURES2) | \
+				 XFS_SB_MVAL(BAD_FEATURES2))
 #define XFS_SB_FEATURES_COMPAT	XFS_SB_MVAL(FEATURES_COMPAT)
 #define XFS_SB_FEATURES_RO_COMPAT XFS_SB_MVAL(FEATURES_RO_COMPAT)
 #define XFS_SB_FEATURES_INCOMPAT XFS_SB_MVAL(FEATURES_INCOMPAT)
@@ -319,9 +322,9 @@ typedef enum {
 	 XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | XFS_SB_GQUOTINO | \
 	 XFS_SB_QFLAGS | XFS_SB_SHARED_VN | XFS_SB_UNIT | XFS_SB_WIDTH | \
 	 XFS_SB_ICOUNT | XFS_SB_IFREE | XFS_SB_FDBLOCKS | XFS_SB_FEATURES2 | \
-	 XFS_SB_BAD_FEATURES2 | XFS_SB_FEATURES_COMPAT | \
-	 XFS_SB_FEATURES_RO_COMPAT | XFS_SB_FEATURES_INCOMPAT | \
-	 XFS_SB_FEATURES_LOG_INCOMPAT | XFS_SB_PQUOTINO)
+	 XFS_SB_FEATURES_COMPAT | XFS_SB_FEATURES_RO_COMPAT | \
+	 XFS_SB_FEATURES_INCOMPAT | XFS_SB_FEATURES_LOG_INCOMPAT | \
+	 XFS_SB_PQUOTINO)
 
 
 /*
@@ -453,13 +456,11 @@ static inline void xfs_sb_version_addattr2(struct xfs_sb *sbp)
 {
 	sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT;
 	sbp->sb_features2 |= XFS_SB_VERSION2_ATTR2BIT;
-	sbp->sb_bad_features2 |= XFS_SB_VERSION2_ATTR2BIT;
 }
 
 static inline void xfs_sb_version_removeattr2(struct xfs_sb *sbp)
 {
 	sbp->sb_features2 &= ~XFS_SB_VERSION2_ATTR2BIT;
-	sbp->sb_bad_features2 &= ~XFS_SB_VERSION2_ATTR2BIT;
 	if (!sbp->sb_features2)
 		sbp->sb_versionnum &= ~XFS_SB_VERSION_MOREBITSBIT;
 }
@@ -475,7 +476,6 @@ static inline void xfs_sb_version_addprojid32bit(struct xfs_sb *sbp)
 {
 	sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT;
 	sbp->sb_features2 |= XFS_SB_VERSION2_PROJID32BIT;
-	sbp->sb_bad_features2 |= XFS_SB_VERSION2_PROJID32BIT;
 }
 
 /*
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 18dc721ca19f..18dc721ca19f 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 752915fa775a..b0a5fe95a3e2 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -40,69 +40,6 @@
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
  */
 
-static const struct {
-	short offset;
-	short type;	/* 0 = integer
-			 * 1 = binary / string (no translation)
-			 */
-} xfs_sb_info[] = {
-	{ offsetof(xfs_sb_t, sb_magicnum),	0 },
-	{ offsetof(xfs_sb_t, sb_blocksize),	0 },
-	{ offsetof(xfs_sb_t, sb_dblocks),	0 },
-	{ offsetof(xfs_sb_t, sb_rblocks),	0 },
-	{ offsetof(xfs_sb_t, sb_rextents),	0 },
-	{ offsetof(xfs_sb_t, sb_uuid),		1 },
-	{ offsetof(xfs_sb_t, sb_logstart),	0 },
-	{ offsetof(xfs_sb_t, sb_rootino),	0 },
-	{ offsetof(xfs_sb_t, sb_rbmino),	0 },
-	{ offsetof(xfs_sb_t, sb_rsumino),	0 },
-	{ offsetof(xfs_sb_t, sb_rextsize),	0 },
-	{ offsetof(xfs_sb_t, sb_agblocks),	0 },
-	{ offsetof(xfs_sb_t, sb_agcount),	0 },
-	{ offsetof(xfs_sb_t, sb_rbmblocks),	0 },
-	{ offsetof(xfs_sb_t, sb_logblocks),	0 },
-	{ offsetof(xfs_sb_t, sb_versionnum),	0 },
-	{ offsetof(xfs_sb_t, sb_sectsize),	0 },
-	{ offsetof(xfs_sb_t, sb_inodesize),	0 },
-	{ offsetof(xfs_sb_t, sb_inopblock),	0 },
-	{ offsetof(xfs_sb_t, sb_fname[0]),	1 },
-	{ offsetof(xfs_sb_t, sb_blocklog),	0 },
-	{ offsetof(xfs_sb_t, sb_sectlog),	0 },
-	{ offsetof(xfs_sb_t, sb_inodelog),	0 },
-	{ offsetof(xfs_sb_t, sb_inopblog),	0 },
-	{ offsetof(xfs_sb_t, sb_agblklog),	0 },
-	{ offsetof(xfs_sb_t, sb_rextslog),	0 },
-	{ offsetof(xfs_sb_t, sb_inprogress),	0 },
-	{ offsetof(xfs_sb_t, sb_imax_pct),	0 },
-	{ offsetof(xfs_sb_t, sb_icount),	0 },
-	{ offsetof(xfs_sb_t, sb_ifree),		0 },
-	{ offsetof(xfs_sb_t, sb_fdblocks),	0 },
-	{ offsetof(xfs_sb_t, sb_frextents),	0 },
-	{ offsetof(xfs_sb_t, sb_uquotino),	0 },
-	{ offsetof(xfs_sb_t, sb_gquotino),	0 },
-	{ offsetof(xfs_sb_t, sb_qflags),	0 },
-	{ offsetof(xfs_sb_t, sb_flags),		0 },
-	{ offsetof(xfs_sb_t, sb_shared_vn),	0 },
-	{ offsetof(xfs_sb_t, sb_inoalignmt),	0 },
-	{ offsetof(xfs_sb_t, sb_unit),		0 },
-	{ offsetof(xfs_sb_t, sb_width),		0 },
-	{ offsetof(xfs_sb_t, sb_dirblklog),	0 },
-	{ offsetof(xfs_sb_t, sb_logsectlog),	0 },
-	{ offsetof(xfs_sb_t, sb_logsectsize),	0 },
-	{ offsetof(xfs_sb_t, sb_logsunit),	0 },
-	{ offsetof(xfs_sb_t, sb_features2),	0 },
-	{ offsetof(xfs_sb_t, sb_bad_features2),	0 },
-	{ offsetof(xfs_sb_t, sb_features_compat),	0 },
-	{ offsetof(xfs_sb_t, sb_features_ro_compat),	0 },
-	{ offsetof(xfs_sb_t, sb_features_incompat),	0 },
-	{ offsetof(xfs_sb_t, sb_features_log_incompat),	0 },
-	{ offsetof(xfs_sb_t, sb_crc),		0 },
-	{ offsetof(xfs_sb_t, sb_pad),		0 },
-	{ offsetof(xfs_sb_t, sb_pquotino),	0 },
-	{ offsetof(xfs_sb_t, sb_lsn),		0 },
-	{ sizeof(xfs_sb_t),			0 }
-};
-
 /*
  * Reference counting access wrappers to the perag structures.
  * Because we never free per-ag structures, the only thing we
@@ -461,58 +398,49 @@ xfs_sb_from_disk(
 	__xfs_sb_from_disk(to, from, true);
 }
 
-static inline void
+static void
 xfs_sb_quota_to_disk(
-	xfs_dsb_t	*to,
-	xfs_sb_t	*from,
-	__int64_t	*fields)
+	struct xfs_dsb	*to,
+	struct xfs_sb	*from)
 {
 	__uint16_t	qflags = from->sb_qflags;
 
+	to->sb_uquotino = cpu_to_be64(from->sb_uquotino);
+	if (xfs_sb_version_has_pquotino(from)) {
+		to->sb_qflags = cpu_to_be16(from->sb_qflags);
+		to->sb_gquotino = cpu_to_be64(from->sb_gquotino);
+		to->sb_pquotino = cpu_to_be64(from->sb_pquotino);
+		return;
+	}
+
 	/*
-	 * We need to do these manipilations only if we are working
-	 * with an older version of on-disk superblock.
+	 * The in-core version of sb_qflags do not have XFS_OQUOTA_*
+	 * flags, whereas the on-disk version does.  So, convert incore
+	 * XFS_{PG}QUOTA_* flags to on-disk XFS_OQUOTA_* flags.
 	 */
-	if (xfs_sb_version_has_pquotino(from))
-		return;
+	qflags &= ~(XFS_PQUOTA_ENFD | XFS_PQUOTA_CHKD |
+			XFS_GQUOTA_ENFD | XFS_GQUOTA_CHKD);
 
-	if (*fields & XFS_SB_QFLAGS) {
-		/*
-		 * The in-core version of sb_qflags do not have
-		 * XFS_OQUOTA_* flags, whereas the on-disk version
-		 * does.  So, convert incore XFS_{PG}QUOTA_* flags
-		 * to on-disk XFS_OQUOTA_* flags.
-		 */
-		qflags &= ~(XFS_PQUOTA_ENFD | XFS_PQUOTA_CHKD |
-				XFS_GQUOTA_ENFD | XFS_GQUOTA_CHKD);
-
-		if (from->sb_qflags &
-				(XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD))
-			qflags |= XFS_OQUOTA_ENFD;
-		if (from->sb_qflags &
-				(XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD))
-			qflags |= XFS_OQUOTA_CHKD;
-		to->sb_qflags = cpu_to_be16(qflags);
-		*fields &= ~XFS_SB_QFLAGS;
-	}
+	if (from->sb_qflags &
+			(XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD))
+		qflags |= XFS_OQUOTA_ENFD;
+	if (from->sb_qflags &
+			(XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD))
+		qflags |= XFS_OQUOTA_CHKD;
+	to->sb_qflags = cpu_to_be16(qflags);
 
 	/*
-	 * GQUOTINO and PQUOTINO cannot be used together in versions of
-	 * superblock that do not have pquotino. from->sb_flags tells us which
-	 * quota is active and should be copied to disk. If neither are active,
-	 * make sure we write NULLFSINO to the sb_gquotino field as a quota
-	 * inode value of "0" is invalid when the XFS_SB_VERSION_QUOTA feature
-	 * bit is set.
+	 * GQUOTINO and PQUOTINO cannot be used together in versions
+	 * of superblock that do not have pquotino. from->sb_flags
+	 * tells us which quota is active and should be copied to
+	 * disk. If neither are active, we should NULL the inode.
 	 *
-	 * Note that we don't need to handle the sb_uquotino or sb_pquotino here
-	 * as they do not require any translation. Hence the main sb field loop
-	 * will write them appropriately from the in-core superblock.
+	 * In all cases, the separate pquotino must remain 0 because it
+	 * it beyond the "end" of the valid non-pquotino superblock.
 	 */
-	if ((*fields & XFS_SB_GQUOTINO) &&
-				(from->sb_qflags & XFS_GQUOTA_ACCT))
+	if (from->sb_qflags & XFS_GQUOTA_ACCT)
 		to->sb_gquotino = cpu_to_be64(from->sb_gquotino);
-	else if ((*fields & XFS_SB_PQUOTINO) &&
-				(from->sb_qflags & XFS_PQUOTA_ACCT))
+	else if (from->sb_qflags & XFS_PQUOTA_ACCT)
 		to->sb_gquotino = cpu_to_be64(from->sb_pquotino);
 	else {
 		/*
@@ -526,63 +454,78 @@ xfs_sb_quota_to_disk(
 			to->sb_gquotino = cpu_to_be64(NULLFSINO);
 	}
 
-	*fields &= ~(XFS_SB_PQUOTINO | XFS_SB_GQUOTINO);
+	to->sb_pquotino = 0;
 }
 
-/*
- * Copy in core superblock to ondisk one.
- *
- * The fields argument is mask of superblock fields to copy.
- */
 void
 xfs_sb_to_disk(
-	xfs_dsb_t	*to,
-	xfs_sb_t	*from,
-	__int64_t	fields)
+	struct xfs_dsb	*to,
+	struct xfs_sb	*from)
 {
-	xfs_caddr_t	to_ptr = (xfs_caddr_t)to;
-	xfs_caddr_t	from_ptr = (xfs_caddr_t)from;
-	xfs_sb_field_t	f;
-	int		first;
-	int		size;
-
-	ASSERT(fields);
-	if (!fields)
-		return;
+	xfs_sb_quota_to_disk(to, from);
 
-	/* We should never write the crc here, it's updated in the IO path */
-	fields &= ~XFS_SB_CRC;
-
-	xfs_sb_quota_to_disk(to, from, &fields);
-	while (fields) {
-		f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
-		first = xfs_sb_info[f].offset;
-		size = xfs_sb_info[f + 1].offset - first;
-
-		ASSERT(xfs_sb_info[f].type == 0 || xfs_sb_info[f].type == 1);
-
-		if (size == 1 || xfs_sb_info[f].type == 1) {
-			memcpy(to_ptr + first, from_ptr + first, size);
-		} else {
-			switch (size) {
-			case 2:
-				*(__be16 *)(to_ptr + first) =
-				      cpu_to_be16(*(__u16 *)(from_ptr + first));
-				break;
-			case 4:
-				*(__be32 *)(to_ptr + first) =
-				      cpu_to_be32(*(__u32 *)(from_ptr + first));
-				break;
-			case 8:
-				*(__be64 *)(to_ptr + first) =
-				      cpu_to_be64(*(__u64 *)(from_ptr + first));
-				break;
-			default:
-				ASSERT(0);
-			}
-		}
+	to->sb_magicnum = cpu_to_be32(from->sb_magicnum);
+	to->sb_blocksize = cpu_to_be32(from->sb_blocksize);
+	to->sb_dblocks = cpu_to_be64(from->sb_dblocks);
+	to->sb_rblocks = cpu_to_be64(from->sb_rblocks);
+	to->sb_rextents = cpu_to_be64(from->sb_rextents);
+	memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid));
+	to->sb_logstart = cpu_to_be64(from->sb_logstart);
+	to->sb_rootino = cpu_to_be64(from->sb_rootino);
+	to->sb_rbmino = cpu_to_be64(from->sb_rbmino);
+	to->sb_rsumino = cpu_to_be64(from->sb_rsumino);
+	to->sb_rextsize = cpu_to_be32(from->sb_rextsize);
+	to->sb_agblocks = cpu_to_be32(from->sb_agblocks);
+	to->sb_agcount = cpu_to_be32(from->sb_agcount);
+	to->sb_rbmblocks = cpu_to_be32(from->sb_rbmblocks);
+	to->sb_logblocks = cpu_to_be32(from->sb_logblocks);
+	to->sb_versionnum = cpu_to_be16(from->sb_versionnum);
+	to->sb_sectsize = cpu_to_be16(from->sb_sectsize);
+	to->sb_inodesize = cpu_to_be16(from->sb_inodesize);
+	to->sb_inopblock = cpu_to_be16(from->sb_inopblock);
+	memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname));
+	to->sb_blocklog = from->sb_blocklog;
+	to->sb_sectlog = from->sb_sectlog;
+	to->sb_inodelog = from->sb_inodelog;
+	to->sb_inopblog = from->sb_inopblog;
+	to->sb_agblklog = from->sb_agblklog;
+	to->sb_rextslog = from->sb_rextslog;
+	to->sb_inprogress = from->sb_inprogress;
+	to->sb_imax_pct = from->sb_imax_pct;
+	to->sb_icount = cpu_to_be64(from->sb_icount);
+	to->sb_ifree = cpu_to_be64(from->sb_ifree);
+	to->sb_fdblocks = cpu_to_be64(from->sb_fdblocks);
+	to->sb_frextents = cpu_to_be64(from->sb_frextents);
 
-		fields &= ~(1LL << f);
+	to->sb_flags = from->sb_flags;
+	to->sb_shared_vn = from->sb_shared_vn;
+	to->sb_inoalignmt = cpu_to_be32(from->sb_inoalignmt);
+	to->sb_unit = cpu_to_be32(from->sb_unit);
+	to->sb_width = cpu_to_be32(from->sb_width);
+	to->sb_dirblklog = from->sb_dirblklog;
+	to->sb_logsectlog = from->sb_logsectlog;
+	to->sb_logsectsize = cpu_to_be16(from->sb_logsectsize);
+	to->sb_logsunit = cpu_to_be32(from->sb_logsunit);
+
+	/*
+	 * We need to ensure that bad_features2 always matches features2.
+	 * Hence we enforce that here rather than having to remember to do it
+	 * everywhere else that updates features2.
+	 */
+	from->sb_bad_features2 = from->sb_features2;
+	to->sb_features2 = cpu_to_be32(from->sb_features2);
+	to->sb_bad_features2 = cpu_to_be32(from->sb_bad_features2);
+
+	if (xfs_sb_version_hascrc(from)) {
+		to->sb_features_compat = cpu_to_be32(from->sb_features_compat);
+		to->sb_features_ro_compat =
+				cpu_to_be32(from->sb_features_ro_compat);
+		to->sb_features_incompat =
+				cpu_to_be32(from->sb_features_incompat);
+		to->sb_features_log_incompat =
+				cpu_to_be32(from->sb_features_log_incompat);
+		to->sb_pad = 0;
+		to->sb_lsn = cpu_to_be64(from->sb_lsn);
 	}
 }
 
@@ -816,42 +759,51 @@ xfs_initialize_perag_data(
 }
 
 /*
- * xfs_mod_sb() can be used to copy arbitrary changes to the
- * in-core superblock into the superblock buffer to be logged.
- * It does not provide the higher level of locking that is
- * needed to protect the in-core superblock from concurrent
- * access.
+ * xfs_log_sb() can be used to copy arbitrary changes to the in-core superblock
+ * into the superblock buffer to be logged.  It does not provide the higher
+ * level of locking that is needed to protect the in-core superblock from
+ * concurrent access.
  */
 void
-xfs_mod_sb(xfs_trans_t *tp, __int64_t fields)
+xfs_log_sb(
+	struct xfs_trans	*tp)
 {
-	xfs_buf_t	*bp;
-	int		first;
-	int		last;
-	xfs_mount_t	*mp;
-	xfs_sb_field_t	f;
-
-	ASSERT(fields);
-	if (!fields)
-		return;
-	mp = tp->t_mountp;
-	bp = xfs_trans_getsb(tp, mp, 0);
-	first = sizeof(xfs_sb_t);
-	last = 0;
-
-	/* translate/copy */
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_buf		*bp = xfs_trans_getsb(tp, mp, 0);
 
-	xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, fields);
+	xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
+	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
+	xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb));
+}
 
-	/* find modified range */
-	f = (xfs_sb_field_t)xfs_highbit64((__uint64_t)fields);
-	ASSERT((1LL << f) & XFS_SB_MOD_BITS);
-	last = xfs_sb_info[f + 1].offset - 1;
+/*
+ * xfs_sync_sb
+ *
+ * Sync the superblock to disk.
+ *
+ * Note that the caller is responsible for checking the frozen state of the
+ * filesystem. This procedure uses the non-blocking transaction allocator and
+ * thus will allow modifications to a frozen fs. This is required because this
+ * code can be called during the process of freezing where use of the high-level
+ * allocator would deadlock.
+ */
+int
+xfs_sync_sb(
+	struct xfs_mount	*mp,
+	bool			wait)
+{
+	struct xfs_trans	*tp;
+	int			error;
 
-	f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
-	ASSERT((1LL << f) & XFS_SB_MOD_BITS);
-	first = xfs_sb_info[f].offset;
+	tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_CHANGE, KM_SLEEP);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		return error;
+	}
 
-	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
-	xfs_trans_log_buf(tp, bp, first, last);
+	xfs_log_sb(tp);
+	if (wait)
+		xfs_trans_set_sync(tp);
+	return xfs_trans_commit(tp, 0);
 }
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 8eb1c54bafbf..b25bb9a343f3 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -27,11 +27,12 @@ extern struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *, xfs_agnumber_t,
 extern void	xfs_perag_put(struct xfs_perag *pag);
 extern int	xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t);
 
-extern void	xfs_sb_calc_crc(struct xfs_buf	*);
-extern void	xfs_mod_sb(struct xfs_trans *, __int64_t);
-extern void	xfs_sb_mount_common(struct xfs_mount *, struct xfs_sb *);
-extern void	xfs_sb_from_disk(struct xfs_sb *, struct xfs_dsb *);
-extern void	xfs_sb_to_disk(struct xfs_dsb *, struct xfs_sb *, __int64_t);
+extern void	xfs_sb_calc_crc(struct xfs_buf *bp);
+extern void	xfs_log_sb(struct xfs_trans *tp);
+extern int	xfs_sync_sb(struct xfs_mount *mp, bool wait);
+extern void	xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp);
+extern void	xfs_sb_from_disk(struct xfs_sb *to, struct xfs_dsb *from);
+extern void	xfs_sb_to_disk(struct xfs_dsb *to, struct xfs_sb *from);
 extern void	xfs_sb_quota_from_disk(struct xfs_sb *sbp);
 
 #endif	/* __XFS_SB_H__ */
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 82404da2ca67..8dda4b321343 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -82,7 +82,7 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops;
 #define	XFS_TRANS_ATTR_RM		23
 #define	XFS_TRANS_ATTR_FLAG		24
 #define	XFS_TRANS_CLEAR_AGI_BUCKET	25
-#define XFS_TRANS_QM_SBCHANGE		26
+#define XFS_TRANS_SB_CHANGE		26
 /*
  * Dummy entries since we use the transaction type to index into the
  * trans_type[] in xlog_recover_print_trans_head()
@@ -95,17 +95,15 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops;
 #define XFS_TRANS_QM_DQCLUSTER		32
 #define XFS_TRANS_QM_QINOCREATE		33
 #define XFS_TRANS_QM_QUOTAOFF_END	34
-#define XFS_TRANS_SB_UNIT		35
-#define XFS_TRANS_FSYNC_TS		36
-#define	XFS_TRANS_GROWFSRT_ALLOC	37
-#define	XFS_TRANS_GROWFSRT_ZERO		38
-#define	XFS_TRANS_GROWFSRT_FREE		39
-#define	XFS_TRANS_SWAPEXT		40
-#define	XFS_TRANS_SB_COUNT		41
-#define	XFS_TRANS_CHECKPOINT		42
-#define	XFS_TRANS_ICREATE		43
-#define	XFS_TRANS_CREATE_TMPFILE	44
-#define	XFS_TRANS_TYPE_MAX		44
+#define XFS_TRANS_FSYNC_TS		35
+#define	XFS_TRANS_GROWFSRT_ALLOC	36
+#define	XFS_TRANS_GROWFSRT_ZERO		37
+#define	XFS_TRANS_GROWFSRT_FREE		38
+#define	XFS_TRANS_SWAPEXT		39
+#define	XFS_TRANS_CHECKPOINT		40
+#define	XFS_TRANS_ICREATE		41
+#define	XFS_TRANS_CREATE_TMPFILE	42
+#define	XFS_TRANS_TYPE_MAX		43
 /* new transaction types need to be reflected in xfs_logprint(8) */
 
 #define XFS_TRANS_TYPES \
@@ -113,7 +111,6 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops;
 	{ XFS_TRANS_SETATTR_SIZE,	"SETATTR_SIZE" }, \
 	{ XFS_TRANS_INACTIVE,		"INACTIVE" }, \
 	{ XFS_TRANS_CREATE,		"CREATE" }, \
-	{ XFS_TRANS_CREATE_TMPFILE,	"CREATE_TMPFILE" }, \
 	{ XFS_TRANS_CREATE_TRUNC,	"CREATE_TRUNC" }, \
 	{ XFS_TRANS_TRUNCATE_FILE,	"TRUNCATE_FILE" }, \
 	{ XFS_TRANS_REMOVE,		"REMOVE" }, \
@@ -134,23 +131,23 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops;
 	{ XFS_TRANS_ATTR_RM,		"ATTR_RM" }, \
 	{ XFS_TRANS_ATTR_FLAG,		"ATTR_FLAG" }, \
 	{ XFS_TRANS_CLEAR_AGI_BUCKET,	"CLEAR_AGI_BUCKET" }, \
-	{ XFS_TRANS_QM_SBCHANGE,	"QM_SBCHANGE" }, \
+	{ XFS_TRANS_SB_CHANGE,		"SBCHANGE" }, \
+	{ XFS_TRANS_DUMMY1,		"DUMMY1" }, \
+	{ XFS_TRANS_DUMMY2,		"DUMMY2" }, \
 	{ XFS_TRANS_QM_QUOTAOFF,	"QM_QUOTAOFF" }, \
 	{ XFS_TRANS_QM_DQALLOC,		"QM_DQALLOC" }, \
 	{ XFS_TRANS_QM_SETQLIM,		"QM_SETQLIM" }, \
 	{ XFS_TRANS_QM_DQCLUSTER,	"QM_DQCLUSTER" }, \
 	{ XFS_TRANS_QM_QINOCREATE,	"QM_QINOCREATE" }, \
 	{ XFS_TRANS_QM_QUOTAOFF_END,	"QM_QOFF_END" }, \
-	{ XFS_TRANS_SB_UNIT,		"SB_UNIT" }, \
 	{ XFS_TRANS_FSYNC_TS,		"FSYNC_TS" }, \
 	{ XFS_TRANS_GROWFSRT_ALLOC,	"GROWFSRT_ALLOC" }, \
 	{ XFS_TRANS_GROWFSRT_ZERO,	"GROWFSRT_ZERO" }, \
 	{ XFS_TRANS_GROWFSRT_FREE,	"GROWFSRT_FREE" }, \
 	{ XFS_TRANS_SWAPEXT,		"SWAPEXT" }, \
-	{ XFS_TRANS_SB_COUNT,		"SB_COUNT" }, \
 	{ XFS_TRANS_CHECKPOINT,		"CHECKPOINT" }, \
-	{ XFS_TRANS_DUMMY1,		"DUMMY1" }, \
-	{ XFS_TRANS_DUMMY2,		"DUMMY2" }, \
+	{ XFS_TRANS_ICREATE,		"ICREATE" }, \
+	{ XFS_TRANS_CREATE_TMPFILE,	"CREATE_TMPFILE" }, \
 	{ XLOG_UNMOUNT_REC_TYPE,	"UNMOUNT" }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index c80c5236c3da..e7e26bd6468f 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -178,6 +178,8 @@ xfs_symlink_local_to_remote(
 	struct xfs_mount	*mp = ip->i_mount;
 	char			*buf;
 
+	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
+
 	if (!xfs_sb_version_hascrc(&mp->m_sb)) {
 		bp->b_ops = NULL;
 		memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 6c1330f29050..68cb1e7bf2bb 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -716,17 +716,6 @@ xfs_calc_clear_agi_bucket_reservation(
 }
 
 /*
- * Clearing the quotaflags in the superblock.
- *	the super block for changing quota flags: sector size
- */
-STATIC uint
-xfs_calc_qm_sbchange_reservation(
-	struct xfs_mount	*mp)
-{
-	return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
-}
-
-/*
  * Adjusting quota limits.
  *    the xfs_disk_dquot_t: sizeof(struct xfs_disk_dquot)
  */
@@ -864,9 +853,6 @@ xfs_trans_resv_calc(
 	 * The following transactions are logged in logical format with
 	 * a default log count.
 	 */
-	resp->tr_qm_sbchange.tr_logres = xfs_calc_qm_sbchange_reservation(mp);
-	resp->tr_qm_sbchange.tr_logcount = XFS_DEFAULT_LOG_COUNT;
-
 	resp->tr_qm_setqlim.tr_logres = xfs_calc_qm_setqlim_reservation(mp);
 	resp->tr_qm_setqlim.tr_logcount = XFS_DEFAULT_LOG_COUNT;
 
diff --git a/fs/xfs/libxfs/xfs_trans_resv.h b/fs/xfs/libxfs/xfs_trans_resv.h
index 1097d14cd583..2d5bdfce6d8f 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.h
+++ b/fs/xfs/libxfs/xfs_trans_resv.h
@@ -56,7 +56,6 @@ struct xfs_trans_resv {
 	struct xfs_trans_res	tr_growrtalloc;	/* grow realtime allocations */
 	struct xfs_trans_res	tr_growrtzero;	/* grow realtime zeroing */
 	struct xfs_trans_res	tr_growrtfree;	/* grow realtime freeing */
-	struct xfs_trans_res	tr_qm_sbchange;	/* change quota flags */
 	struct xfs_trans_res	tr_qm_setqlim;	/* adjust quota limits */
 	struct xfs_trans_res	tr_qm_dqalloc;	/* allocate quota on disk */
 	struct xfs_trans_res	tr_qm_quotaoff;	/* turn quota off */
diff --git a/fs/xfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index b79dc66b2ecd..b79dc66b2ecd 100644
--- a/fs/xfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 18e2f3bbae5e..3a9b7a1b8704 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -135,30 +135,22 @@ xfs_setfilesize_trans_alloc(
  */
 STATIC int
 xfs_setfilesize(
-	struct xfs_ioend	*ioend)
+	struct xfs_inode	*ip,
+	struct xfs_trans	*tp,
+	xfs_off_t		offset,
+	size_t			size)
 {
-	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
-	struct xfs_trans	*tp = ioend->io_append_trans;
 	xfs_fsize_t		isize;
 
-	/*
-	 * The transaction may have been allocated in the I/O submission thread,
-	 * thus we need to mark ourselves as beeing in a transaction manually.
-	 * Similarly for freeze protection.
-	 */
-	current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
-	rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
-			   0, 1, _THIS_IP_);
-
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	isize = xfs_new_eof(ip, ioend->io_offset + ioend->io_size);
+	isize = xfs_new_eof(ip, offset + size);
 	if (!isize) {
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_cancel(tp, 0);
 		return 0;
 	}
 
-	trace_xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
+	trace_xfs_setfilesize(ip, offset, size);
 
 	ip->i_d.di_size = isize;
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
@@ -167,6 +159,25 @@ xfs_setfilesize(
 	return xfs_trans_commit(tp, 0);
 }
 
+STATIC int
+xfs_setfilesize_ioend(
+	struct xfs_ioend	*ioend)
+{
+	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	struct xfs_trans	*tp = ioend->io_append_trans;
+
+	/*
+	 * The transaction may have been allocated in the I/O submission thread,
+	 * thus we need to mark ourselves as being in a transaction manually.
+	 * Similarly for freeze protection.
+	 */
+	current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
+	rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+			   0, 1, _THIS_IP_);
+
+	return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size);
+}
+
 /*
  * Schedule IO completion handling on the final put of an ioend.
  *
@@ -182,8 +193,7 @@ xfs_finish_ioend(
 
 		if (ioend->io_type == XFS_IO_UNWRITTEN)
 			queue_work(mp->m_unwritten_workqueue, &ioend->io_work);
-		else if (ioend->io_append_trans ||
-			 (ioend->io_isdirect && xfs_ioend_is_append(ioend)))
+		else if (ioend->io_append_trans)
 			queue_work(mp->m_data_workqueue, &ioend->io_work);
 		else
 			xfs_destroy_ioend(ioend);
@@ -215,22 +225,8 @@ xfs_end_io(
 	if (ioend->io_type == XFS_IO_UNWRITTEN) {
 		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
 						  ioend->io_size);
-	} else if (ioend->io_isdirect && xfs_ioend_is_append(ioend)) {
-		/*
-		 * For direct I/O we do not know if we need to allocate blocks
-		 * or not so we can't preallocate an append transaction as that
-		 * results in nested reservations and log space deadlocks. Hence
-		 * allocate the transaction here. While this is sub-optimal and
-		 * can block IO completion for some time, we're stuck with doing
-		 * it this way until we can pass the ioend to the direct IO
-		 * allocation callbacks and avoid nesting that way.
-		 */
-		error = xfs_setfilesize_trans_alloc(ioend);
-		if (error)
-			goto done;
-		error = xfs_setfilesize(ioend);
 	} else if (ioend->io_append_trans) {
-		error = xfs_setfilesize(ioend);
+		error = xfs_setfilesize_ioend(ioend);
 	} else {
 		ASSERT(!xfs_ioend_is_append(ioend));
 	}
@@ -242,17 +238,6 @@ done:
 }
 
 /*
- * Call IO completion handling in caller context on the final put of an ioend.
- */
-STATIC void
-xfs_finish_ioend_sync(
-	struct xfs_ioend	*ioend)
-{
-	if (atomic_dec_and_test(&ioend->io_remaining))
-		xfs_end_io(&ioend->io_work);
-}
-
-/*
  * Allocate and initialise an IO completion structure.
  * We need to track unwritten extent write completion here initially.
  * We'll need to extend this for updating the ondisk inode size later
@@ -273,7 +258,6 @@ xfs_alloc_ioend(
 	 * all the I/O from calling the completion routine too early.
 	 */
 	atomic_set(&ioend->io_remaining, 1);
-	ioend->io_isdirect = 0;
 	ioend->io_error = 0;
 	ioend->io_list = NULL;
 	ioend->io_type = type;
@@ -1459,11 +1443,7 @@ xfs_get_blocks_direct(
  *
  * If the private argument is non-NULL __xfs_get_blocks signals us that we
  * need to issue a transaction to convert the range from unwritten to written
- * extents.  In case this is regular synchronous I/O we just call xfs_end_io
- * to do this and we are done.  But in case this was a successful AIO
- * request this handler is called from interrupt context, from which we
- * can't start transactions.  In that case offload the I/O completion to
- * the workqueues we also use for buffered I/O completion.
+ * extents.
  */
 STATIC void
 xfs_end_io_direct_write(
@@ -1472,7 +1452,12 @@ xfs_end_io_direct_write(
 	ssize_t			size,
 	void			*private)
 {
-	struct xfs_ioend	*ioend = iocb->private;
+	struct inode		*inode = file_inode(iocb->ki_filp);
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return;
 
 	/*
 	 * While the generic direct I/O code updates the inode size, it does
@@ -1480,22 +1465,33 @@ xfs_end_io_direct_write(
 	 * end_io handler thinks the on-disk size is outside the in-core
 	 * size.  To prevent this just update it a little bit earlier here.
 	 */
-	if (offset + size > i_size_read(ioend->io_inode))
-		i_size_write(ioend->io_inode, offset + size);
+	if (offset + size > i_size_read(inode))
+		i_size_write(inode, offset + size);
 
 	/*
-	 * blockdev_direct_IO can return an error even after the I/O
-	 * completion handler was called.  Thus we need to protect
-	 * against double-freeing.
+	 * For direct I/O we do not know if we need to allocate blocks or not,
+	 * so we can't preallocate an append transaction, as that results in
+	 * nested reservations and log space deadlocks. Hence allocate the
+	 * transaction here. While this is sub-optimal and can block IO
+	 * completion for some time, we're stuck with doing it this way until
+	 * we can pass the ioend to the direct IO allocation callbacks and
+	 * avoid nesting that way.
 	 */
-	iocb->private = NULL;
-
-	ioend->io_offset = offset;
-	ioend->io_size = size;
-	if (private && size > 0)
-		ioend->io_type = XFS_IO_UNWRITTEN;
+	if (private && size > 0) {
+		xfs_iomap_write_unwritten(ip, offset, size);
+	} else if (offset + size > ip->i_d.di_size) {
+		struct xfs_trans	*tp;
+		int			error;
+
+		tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+		error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
+		if (error) {
+			xfs_trans_cancel(tp, 0);
+			return;
+		}
 
-	xfs_finish_ioend_sync(ioend);
+		xfs_setfilesize(ip, tp, offset, size);
+	}
 }
 
 STATIC ssize_t
@@ -1507,39 +1503,16 @@ xfs_vm_direct_IO(
 {
 	struct inode		*inode = iocb->ki_filp->f_mapping->host;
 	struct block_device	*bdev = xfs_find_bdev_for_inode(inode);
-	struct xfs_ioend	*ioend = NULL;
-	ssize_t			ret;
 
 	if (rw & WRITE) {
-		size_t size = iov_iter_count(iter);
-
-		/*
-		 * We cannot preallocate a size update transaction here as we
-		 * don't know whether allocation is necessary or not. Hence we
-		 * can only tell IO completion that one is necessary if we are
-		 * not doing unwritten extent conversion.
-		 */
-		iocb->private = ioend = xfs_alloc_ioend(inode, XFS_IO_DIRECT);
-		if (offset + size > XFS_I(inode)->i_d.di_size)
-			ioend->io_isdirect = 1;
-
-		ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
+		return __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
 					    offset, xfs_get_blocks_direct,
 					    xfs_end_io_direct_write, NULL,
 					    DIO_ASYNC_EXTEND);
-		if (ret != -EIOCBQUEUED && iocb->private)
-			goto out_destroy_ioend;
-	} else {
-		ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
-					    offset, xfs_get_blocks_direct,
-					    NULL, NULL, 0);
 	}
-
-	return ret;
-
-out_destroy_ioend:
-	xfs_destroy_ioend(ioend);
-	return ret;
+	return __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
+				    offset, xfs_get_blocks_direct,
+				    NULL, NULL, 0);
 }
 
 /*
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index f94dd459dff9..ac644e0137a4 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -24,14 +24,12 @@ extern mempool_t *xfs_ioend_pool;
  * Types of I/O for bmap clustering and I/O completion tracking.
  */
 enum {
-	XFS_IO_DIRECT = 0,	/* special case for direct I/O ioends */
 	XFS_IO_DELALLOC,	/* covers delalloc region */
 	XFS_IO_UNWRITTEN,	/* covers allocated but uninitialized data */
 	XFS_IO_OVERWRITE,	/* covers already allocated extent */
 };
 
 #define XFS_IO_TYPES \
-	{ 0,			"" }, \
 	{ XFS_IO_DELALLOC,		"delalloc" }, \
 	{ XFS_IO_UNWRITTEN,		"unwritten" }, \
 	{ XFS_IO_OVERWRITE,		"overwrite" }
@@ -45,7 +43,6 @@ typedef struct xfs_ioend {
 	unsigned int		io_type;	/* delalloc / unwritten */
 	int			io_error;	/* I/O error code */
 	atomic_t		io_remaining;	/* hold count */
-	unsigned int		io_isdirect : 1;/* direct I/O */
 	struct inode		*io_inode;	/* file being written to */
 	struct buffer_head	*io_buffer_head;/* buffer linked list head */
 	struct buffer_head	*io_buffer_tail;/* buffer linked list tail */
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 2fdb72d2c908..736429a72a12 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -26,43 +26,8 @@ struct xfs_ifork;
 struct xfs_inode;
 struct xfs_mount;
 struct xfs_trans;
+struct xfs_bmalloca;
 
-/*
- * Argument structure for xfs_bmap_alloc.
- */
-struct xfs_bmalloca {
-	xfs_fsblock_t		*firstblock; /* i/o first block allocated */
-	struct xfs_bmap_free	*flist;	/* bmap freelist */
-	struct xfs_trans	*tp;	/* transaction pointer */
-	struct xfs_inode	*ip;	/* incore inode pointer */
-	struct xfs_bmbt_irec	prev;	/* extent before the new one */
-	struct xfs_bmbt_irec	got;	/* extent after, or delayed */
-
-	xfs_fileoff_t		offset;	/* offset in file filling in */
-	xfs_extlen_t		length;	/* i/o length asked/allocated */
-	xfs_fsblock_t		blkno;	/* starting block of new extent */
-
-	struct xfs_btree_cur	*cur;	/* btree cursor */
-	xfs_extnum_t		idx;	/* current extent index */
-	int			nallocs;/* number of extents alloc'd */
-	int			logflags;/* flags for transaction logging */
-
-	xfs_extlen_t		total;	/* total blocks needed for xaction */
-	xfs_extlen_t		minlen;	/* minimum allocation size (blocks) */
-	xfs_extlen_t		minleft; /* amount must be left after alloc */
-	bool			eof;	/* set if allocating past last extent */
-	bool			wasdel;	/* replacing a delayed allocation */
-	bool			userdata;/* set if is user data */
-	bool			aeof;	/* allocated space at eof */
-	bool			conv;	/* overwriting unwritten extents */
-	int			flags;
-	struct completion	*done;
-	struct work_struct	work;
-	int			result;
-};
-
-int	xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
-			int *committed);
 int	xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
 int	xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
 		     int whichfork, int *eof);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index bb502a391792..1790b00bea7a 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1488,6 +1488,7 @@ xfs_buf_iomove(
 static enum lru_status
 xfs_buftarg_wait_rele(
 	struct list_head	*item,
+	struct list_lru_one	*lru,
 	spinlock_t		*lru_lock,
 	void			*arg)
 
@@ -1509,7 +1510,7 @@ xfs_buftarg_wait_rele(
 	 */
 	atomic_set(&bp->b_lru_ref, 0);
 	bp->b_state |= XFS_BSTATE_DISPOSE;
-	list_move(item, dispose);
+	list_lru_isolate_move(lru, item, dispose);
 	spin_unlock(&bp->b_lock);
 	return LRU_REMOVED;
 }
@@ -1546,6 +1547,7 @@ xfs_wait_buftarg(
 static enum lru_status
 xfs_buftarg_isolate(
 	struct list_head	*item,
+	struct list_lru_one	*lru,
 	spinlock_t		*lru_lock,
 	void			*arg)
 {
@@ -1569,7 +1571,7 @@ xfs_buftarg_isolate(
 	}
 
 	bp->b_state |= XFS_BSTATE_DISPOSE;
-	list_move(item, dispose);
+	list_lru_isolate_move(lru, item, dispose);
 	spin_unlock(&bp->b_lock);
 	return LRU_REMOVED;
 }
@@ -1583,10 +1585,9 @@ xfs_buftarg_shrink_scan(
 					struct xfs_buftarg, bt_shrinker);
 	LIST_HEAD(dispose);
 	unsigned long		freed;
-	unsigned long		nr_to_scan = sc->nr_to_scan;
 
-	freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate,
-				       &dispose, &nr_to_scan);
+	freed = list_lru_shrink_walk(&btp->bt_lru, sc,
+				     xfs_buftarg_isolate, &dispose);
 
 	while (!list_empty(&dispose)) {
 		struct xfs_buf *bp;
@@ -1605,7 +1606,7 @@ xfs_buftarg_shrink_count(
 {
 	struct xfs_buftarg	*btp = container_of(shrink,
 					struct xfs_buftarg, bt_shrinker);
-	return list_lru_count_node(&btp->bt_lru, sc->nid);
+	return list_lru_shrink_count(&btp->bt_lru, sc);
 }
 
 void
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 3f9bd58edec7..507d96a57ac7 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -319,6 +319,10 @@ xfs_buf_item_format(
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
 	       (bip->bli_flags & XFS_BLI_STALE));
+	ASSERT((bip->bli_flags & XFS_BLI_STALE) ||
+	       (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF
+	        && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF));
+
 
 	/*
 	 * If it is an inode buffer, transfer the in-memory state to the
@@ -535,7 +539,7 @@ xfs_buf_item_push(
 	if ((bp->b_flags & XBF_WRITE_FAIL) &&
 	    ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) {
 		xfs_warn(bp->b_target->bt_mount,
-"Detected failing async write on buffer block 0x%llx. Retrying async write.\n",
+"Detected failing async write on buffer block 0x%llx. Retrying async write.",
 			 (long long)bp->b_bn);
 	}
 
diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index c24c67e22a2a..2f536f33cd26 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -86,7 +86,7 @@ static inline void xfs_dqflock(xfs_dquot_t *dqp)
 	wait_for_completion(&dqp->q_flush);
 }
 
-static inline int xfs_dqflock_nowait(xfs_dquot_t *dqp)
+static inline bool xfs_dqflock_nowait(xfs_dquot_t *dqp)
 {
 	return try_wait_for_completion(&dqp->q_flush);
 }
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 5eb4a14e0a0f..b97359ba2648 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -30,6 +30,7 @@
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 #include "xfs_log.h"
+#include "xfs_pnfs.h"
 
 /*
  * Note that we only accept fileids which are long enough rather than allow
@@ -245,4 +246,9 @@ const struct export_operations xfs_export_operations = {
 	.fh_to_parent		= xfs_fs_fh_to_parent,
 	.get_parent		= xfs_fs_get_parent,
 	.commit_metadata	= xfs_fs_nfs_commit_metadata,
+#ifdef CONFIG_NFSD_PNFS
+	.get_uuid		= xfs_fs_get_uuid,
+	.map_blocks		= xfs_fs_map_blocks,
+	.commit_blocks		= xfs_fs_commit_blocks,
+#endif
 };
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 13e974e6a889..a2e1cb8a568b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -36,6 +36,7 @@
 #include "xfs_trace.h"
 #include "xfs_log.h"
 #include "xfs_icache.h"
+#include "xfs_pnfs.h"
 
 #include <linux/aio.h>
 #include <linux/dcache.h>
@@ -127,6 +128,42 @@ xfs_iozero(
 	return (-status);
 }
 
+int
+xfs_update_prealloc_flags(
+	struct xfs_inode	*ip,
+	enum xfs_prealloc_flags	flags)
+{
+	struct xfs_trans	*tp;
+	int			error;
+
+	tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID);
+	error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		return error;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+	if (!(flags & XFS_PREALLOC_INVISIBLE)) {
+		ip->i_d.di_mode &= ~S_ISUID;
+		if (ip->i_d.di_mode & S_IXGRP)
+			ip->i_d.di_mode &= ~S_ISGID;
+		xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	}
+
+	if (flags & XFS_PREALLOC_SET)
+		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
+	if (flags & XFS_PREALLOC_CLEAR)
+		ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
+
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	if (flags & XFS_PREALLOC_SYNC)
+		xfs_trans_set_sync(tp);
+	return xfs_trans_commit(tp, 0);
+}
+
 /*
  * Fsync operations on directories are much simpler than on regular files,
  * as there is no file data to flush, and thus also no need for explicit
@@ -360,7 +397,8 @@ STATIC int				/* error (positive) */
 xfs_zero_last_block(
 	struct xfs_inode	*ip,
 	xfs_fsize_t		offset,
-	xfs_fsize_t		isize)
+	xfs_fsize_t		isize,
+	bool			*did_zeroing)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		last_fsb = XFS_B_TO_FSBT(mp, isize);
@@ -388,6 +426,7 @@ xfs_zero_last_block(
 	zero_len = mp->m_sb.sb_blocksize - zero_offset;
 	if (isize + zero_len > offset)
 		zero_len = offset - isize;
+	*did_zeroing = true;
 	return xfs_iozero(ip, isize, zero_len);
 }
 
@@ -406,7 +445,8 @@ int					/* error (positive) */
 xfs_zero_eof(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,		/* starting I/O offset */
-	xfs_fsize_t		isize)		/* current inode size */
+	xfs_fsize_t		isize,		/* current inode size */
+	bool			*did_zeroing)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		start_zero_fsb;
@@ -428,7 +468,7 @@ xfs_zero_eof(
 	 * We only zero a part of that block so it is handled specially.
 	 */
 	if (XFS_B_FSB_OFFSET(mp, isize) != 0) {
-		error = xfs_zero_last_block(ip, offset, isize);
+		error = xfs_zero_last_block(ip, offset, isize, did_zeroing);
 		if (error)
 			return error;
 	}
@@ -488,6 +528,7 @@ xfs_zero_eof(
 		if (error)
 			return error;
 
+		*did_zeroing = true;
 		start_zero_fsb = imap.br_startoff + imap.br_blockcount;
 		ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
 	}
@@ -518,6 +559,10 @@ restart:
 	if (error)
 		return error;
 
+	error = xfs_break_layouts(inode, iolock);
+	if (error)
+		return error;
+
 	/*
 	 * If the offset is beyond the size of the file, we need to zero any
 	 * blocks that fall between the existing EOF and the start of this
@@ -526,13 +571,15 @@ restart:
 	 * having to redo all checks before.
 	 */
 	if (*pos > i_size_read(inode)) {
+		bool	zero = false;
+
 		if (*iolock == XFS_IOLOCK_SHARED) {
 			xfs_rw_iunlock(ip, *iolock);
 			*iolock = XFS_IOLOCK_EXCL;
 			xfs_rw_ilock(ip, *iolock);
 			goto restart;
 		}
-		error = xfs_zero_eof(ip, *pos, i_size_read(inode));
+		error = xfs_zero_eof(ip, *pos, i_size_read(inode), &zero);
 		if (error)
 			return error;
 	}
@@ -699,7 +746,7 @@ xfs_file_buffered_aio_write(
 
 	iov_iter_truncate(from, count);
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 write_retry:
 	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
@@ -784,8 +831,9 @@ xfs_file_fallocate(
 {
 	struct inode		*inode = file_inode(file);
 	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_trans	*tp;
 	long			error;
+	enum xfs_prealloc_flags	flags = 0;
+	uint			iolock = XFS_IOLOCK_EXCL;
 	loff_t			new_size = 0;
 
 	if (!S_ISREG(inode->i_mode))
@@ -794,7 +842,11 @@ xfs_file_fallocate(
 		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
 		return -EOPNOTSUPP;
 
-	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+	xfs_ilock(ip, iolock);
+	error = xfs_break_layouts(inode, &iolock);
+	if (error)
+		goto out_unlock;
+
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		error = xfs_free_file_space(ip, offset, len);
 		if (error)
@@ -822,6 +874,8 @@ xfs_file_fallocate(
 		if (error)
 			goto out_unlock;
 	} else {
+		flags |= XFS_PREALLOC_SET;
+
 		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
 		    offset + len > i_size_read(inode)) {
 			new_size = offset + len;
@@ -839,28 +893,10 @@ xfs_file_fallocate(
 			goto out_unlock;
 	}
 
-	tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID);
-	error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		goto out_unlock;
-	}
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-	ip->i_d.di_mode &= ~S_ISUID;
-	if (ip->i_d.di_mode & S_IXGRP)
-		ip->i_d.di_mode &= ~S_ISGID;
-
-	if (!(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE)))
-		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
-
-	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
 	if (file->f_flags & O_DSYNC)
-		xfs_trans_set_sync(tp);
-	error = xfs_trans_commit(tp, 0);
+		flags |= XFS_PREALLOC_SYNC;
+
+	error = xfs_update_prealloc_flags(ip, flags);
 	if (error)
 		goto out_unlock;
 
@@ -874,7 +910,7 @@ xfs_file_fallocate(
 	}
 
 out_unlock:
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	xfs_iunlock(ip, iolock);
 	return error;
 }
 
@@ -1384,5 +1420,4 @@ static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_vm_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index fdc64220fcb0..74efe5b760dc 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -488,6 +488,7 @@ xfs_growfs_data_private(
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, nfree);
 	if (dpct)
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct);
+	xfs_trans_set_sync(tp);
 	error = xfs_trans_commit(tp, 0);
 	if (error)
 		return error;
@@ -541,7 +542,7 @@ xfs_growfs_data_private(
 			saved_error = error;
 			continue;
 		}
-		xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, XFS_SB_ALL_BITS);
+		xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
 
 		error = xfs_bwrite(bp);
 		xfs_buf_relse(bp);
@@ -601,6 +602,12 @@ xfs_growfs_data(
 	if (!mutex_trylock(&mp->m_growlock))
 		return -EWOULDBLOCK;
 	error = xfs_growfs_data_private(mp, in);
+	/*
+	 * Increment the generation unconditionally, the error could be from
+	 * updating the secondary superblocks, in which case the new size
+	 * is live already.
+	 */
+	mp->m_generation++;
 	mutex_unlock(&mp->m_growlock);
 	return error;
 }
@@ -756,37 +763,6 @@ out:
 	return 0;
 }
 
-/*
- * Dump a transaction into the log that contains no real change. This is needed
- * to be able to make the log dirty or stamp the current tail LSN into the log
- * during the covering operation.
- *
- * We cannot use an inode here for this - that will push dirty state back up
- * into the VFS and then periodic inode flushing will prevent log covering from
- * making progress. Hence we log a field in the superblock instead and use a
- * synchronous transaction to ensure the superblock is immediately unpinned
- * and can be written back.
- */
-int
-xfs_fs_log_dummy(
-	xfs_mount_t	*mp)
-{
-	xfs_trans_t	*tp;
-	int		error;
-
-	tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1, KM_SLEEP);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return error;
-	}
-
-	/* log the UUID because it is an unchanging field */
-	xfs_mod_sb(tp, XFS_SB_UUID);
-	xfs_trans_set_sync(tp);
-	return xfs_trans_commit(tp, 0);
-}
-
 int
 xfs_fs_goingdown(
 	xfs_mount_t	*mp,
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 41f804e740d7..6163767aa856 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1995,6 +1995,7 @@ xfs_iunlink(
 	agi->agi_unlinked[bucket_index] = cpu_to_be32(agino);
 	offset = offsetof(xfs_agi_t, agi_unlinked) +
 		(sizeof(xfs_agino_t) * bucket_index);
+	xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF);
 	xfs_trans_log_buf(tp, agibp, offset,
 			  (offset + sizeof(xfs_agino_t) - 1));
 	return 0;
@@ -2086,6 +2087,7 @@ xfs_iunlink_remove(
 		agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino);
 		offset = offsetof(xfs_agi_t, agi_unlinked) +
 			(sizeof(xfs_agino_t) * bucket_index);
+		xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF);
 		xfs_trans_log_buf(tp, agibp, offset,
 				  (offset + sizeof(xfs_agino_t) - 1));
 	} else {
@@ -2656,6 +2658,124 @@ xfs_sort_for_rename(
 }
 
 /*
+ * xfs_cross_rename()
+ *
+ * responsible for handling RENAME_EXCHANGE flag in renameat2() sytemcall
+ */
+STATIC int
+xfs_cross_rename(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp1,
+	struct xfs_name		*name1,
+	struct xfs_inode	*ip1,
+	struct xfs_inode	*dp2,
+	struct xfs_name		*name2,
+	struct xfs_inode	*ip2,
+	struct xfs_bmap_free	*free_list,
+	xfs_fsblock_t		*first_block,
+	int			spaceres)
+{
+	int		error = 0;
+	int		ip1_flags = 0;
+	int		ip2_flags = 0;
+	int		dp2_flags = 0;
+
+	/* Swap inode number for dirent in first parent */
+	error = xfs_dir_replace(tp, dp1, name1,
+				ip2->i_ino,
+				first_block, free_list, spaceres);
+	if (error)
+		goto out;
+
+	/* Swap inode number for dirent in second parent */
+	error = xfs_dir_replace(tp, dp2, name2,
+				ip1->i_ino,
+				first_block, free_list, spaceres);
+	if (error)
+		goto out;
+
+	/*
+	 * If we're renaming one or more directories across different parents,
+	 * update the respective ".." entries (and link counts) to match the new
+	 * parents.
+	 */
+	if (dp1 != dp2) {
+		dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+
+		if (S_ISDIR(ip2->i_d.di_mode)) {
+			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
+						dp1->i_ino, first_block,
+						free_list, spaceres);
+			if (error)
+				goto out;
+
+			/* transfer ip2 ".." reference to dp1 */
+			if (!S_ISDIR(ip1->i_d.di_mode)) {
+				error = xfs_droplink(tp, dp2);
+				if (error)
+					goto out;
+				error = xfs_bumplink(tp, dp1);
+				if (error)
+					goto out;
+			}
+
+			/*
+			 * Although ip1 isn't changed here, userspace needs
+			 * to be warned about the change, so that applications
+			 * relying on it (like backup ones), will properly
+			 * notify the change
+			 */
+			ip1_flags |= XFS_ICHGTIME_CHG;
+			ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+		}
+
+		if (S_ISDIR(ip1->i_d.di_mode)) {
+			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
+						dp2->i_ino, first_block,
+						free_list, spaceres);
+			if (error)
+				goto out;
+
+			/* transfer ip1 ".." reference to dp2 */
+			if (!S_ISDIR(ip2->i_d.di_mode)) {
+				error = xfs_droplink(tp, dp1);
+				if (error)
+					goto out;
+				error = xfs_bumplink(tp, dp2);
+				if (error)
+					goto out;
+			}
+
+			/*
+			 * Although ip2 isn't changed here, userspace needs
+			 * to be warned about the change, so that applications
+			 * relying on it (like backup ones), will properly
+			 * notify the change
+			 */
+			ip1_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+			ip2_flags |= XFS_ICHGTIME_CHG;
+		}
+	}
+
+	if (ip1_flags) {
+		xfs_trans_ichgtime(tp, ip1, ip1_flags);
+		xfs_trans_log_inode(tp, ip1, XFS_ILOG_CORE);
+	}
+	if (ip2_flags) {
+		xfs_trans_ichgtime(tp, ip2, ip2_flags);
+		xfs_trans_log_inode(tp, ip2, XFS_ILOG_CORE);
+	}
+	if (dp2_flags) {
+		xfs_trans_ichgtime(tp, dp2, dp2_flags);
+		xfs_trans_log_inode(tp, dp2, XFS_ILOG_CORE);
+	}
+	xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
+out:
+	return error;
+}
+
+/*
  * xfs_rename
  */
 int
@@ -2665,7 +2785,8 @@ xfs_rename(
 	xfs_inode_t	*src_ip,
 	xfs_inode_t	*target_dp,
 	struct xfs_name	*target_name,
-	xfs_inode_t	*target_ip)
+	xfs_inode_t	*target_ip,
+	unsigned int	flags)
 {
 	xfs_trans_t	*tp = NULL;
 	xfs_mount_t	*mp = src_dp->i_mount;
@@ -2743,6 +2864,22 @@ xfs_rename(
 	}
 
 	/*
+	 * Handle RENAME_EXCHANGE flags
+	 */
+	if (flags & RENAME_EXCHANGE) {
+		if (target_ip == NULL) {
+			error = -EINVAL;
+			goto error_return;
+		}
+		error = xfs_cross_rename(tp, src_dp, src_name, src_ip,
+					 target_dp, target_name, target_ip,
+					 &free_list, &first_block, spaceres);
+		if (error)
+			goto abort_return;
+		goto finish_rename;
+	}
+
+	/*
 	 * Set up the target.
 	 */
 	if (target_ip == NULL) {
@@ -2881,6 +3018,7 @@ xfs_rename(
 	if (new_parent)
 		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
 
+finish_rename:
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * rename transaction goes to disk before returning to
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 4ed2ba9342dc..a1cd55f3f351 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -338,7 +338,7 @@ int		xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
 int		xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name,
 			   struct xfs_inode *src_ip, struct xfs_inode *target_dp,
 			   struct xfs_name *target_name,
-			   struct xfs_inode *target_ip);
+			   struct xfs_inode *target_ip, unsigned int flags);
 
 void		xfs_ilock(xfs_inode_t *, uint);
 int		xfs_ilock_nowait(xfs_inode_t *, uint);
@@ -377,8 +377,18 @@ int		xfs_droplink(struct xfs_trans *, struct xfs_inode *);
 int		xfs_bumplink(struct xfs_trans *, struct xfs_inode *);
 
 /* from xfs_file.c */
-int		xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
-int		xfs_iozero(struct xfs_inode *, loff_t, size_t);
+enum xfs_prealloc_flags {
+	XFS_PREALLOC_SET	= (1 << 1),
+	XFS_PREALLOC_CLEAR	= (1 << 2),
+	XFS_PREALLOC_SYNC	= (1 << 3),
+	XFS_PREALLOC_INVISIBLE	= (1 << 4),
+};
+
+int	xfs_update_prealloc_flags(struct xfs_inode *ip,
+				  enum xfs_prealloc_flags flags);
+int	xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset,
+		     xfs_fsize_t isize, bool *did_zeroing);
+int	xfs_iozero(struct xfs_inode *ip, loff_t pos, size_t count);
 
 
 #define IHOLD(ip) \
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index a1831980a68e..ac4feae45eb3 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -39,6 +39,7 @@
 #include "xfs_icache.h"
 #include "xfs_symlink.h"
 #include "xfs_trans.h"
+#include "xfs_pnfs.h"
 
 #include <linux/capability.h>
 #include <linux/dcache.h>
@@ -286,7 +287,7 @@ xfs_readlink_by_handle(
 		return PTR_ERR(dentry);
 
 	/* Restrict this handle operation to symlinks only. */
-	if (!S_ISLNK(dentry->d_inode->i_mode)) {
+	if (!d_is_symlink(dentry)) {
 		error = -EINVAL;
 		goto out_dput;
 	}
@@ -606,11 +607,9 @@ xfs_ioc_space(
 	unsigned int		cmd,
 	xfs_flock64_t		*bf)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_trans	*tp;
 	struct iattr		iattr;
-	bool			setprealloc = false;
-	bool			clrprealloc = false;
+	enum xfs_prealloc_flags	flags = 0;
+	uint			iolock = XFS_IOLOCK_EXCL;
 	int			error;
 
 	/*
@@ -630,11 +629,19 @@ xfs_ioc_space(
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
 
+	if (filp->f_flags & O_DSYNC)
+		flags |= XFS_PREALLOC_SYNC;
+	if (ioflags & XFS_IO_INVIS)	
+		flags |= XFS_PREALLOC_INVISIBLE;
+
 	error = mnt_want_write_file(filp);
 	if (error)
 		return error;
 
-	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+	xfs_ilock(ip, iolock);
+	error = xfs_break_layouts(inode, &iolock);
+	if (error)
+		goto out_unlock;
 
 	switch (bf->l_whence) {
 	case 0: /*SEEK_SET*/
@@ -673,25 +680,23 @@ xfs_ioc_space(
 	}
 
 	if (bf->l_start < 0 ||
-	    bf->l_start > mp->m_super->s_maxbytes ||
+	    bf->l_start > inode->i_sb->s_maxbytes ||
 	    bf->l_start + bf->l_len < 0 ||
-	    bf->l_start + bf->l_len >= mp->m_super->s_maxbytes) {
+	    bf->l_start + bf->l_len >= inode->i_sb->s_maxbytes) {
 		error = -EINVAL;
 		goto out_unlock;
 	}
 
 	switch (cmd) {
 	case XFS_IOC_ZERO_RANGE:
+		flags |= XFS_PREALLOC_SET;
 		error = xfs_zero_file_space(ip, bf->l_start, bf->l_len);
-		if (!error)
-			setprealloc = true;
 		break;
 	case XFS_IOC_RESVSP:
 	case XFS_IOC_RESVSP64:
+		flags |= XFS_PREALLOC_SET;
 		error = xfs_alloc_file_space(ip, bf->l_start, bf->l_len,
 						XFS_BMAPI_PREALLOC);
-		if (!error)
-			setprealloc = true;
 		break;
 	case XFS_IOC_UNRESVSP:
 	case XFS_IOC_UNRESVSP64:
@@ -701,6 +706,7 @@ xfs_ioc_space(
 	case XFS_IOC_ALLOCSP64:
 	case XFS_IOC_FREESP:
 	case XFS_IOC_FREESP64:
+		flags |= XFS_PREALLOC_CLEAR;
 		if (bf->l_start > XFS_ISIZE(ip)) {
 			error = xfs_alloc_file_space(ip, XFS_ISIZE(ip),
 					bf->l_start - XFS_ISIZE(ip), 0);
@@ -712,8 +718,6 @@ xfs_ioc_space(
 		iattr.ia_size = bf->l_start;
 
 		error = xfs_setattr_size(ip, &iattr);
-		if (!error)
-			clrprealloc = true;
 		break;
 	default:
 		ASSERT(0);
@@ -723,35 +727,10 @@ xfs_ioc_space(
 	if (error)
 		goto out_unlock;
 
-	tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_writeid, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		goto out_unlock;
-	}
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-
-	if (!(ioflags & XFS_IO_INVIS)) {
-		ip->i_d.di_mode &= ~S_ISUID;
-		if (ip->i_d.di_mode & S_IXGRP)
-			ip->i_d.di_mode &= ~S_ISGID;
-		xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-	}
-
-	if (setprealloc)
-		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
-	else if (clrprealloc)
-		ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
-
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-	if (filp->f_flags & O_DSYNC)
-		xfs_trans_set_sync(tp);
-	error = xfs_trans_commit(tp, 0);
+	error = xfs_update_prealloc_flags(ip, flags);
 
 out_unlock:
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	xfs_iunlock(ip, iolock);
 	mnt_drop_write_file(filp);
 	return error;
 }
@@ -1013,20 +992,182 @@ xfs_diflags_to_linux(
 		inode->i_flags &= ~S_NOATIME;
 }
 
-#define FSX_PROJID	1
-#define FSX_EXTSIZE	2
-#define FSX_XFLAGS	4
-#define FSX_NONBLOCK	8
+static int
+xfs_ioctl_setattr_xflags(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	struct fsxattr		*fa)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	/* Can't change realtime flag if any extents are allocated. */
+	if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
+	    XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & XFS_XFLAG_REALTIME))
+		return -EINVAL;
+
+	/* If realtime flag is set then must have realtime device */
+	if (fa->fsx_xflags & XFS_XFLAG_REALTIME) {
+		if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 ||
+		    (ip->i_d.di_extsize % mp->m_sb.sb_rextsize))
+			return -EINVAL;
+	}
+
+	/*
+	 * Can't modify an immutable/append-only file unless
+	 * we have appropriate permission.
+	 */
+	if (((ip->i_d.di_flags & (XFS_DIFLAG_IMMUTABLE | XFS_DIFLAG_APPEND)) ||
+	     (fa->fsx_xflags & (XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) &&
+	    !capable(CAP_LINUX_IMMUTABLE))
+		return -EPERM;
+
+	xfs_set_diflags(ip, fa->fsx_xflags);
+	xfs_diflags_to_linux(ip);
+	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	XFS_STATS_INC(xs_ig_attrchg);
+	return 0;
+}
+
+/*
+ * Set up the transaction structure for the setattr operation, checking that we
+ * have permission to do so. On success, return a clean transaction and the
+ * inode locked exclusively ready for further operation specific checks. On
+ * failure, return an error without modifying or locking the inode.
+ */
+static struct xfs_trans *
+xfs_ioctl_setattr_get_trans(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			error;
+
+	if (mp->m_flags & XFS_MOUNT_RDONLY)
+		return ERR_PTR(-EROFS);
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return ERR_PTR(-EIO);
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
+	if (error)
+		goto out_cancel;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+	/*
+	 * CAP_FOWNER overrides the following restrictions:
+	 *
+	 * The user ID of the calling process must be equal to the file owner
+	 * ID, except in cases where the CAP_FSETID capability is applicable.
+	 */
+	if (!inode_owner_or_capable(VFS_I(ip))) {
+		error = -EPERM;
+		goto out_cancel;
+	}
+
+	if (mp->m_flags & XFS_MOUNT_WSYNC)
+		xfs_trans_set_sync(tp);
+
+	return tp;
+
+out_cancel:
+	xfs_trans_cancel(tp, 0);
+	return ERR_PTR(error);
+}
+
+/*
+ * extent size hint validation is somewhat cumbersome. Rules are:
+ *
+ * 1. extent size hint is only valid for directories and regular files
+ * 2. XFS_XFLAG_EXTSIZE is only valid for regular files
+ * 3. XFS_XFLAG_EXTSZINHERIT is only valid for directories.
+ * 4. can only be changed on regular files if no extents are allocated
+ * 5. can be changed on directories at any time
+ * 6. extsize hint of 0 turns off hints, clears inode flags.
+ * 7. Extent size must be a multiple of the appropriate block size.
+ * 8. for non-realtime files, the extent size hint must be limited
+ *    to half the AG size to avoid alignment extending the extent beyond the
+ *    limits of the AG.
+ */
+static int
+xfs_ioctl_setattr_check_extsize(
+	struct xfs_inode	*ip,
+	struct fsxattr		*fa)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if ((fa->fsx_xflags & XFS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode))
+		return -EINVAL;
+
+	if ((fa->fsx_xflags & XFS_XFLAG_EXTSZINHERIT) &&
+	    !S_ISDIR(ip->i_d.di_mode))
+		return -EINVAL;
+
+	if (S_ISREG(ip->i_d.di_mode) && ip->i_d.di_nextents &&
+	    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
+		return -EINVAL;
+
+	if (fa->fsx_extsize != 0) {
+		xfs_extlen_t    size;
+		xfs_fsblock_t   extsize_fsb;
+
+		extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
+		if (extsize_fsb > MAXEXTLEN)
+			return -EINVAL;
+
+		if (XFS_IS_REALTIME_INODE(ip) ||
+		    (fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
+			size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog;
+		} else {
+			size = mp->m_sb.sb_blocksize;
+			if (extsize_fsb > mp->m_sb.sb_agblocks / 2)
+				return -EINVAL;
+		}
+
+		if (fa->fsx_extsize % size)
+			return -EINVAL;
+	} else
+		fa->fsx_xflags &= ~(XFS_XFLAG_EXTSIZE | XFS_XFLAG_EXTSZINHERIT);
+
+	return 0;
+}
+
+static int
+xfs_ioctl_setattr_check_projid(
+	struct xfs_inode	*ip,
+	struct fsxattr		*fa)
+{
+	/* Disallow 32bit project ids if projid32bit feature is not enabled. */
+	if (fa->fsx_projid > (__uint16_t)-1 &&
+	    !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
+		return -EINVAL;
+
+	/*
+	 * Project Quota ID state is only allowed to change from within the init
+	 * namespace. Enforce that restriction only if we are trying to change
+	 * the quota ID state. Everything else is allowed in user namespaces.
+	 */
+	if (current_user_ns() == &init_user_ns)
+		return 0;
+
+	if (xfs_get_projid(ip) != fa->fsx_projid)
+		return -EINVAL;
+	if ((fa->fsx_xflags & XFS_XFLAG_PROJINHERIT) !=
+	    (ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT))
+		return -EINVAL;
+
+	return 0;
+}
 
 STATIC int
 xfs_ioctl_setattr(
 	xfs_inode_t		*ip,
-	struct fsxattr		*fa,
-	int			mask)
+	struct fsxattr		*fa)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
-	unsigned int		lock_flags = 0;
 	struct xfs_dquot	*udqp = NULL;
 	struct xfs_dquot	*pdqp = NULL;
 	struct xfs_dquot	*olddquot = NULL;
@@ -1034,17 +1175,9 @@ xfs_ioctl_setattr(
 
 	trace_xfs_ioctl_setattr(ip);
 
-	if (mp->m_flags & XFS_MOUNT_RDONLY)
-		return -EROFS;
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	/*
-	 * Disallow 32bit project ids when projid32bit feature is not enabled.
-	 */
-	if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1) &&
-			!xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
-		return -EINVAL;
+	code = xfs_ioctl_setattr_check_projid(ip, fa);
+	if (code)
+		return code;
 
 	/*
 	 * If disk quotas is on, we make sure that the dquots do exist on disk,
@@ -1054,7 +1187,7 @@ xfs_ioctl_setattr(
 	 * If the IDs do change before we take the ilock, we're covered
 	 * because the i_*dquot fields will get updated anyway.
 	 */
-	if (XFS_IS_QUOTA_ON(mp) && (mask & FSX_PROJID)) {
+	if (XFS_IS_QUOTA_ON(mp)) {
 		code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid,
 					 ip->i_d.di_gid, fa->fsx_projid,
 					 XFS_QMOPT_PQUOTA, &udqp, NULL, &pdqp);
@@ -1062,175 +1195,49 @@ xfs_ioctl_setattr(
 			return code;
 	}
 
-	/*
-	 * For the other attributes, we acquire the inode lock and
-	 * first do an error checking pass.
-	 */
-	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
-	code = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
-	if (code)
-		goto error_return;
-
-	lock_flags = XFS_ILOCK_EXCL;
-	xfs_ilock(ip, lock_flags);
-
-	/*
-	 * CAP_FOWNER overrides the following restrictions:
-	 *
-	 * The user ID of the calling process must be equal
-	 * to the file owner ID, except in cases where the
-	 * CAP_FSETID capability is applicable.
-	 */
-	if (!inode_owner_or_capable(VFS_I(ip))) {
-		code = -EPERM;
-		goto error_return;
-	}
-
-	/*
-	 * Do a quota reservation only if projid is actually going to change.
-	 * Only allow changing of projid from init_user_ns since it is a
-	 * non user namespace aware identifier.
-	 */
-	if (mask & FSX_PROJID) {
-		if (current_user_ns() != &init_user_ns) {
-			code = -EINVAL;
-			goto error_return;
-		}
-
-		if (XFS_IS_QUOTA_RUNNING(mp) &&
-		    XFS_IS_PQUOTA_ON(mp) &&
-		    xfs_get_projid(ip) != fa->fsx_projid) {
-			ASSERT(tp);
-			code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL,
-						pdqp, capable(CAP_FOWNER) ?
-						XFS_QMOPT_FORCE_RES : 0);
-			if (code)	/* out of quota */
-				goto error_return;
-		}
+	tp = xfs_ioctl_setattr_get_trans(ip);
+	if (IS_ERR(tp)) {
+		code = PTR_ERR(tp);
+		goto error_free_dquots;
 	}
 
-	if (mask & FSX_EXTSIZE) {
-		/*
-		 * Can't change extent size if any extents are allocated.
-		 */
-		if (ip->i_d.di_nextents &&
-		    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) !=
-		     fa->fsx_extsize)) {
-			code = -EINVAL;	/* EFBIG? */
-			goto error_return;
-		}
 
-		/*
-		 * Extent size must be a multiple of the appropriate block
-		 * size, if set at all. It must also be smaller than the
-		 * maximum extent size supported by the filesystem.
-		 *
-		 * Also, for non-realtime files, limit the extent size hint to
-		 * half the size of the AGs in the filesystem so alignment
-		 * doesn't result in extents larger than an AG.
-		 */
-		if (fa->fsx_extsize != 0) {
-			xfs_extlen_t    size;
-			xfs_fsblock_t   extsize_fsb;
-
-			extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
-			if (extsize_fsb > MAXEXTLEN) {
-				code = -EINVAL;
-				goto error_return;
-			}
-
-			if (XFS_IS_REALTIME_INODE(ip) ||
-			    ((mask & FSX_XFLAGS) &&
-			    (fa->fsx_xflags & XFS_XFLAG_REALTIME))) {
-				size = mp->m_sb.sb_rextsize <<
-				       mp->m_sb.sb_blocklog;
-			} else {
-				size = mp->m_sb.sb_blocksize;
-				if (extsize_fsb > mp->m_sb.sb_agblocks / 2) {
-					code = -EINVAL;
-					goto error_return;
-				}
-			}
-
-			if (fa->fsx_extsize % size) {
-				code = -EINVAL;
-				goto error_return;
-			}
-		}
+	if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) &&
+	    xfs_get_projid(ip) != fa->fsx_projid) {
+		code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, pdqp,
+				capable(CAP_FOWNER) ?  XFS_QMOPT_FORCE_RES : 0);
+		if (code)	/* out of quota */
+			goto error_trans_cancel;
 	}
 
+	code = xfs_ioctl_setattr_check_extsize(ip, fa);
+	if (code)
+		goto error_trans_cancel;
 
-	if (mask & FSX_XFLAGS) {
-		/*
-		 * Can't change realtime flag if any extents are allocated.
-		 */
-		if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
-		    (XFS_IS_REALTIME_INODE(ip)) !=
-		    (fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
-			code = -EINVAL;	/* EFBIG? */
-			goto error_return;
-		}
-
-		/*
-		 * If realtime flag is set then must have realtime data.
-		 */
-		if ((fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
-			if ((mp->m_sb.sb_rblocks == 0) ||
-			    (mp->m_sb.sb_rextsize == 0) ||
-			    (ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) {
-				code = -EINVAL;
-				goto error_return;
-			}
-		}
-
-		/*
-		 * Can't modify an immutable/append-only file unless
-		 * we have appropriate permission.
-		 */
-		if ((ip->i_d.di_flags &
-				(XFS_DIFLAG_IMMUTABLE|XFS_DIFLAG_APPEND) ||
-		     (fa->fsx_xflags &
-				(XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) &&
-		    !capable(CAP_LINUX_IMMUTABLE)) {
-			code = -EPERM;
-			goto error_return;
-		}
-	}
-
-	xfs_trans_ijoin(tp, ip, 0);
+	code = xfs_ioctl_setattr_xflags(tp, ip, fa);
+	if (code)
+		goto error_trans_cancel;
 
 	/*
-	 * Change file ownership.  Must be the owner or privileged.
+	 * Change file ownership.  Must be the owner or privileged.  CAP_FSETID
+	 * overrides the following restrictions:
+	 *
+	 * The set-user-ID and set-group-ID bits of a file will be cleared upon
+	 * successful return from chown()
 	 */
-	if (mask & FSX_PROJID) {
-		/*
-		 * CAP_FSETID overrides the following restrictions:
-		 *
-		 * The set-user-ID and set-group-ID bits of a file will be
-		 * cleared upon successful return from chown()
-		 */
-		if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
-		    !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
-			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
-
-		/*
-		 * Change the ownerships and register quota modifications
-		 * in the transaction.
-		 */
-		if (xfs_get_projid(ip) != fa->fsx_projid) {
-			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) {
-				olddquot = xfs_qm_vop_chown(tp, ip,
-							&ip->i_pdquot, pdqp);
-			}
-			ASSERT(ip->i_d.di_version > 1);
-			xfs_set_projid(ip, fa->fsx_projid);
-		}
 
-	}
+	if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
+	    !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
+		ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
 
-	if (mask & FSX_XFLAGS) {
-		xfs_set_diflags(ip, fa->fsx_xflags);
-		xfs_diflags_to_linux(ip);
+	/* Change the ownerships and register project quota modifications */
+	if (xfs_get_projid(ip) != fa->fsx_projid) {
+		if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) {
+			olddquot = xfs_qm_vop_chown(tp, ip,
+						&ip->i_pdquot, pdqp);
+		}
+		ASSERT(ip->i_d.di_version > 1);
+		xfs_set_projid(ip, fa->fsx_projid);
 	}
 
 	/*
@@ -1238,34 +1245,12 @@ xfs_ioctl_setattr(
 	 * extent size hint should be set on the inode. If no extent size flags
 	 * are set on the inode then unconditionally clear the extent size hint.
 	 */
-	if (mask & FSX_EXTSIZE) {
-		int	extsize = 0;
-
-		if (ip->i_d.di_flags &
-				(XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT))
-			extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
-		ip->i_d.di_extsize = extsize;
-	}
-
-	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
-	XFS_STATS_INC(xs_ig_attrchg);
+	if (ip->i_d.di_flags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT))
+		ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
+	else
+		ip->i_d.di_extsize = 0;
 
-	/*
-	 * If this is a synchronous mount, make sure that the
-	 * transaction goes to disk before returning to the user.
-	 * This is slightly sub-optimal in that truncates require
-	 * two sync transactions instead of one for wsync filesystems.
-	 * One for the truncate and one for the timestamps since we
-	 * don't want to change the timestamps unless we're sure the
-	 * truncate worked.  Truncates are less than 1% of the laddis
-	 * mix so this probably isn't worth the trouble to optimize.
-	 */
-	if (mp->m_flags & XFS_MOUNT_WSYNC)
-		xfs_trans_set_sync(tp);
 	code = xfs_trans_commit(tp, 0);
-	xfs_iunlock(ip, lock_flags);
 
 	/*
 	 * Release any dquot(s) the inode had kept before chown.
@@ -1276,12 +1261,11 @@ xfs_ioctl_setattr(
 
 	return code;
 
- error_return:
+error_trans_cancel:
+	xfs_trans_cancel(tp, 0);
+error_free_dquots:
 	xfs_qm_dqrele(udqp);
 	xfs_qm_dqrele(pdqp);
-	xfs_trans_cancel(tp, 0);
-	if (lock_flags)
-		xfs_iunlock(ip, lock_flags);
 	return code;
 }
 
@@ -1292,20 +1276,15 @@ xfs_ioc_fssetxattr(
 	void			__user *arg)
 {
 	struct fsxattr		fa;
-	unsigned int		mask;
 	int error;
 
 	if (copy_from_user(&fa, arg, sizeof(fa)))
 		return -EFAULT;
 
-	mask = FSX_XFLAGS | FSX_EXTSIZE | FSX_PROJID;
-	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
-		mask |= FSX_NONBLOCK;
-
 	error = mnt_want_write_file(filp);
 	if (error)
 		return error;
-	error = xfs_ioctl_setattr(ip, &fa, mask);
+	error = xfs_ioctl_setattr(ip, &fa);
 	mnt_drop_write_file(filp);
 	return error;
 }
@@ -1325,14 +1304,14 @@ xfs_ioc_getxflags(
 
 STATIC int
 xfs_ioc_setxflags(
-	xfs_inode_t		*ip,
+	struct xfs_inode	*ip,
 	struct file		*filp,
 	void			__user *arg)
 {
+	struct xfs_trans	*tp;
 	struct fsxattr		fa;
 	unsigned int		flags;
-	unsigned int		mask;
-	int error;
+	int			error;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
 		return -EFAULT;
@@ -1342,15 +1321,26 @@ xfs_ioc_setxflags(
 		      FS_SYNC_FL))
 		return -EOPNOTSUPP;
 
-	mask = FSX_XFLAGS;
-	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
-		mask |= FSX_NONBLOCK;
 	fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
 
 	error = mnt_want_write_file(filp);
 	if (error)
 		return error;
-	error = xfs_ioctl_setattr(ip, &fa, mask);
+
+	tp = xfs_ioctl_setattr_get_trans(ip);
+	if (IS_ERR(tp)) {
+		error = PTR_ERR(tp);
+		goto out_drop_write;
+	}
+
+	error = xfs_ioctl_setattr_xflags(tp, ip, &fa);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		goto out_drop_write;
+	}
+
+	error = xfs_trans_commit(tp, 0);
+out_drop_write:
 	mnt_drop_write_file(filp);
 	return error;
 }
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index ec6772866f3d..bfc7c7c8a0c8 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -423,7 +423,7 @@ xfs_compat_attrmulti_by_handle(
 
 	ops = memdup_user(compat_ptr(am_hreq.ops), size);
 	if (IS_ERR(ops)) {
-		error = -PTR_ERR(ops);
+		error = PTR_ERR(ops);
 		goto out_dput;
 	}
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index c980e2a5086b..ccb1dd0d509e 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -802,7 +802,7 @@ int
 xfs_iomap_write_unwritten(
 	xfs_inode_t	*ip,
 	xfs_off_t	offset,
-	size_t		count)
+	xfs_off_t	count)
 {
 	xfs_mount_t	*mp = ip->i_mount;
 	xfs_fileoff_t	offset_fsb;
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 411fbb8919ef..8688e663d744 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -27,6 +27,6 @@ int xfs_iomap_write_delay(struct xfs_inode *, xfs_off_t, size_t,
 			struct xfs_bmbt_irec *);
 int xfs_iomap_write_allocate(struct xfs_inode *, xfs_off_t,
 			struct xfs_bmbt_irec *);
-int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, size_t);
+int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t);
 
 #endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index c50311cae1b1..e53a90331422 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -37,6 +37,7 @@
 #include "xfs_da_btree.h"
 #include "xfs_dir2.h"
 #include "xfs_trans_space.h"
+#include "xfs_pnfs.h"
 
 #include <linux/capability.h>
 #include <linux/xattr.h>
@@ -380,18 +381,27 @@ xfs_vn_rename(
 	struct inode	*odir,
 	struct dentry	*odentry,
 	struct inode	*ndir,
-	struct dentry	*ndentry)
+	struct dentry	*ndentry,
+	unsigned int	flags)
 {
 	struct inode	*new_inode = ndentry->d_inode;
+	int		omode = 0;
 	struct xfs_name	oname;
 	struct xfs_name	nname;
 
-	xfs_dentry_to_name(&oname, odentry, 0);
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+		return -EINVAL;
+
+	/* if we are exchanging files, we need to set i_mode of both files */
+	if (flags & RENAME_EXCHANGE)
+		omode = ndentry->d_inode->i_mode;
+
+	xfs_dentry_to_name(&oname, odentry, omode);
 	xfs_dentry_to_name(&nname, ndentry, odentry->d_inode->i_mode);
 
 	return xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode),
-			  XFS_I(ndir), &nname, new_inode ?
-						XFS_I(new_inode) : NULL);
+			  XFS_I(ndir), &nname,
+			  new_inode ? XFS_I(new_inode) : NULL, flags);
 }
 
 /*
@@ -496,7 +506,7 @@ xfs_setattr_mode(
 	inode->i_mode |= mode & ~S_IFMT;
 }
 
-static void
+void
 xfs_setattr_time(
 	struct xfs_inode	*ip,
 	struct iattr		*iattr)
@@ -741,6 +751,7 @@ xfs_setattr_size(
 	int			error;
 	uint			lock_flags = 0;
 	uint			commit_flags = 0;
+	bool			did_zeroing = false;
 
 	trace_xfs_setattr(ip);
 
@@ -784,20 +795,16 @@ xfs_setattr_size(
 		return error;
 
 	/*
-	 * Now we can make the changes.  Before we join the inode to the
-	 * transaction, take care of the part of the truncation that must be
-	 * done without the inode lock.  This needs to be done before joining
-	 * the inode to the transaction, because the inode cannot be unlocked
-	 * once it is a part of the transaction.
+	 * File data changes must be complete before we start the transaction to
+	 * modify the inode.  This needs to be done before joining the inode to
+	 * the transaction because the inode cannot be unlocked once it is a
+	 * part of the transaction.
+	 *
+	 * Start with zeroing any data block beyond EOF that we may expose on
+	 * file extension.
 	 */
 	if (newsize > oldsize) {
-		/*
-		 * Do the first part of growing a file: zero any data in the
-		 * last block that is beyond the old EOF.  We need to do this
-		 * before the inode is joined to the transaction to modify
-		 * i_size.
-		 */
-		error = xfs_zero_eof(ip, newsize, oldsize);
+		error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
 		if (error)
 			return error;
 	}
@@ -807,23 +814,18 @@ xfs_setattr_size(
 	 * any previous writes that are beyond the on disk EOF and the new
 	 * EOF that have not been written out need to be written here.  If we
 	 * do not write the data out, we expose ourselves to the null files
-	 * problem.
-	 *
-	 * Only flush from the on disk size to the smaller of the in memory
-	 * file size or the new size as that's the range we really care about
-	 * here and prevents waiting for other data not within the range we
-	 * care about here.
+	 * problem. Note that this includes any block zeroing we did above;
+	 * otherwise those blocks may not be zeroed after a crash.
 	 */
-	if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
+	if (newsize > ip->i_d.di_size &&
+	    (oldsize != ip->i_d.di_size || did_zeroing)) {
 		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
 						      ip->i_d.di_size, newsize);
 		if (error)
 			return error;
 	}
 
-	/*
-	 * Wait for all direct I/O to complete.
-	 */
+	/* Now wait for all direct I/O to complete. */
 	inode_dio_wait(inode);
 
 	/*
@@ -970,9 +972,13 @@ xfs_vn_setattr(
 	int			error;
 
 	if (iattr->ia_valid & ATTR_SIZE) {
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-		error = xfs_setattr_size(ip, iattr);
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+		uint		iolock = XFS_IOLOCK_EXCL;
+
+		xfs_ilock(ip, iolock);
+		error = xfs_break_layouts(dentry->d_inode, &iolock);
+		if (!error)
+			error = xfs_setattr_size(ip, iattr);
+		xfs_iunlock(ip, iolock);
 	} else {
 		error = xfs_setattr_nonsize(ip, iattr, 0);
 	}
@@ -1144,7 +1150,7 @@ static const struct inode_operations xfs_dir_inode_operations = {
 	 */
 	.rmdir			= xfs_vn_unlink,
 	.mknod			= xfs_vn_mknod,
-	.rename			= xfs_vn_rename,
+	.rename2		= xfs_vn_rename,
 	.get_acl		= xfs_get_acl,
 	.set_acl		= xfs_set_acl,
 	.getattr		= xfs_vn_getattr,
@@ -1172,7 +1178,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = {
 	 */
 	.rmdir			= xfs_vn_unlink,
 	.mknod			= xfs_vn_mknod,
-	.rename			= xfs_vn_rename,
+	.rename2		= xfs_vn_rename,
 	.get_acl		= xfs_get_acl,
 	.set_acl		= xfs_set_acl,
 	.getattr		= xfs_vn_getattr,
diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h
index 1c34e4335920..ea7a98e9cb70 100644
--- a/fs/xfs/xfs_iops.h
+++ b/fs/xfs/xfs_iops.h
@@ -32,6 +32,7 @@ extern void xfs_setup_inode(struct xfs_inode *);
  */
 #define XFS_ATTR_NOACL		0x01	/* Don't call posix_acl_chmod */
 
+extern void xfs_setattr_time(struct xfs_inode *ip, struct iattr *iattr);
 extern int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap,
 			       int flags);
 extern int xfs_setattr_size(struct xfs_inode *ip, struct iattr *vap);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index e408bf5a3ff7..bcc7cfabb787 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -33,6 +33,7 @@
 #include "xfs_fsops.h"
 #include "xfs_cksum.h"
 #include "xfs_sysfs.h"
+#include "xfs_sb.h"
 
 kmem_zone_t	*xfs_log_ticket_zone;
 
@@ -1290,9 +1291,20 @@ xfs_log_worker(
 	struct xfs_mount	*mp = log->l_mp;
 
 	/* dgc: errors ignored - not fatal and nowhere to report them */
-	if (xfs_log_need_covered(mp))
-		xfs_fs_log_dummy(mp);
-	else
+	if (xfs_log_need_covered(mp)) {
+		/*
+		 * Dump a transaction into the log that contains no real change.
+		 * This is needed to stamp the current tail LSN into the log
+		 * during the covering operation.
+		 *
+		 * We cannot use an inode here for this - that will push dirty
+		 * state back up into the VFS and then periodic inode flushing
+		 * will prevent log covering from making progress. Hence we
+		 * synchronously log the superblock instead to ensure the
+		 * superblock is immediately unpinned and can be written back.
+		 */
+		xfs_sync_sb(mp, true);
+	} else
 		xfs_log_force(mp, 0);
 
 	/* start pushing all the metadata that is currently dirty */
@@ -1395,6 +1407,8 @@ xlog_alloc_log(
 	ASSERT(xfs_buf_islocked(bp));
 	xfs_buf_unlock(bp);
 
+	/* use high priority wq for log I/O completion */
+	bp->b_ioend_wq = mp->m_log_workqueue;
 	bp->b_iodone = xlog_iodone;
 	log->l_xbuf = bp;
 
@@ -1427,6 +1441,8 @@ xlog_alloc_log(
 		ASSERT(xfs_buf_islocked(bp));
 		xfs_buf_unlock(bp);
 
+		/* use high priority wq for log I/O completion */
+		bp->b_ioend_wq = mp->m_log_workqueue;
 		bp->b_iodone = xlog_iodone;
 		iclog->ic_bp = bp;
 		iclog->ic_data = bp->b_addr;
@@ -1806,8 +1822,6 @@ xlog_sync(
 	XFS_BUF_ZEROFLAGS(bp);
 	XFS_BUF_ASYNC(bp);
 	bp->b_flags |= XBF_SYNCIO;
-	/* use high priority completion wq */
-	bp->b_ioend_wq = log->l_mp->m_log_workqueue;
 
 	if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) {
 		bp->b_flags |= XBF_FUA;
@@ -1856,8 +1870,6 @@ xlog_sync(
 		bp->b_flags |= XBF_SYNCIO;
 		if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
 			bp->b_flags |= XBF_FUA;
-		/* use high priority completion wq */
-		bp->b_ioend_wq = log->l_mp->m_log_workqueue;
 
 		ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1);
 		ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize);
@@ -2027,7 +2039,7 @@ xlog_print_tic_res(
 		"  total reg   = %u bytes (o/flow = %u bytes)\n"
 		"  ophdrs      = %u (ophdr space = %u bytes)\n"
 		"  ophdr + reg = %u bytes\n"
-		"  num regions = %u\n",
+		"  num regions = %u",
 		((ticket->t_trans_type <= 0 ||
 		  ticket->t_trans_type > XFS_TRANS_TYPE_MAX) ?
 		  "bad-trans-type" : trans_type_str[ticket->t_trans_type-1]),
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index d3d38836f87f..4fa80e63eea2 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -408,11 +408,11 @@ xfs_update_alignment(xfs_mount_t *mp)
 		if (xfs_sb_version_hasdalign(sbp)) {
 			if (sbp->sb_unit != mp->m_dalign) {
 				sbp->sb_unit = mp->m_dalign;
-				mp->m_update_flags |= XFS_SB_UNIT;
+				mp->m_update_sb = true;
 			}
 			if (sbp->sb_width != mp->m_swidth) {
 				sbp->sb_width = mp->m_swidth;
-				mp->m_update_flags |= XFS_SB_WIDTH;
+				mp->m_update_sb = true;
 			}
 		} else {
 			xfs_warn(mp,
@@ -583,38 +583,19 @@ int
 xfs_mount_reset_sbqflags(
 	struct xfs_mount	*mp)
 {
-	int			error;
-	struct xfs_trans	*tp;
-
 	mp->m_qflags = 0;
 
-	/*
-	 * It is OK to look at sb_qflags here in mount path,
-	 * without m_sb_lock.
-	 */
+	/* It is OK to look at sb_qflags in the mount path without m_sb_lock. */
 	if (mp->m_sb.sb_qflags == 0)
 		return 0;
 	spin_lock(&mp->m_sb_lock);
 	mp->m_sb.sb_qflags = 0;
 	spin_unlock(&mp->m_sb_lock);
 
-	/*
-	 * If the fs is readonly, let the incore superblock run
-	 * with quotas off but don't flush the update out to disk
-	 */
-	if (mp->m_flags & XFS_MOUNT_RDONLY)
+	if (!xfs_fs_writable(mp, SB_FREEZE_WRITE))
 		return 0;
 
-	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_sbchange, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		xfs_alert(mp, "%s: Superblock update failed!", __func__);
-		return error;
-	}
-
-	xfs_mod_sb(tp, XFS_SB_QFLAGS);
-	return xfs_trans_commit(tp, 0);
+	return xfs_sync_sb(mp, false);
 }
 
 __uint64_t
@@ -659,26 +640,25 @@ xfs_mountfs(
 	xfs_sb_mount_common(mp, sbp);
 
 	/*
-	 * Check for a mismatched features2 values.  Older kernels
-	 * read & wrote into the wrong sb offset for sb_features2
-	 * on some platforms due to xfs_sb_t not being 64bit size aligned
-	 * when sb_features2 was added, which made older superblock
-	 * reading/writing routines swap it as a 64-bit value.
+	 * Check for a mismatched features2 values.  Older kernels read & wrote
+	 * into the wrong sb offset for sb_features2 on some platforms due to
+	 * xfs_sb_t not being 64bit size aligned when sb_features2 was added,
+	 * which made older superblock reading/writing routines swap it as a
+	 * 64-bit value.
 	 *
 	 * For backwards compatibility, we make both slots equal.
 	 *
-	 * If we detect a mismatched field, we OR the set bits into the
-	 * existing features2 field in case it has already been modified; we
-	 * don't want to lose any features.  We then update the bad location
-	 * with the ORed value so that older kernels will see any features2
-	 * flags, and mark the two fields as needing updates once the
-	 * transaction subsystem is online.
+	 * If we detect a mismatched field, we OR the set bits into the existing
+	 * features2 field in case it has already been modified; we don't want
+	 * to lose any features.  We then update the bad location with the ORed
+	 * value so that older kernels will see any features2 flags. The
+	 * superblock writeback code ensures the new sb_features2 is copied to
+	 * sb_bad_features2 before it is logged or written to disk.
 	 */
 	if (xfs_sb_has_mismatched_features2(sbp)) {
 		xfs_warn(mp, "correcting sb_features alignment problem");
 		sbp->sb_features2 |= sbp->sb_bad_features2;
-		sbp->sb_bad_features2 = sbp->sb_features2;
-		mp->m_update_flags |= XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2;
+		mp->m_update_sb = true;
 
 		/*
 		 * Re-check for ATTR2 in case it was found in bad_features2
@@ -692,17 +672,17 @@ xfs_mountfs(
 	if (xfs_sb_version_hasattr2(&mp->m_sb) &&
 	   (mp->m_flags & XFS_MOUNT_NOATTR2)) {
 		xfs_sb_version_removeattr2(&mp->m_sb);
-		mp->m_update_flags |= XFS_SB_FEATURES2;
+		mp->m_update_sb = true;
 
 		/* update sb_versionnum for the clearing of the morebits */
 		if (!sbp->sb_features2)
-			mp->m_update_flags |= XFS_SB_VERSIONNUM;
+			mp->m_update_sb = true;
 	}
 
 	/* always use v2 inodes by default now */
 	if (!(mp->m_sb.sb_versionnum & XFS_SB_VERSION_NLINKBIT)) {
 		mp->m_sb.sb_versionnum |= XFS_SB_VERSION_NLINKBIT;
-		mp->m_update_flags |= XFS_SB_VERSIONNUM;
+		mp->m_update_sb = true;
 	}
 
 	/*
@@ -895,8 +875,8 @@ xfs_mountfs(
 	 * the next remount into writeable mode.  Otherwise we would never
 	 * perform the update e.g. for the root filesystem.
 	 */
-	if (mp->m_update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY)) {
-		error = xfs_mount_log_sb(mp, mp->m_update_flags);
+	if (mp->m_update_sb && !(mp->m_flags & XFS_MOUNT_RDONLY)) {
+		error = xfs_sync_sb(mp, false);
 		if (error) {
 			xfs_warn(mp, "failed to write sb changes");
 			goto out_rtunmount;
@@ -1103,9 +1083,6 @@ xfs_fs_writable(
 int
 xfs_log_sbcount(xfs_mount_t *mp)
 {
-	xfs_trans_t	*tp;
-	int		error;
-
 	/* allow this to proceed during the freeze sequence... */
 	if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE))
 		return 0;
@@ -1119,17 +1096,7 @@ xfs_log_sbcount(xfs_mount_t *mp)
 	if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
 		return 0;
 
-	tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return error;
-	}
-
-	xfs_mod_sb(tp, XFS_SB_IFREE | XFS_SB_ICOUNT | XFS_SB_FDBLOCKS);
-	xfs_trans_set_sync(tp);
-	error = xfs_trans_commit(tp, 0);
-	return error;
+	return xfs_sync_sb(mp, true);
 }
 
 /*
@@ -1423,34 +1390,6 @@ xfs_freesb(
 }
 
 /*
- * Used to log changes to the superblock unit and width fields which could
- * be altered by the mount options, as well as any potential sb_features2
- * fixup. Only the first superblock is updated.
- */
-int
-xfs_mount_log_sb(
-	xfs_mount_t	*mp,
-	__int64_t	fields)
-{
-	xfs_trans_t	*tp;
-	int		error;
-
-	ASSERT(fields & (XFS_SB_UNIT | XFS_SB_WIDTH | XFS_SB_UUID |
-			 XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2 |
-			 XFS_SB_VERSIONNUM));
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return error;
-	}
-	xfs_mod_sb(tp, fields);
-	error = xfs_trans_commit(tp, 0);
-	return error;
-}
-
-/*
  * If the underlying (data/log/rt) device is readonly, there are some
  * operations that cannot proceed.
  */
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 22ccf69d4d3c..0d8abd6364d9 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -162,8 +162,7 @@ typedef struct xfs_mount {
 	struct delayed_work	m_reclaim_work;	/* background inode reclaim */
 	struct delayed_work	m_eofblocks_work; /* background eof blocks
 						     trimming */
-	__int64_t		m_update_flags;	/* sb flags we need to update
-						   on the next remount,rw */
+	bool			m_update_sb;	/* sb needs update in mount */
 	int64_t			m_low_space[XFS_LOWSP_MAX];
 						/* low free space thresholds */
 	struct xfs_kobj		m_kobj;
@@ -175,6 +174,17 @@ typedef struct xfs_mount {
 	struct workqueue_struct	*m_reclaim_workqueue;
 	struct workqueue_struct	*m_log_workqueue;
 	struct workqueue_struct *m_eofblocks_workqueue;
+
+	/*
+	 * Generation of the filesysyem layout.  This is incremented by each
+	 * growfs, and used by the pNFS server to ensure the client updates
+	 * its view of the block device once it gets a layout that might
+	 * reference the newly added blocks.  Does not need to be persistent
+	 * as long as we only allow file system size increments, but if we
+	 * ever support shrinks it would have to be persisted in addition
+	 * to various other kinds of pain inflicted on the pNFS server.
+	 */
+	__uint32_t		m_generation;
 } xfs_mount_t;
 
 /*
@@ -378,7 +388,7 @@ extern void	xfs_unmountfs(xfs_mount_t *);
 extern int	xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int);
 extern int	xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *,
 			uint, int);
-extern int	xfs_mount_log_sb(xfs_mount_t *, __int64_t);
+extern int	xfs_mount_log_sb(xfs_mount_t *);
 extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int);
 extern int	xfs_readsb(xfs_mount_t *, int);
 extern void	xfs_freesb(xfs_mount_t *);
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
new file mode 100644
index 000000000000..365dd57ea760
--- /dev/null
+++ b/fs/xfs/xfs_pnfs.c
@@ -0,0 +1,324 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include "xfs.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_trans.h"
+#include "xfs_log.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_error.h"
+#include "xfs_iomap.h"
+#include "xfs_shared.h"
+#include "xfs_bit.h"
+#include "xfs_pnfs.h"
+
+/*
+ * Ensure that we do not have any outstanding pNFS layouts that can be used by
+ * clients to directly read from or write to this inode.  This must be called
+ * before every operation that can remove blocks from the extent map.
+ * Additionally we call it during the write operation, where aren't concerned
+ * about exposing unallocated blocks but just want to provide basic
+ * synchronization between a local writer and pNFS clients.  mmap writes would
+ * also benefit from this sort of synchronization, but due to the tricky locking
+ * rules in the page fault path we don't bother.
+ */
+int
+xfs_break_layouts(
+	struct inode		*inode,
+	uint			*iolock)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	int			error;
+
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
+
+	while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
+		xfs_iunlock(ip, *iolock);
+		error = break_layout(inode, true);
+		*iolock = XFS_IOLOCK_EXCL;
+		xfs_ilock(ip, *iolock);
+	}
+
+	return error;
+}
+
+/*
+ * Get a unique ID including its location so that the client can identify
+ * the exported device.
+ */
+int
+xfs_fs_get_uuid(
+	struct super_block	*sb,
+	u8			*buf,
+	u32			*len,
+	u64			*offset)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	printk_once(KERN_NOTICE
+"XFS (%s): using experimental pNFS feature, use at your own risk!\n",
+		mp->m_fsname);
+
+	if (*len < sizeof(uuid_t))
+		return -EINVAL;
+
+	memcpy(buf, &mp->m_sb.sb_uuid, sizeof(uuid_t));
+	*len = sizeof(uuid_t);
+	*offset = offsetof(struct xfs_dsb, sb_uuid);
+	return 0;
+}
+
+static void
+xfs_bmbt_to_iomap(
+	struct xfs_inode	*ip,
+	struct iomap		*iomap,
+	struct xfs_bmbt_irec	*imap)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (imap->br_startblock == HOLESTARTBLOCK) {
+		iomap->blkno = IOMAP_NULL_BLOCK;
+		iomap->type = IOMAP_HOLE;
+	} else if (imap->br_startblock == DELAYSTARTBLOCK) {
+		iomap->blkno = IOMAP_NULL_BLOCK;
+		iomap->type = IOMAP_DELALLOC;
+	} else {
+		iomap->blkno =
+			XFS_FSB_TO_DADDR(ip->i_mount, imap->br_startblock);
+		if (imap->br_state == XFS_EXT_UNWRITTEN)
+			iomap->type = IOMAP_UNWRITTEN;
+		else
+			iomap->type = IOMAP_MAPPED;
+	}
+	iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
+	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
+}
+
+/*
+ * Get a layout for the pNFS client.
+ */
+int
+xfs_fs_map_blocks(
+	struct inode		*inode,
+	loff_t			offset,
+	u64			length,
+	struct iomap		*iomap,
+	bool			write,
+	u32			*device_generation)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_bmbt_irec	imap;
+	xfs_fileoff_t		offset_fsb, end_fsb;
+	loff_t			limit;
+	int			bmapi_flags = XFS_BMAPI_ENTIRE;
+	int			nimaps = 1;
+	uint			lock_flags;
+	int			error = 0;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
+	/*
+	 * We can't export inodes residing on the realtime device.  The realtime
+	 * device doesn't have a UUID to identify it, so the client has no way
+	 * to find it.
+	 */
+	if (XFS_IS_REALTIME_INODE(ip))
+		return -ENXIO;
+
+	/*
+	 * Lock out any other I/O before we flush and invalidate the pagecache,
+	 * and then hand out a layout to the remote system.  This is very
+	 * similar to direct I/O, except that the synchronization is much more
+	 * complicated.  See the comment near xfs_break_layouts for a detailed
+	 * explanation.
+	 */
+	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+	error = -EINVAL;
+	limit = mp->m_super->s_maxbytes;
+	if (!write)
+		limit = max(limit, round_up(i_size_read(inode),
+				     inode->i_sb->s_blocksize));
+	if (offset > limit)
+		goto out_unlock;
+	if (offset > limit - length)
+		length = limit - offset;
+
+	error = filemap_write_and_wait(inode->i_mapping);
+	if (error)
+		goto out_unlock;
+	error = invalidate_inode_pages2(inode->i_mapping);
+	if (WARN_ON_ONCE(error))
+		return error;
+
+	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
+	offset_fsb = XFS_B_TO_FSBT(mp, offset);
+
+	lock_flags = xfs_ilock_data_map_shared(ip);
+	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
+				&imap, &nimaps, bmapi_flags);
+	xfs_iunlock(ip, lock_flags);
+
+	if (error)
+		goto out_unlock;
+
+	if (write) {
+		enum xfs_prealloc_flags	flags = 0;
+
+		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+
+		if (!nimaps || imap.br_startblock == HOLESTARTBLOCK) {
+			error = xfs_iomap_write_direct(ip, offset, length,
+						       &imap, nimaps);
+			if (error)
+				goto out_unlock;
+
+			/*
+			 * Ensure the next transaction is committed
+			 * synchronously so that the blocks allocated and
+			 * handed out to the client are guaranteed to be
+			 * present even after a server crash.
+			 */
+			flags |= XFS_PREALLOC_SET | XFS_PREALLOC_SYNC;
+		}
+
+		error = xfs_update_prealloc_flags(ip, flags);
+		if (error)
+			goto out_unlock;
+	}
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+
+	xfs_bmbt_to_iomap(ip, iomap, &imap);
+	*device_generation = mp->m_generation;
+	return error;
+out_unlock:
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	return error;
+}
+
+/*
+ * Ensure the size update falls into a valid allocated block.
+ */
+static int
+xfs_pnfs_validate_isize(
+	struct xfs_inode	*ip,
+	xfs_off_t		isize)
+{
+	struct xfs_bmbt_irec	imap;
+	int			nimaps = 1;
+	int			error = 0;
+
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	error = xfs_bmapi_read(ip, XFS_B_TO_FSBT(ip->i_mount, isize - 1), 1,
+				&imap, &nimaps, 0);
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	if (error)
+		return error;
+
+	if (imap.br_startblock == HOLESTARTBLOCK ||
+	    imap.br_startblock == DELAYSTARTBLOCK ||
+	    imap.br_state == XFS_EXT_UNWRITTEN)
+		return -EIO;
+	return 0;
+}
+
+/*
+ * Make sure the blocks described by maps are stable on disk.  This includes
+ * converting any unwritten extents, flushing the disk cache and updating the
+ * time stamps.
+ *
+ * Note that we rely on the caller to always send us a timestamp update so that
+ * we always commit a transaction here.  If that stops being true we will have
+ * to manually flush the cache here similar to what the fsync code path does
+ * for datasyncs on files that have no dirty metadata.
+ */
+int
+xfs_fs_commit_blocks(
+	struct inode		*inode,
+	struct iomap		*maps,
+	int			nr_maps,
+	struct iattr		*iattr)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	bool			update_isize = false;
+	int			error, i;
+	loff_t			size;
+
+	ASSERT(iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME));
+
+	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+	size = i_size_read(inode);
+	if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size > size) {
+		update_isize = true;
+		size = iattr->ia_size;
+	}
+
+	for (i = 0; i < nr_maps; i++) {
+		u64 start, length, end;
+
+		start = maps[i].offset;
+		if (start > size)
+			continue;
+
+		end = start + maps[i].length;
+		if (end > size)
+			end = size;
+
+		length = end - start;
+		if (!length)
+			continue;
+	
+		/*
+		 * Make sure reads through the pagecache see the new data.
+		 */
+		error = invalidate_inode_pages2_range(inode->i_mapping,
+					start >> PAGE_CACHE_SHIFT,
+					(end - 1) >> PAGE_CACHE_SHIFT);
+		WARN_ON_ONCE(error);
+
+		error = xfs_iomap_write_unwritten(ip, start, length);
+		if (error)
+			goto out_drop_iolock;
+	}
+
+	if (update_isize) {
+		error = xfs_pnfs_validate_isize(ip, size);
+		if (error)
+			goto out_drop_iolock;
+	}
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		goto out_drop_iolock;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	xfs_setattr_time(ip, iattr);
+	if (update_isize) {
+		i_size_write(inode, iattr->ia_size);
+		ip->i_d.di_size = iattr->ia_size;
+	}
+
+	xfs_trans_set_sync(tp);
+	error = xfs_trans_commit(tp, 0);
+
+out_drop_iolock:
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	return error;
+}
diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h
new file mode 100644
index 000000000000..b7fbfce660f6
--- /dev/null
+++ b/fs/xfs/xfs_pnfs.h
@@ -0,0 +1,18 @@
+#ifndef _XFS_PNFS_H
+#define _XFS_PNFS_H 1
+
+#ifdef CONFIG_NFSD_PNFS
+int xfs_fs_get_uuid(struct super_block *sb, u8 *buf, u32 *len, u64 *offset);
+int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length,
+		struct iomap *iomap, bool write, u32 *device_generation);
+int xfs_fs_commit_blocks(struct inode *inode, struct iomap *maps, int nr_maps,
+		struct iattr *iattr);
+
+int xfs_break_layouts(struct inode *inode, uint *iolock);
+#else
+static inline int xfs_break_layouts(struct inode *inode, uint *iolock)
+{
+	return 0;
+}
+#endif /* CONFIG_NFSD_PNFS */
+#endif /* _XFS_PNFS_H */
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 79fb19dd9c83..fbbb9e62e274 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -430,6 +430,7 @@ struct xfs_qm_isolate {
 static enum lru_status
 xfs_qm_dquot_isolate(
 	struct list_head	*item,
+	struct list_lru_one	*lru,
 	spinlock_t		*lru_lock,
 	void			*arg)
 		__releases(lru_lock) __acquires(lru_lock)
@@ -450,7 +451,7 @@ xfs_qm_dquot_isolate(
 		XFS_STATS_INC(xs_qm_dqwants);
 
 		trace_xfs_dqreclaim_want(dqp);
-		list_del_init(&dqp->q_lru);
+		list_lru_isolate(lru, &dqp->q_lru);
 		XFS_STATS_DEC(xs_qm_dquot_unused);
 		return LRU_REMOVED;
 	}
@@ -494,7 +495,7 @@ xfs_qm_dquot_isolate(
 	xfs_dqunlock(dqp);
 
 	ASSERT(dqp->q_nrefs == 0);
-	list_move_tail(&dqp->q_lru, &isol->dispose);
+	list_lru_isolate_move(lru, &dqp->q_lru, &isol->dispose);
 	XFS_STATS_DEC(xs_qm_dquot_unused);
 	trace_xfs_dqreclaim_done(dqp);
 	XFS_STATS_INC(xs_qm_dqreclaims);
@@ -523,7 +524,6 @@ xfs_qm_shrink_scan(
 	struct xfs_qm_isolate	isol;
 	unsigned long		freed;
 	int			error;
-	unsigned long		nr_to_scan = sc->nr_to_scan;
 
 	if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
 		return 0;
@@ -531,8 +531,8 @@ xfs_qm_shrink_scan(
 	INIT_LIST_HEAD(&isol.buffers);
 	INIT_LIST_HEAD(&isol.dispose);
 
-	freed = list_lru_walk_node(&qi->qi_lru, sc->nid, xfs_qm_dquot_isolate, &isol,
-					&nr_to_scan);
+	freed = list_lru_shrink_walk(&qi->qi_lru, sc,
+				     xfs_qm_dquot_isolate, &isol);
 
 	error = xfs_buf_delwri_submit(&isol.buffers);
 	if (error)
@@ -557,7 +557,7 @@ xfs_qm_shrink_count(
 	struct xfs_quotainfo	*qi = container_of(shrink,
 					struct xfs_quotainfo, qi_shrinker);
 
-	return list_lru_count_node(&qi->qi_lru, sc->nid);
+	return list_lru_shrink_count(&qi->qi_lru, sc);
 }
 
 /*
@@ -714,7 +714,6 @@ STATIC int
 xfs_qm_qino_alloc(
 	xfs_mount_t	*mp,
 	xfs_inode_t	**ip,
-	__int64_t	sbfields,
 	uint		flags)
 {
 	xfs_trans_t	*tp;
@@ -777,11 +776,6 @@ xfs_qm_qino_alloc(
 	spin_lock(&mp->m_sb_lock);
 	if (flags & XFS_QMOPT_SBVERSION) {
 		ASSERT(!xfs_sb_version_hasquota(&mp->m_sb));
-		ASSERT((sbfields & (XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO |
-			XFS_SB_GQUOTINO | XFS_SB_PQUOTINO | XFS_SB_QFLAGS)) ==
-				(XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO |
-				 XFS_SB_GQUOTINO | XFS_SB_PQUOTINO |
-				 XFS_SB_QFLAGS));
 
 		xfs_sb_version_addquota(&mp->m_sb);
 		mp->m_sb.sb_uquotino = NULLFSINO;
@@ -798,7 +792,7 @@ xfs_qm_qino_alloc(
 	else
 		mp->m_sb.sb_pquotino = (*ip)->i_ino;
 	spin_unlock(&mp->m_sb_lock);
-	xfs_mod_sb(tp, sbfields);
+	xfs_log_sb(tp);
 
 	if ((error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES))) {
 		xfs_alert(mp, "%s failed (error %d)!", __func__, error);
@@ -842,6 +836,11 @@ xfs_qm_reset_dqcounts(
 		 */
 		xfs_dqcheck(mp, ddq, id+j, type, XFS_QMOPT_DQREPAIR,
 			    "xfs_quotacheck");
+		/*
+		 * Reset type in case we are reusing group quota file for
+		 * project quotas or vice versa
+		 */
+		ddq->d_flags = type;
 		ddq->d_bcount = 0;
 		ddq->d_icount = 0;
 		ddq->d_rtbcount = 0;
@@ -1451,7 +1450,7 @@ xfs_qm_mount_quotas(
 	spin_unlock(&mp->m_sb_lock);
 
 	if (sbf != (mp->m_qflags & XFS_MOUNT_QUOTA_ALL)) {
-		if (xfs_qm_write_sb_changes(mp, XFS_SB_QFLAGS)) {
+		if (xfs_sync_sb(mp, false)) {
 			/*
 			 * We could only have been turning quotas off.
 			 * We aren't in very good shape actually because
@@ -1482,7 +1481,6 @@ xfs_qm_init_quotainos(
 	struct xfs_inode	*gip = NULL;
 	struct xfs_inode	*pip = NULL;
 	int			error;
-	__int64_t		sbflags = 0;
 	uint			flags = 0;
 
 	ASSERT(mp->m_quotainfo);
@@ -1517,9 +1515,6 @@ xfs_qm_init_quotainos(
 		}
 	} else {
 		flags |= XFS_QMOPT_SBVERSION;
-		sbflags |= (XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO |
-			    XFS_SB_GQUOTINO | XFS_SB_PQUOTINO |
-			    XFS_SB_QFLAGS);
 	}
 
 	/*
@@ -1530,7 +1525,6 @@ xfs_qm_init_quotainos(
 	 */
 	if (XFS_IS_UQUOTA_ON(mp) && uip == NULL) {
 		error = xfs_qm_qino_alloc(mp, &uip,
-					      sbflags | XFS_SB_UQUOTINO,
 					      flags | XFS_QMOPT_UQUOTA);
 		if (error)
 			goto error_rele;
@@ -1539,7 +1533,6 @@ xfs_qm_init_quotainos(
 	}
 	if (XFS_IS_GQUOTA_ON(mp) && gip == NULL) {
 		error = xfs_qm_qino_alloc(mp, &gip,
-					  sbflags | XFS_SB_GQUOTINO,
 					  flags | XFS_QMOPT_GQUOTA);
 		if (error)
 			goto error_rele;
@@ -1548,7 +1541,6 @@ xfs_qm_init_quotainos(
 	}
 	if (XFS_IS_PQUOTA_ON(mp) && pip == NULL) {
 		error = xfs_qm_qino_alloc(mp, &pip,
-					  sbflags | XFS_SB_PQUOTINO,
 					  flags | XFS_QMOPT_PQUOTA);
 		if (error)
 			goto error_rele;
@@ -1587,32 +1579,6 @@ xfs_qm_dqfree_one(
 	xfs_qm_dqdestroy(dqp);
 }
 
-/*
- * Start a transaction and write the incore superblock changes to
- * disk. flags parameter indicates which fields have changed.
- */
-int
-xfs_qm_write_sb_changes(
-	xfs_mount_t	*mp,
-	__int64_t	flags)
-{
-	xfs_trans_t	*tp;
-	int		error;
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_sbchange, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return error;
-	}
-
-	xfs_mod_sb(tp, flags);
-	error = xfs_trans_commit(tp, 0);
-
-	return error;
-}
-
-
 /* --------------- utility functions for vnodeops ---------------- */
 
 
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 41f6c0b9d51c..0d4d3590cf85 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -157,7 +157,6 @@ struct xfs_dquot_acct {
 #define XFS_QM_RTBWARNLIMIT	5
 
 extern void		xfs_qm_destroy_quotainfo(struct xfs_mount *);
-extern int		xfs_qm_write_sb_changes(struct xfs_mount *, __int64_t);
 
 /* dquot stuff */
 extern void		xfs_qm_dqpurge_all(struct xfs_mount *, uint);
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index cb6168ec92c9..9b965db45800 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -91,8 +91,7 @@ xfs_qm_scall_quotaoff(
 		mutex_unlock(&q->qi_quotaofflock);
 
 		/* XXX what to do if error ? Revert back to old vals incore ? */
-		error = xfs_qm_write_sb_changes(mp, XFS_SB_QFLAGS);
-		return error;
+		return xfs_sync_sb(mp, false);
 	}
 
 	dqtype = 0;
@@ -313,7 +312,6 @@ xfs_qm_scall_quotaon(
 {
 	int		error;
 	uint		qf;
-	__int64_t	sbflags;
 
 	flags &= (XFS_ALL_QUOTA_ACCT | XFS_ALL_QUOTA_ENFD);
 	/*
@@ -321,30 +319,22 @@ xfs_qm_scall_quotaon(
 	 */
 	flags &= ~(XFS_ALL_QUOTA_ACCT);
 
-	sbflags = 0;
-
 	if (flags == 0) {
 		xfs_debug(mp, "%s: zero flags, m_qflags=%x",
 			__func__, mp->m_qflags);
 		return -EINVAL;
 	}
 
-	/* No fs can turn on quotas with a delayed effect */
-	ASSERT((flags & XFS_ALL_QUOTA_ACCT) == 0);
-
 	/*
 	 * Can't enforce without accounting. We check the superblock
 	 * qflags here instead of m_qflags because rootfs can have
 	 * quota acct on ondisk without m_qflags' knowing.
 	 */
-	if (((flags & XFS_UQUOTA_ACCT) == 0 &&
-	     (mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) == 0 &&
+	if (((mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) == 0 &&
 	     (flags & XFS_UQUOTA_ENFD)) ||
-	    ((flags & XFS_GQUOTA_ACCT) == 0 &&
-	     (mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 &&
+	    ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 &&
 	     (flags & XFS_GQUOTA_ENFD)) ||
-	    ((flags & XFS_PQUOTA_ACCT) == 0 &&
-	     (mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 &&
+	    ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 &&
 	     (flags & XFS_PQUOTA_ENFD))) {
 		xfs_debug(mp,
 			"%s: Can't enforce without acct, flags=%x sbflags=%x",
@@ -369,11 +359,11 @@ xfs_qm_scall_quotaon(
 	/*
 	 * There's nothing to change if it's the same.
 	 */
-	if ((qf & flags) == flags && sbflags == 0)
+	if ((qf & flags) == flags)
 		return -EEXIST;
-	sbflags |= XFS_SB_QFLAGS;
 
-	if ((error = xfs_qm_write_sb_changes(mp, sbflags)))
+	error = xfs_sync_sb(mp, false);
+	if (error)
 		return error;
 	/*
 	 * If we aren't trying to switch on quota enforcement, we are done.
@@ -383,8 +373,7 @@ xfs_qm_scall_quotaon(
 	     ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) !=
 	     (mp->m_qflags & XFS_PQUOTA_ACCT)) ||
 	     ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) !=
-	     (mp->m_qflags & XFS_GQUOTA_ACCT)) ||
-	    (flags & XFS_ALL_QUOTA_ENFD) == 0)
+	     (mp->m_qflags & XFS_GQUOTA_ACCT)))
 		return 0;
 
 	if (! XFS_IS_QUOTA_RUNNING(mp))
@@ -421,20 +410,12 @@ xfs_qm_scall_getqstat(
 	memset(out, 0, sizeof(fs_quota_stat_t));
 
 	out->qs_version = FS_QSTAT_VERSION;
-	if (!xfs_sb_version_hasquota(&mp->m_sb)) {
-		out->qs_uquota.qfs_ino = NULLFSINO;
-		out->qs_gquota.qfs_ino = NULLFSINO;
-		return 0;
-	}
-
 	out->qs_flags = (__uint16_t) xfs_qm_export_flags(mp->m_qflags &
 							(XFS_ALL_QUOTA_ACCT|
 							 XFS_ALL_QUOTA_ENFD));
-	if (q) {
-		uip = q->qi_uquotaip;
-		gip = q->qi_gquotaip;
-		pip = q->qi_pquotaip;
-	}
+	uip = q->qi_uquotaip;
+	gip = q->qi_gquotaip;
+	pip = q->qi_pquotaip;
 	if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) {
 		if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino,
 					0, 0, &uip) == 0)
@@ -480,14 +461,13 @@ xfs_qm_scall_getqstat(
 		if (temppqip)
 			IRELE(pip);
 	}
-	if (q) {
-		out->qs_incoredqs = q->qi_dquots;
-		out->qs_btimelimit = q->qi_btimelimit;
-		out->qs_itimelimit = q->qi_itimelimit;
-		out->qs_rtbtimelimit = q->qi_rtbtimelimit;
-		out->qs_bwarnlimit = q->qi_bwarnlimit;
-		out->qs_iwarnlimit = q->qi_iwarnlimit;
-	}
+	out->qs_incoredqs = q->qi_dquots;
+	out->qs_btimelimit = q->qi_btimelimit;
+	out->qs_itimelimit = q->qi_itimelimit;
+	out->qs_rtbtimelimit = q->qi_rtbtimelimit;
+	out->qs_bwarnlimit = q->qi_bwarnlimit;
+	out->qs_iwarnlimit = q->qi_iwarnlimit;
+
 	return 0;
 }
 
@@ -508,13 +488,6 @@ xfs_qm_scall_getqstatv(
 	bool                    tempgqip = false;
 	bool                    temppqip = false;
 
-	if (!xfs_sb_version_hasquota(&mp->m_sb)) {
-		out->qs_uquota.qfs_ino = NULLFSINO;
-		out->qs_gquota.qfs_ino = NULLFSINO;
-		out->qs_pquota.qfs_ino = NULLFSINO;
-		return 0;
-	}
-
 	out->qs_flags = (__uint16_t) xfs_qm_export_flags(mp->m_qflags &
 							(XFS_ALL_QUOTA_ACCT|
 							 XFS_ALL_QUOTA_ENFD));
@@ -522,11 +495,9 @@ xfs_qm_scall_getqstatv(
 	out->qs_gquota.qfs_ino = mp->m_sb.sb_gquotino;
 	out->qs_pquota.qfs_ino = mp->m_sb.sb_pquotino;
 
-	if (q) {
-		uip = q->qi_uquotaip;
-		gip = q->qi_gquotaip;
-		pip = q->qi_pquotaip;
-	}
+	uip = q->qi_uquotaip;
+	gip = q->qi_gquotaip;
+	pip = q->qi_pquotaip;
 	if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) {
 		if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino,
 					0, 0, &uip) == 0)
@@ -561,14 +532,13 @@ xfs_qm_scall_getqstatv(
 		if (temppqip)
 			IRELE(pip);
 	}
-	if (q) {
-		out->qs_incoredqs = q->qi_dquots;
-		out->qs_btimelimit = q->qi_btimelimit;
-		out->qs_itimelimit = q->qi_itimelimit;
-		out->qs_rtbtimelimit = q->qi_rtbtimelimit;
-		out->qs_bwarnlimit = q->qi_bwarnlimit;
-		out->qs_iwarnlimit = q->qi_iwarnlimit;
-	}
+	out->qs_incoredqs = q->qi_dquots;
+	out->qs_btimelimit = q->qi_btimelimit;
+	out->qs_itimelimit = q->qi_itimelimit;
+	out->qs_rtbtimelimit = q->qi_rtbtimelimit;
+	out->qs_bwarnlimit = q->qi_bwarnlimit;
+	out->qs_iwarnlimit = q->qi_iwarnlimit;
+
 	return 0;
 }
 
@@ -800,7 +770,7 @@ xfs_qm_log_quotaoff(
 	mp->m_sb.sb_qflags = (mp->m_qflags & ~(flags)) & XFS_MOUNT_QUOTA_ALL;
 	spin_unlock(&mp->m_sb_lock);
 
-	xfs_mod_sb(tp, XFS_SB_QFLAGS);
+	xfs_log_sb(tp);
 
 	/*
 	 * We have to make sure that the transaction is secure on disk before we
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index 801a84c1cdc3..6923905ab33d 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -64,19 +64,10 @@ xfs_fs_get_xstatev(
 	return xfs_qm_scall_getqstatv(mp, fqs);
 }
 
-STATIC int
-xfs_fs_set_xstate(
-	struct super_block	*sb,
-	unsigned int		uflags,
-	int			op)
+static unsigned int
+xfs_quota_flags(unsigned int uflags)
 {
-	struct xfs_mount	*mp = XFS_M(sb);
-	unsigned int		flags = 0;
-
-	if (sb->s_flags & MS_RDONLY)
-		return -EROFS;
-	if (op != Q_XQUOTARM && !XFS_IS_QUOTA_RUNNING(mp))
-		return -ENOSYS;
+	unsigned int flags = 0;
 
 	if (uflags & FS_QUOTA_UDQ_ACCT)
 		flags |= XFS_UQUOTA_ACCT;
@@ -91,16 +82,39 @@ xfs_fs_set_xstate(
 	if (uflags & FS_QUOTA_PDQ_ENFD)
 		flags |= XFS_PQUOTA_ENFD;
 
-	switch (op) {
-	case Q_XQUOTAON:
-		return xfs_qm_scall_quotaon(mp, flags);
-	case Q_XQUOTAOFF:
-		if (!XFS_IS_QUOTA_ON(mp))
-			return -EINVAL;
-		return xfs_qm_scall_quotaoff(mp, flags);
-	}
+	return flags;
+}
+
+STATIC int
+xfs_quota_enable(
+	struct super_block	*sb,
+	unsigned int		uflags)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (sb->s_flags & MS_RDONLY)
+		return -EROFS;
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+
+	return xfs_qm_scall_quotaon(mp, xfs_quota_flags(uflags));
+}
+
+STATIC int
+xfs_quota_disable(
+	struct super_block	*sb,
+	unsigned int		uflags)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (sb->s_flags & MS_RDONLY)
+		return -EROFS;
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -EINVAL;
 
-	return -EINVAL;
+	return xfs_qm_scall_quotaoff(mp, xfs_quota_flags(uflags));
 }
 
 STATIC int
@@ -166,7 +180,8 @@ xfs_fs_set_dqblk(
 const struct quotactl_ops xfs_quotactl_operations = {
 	.get_xstatev		= xfs_fs_get_xstatev,
 	.get_xstate		= xfs_fs_get_xstate,
-	.set_xstate		= xfs_fs_set_xstate,
+	.quota_enable		= xfs_quota_enable,
+	.quota_disable		= xfs_quota_disable,
 	.rm_xquota		= xfs_fs_rm_xquota,
 	.get_dqblk		= xfs_fs_get_dqblk,
 	.set_dqblk		= xfs_fs_set_dqblk,
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 19cbda196369..8fcc4ccc5c79 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -685,7 +685,7 @@ xfs_blkdev_get(
 				    mp);
 	if (IS_ERR(*bdevp)) {
 		error = PTR_ERR(*bdevp);
-		xfs_warn(mp, "Invalid device [%s], error=%d\n", name, error);
+		xfs_warn(mp, "Invalid device [%s], error=%d", name, error);
 	}
 
 	return error;
@@ -1111,6 +1111,11 @@ xfs_fs_statfs(
 					statp->f_files,
 					mp->m_maxicount);
 
+	/* If sb_icount overshot maxicount, report actual allocation */
+	statp->f_files = max_t(typeof(statp->f_files),
+					statp->f_files,
+					sbp->sb_icount);
+
 	/* make sure statp->f_ffree does not underflow */
 	ffree = statp->f_files - (sbp->sb_icount - sbp->sb_ifree);
 	statp->f_ffree = max_t(__int64_t, ffree, 0);
@@ -1257,13 +1262,13 @@ xfs_fs_remount(
 		 * If this is the first remount to writeable state we
 		 * might have some superblock changes to update.
 		 */
-		if (mp->m_update_flags) {
-			error = xfs_mount_log_sb(mp, mp->m_update_flags);
+		if (mp->m_update_sb) {
+			error = xfs_sync_sb(mp, false);
 			if (error) {
 				xfs_warn(mp, "failed to write sb changes");
 				return error;
 			}
-			mp->m_update_flags = 0;
+			mp->m_update_sb = false;
 		}
 
 		/*
@@ -1293,8 +1298,9 @@ xfs_fs_remount(
 
 /*
  * Second stage of a freeze. The data is already frozen so we only
- * need to take care of the metadata. Once that's done write a dummy
- * record to dirty the log in case of a crash while frozen.
+ * need to take care of the metadata. Once that's done sync the superblock
+ * to the log to dirty it in case of a crash while frozen. This ensures that we
+ * will recover the unlinked inode lists on the next mount.
  */
 STATIC int
 xfs_fs_freeze(
@@ -1304,7 +1310,7 @@ xfs_fs_freeze(
 
 	xfs_save_resvblks(mp);
 	xfs_quiesce_attr(mp);
-	return xfs_fs_log_dummy(mp);
+	return xfs_sync_sb(mp, true);
 }
 
 STATIC int
@@ -1531,7 +1537,7 @@ xfs_fs_mount(
 static long
 xfs_fs_nr_cached_objects(
 	struct super_block	*sb,
-	int			nid)
+	struct shrink_control	*sc)
 {
 	return xfs_reclaim_inodes_count(XFS_M(sb));
 }
@@ -1539,10 +1545,9 @@ xfs_fs_nr_cached_objects(
 static long
 xfs_fs_free_cached_objects(
 	struct super_block	*sb,
-	long			nr_to_scan,
-	int			nid)
+	struct shrink_control	*sc)
 {
-	return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
+	return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan);
 }
 
 static const struct super_operations xfs_super_operations = {
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index 1743b9f8e23d..a0c8067cea6f 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -149,24 +149,6 @@ static struct ctl_table xfs_table[] = {
 		.extra2		= &xfs_params.inherit_noatim.max
 	},
 	{
-		.procname	= "xfsbufd_centisecs",
-		.data		= &xfs_params.xfs_buf_timer.val,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &xfs_params.xfs_buf_timer.min,
-		.extra2		= &xfs_params.xfs_buf_timer.max
-	},
-	{
-		.procname	= "age_buffer_centisecs",
-		.data		= &xfs_params.xfs_buf_age.val,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &xfs_params.xfs_buf_age.min,
-		.extra2		= &xfs_params.xfs_buf_age.max
-	},
-	{
 		.procname	= "inherit_nosymlinks",
 		.data		= &xfs_params.inherit_nosym.val,
 		.maxlen		= sizeof(int),
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index fa3135b9bf04..eb90cd59a0ec 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -472,6 +472,7 @@ xfs_trans_apply_sb_deltas(
 		whole = 1;
 	}
 
+	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
 	if (whole)
 		/*
 		 * Log the whole thing, the fields are noncontiguous.
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 0a4d4ab6d9a9..75798412859a 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -327,9 +327,10 @@ xfs_trans_read_buf_map(
 		return -EIO;
 	}
 
-	if (tp)
+	if (tp) {
 		_xfs_trans_bjoin(tp, bp, 1);
-	trace_xfs_trans_read_buf(bp->b_fspriv);
+		trace_xfs_trans_read_buf(bp->b_fspriv);
+	}
 	*bpp = bp;
 	return 0;