Merge tag 'for-v4.6-rc/omap-fixes-a' of git://git.kernel.org/pub/scm/linux/kernel/git/pjw/omap-pending into omap-for-v4.6/fixes

ARM: OMAP2+: first hwmod fix for v4.6-rc Fix a longstanding bug in the hwmod code that could cause hardware SYSCONFIG register values to not match the kernel's idea of what they should be, and that could result in lower performance during IP block idle entry. Basic build, boot, and PM test logs are available here: http://www.pwsan.com/omap/testlogs/omap-hwmod-fixes-a-for-v4.6-rc/20160326231727/
author: Tony Lindgren <tony@atomide.com> 2016-03-30 10:36:06 -0700
committer: Tony Lindgren <tony@atomide.com> 2016-03-30 10:36:06 -0700
commit: 1809de7e7d37c585e01a1bcc583ea92b78fc759d (patch)
tree: 76c5b35c2b04eafce86a1a729c02ab705eba44bc /fs
parent: ARM: OMAP2+: Use srst_udelay for USB on dm814x (diff)
parent: ARM: OMAP2+: hwmod: Fix updating of sysconfig register (diff)
download: wireguard-linux-1809de7e7d37c585e01a1bcc583ea92b78fc759d.tar.xz
wireguard-linux-1809de7e7d37c585e01a1bcc583ea92b78fc759d.zip
404 files changed, 24835 insertions, 9951 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index 9adee0d7536e..6725f59c18e6 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -84,6 +84,8 @@ config MANDATORY_FILE_LOCKING
 
 	  To the best of my knowledge this is dead code that no one cares about.
 
+source "fs/crypto/Kconfig"
+
 source "fs/notify/Kconfig"
 
 source "fs/quota/Kconfig"
@@ -207,6 +209,7 @@ menuconfig MISC_FILESYSTEMS
 
 if MISC_FILESYSTEMS
 
+source "fs/orangefs/Kconfig"
 source "fs/adfs/Kconfig"
 source "fs/affs/Kconfig"
 source "fs/ecryptfs/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index 79f522575cba..85b6e13b62d3 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -30,6 +30,7 @@ obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_USERFAULTFD)	+= userfaultfd.o
 obj-$(CONFIG_AIO)               += aio.o
 obj-$(CONFIG_FS_DAX)		+= dax.o
+obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o
@@ -105,6 +106,7 @@ obj-$(CONFIG_AUTOFS4_FS)	+= autofs4/
 obj-$(CONFIG_ADFS_FS)		+= adfs/
 obj-$(CONFIG_FUSE_FS)		+= fuse/
 obj-$(CONFIG_OVERLAY_FS)	+= overlayfs/
+obj-$(CONFIG_ORANGEFS_FS)       += orangefs/
 obj-$(CONFIG_UDF_FS)		+= udf/
 obj-$(CONFIG_SUN_OPENPROMFS)	+= openpromfs/
 obj-$(CONFIG_OMFS_FS)		+= omfs/
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 0548c53f41d5..22fc7c802d69 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -511,8 +511,6 @@ affs_do_readpage_ofs(struct page *page, unsigned to)
 	pr_debug("%s(%lu, %ld, 0, %d)\n", __func__, inode->i_ino,
 		 page->index, to);
 	BUG_ON(to > PAGE_CACHE_SIZE);
-	kmap(page);
-	data = page_address(page);
 	bsize = AFFS_SB(sb)->s_data_blksize;
 	tmp = page->index << PAGE_CACHE_SHIFT;
 	bidx = tmp / bsize;
@@ -524,14 +522,15 @@ affs_do_readpage_ofs(struct page *page, unsigned to)
 			return PTR_ERR(bh);
 		tmp = min(bsize - boff, to - pos);
 		BUG_ON(pos + tmp > to || tmp > bsize);
+		data = kmap_atomic(page);
 		memcpy(data + pos, AFFS_DATA(bh) + boff, tmp);
+		kunmap_atomic(data);
 		affs_brelse(bh);
 		bidx++;
 		pos += tmp;
 		boff = 0;
 	}
 	flush_dcache_page(page);
-	kunmap(page);
 	return 0;
 }
 
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index c37149b929be..f0d268b97d19 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -1,15 +1,11 @@
-/* -*- c -*- ------------------------------------------------------------- *
- *   
- * linux/fs/autofs/autofs_i.h
- *
- *   Copyright 1997-1998 Transmeta Corporation - All Rights Reserved
- *   Copyright 2005-2006 Ian Kent <raven@themaw.net>
+/*
+ *  Copyright 1997-1998 Transmeta Corporation - All Rights Reserved
+ *  Copyright 2005-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
+ */
 
 /* Internal header file for autofs */
 
@@ -35,28 +31,23 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <asm/current.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* #define DEBUG */
 
-#define DPRINTK(fmt, ...)				\
-	pr_debug("pid %d: %s: " fmt "\n",		\
-		current->pid, __func__, ##__VA_ARGS__)
-
-#define AUTOFS_WARN(fmt, ...)				\
-	printk(KERN_WARNING "pid %d: %s: " fmt "\n",	\
-		current->pid, __func__, ##__VA_ARGS__)
-
-#define AUTOFS_ERROR(fmt, ...)				\
-	printk(KERN_ERR "pid %d: %s: " fmt "\n",	\
-		current->pid, __func__, ##__VA_ARGS__)
-
-/* Unified info structure.  This is pointed to by both the dentry and
-   inode structures.  Each file in the filesystem has an instance of this
-   structure.  It holds a reference to the dentry, so dentries are never
-   flushed while the file exists.  All name lookups are dealt with at the
-   dentry level, although the filesystem can interfere in the validation
-   process.  Readdir is implemented by traversing the dentry lists. */
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+#define pr_fmt(fmt) KBUILD_MODNAME ":pid:%d:%s: " fmt, current->pid, __func__
+
+/*
+ * Unified info structure.  This is pointed to by both the dentry and
+ * inode structures.  Each file in the filesystem has an instance of this
+ * structure.  It holds a reference to the dentry, so dentries are never
+ * flushed while the file exists.  All name lookups are dealt with at the
+ * dentry level, although the filesystem can interfere in the validation
+ * process.  Readdir is implemented by traversing the dentry lists.
+ */
 struct autofs_info {
 	struct dentry	*dentry;
 	struct inode	*inode;
@@ -78,7 +69,7 @@ struct autofs_info {
 	kgid_t gid;
 };
 
-#define AUTOFS_INF_EXPIRING	(1<<0) /* dentry is in the process of expiring */
+#define AUTOFS_INF_EXPIRING	(1<<0) /* dentry in the process of expiring */
 #define AUTOFS_INF_NO_RCU	(1<<1) /* the dentry is being considered
 					* for expiry, so RCU_walk is
 					* not permitted
@@ -140,10 +131,11 @@ static inline struct autofs_info *autofs4_dentry_ino(struct dentry *dentry)
 }
 
 /* autofs4_oz_mode(): do we see the man behind the curtain?  (The
-   processes which do manipulations for us in user space sees the raw
-   filesystem without "magic".) */
-
-static inline int autofs4_oz_mode(struct autofs_sb_info *sbi) {
+ * processes which do manipulations for us in user space sees the raw
+ * filesystem without "magic".)
+ */
+static inline int autofs4_oz_mode(struct autofs_sb_info *sbi)
+{
 	return sbi->catatonic || task_pgrp(current) == sbi->oz_pgrp;
 }
 
@@ -154,12 +146,12 @@ void autofs4_free_ino(struct autofs_info *);
 int is_autofs4_dentry(struct dentry *);
 int autofs4_expire_wait(struct dentry *dentry, int rcu_walk);
 int autofs4_expire_run(struct super_block *, struct vfsmount *,
-			struct autofs_sb_info *,
-			struct autofs_packet_expire __user *);
+		       struct autofs_sb_info *,
+		       struct autofs_packet_expire __user *);
 int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 			    struct autofs_sb_info *sbi, int when);
 int autofs4_expire_multi(struct super_block *, struct vfsmount *,
-			struct autofs_sb_info *, int __user *);
+			 struct autofs_sb_info *, int __user *);
 struct dentry *autofs4_expire_direct(struct super_block *sb,
 				     struct vfsmount *mnt,
 				     struct autofs_sb_info *sbi, int how);
@@ -224,8 +216,8 @@ static inline int autofs_prepare_pipe(struct file *pipe)
 
 /* Queue management functions */
 
-int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify);
-int autofs4_wait_release(struct autofs_sb_info *,autofs_wqt_t,int);
+int autofs4_wait(struct autofs_sb_info *, struct dentry *, enum autofs_notify);
+int autofs4_wait_release(struct autofs_sb_info *, autofs_wqt_t, int);
 void autofs4_catatonic_mode(struct autofs_sb_info *);
 
 static inline u32 autofs4_get_dev(struct autofs_sb_info *sbi)
@@ -242,37 +234,37 @@ static inline void __autofs4_add_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+
 	if (ino) {
 		if (list_empty(&ino->expiring))
 			list_add(&ino->expiring, &sbi->expiring_list);
 	}
-	return;
 }
 
 static inline void autofs4_add_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		if (list_empty(&ino->expiring))
 			list_add(&ino->expiring, &sbi->expiring_list);
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 static inline void autofs4_del_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		if (!list_empty(&ino->expiring))
 			list_del_init(&ino->expiring);
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 extern void autofs4_kill_sb(struct super_block *);
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index ac7d921ed984..c7fcc7438843 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -72,13 +72,13 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param)
 {
 	int err = 0;
 
-	if ((AUTOFS_DEV_IOCTL_VERSION_MAJOR != param->ver_major) ||
-	    (AUTOFS_DEV_IOCTL_VERSION_MINOR < param->ver_minor)) {
-		AUTOFS_WARN("ioctl control interface version mismatch: "
-		     "kernel(%u.%u), user(%u.%u), cmd(%d)",
-		     AUTOFS_DEV_IOCTL_VERSION_MAJOR,
-		     AUTOFS_DEV_IOCTL_VERSION_MINOR,
-		     param->ver_major, param->ver_minor, cmd);
+	if ((param->ver_major != AUTOFS_DEV_IOCTL_VERSION_MAJOR) ||
+	    (param->ver_minor > AUTOFS_DEV_IOCTL_VERSION_MINOR)) {
+		pr_warn("ioctl control interface version mismatch: "
+			"kernel(%u.%u), user(%u.%u), cmd(%d)\n",
+			AUTOFS_DEV_IOCTL_VERSION_MAJOR,
+			AUTOFS_DEV_IOCTL_VERSION_MINOR,
+			param->ver_major, param->ver_minor, cmd);
 		err = -EINVAL;
 	}
 
@@ -93,7 +93,8 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param)
  * Copy parameter control struct, including a possible path allocated
  * at the end of the struct.
  */
-static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in)
+static struct autofs_dev_ioctl *
+		copy_dev_ioctl(struct autofs_dev_ioctl __user *in)
 {
 	struct autofs_dev_ioctl tmp, *res;
 
@@ -116,7 +117,6 @@ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *i
 static inline void free_dev_ioctl(struct autofs_dev_ioctl *param)
 {
 	kfree(param);
-	return;
 }
 
 /*
@@ -129,24 +129,24 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
 
 	err = check_dev_ioctl_version(cmd, param);
 	if (err) {
-		AUTOFS_WARN("invalid device control module version "
-		     "supplied for cmd(0x%08x)", cmd);
+		pr_warn("invalid device control module version "
+			"supplied for cmd(0x%08x)\n", cmd);
 		goto out;
 	}
 
 	if (param->size > sizeof(*param)) {
 		err = invalid_str(param->path, param->size - sizeof(*param));
 		if (err) {
-			AUTOFS_WARN(
-			  "path string terminator missing for cmd(0x%08x)",
+			pr_warn(
+			  "path string terminator missing for cmd(0x%08x)\n",
 			  cmd);
 			goto out;
 		}
 
 		err = check_name(param->path);
 		if (err) {
-			AUTOFS_WARN("invalid path supplied for cmd(0x%08x)",
-				    cmd);
+			pr_warn("invalid path supplied for cmd(0x%08x)\n",
+				cmd);
 			goto out;
 		}
 	}
@@ -197,7 +197,9 @@ static int find_autofs_mount(const char *pathname,
 			     void *data)
 {
 	struct path path;
-	int err = kern_path_mountpoint(AT_FDCWD, pathname, &path, 0);
+	int err;
+
+	err = kern_path_mountpoint(AT_FDCWD, pathname, &path, 0);
 	if (err)
 		return err;
 	err = -ENOENT;
@@ -225,6 +227,7 @@ static int test_by_dev(struct path *path, void *p)
 static int test_by_type(struct path *path, void *p)
 {
 	struct autofs_info *ino = autofs4_dentry_ino(path->dentry);
+
 	return ino && ino->sbi->type & *(unsigned *)p;
 }
 
@@ -370,7 +373,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,
 		new_pid = get_task_pid(current, PIDTYPE_PGID);
 
 		if (ns_of_pid(new_pid) != ns_of_pid(sbi->oz_pgrp)) {
-			AUTOFS_WARN("Not allowed to change PID namespace");
+			pr_warn("not allowed to change PID namespace\n");
 			err = -EINVAL;
 			goto out;
 		}
@@ -456,8 +459,10 @@ static int autofs_dev_ioctl_requester(struct file *fp,
 		err = 0;
 		autofs4_expire_wait(path.dentry, 0);
 		spin_lock(&sbi->fs_lock);
-		param->requester.uid = from_kuid_munged(current_user_ns(), ino->uid);
-		param->requester.gid = from_kgid_munged(current_user_ns(), ino->gid);
+		param->requester.uid =
+			from_kuid_munged(current_user_ns(), ino->uid);
+		param->requester.gid =
+			from_kgid_munged(current_user_ns(), ino->gid);
 		spin_unlock(&sbi->fs_lock);
 	}
 	path_put(&path);
@@ -619,7 +624,8 @@ static ioctl_fn lookup_dev_ioctl(unsigned int cmd)
 }
 
 /* ioctl dispatcher */
-static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __user *user)
+static int _autofs_dev_ioctl(unsigned int command,
+			     struct autofs_dev_ioctl __user *user)
 {
 	struct autofs_dev_ioctl *param;
 	struct file *fp;
@@ -655,7 +661,7 @@ static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __use
 
 	fn = lookup_dev_ioctl(cmd);
 	if (!fn) {
-		AUTOFS_WARN("unknown command 0x%08x", command);
+		pr_warn("unknown command 0x%08x\n", command);
 		return -ENOTTY;
 	}
 
@@ -711,6 +717,7 @@ out:
 static long autofs_dev_ioctl(struct file *file, uint command, ulong u)
 {
 	int err;
+
 	err = _autofs_dev_ioctl(command, (struct autofs_dev_ioctl __user *) u);
 	return (long) err;
 }
@@ -733,8 +740,8 @@ static const struct file_operations _dev_ioctl_fops = {
 
 static struct miscdevice _autofs_dev_ioctl_misc = {
 	.minor		= AUTOFS_MINOR,
-	.name  		= AUTOFS_DEVICE_NAME,
-	.fops  		= &_dev_ioctl_fops
+	.name		= AUTOFS_DEVICE_NAME,
+	.fops		= &_dev_ioctl_fops
 };
 
 MODULE_ALIAS_MISCDEV(AUTOFS_MINOR);
@@ -747,7 +754,7 @@ int __init autofs_dev_ioctl_init(void)
 
 	r = misc_register(&_autofs_dev_ioctl_misc);
 	if (r) {
-		AUTOFS_ERROR("misc_register failed for control device");
+		pr_err("misc_register failed for control device\n");
 		return r;
 	}
 
@@ -757,6 +764,4 @@ int __init autofs_dev_ioctl_init(void)
 void autofs_dev_ioctl_exit(void)
 {
 	misc_deregister(&_autofs_dev_ioctl_misc);
-	return;
 }
-
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 1cebc3c52fa5..9510d8d2e9cd 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -1,16 +1,12 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/expire.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
- *  Copyright 2001-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
+ * Copyright 2001-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include "autofs_i.h"
 
@@ -18,7 +14,7 @@ static unsigned long now;
 
 /* Check if a dentry can be expired */
 static inline int autofs4_can_expire(struct dentry *dentry,
-					unsigned long timeout, int do_now)
+				     unsigned long timeout, int do_now)
 {
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 
@@ -41,7 +37,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 	struct path path = {.mnt = mnt, .dentry = dentry};
 	int status = 1;
 
-	DPRINTK("dentry %p %pd", dentry, dentry);
+	pr_debug("dentry %p %pd\n", dentry, dentry);
 
 	path_get(&path);
 
@@ -58,14 +54,16 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 
 	/* Update the expiry counter if fs is busy */
 	if (!may_umount_tree(path.mnt)) {
-		struct autofs_info *ino = autofs4_dentry_ino(top);
+		struct autofs_info *ino;
+
+		ino = autofs4_dentry_ino(top);
 		ino->last_used = jiffies;
 		goto done;
 	}
 
 	status = 0;
 done:
-	DPRINTK("returning = %d", status);
+	pr_debug("returning = %d\n", status);
 	path_put(&path);
 	return status;
 }
@@ -74,7 +72,7 @@ done:
  * Calculate and dget next entry in the subdirs list under root.
  */
 static struct dentry *get_next_positive_subdir(struct dentry *prev,
-						struct dentry *root)
+					       struct dentry *root)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb);
 	struct list_head *next;
@@ -121,7 +119,7 @@ cont:
  * Calculate and dget next entry in top down tree traversal.
  */
 static struct dentry *get_next_positive_dentry(struct dentry *prev,
-						struct dentry *root)
+					       struct dentry *root)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb);
 	struct list_head *next;
@@ -187,15 +185,17 @@ again:
  * autofs submounts.
  */
 static int autofs4_direct_busy(struct vfsmount *mnt,
-				struct dentry *top,
-				unsigned long timeout,
-				int do_now)
+			       struct dentry *top,
+			       unsigned long timeout,
+			       int do_now)
 {
-	DPRINTK("top %p %pd", top, top);
+	pr_debug("top %p %pd\n", top, top);
 
 	/* If it's busy update the expiry counters */
 	if (!may_umount_tree(mnt)) {
-		struct autofs_info *ino = autofs4_dentry_ino(top);
+		struct autofs_info *ino;
+
+		ino = autofs4_dentry_ino(top);
 		if (ino)
 			ino->last_used = jiffies;
 		return 1;
@@ -208,7 +208,8 @@ static int autofs4_direct_busy(struct vfsmount *mnt,
 	return 0;
 }
 
-/* Check a directory tree of mount points for busyness
+/*
+ * Check a directory tree of mount points for busyness
  * The tree is not busy iff no mountpoints are busy
  */
 static int autofs4_tree_busy(struct vfsmount *mnt,
@@ -219,7 +220,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
 	struct autofs_info *top_ino = autofs4_dentry_ino(top);
 	struct dentry *p;
 
-	DPRINTK("top %p %pd", top, top);
+	pr_debug("top %p %pd\n", top, top);
 
 	/* Negative dentry - give up */
 	if (!simple_positive(top))
@@ -227,7 +228,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
 
 	p = NULL;
 	while ((p = get_next_positive_dentry(p, top))) {
-		DPRINTK("dentry %p %pd", p, p);
+		pr_debug("dentry %p %pd\n", p, p);
 
 		/*
 		 * Is someone visiting anywhere in the subtree ?
@@ -273,11 +274,11 @@ static struct dentry *autofs4_check_leaves(struct vfsmount *mnt,
 {
 	struct dentry *p;
 
-	DPRINTK("parent %p %pd", parent, parent);
+	pr_debug("parent %p %pd\n", parent, parent);
 
 	p = NULL;
 	while ((p = get_next_positive_dentry(p, parent))) {
-		DPRINTK("dentry %p %pd", p, p);
+		pr_debug("dentry %p %pd\n", p, p);
 
 		if (d_mountpoint(p)) {
 			/* Can we umount this guy */
@@ -362,7 +363,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	 *	   offset (autofs-5.0+).
 	 */
 	if (d_mountpoint(dentry)) {
-		DPRINTK("checking mountpoint %p %pd", dentry, dentry);
+		pr_debug("checking mountpoint %p %pd\n", dentry, dentry);
 
 		/* Can we umount this guy */
 		if (autofs4_mount_busy(mnt, dentry))
@@ -375,7 +376,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	}
 
 	if (d_really_is_positive(dentry) && d_is_symlink(dentry)) {
-		DPRINTK("checking symlink %p %pd", dentry, dentry);
+		pr_debug("checking symlink %p %pd\n", dentry, dentry);
 		/*
 		 * A symlink can't be "busy" in the usual sense so
 		 * just check last used for expire timeout.
@@ -404,6 +405,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	} else {
 		/* Path walk currently on this dentry? */
 		struct dentry *expired;
+
 		ino_count = atomic_read(&ino->count) + 1;
 		if (d_count(dentry) > ino_count)
 			return NULL;
@@ -471,7 +473,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	return NULL;
 
 found:
-	DPRINTK("returning %p %pd", expired, expired);
+	pr_debug("returning %p %pd\n", expired, expired);
 	ino->flags |= AUTOFS_INF_EXPIRING;
 	smp_mb();
 	ino->flags &= ~AUTOFS_INF_NO_RCU;
@@ -503,12 +505,12 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 	if (ino->flags & AUTOFS_INF_EXPIRING) {
 		spin_unlock(&sbi->fs_lock);
 
-		DPRINTK("waiting for expire %p name=%pd", dentry, dentry);
+		pr_debug("waiting for expire %p name=%pd\n", dentry, dentry);
 
 		status = autofs4_wait(sbi, dentry, NFY_NONE);
 		wait_for_completion(&ino->expire_complete);
 
-		DPRINTK("expire done status=%d", status);
+		pr_debug("expire done status=%d\n", status);
 
 		if (d_unhashed(dentry))
 			return -EAGAIN;
@@ -522,21 +524,22 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 
 /* Perform an expiry operation */
 int autofs4_expire_run(struct super_block *sb,
-		      struct vfsmount *mnt,
-		      struct autofs_sb_info *sbi,
-		      struct autofs_packet_expire __user *pkt_p)
+		       struct vfsmount *mnt,
+		       struct autofs_sb_info *sbi,
+		       struct autofs_packet_expire __user *pkt_p)
 {
 	struct autofs_packet_expire pkt;
 	struct autofs_info *ino;
 	struct dentry *dentry;
 	int ret = 0;
 
-	memset(&pkt,0,sizeof pkt);
+	memset(&pkt, 0, sizeof(pkt));
 
 	pkt.hdr.proto_version = sbi->version;
 	pkt.hdr.type = autofs_ptype_expire;
 
-	if ((dentry = autofs4_expire_indirect(sb, mnt, sbi, 0)) == NULL)
+	dentry = autofs4_expire_indirect(sb, mnt, sbi, 0);
+	if (!dentry)
 		return -EAGAIN;
 
 	pkt.len = dentry->d_name.len;
@@ -544,7 +547,7 @@ int autofs4_expire_run(struct super_block *sb,
 	pkt.name[pkt.len] = '\0';
 	dput(dentry);
 
-	if ( copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)) )
+	if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)))
 		ret = -EFAULT;
 
 	spin_lock(&sbi->fs_lock);
@@ -573,7 +576,8 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 		struct autofs_info *ino = autofs4_dentry_ino(dentry);
 
 		/* This is synchronous because it makes the daemon a
-                   little easier */
+		 * little easier
+		 */
 		ret = autofs4_wait(sbi, dentry, NFY_EXPIRE);
 
 		spin_lock(&sbi->fs_lock);
@@ -588,8 +592,10 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 	return ret;
 }
 
-/* Call repeatedly until it returns -EAGAIN, meaning there's nothing
-   more to be done */
+/*
+ * Call repeatedly until it returns -EAGAIN, meaning there's nothing
+ * more to be done.
+ */
 int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 			struct autofs_sb_info *sbi, int __user *arg)
 {
diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c
index b3db517e89ec..8cf0e63389ae 100644
--- a/fs/autofs4/init.c
+++ b/fs/autofs4/init.c
@@ -1,14 +1,10 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/init.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index a3ae0b2aeb5a..61b21051bd5a 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -1,15 +1,11 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/inode.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 2005-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 2005-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -24,7 +20,9 @@
 
 struct autofs_info *autofs4_new_ino(struct autofs_sb_info *sbi)
 {
-	struct autofs_info *ino = kzalloc(sizeof(*ino), GFP_KERNEL);
+	struct autofs_info *ino;
+
+	ino = kzalloc(sizeof(*ino), GFP_KERNEL);
 	if (ino) {
 		INIT_LIST_HEAD(&ino->active);
 		INIT_LIST_HEAD(&ino->expiring);
@@ -62,7 +60,7 @@ void autofs4_kill_sb(struct super_block *sb)
 		put_pid(sbi->oz_pgrp);
 	}
 
-	DPRINTK("shutting down");
+	pr_debug("shutting down\n");
 	kill_litter_super(sb);
 	if (sbi)
 		kfree_rcu(sbi, rcu);
@@ -94,7 +92,12 @@ static int autofs4_show_options(struct seq_file *m, struct dentry *root)
 		seq_printf(m, ",direct");
 	else
 		seq_printf(m, ",indirect");
-
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	if (sbi->pipe)
+		seq_printf(m, ",pipe_ino=%ld", sbi->pipe->f_inode->i_ino);
+	else
+		seq_printf(m, ",pipe_ino=-1");
+#endif
 	return 0;
 }
 
@@ -147,6 +150,7 @@ static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid,
 
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
+
 		if (!*p)
 			continue;
 
@@ -204,9 +208,9 @@ static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid,
 
 int autofs4_fill_super(struct super_block *s, void *data, int silent)
 {
-	struct inode * root_inode;
-	struct dentry * root;
-	struct file * pipe;
+	struct inode *root_inode;
+	struct dentry *root;
+	struct file *pipe;
 	int pipefd;
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
@@ -217,7 +221,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
-	DPRINTK("starting up, sbi = %p",sbi);
+	pr_debug("starting up, sbi = %p\n", sbi);
 
 	s->s_fs_info = sbi;
 	sbi->magic = AUTOFS_SBI_MAGIC;
@@ -266,14 +270,14 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	if (parse_options(data, &pipefd, &root_inode->i_uid, &root_inode->i_gid,
 			  &pgrp, &pgrp_set, &sbi->type, &sbi->min_proto,
 			  &sbi->max_proto)) {
-		printk("autofs: called with bogus options\n");
+		pr_err("called with bogus options\n");
 		goto fail_dput;
 	}
 
 	if (pgrp_set) {
 		sbi->oz_pgrp = find_get_pid(pgrp);
 		if (!sbi->oz_pgrp) {
-			pr_warn("autofs: could not find process group %d\n",
+			pr_err("could not find process group %d\n",
 				pgrp);
 			goto fail_dput;
 		}
@@ -290,10 +294,10 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	/* Couldn't this be tested earlier? */
 	if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION ||
 	    sbi->min_proto > AUTOFS_MAX_PROTO_VERSION) {
-		printk("autofs: kernel does not match daemon version "
+		pr_err("kernel does not match daemon version "
 		       "daemon (%d, %d) kernel (%d, %d)\n",
-			sbi->min_proto, sbi->max_proto,
-			AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION);
+		       sbi->min_proto, sbi->max_proto,
+		       AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION);
 		goto fail_dput;
 	}
 
@@ -304,11 +308,11 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 		sbi->version = sbi->max_proto;
 	sbi->sub_version = AUTOFS_PROTO_SUBVERSION;
 
-	DPRINTK("pipe fd = %d, pgrp = %u", pipefd, pid_nr(sbi->oz_pgrp));
+	pr_debug("pipe fd = %d, pgrp = %u\n", pipefd, pid_nr(sbi->oz_pgrp));
 	pipe = fget(pipefd);
 
 	if (!pipe) {
-		printk("autofs: could not open pipe file descriptor\n");
+		pr_err("could not open pipe file descriptor\n");
 		goto fail_dput;
 	}
 	ret = autofs_prepare_pipe(pipe);
@@ -323,12 +327,12 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	 */
 	s->s_root = root;
 	return 0;
-	
+
 	/*
 	 * Failure ... clean up.
 	 */
 fail_fput:
-	printk("autofs: pipe file descriptor does not contain proper ops\n");
+	pr_err("pipe file descriptor does not contain proper ops\n");
 	fput(pipe);
 	/* fall through */
 fail_dput:
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index c6d7d3dbd52a..7ab923940d18 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -1,16 +1,12 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/root.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
- *  Copyright 2001-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
+ * Copyright 2001-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/capability.h>
 #include <linux/errno.h>
@@ -23,16 +19,18 @@
 
 #include "autofs_i.h"
 
-static int autofs4_dir_symlink(struct inode *,struct dentry *,const char *);
-static int autofs4_dir_unlink(struct inode *,struct dentry *);
-static int autofs4_dir_rmdir(struct inode *,struct dentry *);
-static int autofs4_dir_mkdir(struct inode *,struct dentry *,umode_t);
-static long autofs4_root_ioctl(struct file *,unsigned int,unsigned long);
+static int autofs4_dir_symlink(struct inode *, struct dentry *, const char *);
+static int autofs4_dir_unlink(struct inode *, struct dentry *);
+static int autofs4_dir_rmdir(struct inode *, struct dentry *);
+static int autofs4_dir_mkdir(struct inode *, struct dentry *, umode_t);
+static long autofs4_root_ioctl(struct file *, unsigned int, unsigned long);
 #ifdef CONFIG_COMPAT
-static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
+static long autofs4_root_compat_ioctl(struct file *,
+				      unsigned int, unsigned long);
 #endif
 static int autofs4_dir_open(struct inode *inode, struct file *file);
-static struct dentry *autofs4_lookup(struct inode *,struct dentry *, unsigned int);
+static struct dentry *autofs4_lookup(struct inode *,
+				     struct dentry *, unsigned int);
 static struct vfsmount *autofs4_d_automount(struct path *);
 static int autofs4_d_manage(struct dentry *, bool);
 static void autofs4_dentry_release(struct dentry *);
@@ -74,7 +72,9 @@ const struct dentry_operations autofs4_dentry_operations = {
 static void autofs4_add_active(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	struct autofs_info *ino;
+
+	ino = autofs4_dentry_ino(dentry);
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		if (!ino->active_count) {
@@ -84,13 +84,14 @@ static void autofs4_add_active(struct dentry *dentry)
 		ino->active_count++;
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 static void autofs4_del_active(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	struct autofs_info *ino;
+
+	ino = autofs4_dentry_ino(dentry);
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		ino->active_count--;
@@ -100,7 +101,6 @@ static void autofs4_del_active(struct dentry *dentry)
 		}
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 static int autofs4_dir_open(struct inode *inode, struct file *file)
@@ -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);
+	pr_debug("file=%p dentry=%p %pd\n", file, dentry, dentry);
 
 	if (autofs4_oz_mode(sbi))
 		goto out;
@@ -138,7 +138,7 @@ static void autofs4_dentry_release(struct dentry *de)
 	struct autofs_info *ino = autofs4_dentry_ino(de);
 	struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb);
 
-	DPRINTK("releasing %p", de);
+	pr_debug("releasing %p\n", de);
 
 	if (!ino)
 		return;
@@ -278,9 +278,9 @@ static int autofs4_mount_wait(struct dentry *dentry, bool rcu_walk)
 	if (ino->flags & AUTOFS_INF_PENDING) {
 		if (rcu_walk)
 			return -ECHILD;
-		DPRINTK("waiting for mount name=%pd", dentry);
+		pr_debug("waiting for mount name=%pd\n", dentry);
 		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
-		DPRINTK("mount wait done status=%d", status);
+		pr_debug("mount wait done status=%d\n", status);
 	}
 	ino->last_used = jiffies;
 	return status;
@@ -320,7 +320,9 @@ static struct dentry *autofs4_mountpoint_changed(struct path *path)
 	if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) {
 		struct dentry *parent = dentry->d_parent;
 		struct autofs_info *ino;
-		struct dentry *new = d_lookup(parent, &dentry->d_name);
+		struct dentry *new;
+
+		new = d_lookup(parent, &dentry->d_name);
 		if (!new)
 			return NULL;
 		ino = autofs4_dentry_ino(new);
@@ -338,7 +340,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
 
-	DPRINTK("dentry=%p %pd", dentry, dentry);
+	pr_debug("dentry=%p %pd\n", dentry, dentry);
 
 	/* The daemon never triggers a mount. */
 	if (autofs4_oz_mode(sbi))
@@ -425,7 +427,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
 
-	DPRINTK("dentry=%p %pd", dentry, dentry);
+	pr_debug("dentry=%p %pd\n", dentry, dentry);
 
 	/* The daemon never waits. */
 	if (autofs4_oz_mode(sbi)) {
@@ -455,6 +457,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 		 * a mount-trap.
 		 */
 		struct inode *inode;
+
 		if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))
 			return 0;
 		if (d_mountpoint(dentry))
@@ -494,13 +497,14 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 }
 
 /* Lookups in the root directory */
-static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+static struct dentry *autofs4_lookup(struct inode *dir,
+				     struct dentry *dentry, unsigned int flags)
 {
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
 	struct dentry *active;
 
-	DPRINTK("name = %pd", dentry);
+	pr_debug("name = %pd\n", dentry);
 
 	/* File name too long to exist */
 	if (dentry->d_name.len > NAME_MAX)
@@ -508,14 +512,14 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u
 
 	sbi = autofs4_sbi(dir->i_sb);
 
-	DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d",
-		current->pid, task_pgrp_nr(current), sbi->catatonic,
-		autofs4_oz_mode(sbi));
+	pr_debug("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d\n",
+		 current->pid, task_pgrp_nr(current), sbi->catatonic,
+		 autofs4_oz_mode(sbi));
 
 	active = autofs4_lookup_active(dentry);
-	if (active) {
+	if (active)
 		return active;
-	} else {
+	else {
 		/*
 		 * A dentry that is not within the root can never trigger a
 		 * mount operation, unless the directory already exists, so we
@@ -526,7 +530,8 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u
 			return ERR_PTR(-ENOENT);
 
 		/* Mark entries in the root as mount triggers */
-		if (autofs_type_indirect(sbi->type) && IS_ROOT(dentry->d_parent))
+		if (IS_ROOT(dentry->d_parent) &&
+		    autofs_type_indirect(sbi->type))
 			__managed_dentry_set_managed(dentry);
 
 		ino = autofs4_new_ino(sbi);
@@ -537,8 +542,6 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u
 		ino->dentry = dentry;
 
 		autofs4_add_active(dentry);
-
-		d_instantiate(dentry, NULL);
 	}
 	return NULL;
 }
@@ -554,7 +557,7 @@ static int autofs4_dir_symlink(struct inode *dir,
 	size_t size = strlen(symname);
 	char *cp;
 
-	DPRINTK("%s <- %pd", symname, dentry);
+	pr_debug("%s <- %pd\n", symname, dentry);
 
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
@@ -613,7 +616,7 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	struct autofs_info *p_ino;
-	
+
 	/* This allows root to remove symlinks */
 	if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -664,7 +667,6 @@ static void autofs_set_leaf_automount_flags(struct dentry *dentry)
 	if (IS_ROOT(parent->d_parent))
 		return;
 	managed_dentry_clear_managed(parent);
-	return;
 }
 
 static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
@@ -687,7 +689,6 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
 	if (d_child->next == &parent->d_subdirs &&
 	    d_child->prev == &parent->d_subdirs)
 		managed_dentry_set_managed(parent);
-	return;
 }
 
 static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
@@ -695,8 +696,8 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	struct autofs_info *p_ino;
-	
-	DPRINTK("dentry %p, removing %pd", dentry, dentry);
+
+	pr_debug("dentry %p, removing %pd\n", dentry, dentry);
 
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
@@ -728,7 +729,8 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 	return 0;
 }
 
-static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int autofs4_dir_mkdir(struct inode *dir,
+			     struct dentry *dentry, umode_t mode)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
@@ -738,7 +740,7 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t m
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
 
-	DPRINTK("dentry %p, creating %pd", dentry, dentry);
+	pr_debug("dentry %p, creating %pd\n", dentry, dentry);
 
 	BUG_ON(!ino);
 
@@ -768,14 +770,18 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t m
 /* Get/set timeout ioctl() operation */
 #ifdef CONFIG_COMPAT
 static inline int autofs4_compat_get_set_timeout(struct autofs_sb_info *sbi,
-					 compat_ulong_t __user *p)
+						 compat_ulong_t __user *p)
 {
-	int rv;
 	unsigned long ntimeout;
+	int rv;
+
+	rv = get_user(ntimeout, p);
+	if (rv)
+		goto error;
 
-	if ((rv = get_user(ntimeout, p)) ||
-	     (rv = put_user(sbi->exp_timeout/HZ, p)))
-		return rv;
+	rv = put_user(sbi->exp_timeout/HZ, p);
+	if (rv)
+		goto error;
 
 	if (ntimeout > UINT_MAX/HZ)
 		sbi->exp_timeout = 0;
@@ -783,18 +789,24 @@ static inline int autofs4_compat_get_set_timeout(struct autofs_sb_info *sbi,
 		sbi->exp_timeout = ntimeout * HZ;
 
 	return 0;
+error:
+	return rv;
 }
 #endif
 
 static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi,
-					 unsigned long __user *p)
+					  unsigned long __user *p)
 {
-	int rv;
 	unsigned long ntimeout;
+	int rv;
+
+	rv = get_user(ntimeout, p);
+	if (rv)
+		goto error;
 
-	if ((rv = get_user(ntimeout, p)) ||
-	     (rv = put_user(sbi->exp_timeout/HZ, p)))
-		return rv;
+	rv = put_user(sbi->exp_timeout/HZ, p);
+	if (rv)
+		goto error;
 
 	if (ntimeout > ULONG_MAX/HZ)
 		sbi->exp_timeout = 0;
@@ -802,16 +814,20 @@ static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi,
 		sbi->exp_timeout = ntimeout * HZ;
 
 	return 0;
+error:
+	return rv;
 }
 
 /* Return protocol version */
-static inline int autofs4_get_protover(struct autofs_sb_info *sbi, int __user *p)
+static inline int autofs4_get_protover(struct autofs_sb_info *sbi,
+				       int __user *p)
 {
 	return put_user(sbi->version, p);
 }
 
 /* Return protocol sub version */
-static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi, int __user *p)
+static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi,
+					  int __user *p)
 {
 	return put_user(sbi->sub_version, p);
 }
@@ -826,7 +842,7 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
 	if (may_umount(mnt))
 		status = 1;
 
-	DPRINTK("returning %d", status);
+	pr_debug("returning %d\n", status);
 
 	status = put_user(status, p);
 
@@ -834,9 +850,9 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
 }
 
 /* Identify autofs4_dentries - this is so we can tell if there's
-   an extra dentry refcount or not.  We only hold a refcount on the
-   dentry if its non-negative (ie, d_inode != NULL)
-*/
+ * an extra dentry refcount or not.  We only hold a refcount on the
+ * dentry if its non-negative (ie, d_inode != NULL)
+ */
 int is_autofs4_dentry(struct dentry *dentry)
 {
 	return dentry && d_really_is_positive(dentry) &&
@@ -854,21 +870,21 @@ static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp,
 	struct autofs_sb_info *sbi = autofs4_sbi(inode->i_sb);
 	void __user *p = (void __user *)arg;
 
-	DPRINTK("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u",
-		cmd,arg,sbi,task_pgrp_nr(current));
+	pr_debug("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u\n",
+		 cmd, arg, sbi, task_pgrp_nr(current));
 
 	if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
 	     _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT)
 		return -ENOTTY;
-	
+
 	if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	
-	switch(cmd) {
+
+	switch (cmd) {
 	case AUTOFS_IOC_READY:	/* Wait queue: go ahead and retry */
-		return autofs4_wait_release(sbi,(autofs_wqt_t)arg,0);
+		return autofs4_wait_release(sbi, (autofs_wqt_t) arg, 0);
 	case AUTOFS_IOC_FAIL:	/* Wait queue: fail with ENOENT */
-		return autofs4_wait_release(sbi,(autofs_wqt_t)arg,-ENOENT);
+		return autofs4_wait_release(sbi, (autofs_wqt_t) arg, -ENOENT);
 	case AUTOFS_IOC_CATATONIC: /* Enter catatonic mode (daemon shutdown) */
 		autofs4_catatonic_mode(sbi);
 		return 0;
@@ -888,13 +904,15 @@ static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp,
 
 	/* return a single thing to expire */
 	case AUTOFS_IOC_EXPIRE:
-		return autofs4_expire_run(inode->i_sb,filp->f_path.mnt,sbi, p);
+		return autofs4_expire_run(inode->i_sb,
+					  filp->f_path.mnt, sbi, p);
 	/* same as above, but can send multiple expires through pipe */
 	case AUTOFS_IOC_EXPIRE_MULTI:
-		return autofs4_expire_multi(inode->i_sb,filp->f_path.mnt,sbi, p);
+		return autofs4_expire_multi(inode->i_sb,
+					    filp->f_path.mnt, sbi, p);
 
 	default:
-		return -ENOSYS;
+		return -EINVAL;
 	}
 }
 
@@ -902,12 +920,13 @@ static long autofs4_root_ioctl(struct file *filp,
 			       unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
+
 	return autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
 }
 
 #ifdef CONFIG_COMPAT
 static long autofs4_root_compat_ioctl(struct file *filp,
-			     unsigned int cmd, unsigned long arg)
+				      unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	int ret;
@@ -916,7 +935,7 @@ static long autofs4_root_compat_ioctl(struct file *filp,
 		ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
 	else
 		ret = autofs4_root_ioctl_unlocked(inode, filp, cmd,
-			(unsigned long)compat_ptr(arg));
+					      (unsigned long) compat_ptr(arg));
 
 	return ret;
 }
diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c
index 84e037d1d129..99aab00dc217 100644
--- a/fs/autofs4/symlink.c
+++ b/fs/autofs4/symlink.c
@@ -1,14 +1,10 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/symlink.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include "autofs_i.h"
 
@@ -18,6 +14,7 @@ static const char *autofs4_get_link(struct dentry *dentry,
 {
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
+
 	if (!dentry)
 		return ERR_PTR(-ECHILD);
 	sbi = autofs4_sbi(dentry->d_sb);
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 35b755e79c2d..0146d911f468 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -1,15 +1,11 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/waitq.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 2001-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 2001-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/slab.h>
 #include <linux/time.h>
@@ -18,7 +14,8 @@
 #include "autofs_i.h"
 
 /* We make this a static variable rather than a part of the superblock; it
-   is better if we don't reassign numbers easily even across filesystems */
+ * is better if we don't reassign numbers easily even across filesystems
+ */
 static autofs_wqt_t autofs4_next_wait_queue = 1;
 
 /* These are the signals we allow interrupting a pending mount */
@@ -34,7 +31,7 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi)
 		return;
 	}
 
-	DPRINTK("entering catatonic mode");
+	pr_debug("entering catatonic mode\n");
 
 	sbi->catatonic = 1;
 	wq = sbi->queues;
@@ -69,17 +66,19 @@ static int autofs4_write(struct autofs_sb_info *sbi,
 	set_fs(KERNEL_DS);
 
 	mutex_lock(&sbi->pipe_mutex);
-	while (bytes &&
-	       (wr = __vfs_write(file,data,bytes,&file->f_pos)) > 0) {
+	wr = __vfs_write(file, data, bytes, &file->f_pos);
+	while (bytes && wr) {
 		data += wr;
 		bytes -= wr;
+		wr = __vfs_write(file, data, bytes, &file->f_pos);
 	}
 	mutex_unlock(&sbi->pipe_mutex);
 
 	set_fs(fs);
 
 	/* Keep the currently executing process from receiving a
-	   SIGPIPE unless it was already supposed to get one */
+	 * SIGPIPE unless it was already supposed to get one
+	 */
 	if (wr == -EPIPE && !sigpipe) {
 		spin_lock_irqsave(&current->sighand->siglock, flags);
 		sigdelset(&current->pending.signal, SIGPIPE);
@@ -89,7 +88,7 @@ static int autofs4_write(struct autofs_sb_info *sbi,
 
 	return (bytes > 0);
 }
-	
+
 static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 				 struct autofs_wait_queue *wq,
 				 int type)
@@ -102,10 +101,11 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 	struct file *pipe = NULL;
 	size_t pktsz;
 
-	DPRINTK("wait id = 0x%08lx, name = %.*s, type=%d",
-		(unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, type);
+	pr_debug("wait id = 0x%08lx, name = %.*s, type=%d\n",
+		 (unsigned long) wq->wait_queue_token,
+		 wq->name.len, wq->name.name, type);
 
-	memset(&pkt,0,sizeof pkt); /* For security reasons */
+	memset(&pkt, 0, sizeof(pkt)); /* For security reasons */
 
 	pkt.hdr.proto_version = sbi->version;
 	pkt.hdr.type = type;
@@ -126,7 +126,8 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 	}
 	case autofs_ptype_expire_multi:
 	{
-		struct autofs_packet_expire_multi *ep = &pkt.v4_pkt.expire_multi;
+		struct autofs_packet_expire_multi *ep =
+					&pkt.v4_pkt.expire_multi;
 
 		pktsz = sizeof(*ep);
 
@@ -163,7 +164,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 		break;
 	}
 	default:
-		printk("autofs4_notify_daemon: bad type %d!\n", type);
+		pr_warn("bad type %d!\n", type);
 		mutex_unlock(&sbi->wq_mutex);
 		return;
 	}
@@ -231,7 +232,7 @@ autofs4_find_wait(struct autofs_sb_info *sbi, struct qstr *qstr)
 		if (wq->name.hash == qstr->hash &&
 		    wq->name.len == qstr->len &&
 		    wq->name.name &&
-			 !memcmp(wq->name.name, qstr->name, qstr->len))
+		    !memcmp(wq->name.name, qstr->name, qstr->len))
 			break;
 	}
 	return wq;
@@ -248,7 +249,7 @@ autofs4_find_wait(struct autofs_sb_info *sbi, struct qstr *qstr)
 static int validate_request(struct autofs_wait_queue **wait,
 			    struct autofs_sb_info *sbi,
 			    struct qstr *qstr,
-			    struct dentry*dentry, enum autofs_notify notify)
+			    struct dentry *dentry, enum autofs_notify notify)
 {
 	struct autofs_wait_queue *wq;
 	struct autofs_info *ino;
@@ -322,8 +323,10 @@ static int validate_request(struct autofs_wait_queue **wait,
 		 * continue on and create a new request.
 		 */
 		if (!IS_ROOT(dentry)) {
-			if (d_really_is_positive(dentry) && d_unhashed(dentry)) {
+			if (d_unhashed(dentry) &&
+			    d_really_is_positive(dentry)) {
 				struct dentry *parent = dentry->d_parent;
+
 				new = d_lookup(parent, &dentry->d_name);
 				if (new)
 					dentry = new;
@@ -340,8 +343,8 @@ static int validate_request(struct autofs_wait_queue **wait,
 	return 1;
 }
 
-int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
-		enum autofs_notify notify)
+int autofs4_wait(struct autofs_sb_info *sbi,
+		 struct dentry *dentry, enum autofs_notify notify)
 {
 	struct autofs_wait_queue *wq;
 	struct qstr qstr;
@@ -411,7 +414,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 
 	if (!wq) {
 		/* Create a new wait queue */
-		wq = kmalloc(sizeof(struct autofs_wait_queue),GFP_KERNEL);
+		wq = kmalloc(sizeof(struct autofs_wait_queue), GFP_KERNEL);
 		if (!wq) {
 			kfree(qstr.name);
 			mutex_unlock(&sbi->wq_mutex);
@@ -450,17 +453,19 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 					autofs_ptype_expire_indirect;
 		}
 
-		DPRINTK("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
-			(unsigned long) wq->wait_queue_token, wq->name.len,
-			wq->name.name, notify);
+		pr_debug("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
+			 (unsigned long) wq->wait_queue_token, wq->name.len,
+			 wq->name.name, notify);
 
-		/* autofs4_notify_daemon() may block; it will unlock ->wq_mutex */
+		/*
+		 * autofs4_notify_daemon() may block; it will unlock ->wq_mutex
+		 */
 		autofs4_notify_daemon(sbi, wq, type);
 	} else {
 		wq->wait_ctr++;
-		DPRINTK("existing wait id = 0x%08lx, name = %.*s, nfy=%d",
-			(unsigned long) wq->wait_queue_token, wq->name.len,
-			wq->name.name, notify);
+		pr_debug("existing wait id = 0x%08lx, name = %.*s, nfy=%d\n",
+			 (unsigned long) wq->wait_queue_token, wq->name.len,
+			 wq->name.name, notify);
 		mutex_unlock(&sbi->wq_mutex);
 		kfree(qstr.name);
 	}
@@ -471,12 +476,14 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 	 */
 	if (wq->name.name) {
 		/* Block all but "shutdown" signals while waiting */
-		sigset_t oldset;
+		unsigned long shutdown_sigs_mask;
 		unsigned long irqflags;
+		sigset_t oldset;
 
 		spin_lock_irqsave(&current->sighand->siglock, irqflags);
 		oldset = current->blocked;
-		siginitsetinv(&current->blocked, SHUTDOWN_SIGS & ~oldset.sig[0]);
+		shutdown_sigs_mask = SHUTDOWN_SIGS & ~oldset.sig[0];
+		siginitsetinv(&current->blocked, shutdown_sigs_mask);
 		recalc_sigpending();
 		spin_unlock_irqrestore(&current->sighand->siglock, irqflags);
 
@@ -487,7 +494,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 		recalc_sigpending();
 		spin_unlock_irqrestore(&current->sighand->siglock, irqflags);
 	} else {
-		DPRINTK("skipped sleeping");
+		pr_debug("skipped sleeping\n");
 	}
 
 	status = wq->status;
@@ -562,4 +569,3 @@ int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_tok
 
 	return 0;
 }
-
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 051ea4809c14..7d914c67a9d0 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -653,7 +653,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top)
 
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		random_variable = (unsigned long) get_random_int();
+		random_variable = get_random_long();
 		random_variable &= STACK_RND_MASK;
 		random_variable <<= PAGE_SHIFT;
 	}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7b9cd49622b1..3172c4e2f502 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -575,7 +575,11 @@ static const struct super_operations bdev_sops = {
 static struct dentry *bd_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
-	return mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
+	struct dentry *dent;
+	dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
+	if (dent)
+		dent->d_sb->s_iflags |= SB_I_CGROUPWB;
+	return dent;
 }
 
 static struct file_system_type bd_type = {
@@ -1201,7 +1205,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
-		bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0;
+		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access)
+			bdev->bd_inode->i_flags = S_DAX;
+		else
+			bdev->bd_inode->i_flags = 0;
+
 		if (!partno) {
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
@@ -1693,13 +1701,24 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int blkdev_writepages(struct address_space *mapping,
+			     struct writeback_control *wbc)
+{
+	if (dax_mapping(mapping)) {
+		struct block_device *bdev = I_BDEV(mapping->host);
+
+		return dax_writeback_mapping_range(mapping, bdev, wbc);
+	}
+	return generic_writepages(mapping, wbc);
+}
+
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.readpages	= blkdev_readpages,
 	.writepage	= blkdev_writepage,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
-	.writepages	= generic_writepages,
+	.writepages	= blkdev_writepages,
 	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
 	.is_dirty_writeback = buffer_check_dirty_writeback,
@@ -1730,43 +1749,25 @@ static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return __dax_fault(vma, vmf, blkdev_get_block, NULL);
 }
 
-static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, unsigned int flags)
-{
-	return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
-}
-
-static void blkdev_vm_open(struct vm_area_struct *vma)
+static int blkdev_dax_pfn_mkwrite(struct vm_area_struct *vma,
+		struct vm_fault *vmf)
 {
-	struct inode *bd_inode = bdev_file_inode(vma->vm_file);
-	struct block_device *bdev = I_BDEV(bd_inode);
-
-	inode_lock(bd_inode);
-	bdev->bd_map_count++;
-	inode_unlock(bd_inode);
+	return dax_pfn_mkwrite(vma, vmf);
 }
 
-static void blkdev_vm_close(struct vm_area_struct *vma)
+static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, unsigned int flags)
 {
-	struct inode *bd_inode = bdev_file_inode(vma->vm_file);
-	struct block_device *bdev = I_BDEV(bd_inode);
-
-	inode_lock(bd_inode);
-	bdev->bd_map_count--;
-	inode_unlock(bd_inode);
+	return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
 }
 
 static const struct vm_operations_struct blkdev_dax_vm_ops = {
-	.open		= blkdev_vm_open,
-	.close		= blkdev_vm_close,
 	.fault		= blkdev_dax_fault,
 	.pmd_fault	= blkdev_dax_pmd_fault,
-	.pfn_mkwrite	= blkdev_dax_fault,
+	.pfn_mkwrite	= blkdev_dax_pfn_mkwrite,
 };
 
 static const struct vm_operations_struct blkdev_default_vm_ops = {
-	.open		= blkdev_vm_open,
-	.close		= blkdev_vm_close,
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 };
@@ -1774,18 +1775,14 @@ static const struct vm_operations_struct blkdev_default_vm_ops = {
 static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *bd_inode = bdev_file_inode(file);
-	struct block_device *bdev = I_BDEV(bd_inode);
 
 	file_accessed(file);
-	inode_lock(bd_inode);
-	bdev->bd_map_count++;
 	if (IS_DAX(bd_inode)) {
 		vma->vm_ops = &blkdev_dax_vm_ops;
 		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
 	} else {
 		vma->vm_ops = &blkdev_default_vm_ops;
 	}
-	inode_unlock(bd_inode);
 
 	return 0;
 }
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 88d9af3d4581..5fb60ea7eee2 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -328,8 +328,8 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
 		list_add_tail(&work->ordered_list, &wq->ordered_list);
 		spin_unlock_irqrestore(&wq->list_lock, flags);
 	}
-	queue_work(wq->normal_wq, &work->normal_work);
 	trace_btrfs_work_queued(work);
+	queue_work(wq->normal_wq, &work->normal_work);
 }
 
 void btrfs_queue_work(struct btrfs_workqueue *wq,
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index b90cd3776f8e..80e8472d618b 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -148,8 +148,7 @@ int __init btrfs_prelim_ref_init(void)
 
 void btrfs_prelim_ref_exit(void)
 {
-	if (btrfs_prelim_ref_cache)
-		kmem_cache_destroy(btrfs_prelim_ref_cache);
+	kmem_cache_destroy(btrfs_prelim_ref_cache);
 }
 
 /*
@@ -566,17 +565,14 @@ static void __merge_refs(struct list_head *head, int mode)
 		struct __prelim_ref *pos2 = pos1, *tmp;
 
 		list_for_each_entry_safe_continue(pos2, tmp, head, list) {
-			struct __prelim_ref *xchg, *ref1 = pos1, *ref2 = pos2;
+			struct __prelim_ref *ref1 = pos1, *ref2 = pos2;
 			struct extent_inode_elem *eie;
 
 			if (!ref_for_same_block(ref1, ref2))
 				continue;
 			if (mode == 1) {
-				if (!ref1->parent && ref2->parent) {
-					xchg = ref1;
-					ref1 = ref2;
-					ref2 = xchg;
-				}
+				if (!ref1->parent && ref2->parent)
+					swap(ref1, ref2);
 			} else {
 				if (ref1->parent != ref2->parent)
 					continue;
@@ -1406,7 +1402,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 			read_extent_buffer(eb, dest + bytes_left,
 					   name_off, name_len);
 		if (eb != eb_in) {
-			btrfs_tree_read_unlock_blocking(eb);
+			if (!path->skip_locking)
+				btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
 		}
 		ret = btrfs_find_item(fs_root, path, parent, 0,
@@ -1426,9 +1423,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
 		if (eb != eb_in) {
-			atomic_inc(&eb->refs);
-			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			if (!path->skip_locking)
+				btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			path->nodes[0] = NULL;
+			path->locks[0] = 0;
 		}
 		btrfs_release_path(path);
 		iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 861d472564c1..e34a71b3e225 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -95,6 +95,7 @@
 #include <linux/genhd.h>
 #include <linux/blkdev.h>
 #include <linux/vmalloc.h>
+#include <linux/string.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "hash.h"
@@ -105,6 +106,7 @@
 #include "locking.h"
 #include "check-integrity.h"
 #include "rcu-string.h"
+#include "compression.h"
 
 #define BTRFSIC_BLOCK_HASHTABLE_SIZE 0x10000
 #define BTRFSIC_BLOCK_LINK_HASHTABLE_SIZE 0x10000
@@ -176,7 +178,7 @@ struct btrfsic_block {
  * Elements of this type are allocated dynamically and required because
  * each block object can refer to and can be ref from multiple blocks.
  * The key to lookup them in the hashtable is the dev_bytenr of
- * the block ref to plus the one from the block refered from.
+ * the block ref to plus the one from the block referred from.
  * The fact that they are searchable via a hashtable and that a
  * ref_cnt is maintained is not required for the btrfs integrity
  * check algorithm itself, it is only used to make the output more
@@ -3076,7 +3078,7 @@ int btrfsic_mount(struct btrfs_root *root,
 
 	list_for_each_entry(device, dev_head, dev_list) {
 		struct btrfsic_dev_state *ds;
-		char *p;
+		const char *p;
 
 		if (!device->bdev || !device->name)
 			continue;
@@ -3092,11 +3094,7 @@ int btrfsic_mount(struct btrfs_root *root,
 		ds->state = state;
 		bdevname(ds->bdev, ds->name);
 		ds->name[BDEVNAME_SIZE - 1] = '\0';
-		for (p = ds->name; *p != '\0'; p++);
-		while (p > ds->name && *p != '/')
-			p--;
-		if (*p == '/')
-			p++;
+		p = kbasename(ds->name);
 		strlcpy(ds->name, p, sizeof(ds->name));
 		btrfsic_dev_state_hashtable_add(ds,
 						&btrfsic_dev_state_hashtable);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index c473c42d7d6c..3346cd8f9910 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -637,11 +637,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	faili = nr_pages - 1;
 	cb->nr_pages = nr_pages;
 
-	/* In the parent-locked case, we only locked the range we are
-	 * interested in.  In all other cases, we can opportunistically
-	 * cache decompressed data that goes beyond the requested range. */
-	if (!(bio_flags & EXTENT_BIO_PARENT_LOCKED))
-		add_ra_bio_pages(inode, em_start + em_len, cb);
+	add_ra_bio_pages(inode, em_start + em_len, cb);
 
 	/* include any pages we added in add_ra-bio_pages */
 	uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 13a4dc0436c9..f49d8b8c0f00 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -48,6 +48,15 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 void btrfs_clear_biovec_end(struct bio_vec *bvec, int vcnt,
 				   unsigned long pg_index,
 				   unsigned long pg_offset);
+
+enum btrfs_compression_type {
+	BTRFS_COMPRESS_NONE  = 0,
+	BTRFS_COMPRESS_ZLIB  = 1,
+	BTRFS_COMPRESS_LZO   = 2,
+	BTRFS_COMPRESS_TYPES = 2,
+	BTRFS_COMPRESS_LAST  = 3,
+};
+
 struct btrfs_compress_op {
 	struct list_head *(*alloc_workspace)(void);
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 769e0ff1b4ce..77592931ab4f 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -311,7 +311,7 @@ struct tree_mod_root {
 
 struct tree_mod_elem {
 	struct rb_node node;
-	u64 index;		/* shifted logical */
+	u64 logical;
 	u64 seq;
 	enum mod_log_op op;
 
@@ -435,11 +435,11 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 
 /*
  * key order of the log:
- *       index -> sequence
+ *       node/leaf start address -> sequence
  *
- * the index is the shifted logical of the *new* root node for root replace
- * operations, or the shifted logical of the affected block for all other
- * operations.
+ * The 'start address' is the logical address of the *new* root node
+ * for root replace operations, or the logical address of the affected
+ * block for all other operations.
  *
  * Note: must be called with write lock (tree_mod_log_write_lock).
  */
@@ -460,9 +460,9 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
 	while (*new) {
 		cur = container_of(*new, struct tree_mod_elem, node);
 		parent = *new;
-		if (cur->index < tm->index)
+		if (cur->logical < tm->logical)
 			new = &((*new)->rb_left);
-		else if (cur->index > tm->index)
+		else if (cur->logical > tm->logical)
 			new = &((*new)->rb_right);
 		else if (cur->seq < tm->seq)
 			new = &((*new)->rb_left);
@@ -523,7 +523,7 @@ alloc_tree_mod_elem(struct extent_buffer *eb, int slot,
 	if (!tm)
 		return NULL;
 
-	tm->index = eb->start >> PAGE_CACHE_SHIFT;
+	tm->logical = eb->start;
 	if (op != MOD_LOG_KEY_ADD) {
 		btrfs_node_key(eb, &tm->key, slot);
 		tm->blockptr = btrfs_node_blockptr(eb, slot);
@@ -588,7 +588,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
 		goto free_tms;
 	}
 
-	tm->index = eb->start >> PAGE_CACHE_SHIFT;
+	tm->logical = eb->start;
 	tm->slot = src_slot;
 	tm->move.dst_slot = dst_slot;
 	tm->move.nr_items = nr_items;
@@ -699,7 +699,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 		goto free_tms;
 	}
 
-	tm->index = new_root->start >> PAGE_CACHE_SHIFT;
+	tm->logical = new_root->start;
 	tm->old_root.logical = old_root->start;
 	tm->old_root.level = btrfs_header_level(old_root);
 	tm->generation = btrfs_header_generation(old_root);
@@ -739,16 +739,15 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
 	struct rb_node *node;
 	struct tree_mod_elem *cur = NULL;
 	struct tree_mod_elem *found = NULL;
-	u64 index = start >> PAGE_CACHE_SHIFT;
 
 	tree_mod_log_read_lock(fs_info);
 	tm_root = &fs_info->tree_mod_log;
 	node = tm_root->rb_node;
 	while (node) {
 		cur = container_of(node, struct tree_mod_elem, node);
-		if (cur->index < index) {
+		if (cur->logical < start) {
 			node = node->rb_left;
-		} else if (cur->index > index) {
+		} else if (cur->logical > start) {
 			node = node->rb_right;
 		} else if (cur->seq < min_seq) {
 			node = node->rb_left;
@@ -1230,9 +1229,10 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info,
 		return NULL;
 
 	/*
-	 * the very last operation that's logged for a root is the replacement
-	 * operation (if it is replaced at all). this has the index of the *new*
-	 * root, making it the very first operation that's logged for this root.
+	 * the very last operation that's logged for a root is the
+	 * replacement operation (if it is replaced at all). this has
+	 * the logical address of the *new* root, making it the very
+	 * first operation that's logged for this root.
 	 */
 	while (1) {
 		tm = tree_mod_log_search_oldest(fs_info, root_logical,
@@ -1336,7 +1336,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 		if (!next)
 			break;
 		tm = container_of(next, struct tree_mod_elem, node);
-		if (tm->index != first_tm->index)
+		if (tm->logical != first_tm->logical)
 			break;
 	}
 	tree_mod_log_read_unlock(fs_info);
@@ -5361,7 +5361,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 		goto out;
 	}
 
-	tmp_buf = kmalloc(left_root->nodesize, GFP_NOFS);
+	tmp_buf = kmalloc(left_root->nodesize, GFP_KERNEL);
 	if (!tmp_buf) {
 		ret = -ENOMEM;
 		goto out;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index bfe4a337fb4d..84a6a5b3384a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -100,6 +100,9 @@ struct btrfs_ordered_sum;
 /* tracks free space in block groups. */
 #define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL
 
+/* device stats in the device tree */
+#define BTRFS_DEV_STATS_OBJECTID 0ULL
+
 /* for storing balance parameters in the root tree */
 #define BTRFS_BALANCE_OBJECTID -4ULL
 
@@ -715,14 +718,6 @@ struct btrfs_timespec {
 	__le32 nsec;
 } __attribute__ ((__packed__));
 
-enum btrfs_compression_type {
-	BTRFS_COMPRESS_NONE  = 0,
-	BTRFS_COMPRESS_ZLIB  = 1,
-	BTRFS_COMPRESS_LZO   = 2,
-	BTRFS_COMPRESS_TYPES = 2,
-	BTRFS_COMPRESS_LAST  = 3,
-};
-
 struct btrfs_inode_item {
 	/* nfs style generation number */
 	__le64 generation;
@@ -793,7 +788,7 @@ struct btrfs_root_item {
 
 	/*
 	 * This generation number is used to test if the new fields are valid
-	 * and up to date while reading the root item. Everytime the root item
+	 * and up to date while reading the root item. Every time the root item
 	 * is written out, the "generation" field is copied into this field. If
 	 * anyone ever mounted the fs with an older kernel, we will have
 	 * mismatching generation values here and thus must invalidate the
@@ -1002,8 +997,10 @@ struct btrfs_dev_replace {
 	pid_t lock_owner;
 	atomic_t nesting_level;
 	struct mutex lock_finishing_cancel_unmount;
-	struct mutex lock_management_lock;
-	struct mutex lock;
+	rwlock_t lock;
+	atomic_t read_locks;
+	atomic_t blocking_readers;
+	wait_queue_head_t read_lock_wq;
 
 	struct btrfs_scrub_progress scrub_progress;
 };
@@ -1222,10 +1219,10 @@ struct btrfs_space_info {
 	 * we've called update_block_group and dropped the bytes_used counter
 	 * and increased the bytes_pinned counter.  However this means that
 	 * bytes_pinned does not reflect the bytes that will be pinned once the
-	 * delayed refs are flushed, so this counter is inc'ed everytime we call
-	 * btrfs_free_extent so it is a realtime count of what will be freed
-	 * once the transaction is committed.  It will be zero'ed everytime the
-	 * transaction commits.
+	 * delayed refs are flushed, so this counter is inc'ed every time we
+	 * call btrfs_free_extent so it is a realtime count of what will be
+	 * freed once the transaction is committed.  It will be zero'ed every
+	 * time the transaction commits.
 	 */
 	struct percpu_counter total_bytes_pinned;
 
@@ -1822,6 +1819,9 @@ struct btrfs_fs_info {
 	spinlock_t reada_lock;
 	struct radix_tree_root reada_tree;
 
+	/* readahead works cnt */
+	atomic_t reada_works_cnt;
+
 	/* Extent buffer radix tree */
 	spinlock_t buffer_lock;
 	struct radix_tree_root buffer_radix;
@@ -2185,13 +2185,43 @@ struct btrfs_ioctl_defrag_range_args {
  */
 #define BTRFS_QGROUP_RELATION_KEY       246
 
+/*
+ * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY.
+ */
 #define BTRFS_BALANCE_ITEM_KEY	248
 
 /*
- * Persistantly stores the io stats in the device tree.
- * One key for all stats, (0, BTRFS_DEV_STATS_KEY, devid).
+ * The key type for tree items that are stored persistently, but do not need to
+ * exist for extended period of time. The items can exist in any tree.
+ *
+ * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data]
+ *
+ * Existing items:
+ *
+ * - balance status item
+ *   (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0)
  */
-#define BTRFS_DEV_STATS_KEY	249
+#define BTRFS_TEMPORARY_ITEM_KEY	248
+
+/*
+ * Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY
+ */
+#define BTRFS_DEV_STATS_KEY		249
+
+/*
+ * The key type for tree items that are stored persistently and usually exist
+ * for a long period, eg. filesystem lifetime. The item kinds can be status
+ * information, stats or preference values. The item can exist in any tree.
+ *
+ * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data]
+ *
+ * Existing items:
+ *
+ * - device statistics, store IO stats in the device tree, one key for all
+ *   stats
+ *   (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0)
+ */
+#define BTRFS_PERSISTENT_ITEM_KEY	249
 
 /*
  * Persistantly stores the device replace state in the device tree.
@@ -2241,7 +2271,7 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_ENOSPC_DEBUG	 (1 << 15)
 #define BTRFS_MOUNT_AUTO_DEFRAG		(1 << 16)
 #define BTRFS_MOUNT_INODE_MAP_CACHE	(1 << 17)
-#define BTRFS_MOUNT_RECOVERY		(1 << 18)
+#define BTRFS_MOUNT_USEBACKUPROOT	(1 << 18)
 #define BTRFS_MOUNT_SKIP_BALANCE	(1 << 19)
 #define BTRFS_MOUNT_CHECK_INTEGRITY	(1 << 20)
 #define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
@@ -2250,9 +2280,10 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_FRAGMENT_DATA	(1 << 24)
 #define BTRFS_MOUNT_FRAGMENT_METADATA	(1 << 25)
 #define BTRFS_MOUNT_FREE_SPACE_TREE	(1 << 26)
+#define BTRFS_MOUNT_NOLOGREPLAY		(1 << 27)
 
 #define BTRFS_DEFAULT_COMMIT_INTERVAL	(30)
-#define BTRFS_DEFAULT_MAX_INLINE	(8192)
+#define BTRFS_DEFAULT_MAX_INLINE	(2048)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -2353,6 +2384,9 @@ struct btrfs_map_token {
 	unsigned long offset;
 };
 
+#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
+				((bytes) >> (fs_info)->sb->s_blocksize_bits)
+
 static inline void btrfs_init_map_token (struct btrfs_map_token *token)
 {
 	token->kaddr = NULL;
@@ -3448,8 +3482,7 @@ u64 btrfs_csum_bytes_to_leaves(struct btrfs_root *root, u64 csum_bytes);
 static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root,
 						 unsigned num_items)
 {
-	return (root->nodesize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
-		2 * num_items;
+	return root->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
 }
 
 /*
@@ -4027,7 +4060,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct inode *dir, u64 objectid,
 			const char *name, int name_len);
-int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
+int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 			int front);
 int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
@@ -4089,6 +4122,7 @@ void btrfs_test_inode_set_ops(struct inode *inode);
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int btrfs_ioctl_get_supported_features(void __user *arg);
 void btrfs_update_iflags(struct inode *inode);
 void btrfs_inherit_iflags(struct inode *inode, struct inode *dir);
 int btrfs_is_empty_uuid(u8 *uuid);
@@ -4151,7 +4185,8 @@ void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
 ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
 
 /* super.c */
-int btrfs_parse_options(struct btrfs_root *root, char *options);
+int btrfs_parse_options(struct btrfs_root *root, char *options,
+			unsigned long new_flags);
 int btrfs_sync_fs(struct super_block *sb, int wait);
 
 #ifdef CONFIG_PRINTK
@@ -4525,8 +4560,8 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 			      struct btrfs_key *start, struct btrfs_key *end);
 int btrfs_reada_wait(void *handle);
 void btrfs_reada_detach(void *handle);
-int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
-			 u64 start, int err);
+int btree_readahead_hook(struct btrfs_fs_info *fs_info,
+			 struct extent_buffer *eb, u64 start, int err);
 
 static inline int is_fstree(u64 rootid)
 {
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 0be47e4b8136..6cef0062f929 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -43,8 +43,7 @@ int __init btrfs_delayed_inode_init(void)
 
 void btrfs_delayed_inode_exit(void)
 {
-	if (delayed_node_cache)
-		kmem_cache_destroy(delayed_node_cache);
+	kmem_cache_destroy(delayed_node_cache);
 }
 
 static inline void btrfs_init_delayed_node(
@@ -651,9 +650,14 @@ static int btrfs_delayed_inode_reserve_metadata(
 			goto out;
 
 		ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
-		if (!WARN_ON(ret))
+		if (!ret)
 			goto out;
 
+		if (btrfs_test_opt(root, ENOSPC_DEBUG)) {
+			btrfs_debug(root->fs_info,
+				    "block rsv migrate returned %d", ret);
+			WARN_ON(1);
+		}
 		/*
 		 * Ok this is a problem, let's just steal from the global rsv
 		 * since this really shouldn't happen that often.
@@ -1689,7 +1693,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list,
  *
  */
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list)
+				    struct list_head *ins_list, bool *emitted)
 {
 	struct btrfs_dir_item *di;
 	struct btrfs_delayed_item *curr, *next;
@@ -1733,6 +1737,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
 
 		if (over)
 			return 1;
+		*emitted = true;
 	}
 	return 0;
 }
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index f70119f25421..0167853c84ae 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index);
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list);
+				    struct list_head *ins_list, bool *emitted);
 
 /* for init */
 int __init btrfs_delayed_inode_init(void);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 914ac13bd92f..430b3689b112 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -929,14 +929,10 @@ btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
 
 void btrfs_delayed_ref_exit(void)
 {
-	if (btrfs_delayed_ref_head_cachep)
-		kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
-	if (btrfs_delayed_tree_ref_cachep)
-		kmem_cache_destroy(btrfs_delayed_tree_ref_cachep);
-	if (btrfs_delayed_data_ref_cachep)
-		kmem_cache_destroy(btrfs_delayed_data_ref_cachep);
-	if (btrfs_delayed_extent_op_cachep)
-		kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
+	kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
+	kmem_cache_destroy(btrfs_delayed_tree_ref_cachep);
+	kmem_cache_destroy(btrfs_delayed_data_ref_cachep);
+	kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
 }
 
 int btrfs_delayed_ref_init(void)
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index cbb7dbfb3fff..a1d6652e0c47 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -202,13 +202,13 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
 	struct btrfs_dev_replace_item *ptr;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 0);
 	if (!dev_replace->is_valid ||
 	    !dev_replace->item_needs_writeback) {
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 0);
 		return 0;
 	}
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 0);
 
 	key.objectid = 0;
 	key.type = BTRFS_DEV_REPLACE_KEY;
@@ -264,7 +264,7 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
 	ptr = btrfs_item_ptr(eb, path->slots[0],
 			     struct btrfs_dev_replace_item);
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	if (dev_replace->srcdev)
 		btrfs_set_dev_replace_src_devid(eb, ptr,
 			dev_replace->srcdev->devid);
@@ -287,7 +287,7 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
 	btrfs_set_dev_replace_cursor_right(eb, ptr,
 		dev_replace->cursor_right);
 	dev_replace->item_needs_writeback = 0;
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 
 	btrfs_mark_buffer_dirty(eb);
 
@@ -356,7 +356,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 		return PTR_ERR(trans);
 	}
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	switch (dev_replace->replace_state) {
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
@@ -395,7 +395,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	dev_replace->is_valid = 1;
 	dev_replace->item_needs_writeback = 1;
 	args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 
 	ret = btrfs_sysfs_add_device_link(tgt_device->fs_devices, tgt_device);
 	if (ret)
@@ -407,7 +407,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
-		btrfs_dev_replace_lock(dev_replace);
+		btrfs_dev_replace_lock(dev_replace, 1);
 		goto leave;
 	}
 
@@ -433,7 +433,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 leave:
 	dev_replace->srcdev = NULL;
 	dev_replace->tgtdev = NULL;
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 	btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
 	return ret;
 }
@@ -471,18 +471,18 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	/* don't allow cancel or unmount to disturb the finishing procedure */
 	mutex_lock(&dev_replace->lock_finishing_cancel_unmount);
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 0);
 	/* was the operation canceled, or is it finished? */
 	if (dev_replace->replace_state !=
 	    BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED) {
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 0);
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return 0;
 	}
 
 	tgt_device = dev_replace->tgtdev;
 	src_device = dev_replace->srcdev;
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 0);
 
 	/*
 	 * flush all outstanding I/O and inode extent mappings before the
@@ -507,7 +507,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	/* keep away write_all_supers() during the finishing procedure */
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	mutex_lock(&root->fs_info->chunk_mutex);
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	dev_replace->replace_state =
 		scrub_ret ? BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED
 			  : BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED;
@@ -528,7 +528,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 			        rcu_str_deref(src_device->name),
 			      src_device->devid,
 			      rcu_str_deref(tgt_device->name), scrub_ret);
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 1);
 		mutex_unlock(&root->fs_info->chunk_mutex);
 		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 		mutex_unlock(&uuid_mutex);
@@ -565,7 +565,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 	fs_info->fs_devices->rw_devices++;
 
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 
 	btrfs_rm_dev_replace_blocked(fs_info);
 
@@ -649,7 +649,7 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 	struct btrfs_device *srcdev;
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 0);
 	/* even if !dev_replace_is_valid, the values are good enough for
 	 * the replace_status ioctl */
 	args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
@@ -675,7 +675,7 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 			div_u64(btrfs_device_get_total_bytes(srcdev), 1000));
 		break;
 	}
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 0);
 }
 
 int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info,
@@ -698,13 +698,13 @@ static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		return -EROFS;
 
 	mutex_lock(&dev_replace->lock_finishing_cancel_unmount);
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	switch (dev_replace->replace_state) {
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
 		result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NOT_STARTED;
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 1);
 		goto leave;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
@@ -717,7 +717,7 @@ static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED;
 	dev_replace->time_stopped = get_seconds();
 	dev_replace->item_needs_writeback = 1;
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 	btrfs_scrub_cancel(fs_info);
 
 	trans = btrfs_start_transaction(root, 0);
@@ -740,7 +740,7 @@ void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info)
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 
 	mutex_lock(&dev_replace->lock_finishing_cancel_unmount);
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	switch (dev_replace->replace_state) {
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
@@ -756,7 +756,7 @@ void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info)
 		break;
 	}
 
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 }
 
@@ -766,12 +766,12 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
 	struct task_struct *task;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	switch (dev_replace->replace_state) {
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 1);
 		return 0;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 		break;
@@ -784,10 +784,10 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
 		btrfs_info(fs_info, "cannot continue dev_replace, tgtdev is missing");
 		btrfs_info(fs_info,
 			"you may cancel the operation after 'mount -o degraded'");
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 1);
 		return 0;
 	}
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 
 	WARN_ON(atomic_xchg(
 		&fs_info->mutually_exclusive_operation_running, 1));
@@ -802,7 +802,7 @@ static int btrfs_dev_replace_kthread(void *data)
 	struct btrfs_ioctl_dev_replace_args *status_args;
 	u64 progress;
 
-	status_args = kzalloc(sizeof(*status_args), GFP_NOFS);
+	status_args = kzalloc(sizeof(*status_args), GFP_KERNEL);
 	if (status_args) {
 		btrfs_dev_replace_status(fs_info, status_args);
 		progress = status_args->status.progress_1000;
@@ -858,55 +858,65 @@ int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
 		 * not called and the the filesystem is remounted
 		 * in degraded state. This does not stop the
 		 * dev_replace procedure. It needs to be canceled
-		 * manually if the cancelation is wanted.
+		 * manually if the cancellation is wanted.
 		 */
 		break;
 	}
 	return 1;
 }
 
-void btrfs_dev_replace_lock(struct btrfs_dev_replace *dev_replace)
+void btrfs_dev_replace_lock(struct btrfs_dev_replace *dev_replace, int rw)
 {
-	/* the beginning is just an optimization for the typical case */
-	if (atomic_read(&dev_replace->nesting_level) == 0) {
-acquire_lock:
-		/* this is not a nested case where the same thread
-		 * is trying to acqurire the same lock twice */
-		mutex_lock(&dev_replace->lock);
-		mutex_lock(&dev_replace->lock_management_lock);
-		dev_replace->lock_owner = current->pid;
-		atomic_inc(&dev_replace->nesting_level);
-		mutex_unlock(&dev_replace->lock_management_lock);
-		return;
+	if (rw == 1) {
+		/* write */
+again:
+		wait_event(dev_replace->read_lock_wq,
+			   atomic_read(&dev_replace->blocking_readers) == 0);
+		write_lock(&dev_replace->lock);
+		if (atomic_read(&dev_replace->blocking_readers)) {
+			write_unlock(&dev_replace->lock);
+			goto again;
+		}
+	} else {
+		read_lock(&dev_replace->lock);
+		atomic_inc(&dev_replace->read_locks);
 	}
+}
 
-	mutex_lock(&dev_replace->lock_management_lock);
-	if (atomic_read(&dev_replace->nesting_level) > 0 &&
-	    dev_replace->lock_owner == current->pid) {
-		WARN_ON(!mutex_is_locked(&dev_replace->lock));
-		atomic_inc(&dev_replace->nesting_level);
-		mutex_unlock(&dev_replace->lock_management_lock);
-		return;
+void btrfs_dev_replace_unlock(struct btrfs_dev_replace *dev_replace, int rw)
+{
+	if (rw == 1) {
+		/* write */
+		ASSERT(atomic_read(&dev_replace->blocking_readers) == 0);
+		write_unlock(&dev_replace->lock);
+	} else {
+		ASSERT(atomic_read(&dev_replace->read_locks) > 0);
+		atomic_dec(&dev_replace->read_locks);
+		read_unlock(&dev_replace->lock);
 	}
+}
 
-	mutex_unlock(&dev_replace->lock_management_lock);
-	goto acquire_lock;
+/* inc blocking cnt and release read lock */
+void btrfs_dev_replace_set_lock_blocking(
+					struct btrfs_dev_replace *dev_replace)
+{
+	/* only set blocking for read lock */
+	ASSERT(atomic_read(&dev_replace->read_locks) > 0);
+	atomic_inc(&dev_replace->blocking_readers);
+	read_unlock(&dev_replace->lock);
 }
 
-void btrfs_dev_replace_unlock(struct btrfs_dev_replace *dev_replace)
+/* acquire read lock and dec blocking cnt */
+void btrfs_dev_replace_clear_lock_blocking(
+					struct btrfs_dev_replace *dev_replace)
 {
-	WARN_ON(!mutex_is_locked(&dev_replace->lock));
-	mutex_lock(&dev_replace->lock_management_lock);
-	WARN_ON(atomic_read(&dev_replace->nesting_level) < 1);
-	WARN_ON(dev_replace->lock_owner != current->pid);
-	atomic_dec(&dev_replace->nesting_level);
-	if (atomic_read(&dev_replace->nesting_level) == 0) {
-		dev_replace->lock_owner = 0;
-		mutex_unlock(&dev_replace->lock_management_lock);
-		mutex_unlock(&dev_replace->lock);
-	} else {
-		mutex_unlock(&dev_replace->lock_management_lock);
-	}
+	/* only set blocking for read lock */
+	ASSERT(atomic_read(&dev_replace->read_locks) > 0);
+	ASSERT(atomic_read(&dev_replace->blocking_readers) > 0);
+	read_lock(&dev_replace->lock);
+	if (atomic_dec_and_test(&dev_replace->blocking_readers) &&
+	    waitqueue_active(&dev_replace->read_lock_wq))
+		wake_up(&dev_replace->read_lock_wq);
 }
 
 void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 20035cbbf021..29e3ef5f96bd 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -34,8 +34,11 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info,
 void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info);
 int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info);
 int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
-void btrfs_dev_replace_lock(struct btrfs_dev_replace *dev_replace);
-void btrfs_dev_replace_unlock(struct btrfs_dev_replace *dev_replace);
+void btrfs_dev_replace_lock(struct btrfs_dev_replace *dev_replace, int rw);
+void btrfs_dev_replace_unlock(struct btrfs_dev_replace *dev_replace, int rw);
+void btrfs_dev_replace_set_lock_blocking(struct btrfs_dev_replace *dev_replace);
+void btrfs_dev_replace_clear_lock_blocking(
+					struct btrfs_dev_replace *dev_replace);
 
 static inline void btrfs_dev_replace_stats_inc(atomic64_t *stat_value)
 {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index dd08e29f5117..4b02591b0301 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -50,6 +50,7 @@
 #include "raid56.h"
 #include "sysfs.h"
 #include "qgroup.h"
+#include "compression.h"
 
 #ifdef CONFIG_X86
 #include <asm/cpufeature.h>
@@ -110,8 +111,7 @@ int __init btrfs_end_io_wq_init(void)
 
 void btrfs_end_io_wq_exit(void)
 {
-	if (btrfs_end_io_wq_cache)
-		kmem_cache_destroy(btrfs_end_io_wq_cache);
+	kmem_cache_destroy(btrfs_end_io_wq_cache);
 }
 
 /*
@@ -182,6 +182,7 @@ static struct btrfs_lockdep_keyset {
 	{ .id = BTRFS_TREE_RELOC_OBJECTID,	.name_stem = "treloc"	},
 	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	.name_stem = "dreloc"	},
 	{ .id = BTRFS_UUID_TREE_OBJECTID,	.name_stem = "uuid"	},
+	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	.name_stem = "free-space" },
 	{ .id = 0,				.name_stem = "tree"	},
 };
 
@@ -611,6 +612,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	int found_level;
 	struct extent_buffer *eb;
 	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret = 0;
 	int reads_done;
 
@@ -636,21 +638,21 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != eb->start) {
-		btrfs_err_rl(eb->fs_info, "bad tree block start %llu %llu",
-			       found_start, eb->start);
+		btrfs_err_rl(fs_info, "bad tree block start %llu %llu",
+			     found_start, eb->start);
 		ret = -EIO;
 		goto err;
 	}
-	if (check_tree_block_fsid(root->fs_info, eb)) {
-		btrfs_err_rl(eb->fs_info, "bad fsid on block %llu",
-			       eb->start);
+	if (check_tree_block_fsid(fs_info, eb)) {
+		btrfs_err_rl(fs_info, "bad fsid on block %llu",
+			     eb->start);
 		ret = -EIO;
 		goto err;
 	}
 	found_level = btrfs_header_level(eb);
 	if (found_level >= BTRFS_MAX_LEVEL) {
-		btrfs_err(root->fs_info, "bad tree block level %d",
-			   (int)btrfs_header_level(eb));
+		btrfs_err(fs_info, "bad tree block level %d",
+			  (int)btrfs_header_level(eb));
 		ret = -EIO;
 		goto err;
 	}
@@ -658,7 +660,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb),
 				       eb, found_level);
 
-	ret = csum_tree_block(root->fs_info, eb, 1);
+	ret = csum_tree_block(fs_info, eb, 1);
 	if (ret) {
 		ret = -EIO;
 		goto err;
@@ -679,7 +681,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 err:
 	if (reads_done &&
 	    test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
-		btree_readahead_hook(root, eb, eb->start, ret);
+		btree_readahead_hook(fs_info, eb, eb->start, ret);
 
 	if (ret) {
 		/*
@@ -698,14 +700,13 @@ out:
 static int btree_io_failed_hook(struct page *page, int failed_mirror)
 {
 	struct extent_buffer *eb;
-	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
 
 	eb = (struct extent_buffer *)page->private;
 	set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = failed_mirror;
 	atomic_dec(&eb->io_pages);
 	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
-		btree_readahead_hook(root, eb, eb->start, -EIO);
+		btree_readahead_hook(eb->fs_info, eb, eb->start, -EIO);
 	return -EIO;	/* we fixed nothing */
 }
 
@@ -815,7 +816,7 @@ static void run_one_async_done(struct btrfs_work *work)
 	    waitqueue_active(&fs_info->async_submit_wait))
 		wake_up(&fs_info->async_submit_wait);
 
-	/* If an error occured we just want to clean up the bio and move on */
+	/* If an error occurred we just want to clean up the bio and move on */
 	if (async->error) {
 		async->bio->bi_error = async->error;
 		bio_endio(async->bio);
@@ -930,7 +931,7 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags)
 	if (bio_flags & EXTENT_BIO_TREE_LOG)
 		return 0;
 #ifdef CONFIG_X86
-	if (static_cpu_has_safe(X86_FEATURE_XMM4_2))
+	if (static_cpu_has(X86_FEATURE_XMM4_2))
 		return 0;
 #endif
 	return 1;
@@ -1295,9 +1296,10 @@ static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize,
 	spin_lock_init(&root->root_item_lock);
 }
 
-static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info)
+static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
+		gfp_t flags)
 {
-	struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS);
+	struct btrfs_root *root = kzalloc(sizeof(*root), flags);
 	if (root)
 		root->fs_info = fs_info;
 	return root;
@@ -1309,7 +1311,7 @@ struct btrfs_root *btrfs_alloc_dummy_root(void)
 {
 	struct btrfs_root *root;
 
-	root = btrfs_alloc_root(NULL);
+	root = btrfs_alloc_root(NULL, GFP_KERNEL);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 	__setup_root(4096, 4096, 4096, root, NULL, 1);
@@ -1331,7 +1333,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	int ret = 0;
 	uuid_le uuid;
 
-	root = btrfs_alloc_root(fs_info);
+	root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 
@@ -1407,7 +1409,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	struct btrfs_root *tree_root = fs_info->tree_root;
 	struct extent_buffer *leaf;
 
-	root = btrfs_alloc_root(fs_info);
+	root = btrfs_alloc_root(fs_info, GFP_NOFS);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 
@@ -1505,7 +1507,7 @@ static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 	if (!path)
 		return ERR_PTR(-ENOMEM);
 
-	root = btrfs_alloc_root(fs_info);
+	root = btrfs_alloc_root(fs_info, GFP_NOFS);
 	if (!root) {
 		ret = -ENOMEM;
 		goto alloc_fail;
@@ -1787,7 +1789,6 @@ static int cleaner_kthread(void *arg)
 	int again;
 	struct btrfs_trans_handle *trans;
 
-	set_freezable();
 	do {
 		again = 0;
 
@@ -2272,9 +2273,11 @@ static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info)
 	fs_info->dev_replace.lock_owner = 0;
 	atomic_set(&fs_info->dev_replace.nesting_level, 0);
 	mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
-	mutex_init(&fs_info->dev_replace.lock_management_lock);
-	mutex_init(&fs_info->dev_replace.lock);
+	rwlock_init(&fs_info->dev_replace.lock);
+	atomic_set(&fs_info->dev_replace.read_locks, 0);
+	atomic_set(&fs_info->dev_replace.blocking_readers, 0);
 	init_waitqueue_head(&fs_info->replace_wait);
+	init_waitqueue_head(&fs_info->dev_replace.read_lock_wq);
 }
 
 static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
@@ -2385,7 +2388,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 		return -EIO;
 	}
 
-	log_tree_root = btrfs_alloc_root(fs_info);
+	log_tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	if (!log_tree_root)
 		return -ENOMEM;
 
@@ -2510,8 +2513,8 @@ int open_ctree(struct super_block *sb,
 	int backup_index = 0;
 	int max_active;
 
-	tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info);
-	chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info);
+	tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
+	chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	if (!tree_root || !chunk_root) {
 		err = -ENOMEM;
 		goto fail;
@@ -2603,6 +2606,7 @@ int open_ctree(struct super_block *sb,
 	atomic_set(&fs_info->nr_async_bios, 0);
 	atomic_set(&fs_info->defrag_running, 0);
 	atomic_set(&fs_info->qgroup_op_seq, 0);
+	atomic_set(&fs_info->reada_works_cnt, 0);
 	atomic64_set(&fs_info->tree_mod_seq, 0);
 	fs_info->sb = sb;
 	fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
@@ -2622,7 +2626,7 @@ int open_ctree(struct super_block *sb,
 	INIT_LIST_HEAD(&fs_info->ordered_roots);
 	spin_lock_init(&fs_info->ordered_root_lock);
 	fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
-					GFP_NOFS);
+					GFP_KERNEL);
 	if (!fs_info->delayed_root) {
 		err = -ENOMEM;
 		goto fail_iput;
@@ -2750,7 +2754,7 @@ int open_ctree(struct super_block *sb,
 	 */
 	fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
 
-	ret = btrfs_parse_options(tree_root, options);
+	ret = btrfs_parse_options(tree_root, options, sb->s_flags);
 	if (ret) {
 		err = ret;
 		goto fail_alloc;
@@ -3029,8 +3033,9 @@ retry_root_backup:
 	if (ret)
 		goto fail_trans_kthread;
 
-	/* do not make disk changes in broken FS */
-	if (btrfs_super_log_root(disk_super) != 0) {
+	/* do not make disk changes in broken FS or nologreplay is given */
+	if (btrfs_super_log_root(disk_super) != 0 &&
+	    !btrfs_test_opt(tree_root, NOLOGREPLAY)) {
 		ret = btrfs_replay_log(fs_info, fs_devices);
 		if (ret) {
 			err = ret;
@@ -3146,6 +3151,12 @@ retry_root_backup:
 
 	fs_info->open = 1;
 
+	/*
+	 * backuproot only affect mount behavior, and if open_ctree succeeded,
+	 * no need to keep the flag
+	 */
+	btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT);
+
 	return 0;
 
 fail_qgroup:
@@ -3200,7 +3211,7 @@ fail:
 	return err;
 
 recovery_tree_root:
-	if (!btrfs_test_opt(tree_root, RECOVERY))
+	if (!btrfs_test_opt(tree_root, USEBACKUPROOT))
 		goto fail_tree_roots;
 
 	free_root_pointers(fs_info, 0);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e2287c7c10be..53e12977bfd0 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4838,7 +4838,7 @@ static inline int need_do_async_reclaim(struct btrfs_space_info *space_info,
 	u64 thresh = div_factor_fine(space_info->total_bytes, 98);
 
 	/* If we're just plain full then async reclaim just slows us down. */
-	if (space_info->bytes_used >= thresh)
+	if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh)
 		return 0;
 
 	return (used >= thresh && !btrfs_fs_closing(fs_info) &&
@@ -5373,27 +5373,33 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 
 	block_rsv->size = min_t(u64, num_bytes, SZ_512M);
 
-	num_bytes = sinfo->bytes_used + sinfo->bytes_pinned +
-		    sinfo->bytes_reserved + sinfo->bytes_readonly +
-		    sinfo->bytes_may_use;
-
-	if (sinfo->total_bytes > num_bytes) {
-		num_bytes = sinfo->total_bytes - num_bytes;
-		block_rsv->reserved += num_bytes;
-		sinfo->bytes_may_use += num_bytes;
-		trace_btrfs_space_reservation(fs_info, "space_info",
-				      sinfo->flags, num_bytes, 1);
-	}
-
-	if (block_rsv->reserved >= block_rsv->size) {
+	if (block_rsv->reserved < block_rsv->size) {
+		num_bytes = sinfo->bytes_used + sinfo->bytes_pinned +
+			sinfo->bytes_reserved + sinfo->bytes_readonly +
+			sinfo->bytes_may_use;
+		if (sinfo->total_bytes > num_bytes) {
+			num_bytes = sinfo->total_bytes - num_bytes;
+			num_bytes = min(num_bytes,
+					block_rsv->size - block_rsv->reserved);
+			block_rsv->reserved += num_bytes;
+			sinfo->bytes_may_use += num_bytes;
+			trace_btrfs_space_reservation(fs_info, "space_info",
+						      sinfo->flags, num_bytes,
+						      1);
+		}
+	} else if (block_rsv->reserved > block_rsv->size) {
 		num_bytes = block_rsv->reserved - block_rsv->size;
 		sinfo->bytes_may_use -= num_bytes;
 		trace_btrfs_space_reservation(fs_info, "space_info",
 				      sinfo->flags, num_bytes, 0);
 		block_rsv->reserved = block_rsv->size;
-		block_rsv->full = 1;
 	}
 
+	if (block_rsv->reserved == block_rsv->size)
+		block_rsv->full = 1;
+	else
+		block_rsv->full = 0;
+
 	spin_unlock(&block_rsv->lock);
 	spin_unlock(&sinfo->lock);
 }
@@ -5752,7 +5758,7 @@ out_fail:
 
 		/*
 		 * This is tricky, but first we need to figure out how much we
-		 * free'd from any free-ers that occured during this
+		 * free'd from any free-ers that occurred during this
 		 * reservation, so we reset ->csum_bytes to the csum_bytes
 		 * before we dropped our lock, and then call the free for the
 		 * number of bytes that were freed while we were trying our
@@ -7018,7 +7024,7 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
 		   struct btrfs_free_cluster *cluster,
 		   int delalloc)
 {
-	struct btrfs_block_group_cache *used_bg;
+	struct btrfs_block_group_cache *used_bg = NULL;
 	bool locked = false;
 again:
 	spin_lock(&cluster->refill_lock);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2e7c97a3f344..76a0c8597d98 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -206,10 +206,8 @@ void extent_io_exit(void)
 	 * destroy caches.
 	 */
 	rcu_barrier();
-	if (extent_state_cache)
-		kmem_cache_destroy(extent_state_cache);
-	if (extent_buffer_cache)
-		kmem_cache_destroy(extent_buffer_cache);
+	kmem_cache_destroy(extent_state_cache);
+	kmem_cache_destroy(extent_buffer_cache);
 	if (btrfs_bioset)
 		bioset_free(btrfs_bioset);
 }
@@ -232,7 +230,7 @@ static struct extent_state *alloc_extent_state(gfp_t mask)
 	if (!state)
 		return state;
 	state->state = 0;
-	state->private = 0;
+	state->failrec = NULL;
 	RB_CLEAR_NODE(&state->rb_node);
 	btrfs_leak_debug_add(&state->leak_list, &states);
 	atomic_set(&state->refs, 1);
@@ -1844,7 +1842,8 @@ out:
  * set the private field for a given byte offset in the tree.  If there isn't
  * an extent_state there already, this does nothing.
  */
-static int set_state_private(struct extent_io_tree *tree, u64 start, u64 private)
+static noinline int set_state_failrec(struct extent_io_tree *tree, u64 start,
+		struct io_failure_record *failrec)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -1865,13 +1864,14 @@ static int set_state_private(struct extent_io_tree *tree, u64 start, u64 private
 		ret = -ENOENT;
 		goto out;
 	}
-	state->private = private;
+	state->failrec = failrec;
 out:
 	spin_unlock(&tree->lock);
 	return ret;
 }
 
-int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private)
+static noinline int get_state_failrec(struct extent_io_tree *tree, u64 start,
+		struct io_failure_record **failrec)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -1892,7 +1892,7 @@ int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private)
 		ret = -ENOENT;
 		goto out;
 	}
-	*private = state->private;
+	*failrec = state->failrec;
 out:
 	spin_unlock(&tree->lock);
 	return ret;
@@ -1972,7 +1972,7 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec)
 	int err = 0;
 	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
 
-	set_state_private(failure_tree, rec->start, 0);
+	set_state_failrec(failure_tree, rec->start, NULL);
 	ret = clear_extent_bits(failure_tree, rec->start,
 				rec->start + rec->len - 1,
 				EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
@@ -2089,7 +2089,6 @@ int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 		     unsigned int pg_offset)
 {
 	u64 private;
-	u64 private_failure;
 	struct io_failure_record *failrec;
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	struct extent_state *state;
@@ -2102,12 +2101,11 @@ int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 	if (!ret)
 		return 0;
 
-	ret = get_state_private(&BTRFS_I(inode)->io_failure_tree, start,
-				&private_failure);
+	ret = get_state_failrec(&BTRFS_I(inode)->io_failure_tree, start,
+			&failrec);
 	if (ret)
 		return 0;
 
-	failrec = (struct io_failure_record *)(unsigned long) private_failure;
 	BUG_ON(!failrec->this_mirror);
 
 	if (failrec->in_validation) {
@@ -2167,7 +2165,7 @@ void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end)
 
 		next = next_state(state);
 
-		failrec = (struct io_failure_record *)(unsigned long)state->private;
+		failrec = state->failrec;
 		free_extent_state(state);
 		kfree(failrec);
 
@@ -2177,10 +2175,9 @@ void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end)
 }
 
 int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
-				struct io_failure_record **failrec_ret)
+		struct io_failure_record **failrec_ret)
 {
 	struct io_failure_record *failrec;
-	u64 private;
 	struct extent_map *em;
 	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
@@ -2188,7 +2185,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 	int ret;
 	u64 logical;
 
-	ret = get_state_private(failure_tree, start, &private);
+	ret = get_state_failrec(failure_tree, start, &failrec);
 	if (ret) {
 		failrec = kzalloc(sizeof(*failrec), GFP_NOFS);
 		if (!failrec)
@@ -2237,8 +2234,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 		ret = set_extent_bits(failure_tree, start, end,
 					EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
 		if (ret >= 0)
-			ret = set_state_private(failure_tree, start,
-						(u64)(unsigned long)failrec);
+			ret = set_state_failrec(failure_tree, start, failrec);
 		/* set the bits in the inode's tree */
 		if (ret >= 0)
 			ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED,
@@ -2248,7 +2244,6 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 			return ret;
 		}
 	} else {
-		failrec = (struct io_failure_record *)(unsigned long)private;
 		pr_debug("Get IO Failure Record: (found) logical=%llu, start=%llu, len=%llu, validation=%d\n",
 			 failrec->logical, failrec->start, failrec->len,
 			 failrec->in_validation);
@@ -2897,12 +2892,11 @@ static int __do_readpage(struct extent_io_tree *tree,
 	struct block_device *bdev;
 	int ret;
 	int nr = 0;
-	int parent_locked = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
 	size_t pg_offset = 0;
 	size_t iosize;
 	size_t disk_io_size;
 	size_t blocksize = inode->i_sb->s_blocksize;
-	unsigned long this_bio_flag = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
+	unsigned long this_bio_flag = 0;
 
 	set_page_extent_mapped(page);
 
@@ -2942,18 +2936,16 @@ static int __do_readpage(struct extent_io_tree *tree,
 			kunmap_atomic(userpage);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			if (!parent_locked)
-				unlock_extent_cached(tree, cur,
-						     cur + iosize - 1,
-						     &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur,
+					     cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			break;
 		}
 		em = __get_extent_map(inode, page, pg_offset, cur,
 				      end - cur + 1, get_extent, em_cached);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, end);
+			unlock_extent(tree, cur, end);
 			break;
 		}
 		extent_offset = cur - em->start;
@@ -3038,12 +3030,9 @@ static int __do_readpage(struct extent_io_tree *tree,
 
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			if (parent_locked)
-				free_extent_state(cached);
-			else
-				unlock_extent_cached(tree, cur,
-						     cur + iosize - 1,
-						     &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur,
+					     cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3052,8 +3041,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 		if (test_range_bit(tree, cur, cur_end,
 				   EXTENT_UPTODATE, 1, NULL)) {
 			check_page_uptodate(tree, page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3063,8 +3051,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 		 */
 		if (block_start == EXTENT_MAP_INLINE) {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3083,8 +3070,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 			*bio_flags = this_bio_flag;
 		} else {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 		}
 		cur = cur + iosize;
 		pg_offset += iosize;
@@ -3186,7 +3172,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 
 	while (1) {
 		lock_extent(tree, start, end);
-		ordered = btrfs_lookup_ordered_extent(inode, start);
+		ordered = btrfs_lookup_ordered_range(inode, start,
+						PAGE_CACHE_SIZE);
 		if (!ordered)
 			break;
 		unlock_extent(tree, start, end);
@@ -3213,20 +3200,6 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	return ret;
 }
 
-int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
-				 get_extent_t *get_extent, int mirror_num)
-{
-	struct bio *bio = NULL;
-	unsigned long bio_flags = EXTENT_BIO_PARENT_LOCKED;
-	int ret;
-
-	ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
-			    &bio_flags, READ, NULL);
-	if (bio)
-		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
-	return ret;
-}
-
 static noinline void update_nr_written(struct page *page,
 				      struct writeback_control *wbc,
 				      unsigned long nr_written)
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0377413bd4b9..5dbf92e68fbd 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -29,7 +29,6 @@
  */
 #define EXTENT_BIO_COMPRESSED 1
 #define EXTENT_BIO_TREE_LOG 2
-#define EXTENT_BIO_PARENT_LOCKED 4
 #define EXTENT_BIO_FLAG_SHIFT 16
 
 /* these are bit numbers for test/set bit */
@@ -62,6 +61,7 @@
 struct extent_state;
 struct btrfs_root;
 struct btrfs_io_bio;
+struct io_failure_record;
 
 typedef	int (extent_submit_bio_hook_t)(struct inode *inode, int rw,
 				       struct bio *bio, int mirror_num,
@@ -112,8 +112,7 @@ struct extent_state {
 	atomic_t refs;
 	unsigned state;
 
-	/* for use by the FS */
-	u64 private;
+	struct io_failure_record *failrec;
 
 #ifdef CONFIG_BTRFS_DEBUG
 	struct list_head leak_list;
@@ -210,8 +209,6 @@ static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 			  get_extent_t *get_extent, int mirror_num);
-int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
-				 get_extent_t *get_extent, int mirror_num);
 int __init extent_io_init(void);
 void extent_io_exit(void);
 
@@ -345,7 +342,6 @@ int extent_readpages(struct extent_io_tree *tree,
 		     get_extent_t get_extent);
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len, get_extent_t *get_extent);
-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,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 84fb56d5c018..318b048eb254 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -4,6 +4,7 @@
 #include <linux/hardirq.h>
 #include "ctree.h"
 #include "extent_map.h"
+#include "compression.h"
 
 
 static struct kmem_cache *extent_map_cache;
@@ -20,8 +21,7 @@ int __init extent_map_init(void)
 
 void extent_map_exit(void)
 {
-	if (extent_map_cache)
-		kmem_cache_destroy(extent_map_cache);
+	kmem_cache_destroy(extent_map_cache);
 }
 
 /**
@@ -62,7 +62,7 @@ struct extent_map *alloc_extent_map(void)
 
 /**
  * free_extent_map - drop reference count of an extent_map
- * @em:		extent map beeing releasead
+ * @em:		extent map being releasead
  *
  * Drops the reference out on @em by one and free the structure
  * if the reference count hits zero.
@@ -422,7 +422,7 @@ struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
 /**
  * remove_extent_mapping - removes an extent_map from the extent tree
  * @tree:	extent tree to remove from
- * @em:		extent map beeing removed
+ * @em:		extent map being removed
  *
  * Removes @em from @tree.  No reference counts are dropped, and no checks
  * are done to see if the range is in use
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index a67e1c828d0f..b5baf5bdc8e1 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -25,6 +25,7 @@
 #include "transaction.h"
 #include "volumes.h"
 #include "print-tree.h"
+#include "compression.h"
 
 #define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \
 				   sizeof(struct btrfs_item) * 2) / \
@@ -172,6 +173,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	u64 item_start_offset = 0;
 	u64 item_last_offset = 0;
 	u64 disk_bytenr;
+	u64 page_bytes_left;
 	u32 diff;
 	int nblocks;
 	int bio_index = 0;
@@ -220,6 +222,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
 	if (dio)
 		offset = logical_offset;
+
+	page_bytes_left = bvec->bv_len;
 	while (bio_index < bio->bi_vcnt) {
 		if (!dio)
 			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
@@ -243,7 +247,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 				if (BTRFS_I(inode)->root->root_key.objectid ==
 				    BTRFS_DATA_RELOC_TREE_OBJECTID) {
 					set_extent_bits(io_tree, offset,
-						offset + bvec->bv_len - 1,
+						offset + root->sectorsize - 1,
 						EXTENT_NODATASUM, GFP_NOFS);
 				} else {
 					btrfs_info(BTRFS_I(inode)->root->fs_info,
@@ -281,13 +285,29 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 found:
 		csum += count * csum_size;
 		nblocks -= count;
-		bio_index += count;
+
 		while (count--) {
-			disk_bytenr += bvec->bv_len;
-			offset += bvec->bv_len;
-			bvec++;
+			disk_bytenr += root->sectorsize;
+			offset += root->sectorsize;
+			page_bytes_left -= root->sectorsize;
+			if (!page_bytes_left) {
+				bio_index++;
+				/*
+				 * make sure we're still inside the
+				 * bio before we update page_bytes_left
+				 */
+				if (bio_index >= bio->bi_vcnt) {
+					WARN_ON_ONCE(count);
+					goto done;
+				}
+				bvec++;
+				page_bytes_left = bvec->bv_len;
+			}
+
 		}
 	}
+
+done:
 	btrfs_free_path(path);
 	return 0;
 }
@@ -432,6 +452,8 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 	struct bio_vec *bvec = bio->bi_io_vec;
 	int bio_index = 0;
 	int index;
+	int nr_sectors;
+	int i;
 	unsigned long total_bytes = 0;
 	unsigned long this_sum_bytes = 0;
 	u64 offset;
@@ -459,41 +481,56 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		if (!contig)
 			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
 
-		if (offset >= ordered->file_offset + ordered->len ||
-		    offset < ordered->file_offset) {
-			unsigned long bytes_left;
-			sums->len = this_sum_bytes;
-			this_sum_bytes = 0;
-			btrfs_add_ordered_sum(inode, ordered, sums);
-			btrfs_put_ordered_extent(ordered);
+		data = kmap_atomic(bvec->bv_page);
 
-			bytes_left = bio->bi_iter.bi_size - total_bytes;
+		nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+						bvec->bv_len + root->sectorsize
+						- 1);
+
+		for (i = 0; i < nr_sectors; i++) {
+			if (offset >= ordered->file_offset + ordered->len ||
+				offset < ordered->file_offset) {
+				unsigned long bytes_left;
+
+				kunmap_atomic(data);
+				sums->len = this_sum_bytes;
+				this_sum_bytes = 0;
+				btrfs_add_ordered_sum(inode, ordered, sums);
+				btrfs_put_ordered_extent(ordered);
+
+				bytes_left = bio->bi_iter.bi_size - total_bytes;
+
+				sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
+					GFP_NOFS);
+				BUG_ON(!sums); /* -ENOMEM */
+				sums->len = bytes_left;
+				ordered = btrfs_lookup_ordered_extent(inode,
+								offset);
+				ASSERT(ordered); /* Logic error */
+				sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9)
+					+ total_bytes;
+				index = 0;
+
+				data = kmap_atomic(bvec->bv_page);
+			}
 
-			sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
-				       GFP_NOFS);
-			BUG_ON(!sums); /* -ENOMEM */
-			sums->len = bytes_left;
-			ordered = btrfs_lookup_ordered_extent(inode, offset);
-			BUG_ON(!ordered); /* Logic error */
-			sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
-				       total_bytes;
-			index = 0;
+			sums->sums[index] = ~(u32)0;
+			sums->sums[index]
+				= btrfs_csum_data(data + bvec->bv_offset
+						+ (i * root->sectorsize),
+						sums->sums[index],
+						root->sectorsize);
+			btrfs_csum_final(sums->sums[index],
+					(char *)(sums->sums + index));
+			index++;
+			offset += root->sectorsize;
+			this_sum_bytes += root->sectorsize;
+			total_bytes += root->sectorsize;
 		}
 
-		data = kmap_atomic(bvec->bv_page);
-		sums->sums[index] = ~(u32)0;
-		sums->sums[index] = btrfs_csum_data(data + bvec->bv_offset,
-						    sums->sums[index],
-						    bvec->bv_len);
 		kunmap_atomic(data);
-		btrfs_csum_final(sums->sums[index],
-				 (char *)(sums->sums + index));
 
 		bio_index++;
-		index++;
-		total_bytes += bvec->bv_len;
-		this_sum_bytes += bvec->bv_len;
-		offset += bvec->bv_len;
 		bvec++;
 	}
 	this_sum_bytes = 0;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 098bb8f690c9..15a09cb156ce 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -41,6 +41,7 @@
 #include "locking.h"
 #include "volumes.h"
 #include "qgroup.h"
+#include "compression.h"
 
 static struct kmem_cache *btrfs_inode_defrag_cachep;
 /*
@@ -498,7 +499,7 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
 	loff_t isize = i_size_read(inode);
 
 	start_pos = pos & ~((u64)root->sectorsize - 1);
-	num_bytes = ALIGN(write_bytes + pos - start_pos, root->sectorsize);
+	num_bytes = round_up(write_bytes + pos - start_pos, root->sectorsize);
 
 	end_of_last_block = start_pos + num_bytes - 1;
 	err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
@@ -1379,16 +1380,19 @@ fail:
 static noinline int
 lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 				size_t num_pages, loff_t pos,
+				size_t write_bytes,
 				u64 *lockstart, u64 *lockend,
 				struct extent_state **cached_state)
 {
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	u64 start_pos;
 	u64 last_pos;
 	int i;
 	int ret = 0;
 
-	start_pos = pos & ~((u64)PAGE_CACHE_SIZE - 1);
-	last_pos = start_pos + ((u64)num_pages << PAGE_CACHE_SHIFT) - 1;
+	start_pos = round_down(pos, root->sectorsize);
+	last_pos = start_pos
+		+ round_up(pos + write_bytes - start_pos, root->sectorsize) - 1;
 
 	if (start_pos < inode->i_size) {
 		struct btrfs_ordered_extent *ordered;
@@ -1503,6 +1507,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 
 	while (iov_iter_count(i) > 0) {
 		size_t offset = pos & (PAGE_CACHE_SIZE - 1);
+		size_t sector_offset;
 		size_t write_bytes = min(iov_iter_count(i),
 					 nrptrs * (size_t)PAGE_CACHE_SIZE -
 					 offset);
@@ -1511,6 +1516,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		size_t reserve_bytes;
 		size_t dirty_pages;
 		size_t copied;
+		size_t dirty_sectors;
+		size_t num_sectors;
 
 		WARN_ON(num_pages > nrptrs);
 
@@ -1523,29 +1530,29 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			break;
 		}
 
-		reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+		sector_offset = pos & (root->sectorsize - 1);
+		reserve_bytes = round_up(write_bytes + sector_offset,
+				root->sectorsize);
 
-		if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
-					     BTRFS_INODE_PREALLOC)) {
-			ret = check_can_nocow(inode, pos, &write_bytes);
-			if (ret < 0)
-				break;
-			if (ret > 0) {
-				/*
-				 * For nodata cow case, no need to reserve
-				 * data space.
-				 */
-				only_release_metadata = true;
-				/*
-				 * our prealloc extent may be smaller than
-				 * write_bytes, so scale down.
-				 */
-				num_pages = DIV_ROUND_UP(write_bytes + offset,
-							 PAGE_CACHE_SIZE);
-				reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
-				goto reserve_metadata;
-			}
+		if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+					      BTRFS_INODE_PREALLOC)) &&
+		    check_can_nocow(inode, pos, &write_bytes) > 0) {
+			/*
+			 * For nodata cow case, no need to reserve
+			 * data space.
+			 */
+			only_release_metadata = true;
+			/*
+			 * our prealloc extent may be smaller than
+			 * write_bytes, so scale down.
+			 */
+			num_pages = DIV_ROUND_UP(write_bytes + offset,
+						 PAGE_CACHE_SIZE);
+			reserve_bytes = round_up(write_bytes + sector_offset,
+					root->sectorsize);
+			goto reserve_metadata;
 		}
+
 		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
 		if (ret < 0)
 			break;
@@ -1576,8 +1583,8 @@ again:
 			break;
 
 		ret = lock_and_cleanup_extent_if_need(inode, pages, num_pages,
-						      pos, &lockstart, &lockend,
-						      &cached_state);
+						pos, write_bytes, &lockstart,
+						&lockend, &cached_state);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				goto again;
@@ -1612,9 +1619,16 @@ again:
 		 * we still have an outstanding extent for the chunk we actually
 		 * managed to copy.
 		 */
-		if (num_pages > dirty_pages) {
-			release_bytes = (num_pages - dirty_pages) <<
-				PAGE_CACHE_SHIFT;
+		num_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+						reserve_bytes);
+		dirty_sectors = round_up(copied + sector_offset,
+					root->sectorsize);
+		dirty_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+						dirty_sectors);
+
+		if (num_sectors > dirty_sectors) {
+			release_bytes = (write_bytes - copied)
+				& ~((u64)root->sectorsize - 1);
 			if (copied > 0) {
 				spin_lock(&BTRFS_I(inode)->lock);
 				BTRFS_I(inode)->outstanding_extents++;
@@ -1633,7 +1647,8 @@ again:
 			}
 		}
 
-		release_bytes = dirty_pages << PAGE_CACHE_SHIFT;
+		release_bytes = round_up(copied + sector_offset,
+					root->sectorsize);
 
 		if (copied > 0)
 			ret = btrfs_dirty_pages(root, inode, pages,
@@ -1654,8 +1669,7 @@ again:
 
 		if (only_release_metadata && copied > 0) {
 			lockstart = round_down(pos, root->sectorsize);
-			lockend = lockstart +
-				(dirty_pages << PAGE_CACHE_SHIFT) - 1;
+			lockend = round_up(pos + copied, root->sectorsize) - 1;
 
 			set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
 				       lockend, EXTENT_NORESERVE, NULL,
@@ -1761,6 +1775,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	ssize_t err;
 	loff_t pos;
 	size_t count;
+	loff_t oldsize;
+	int clean_page = 0;
 
 	inode_lock(inode);
 	err = generic_write_checks(iocb, from);
@@ -1799,14 +1815,17 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	pos = iocb->ki_pos;
 	count = iov_iter_count(from);
 	start_pos = round_down(pos, root->sectorsize);
-	if (start_pos > i_size_read(inode)) {
+	oldsize = i_size_read(inode);
+	if (start_pos > oldsize) {
 		/* Expand hole size to cover write data, preventing empty gap */
 		end_pos = round_up(pos + count, root->sectorsize);
-		err = btrfs_cont_expand(inode, i_size_read(inode), end_pos);
+		err = btrfs_cont_expand(inode, oldsize, end_pos);
 		if (err) {
 			inode_unlock(inode);
 			goto out;
 		}
+		if (start_pos > round_up(oldsize, root->sectorsize))
+			clean_page = 1;
 	}
 
 	if (sync)
@@ -1818,6 +1837,9 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 		num_written = __btrfs_buffered_write(file, from, pos);
 		if (num_written > 0)
 			iocb->ki_pos = pos + num_written;
+		if (clean_page)
+			pagecache_isize_extended(inode, oldsize,
+						i_size_read(inode));
 	}
 
 	inode_unlock(inode);
@@ -1825,7 +1847,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	/*
 	 * 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.
+	 * transaction will appear to have already occurred.
 	 */
 	spin_lock(&BTRFS_I(inode)->lock);
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
@@ -1996,10 +2018,11 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 */
 	smp_mb();
 	if (btrfs_inode_in_log(inode, root->fs_info->generation) ||
-	    (BTRFS_I(inode)->last_trans <=
-	     root->fs_info->last_trans_committed &&
-	     (full_sync ||
-	      !btrfs_have_ordered_extents_in_range(inode, start, len)))) {
+	    (full_sync && BTRFS_I(inode)->last_trans <=
+	     root->fs_info->last_trans_committed) ||
+	    (!btrfs_have_ordered_extents_in_range(inode, start, len) &&
+	     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
@@ -2293,10 +2316,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	int ret = 0;
 	int err = 0;
 	unsigned int rsv_count;
-	bool same_page;
+	bool same_block;
 	bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
 	u64 ino_size;
-	bool truncated_page = false;
+	bool truncated_block = false;
 	bool updated_inode = false;
 
 	ret = btrfs_wait_ordered_range(inode, offset, len);
@@ -2304,7 +2327,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		return ret;
 
 	inode_lock(inode);
-	ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
+	ino_size = round_up(inode->i_size, root->sectorsize);
 	ret = find_first_non_hole(inode, &offset, &len);
 	if (ret < 0)
 		goto out_only_mutex;
@@ -2317,31 +2340,30 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
 	lockend = round_down(offset + len,
 			     BTRFS_I(inode)->root->sectorsize) - 1;
-	same_page = ((offset >> PAGE_CACHE_SHIFT) ==
-		    ((offset + len - 1) >> PAGE_CACHE_SHIFT));
-
+	same_block = (BTRFS_BYTES_TO_BLKS(root->fs_info, offset))
+		== (BTRFS_BYTES_TO_BLKS(root->fs_info, offset + len - 1));
 	/*
-	 * We needn't truncate any page which is beyond the end of the file
+	 * We needn't truncate any block which is beyond the end of the file
 	 * because we are sure there is no data there.
 	 */
 	/*
-	 * Only do this if we are in the same page and we aren't doing the
-	 * entire page.
+	 * Only do this if we are in the same block and we aren't doing the
+	 * entire block.
 	 */
-	if (same_page && len < PAGE_CACHE_SIZE) {
+	if (same_block && len < root->sectorsize) {
 		if (offset < ino_size) {
-			truncated_page = true;
-			ret = btrfs_truncate_page(inode, offset, len, 0);
+			truncated_block = true;
+			ret = btrfs_truncate_block(inode, offset, len, 0);
 		} else {
 			ret = 0;
 		}
 		goto out_only_mutex;
 	}
 
-	/* zero back part of the first page */
+	/* zero back part of the first block */
 	if (offset < ino_size) {
-		truncated_page = true;
-		ret = btrfs_truncate_page(inode, offset, 0, 0);
+		truncated_block = true;
+		ret = btrfs_truncate_block(inode, offset, 0, 0);
 		if (ret) {
 			inode_unlock(inode);
 			return ret;
@@ -2376,9 +2398,10 @@ 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);
+				truncated_block = true;
+				ret = btrfs_truncate_block(inode,
+							tail_start + tail_len,
+							0, 1);
 				if (ret)
 					goto out_only_mutex;
 			}
@@ -2544,7 +2567,7 @@ out_trans:
 		goto out_free;
 
 	inode_inc_iversion(inode);
-	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb);
 
 	trans->block_rsv = &root->fs_info->trans_block_rsv;
 	ret = btrfs_update_inode(trans, root, inode);
@@ -2558,7 +2581,7 @@ 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 (!updated_inode && truncated_block && !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
@@ -2611,7 +2634,7 @@ static int add_falloc_range(struct list_head *head, u64 start, u64 len)
 		return 0;
 	}
 insert:
-	range = kmalloc(sizeof(*range), GFP_NOFS);
+	range = kmalloc(sizeof(*range), GFP_KERNEL);
 	if (!range)
 		return -ENOMEM;
 	range->start = start;
@@ -2678,10 +2701,10 @@ static long btrfs_fallocate(struct file *file, int mode,
 	} else if (offset + len > inode->i_size) {
 		/*
 		 * If we are fallocating from the end of the file onward we
-		 * need to zero out the end of the page if i_size lands in the
-		 * middle of a page.
+		 * need to zero out the end of the block if i_size lands in the
+		 * middle of a block.
 		 */
-		ret = btrfs_truncate_page(inode, inode->i_size, 0, 0);
+		ret = btrfs_truncate_block(inode, inode->i_size, 0, 0);
 		if (ret)
 			goto out;
 	}
@@ -2712,7 +2735,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 			btrfs_put_ordered_extent(ordered);
 			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 					     alloc_start, locked_end,
-					     &cached_state, GFP_NOFS);
+					     &cached_state, GFP_KERNEL);
 			/*
 			 * we can't wait on the range with the transaction
 			 * running or with the extent lock held
@@ -2794,7 +2817,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		if (IS_ERR(trans)) {
 			ret = PTR_ERR(trans);
 		} else {
-			inode->i_ctime = CURRENT_TIME;
+			inode->i_ctime = current_fs_time(inode->i_sb);
 			i_size_write(inode, actual_end);
 			btrfs_ordered_update_i_size(inode, actual_end, NULL);
 			ret = btrfs_update_inode(trans, root, inode);
@@ -2806,7 +2829,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 	}
 out_unlock:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
-			     &cached_state, GFP_NOFS);
+			     &cached_state, GFP_KERNEL);
 out:
 	/*
 	 * As we waited the extent range, the data_rsv_map must be empty
@@ -2939,8 +2962,7 @@ const struct file_operations btrfs_file_operations = {
 
 void btrfs_auto_defrag_exit(void)
 {
-	if (btrfs_inode_defrag_cachep)
-		kmem_cache_destroy(btrfs_inode_defrag_cachep);
+	kmem_cache_destroy(btrfs_inode_defrag_cachep);
 }
 
 int btrfs_auto_defrag_init(void)
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 393e36bd5845..53dbeaf6ce94 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -153,6 +153,20 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize)
 
 static unsigned long *alloc_bitmap(u32 bitmap_size)
 {
+	void *mem;
+
+	/*
+	 * The allocation size varies, observed numbers were < 4K up to 16K.
+	 * Using vmalloc unconditionally would be too heavy, we'll try
+	 * contiguous allocations first.
+	 */
+	if  (bitmap_size <= PAGE_SIZE)
+		return kzalloc(bitmap_size, GFP_NOFS);
+
+	mem = kzalloc(bitmap_size, GFP_NOFS | __GFP_NOWARN);
+	if (mem)
+		return mem;
+
 	return __vmalloc(bitmap_size, GFP_NOFS | __GFP_HIGHMEM | __GFP_ZERO,
 			 PAGE_KERNEL);
 }
@@ -289,7 +303,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 
 	ret = 0;
 out:
-	vfree(bitmap);
+	kvfree(bitmap);
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
 	return ret;
@@ -438,7 +452,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 
 	ret = 0;
 out:
-	vfree(bitmap);
+	kvfree(bitmap);
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
 	return ret;
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index e50316c4af15..1f0ec19b23f6 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -556,6 +556,9 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
 	mutex_lock(&root->objectid_mutex);
 
 	if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
+		btrfs_warn(root->fs_info,
+			   "the objectid of root %llu reaches its highest value",
+			   root->root_key.objectid);
 		ret = -ENOSPC;
 		goto out;
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e28f3d4691af..41a5688ffdfe 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -263,7 +263,7 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
 		data_len = compressed_size;
 
 	if (start > 0 ||
-	    actual_end > PAGE_CACHE_SIZE ||
+	    actual_end > root->sectorsize ||
 	    data_len > BTRFS_MAX_INLINE_DATA_SIZE(root) ||
 	    (!compressed_size &&
 	    (actual_end & (root->sectorsize - 1)) == 0) ||
@@ -2002,7 +2002,8 @@ again:
 	if (PagePrivate2(page))
 		goto out;
 
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+	ordered = btrfs_lookup_ordered_range(inode, page_start,
+					PAGE_CACHE_SIZE);
 	if (ordered) {
 		unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
 				     page_end, &cached_state, GFP_NOFS);
@@ -4013,7 +4014,8 @@ err:
 	btrfs_i_size_write(dir, dir->i_size - name_len * 2);
 	inode_inc_iversion(inode);
 	inode_inc_iversion(dir);
-	inode->i_ctime = dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	inode->i_ctime = dir->i_mtime =
+		dir->i_ctime = current_fs_time(inode->i_sb);
 	ret = btrfs_update_inode(trans, root, dir);
 out:
 	return ret;
@@ -4156,7 +4158,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 
 	btrfs_i_size_write(dir, dir->i_size - name_len * 2);
 	inode_inc_iversion(dir);
-	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
 	ret = btrfs_update_inode_fallback(trans, root, dir);
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
@@ -4211,11 +4213,20 @@ static int truncate_space_check(struct btrfs_trans_handle *trans,
 {
 	int ret;
 
+	/*
+	 * This is only used to apply pressure to the enospc system, we don't
+	 * intend to use this reservation at all.
+	 */
 	bytes_deleted = btrfs_csum_bytes_to_leaves(root, bytes_deleted);
+	bytes_deleted *= root->nodesize;
 	ret = btrfs_block_rsv_add(root, &root->fs_info->trans_block_rsv,
 				  bytes_deleted, BTRFS_RESERVE_NO_FLUSH);
-	if (!ret)
+	if (!ret) {
+		trace_btrfs_space_reservation(root->fs_info, "transaction",
+					      trans->transid,
+					      bytes_deleted, 1);
 		trans->bytes_reserved += bytes_deleted;
+	}
 	return ret;
 
 }
@@ -4248,7 +4259,8 @@ static int truncate_inline_extent(struct inode *inode,
 		 * read the extent item from disk (data not in the page cache).
 		 */
 		btrfs_release_path(path);
-		return btrfs_truncate_page(inode, offset, page_end - offset, 0);
+		return btrfs_truncate_block(inode, offset, page_end - offset,
+					0);
 	}
 
 	btrfs_set_file_extent_ram_bytes(leaf, fi, size);
@@ -4601,17 +4613,17 @@ error:
 }
 
 /*
- * btrfs_truncate_page - read, zero a chunk and write a page
+ * btrfs_truncate_block - read, zero a chunk and write a block
  * @inode - inode that we're zeroing
  * @from - the offset to start zeroing
  * @len - the length to zero, 0 to zero the entire range respective to the
  *	offset
  * @front - zero up to the offset instead of from the offset on
  *
- * This will find the page for the "from" offset and cow the page and zero the
+ * This will find the block for the "from" offset and cow the block and zero the
  * part we want to zero.  This is used with truncate and hole punching.
  */
-int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
+int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 			int front)
 {
 	struct address_space *mapping = inode->i_mapping;
@@ -4622,18 +4634,19 @@ int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
 	char *kaddr;
 	u32 blocksize = root->sectorsize;
 	pgoff_t index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned offset = from & (blocksize - 1);
 	struct page *page;
 	gfp_t mask = btrfs_alloc_write_mask(mapping);
 	int ret = 0;
-	u64 page_start;
-	u64 page_end;
+	u64 block_start;
+	u64 block_end;
 
 	if ((offset & (blocksize - 1)) == 0 &&
 	    (!len || ((len & (blocksize - 1)) == 0)))
 		goto out;
+
 	ret = btrfs_delalloc_reserve_space(inode,
-			round_down(from, PAGE_CACHE_SIZE), PAGE_CACHE_SIZE);
+			round_down(from, blocksize), blocksize);
 	if (ret)
 		goto out;
 
@@ -4641,14 +4654,14 @@ again:
 	page = find_or_create_page(mapping, index, mask);
 	if (!page) {
 		btrfs_delalloc_release_space(inode,
-				round_down(from, PAGE_CACHE_SIZE),
-				PAGE_CACHE_SIZE);
+				round_down(from, blocksize),
+				blocksize);
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	page_start = page_offset(page);
-	page_end = page_start + PAGE_CACHE_SIZE - 1;
+	block_start = round_down(from, blocksize);
+	block_end = block_start + blocksize - 1;
 
 	if (!PageUptodate(page)) {
 		ret = btrfs_readpage(NULL, page);
@@ -4665,12 +4678,12 @@ again:
 	}
 	wait_on_page_writeback(page);
 
-	lock_extent_bits(io_tree, page_start, page_end, &cached_state);
+	lock_extent_bits(io_tree, block_start, block_end, &cached_state);
 	set_page_extent_mapped(page);
 
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+	ordered = btrfs_lookup_ordered_extent(inode, block_start);
 	if (ordered) {
-		unlock_extent_cached(io_tree, page_start, page_end,
+		unlock_extent_cached(io_tree, block_start, block_end,
 				     &cached_state, GFP_NOFS);
 		unlock_page(page);
 		page_cache_release(page);
@@ -4679,39 +4692,41 @@ again:
 		goto again;
 	}
 
-	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end,
+	clear_extent_bit(&BTRFS_I(inode)->io_tree, block_start, block_end,
 			  EXTENT_DIRTY | EXTENT_DELALLOC |
 			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
 			  0, 0, &cached_state, GFP_NOFS);
 
-	ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
+	ret = btrfs_set_extent_delalloc(inode, block_start, block_end,
 					&cached_state);
 	if (ret) {
-		unlock_extent_cached(io_tree, page_start, page_end,
+		unlock_extent_cached(io_tree, block_start, block_end,
 				     &cached_state, GFP_NOFS);
 		goto out_unlock;
 	}
 
-	if (offset != PAGE_CACHE_SIZE) {
+	if (offset != blocksize) {
 		if (!len)
-			len = PAGE_CACHE_SIZE - offset;
+			len = blocksize - offset;
 		kaddr = kmap(page);
 		if (front)
-			memset(kaddr, 0, offset);
+			memset(kaddr + (block_start - page_offset(page)),
+				0, offset);
 		else
-			memset(kaddr + offset, 0, len);
+			memset(kaddr + (block_start - page_offset(page)) +  offset,
+				0, len);
 		flush_dcache_page(page);
 		kunmap(page);
 	}
 	ClearPageChecked(page);
 	set_page_dirty(page);
-	unlock_extent_cached(io_tree, page_start, page_end, &cached_state,
+	unlock_extent_cached(io_tree, block_start, block_end, &cached_state,
 			     GFP_NOFS);
 
 out_unlock:
 	if (ret)
-		btrfs_delalloc_release_space(inode, page_start,
-					     PAGE_CACHE_SIZE);
+		btrfs_delalloc_release_space(inode, block_start,
+					     blocksize);
 	unlock_page(page);
 	page_cache_release(page);
 out:
@@ -4782,11 +4797,11 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 	int err = 0;
 
 	/*
-	 * If our size started in the middle of a page we need to zero out the
-	 * rest of the page before we expand the i_size, otherwise we could
+	 * If our size started in the middle of a block we need to zero out the
+	 * rest of the block before we expand the i_size, otherwise we could
 	 * expose stale data.
 	 */
-	err = btrfs_truncate_page(inode, oldsize, 0, 0);
+	err = btrfs_truncate_block(inode, oldsize, 0, 0);
 	if (err)
 		return err;
 
@@ -4895,7 +4910,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 	}
 
 	if (newsize > oldsize) {
-		truncate_pagecache(inode, newsize);
 		/*
 		 * Don't do an expanding truncate while snapshoting is ongoing.
 		 * This is to ensure the snapshot captures a fully consistent
@@ -4918,6 +4932,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 
 		i_size_write(inode, newsize);
 		btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+		pagecache_isize_extended(inode, oldsize, newsize);
 		ret = btrfs_update_inode(trans, root, inode);
 		btrfs_end_write_no_snapshoting(root);
 		btrfs_end_transaction(trans, root);
@@ -5588,7 +5603,7 @@ 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 = CURRENT_TIME;
+	inode->i_mtime = current_fs_time(inode->i_sb);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
 	BTRFS_I(inode)->i_otime = inode->i_mtime;
@@ -5717,6 +5732,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	char *name_ptr;
 	int name_len;
 	int is_curr = 0;	/* ctx->pos points to the current index? */
+	bool emitted;
 
 	/* FIXME, use a real flag for deciding about the key type */
 	if (root->fs_info->tree_root == root)
@@ -5745,6 +5761,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (ret < 0)
 		goto err;
 
+	emitted = false;
 	while (1) {
 		leaf = path->nodes[0];
 		slot = path->slots[0];
@@ -5788,7 +5805,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 			if (name_len <= sizeof(tmp_name)) {
 				name_ptr = tmp_name;
 			} else {
-				name_ptr = kmalloc(name_len, GFP_NOFS);
+				name_ptr = kmalloc(name_len, GFP_KERNEL);
 				if (!name_ptr) {
 					ret = -ENOMEM;
 					goto err;
@@ -5824,6 +5841,7 @@ skip:
 
 			if (over)
 				goto nopos;
+			emitted = true;
 			di_len = btrfs_dir_name_len(leaf, di) +
 				 btrfs_dir_data_len(leaf, di) + sizeof(*di);
 			di_cur += di_len;
@@ -5836,11 +5854,20 @@ next:
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		if (is_curr)
 			ctx->pos++;
-		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
+		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted);
 		if (ret)
 			goto nopos;
 	}
 
+	/*
+	 * If we haven't emitted any dir entry, we must not touch ctx->pos as
+	 * it was was set to the termination value in previous call. We assume
+	 * that "." and ".." were emitted if we reach this point and set the
+	 * termination value as well for an empty directory.
+	 */
+	if (ctx->pos > 2 && !emitted)
+		goto nopos;
+
 	/* Reached end of directory/root. Bump pos past the last item. */
 	ctx->pos++;
 
@@ -6160,7 +6187,7 @@ 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 = CURRENT_TIME;
+	inode->i_mtime = current_fs_time(inode->i_sb);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
 	BTRFS_I(inode)->i_otime = inode->i_mtime;
@@ -6273,7 +6300,8 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 	btrfs_i_size_write(parent_inode, parent_inode->i_size +
 			   name_len * 2);
 	inode_inc_iversion(parent_inode);
-	parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
+	parent_inode->i_mtime = parent_inode->i_ctime =
+		current_fs_time(parent_inode->i_sb);
 	ret = btrfs_update_inode(trans, root, parent_inode);
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
@@ -6491,7 +6519,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	BTRFS_I(inode)->dir_index = 0ULL;
 	inc_nlink(inode);
 	inode_inc_iversion(inode);
-	inode->i_ctime = CURRENT_TIME;
+	inode->i_ctime = current_fs_time(inode->i_sb);
 	ihold(inode);
 	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
 
@@ -7116,21 +7144,41 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 	if (ret)
 		return ERR_PTR(ret);
 
-	em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
-			      ins.offset, ins.offset, ins.offset, 0);
-	if (IS_ERR(em)) {
-		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
-		return em;
-	}
-
+	/*
+	 * Create the ordered extent before the extent map. This is to avoid
+	 * races with the fast fsync path that would lead to it logging file
+	 * extent items that point to disk extents that were not yet written to.
+	 * The fast fsync path collects ordered extents into a local list and
+	 * then collects all the new extent maps, so we must create the ordered
+	 * extent first and make sure the fast fsync path collects any new
+	 * ordered extents after collecting new extent maps as well.
+	 * The fsync path simply can not rely on inode_dio_wait() because it
+	 * causes deadlock with AIO.
+	 */
 	ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
 					   ins.offset, ins.offset, 0);
 	if (ret) {
 		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
-		free_extent_map(em);
 		return ERR_PTR(ret);
 	}
 
+	em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
+			      ins.offset, ins.offset, ins.offset, 0);
+	if (IS_ERR(em)) {
+		struct btrfs_ordered_extent *oe;
+
+		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
+		oe = btrfs_lookup_ordered_extent(inode, start);
+		ASSERT(oe);
+		if (WARN_ON(!oe))
+			return em;
+		set_bit(BTRFS_ORDERED_IOERR, &oe->flags);
+		set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags);
+		btrfs_remove_ordered_extent(inode, oe);
+		/* Once for our lookup and once for the ordered extents tree. */
+		btrfs_put_ordered_extent(oe);
+		btrfs_put_ordered_extent(oe);
+	}
 	return em;
 }
 
@@ -7382,7 +7430,26 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 				     cached_state, GFP_NOFS);
 
 		if (ordered) {
-			btrfs_start_ordered_extent(inode, ordered, 1);
+			/*
+			 * If we are doing a DIO read and the ordered extent we
+			 * found is for a buffered write, we can not wait for it
+			 * to complete and retry, because if we do so we can
+			 * deadlock with concurrent buffered writes on page
+			 * locks. This happens only if our DIO read covers more
+			 * than one extent map, if at this point has already
+			 * created an ordered extent for a previous extent map
+			 * and locked its range in the inode's io tree, and a
+			 * concurrent write against that previous extent map's
+			 * range and this range started (we unlock the ranges
+			 * in the io tree only when the bios complete and
+			 * buffered writes always lock pages before attempting
+			 * to lock range in the io tree).
+			 */
+			if (writing ||
+			    test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags))
+				btrfs_start_ordered_extent(inode, ordered, 1);
+			else
+				ret = -ENOTBLK;
 			btrfs_put_ordered_extent(ordered);
 		} else {
 			/*
@@ -7399,9 +7466,11 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 			 * that page.
 			 */
 			ret = -ENOTBLK;
-			break;
 		}
 
+		if (ret)
+			break;
+
 		cond_resched();
 	}
 
@@ -7732,9 +7801,9 @@ static int btrfs_check_dio_repairable(struct inode *inode,
 }
 
 static int dio_read_error(struct inode *inode, struct bio *failed_bio,
-			  struct page *page, u64 start, u64 end,
-			  int failed_mirror, bio_end_io_t *repair_endio,
-			  void *repair_arg)
+			struct page *page, unsigned int pgoff,
+			u64 start, u64 end, int failed_mirror,
+			bio_end_io_t *repair_endio, void *repair_arg)
 {
 	struct io_failure_record *failrec;
 	struct bio *bio;
@@ -7755,7 +7824,9 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 		return -EIO;
 	}
 
-	if (failed_bio->bi_vcnt > 1)
+	if ((failed_bio->bi_vcnt > 1)
+		|| (failed_bio->bi_io_vec->bv_len
+			> BTRFS_I(inode)->root->sectorsize))
 		read_mode = READ_SYNC | REQ_FAILFAST_DEV;
 	else
 		read_mode = READ_SYNC;
@@ -7763,7 +7834,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	isector = start - btrfs_io_bio(failed_bio)->logical;
 	isector >>= inode->i_sb->s_blocksize_bits;
 	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
-				      0, isector, repair_endio, repair_arg);
+				pgoff, isector, repair_endio, repair_arg);
 	if (!bio) {
 		free_io_failure(inode, failrec);
 		return -EIO;
@@ -7793,12 +7864,17 @@ struct btrfs_retry_complete {
 static void btrfs_retry_endio_nocsum(struct bio *bio)
 {
 	struct btrfs_retry_complete *done = bio->bi_private;
+	struct inode *inode;
 	struct bio_vec *bvec;
 	int i;
 
 	if (bio->bi_error)
 		goto end;
 
+	ASSERT(bio->bi_vcnt == 1);
+	inode = bio->bi_io_vec->bv_page->mapping->host;
+	ASSERT(bio->bi_io_vec->bv_len == BTRFS_I(inode)->root->sectorsize);
+
 	done->uptodate = 1;
 	bio_for_each_segment_all(bvec, bio, i)
 		clean_io_failure(done->inode, done->start, bvec->bv_page, 0);
@@ -7810,25 +7886,35 @@ end:
 static int __btrfs_correct_data_nocsum(struct inode *inode,
 				       struct btrfs_io_bio *io_bio)
 {
+	struct btrfs_fs_info *fs_info;
 	struct bio_vec *bvec;
 	struct btrfs_retry_complete done;
 	u64 start;
+	unsigned int pgoff;
+	u32 sectorsize;
+	int nr_sectors;
 	int i;
 	int ret;
 
+	fs_info = BTRFS_I(inode)->root->fs_info;
+	sectorsize = BTRFS_I(inode)->root->sectorsize;
+
 	start = io_bio->logical;
 	done.inode = inode;
 
 	bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-try_again:
+		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+		pgoff = bvec->bv_offset;
+
+next_block_or_try_again:
 		done.uptodate = 0;
 		done.start = start;
 		init_completion(&done.done);
 
-		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start,
-				     start + bvec->bv_len - 1,
-				     io_bio->mirror_num,
-				     btrfs_retry_endio_nocsum, &done);
+		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+				pgoff, start, start + sectorsize - 1,
+				io_bio->mirror_num,
+				btrfs_retry_endio_nocsum, &done);
 		if (ret)
 			return ret;
 
@@ -7836,10 +7922,15 @@ try_again:
 
 		if (!done.uptodate) {
 			/* We might have another mirror, so try again */
-			goto try_again;
+			goto next_block_or_try_again;
 		}
 
-		start += bvec->bv_len;
+		start += sectorsize;
+
+		if (nr_sectors--) {
+			pgoff += sectorsize;
+			goto next_block_or_try_again;
+		}
 	}
 
 	return 0;
@@ -7849,7 +7940,9 @@ static void btrfs_retry_endio(struct bio *bio)
 {
 	struct btrfs_retry_complete *done = bio->bi_private;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+	struct inode *inode;
 	struct bio_vec *bvec;
+	u64 start;
 	int uptodate;
 	int ret;
 	int i;
@@ -7858,13 +7951,20 @@ static void btrfs_retry_endio(struct bio *bio)
 		goto end;
 
 	uptodate = 1;
+
+	start = done->start;
+
+	ASSERT(bio->bi_vcnt == 1);
+	inode = bio->bi_io_vec->bv_page->mapping->host;
+	ASSERT(bio->bi_io_vec->bv_len == BTRFS_I(inode)->root->sectorsize);
+
 	bio_for_each_segment_all(bvec, bio, i) {
 		ret = __readpage_endio_check(done->inode, io_bio, i,
-					     bvec->bv_page, 0,
-					     done->start, bvec->bv_len);
+					bvec->bv_page, bvec->bv_offset,
+					done->start, bvec->bv_len);
 		if (!ret)
 			clean_io_failure(done->inode, done->start,
-					 bvec->bv_page, 0);
+					bvec->bv_page, bvec->bv_offset);
 		else
 			uptodate = 0;
 	}
@@ -7878,20 +7978,34 @@ end:
 static int __btrfs_subio_endio_read(struct inode *inode,
 				    struct btrfs_io_bio *io_bio, int err)
 {
+	struct btrfs_fs_info *fs_info;
 	struct bio_vec *bvec;
 	struct btrfs_retry_complete done;
 	u64 start;
 	u64 offset = 0;
+	u32 sectorsize;
+	int nr_sectors;
+	unsigned int pgoff;
+	int csum_pos;
 	int i;
 	int ret;
 
+	fs_info = BTRFS_I(inode)->root->fs_info;
+	sectorsize = BTRFS_I(inode)->root->sectorsize;
+
 	err = 0;
 	start = io_bio->logical;
 	done.inode = inode;
 
 	bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-		ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
-					     0, start, bvec->bv_len);
+		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+
+		pgoff = bvec->bv_offset;
+next_block:
+		csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
+		ret = __readpage_endio_check(inode, io_bio, csum_pos,
+					bvec->bv_page, pgoff, start,
+					sectorsize);
 		if (likely(!ret))
 			goto next;
 try_again:
@@ -7899,10 +8013,10 @@ try_again:
 		done.start = start;
 		init_completion(&done.done);
 
-		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start,
-				     start + bvec->bv_len - 1,
-				     io_bio->mirror_num,
-				     btrfs_retry_endio, &done);
+		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+				pgoff, start, start + sectorsize - 1,
+				io_bio->mirror_num,
+				btrfs_retry_endio, &done);
 		if (ret) {
 			err = ret;
 			goto next;
@@ -7915,8 +8029,15 @@ try_again:
 			goto try_again;
 		}
 next:
-		offset += bvec->bv_len;
-		start += bvec->bv_len;
+		offset += sectorsize;
+		start += sectorsize;
+
+		ASSERT(nr_sectors);
+
+		if (--nr_sectors) {
+			pgoff += sectorsize;
+			goto next_block;
+		}
 	}
 
 	return err;
@@ -7954,6 +8075,7 @@ static void btrfs_endio_direct_read(struct bio *bio)
 
 	kfree(dip);
 
+	dio_bio->bi_error = bio->bi_error;
 	dio_end_io(dio_bio, bio->bi_error);
 
 	if (io_bio->end_io)
@@ -8008,6 +8130,7 @@ static void btrfs_endio_direct_write(struct bio *bio)
 
 	kfree(dip);
 
+	dio_bio->bi_error = bio->bi_error;
 	dio_end_io(dio_bio, bio->bi_error);
 	bio_put(bio);
 }
@@ -8168,9 +8291,11 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	u64 file_offset = dip->logical_offset;
 	u64 submit_len = 0;
 	u64 map_length;
-	int nr_pages = 0;
-	int ret;
+	u32 blocksize = root->sectorsize;
 	int async_submit = 0;
+	int nr_sectors;
+	int ret;
+	int i;
 
 	map_length = orig_bio->bi_iter.bi_size;
 	ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
@@ -8200,9 +8325,12 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	atomic_inc(&dip->pending_bios);
 
 	while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
-		if (map_length < submit_len + bvec->bv_len ||
-		    bio_add_page(bio, bvec->bv_page, bvec->bv_len,
-				 bvec->bv_offset) < bvec->bv_len) {
+		nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info, bvec->bv_len);
+		i = 0;
+next_block:
+		if (unlikely(map_length < submit_len + blocksize ||
+		    bio_add_page(bio, bvec->bv_page, blocksize,
+			    bvec->bv_offset + (i * blocksize)) < blocksize)) {
 			/*
 			 * inc the count before we submit the bio so
 			 * we know the end IO handler won't happen before
@@ -8223,7 +8351,6 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 			file_offset += submit_len;
 
 			submit_len = 0;
-			nr_pages = 0;
 
 			bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev,
 						  start_sector, GFP_NOFS);
@@ -8241,9 +8368,14 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 				bio_put(bio);
 				goto out_err;
 			}
+
+			goto next_block;
 		} else {
-			submit_len += bvec->bv_len;
-			nr_pages++;
+			submit_len += blocksize;
+			if (--nr_sectors) {
+				i++;
+				goto next_block;
+			}
 			bvec++;
 		}
 	}
@@ -8608,6 +8740,8 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 	struct extent_state *cached_state = NULL;
 	u64 page_start = page_offset(page);
 	u64 page_end = page_start + PAGE_CACHE_SIZE - 1;
+	u64 start;
+	u64 end;
 	int inode_evicting = inode->i_state & I_FREEING;
 
 	/*
@@ -8627,14 +8761,18 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 
 	if (!inode_evicting)
 		lock_extent_bits(tree, page_start, page_end, &cached_state);
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+again:
+	start = page_start;
+	ordered = btrfs_lookup_ordered_range(inode, start,
+					page_end - start + 1);
 	if (ordered) {
+		end = min(page_end, ordered->file_offset + ordered->len - 1);
 		/*
 		 * IO on this page will never be started, so we need
 		 * to account for any ordered extents now
 		 */
 		if (!inode_evicting)
-			clear_extent_bit(tree, page_start, page_end,
+			clear_extent_bit(tree, start, end,
 					 EXTENT_DIRTY | EXTENT_DELALLOC |
 					 EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
 					 EXTENT_DEFRAG, 1, 0, &cached_state,
@@ -8651,22 +8789,26 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 
 			spin_lock_irq(&tree->lock);
 			set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
-			new_len = page_start - ordered->file_offset;
+			new_len = start - ordered->file_offset;
 			if (new_len < ordered->truncated_len)
 				ordered->truncated_len = new_len;
 			spin_unlock_irq(&tree->lock);
 
 			if (btrfs_dec_test_ordered_pending(inode, &ordered,
-							   page_start,
-							   PAGE_CACHE_SIZE, 1))
+							   start,
+							   end - start + 1, 1))
 				btrfs_finish_ordered_io(ordered);
 		}
 		btrfs_put_ordered_extent(ordered);
 		if (!inode_evicting) {
 			cached_state = NULL;
-			lock_extent_bits(tree, page_start, page_end,
+			lock_extent_bits(tree, start, end,
 					 &cached_state);
 		}
+
+		start = end + 1;
+		if (start < page_end)
+			goto again;
 	}
 
 	/*
@@ -8727,15 +8869,28 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	loff_t size;
 	int ret;
 	int reserved = 0;
+	u64 reserved_space;
 	u64 page_start;
 	u64 page_end;
+	u64 end;
+
+	reserved_space = PAGE_CACHE_SIZE;
 
 	sb_start_pagefault(inode->i_sb);
 	page_start = page_offset(page);
 	page_end = page_start + PAGE_CACHE_SIZE - 1;
+	end = page_end;
 
+	/*
+	 * Reserving delalloc space after obtaining the page lock can lead to
+	 * deadlock. For example, if a dirty page is locked by this function
+	 * and the call to btrfs_delalloc_reserve_space() ends up triggering
+	 * dirty page write out, then the btrfs_writepage() function could
+	 * end up waiting indefinitely to get a lock on the page currently
+	 * being processed by btrfs_page_mkwrite() function.
+	 */
 	ret = btrfs_delalloc_reserve_space(inode, page_start,
-					   PAGE_CACHE_SIZE);
+					   reserved_space);
 	if (!ret) {
 		ret = file_update_time(vma->vm_file);
 		reserved = 1;
@@ -8769,7 +8924,7 @@ again:
 	 * we can't set the delalloc bits if there are pending ordered
 	 * extents.  Drop our locks and wait for them to finish
 	 */
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+	ordered = btrfs_lookup_ordered_range(inode, page_start, page_end);
 	if (ordered) {
 		unlock_extent_cached(io_tree, page_start, page_end,
 				     &cached_state, GFP_NOFS);
@@ -8779,6 +8934,18 @@ again:
 		goto again;
 	}
 
+	if (page->index == ((size - 1) >> PAGE_CACHE_SHIFT)) {
+		reserved_space = round_up(size - page_start, root->sectorsize);
+		if (reserved_space < PAGE_CACHE_SIZE) {
+			end = page_start + reserved_space - 1;
+			spin_lock(&BTRFS_I(inode)->lock);
+			BTRFS_I(inode)->outstanding_extents++;
+			spin_unlock(&BTRFS_I(inode)->lock);
+			btrfs_delalloc_release_space(inode, page_start,
+						PAGE_CACHE_SIZE - reserved_space);
+		}
+	}
+
 	/*
 	 * XXX - page_mkwrite gets called every time the page is dirtied, even
 	 * if it was already dirty, so for space accounting reasons we need to
@@ -8786,12 +8953,12 @@ again:
 	 * is probably a better way to do this, but for now keep consistent with
 	 * prepare_pages in the normal write path.
 	 */
-	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end,
+	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end,
 			  EXTENT_DIRTY | EXTENT_DELALLOC |
 			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
 			  0, 0, &cached_state, GFP_NOFS);
 
-	ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
+	ret = btrfs_set_extent_delalloc(inode, page_start, end,
 					&cached_state);
 	if (ret) {
 		unlock_extent_cached(io_tree, page_start, page_end,
@@ -8830,7 +8997,7 @@ out_unlock:
 	}
 	unlock_page(page);
 out:
-	btrfs_delalloc_release_space(inode, page_start, PAGE_CACHE_SIZE);
+	btrfs_delalloc_release_space(inode, page_start, reserved_space);
 out_noreserve:
 	sb_end_pagefault(inode->i_sb);
 	return ret;
@@ -9156,16 +9323,11 @@ void btrfs_destroy_cachep(void)
 	 * destroy cache.
 	 */
 	rcu_barrier();
-	if (btrfs_inode_cachep)
-		kmem_cache_destroy(btrfs_inode_cachep);
-	if (btrfs_trans_handle_cachep)
-		kmem_cache_destroy(btrfs_trans_handle_cachep);
-	if (btrfs_transaction_cachep)
-		kmem_cache_destroy(btrfs_transaction_cachep);
-	if (btrfs_path_cachep)
-		kmem_cache_destroy(btrfs_path_cachep);
-	if (btrfs_free_space_cachep)
-		kmem_cache_destroy(btrfs_free_space_cachep);
+	kmem_cache_destroy(btrfs_inode_cachep);
+	kmem_cache_destroy(btrfs_trans_handle_cachep);
+	kmem_cache_destroy(btrfs_transaction_cachep);
+	kmem_cache_destroy(btrfs_path_cachep);
+	kmem_cache_destroy(btrfs_free_space_cachep);
 }
 
 int btrfs_init_cachep(void)
@@ -9216,7 +9378,6 @@ static int btrfs_getattr(struct vfsmount *mnt,
 
 	generic_fillattr(inode, stat);
 	stat->dev = BTRFS_I(inode)->root->anon_dev;
-	stat->blksize = PAGE_CACHE_SIZE;
 
 	spin_lock(&BTRFS_I(inode)->lock);
 	delalloc_bytes = BTRFS_I(inode)->delalloc_bytes;
@@ -9234,7 +9395,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct btrfs_root *dest = BTRFS_I(new_dir)->root;
 	struct inode *new_inode = d_inode(new_dentry);
 	struct inode *old_inode = d_inode(old_dentry);
-	struct timespec ctime = CURRENT_TIME;
 	u64 index = 0;
 	u64 root_objectid;
 	int ret;
@@ -9331,9 +9491,9 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	inode_inc_iversion(old_dir);
 	inode_inc_iversion(new_dir);
 	inode_inc_iversion(old_inode);
-	old_dir->i_ctime = old_dir->i_mtime = ctime;
-	new_dir->i_ctime = new_dir->i_mtime = ctime;
-	old_inode->i_ctime = ctime;
+	old_dir->i_ctime = old_dir->i_mtime =
+	new_dir->i_ctime = new_dir->i_mtime =
+	old_inode->i_ctime = current_fs_time(old_dir->i_sb);
 
 	if (old_dentry->d_parent != new_dentry->d_parent)
 		btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
@@ -9358,7 +9518,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	if (new_inode) {
 		inode_inc_iversion(new_inode);
-		new_inode->i_ctime = CURRENT_TIME;
+		new_inode->i_ctime = current_fs_time(new_inode->i_sb);
 		if (unlikely(btrfs_ino(new_inode) ==
 			     BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 			root_objectid = BTRFS_I(new_inode)->location.objectid;
@@ -9836,7 +9996,7 @@ next:
 		*alloc_hint = ins.objectid + ins.offset;
 
 		inode_inc_iversion(inode);
-		inode->i_ctime = CURRENT_TIME;
+		inode->i_ctime = current_fs_time(inode->i_sb);
 		BTRFS_I(inode)->flags |= BTRFS_INODE_PREALLOC;
 		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
 		    (actual_len > inode->i_size) &&
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 952172ca7e45..053e677839fe 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -59,6 +59,8 @@
 #include "props.h"
 #include "sysfs.h"
 #include "qgroup.h"
+#include "tree-log.h"
+#include "compression.h"
 
 #ifdef CONFIG_64BIT
 /* If we have a 32-bit userspace and 64-bit kernel, then the UAPI
@@ -347,7 +349,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 
 	btrfs_update_iflags(inode);
 	inode_inc_iversion(inode);
-	inode->i_ctime = CURRENT_TIME;
+	inode->i_ctime = current_fs_time(inode->i_sb);
 	ret = btrfs_update_inode(trans, root, inode);
 
 	btrfs_end_transaction(trans, root);
@@ -443,7 +445,7 @@ static noinline int create_subvol(struct inode *dir,
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_root *new_root;
 	struct btrfs_block_rsv block_rsv;
-	struct timespec cur_time = CURRENT_TIME;
+	struct timespec cur_time = current_fs_time(dir->i_sb);
 	struct inode *inode;
 	int ret;
 	int err;
@@ -844,10 +846,6 @@ static noinline int btrfs_mksubvol(struct path *parent,
 	if (IS_ERR(dentry))
 		goto out_unlock;
 
-	error = -EEXIST;
-	if (d_really_is_positive(dentry))
-		goto out_dput;
-
 	error = btrfs_may_create(dir, dentry);
 	if (error)
 		goto out_dput;
@@ -2097,8 +2095,6 @@ static noinline int search_ioctl(struct inode *inode,
 		key.offset = (u64)-1;
 		root = btrfs_read_fs_root_no_name(info, &key);
 		if (IS_ERR(root)) {
-			btrfs_err(info, "could not find root %llu",
-			       sk->tree_id);
 			btrfs_free_path(path);
 			return -ENOENT;
 		}
@@ -2476,6 +2472,8 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 
+	btrfs_record_snapshot_destroy(trans, dir);
+
 	ret = btrfs_unlink_subvol(trans, root, dir,
 				dest->root_key.objectid,
 				dentry->d_name.name,
@@ -2794,24 +2792,29 @@ out:
 static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
 {
 	struct page *page;
-	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 
 	page = grab_cache_page(inode->i_mapping, index);
 	if (!page)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (!PageUptodate(page)) {
-		if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
-						 0))
-			return NULL;
+		int ret;
+
+		ret = btrfs_readpage(NULL, page);
+		if (ret)
+			return ERR_PTR(ret);
 		lock_page(page);
 		if (!PageUptodate(page)) {
 			unlock_page(page);
 			page_cache_release(page);
-			return NULL;
+			return ERR_PTR(-EIO);
+		}
+		if (page->mapping != inode->i_mapping) {
+			unlock_page(page);
+			page_cache_release(page);
+			return ERR_PTR(-EAGAIN);
 		}
 	}
-	unlock_page(page);
 
 	return page;
 }
@@ -2823,17 +2826,31 @@ static int gather_extent_pages(struct inode *inode, struct page **pages,
 	pgoff_t index = off >> PAGE_CACHE_SHIFT;
 
 	for (i = 0; i < num_pages; i++) {
+again:
 		pages[i] = extent_same_get_page(inode, index + i);
-		if (!pages[i])
-			return -ENOMEM;
+		if (IS_ERR(pages[i])) {
+			int err = PTR_ERR(pages[i]);
+
+			if (err == -EAGAIN)
+				goto again;
+			pages[i] = NULL;
+			return err;
+		}
 	}
 	return 0;
 }
 
-static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
+static int lock_extent_range(struct inode *inode, u64 off, u64 len,
+			     bool retry_range_locking)
 {
-	/* do any pending delalloc/csum calc on src, one way or
-	   another, and lock file content */
+	/*
+	 * Do any pending delalloc/csum calculations on inode, one way or
+	 * another, and lock file content.
+	 * The locking order is:
+	 *
+	 *   1) pages
+	 *   2) range in the inode's io tree
+	 */
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
 		lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
@@ -2851,8 +2868,11 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
 		unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
+		if (!retry_range_locking)
+			return -EAGAIN;
 		btrfs_wait_ordered_range(inode, off, len);
 	}
+	return 0;
 }
 
 static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
@@ -2877,15 +2897,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
 	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
 }
 
-static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
-				     struct inode *inode2, u64 loff2, u64 len)
+static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+				    struct inode *inode2, u64 loff2, u64 len,
+				    bool retry_range_locking)
 {
+	int ret;
+
 	if (inode1 < inode2) {
 		swap(inode1, inode2);
 		swap(loff1, loff2);
 	}
-	lock_extent_range(inode1, loff1, len);
-	lock_extent_range(inode2, loff2, len);
+	ret = lock_extent_range(inode1, loff1, len, retry_range_locking);
+	if (ret)
+		return ret;
+	ret = lock_extent_range(inode2, loff2, len, retry_range_locking);
+	if (ret)
+		unlock_extent(&BTRFS_I(inode1)->io_tree, loff1,
+			      loff1 + len - 1);
+	return ret;
 }
 
 struct cmp_pages {
@@ -2901,11 +2930,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
 
 	for (i = 0; i < cmp->num_pages; i++) {
 		pg = cmp->src_pages[i];
-		if (pg)
+		if (pg) {
+			unlock_page(pg);
 			page_cache_release(pg);
+		}
 		pg = cmp->dst_pages[i];
-		if (pg)
+		if (pg) {
+			unlock_page(pg);
 			page_cache_release(pg);
+		}
 	}
 	kfree(cmp->src_pages);
 	kfree(cmp->dst_pages);
@@ -2925,8 +2958,8 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
 	 * of the array is bounded by len, which is in turn bounded by
 	 * BTRFS_MAX_DEDUPE_LEN.
 	 */
-	src_pgarr = kzalloc(num_pages * sizeof(struct page *), GFP_NOFS);
-	dst_pgarr = kzalloc(num_pages * sizeof(struct page *), GFP_NOFS);
+	src_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
+	dst_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
 	if (!src_pgarr || !dst_pgarr) {
 		kfree(src_pgarr);
 		kfree(dst_pgarr);
@@ -2966,6 +2999,8 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
 
 		src_page = cmp->src_pages[i];
 		dst_page = cmp->dst_pages[i];
+		ASSERT(PageLocked(src_page));
+		ASSERT(PageLocked(dst_page));
 
 		addr = kmap_atomic(src_page);
 		dst_addr = kmap_atomic(dst_page);
@@ -3031,6 +3066,9 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		ret = extent_same_check_offsets(src, loff, &len, olen);
 		if (ret)
 			goto out_unlock;
+		ret = extent_same_check_offsets(src, dst_loff, &len, olen);
+		if (ret)
+			goto out_unlock;
 
 		/*
 		 * Single inode case wants the same checks, except we
@@ -3078,14 +3116,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		goto out_unlock;
 	}
 
+again:
 	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
 	if (ret)
 		goto out_unlock;
 
 	if (same_inode)
-		lock_extent_range(src, same_lock_start, same_lock_len);
+		ret = lock_extent_range(src, same_lock_start, same_lock_len,
+					false);
 	else
-		btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+		ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len,
+					       false);
+	/*
+	 * If one of the inodes has dirty pages in the respective range or
+	 * ordered extents, we need to flush dellaloc and wait for all ordered
+	 * extents in the range. We must unlock the pages and the ranges in the
+	 * io trees to avoid deadlocks when flushing delalloc (requires locking
+	 * pages) and when waiting for ordered extents to complete (they require
+	 * range locking).
+	 */
+	if (ret == -EAGAIN) {
+		/*
+		 * Ranges in the io trees already unlocked. Now unlock all
+		 * pages before waiting for all IO to complete.
+		 */
+		btrfs_cmp_data_free(&cmp);
+		if (same_inode) {
+			btrfs_wait_ordered_range(src, same_lock_start,
+						 same_lock_len);
+		} else {
+			btrfs_wait_ordered_range(src, loff, len);
+			btrfs_wait_ordered_range(dst, dst_loff, len);
+		}
+		goto again;
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		btrfs_cmp_data_free(&cmp);
+		return ret;
+	}
 
 	/* pass original length for comparison so we stay within i_size */
 	ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
@@ -3148,7 +3218,7 @@ static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
 
 	inode_inc_iversion(inode);
 	if (!no_time_update)
-		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb);
 	/*
 	 * We round up to the block size at eof when determining which
 	 * extents to clone above, but shouldn't round up the file size.
@@ -3795,9 +3865,15 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 		u64 lock_start = min_t(u64, off, destoff);
 		u64 lock_len = max_t(u64, off, destoff) + len - lock_start;
 
-		lock_extent_range(src, lock_start, lock_len);
+		ret = lock_extent_range(src, lock_start, lock_len, true);
 	} else {
-		btrfs_double_extent_lock(src, off, inode, destoff, len);
+		ret = btrfs_double_extent_lock(src, off, inode, destoff, len,
+					       true);
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		goto out_unlock;
 	}
 
 	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
@@ -3814,8 +3890,9 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 	 * Truncate page cache pages so that future reads will see the cloned
 	 * data immediately and not the previous data.
 	 */
-	truncate_inode_pages_range(&inode->i_data, destoff,
-				   PAGE_CACHE_ALIGN(destoff + len) - 1);
+	truncate_inode_pages_range(&inode->i_data,
+				round_down(destoff, PAGE_CACHE_SIZE),
+				round_up(destoff + len, PAGE_CACHE_SIZE) - 1);
 out_unlock:
 	if (!same_inode)
 		btrfs_double_inode_unlock(src, inode);
@@ -4956,7 +5033,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_root_item *root_item = &root->root_item;
 	struct btrfs_trans_handle *trans;
-	struct timespec ct = CURRENT_TIME;
+	struct timespec ct = current_fs_time(inode->i_sb);
 	int ret = 0;
 	int received_uuid_changed;
 
@@ -5187,8 +5264,7 @@ out_unlock:
 	  .compat_ro_flags = BTRFS_FEATURE_COMPAT_RO_##suffix, \
 	  .incompat_flags = BTRFS_FEATURE_INCOMPAT_##suffix }
 
-static int btrfs_ioctl_get_supported_features(struct file *file,
-					      void __user *arg)
+int btrfs_ioctl_get_supported_features(void __user *arg)
 {
 	static const struct btrfs_ioctl_feature_flags features[3] = {
 		INIT_FEATURE_FLAGS(SUPP),
@@ -5467,7 +5543,7 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case BTRFS_IOC_SET_FSLABEL:
 		return btrfs_ioctl_set_fslabel(file, argp);
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
-		return btrfs_ioctl_get_supported_features(file, argp);
+		return btrfs_ioctl_get_supported_features(argp);
 	case BTRFS_IOC_GET_FEATURES:
 		return btrfs_ioctl_get_features(file, argp);
 	case BTRFS_IOC_SET_FEATURES:
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 8c27292ea9ea..0de7da5a610d 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -25,6 +25,7 @@
 #include "btrfs_inode.h"
 #include "extent_io.h"
 #include "disk-io.h"
+#include "compression.h"
 
 static struct kmem_cache *btrfs_ordered_extent_cache;
 
@@ -1009,7 +1010,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 	for (; node; node = rb_prev(node)) {
 		test = rb_entry(node, struct btrfs_ordered_extent, rb_node);
 
-		/* We treat this entry as if it doesnt exist */
+		/* We treat this entry as if it doesn't exist */
 		if (test_bit(BTRFS_ORDERED_UPDATED_ISIZE, &test->flags))
 			continue;
 		if (test->file_offset + test->len <= disk_i_size)
@@ -1114,6 +1115,5 @@ int __init ordered_data_init(void)
 
 void ordered_data_exit(void)
 {
-	if (btrfs_ordered_extent_cache)
-		kmem_cache_destroy(btrfs_ordered_extent_cache);
+	kmem_cache_destroy(btrfs_ordered_extent_cache);
 }
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 647ab12fdf5d..147dc6ca5de1 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -295,8 +295,27 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 			       btrfs_dev_extent_chunk_offset(l, dev_extent),
 			       btrfs_dev_extent_length(l, dev_extent));
 			break;
-		case BTRFS_DEV_STATS_KEY:
-			printk(KERN_INFO "\t\tdevice stats\n");
+		case BTRFS_PERSISTENT_ITEM_KEY:
+			printk(KERN_INFO "\t\tpersistent item objectid %llu offset %llu\n",
+					key.objectid, key.offset);
+			switch (key.objectid) {
+			case BTRFS_DEV_STATS_OBJECTID:
+				printk(KERN_INFO "\t\tdevice stats\n");
+				break;
+			default:
+				printk(KERN_INFO "\t\tunknown persistent item\n");
+			}
+			break;
+		case BTRFS_TEMPORARY_ITEM_KEY:
+			printk(KERN_INFO "\t\ttemporary item objectid %llu offset %llu\n",
+					key.objectid, key.offset);
+			switch (key.objectid) {
+			case BTRFS_BALANCE_OBJECTID:
+				printk(KERN_INFO "\t\tbalance status\n");
+				break;
+			default:
+				printk(KERN_INFO "\t\tunknown temporary item\n");
+			}
 			break;
 		case BTRFS_DEV_REPLACE_KEY:
 			printk(KERN_INFO "\t\tdev replace\n");
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index f9e60231f685..36992128c746 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -22,6 +22,7 @@
 #include "hash.h"
 #include "transaction.h"
 #include "xattr.h"
+#include "compression.h"
 
 #define BTRFS_PROP_HANDLERS_HT_BITS 8
 static DEFINE_HASHTABLE(prop_handlers_ht, BTRFS_PROP_HANDLERS_HT_BITS);
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 619f92963e27..b892914968c1 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -72,7 +72,7 @@ struct reada_extent {
 	spinlock_t		lock;
 	struct reada_zone	*zones[BTRFS_MAX_MIRRORS];
 	int			nzones;
-	struct btrfs_device	*scheduled_for;
+	int			scheduled;
 };
 
 struct reada_zone {
@@ -101,67 +101,53 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info);
 static void __reada_start_machine(struct btrfs_fs_info *fs_info);
 
 static int reada_add_block(struct reada_control *rc, u64 logical,
-			   struct btrfs_key *top, int level, u64 generation);
+			   struct btrfs_key *top, u64 generation);
 
 /* recurses */
 /* in case of err, eb might be NULL */
-static int __readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
-			    u64 start, int err)
+static void __readahead_hook(struct btrfs_fs_info *fs_info,
+			     struct reada_extent *re, struct extent_buffer *eb,
+			     u64 start, int err)
 {
 	int level = 0;
 	int nritems;
 	int i;
 	u64 bytenr;
 	u64 generation;
-	struct reada_extent *re;
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct list_head list;
-	unsigned long index = start >> PAGE_CACHE_SHIFT;
-	struct btrfs_device *for_dev;
 
 	if (eb)
 		level = btrfs_header_level(eb);
 
-	/* find extent */
-	spin_lock(&fs_info->reada_lock);
-	re = radix_tree_lookup(&fs_info->reada_tree, index);
-	if (re)
-		re->refcnt++;
-	spin_unlock(&fs_info->reada_lock);
-
-	if (!re)
-		return -1;
-
 	spin_lock(&re->lock);
 	/*
 	 * just take the full list from the extent. afterwards we
 	 * don't need the lock anymore
 	 */
 	list_replace_init(&re->extctl, &list);
-	for_dev = re->scheduled_for;
-	re->scheduled_for = NULL;
+	re->scheduled = 0;
 	spin_unlock(&re->lock);
 
-	if (err == 0) {
-		nritems = level ? btrfs_header_nritems(eb) : 0;
-		generation = btrfs_header_generation(eb);
-		/*
-		 * FIXME: currently we just set nritems to 0 if this is a leaf,
-		 * effectively ignoring the content. In a next step we could
-		 * trigger more readahead depending from the content, e.g.
-		 * fetch the checksums for the extents in the leaf.
-		 */
-	} else {
-		/*
-		 * this is the error case, the extent buffer has not been
-		 * read correctly. We won't access anything from it and
-		 * just cleanup our data structures. Effectively this will
-		 * cut the branch below this node from read ahead.
-		 */
-		nritems = 0;
-		generation = 0;
-	}
+	/*
+	 * this is the error case, the extent buffer has not been
+	 * read correctly. We won't access anything from it and
+	 * just cleanup our data structures. Effectively this will
+	 * cut the branch below this node from read ahead.
+	 */
+	if (err)
+		goto cleanup;
 
+	/*
+	 * FIXME: currently we just set nritems to 0 if this is a leaf,
+	 * effectively ignoring the content. In a next step we could
+	 * trigger more readahead depending from the content, e.g.
+	 * fetch the checksums for the extents in the leaf.
+	 */
+	if (!level)
+		goto cleanup;
+
+	nritems = btrfs_header_nritems(eb);
+	generation = btrfs_header_generation(eb);
 	for (i = 0; i < nritems; i++) {
 		struct reada_extctl *rec;
 		u64 n_gen;
@@ -188,19 +174,20 @@ static int __readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
 			 */
 #ifdef DEBUG
 			if (rec->generation != generation) {
-				btrfs_debug(root->fs_info,
-					   "generation mismatch for (%llu,%d,%llu) %llu != %llu",
-				       key.objectid, key.type, key.offset,
-				       rec->generation, generation);
+				btrfs_debug(fs_info,
+					    "generation mismatch for (%llu,%d,%llu) %llu != %llu",
+					    key.objectid, key.type, key.offset,
+					    rec->generation, generation);
 			}
 #endif
 			if (rec->generation == generation &&
 			    btrfs_comp_cpu_keys(&key, &rc->key_end) < 0 &&
 			    btrfs_comp_cpu_keys(&next_key, &rc->key_start) > 0)
-				reada_add_block(rc, bytenr, &next_key,
-						level - 1, n_gen);
+				reada_add_block(rc, bytenr, &next_key, n_gen);
 		}
 	}
+
+cleanup:
 	/*
 	 * free extctl records
 	 */
@@ -222,26 +209,37 @@ static int __readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
 
 		reada_extent_put(fs_info, re);	/* one ref for each entry */
 	}
-	reada_extent_put(fs_info, re);	/* our ref */
-	if (for_dev)
-		atomic_dec(&for_dev->reada_in_flight);
 
-	return 0;
+	return;
 }
 
 /*
  * start is passed separately in case eb in NULL, which may be the case with
  * failed I/O
  */
-int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
-			 u64 start, int err)
+int btree_readahead_hook(struct btrfs_fs_info *fs_info,
+			 struct extent_buffer *eb, u64 start, int err)
 {
-	int ret;
+	int ret = 0;
+	struct reada_extent *re;
 
-	ret = __readahead_hook(root, eb, start, err);
+	/* find extent */
+	spin_lock(&fs_info->reada_lock);
+	re = radix_tree_lookup(&fs_info->reada_tree,
+			       start >> PAGE_CACHE_SHIFT);
+	if (re)
+		re->refcnt++;
+	spin_unlock(&fs_info->reada_lock);
+	if (!re) {
+		ret = -1;
+		goto start_machine;
+	}
 
-	reada_start_machine(root->fs_info);
+	__readahead_hook(fs_info, re, eb, start, err);
+	reada_extent_put(fs_info, re);	/* our ref */
 
+start_machine:
+	reada_start_machine(fs_info);
 	return ret;
 }
 
@@ -260,18 +258,14 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
 	spin_lock(&fs_info->reada_lock);
 	ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
 				     logical >> PAGE_CACHE_SHIFT, 1);
-	if (ret == 1)
+	if (ret == 1 && logical >= zone->start && logical <= zone->end) {
 		kref_get(&zone->refcnt);
-	spin_unlock(&fs_info->reada_lock);
-
-	if (ret == 1) {
-		if (logical >= zone->start && logical < zone->end)
-			return zone;
-		spin_lock(&fs_info->reada_lock);
-		kref_put(&zone->refcnt, reada_zone_release);
 		spin_unlock(&fs_info->reada_lock);
+		return zone;
 	}
 
+	spin_unlock(&fs_info->reada_lock);
+
 	cache = btrfs_lookup_block_group(fs_info, logical);
 	if (!cache)
 		return NULL;
@@ -280,7 +274,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
 	end = start + cache->key.offset - 1;
 	btrfs_put_block_group(cache);
 
-	zone = kzalloc(sizeof(*zone), GFP_NOFS);
+	zone = kzalloc(sizeof(*zone), GFP_KERNEL);
 	if (!zone)
 		return NULL;
 
@@ -307,8 +301,10 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
 		kfree(zone);
 		ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
 					     logical >> PAGE_CACHE_SHIFT, 1);
-		if (ret == 1)
+		if (ret == 1 && logical >= zone->start && logical <= zone->end)
 			kref_get(&zone->refcnt);
+		else
+			zone = NULL;
 	}
 	spin_unlock(&fs_info->reada_lock);
 
@@ -317,7 +313,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
 
 static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 					      u64 logical,
-					      struct btrfs_key *top, int level)
+					      struct btrfs_key *top)
 {
 	int ret;
 	struct reada_extent *re = NULL;
@@ -330,9 +326,9 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	u64 length;
 	int real_stripes;
 	int nzones = 0;
-	int i;
 	unsigned long index = logical >> PAGE_CACHE_SHIFT;
 	int dev_replace_is_ongoing;
+	int have_zone = 0;
 
 	spin_lock(&fs_info->reada_lock);
 	re = radix_tree_lookup(&fs_info->reada_tree, index);
@@ -343,7 +339,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	if (re)
 		return re;
 
-	re = kzalloc(sizeof(*re), GFP_NOFS);
+	re = kzalloc(sizeof(*re), GFP_KERNEL);
 	if (!re)
 		return NULL;
 
@@ -375,11 +371,16 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 		struct reada_zone *zone;
 
 		dev = bbio->stripes[nzones].dev;
+
+		/* cannot read ahead on missing device. */
+		 if (!dev->bdev)
+			continue;
+
 		zone = reada_find_zone(fs_info, dev, logical, bbio);
 		if (!zone)
-			break;
+			continue;
 
-		re->zones[nzones] = zone;
+		re->zones[re->nzones++] = zone;
 		spin_lock(&zone->lock);
 		if (!zone->elems)
 			kref_get(&zone->refcnt);
@@ -389,14 +390,13 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 		kref_put(&zone->refcnt, reada_zone_release);
 		spin_unlock(&fs_info->reada_lock);
 	}
-	re->nzones = nzones;
-	if (nzones == 0) {
+	if (re->nzones == 0) {
 		/* not a single zone found, error and out */
 		goto error;
 	}
 
 	/* insert extent in reada_tree + all per-device trees, all or nothing */
-	btrfs_dev_replace_lock(&fs_info->dev_replace);
+	btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
 	spin_lock(&fs_info->reada_lock);
 	ret = radix_tree_insert(&fs_info->reada_tree, index, re);
 	if (ret == -EEXIST) {
@@ -404,19 +404,20 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 		BUG_ON(!re_exist);
 		re_exist->refcnt++;
 		spin_unlock(&fs_info->reada_lock);
-		btrfs_dev_replace_unlock(&fs_info->dev_replace);
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 		goto error;
 	}
 	if (ret) {
 		spin_unlock(&fs_info->reada_lock);
-		btrfs_dev_replace_unlock(&fs_info->dev_replace);
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 		goto error;
 	}
 	prev_dev = NULL;
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(
 			&fs_info->dev_replace);
-	for (i = 0; i < nzones; ++i) {
-		dev = bbio->stripes[i].dev;
+	for (nzones = 0; nzones < re->nzones; ++nzones) {
+		dev = re->zones[nzones]->device;
+
 		if (dev == prev_dev) {
 			/*
 			 * in case of DUP, just add the first zone. As both
@@ -427,15 +428,9 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 			 */
 			continue;
 		}
-		if (!dev->bdev) {
-			/*
-			 * cannot read ahead on missing device, but for RAID5/6,
-			 * REQ_GET_READ_MIRRORS return 1. So don't skip missing
-			 * device for such case.
-			 */
-			if (nzones > 1)
-				continue;
-		}
+		if (!dev->bdev)
+			continue;
+
 		if (dev_replace_is_ongoing &&
 		    dev == fs_info->dev_replace.tgtdev) {
 			/*
@@ -447,8 +442,8 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 		prev_dev = dev;
 		ret = radix_tree_insert(&dev->reada_extents, index, re);
 		if (ret) {
-			while (--i >= 0) {
-				dev = bbio->stripes[i].dev;
+			while (--nzones >= 0) {
+				dev = re->zones[nzones]->device;
 				BUG_ON(dev == NULL);
 				/* ignore whether the entry was inserted */
 				radix_tree_delete(&dev->reada_extents, index);
@@ -456,21 +451,24 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 			BUG_ON(fs_info == NULL);
 			radix_tree_delete(&fs_info->reada_tree, index);
 			spin_unlock(&fs_info->reada_lock);
-			btrfs_dev_replace_unlock(&fs_info->dev_replace);
+			btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 			goto error;
 		}
+		have_zone = 1;
 	}
 	spin_unlock(&fs_info->reada_lock);
-	btrfs_dev_replace_unlock(&fs_info->dev_replace);
+	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
+
+	if (!have_zone)
+		goto error;
 
 	btrfs_put_bbio(bbio);
 	return re;
 
 error:
-	while (nzones) {
+	for (nzones = 0; nzones < re->nzones; ++nzones) {
 		struct reada_zone *zone;
 
-		--nzones;
 		zone = re->zones[nzones];
 		kref_get(&zone->refcnt);
 		spin_lock(&zone->lock);
@@ -531,8 +529,6 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
 		kref_put(&zone->refcnt, reada_zone_release);
 		spin_unlock(&fs_info->reada_lock);
 	}
-	if (re->scheduled_for)
-		atomic_dec(&re->scheduled_for->reada_in_flight);
 
 	kfree(re);
 }
@@ -556,17 +552,17 @@ static void reada_control_release(struct kref *kref)
 }
 
 static int reada_add_block(struct reada_control *rc, u64 logical,
-			   struct btrfs_key *top, int level, u64 generation)
+			   struct btrfs_key *top, u64 generation)
 {
 	struct btrfs_root *root = rc->root;
 	struct reada_extent *re;
 	struct reada_extctl *rec;
 
-	re = reada_find_extent(root, logical, top, level); /* takes one ref */
+	re = reada_find_extent(root, logical, top); /* takes one ref */
 	if (!re)
 		return -1;
 
-	rec = kzalloc(sizeof(*rec), GFP_NOFS);
+	rec = kzalloc(sizeof(*rec), GFP_KERNEL);
 	if (!rec) {
 		reada_extent_put(root->fs_info, re);
 		return -ENOMEM;
@@ -662,7 +658,6 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 	u64 logical;
 	int ret;
 	int i;
-	int need_kick = 0;
 
 	spin_lock(&fs_info->reada_lock);
 	if (dev->reada_curr_zone == NULL) {
@@ -679,7 +674,7 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 	 */
 	ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
 				     dev->reada_next >> PAGE_CACHE_SHIFT, 1);
-	if (ret == 0 || re->logical >= dev->reada_curr_zone->end) {
+	if (ret == 0 || re->logical > dev->reada_curr_zone->end) {
 		ret = reada_pick_zone(dev);
 		if (!ret) {
 			spin_unlock(&fs_info->reada_lock);
@@ -698,6 +693,15 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 
 	spin_unlock(&fs_info->reada_lock);
 
+	spin_lock(&re->lock);
+	if (re->scheduled || list_empty(&re->extctl)) {
+		spin_unlock(&re->lock);
+		reada_extent_put(fs_info, re);
+		return 0;
+	}
+	re->scheduled = 1;
+	spin_unlock(&re->lock);
+
 	/*
 	 * find mirror num
 	 */
@@ -709,29 +713,20 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 	}
 	logical = re->logical;
 
-	spin_lock(&re->lock);
-	if (re->scheduled_for == NULL) {
-		re->scheduled_for = dev;
-		need_kick = 1;
-	}
-	spin_unlock(&re->lock);
-
-	reada_extent_put(fs_info, re);
-
-	if (!need_kick)
-		return 0;
-
 	atomic_inc(&dev->reada_in_flight);
 	ret = reada_tree_block_flagged(fs_info->extent_root, logical,
 			mirror_num, &eb);
 	if (ret)
-		__readahead_hook(fs_info->extent_root, NULL, logical, ret);
+		__readahead_hook(fs_info, re, NULL, logical, ret);
 	else if (eb)
-		__readahead_hook(fs_info->extent_root, eb, eb->start, ret);
+		__readahead_hook(fs_info, re, eb, eb->start, ret);
 
 	if (eb)
 		free_extent_buffer(eb);
 
+	atomic_dec(&dev->reada_in_flight);
+	reada_extent_put(fs_info, re);
+
 	return 1;
 
 }
@@ -752,6 +747,8 @@ static void reada_start_machine_worker(struct btrfs_work *work)
 	set_task_ioprio(current, BTRFS_IOPRIO_READA);
 	__reada_start_machine(fs_info);
 	set_task_ioprio(current, old_ioprio);
+
+	atomic_dec(&fs_info->reada_works_cnt);
 }
 
 static void __reada_start_machine(struct btrfs_fs_info *fs_info)
@@ -783,15 +780,19 @@ static void __reada_start_machine(struct btrfs_fs_info *fs_info)
 	 * enqueue to workers to finish it. This will distribute the load to
 	 * the cores.
 	 */
-	for (i = 0; i < 2; ++i)
+	for (i = 0; i < 2; ++i) {
 		reada_start_machine(fs_info);
+		if (atomic_read(&fs_info->reada_works_cnt) >
+		    BTRFS_MAX_MIRRORS * 2)
+			break;
+	}
 }
 
 static void reada_start_machine(struct btrfs_fs_info *fs_info)
 {
 	struct reada_machine_work *rmw;
 
-	rmw = kzalloc(sizeof(*rmw), GFP_NOFS);
+	rmw = kzalloc(sizeof(*rmw), GFP_KERNEL);
 	if (!rmw) {
 		/* FIXME we cannot handle this properly right now */
 		BUG();
@@ -801,6 +802,7 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
 	rmw->fs_info = fs_info;
 
 	btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
+	atomic_inc(&fs_info->reada_works_cnt);
 }
 
 #ifdef DEBUG
@@ -848,10 +850,9 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 			if (ret == 0)
 				break;
 			printk(KERN_DEBUG
-				"  re: logical %llu size %u empty %d for %lld",
+				"  re: logical %llu size %u empty %d scheduled %d",
 				re->logical, fs_info->tree_root->nodesize,
-				list_empty(&re->extctl), re->scheduled_for ?
-				re->scheduled_for->devid : -1);
+				list_empty(&re->extctl), re->scheduled);
 
 			for (i = 0; i < re->nzones; ++i) {
 				printk(KERN_CONT " zone %llu-%llu devs",
@@ -878,27 +879,21 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 					     index, 1);
 		if (ret == 0)
 			break;
-		if (!re->scheduled_for) {
+		if (!re->scheduled) {
 			index = (re->logical >> PAGE_CACHE_SHIFT) + 1;
 			continue;
 		}
 		printk(KERN_DEBUG
-			"re: logical %llu size %u list empty %d for %lld",
+			"re: logical %llu size %u list empty %d scheduled %d",
 			re->logical, fs_info->tree_root->nodesize,
-			list_empty(&re->extctl),
-			re->scheduled_for ? re->scheduled_for->devid : -1);
+			list_empty(&re->extctl), re->scheduled);
 		for (i = 0; i < re->nzones; ++i) {
 			printk(KERN_CONT " zone %llu-%llu devs",
 				re->zones[i]->start,
 				re->zones[i]->end);
-			for (i = 0; i < re->nzones; ++i) {
-				printk(KERN_CONT " zone %llu-%llu devs",
-					re->zones[i]->start,
-					re->zones[i]->end);
-				for (j = 0; j < re->zones[i]->ndevs; ++j) {
-					printk(KERN_CONT " %lld",
-						re->zones[i]->devs[j]->devid);
-				}
+			for (j = 0; j < re->zones[i]->ndevs; ++j) {
+				printk(KERN_CONT " %lld",
+				       re->zones[i]->devs[j]->devid);
 			}
 		}
 		printk(KERN_CONT "\n");
@@ -917,7 +912,6 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 	struct reada_control *rc;
 	u64 start;
 	u64 generation;
-	int level;
 	int ret;
 	struct extent_buffer *node;
 	static struct btrfs_key max_key = {
@@ -926,7 +920,7 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 		.offset = (u64)-1
 	};
 
-	rc = kzalloc(sizeof(*rc), GFP_NOFS);
+	rc = kzalloc(sizeof(*rc), GFP_KERNEL);
 	if (!rc)
 		return ERR_PTR(-ENOMEM);
 
@@ -940,11 +934,10 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 
 	node = btrfs_root_node(root);
 	start = node->start;
-	level = btrfs_header_level(node);
 	generation = btrfs_header_generation(node);
 	free_extent_buffer(node);
 
-	ret = reada_add_block(rc, start, &max_key, level, generation);
+	ret = reada_add_block(rc, start, &max_key, generation);
 	if (ret) {
 		kfree(rc);
 		return ERR_PTR(ret);
@@ -959,8 +952,11 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 int btrfs_reada_wait(void *handle)
 {
 	struct reada_control *rc = handle;
+	struct btrfs_fs_info *fs_info = rc->root->fs_info;
 
 	while (atomic_read(&rc->elems)) {
+		if (!atomic_read(&fs_info->reada_works_cnt))
+			reada_start_machine(fs_info);
 		wait_event_timeout(rc->wait, atomic_read(&rc->elems) == 0,
 				   5 * HZ);
 		dump_devs(rc->root->fs_info,
@@ -977,9 +973,13 @@ int btrfs_reada_wait(void *handle)
 int btrfs_reada_wait(void *handle)
 {
 	struct reada_control *rc = handle;
+	struct btrfs_fs_info *fs_info = rc->root->fs_info;
 
 	while (atomic_read(&rc->elems)) {
-		wait_event(rc->wait, atomic_read(&rc->elems) == 0);
+		if (!atomic_read(&fs_info->reada_works_cnt))
+			reada_start_machine(fs_info);
+		wait_event_timeout(rc->wait, atomic_read(&rc->elems) == 0,
+				   (HZ + 9) / 10);
 	}
 
 	kref_put(&rc->refcnt, reada_control_release);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index fd1c4d982463..2bd0011450df 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -575,7 +575,8 @@ static int is_cowonly_root(u64 root_objectid)
 	    root_objectid == BTRFS_TREE_LOG_OBJECTID ||
 	    root_objectid == BTRFS_CSUM_TREE_OBJECTID ||
 	    root_objectid == BTRFS_UUID_TREE_OBJECTID ||
-	    root_objectid == BTRFS_QUOTA_TREE_OBJECTID)
+	    root_objectid == BTRFS_QUOTA_TREE_OBJECTID ||
+	    root_objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
 		return 1;
 	return 0;
 }
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 7cf8509deda7..9fcd6dfc3266 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -310,8 +310,16 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
 		set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
 
 		err = btrfs_insert_fs_root(root->fs_info, root);
+		/*
+		 * The root might have been inserted already, as before we look
+		 * for orphan roots, log replay might have happened, which
+		 * triggers a transaction commit and qgroup accounting, which
+		 * in turn reads and inserts fs roots while doing backref
+		 * walking.
+		 */
+		if (err == -EEXIST)
+			err = 0;
 		if (err) {
-			BUG_ON(err == -EEXIST);
 			btrfs_free_fs_root(root);
 			break;
 		}
@@ -488,7 +496,7 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root)
 {
 	struct btrfs_root_item *item = &root->root_item;
-	struct timespec ct = CURRENT_TIME;
+	struct timespec ct = current_fs_time(root->fs_info->sb);
 
 	spin_lock(&root->root_item_lock);
 	btrfs_set_root_ctransid(item, trans->transid);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 92bf5ee732fb..39dbdcbf4d13 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -461,7 +461,7 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 	struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
 	int ret;
 
-	sctx = kzalloc(sizeof(*sctx), GFP_NOFS);
+	sctx = kzalloc(sizeof(*sctx), GFP_KERNEL);
 	if (!sctx)
 		goto nomem;
 	atomic_set(&sctx->refs, 1);
@@ -472,7 +472,7 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 	for (i = 0; i < SCRUB_BIOS_PER_SCTX; ++i) {
 		struct scrub_bio *sbio;
 
-		sbio = kzalloc(sizeof(*sbio), GFP_NOFS);
+		sbio = kzalloc(sizeof(*sbio), GFP_KERNEL);
 		if (!sbio)
 			goto nomem;
 		sctx->bios[i] = sbio;
@@ -611,7 +611,7 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 	u64 flags = 0;
 	u64 ref_root;
 	u32 item_size;
-	u8 ref_level;
+	u8 ref_level = 0;
 	int ret;
 
 	WARN_ON(sblock->page_count < 1);
@@ -1654,7 +1654,7 @@ static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
 again:
 	if (!wr_ctx->wr_curr_bio) {
 		wr_ctx->wr_curr_bio = kzalloc(sizeof(*wr_ctx->wr_curr_bio),
-					      GFP_NOFS);
+					      GFP_KERNEL);
 		if (!wr_ctx->wr_curr_bio) {
 			mutex_unlock(&wr_ctx->wr_lock);
 			return -ENOMEM;
@@ -1671,7 +1671,8 @@ again:
 		sbio->dev = wr_ctx->tgtdev;
 		bio = sbio->bio;
 		if (!bio) {
-			bio = btrfs_io_bio_alloc(GFP_NOFS, wr_ctx->pages_per_wr_bio);
+			bio = btrfs_io_bio_alloc(GFP_KERNEL,
+					wr_ctx->pages_per_wr_bio);
 			if (!bio) {
 				mutex_unlock(&wr_ctx->wr_lock);
 				return -ENOMEM;
@@ -2076,7 +2077,8 @@ again:
 		sbio->dev = spage->dev;
 		bio = sbio->bio;
 		if (!bio) {
-			bio = btrfs_io_bio_alloc(GFP_NOFS, sctx->pages_per_rd_bio);
+			bio = btrfs_io_bio_alloc(GFP_KERNEL,
+					sctx->pages_per_rd_bio);
 			if (!bio)
 				return -ENOMEM;
 			sbio->bio = bio;
@@ -2241,7 +2243,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 	struct scrub_block *sblock;
 	int index;
 
-	sblock = kzalloc(sizeof(*sblock), GFP_NOFS);
+	sblock = kzalloc(sizeof(*sblock), GFP_KERNEL);
 	if (!sblock) {
 		spin_lock(&sctx->stat_lock);
 		sctx->stat.malloc_errors++;
@@ -2259,7 +2261,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 		struct scrub_page *spage;
 		u64 l = min_t(u64, len, PAGE_SIZE);
 
-		spage = kzalloc(sizeof(*spage), GFP_NOFS);
+		spage = kzalloc(sizeof(*spage), GFP_KERNEL);
 		if (!spage) {
 leave_nomem:
 			spin_lock(&sctx->stat_lock);
@@ -2286,7 +2288,7 @@ leave_nomem:
 			spage->have_csum = 0;
 		}
 		sblock->page_count++;
-		spage->page = alloc_page(GFP_NOFS);
+		spage->page = alloc_page(GFP_KERNEL);
 		if (!spage->page)
 			goto leave_nomem;
 		len -= l;
@@ -2541,7 +2543,7 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
 	struct scrub_block *sblock;
 	int index;
 
-	sblock = kzalloc(sizeof(*sblock), GFP_NOFS);
+	sblock = kzalloc(sizeof(*sblock), GFP_KERNEL);
 	if (!sblock) {
 		spin_lock(&sctx->stat_lock);
 		sctx->stat.malloc_errors++;
@@ -2561,7 +2563,7 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
 		struct scrub_page *spage;
 		u64 l = min_t(u64, len, PAGE_SIZE);
 
-		spage = kzalloc(sizeof(*spage), GFP_NOFS);
+		spage = kzalloc(sizeof(*spage), GFP_KERNEL);
 		if (!spage) {
 leave_nomem:
 			spin_lock(&sctx->stat_lock);
@@ -2591,7 +2593,7 @@ leave_nomem:
 			spage->have_csum = 0;
 		}
 		sblock->page_count++;
-		spage->page = alloc_page(GFP_NOFS);
+		spage->page = alloc_page(GFP_KERNEL);
 		if (!spage->page)
 			goto leave_nomem;
 		len -= l;
@@ -3857,16 +3859,16 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		return -EIO;
 	}
 
-	btrfs_dev_replace_lock(&fs_info->dev_replace);
+	btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
 	if (dev->scrub_device ||
 	    (!is_dev_replace &&
 	     btrfs_dev_replace_is_ongoing(&fs_info->dev_replace))) {
-		btrfs_dev_replace_unlock(&fs_info->dev_replace);
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 		mutex_unlock(&fs_info->scrub_lock);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		return -EINPROGRESS;
 	}
-	btrfs_dev_replace_unlock(&fs_info->dev_replace);
+	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 
 	ret = scrub_workers_get(fs_info, is_dev_replace);
 	if (ret) {
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 63a6152be04b..19b7bf4284ee 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -34,6 +34,7 @@
 #include "disk-io.h"
 #include "btrfs_inode.h"
 #include "transaction.h"
+#include "compression.h"
 
 static int g_verbose = 0;
 
@@ -304,7 +305,7 @@ static struct fs_path *fs_path_alloc(void)
 {
 	struct fs_path *p;
 
-	p = kmalloc(sizeof(*p), GFP_NOFS);
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return NULL;
 	p->reversed = 0;
@@ -363,11 +364,11 @@ static int fs_path_ensure_buf(struct fs_path *p, int len)
 	 * First time the inline_buf does not suffice
 	 */
 	if (p->buf == p->inline_buf) {
-		tmp_buf = kmalloc(len, GFP_NOFS);
+		tmp_buf = kmalloc(len, GFP_KERNEL);
 		if (tmp_buf)
 			memcpy(tmp_buf, p->buf, old_buf_len);
 	} else {
-		tmp_buf = krealloc(p->buf, len, GFP_NOFS);
+		tmp_buf = krealloc(p->buf, len, GFP_KERNEL);
 	}
 	if (!tmp_buf)
 		return -ENOMEM;
@@ -995,7 +996,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 	 * values are small.
 	 */
 	buf_len = PATH_MAX;
-	buf = kmalloc(buf_len, GFP_NOFS);
+	buf = kmalloc(buf_len, GFP_KERNEL);
 	if (!buf) {
 		ret = -ENOMEM;
 		goto out;
@@ -1042,7 +1043,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 				buf = NULL;
 			} else {
 				char *tmp = krealloc(buf, buf_len,
-						     GFP_NOFS | __GFP_NOWARN);
+						GFP_KERNEL | __GFP_NOWARN);
 
 				if (!tmp)
 					kfree(buf);
@@ -1303,7 +1304,7 @@ static int find_extent_clone(struct send_ctx *sctx,
 	/* We only use this path under the commit sem */
 	tmp_path->need_commit_sem = 0;
 
-	backref_ctx = kmalloc(sizeof(*backref_ctx), GFP_NOFS);
+	backref_ctx = kmalloc(sizeof(*backref_ctx), GFP_KERNEL);
 	if (!backref_ctx) {
 		ret = -ENOMEM;
 		goto out;
@@ -1984,7 +1985,7 @@ static int name_cache_insert(struct send_ctx *sctx,
 	nce_head = radix_tree_lookup(&sctx->name_cache,
 			(unsigned long)nce->ino);
 	if (!nce_head) {
-		nce_head = kmalloc(sizeof(*nce_head), GFP_NOFS);
+		nce_head = kmalloc(sizeof(*nce_head), GFP_KERNEL);
 		if (!nce_head) {
 			kfree(nce);
 			return -ENOMEM;
@@ -2179,7 +2180,7 @@ out_cache:
 	/*
 	 * Store the result of the lookup in the name cache.
 	 */
-	nce = kmalloc(sizeof(*nce) + fs_path_len(dest) + 1, GFP_NOFS);
+	nce = kmalloc(sizeof(*nce) + fs_path_len(dest) + 1, GFP_KERNEL);
 	if (!nce) {
 		ret = -ENOMEM;
 		goto out;
@@ -2315,7 +2316,7 @@ static int send_subvol_begin(struct send_ctx *sctx)
 	if (!path)
 		return -ENOMEM;
 
-	name = kmalloc(BTRFS_PATH_NAME_MAX, GFP_NOFS);
+	name = kmalloc(BTRFS_PATH_NAME_MAX, GFP_KERNEL);
 	if (!name) {
 		btrfs_free_path(path);
 		return -ENOMEM;
@@ -2730,7 +2731,7 @@ static int __record_ref(struct list_head *head, u64 dir,
 {
 	struct recorded_ref *ref;
 
-	ref = kmalloc(sizeof(*ref), GFP_NOFS);
+	ref = kmalloc(sizeof(*ref), GFP_KERNEL);
 	if (!ref)
 		return -ENOMEM;
 
@@ -2755,7 +2756,7 @@ static int dup_ref(struct recorded_ref *ref, struct list_head *list)
 {
 	struct recorded_ref *new;
 
-	new = kmalloc(sizeof(*ref), GFP_NOFS);
+	new = kmalloc(sizeof(*ref), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
@@ -2818,7 +2819,7 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
 	struct rb_node *parent = NULL;
 	struct orphan_dir_info *entry, *odi;
 
-	odi = kmalloc(sizeof(*odi), GFP_NOFS);
+	odi = kmalloc(sizeof(*odi), GFP_KERNEL);
 	if (!odi)
 		return ERR_PTR(-ENOMEM);
 	odi->ino = dir_ino;
@@ -2973,7 +2974,7 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino, bool orphanized)
 	struct rb_node *parent = NULL;
 	struct waiting_dir_move *entry, *dm;
 
-	dm = kmalloc(sizeof(*dm), GFP_NOFS);
+	dm = kmalloc(sizeof(*dm), GFP_KERNEL);
 	if (!dm)
 		return -ENOMEM;
 	dm->ino = ino;
@@ -3040,7 +3041,7 @@ static int add_pending_dir_move(struct send_ctx *sctx,
 	int exists = 0;
 	int ret;
 
-	pm = kmalloc(sizeof(*pm), GFP_NOFS);
+	pm = kmalloc(sizeof(*pm), GFP_KERNEL);
 	if (!pm)
 		return -ENOMEM;
 	pm->parent_ino = parent_ino;
@@ -4280,7 +4281,7 @@ static int __find_xattr(int num, struct btrfs_key *di_key,
 	    strncmp(name, ctx->name, name_len) == 0) {
 		ctx->found_idx = num;
 		ctx->found_data_len = data_len;
-		ctx->found_data = kmemdup(data, data_len, GFP_NOFS);
+		ctx->found_data = kmemdup(data, data_len, GFP_KERNEL);
 		if (!ctx->found_data)
 			return -ENOMEM;
 		return 1;
@@ -4481,7 +4482,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 	while (index <= last_index) {
 		unsigned cur_len = min_t(unsigned, len,
 					 PAGE_CACHE_SIZE - pg_offset);
-		page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
+		page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL);
 		if (!page) {
 			ret = -ENOMEM;
 			break;
@@ -5989,7 +5990,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 		goto out;
 	}
 
-	sctx = kzalloc(sizeof(struct send_ctx), GFP_NOFS);
+	sctx = kzalloc(sizeof(struct send_ctx), GFP_KERNEL);
 	if (!sctx) {
 		ret = -ENOMEM;
 		goto out;
@@ -5997,7 +5998,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 
 	INIT_LIST_HEAD(&sctx->new_refs);
 	INIT_LIST_HEAD(&sctx->deleted_refs);
-	INIT_RADIX_TREE(&sctx->name_cache, GFP_NOFS);
+	INIT_RADIX_TREE(&sctx->name_cache, GFP_KERNEL);
 	INIT_LIST_HEAD(&sctx->name_cache_list);
 
 	sctx->flags = arg->flags;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d41e09fe8e38..00b8f37cc306 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -303,7 +303,8 @@ enum {
 	Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_rescan_uuid_tree,
 	Opt_commit_interval, Opt_barrier, Opt_nodefrag, Opt_nodiscard,
 	Opt_noenospc_debug, Opt_noflushoncommit, Opt_acl, Opt_datacow,
-	Opt_datasum, Opt_treelog, Opt_noinode_cache,
+	Opt_datasum, Opt_treelog, Opt_noinode_cache, Opt_usebackuproot,
+	Opt_nologreplay, Opt_norecovery,
 #ifdef CONFIG_BTRFS_DEBUG
 	Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all,
 #endif
@@ -335,6 +336,8 @@ static const match_table_t tokens = {
 	{Opt_noacl, "noacl"},
 	{Opt_notreelog, "notreelog"},
 	{Opt_treelog, "treelog"},
+	{Opt_nologreplay, "nologreplay"},
+	{Opt_norecovery, "norecovery"},
 	{Opt_flushoncommit, "flushoncommit"},
 	{Opt_noflushoncommit, "noflushoncommit"},
 	{Opt_ratio, "metadata_ratio=%d"},
@@ -352,7 +355,8 @@ static const match_table_t tokens = {
 	{Opt_inode_cache, "inode_cache"},
 	{Opt_noinode_cache, "noinode_cache"},
 	{Opt_no_space_cache, "nospace_cache"},
-	{Opt_recovery, "recovery"},
+	{Opt_recovery, "recovery"}, /* deprecated */
+	{Opt_usebackuproot, "usebackuproot"},
 	{Opt_skip_balance, "skip_balance"},
 	{Opt_check_integrity, "check_int"},
 	{Opt_check_integrity_including_extent_data, "check_int_data"},
@@ -373,7 +377,8 @@ static const match_table_t tokens = {
  * reading in a new superblock is parsed here.
  * XXX JDM: This needs to be cleaned up for remount.
  */
-int btrfs_parse_options(struct btrfs_root *root, char *options)
+int btrfs_parse_options(struct btrfs_root *root, char *options,
+			unsigned long new_flags)
 {
 	struct btrfs_fs_info *info = root->fs_info;
 	substring_t args[MAX_OPT_ARGS];
@@ -393,8 +398,12 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 	else if (cache_gen)
 		btrfs_set_opt(info->mount_opt, SPACE_CACHE);
 
+	/*
+	 * Even the options are empty, we still need to do extra check
+	 * against new flags
+	 */
 	if (!options)
-		goto out;
+		goto check;
 
 	/*
 	 * strsep changes the string, duplicate it because parse_options
@@ -606,6 +615,11 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			btrfs_clear_and_info(root, NOTREELOG,
 					     "enabling tree log");
 			break;
+		case Opt_norecovery:
+		case Opt_nologreplay:
+			btrfs_set_and_info(root, NOLOGREPLAY,
+					   "disabling log replay at mount time");
+			break;
 		case Opt_flushoncommit:
 			btrfs_set_and_info(root, FLUSHONCOMMIT,
 					   "turning on flush-on-commit");
@@ -696,8 +710,12 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 					     "disabling auto defrag");
 			break;
 		case Opt_recovery:
-			btrfs_info(root->fs_info, "enabling auto recovery");
-			btrfs_set_opt(info->mount_opt, RECOVERY);
+			btrfs_warn(root->fs_info,
+				   "'recovery' is deprecated, use 'usebackuproot' instead");
+		case Opt_usebackuproot:
+			btrfs_info(root->fs_info,
+				   "trying to use backup root at mount time");
+			btrfs_set_opt(info->mount_opt, USEBACKUPROOT);
 			break;
 		case Opt_skip_balance:
 			btrfs_set_opt(info->mount_opt, SKIP_BALANCE);
@@ -792,6 +810,15 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			break;
 		}
 	}
+check:
+	/*
+	 * Extra check for current option against current flag
+	 */
+	if (btrfs_test_opt(root, NOLOGREPLAY) && !(new_flags & MS_RDONLY)) {
+		btrfs_err(root->fs_info,
+			  "nologreplay must be used with ro mount option");
+		ret = -EINVAL;
+	}
 out:
 	if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE) &&
 	    !btrfs_test_opt(root, FREE_SPACE_TREE) &&
@@ -1202,6 +1229,8 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",ssd");
 	if (btrfs_test_opt(root, NOTREELOG))
 		seq_puts(seq, ",notreelog");
+	if (btrfs_test_opt(root, NOLOGREPLAY))
+		seq_puts(seq, ",nologreplay");
 	if (btrfs_test_opt(root, FLUSHONCOMMIT))
 		seq_puts(seq, ",flushoncommit");
 	if (btrfs_test_opt(root, DISCARD))
@@ -1228,8 +1257,6 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",inode_cache");
 	if (btrfs_test_opt(root, SKIP_BALANCE))
 		seq_puts(seq, ",skip_balance");
-	if (btrfs_test_opt(root, RECOVERY))
-		seq_puts(seq, ",recovery");
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
 	if (btrfs_test_opt(root, CHECK_INTEGRITY_INCLUDING_EXTENT_DATA))
 		seq_puts(seq, ",check_int_data");
@@ -1685,7 +1712,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		}
 	}
 
-	ret = btrfs_parse_options(root, data);
+	ret = btrfs_parse_options(root, data, *flags);
 	if (ret) {
 		ret = -EINVAL;
 		goto restore;
@@ -2163,6 +2190,9 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 			break;
 		ret = !(fs_devices->num_devices == fs_devices->total_devices);
 		break;
+	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
+		ret = btrfs_ioctl_get_supported_features((void __user*)arg);
+		break;
 	}
 
 	kfree(vol);
@@ -2261,7 +2291,7 @@ static void btrfs_interface_exit(void)
 	misc_deregister(&btrfs_misc);
 }
 
-static void btrfs_print_info(void)
+static void btrfs_print_mod_info(void)
 {
 	printk(KERN_INFO "Btrfs loaded"
 #ifdef CONFIG_BTRFS_DEBUG
@@ -2363,7 +2393,7 @@ static int __init init_btrfs_fs(void)
 
 	btrfs_init_lockdep();
 
-	btrfs_print_info();
+	btrfs_print_mod_info();
 
 	err = btrfs_run_sanity_tests();
 	if (err)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index e0ac85949067..539e7b5e3f86 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -202,6 +202,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF);
 BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56);
 BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
 BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
+BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
 
 static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(mixed_backref),
@@ -213,6 +214,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(raid56),
 	BTRFS_FEAT_ATTR_PTR(skinny_metadata),
 	BTRFS_FEAT_ATTR_PTR(no_holes),
+	BTRFS_FEAT_ATTR_PTR(free_space_tree),
 	NULL
 };
 
@@ -780,6 +782,39 @@ failure:
 	return error;
 }
 
+
+/*
+ * Change per-fs features in /sys/fs/btrfs/UUID/features to match current
+ * values in superblock. Call after any changes to incompat/compat_ro flags
+ */
+void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
+		u64 bit, enum btrfs_feature_set set)
+{
+	struct btrfs_fs_devices *fs_devs;
+	struct kobject *fsid_kobj;
+	u64 features;
+	int ret;
+
+	if (!fs_info)
+		return;
+
+	features = get_features(fs_info, set);
+	ASSERT(bit & supported_feature_masks[set]);
+
+	fs_devs = fs_info->fs_devices;
+	fsid_kobj = &fs_devs->fsid_kobj;
+
+	if (!fsid_kobj->state_initialized)
+		return;
+
+	/*
+	 * FIXME: this is too heavy to update just one value, ideally we'd like
+	 * to use sysfs_update_group but some refactoring is needed first.
+	 */
+	sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group);
+	ret = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group);
+}
+
 static int btrfs_init_debugfs(void)
 {
 #ifdef CONFIG_DEBUG_FS
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 9c09522125a6..d7da1a4c2f6c 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -56,7 +56,7 @@ static struct btrfs_feature_attr btrfs_attr_##_name = {			     \
 #define BTRFS_FEAT_ATTR_COMPAT(name, feature) \
 	BTRFS_FEAT_ATTR(name, FEAT_COMPAT, BTRFS_FEATURE_COMPAT, feature)
 #define BTRFS_FEAT_ATTR_COMPAT_RO(name, feature) \
-	BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT, feature)
+	BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT_RO, feature)
 #define BTRFS_FEAT_ATTR_INCOMPAT(name, feature) \
 	BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature)
 
@@ -90,4 +90,7 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs,
 				struct kobject *parent);
 int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs);
 void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs);
+void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
+		u64 bit, enum btrfs_feature_set set);
+
 #endif /* _BTRFS_SYSFS_H_ */
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index b1d920b30070..f54bf450bad3 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -82,18 +82,18 @@ void btrfs_destroy_test_fs(void)
 struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void)
 {
 	struct btrfs_fs_info *fs_info = kzalloc(sizeof(struct btrfs_fs_info),
-						GFP_NOFS);
+						GFP_KERNEL);
 
 	if (!fs_info)
 		return fs_info;
 	fs_info->fs_devices = kzalloc(sizeof(struct btrfs_fs_devices),
-				      GFP_NOFS);
+				      GFP_KERNEL);
 	if (!fs_info->fs_devices) {
 		kfree(fs_info);
 		return NULL;
 	}
 	fs_info->super_copy = kzalloc(sizeof(struct btrfs_super_block),
-				      GFP_NOFS);
+				      GFP_KERNEL);
 	if (!fs_info->super_copy) {
 		kfree(fs_info->fs_devices);
 		kfree(fs_info);
@@ -137,7 +137,6 @@ static void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
 	void **slot;
 
 	spin_lock(&fs_info->buffer_lock);
-restart:
 	radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) {
 		struct extent_buffer *eb;
 
@@ -147,7 +146,7 @@ restart:
 		/* Shouldn't happen but that kind of thinking creates CVE's */
 		if (radix_tree_exception(eb)) {
 			if (radix_tree_deref_retry(eb))
-				goto restart;
+				slot = radix_tree_iter_retry(&iter);
 			continue;
 		}
 		spin_unlock(&fs_info->buffer_lock);
@@ -180,21 +179,15 @@ btrfs_alloc_dummy_block_group(unsigned long length)
 {
 	struct btrfs_block_group_cache *cache;
 
-	cache = kzalloc(sizeof(*cache), GFP_NOFS);
+	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
 	if (!cache)
 		return NULL;
 	cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
-					GFP_NOFS);
+					GFP_KERNEL);
 	if (!cache->free_space_ctl) {
 		kfree(cache);
 		return NULL;
 	}
-	cache->fs_info = btrfs_alloc_dummy_fs_info();
-	if (!cache->fs_info) {
-		kfree(cache->free_space_ctl);
-		kfree(cache);
-		return NULL;
-	}
 
 	cache->key.objectid = 0;
 	cache->key.offset = length;
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index e29fa297e053..669b58201e36 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -94,7 +94,7 @@ static int test_find_delalloc(void)
 	 * test.
 	 */
 	for (index = 0; index < (total_dirty >> PAGE_CACHE_SHIFT); index++) {
-		page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
+		page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL);
 		if (!page) {
 			test_msg("Failed to allocate test page\n");
 			ret = -ENOMEM;
@@ -113,7 +113,7 @@ static int test_find_delalloc(void)
 	 * |--- delalloc ---|
 	 * |---  search  ---|
 	 */
-	set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_NOFS);
+	set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_KERNEL);
 	start = 0;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -144,7 +144,7 @@ static int test_find_delalloc(void)
 		test_msg("Couldn't find the locked page\n");
 		goto out_bits;
 	}
-	set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_NOFS);
+	set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_KERNEL);
 	start = test_start;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -199,7 +199,7 @@ static int test_find_delalloc(void)
 	 *
 	 * We are re-using our test_start from above since it works out well.
 	 */
-	set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_NOFS);
+	set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_KERNEL);
 	start = test_start;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -262,7 +262,7 @@ static int test_find_delalloc(void)
 	}
 	ret = 0;
 out_bits:
-	clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_NOFS);
+	clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_KERNEL);
 out:
 	if (locked_page)
 		page_cache_release(locked_page);
@@ -360,7 +360,7 @@ static int test_eb_bitmaps(void)
 
 	test_msg("Running extent buffer bitmap tests\n");
 
-	bitmap = kmalloc(len, GFP_NOFS);
+	bitmap = kmalloc(len, GFP_KERNEL);
 	if (!bitmap) {
 		test_msg("Couldn't allocate test bitmap\n");
 		return -ENOMEM;
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
index d05fe1ab4808..7cea4462acd5 100644
--- a/fs/btrfs/tests/free-space-tree-tests.c
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -485,6 +485,7 @@ static int run_test(test_func_t test_func, int bitmaps)
 	cache->bitmap_low_thresh = 0;
 	cache->bitmap_high_thresh = (u32)-1;
 	cache->needs_free_space = 1;
+	cache->fs_info = root->fs_info;
 
 	btrfs_init_dummy_trans(&trans);
 
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 5de55fdd28bc..863a6a3af1f8 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -22,6 +22,7 @@
 #include "../disk-io.h"
 #include "../extent_io.h"
 #include "../volumes.h"
+#include "../compression.h"
 
 static void insert_extent(struct btrfs_root *root, u64 start, u64 len,
 			  u64 ram_bytes, u64 offset, u64 disk_bytenr,
@@ -974,7 +975,7 @@ static int test_extent_accounting(void)
 			       (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
 			       EXTENT_DELALLOC | EXTENT_DIRTY |
 			       EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0,
-			       NULL, GFP_NOFS);
+			       NULL, GFP_KERNEL);
 	if (ret) {
 		test_msg("clear_extent_bit returned %d\n", ret);
 		goto out;
@@ -1045,7 +1046,7 @@ static int test_extent_accounting(void)
 			       BTRFS_MAX_EXTENT_SIZE+8191,
 			       EXTENT_DIRTY | EXTENT_DELALLOC |
 			       EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
-			       NULL, GFP_NOFS);
+			       NULL, GFP_KERNEL);
 	if (ret) {
 		test_msg("clear_extent_bit returned %d\n", ret);
 		goto out;
@@ -1079,7 +1080,7 @@ static int test_extent_accounting(void)
 	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);
+			       NULL, GFP_KERNEL);
 	if (ret) {
 		test_msg("clear_extent_bit returned %d\n", ret);
 		goto out;
@@ -1096,7 +1097,7 @@ out:
 		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);
+				 NULL, GFP_KERNEL);
 	iput(inode);
 	btrfs_free_dummy_root(root);
 	return ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index b6031ce474f7..43885e51b882 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -637,6 +637,8 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
 
 	trans->block_rsv = &root->fs_info->trans_block_rsv;
 	trans->bytes_reserved = num_bytes;
+	trace_btrfs_space_reservation(root->fs_info, "transaction",
+				      trans->transid, num_bytes, 1);
 
 	return trans;
 }
@@ -1333,7 +1335,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	struct dentry *dentry;
 	struct extent_buffer *tmp;
 	struct extent_buffer *old;
-	struct timespec cur_time = CURRENT_TIME;
+	struct timespec cur_time;
 	int ret = 0;
 	u64 to_reserve = 0;
 	u64 index = 0;
@@ -1375,12 +1377,16 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	rsv = trans->block_rsv;
 	trans->block_rsv = &pending->block_rsv;
 	trans->bytes_reserved = trans->block_rsv->reserved;
-
+	trace_btrfs_space_reservation(root->fs_info, "transaction",
+				      trans->transid,
+				      trans->bytes_reserved, 1);
 	dentry = pending->dentry;
 	parent_inode = pending->dir;
 	parent_root = BTRFS_I(parent_inode)->root;
 	record_root_in_trans(trans, parent_root);
 
+	cur_time = current_fs_time(parent_inode->i_sb);
+
 	/*
 	 * insert the directory item
 	 */
@@ -1523,7 +1529,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 
 	btrfs_i_size_write(parent_inode, parent_inode->i_size +
 					 dentry->d_name.len * 2);
-	parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
+	parent_inode->i_mtime = parent_inode->i_ctime =
+		current_fs_time(parent_inode->i_sb);
 	ret = btrfs_update_inode_fallback(trans, parent_root, parent_inode);
 	if (ret) {
 		btrfs_abort_transaction(trans, root, ret);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 323e12cc9d2f..24d03c751149 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -26,6 +26,7 @@
 #include "print-tree.h"
 #include "backref.h"
 #include "hash.h"
+#include "compression.h"
 
 /* magic values for the inode_only field in btrfs_log_inode:
  *
@@ -1045,7 +1046,7 @@ again:
 
 		/*
 		 * NOTE: we have searched root tree and checked the
-		 * coresponding ref, it does not need to check again.
+		 * corresponding ref, it does not need to check again.
 		 */
 		*search_done = 1;
 	}
@@ -4127,7 +4128,9 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 				     struct inode *inode,
 				     struct btrfs_path *path,
 				     struct list_head *logged_list,
-				     struct btrfs_log_ctx *ctx)
+				     struct btrfs_log_ctx *ctx,
+				     const u64 start,
+				     const u64 end)
 {
 	struct extent_map *em, *n;
 	struct list_head extents;
@@ -4166,7 +4169,13 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	}
 
 	list_sort(NULL, &extents, extent_cmp);
-
+	/*
+	 * Collect any new ordered extents within the range. This is to
+	 * prevent logging file extent items without waiting for the disk
+	 * location they point to being written. We do this only to deal
+	 * with races against concurrent lockless direct IO writes.
+	 */
+	btrfs_get_logged_extents(inode, logged_list, start, end);
 process:
 	while (!list_empty(&extents)) {
 		em = list_entry(extents.next, struct extent_map, list);
@@ -4492,7 +4501,22 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 
 	mutex_lock(&BTRFS_I(inode)->log_mutex);
 
-	btrfs_get_logged_extents(inode, &logged_list, start, end);
+	/*
+	 * Collect ordered extents only if we are logging data. This is to
+	 * ensure a subsequent request to log this inode in LOG_INODE_ALL mode
+	 * will process the ordered extents if they still exists at the time,
+	 * because when we collect them we test and set for the flag
+	 * BTRFS_ORDERED_LOGGED to prevent multiple log requests to process the
+	 * same ordered extents. The consequence for the LOG_INODE_ALL log mode
+	 * not processing the ordered extents is that we end up logging the
+	 * corresponding file extent items, based on the extent maps in the
+	 * inode's extent_map_tree's modified_list, without logging the
+	 * respective checksums (since the may still be only attached to the
+	 * ordered extents and have not been inserted in the csum tree by
+	 * btrfs_finish_ordered_io() yet).
+	 */
+	if (inode_only == LOG_INODE_ALL)
+		btrfs_get_logged_extents(inode, &logged_list, start, end);
 
 	/*
 	 * a brute force approach to making sure we get the most uptodate
@@ -4701,7 +4725,7 @@ log_extents:
 			goto out_unlock;
 		}
 		ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
-						&logged_list, ctx);
+						&logged_list, ctx, start, end);
 		if (ret) {
 			err = ret;
 			goto out_unlock;
@@ -4764,6 +4788,42 @@ out_unlock:
 }
 
 /*
+ * Check if we must fallback to a transaction commit when logging an inode.
+ * This must be called after logging the inode and is used only in the context
+ * when fsyncing an inode requires the need to log some other inode - in which
+ * case we can't lock the i_mutex of each other inode we need to log as that
+ * can lead to deadlocks with concurrent fsync against other inodes (as we can
+ * log inodes up or down in the hierarchy) or rename operations for example. So
+ * we take the log_mutex of the inode after we have logged it and then check for
+ * its last_unlink_trans value - this is safe because any task setting
+ * last_unlink_trans must take the log_mutex and it must do this before it does
+ * the actual unlink operation, so if we do this check before a concurrent task
+ * sets last_unlink_trans it means we've logged a consistent version/state of
+ * all the inode items, otherwise we are not sure and must do a transaction
+ * commit (the concurrent task migth have only updated last_unlink_trans before
+ * we logged the inode or it might have also done the unlink).
+ */
+static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
+					  struct inode *inode)
+{
+	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+	bool ret = false;
+
+	mutex_lock(&BTRFS_I(inode)->log_mutex);
+	if (BTRFS_I(inode)->last_unlink_trans > fs_info->last_trans_committed) {
+		/*
+		 * Make sure any commits to the log are forced to be full
+		 * commits.
+		 */
+		btrfs_set_log_full_commit(fs_info, trans);
+		ret = true;
+	}
+	mutex_unlock(&BTRFS_I(inode)->log_mutex);
+
+	return ret;
+}
+
+/*
  * follow the dentry parent pointers up the chain and see if any
  * of the directories in it require a full commit before they can
  * be logged.  Returns zero if nothing special needs to be done or 1 if
@@ -4776,7 +4836,6 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 					       u64 last_committed)
 {
 	int ret = 0;
-	struct btrfs_root *root;
 	struct dentry *old_parent = NULL;
 	struct inode *orig_inode = inode;
 
@@ -4808,14 +4867,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 			BTRFS_I(inode)->logged_trans = trans->transid;
 		smp_mb();
 
-		if (BTRFS_I(inode)->last_unlink_trans > last_committed) {
-			root = BTRFS_I(inode)->root;
-
-			/*
-			 * make sure any commits to the log are forced
-			 * to be full commits
-			 */
-			btrfs_set_log_full_commit(root->fs_info, trans);
+		if (btrfs_must_commit_transaction(trans, inode)) {
 			ret = 1;
 			break;
 		}
@@ -4974,6 +5026,9 @@ process_leaf:
 			btrfs_release_path(path);
 			ret = btrfs_log_inode(trans, root, di_inode,
 					      log_mode, 0, LLONG_MAX, ctx);
+			if (!ret &&
+			    btrfs_must_commit_transaction(trans, di_inode))
+				ret = 1;
 			iput(di_inode);
 			if (ret)
 				goto next_dir_inode;
@@ -5088,6 +5143,9 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 
 			ret = btrfs_log_inode(trans, root, dir_inode,
 					      LOG_INODE_ALL, 0, LLONG_MAX, ctx);
+			if (!ret &&
+			    btrfs_must_commit_transaction(trans, dir_inode))
+				ret = 1;
 			iput(dir_inode);
 			if (ret)
 				goto out;
@@ -5439,6 +5497,9 @@ error:
  * They revolve around files there were unlinked from the directory, and
  * this function updates the parent directory so that a full commit is
  * properly done if it is fsync'd later after the unlinks are done.
+ *
+ * Must be called before the unlink operations (updates to the subvolume tree,
+ * inodes, etc) are done.
  */
 void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 			     struct inode *dir, struct inode *inode,
@@ -5454,8 +5515,11 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 	 * into the file.  When the file is logged we check it and
 	 * don't log the parents if the file is fully on disk.
 	 */
-	if (S_ISREG(inode->i_mode))
+	if (S_ISREG(inode->i_mode)) {
+		mutex_lock(&BTRFS_I(inode)->log_mutex);
 		BTRFS_I(inode)->last_unlink_trans = trans->transid;
+		mutex_unlock(&BTRFS_I(inode)->log_mutex);
+	}
 
 	/*
 	 * if this directory was already logged any new
@@ -5486,7 +5550,29 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 	return;
 
 record:
+	mutex_lock(&BTRFS_I(dir)->log_mutex);
 	BTRFS_I(dir)->last_unlink_trans = trans->transid;
+	mutex_unlock(&BTRFS_I(dir)->log_mutex);
+}
+
+/*
+ * Make sure that if someone attempts to fsync the parent directory of a deleted
+ * snapshot, it ends up triggering a transaction commit. This is to guarantee
+ * that after replaying the log tree of the parent directory's root we will not
+ * see the snapshot anymore and at log replay time we will not see any log tree
+ * corresponding to the deleted snapshot's root, which could lead to replaying
+ * it after replaying the log tree of the parent directory (which would replay
+ * the snapshot delete operation).
+ *
+ * Must be called before the actual snapshot destroy operation (updates to the
+ * parent root and tree of tree roots trees, etc) are done.
+ */
+void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
+				   struct inode *dir)
+{
+	mutex_lock(&BTRFS_I(dir)->log_mutex);
+	BTRFS_I(dir)->last_unlink_trans = trans->transid;
+	mutex_unlock(&BTRFS_I(dir)->log_mutex);
 }
 
 /*
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index 6916a781ea02..a9f1b75d080d 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -79,6 +79,8 @@ int btrfs_pin_log_trans(struct btrfs_root *root);
 void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 			     struct inode *dir, struct inode *inode,
 			     int for_rename);
+void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
+				   struct inode *dir);
 int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 			struct inode *inode, struct inode *old_dir,
 			struct dentry *parent);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 366b335946fa..e2b54d546b7c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -138,7 +138,7 @@ static struct btrfs_fs_devices *__alloc_fs_devices(void)
 {
 	struct btrfs_fs_devices *fs_devs;
 
-	fs_devs = kzalloc(sizeof(*fs_devs), GFP_NOFS);
+	fs_devs = kzalloc(sizeof(*fs_devs), GFP_KERNEL);
 	if (!fs_devs)
 		return ERR_PTR(-ENOMEM);
 
@@ -220,7 +220,7 @@ static struct btrfs_device *__alloc_device(void)
 {
 	struct btrfs_device *dev;
 
-	dev = kzalloc(sizeof(*dev), GFP_NOFS);
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
@@ -733,7 +733,8 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		 * uuid mutex so nothing we touch in here is going to disappear.
 		 */
 		if (orig_dev->name) {
-			name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS);
+			name = rcu_string_strdup(orig_dev->name->str,
+					GFP_KERNEL);
 			if (!name) {
 				kfree(device);
 				goto error;
@@ -1714,12 +1715,12 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	} while (read_seqretry(&root->fs_info->profiles_lock, seq));
 
 	num_devices = root->fs_info->fs_devices->num_devices;
-	btrfs_dev_replace_lock(&root->fs_info->dev_replace);
+	btrfs_dev_replace_lock(&root->fs_info->dev_replace, 0);
 	if (btrfs_dev_replace_is_ongoing(&root->fs_info->dev_replace)) {
 		WARN_ON(num_devices < 1);
 		num_devices--;
 	}
-	btrfs_dev_replace_unlock(&root->fs_info->dev_replace);
+	btrfs_dev_replace_unlock(&root->fs_info->dev_replace, 0);
 
 	if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) && num_devices <= 4) {
 		ret = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET;
@@ -2287,7 +2288,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 		goto error;
 	}
 
-	name = rcu_string_strdup(device_path, GFP_NOFS);
+	name = rcu_string_strdup(device_path, GFP_KERNEL);
 	if (!name) {
 		kfree(device);
 		ret = -ENOMEM;
@@ -2748,7 +2749,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	    em->start + em->len < chunk_offset) {
 		/*
 		 * This is a logic error, but we don't want to just rely on the
-		 * user having built with ASSERT enabled, so if ASSERT doens't
+		 * user having built with ASSERT enabled, so if ASSERT doesn't
 		 * do anything we still error out.
 		 */
 		ASSERT(0);
@@ -2966,7 +2967,7 @@ static int insert_balance_item(struct btrfs_root *root,
 	}
 
 	key.objectid = BTRFS_BALANCE_OBJECTID;
-	key.type = BTRFS_BALANCE_ITEM_KEY;
+	key.type = BTRFS_TEMPORARY_ITEM_KEY;
 	key.offset = 0;
 
 	ret = btrfs_insert_empty_item(trans, root, path, &key,
@@ -3015,7 +3016,7 @@ static int del_balance_item(struct btrfs_root *root)
 	}
 
 	key.objectid = BTRFS_BALANCE_OBJECTID;
-	key.type = BTRFS_BALANCE_ITEM_KEY;
+	key.type = BTRFS_TEMPORARY_ITEM_KEY;
 	key.offset = 0;
 
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
@@ -3686,12 +3687,12 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 	}
 
 	num_devices = fs_info->fs_devices->num_devices;
-	btrfs_dev_replace_lock(&fs_info->dev_replace);
+	btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
 	if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) {
 		BUG_ON(num_devices < 1);
 		num_devices--;
 	}
-	btrfs_dev_replace_unlock(&fs_info->dev_replace);
+	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 	allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
 	if (num_devices == 1)
 		allowed |= BTRFS_BLOCK_GROUP_DUP;
@@ -3867,7 +3868,7 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
 		return -ENOMEM;
 
 	key.objectid = BTRFS_BALANCE_OBJECTID;
-	key.type = BTRFS_BALANCE_ITEM_KEY;
+	key.type = BTRFS_TEMPORARY_ITEM_KEY;
 	key.offset = 0;
 
 	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
@@ -4118,7 +4119,7 @@ out:
  * Callback for btrfs_uuid_tree_iterate().
  * returns:
  * 0	check succeeded, the entry is not outdated.
- * < 0	if an error occured.
+ * < 0	if an error occurred.
  * > 0	if the check failed, which means the caller shall remove the entry.
  */
 static int btrfs_check_uuid_tree_entry(struct btrfs_fs_info *fs_info,
@@ -5062,10 +5063,10 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		ret = 1;
 	free_extent_map(em);
 
-	btrfs_dev_replace_lock(&fs_info->dev_replace);
+	btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
 	if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace))
 		ret++;
-	btrfs_dev_replace_unlock(&fs_info->dev_replace);
+	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 
 	return ret;
 }
@@ -5325,10 +5326,12 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 	if (!bbio_ret)
 		goto out;
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 0);
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
 	if (!dev_replace_is_ongoing)
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 0);
+	else
+		btrfs_dev_replace_set_lock_blocking(dev_replace);
 
 	if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 &&
 	    !(rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS)) &&
@@ -5751,8 +5754,10 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		bbio->mirror_num = map->num_stripes + 1;
 	}
 out:
-	if (dev_replace_is_ongoing)
-		btrfs_dev_replace_unlock(dev_replace);
+	if (dev_replace_is_ongoing) {
+		btrfs_dev_replace_clear_lock_blocking(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 0);
+	}
 	free_extent_map(em);
 	return ret;
 }
@@ -6705,8 +6710,8 @@ int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info)
 		int item_size;
 		struct btrfs_dev_stats_item *ptr;
 
-		key.objectid = 0;
-		key.type = BTRFS_DEV_STATS_KEY;
+		key.objectid = BTRFS_DEV_STATS_OBJECTID;
+		key.type = BTRFS_PERSISTENT_ITEM_KEY;
 		key.offset = device->devid;
 		ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
 		if (ret) {
@@ -6753,8 +6758,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans,
 	int ret;
 	int i;
 
-	key.objectid = 0;
-	key.type = BTRFS_DEV_STATS_KEY;
+	key.objectid = BTRFS_DEV_STATS_OBJECTID;
+	key.type = BTRFS_PERSISTENT_ITEM_KEY;
 	key.offset = device->devid;
 
 	path = btrfs_alloc_path();
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 6c68d6356197..145d2b89e62d 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -249,7 +249,7 @@ int __btrfs_setxattr(struct btrfs_trans_handle *trans,
 		goto out;
 
 	inode_inc_iversion(inode);
-	inode->i_ctime = CURRENT_TIME;
+	inode->i_ctime = current_fs_time(inode->i_sb);
 	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
 	ret = btrfs_update_inode(trans, root, inode);
 	BUG_ON(ret);
@@ -260,16 +260,12 @@ out:
 
 ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 {
-	struct btrfs_key key, found_key;
+	struct btrfs_key key;
 	struct inode *inode = d_inode(dentry);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path;
-	struct extent_buffer *leaf;
-	struct btrfs_dir_item *di;
-	int ret = 0, slot;
+	int ret = 0;
 	size_t total_size = 0, size_left = size;
-	unsigned long name_ptr;
-	size_t name_len;
 
 	/*
 	 * ok we want all objects associated with this id.
@@ -291,6 +287,13 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 		goto err;
 
 	while (1) {
+		struct extent_buffer *leaf;
+		int slot;
+		struct btrfs_dir_item *di;
+		struct btrfs_key found_key;
+		u32 item_size;
+		u32 cur;
+
 		leaf = path->nodes[0];
 		slot = path->slots[0];
 
@@ -316,31 +319,45 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 		if (found_key.type > BTRFS_XATTR_ITEM_KEY)
 			break;
 		if (found_key.type < BTRFS_XATTR_ITEM_KEY)
-			goto next;
+			goto next_item;
 
 		di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
-		if (verify_dir_item(root, leaf, di))
-			goto next;
-
-		name_len = btrfs_dir_name_len(leaf, di);
-		total_size += name_len + 1;
+		item_size = btrfs_item_size_nr(leaf, slot);
+		cur = 0;
+		while (cur < item_size) {
+			u16 name_len = btrfs_dir_name_len(leaf, di);
+			u16 data_len = btrfs_dir_data_len(leaf, di);
+			u32 this_len = sizeof(*di) + name_len + data_len;
+			unsigned long name_ptr = (unsigned long)(di + 1);
+
+			if (verify_dir_item(root, leaf, di)) {
+				ret = -EIO;
+				goto err;
+			}
 
-		/* we are just looking for how big our buffer needs to be */
-		if (!size)
-			goto next;
+			total_size += name_len + 1;
+			/*
+			 * We are just looking for how big our buffer needs to
+			 * be.
+			 */
+			if (!size)
+				goto next;
 
-		if (!buffer || (name_len + 1) > size_left) {
-			ret = -ERANGE;
-			goto err;
-		}
+			if (!buffer || (name_len + 1) > size_left) {
+				ret = -ERANGE;
+				goto err;
+			}
 
-		name_ptr = (unsigned long)(di + 1);
-		read_extent_buffer(leaf, buffer, name_ptr, name_len);
-		buffer[name_len] = '\0';
+			read_extent_buffer(leaf, buffer, name_ptr, name_len);
+			buffer[name_len] = '\0';
 
-		size_left -= name_len + 1;
-		buffer += name_len + 1;
+			size_left -= name_len + 1;
+			buffer += name_len + 1;
 next:
+			cur += this_len;
+			di = (struct btrfs_dir_item *)((char *)di + this_len);
+		}
+next_item:
 		path->slots[0]++;
 	}
 	ret = total_size;
diff --git a/fs/buffer.c b/fs/buffer.c
index e1632abb4ca9..33be29675358 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -621,17 +621,17 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  * If warn is true, then emit a warning if the page is not uptodate and has
  * not been truncated.
  *
- * The caller must hold mem_cgroup_begin_page_stat() lock.
+ * The caller must hold lock_page_memcg().
  */
 static void __set_page_dirty(struct page *page, struct address_space *mapping,
-			     struct mem_cgroup *memcg, int warn)
+			     int warn)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
-		account_page_dirtied(page, mapping, memcg);
+		account_page_dirtied(page, mapping);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
@@ -666,7 +666,6 @@ static void __set_page_dirty(struct page *page, struct address_space *mapping,
 int __set_page_dirty_buffers(struct page *page)
 {
 	int newly_dirty;
-	struct mem_cgroup *memcg;
 	struct address_space *mapping = page_mapping(page);
 
 	if (unlikely(!mapping))
@@ -683,17 +682,17 @@ int __set_page_dirty_buffers(struct page *page)
 		} while (bh != head);
 	}
 	/*
-	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
-	 * per-memcg dirty page counters.
+	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * synchronized with per-memcg dirty page counters.
 	 */
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 
 	if (newly_dirty)
-		__set_page_dirty(page, mapping, memcg, 1);
+		__set_page_dirty(page, mapping, 1);
 
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 
 	if (newly_dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
@@ -1167,15 +1166,14 @@ void mark_buffer_dirty(struct buffer_head *bh)
 	if (!test_set_buffer_dirty(bh)) {
 		struct page *page = bh->b_page;
 		struct address_space *mapping = NULL;
-		struct mem_cgroup *memcg;
 
-		memcg = mem_cgroup_begin_page_stat(page);
+		lock_page_memcg(page);
 		if (!TestSetPageDirty(page)) {
 			mapping = page_mapping(page);
 			if (mapping)
-				__set_page_dirty(page, mapping, memcg, 0);
+				__set_page_dirty(page, mapping, 0);
 		}
-		mem_cgroup_end_page_stat(memcg);
+		unlock_page_memcg(page);
 		if (mapping)
 			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index 452e98dd7560..1ee54ffd3a24 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -162,6 +162,8 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
 				      size_t buflen, loff_t *pos)
 {
 	struct cachefiles_cache *cache = file->private_data;
+	unsigned long long b_released;
+	unsigned f_released;
 	char buffer[256];
 	int n;
 
@@ -174,6 +176,8 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
 	cachefiles_has_space(cache, 0, 0);
 
 	/* summarise */
+	f_released = atomic_xchg(&cache->f_released, 0);
+	b_released = atomic_long_xchg(&cache->b_released, 0);
 	clear_bit(CACHEFILES_STATE_CHANGED, &cache->flags);
 
 	n = snprintf(buffer, sizeof(buffer),
@@ -183,15 +187,18 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
 		     " fstop=%llx"
 		     " brun=%llx"
 		     " bcull=%llx"
-		     " bstop=%llx",
+		     " bstop=%llx"
+		     " freleased=%x"
+		     " breleased=%llx",
 		     test_bit(CACHEFILES_CULLING, &cache->flags) ? '1' : '0',
 		     (unsigned long long) cache->frun,
 		     (unsigned long long) cache->fcull,
 		     (unsigned long long) cache->fstop,
 		     (unsigned long long) cache->brun,
 		     (unsigned long long) cache->bcull,
-		     (unsigned long long) cache->bstop
-		     );
+		     (unsigned long long) cache->bstop,
+		     f_released,
+		     b_released);
 
 	if (n > buflen)
 		return -EMSGSIZE;
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 675a3332d72f..861d611b8c05 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -291,15 +291,8 @@ static void cachefiles_drop_object(struct fscache_object *_object)
 	}
 
 	/* note that the object is now inactive */
-	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
-		write_lock(&cache->active_lock);
-		if (!test_and_clear_bit(CACHEFILES_OBJECT_ACTIVE,
-					&object->flags))
-			BUG();
-		rb_erase(&object->active_node, &cache->active_nodes);
-		wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
-		write_unlock(&cache->active_lock);
-	}
+	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags))
+		cachefiles_mark_object_inactive(cache, object);
 
 	dput(object->dentry);
 	object->dentry = NULL;
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 9c4b737a54df..2fcde1a34b7c 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -66,6 +66,8 @@ struct cachefiles_cache {
 	struct rb_root			active_nodes;	/* active nodes (can't be culled) */
 	rwlock_t			active_lock;	/* lock for active_nodes */
 	atomic_t			gravecounter;	/* graveyard uniquifier */
+	atomic_t			f_released;	/* number of objects released lately */
+	atomic_long_t			b_released;	/* number of blocks released lately */
 	unsigned			frun_percent;	/* when to stop culling (% files) */
 	unsigned			fcull_percent;	/* when to start culling (% files) */
 	unsigned			fstop_percent;	/* when to stop allocating (% files) */
@@ -157,6 +159,8 @@ extern char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type);
 /*
  * namei.c
  */
+extern void cachefiles_mark_object_inactive(struct cachefiles_cache *cache,
+					    struct cachefiles_object *object);
 extern int cachefiles_delete_object(struct cachefiles_cache *cache,
 				    struct cachefiles_object *object);
 extern int cachefiles_walk_to_object(struct cachefiles_object *parent,
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 1c2334c163dd..4ae75006e73b 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -258,6 +258,28 @@ requeue:
 }
 
 /*
+ * Mark an object as being inactive.
+ */
+void cachefiles_mark_object_inactive(struct cachefiles_cache *cache,
+				     struct cachefiles_object *object)
+{
+	write_lock(&cache->active_lock);
+	rb_erase(&object->active_node, &cache->active_nodes);
+	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
+	write_unlock(&cache->active_lock);
+
+	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
+
+	/* This object can now be culled, so we need to let the daemon know
+	 * that there is something it can remove if it needs to.
+	 */
+	atomic_long_add(d_backing_inode(object->dentry)->i_blocks,
+			&cache->b_released);
+	if (atomic_inc_return(&cache->f_released))
+		cachefiles_state_changed(cache);
+}
+
+/*
  * delete an object representation from the cache
  * - file backed objects are unlinked
  * - directory backed objects are stuffed into the graveyard for userspace to
@@ -684,11 +706,7 @@ mark_active_timed_out:
 
 check_error:
 	_debug("check error %d", ret);
-	write_lock(&cache->active_lock);
-	rb_erase(&object->active_node, &cache->active_nodes);
-	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
-	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
-	write_unlock(&cache->active_lock);
+	cachefiles_mark_object_inactive(cache, object);
 release_dentry:
 	dput(object->dentry);
 	object->dentry = NULL;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index c22213789090..fc5cae2a0db2 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -175,8 +175,8 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
 
 static int ceph_releasepage(struct page *page, gfp_t g)
 {
-	struct inode *inode = page->mapping ? page->mapping->host : NULL;
-	dout("%p releasepage %p idx %lu\n", inode, page, page->index);
+	dout("%p releasepage %p idx %lu\n", page->mapping->host,
+	     page, page->index);
 	WARN_ON(PageDirty(page));
 
 	/* Can we release the page from the cache? */
@@ -276,7 +276,7 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
 	for (i = 0; i < num_pages; i++) {
 		struct page *page = osd_data->pages[i];
 
-		if (rc < 0 && rc != ENOENT)
+		if (rc < 0 && rc != -ENOENT)
 			goto unlock;
 		if (bytes < (int)PAGE_CACHE_SIZE) {
 			/* zero (remainder of) page */
@@ -606,71 +606,71 @@ static void writepages_finish(struct ceph_osd_request *req,
 	struct inode *inode = req->r_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_osd_data *osd_data;
-	unsigned wrote;
 	struct page *page;
-	int num_pages;
-	int i;
+	int num_pages, total_pages = 0;
+	int i, j;
+	int rc = req->r_result;
 	struct ceph_snap_context *snapc = req->r_snapc;
 	struct address_space *mapping = inode->i_mapping;
-	int rc = req->r_result;
-	u64 bytes = req->r_ops[0].extent.length;
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	long writeback_stat;
-	unsigned issued = ceph_caps_issued(ci);
+	bool remove_page;
 
-	osd_data = osd_req_op_extent_osd_data(req, 0);
-	BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
-	num_pages = calc_pages_for((u64)osd_data->alignment,
-					(u64)osd_data->length);
-	if (rc >= 0) {
-		/*
-		 * Assume we wrote the pages we originally sent.  The
-		 * osd might reply with fewer pages if our writeback
-		 * raced with a truncation and was adjusted at the osd,
-		 * so don't believe the reply.
-		 */
-		wrote = num_pages;
-	} else {
-		wrote = 0;
+
+	dout("writepages_finish %p rc %d\n", inode, rc);
+	if (rc < 0)
 		mapping_set_error(mapping, rc);
-	}
-	dout("writepages_finish %p rc %d bytes %llu wrote %d (pages)\n",
-	     inode, rc, bytes, wrote);
 
-	/* clean all pages */
-	for (i = 0; i < num_pages; i++) {
-		page = osd_data->pages[i];
-		BUG_ON(!page);
-		WARN_ON(!PageUptodate(page));
+	/*
+	 * We lost the cache cap, need to truncate the page before
+	 * it is unlocked, otherwise we'd truncate it later in the
+	 * page truncation thread, possibly losing some data that
+	 * raced its way in
+	 */
+	remove_page = !(ceph_caps_issued(ci) &
+			(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO));
 
-		writeback_stat =
-			atomic_long_dec_return(&fsc->writeback_count);
-		if (writeback_stat <
-		    CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
-			clear_bdi_congested(&fsc->backing_dev_info,
-					    BLK_RW_ASYNC);
+	/* clean all pages */
+	for (i = 0; i < req->r_num_ops; i++) {
+		if (req->r_ops[i].op != CEPH_OSD_OP_WRITE)
+			break;
 
-		ceph_put_snap_context(page_snap_context(page));
-		page->private = 0;
-		ClearPagePrivate(page);
-		dout("unlocking %d %p\n", i, page);
-		end_page_writeback(page);
+		osd_data = osd_req_op_extent_osd_data(req, i);
+		BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
+		num_pages = calc_pages_for((u64)osd_data->alignment,
+					   (u64)osd_data->length);
+		total_pages += num_pages;
+		for (j = 0; j < num_pages; j++) {
+			page = osd_data->pages[j];
+			BUG_ON(!page);
+			WARN_ON(!PageUptodate(page));
+
+			if (atomic_long_dec_return(&fsc->writeback_count) <
+			     CONGESTION_OFF_THRESH(
+					fsc->mount_options->congestion_kb))
+				clear_bdi_congested(&fsc->backing_dev_info,
+						    BLK_RW_ASYNC);
+
+			ceph_put_snap_context(page_snap_context(page));
+			page->private = 0;
+			ClearPagePrivate(page);
+			dout("unlocking %p\n", page);
+			end_page_writeback(page);
+
+			if (remove_page)
+				generic_error_remove_page(inode->i_mapping,
+							  page);
 
-		/*
-		 * We lost the cache cap, need to truncate the page before
-		 * it is unlocked, otherwise we'd truncate it later in the
-		 * page truncation thread, possibly losing some data that
-		 * raced its way in
-		 */
-		if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0)
-			generic_error_remove_page(inode->i_mapping, page);
+			unlock_page(page);
+		}
+		dout("writepages_finish %p wrote %llu bytes cleaned %d pages\n",
+		     inode, osd_data->length, rc >= 0 ? num_pages : 0);
 
-		unlock_page(page);
+		ceph_release_pages(osd_data->pages, num_pages);
 	}
-	dout("%p wrote+cleaned %d pages\n", inode, wrote);
-	ceph_put_wrbuffer_cap_refs(ci, num_pages, snapc);
 
-	ceph_release_pages(osd_data->pages, num_pages);
+	ceph_put_wrbuffer_cap_refs(ci, total_pages, snapc);
+
+	osd_data = osd_req_op_extent_osd_data(req, 0);
 	if (osd_data->pages_from_pool)
 		mempool_free(osd_data->pages,
 			     ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool);
@@ -778,17 +778,15 @@ retry:
 	while (!done && index <= end) {
 		unsigned i;
 		int first;
-		pgoff_t next;
-		int pvec_pages, locked_pages;
-		struct page **pages = NULL;
+		pgoff_t strip_unit_end = 0;
+		int num_ops = 0, op_idx;
+		int pvec_pages, locked_pages = 0;
+		struct page **pages = NULL, **data_pages;
 		mempool_t *pool = NULL;	/* Becomes non-null if mempool used */
 		struct page *page;
 		int want;
-		u64 offset, len;
-		long writeback_stat;
+		u64 offset = 0, len = 0;
 
-		next = 0;
-		locked_pages = 0;
 		max_pages = max_pages_ever;
 
 get_more_pages:
@@ -824,8 +822,8 @@ get_more_pages:
 				unlock_page(page);
 				break;
 			}
-			if (next && (page->index != next)) {
-				dout("not consecutive %p\n", page);
+			if (strip_unit_end && (page->index > strip_unit_end)) {
+				dout("end of strip unit %p\n", page);
 				unlock_page(page);
 				break;
 			}
@@ -867,36 +865,31 @@ get_more_pages:
 			/*
 			 * We have something to write.  If this is
 			 * the first locked page this time through,
-			 * allocate an osd request and a page array
-			 * that it will use.
+			 * calculate max possinle write size and
+			 * allocate a page array
 			 */
 			if (locked_pages == 0) {
-				BUG_ON(pages);
+				u64 objnum;
+				u64 objoff;
+
 				/* prepare async write request */
 				offset = (u64)page_offset(page);
 				len = wsize;
-				req = ceph_osdc_new_request(&fsc->client->osdc,
-							&ci->i_layout, vino,
-							offset, &len, 0,
-							do_sync ? 2 : 1,
-							CEPH_OSD_OP_WRITE,
-							CEPH_OSD_FLAG_WRITE |
-							CEPH_OSD_FLAG_ONDISK,
-							snapc, truncate_seq,
-							truncate_size, true);
-				if (IS_ERR(req)) {
-					rc = PTR_ERR(req);
+
+				rc = ceph_calc_file_object_mapping(&ci->i_layout,
+								offset, len,
+								&objnum, &objoff,
+								&len);
+				if (rc < 0) {
 					unlock_page(page);
 					break;
 				}
 
-				if (do_sync)
-					osd_req_op_init(req, 1,
-							CEPH_OSD_OP_STARTSYNC, 0);
-
-				req->r_callback = writepages_finish;
-				req->r_inode = inode;
+				num_ops = 1 + do_sync;
+				strip_unit_end = page->index +
+					((len - 1) >> PAGE_CACHE_SHIFT);
 
+				BUG_ON(pages);
 				max_pages = calc_pages_for(0, (u64)len);
 				pages = kmalloc(max_pages * sizeof (*pages),
 						GFP_NOFS);
@@ -905,6 +898,20 @@ get_more_pages:
 					pages = mempool_alloc(pool, GFP_NOFS);
 					BUG_ON(!pages);
 				}
+
+				len = 0;
+			} else if (page->index !=
+				   (offset + len) >> PAGE_CACHE_SHIFT) {
+				if (num_ops >= (pool ?  CEPH_OSD_SLAB_OPS :
+							CEPH_OSD_MAX_OPS)) {
+					redirty_page_for_writepage(wbc, page);
+					unlock_page(page);
+					break;
+				}
+
+				num_ops++;
+				offset = (u64)page_offset(page);
+				len = 0;
 			}
 
 			/* note position of first page in pvec */
@@ -913,18 +920,16 @@ get_more_pages:
 			dout("%p will write page %p idx %lu\n",
 			     inode, page, page->index);
 
-			writeback_stat =
-			       atomic_long_inc_return(&fsc->writeback_count);
-			if (writeback_stat > CONGESTION_ON_THRESH(
+			if (atomic_long_inc_return(&fsc->writeback_count) >
+			    CONGESTION_ON_THRESH(
 				    fsc->mount_options->congestion_kb)) {
 				set_bdi_congested(&fsc->backing_dev_info,
 						  BLK_RW_ASYNC);
 			}
 
-			set_page_writeback(page);
 			pages[locked_pages] = page;
 			locked_pages++;
-			next = page->index + 1;
+			len += PAGE_CACHE_SIZE;
 		}
 
 		/* did we get anything? */
@@ -944,38 +949,119 @@ get_more_pages:
 			/* shift unused pages over in the pvec...  we
 			 * will need to release them below. */
 			for (j = i; j < pvec_pages; j++) {
-				dout(" pvec leftover page %p\n",
-				     pvec.pages[j]);
+				dout(" pvec leftover page %p\n", pvec.pages[j]);
 				pvec.pages[j-i+first] = pvec.pages[j];
 			}
 			pvec.nr -= i-first;
 		}
 
-		/* Format the osd request message and submit the write */
+new_request:
 		offset = page_offset(pages[0]);
-		len = (u64)locked_pages << PAGE_CACHE_SHIFT;
-		if (snap_size == -1) {
-			len = min(len, (u64)i_size_read(inode) - offset);
-			 /* writepages_finish() clears writeback pages
-			  * according to the data length, so make sure
-			  * data length covers all locked pages */
-			len = max(len, 1 +
-				((u64)(locked_pages - 1) << PAGE_CACHE_SHIFT));
-		} else {
-			len = min(len, snap_size - offset);
+		len = wsize;
+
+		req = ceph_osdc_new_request(&fsc->client->osdc,
+					&ci->i_layout, vino,
+					offset, &len, 0, num_ops,
+					CEPH_OSD_OP_WRITE,
+					CEPH_OSD_FLAG_WRITE |
+					CEPH_OSD_FLAG_ONDISK,
+					snapc, truncate_seq,
+					truncate_size, false);
+		if (IS_ERR(req)) {
+			req = ceph_osdc_new_request(&fsc->client->osdc,
+						&ci->i_layout, vino,
+						offset, &len, 0,
+						min(num_ops,
+						    CEPH_OSD_SLAB_OPS),
+						CEPH_OSD_OP_WRITE,
+						CEPH_OSD_FLAG_WRITE |
+						CEPH_OSD_FLAG_ONDISK,
+						snapc, truncate_seq,
+						truncate_size, true);
+			BUG_ON(IS_ERR(req));
 		}
-		dout("writepages got %d pages at %llu~%llu\n",
-		     locked_pages, offset, len);
+		BUG_ON(len < page_offset(pages[locked_pages - 1]) +
+			     PAGE_CACHE_SIZE - offset);
+
+		req->r_callback = writepages_finish;
+		req->r_inode = inode;
 
-		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
+		/* Format the osd request message and submit the write */
+		len = 0;
+		data_pages = pages;
+		op_idx = 0;
+		for (i = 0; i < locked_pages; i++) {
+			u64 cur_offset = page_offset(pages[i]);
+			if (offset + len != cur_offset) {
+				if (op_idx + do_sync + 1 == req->r_num_ops)
+					break;
+				osd_req_op_extent_dup_last(req, op_idx,
+							   cur_offset - offset);
+				dout("writepages got pages at %llu~%llu\n",
+				     offset, len);
+				osd_req_op_extent_osd_data_pages(req, op_idx,
+							data_pages, len, 0,
 							!!pool, false);
+				osd_req_op_extent_update(req, op_idx, len);
 
-		pages = NULL;	/* request message now owns the pages array */
-		pool = NULL;
+				len = 0;
+				offset = cur_offset; 
+				data_pages = pages + i;
+				op_idx++;
+			}
 
-		/* Update the write op length in case we changed it */
+			set_page_writeback(pages[i]);
+			len += PAGE_CACHE_SIZE;
+		}
+
+		if (snap_size != -1) {
+			len = min(len, snap_size - offset);
+		} else if (i == locked_pages) {
+			/* writepages_finish() clears writeback pages
+			 * according to the data length, so make sure
+			 * data length covers all locked pages */
+			u64 min_len = len + 1 - PAGE_CACHE_SIZE;
+			len = min(len, (u64)i_size_read(inode) - offset);
+			len = max(len, min_len);
+		}
+		dout("writepages got pages at %llu~%llu\n", offset, len);
+
+		osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len,
+						 0, !!pool, false);
+		osd_req_op_extent_update(req, op_idx, len);
+
+		if (do_sync) {
+			op_idx++;
+			osd_req_op_init(req, op_idx, CEPH_OSD_OP_STARTSYNC, 0);
+		}
+		BUG_ON(op_idx + 1 != req->r_num_ops);
 
-		osd_req_op_extent_update(req, 0, len);
+		pool = NULL;
+		if (i < locked_pages) {
+			BUG_ON(num_ops <= req->r_num_ops);
+			num_ops -= req->r_num_ops;
+			num_ops += do_sync;
+			locked_pages -= i;
+
+			/* allocate new pages array for next request */
+			data_pages = pages;
+			pages = kmalloc(locked_pages * sizeof (*pages),
+					GFP_NOFS);
+			if (!pages) {
+				pool = fsc->wb_pagevec_pool;
+				pages = mempool_alloc(pool, GFP_NOFS);
+				BUG_ON(!pages);
+			}
+			memcpy(pages, data_pages + i,
+			       locked_pages * sizeof(*pages));
+			memset(data_pages + i, 0,
+			       locked_pages * sizeof(*pages));
+		} else {
+			BUG_ON(num_ops != req->r_num_ops);
+			index = pages[i - 1]->index + 1;
+			/* request message now owns the pages array */
+			pages = NULL;
+		}
 
 		vino = ceph_vino(inode);
 		ceph_osdc_build_request(req, offset, snapc, vino.snap,
@@ -985,9 +1071,10 @@ get_more_pages:
 		BUG_ON(rc);
 		req = NULL;
 
-		/* continue? */
-		index = next;
-		wbc->nr_to_write -= locked_pages;
+		wbc->nr_to_write -= i;
+		if (pages)
+			goto new_request;
+
 		if (wbc->nr_to_write <= 0)
 			done = 1;
 
@@ -1522,7 +1609,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 				    ceph_vino(inode), 0, &len, 0, 1,
 				    CEPH_OSD_OP_CREATE,
 				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
-				    ceph_empty_snapc, 0, 0, false);
+				    NULL, 0, 0, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out;
@@ -1540,9 +1627,8 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 				    ceph_vino(inode), 0, &len, 1, 3,
 				    CEPH_OSD_OP_WRITE,
 				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
-				    ceph_empty_snapc,
-				    ci->i_truncate_seq, ci->i_truncate_size,
-				    false);
+				    NULL, ci->i_truncate_seq,
+				    ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out;
@@ -1663,8 +1749,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
 		goto out;
 	}
 
-	rd_req = ceph_osdc_alloc_request(&fsc->client->osdc,
-					 ceph_empty_snapc,
+	rd_req = ceph_osdc_alloc_request(&fsc->client->osdc, NULL,
 					 1, false, GFP_NOFS);
 	if (!rd_req) {
 		err = -ENOMEM;
@@ -1678,8 +1763,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
 		 "%llx.00000000", ci->i_vino.ino);
 	rd_req->r_base_oid.name_len = strlen(rd_req->r_base_oid.name);
 
-	wr_req = ceph_osdc_alloc_request(&fsc->client->osdc,
-					 ceph_empty_snapc,
+	wr_req = ceph_osdc_alloc_request(&fsc->client->osdc, NULL,
 					 1, false, GFP_NOFS);
 	if (!wr_req) {
 		err = -ENOMEM;
@@ -1756,6 +1840,10 @@ int ceph_pool_perm_check(struct ceph_inode_info *ci, int need)
 	u32 pool;
 	int ret, flags;
 
+	/* does not support pool namespace yet */
+	if (ci->i_pool_ns_len)
+		return -EIO;
+
 	if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode),
 				NOPOOLPERM))
 		return 0;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index cdbf8cf3d52c..de17bb232ff8 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -991,7 +991,7 @@ static int send_cap_msg(struct ceph_mds_session *session,
 			u32 seq, u64 flush_tid, u64 oldest_flush_tid,
 			u32 issue_seq, u32 mseq, u64 size, u64 max_size,
 			struct timespec *mtime, struct timespec *atime,
-			u64 time_warp_seq,
+			struct timespec *ctime, u64 time_warp_seq,
 			kuid_t uid, kgid_t gid, umode_t mode,
 			u64 xattr_version,
 			struct ceph_buffer *xattrs_buf,
@@ -1042,6 +1042,8 @@ static int send_cap_msg(struct ceph_mds_session *session,
 		ceph_encode_timespec(&fc->mtime, mtime);
 	if (atime)
 		ceph_encode_timespec(&fc->atime, atime);
+	if (ctime)
+		ceph_encode_timespec(&fc->ctime, ctime);
 	fc->time_warp_seq = cpu_to_le32(time_warp_seq);
 
 	fc->uid = cpu_to_le32(from_kuid(&init_user_ns, uid));
@@ -1116,7 +1118,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	int held, revoking, dropping, keep;
 	u64 seq, issue_seq, mseq, time_warp_seq, follows;
 	u64 size, max_size;
-	struct timespec mtime, atime;
+	struct timespec mtime, atime, ctime;
 	int wake = 0;
 	umode_t mode;
 	kuid_t uid;
@@ -1180,6 +1182,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	ci->i_requested_max_size = max_size;
 	mtime = inode->i_mtime;
 	atime = inode->i_atime;
+	ctime = inode->i_ctime;
 	time_warp_seq = ci->i_time_warp_seq;
 	uid = inode->i_uid;
 	gid = inode->i_gid;
@@ -1198,7 +1201,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	ret = send_cap_msg(session, ceph_vino(inode).ino, cap_id,
 		op, keep, want, flushing, seq,
 		flush_tid, oldest_flush_tid, issue_seq, mseq,
-		size, max_size, &mtime, &atime, time_warp_seq,
+		size, max_size, &mtime, &atime, &ctime, time_warp_seq,
 		uid, gid, mode, xattr_version, xattr_blob,
 		follows, inline_data);
 	if (ret < 0) {
@@ -1320,7 +1323,7 @@ retry:
 			     capsnap->dirty, 0, capsnap->flush_tid, 0,
 			     0, mseq, capsnap->size, 0,
 			     &capsnap->mtime, &capsnap->atime,
-			     capsnap->time_warp_seq,
+			     &capsnap->ctime, capsnap->time_warp_seq,
 			     capsnap->uid, capsnap->gid, capsnap->mode,
 			     capsnap->xattr_version, capsnap->xattr_blob,
 			     capsnap->follows, capsnap->inline_data);
@@ -2753,7 +2756,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			     void *inline_data, int inline_len,
 			     struct ceph_buffer *xattr_buf,
 			     struct ceph_mds_session *session,
-			     struct ceph_cap *cap, int issued)
+			     struct ceph_cap *cap, int issued,
+			     u32 pool_ns_len)
 	__releases(ci->i_ceph_lock)
 	__releases(mdsc->snap_rwsem)
 {
@@ -2873,6 +2877,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
 		/* file layout may have changed */
 		ci->i_layout = grant->layout;
+		ci->i_pool_ns_len = pool_ns_len;
+
 		/* size/truncate_seq? */
 		queue_trunc = ceph_fill_file_size(inode, issued,
 					le32_to_cpu(grant->truncate_seq),
@@ -3411,6 +3417,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	u32  inline_len = 0;
 	void *snaptrace;
 	size_t snaptrace_len;
+	u32 pool_ns_len = 0;
 	void *p, *end;
 
 	dout("handle_caps from mds%d\n", mds);
@@ -3463,6 +3470,21 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		p += inline_len;
 	}
 
+	if (le16_to_cpu(msg->hdr.version) >= 8) {
+		u64 flush_tid;
+		u32 caller_uid, caller_gid;
+		u32 osd_epoch_barrier;
+		/* version >= 5 */
+		ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad);
+		/* version >= 6 */
+		ceph_decode_64_safe(&p, end, flush_tid, bad);
+		/* version >= 7 */
+		ceph_decode_32_safe(&p, end, caller_uid, bad);
+		ceph_decode_32_safe(&p, end, caller_gid, bad);
+		/* version >= 8 */
+		ceph_decode_32_safe(&p, end, pool_ns_len, bad);
+	}
+
 	/* lookup ino */
 	inode = ceph_find_inode(sb, vino);
 	ci = ceph_inode(inode);
@@ -3518,7 +3540,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 				  &cap, &issued);
 		handle_cap_grant(mdsc, inode, h,
 				 inline_version, inline_data, inline_len,
-				 msg->middle, session, cap, issued);
+				 msg->middle, session, cap, issued,
+				 pool_ns_len);
 		if (realm)
 			ceph_put_snap_realm(mdsc, realm);
 		goto done_unlocked;
@@ -3542,7 +3565,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		issued |= __ceph_caps_dirty(ci);
 		handle_cap_grant(mdsc, inode, h,
 				 inline_version, inline_data, inline_len,
-				 msg->middle, session, cap, issued);
+				 msg->middle, session, cap, issued,
+				 pool_ns_len);
 		goto done_unlocked;
 
 	case CEPH_CAP_OP_FLUSH_ACK:
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index fd11fb231a2e..fadc243dfb28 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -38,7 +38,7 @@ int ceph_init_dentry(struct dentry *dentry)
 	if (dentry->d_fsdata)
 		return 0;
 
-	di = kmem_cache_alloc(ceph_dentry_cachep, GFP_KERNEL | __GFP_ZERO);
+	di = kmem_cache_zalloc(ceph_dentry_cachep, GFP_KERNEL);
 	if (!di)
 		return -ENOMEM;          /* oh well */
 
@@ -68,23 +68,6 @@ out_unlock:
 	return 0;
 }
 
-struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry)
-{
-	struct inode *inode = NULL;
-
-	if (!dentry)
-		return NULL;
-
-	spin_lock(&dentry->d_lock);
-	if (!IS_ROOT(dentry)) {
-		inode = d_inode(dentry->d_parent);
-		ihold(inode);
-	}
-	spin_unlock(&dentry->d_lock);
-	return inode;
-}
-
-
 /*
  * for readdir, we encode the directory frag and offset within that
  * frag into f_pos.
@@ -624,6 +607,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int op;
+	int mask;
 	int err;
 
 	dout("lookup %p dentry %p '%pd'\n",
@@ -666,8 +650,12 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 		return ERR_CAST(req);
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
-	/* we only need inode linkage */
-	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE);
+
+	mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
+	if (ceph_security_xattr_wanted(dir))
+		mask |= CEPH_CAP_XATTR_SHARED;
+	req->r_args.getattr.mask = cpu_to_le32(mask);
+
 	req->r_locked_dir = dir;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	err = ceph_handle_snapdir(req, dentry, err);
@@ -1095,6 +1083,7 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry)
 static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	int valid = 0;
+	struct dentry *parent;
 	struct inode *dir;
 
 	if (flags & LOOKUP_RCU)
@@ -1103,7 +1092,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 	dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
 	     dentry, d_inode(dentry), ceph_dentry(dentry)->offset);
 
-	dir = ceph_get_dentry_parent_inode(dentry);
+	parent = dget_parent(dentry);
+	dir = d_inode(parent);
 
 	/* always trust cached snapped dentries, snapdir dentry */
 	if (ceph_snap(dir) != CEPH_NOSNAP) {
@@ -1121,13 +1111,48 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 			valid = 1;
 	}
 
+	if (!valid) {
+		struct ceph_mds_client *mdsc =
+			ceph_sb_to_client(dir->i_sb)->mdsc;
+		struct ceph_mds_request *req;
+		int op, mask, err;
+
+		op = ceph_snap(dir) == CEPH_SNAPDIR ?
+			CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP;
+		req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS);
+		if (!IS_ERR(req)) {
+			req->r_dentry = dget(dentry);
+			req->r_num_caps = 2;
+
+			mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
+			if (ceph_security_xattr_wanted(dir))
+				mask |= CEPH_CAP_XATTR_SHARED;
+			req->r_args.getattr.mask = mask;
+
+			req->r_locked_dir = dir;
+			err = ceph_mdsc_do_request(mdsc, NULL, req);
+			if (err == 0 || err == -ENOENT) {
+				if (dentry == req->r_dentry) {
+					valid = !d_unhashed(dentry);
+				} else {
+					d_invalidate(req->r_dentry);
+					err = -EAGAIN;
+				}
+			}
+			ceph_mdsc_put_request(req);
+			dout("d_revalidate %p lookup result=%d\n",
+			     dentry, err);
+		}
+	}
+
 	dout("d_revalidate %p %s\n", dentry, valid ? "valid" : "invalid");
 	if (valid) {
 		ceph_dentry_lru_touch(dentry);
 	} else {
 		ceph_dir_clear_complete(dir);
 	}
-	iput(dir);
+
+	dput(parent);
 	return valid;
 }
 
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 3b3172357326..6e72c98162d5 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -71,12 +71,18 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
 	inode = ceph_find_inode(sb, vino);
 	if (!inode) {
 		struct ceph_mds_request *req;
+		int mask;
 
 		req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
 					       USE_ANY_MDS);
 		if (IS_ERR(req))
 			return ERR_CAST(req);
 
+		mask = CEPH_STAT_CAP_INODE;
+		if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
+			mask |= CEPH_CAP_XATTR_SHARED;
+		req->r_args.getattr.mask = cpu_to_le32(mask);
+
 		req->r_ino1 = vino;
 		req->r_num_caps = 1;
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
@@ -128,6 +134,7 @@ static struct dentry *__get_parent(struct super_block *sb,
 	struct ceph_mds_request *req;
 	struct inode *inode;
 	struct dentry *dentry;
+	int mask;
 	int err;
 
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPPARENT,
@@ -144,6 +151,12 @@ static struct dentry *__get_parent(struct super_block *sb,
 			.snap = CEPH_NOSNAP,
 		};
 	}
+
+	mask = CEPH_STAT_CAP_INODE;
+	if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
+		mask |= CEPH_CAP_XATTR_SHARED;
+	req->r_args.getattr.mask = cpu_to_le32(mask);
+
 	req->r_num_caps = 1;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	inode = req->r_target_inode;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 86a9c383955e..ef38f01c1795 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -157,7 +157,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 	case S_IFDIR:
 		dout("init_file %p %p 0%o (regular)\n", inode, file,
 		     inode->i_mode);
-		cf = kmem_cache_alloc(ceph_file_cachep, GFP_KERNEL | __GFP_ZERO);
+		cf = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL);
 		if (cf == NULL) {
 			ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
 			return -ENOMEM;
@@ -300,6 +300,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct ceph_mds_request *req;
 	struct dentry *dn;
 	struct ceph_acls_info acls = {};
+       int mask;
 	int err;
 
 	dout("atomic_open %p dentry %p '%pd' %s flags %d mode 0%o\n",
@@ -335,6 +336,12 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 			acls.pagelist = NULL;
 		}
 	}
+
+       mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
+       if (ceph_security_xattr_wanted(dir))
+               mask |= CEPH_CAP_XATTR_SHARED;
+       req->r_args.open.mask = cpu_to_le32(mask);
+
 	req->r_locked_dir = dir;           /* caller holds dir->i_mutex */
 	err = ceph_mdsc_do_request(mdsc,
 				   (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
@@ -698,8 +705,8 @@ static void ceph_aio_retry_work(struct work_struct *work)
 
 	req = ceph_osdc_alloc_request(orig_req->r_osdc, snapc, 2,
 			false, GFP_NOFS);
-	if (IS_ERR(req)) {
-		ret = PTR_ERR(req);
+	if (!req) {
+		ret = -ENOMEM;
 		req = orig_req;
 		goto out;
 	}
@@ -716,7 +723,6 @@ static void ceph_aio_retry_work(struct work_struct *work)
 	ceph_osdc_build_request(req, req->r_ops[0].extent.offset,
 				snapc, CEPH_NOSNAP, &aio_req->mtime);
 
-	ceph_put_snap_context(snapc);
 	ceph_osdc_put_request(orig_req);
 
 	req->r_callback = ceph_aio_complete_req;
@@ -726,11 +732,11 @@ static void ceph_aio_retry_work(struct work_struct *work)
 	ret = ceph_osdc_start_request(req->r_osdc, req, false);
 out:
 	if (ret < 0) {
-		BUG_ON(ret == -EOLDSNAPC);
 		req->r_result = ret;
 		ceph_aio_complete_req(req, NULL);
 	}
 
+	ceph_put_snap_context(snapc);
 	kfree(aio_work);
 }
 
@@ -783,7 +789,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	int num_pages = 0;
 	int flags;
 	int ret;
-	struct timespec mtime = CURRENT_TIME;
+	struct timespec mtime = current_fs_time(inode->i_sb);
 	size_t count = iov_iter_count(iter);
 	loff_t pos = iocb->ki_pos;
 	bool write = iov_iter_rw(iter) == WRITE;
@@ -949,7 +955,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 				ret = ceph_osdc_start_request(req->r_osdc,
 							      req, false);
 			if (ret < 0) {
-				BUG_ON(ret == -EOLDSNAPC);
 				req->r_result = ret;
 				ceph_aio_complete_req(req, NULL);
 			}
@@ -988,7 +993,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	int flags;
 	int check_caps = 0;
 	int ret;
-	struct timespec mtime = CURRENT_TIME;
+	struct timespec mtime = current_fs_time(inode->i_sb);
 	size_t count = iov_iter_count(from);
 
 	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index fb4ba2e4e2a5..ed58b168904a 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -396,6 +396,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	ci->i_symlink = NULL;
 
 	memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
+	ci->i_pool_ns_len = 0;
 
 	ci->i_fragtree = RB_ROOT;
 	mutex_init(&ci->i_fragtree_mutex);
@@ -548,6 +549,10 @@ int ceph_fill_file_size(struct inode *inode, int issued,
 	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) > 0 ||
 	    (truncate_seq == ci->i_truncate_seq && size > inode->i_size)) {
 		dout("size %lld -> %llu\n", inode->i_size, size);
+		if (size > 0 && S_ISDIR(inode->i_mode)) {
+			pr_err("fill_file_size non-zero size for directory\n");
+			size = 0;
+		}
 		i_size_write(inode, size);
 		inode->i_blocks = (size + (1<<9) - 1) >> 9;
 		ci->i_reported_size = size;
@@ -756,6 +761,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 		if (ci->i_layout.fl_pg_pool != info->layout.fl_pg_pool)
 			ci->i_ceph_flags &= ~CEPH_I_POOL_PERM;
 		ci->i_layout = info->layout;
+		ci->i_pool_ns_len = iinfo->pool_ns_len;
 
 		queue_trunc = ceph_fill_file_size(inode, issued,
 					le32_to_cpu(info->truncate_seq),
@@ -975,13 +981,8 @@ out_unlock:
 /*
  * splice a dentry to an inode.
  * caller must hold directory i_mutex for this to be safe.
- *
- * we will only rehash the resulting dentry if @prehash is
- * true; @prehash will be set to false (for the benefit of
- * the caller) if we fail.
  */
-static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
-				    bool *prehash)
+static struct dentry *splice_dentry(struct dentry *dn, struct inode *in)
 {
 	struct dentry *realdn;
 
@@ -994,8 +995,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 	if (IS_ERR(realdn)) {
 		pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
 		       PTR_ERR(realdn), dn, in, ceph_vinop(in));
-		if (prehash)
-			*prehash = false; /* don't rehash on error */
 		dn = realdn; /* note realdn contains the error */
 		goto out;
 	} else if (realdn) {
@@ -1011,8 +1010,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 		dout("dn %p attached to %p ino %llx.%llx\n",
 		     dn, d_inode(dn), ceph_vinop(d_inode(dn)));
 	}
-	if ((!prehash || *prehash) && d_unhashed(dn))
-		d_rehash(dn);
 out:
 	return dn;
 }
@@ -1245,10 +1242,8 @@ retry_lookup:
 				dout("d_delete %p\n", dn);
 				d_delete(dn);
 			} else {
-				dout("d_instantiate %p NULL\n", dn);
-				d_instantiate(dn, NULL);
 				if (have_lease && d_unhashed(dn))
-					d_rehash(dn);
+					d_add(dn, NULL);
 				update_dentry_lease(dn, rinfo->dlease,
 						    session,
 						    req->r_request_started);
@@ -1260,7 +1255,7 @@ retry_lookup:
 		if (d_really_is_negative(dn)) {
 			ceph_dir_clear_ordered(dir);
 			ihold(in);
-			dn = splice_dentry(dn, in, &have_lease);
+			dn = splice_dentry(dn, in);
 			if (IS_ERR(dn)) {
 				err = PTR_ERR(dn);
 				goto done;
@@ -1270,6 +1265,7 @@ retry_lookup:
 			dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
 			     dn, d_inode(dn), ceph_vinop(d_inode(dn)),
 			     ceph_vinop(in));
+			d_invalidate(dn);
 			have_lease = false;
 		}
 
@@ -1290,7 +1286,7 @@ retry_lookup:
 		dout(" linking snapped dir %p to dn %p\n", in, dn);
 		ceph_dir_clear_ordered(dir);
 		ihold(in);
-		dn = splice_dentry(dn, in, NULL);
+		dn = splice_dentry(dn, in);
 		if (IS_ERR(dn)) {
 			err = PTR_ERR(dn);
 			goto done;
@@ -1358,15 +1354,20 @@ static int fill_readdir_cache(struct inode *dir, struct dentry *dn,
 
 	if (!ctl->page || pgoff != page_index(ctl->page)) {
 		ceph_readdir_cache_release(ctl);
-		ctl->page  = grab_cache_page(&dir->i_data, pgoff);
+		if (idx == 0)
+			ctl->page = grab_cache_page(&dir->i_data, pgoff);
+		else
+			ctl->page = find_lock_page(&dir->i_data, pgoff);
 		if (!ctl->page) {
 			ctl->index = -1;
-			return -ENOMEM;
+			return idx == 0 ? -ENOMEM : 0;
 		}
 		/* reading/filling the cache are serialized by
 		 * i_mutex, no need to use page lock */
 		unlock_page(ctl->page);
 		ctl->dentries = kmap(ctl->page);
+		if (idx == 0)
+			memset(ctl->dentries, 0, PAGE_CACHE_SIZE);
 	}
 
 	if (req->r_dir_release_cnt == atomic64_read(&ci->i_release_count) &&
@@ -1389,7 +1390,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	struct qstr dname;
 	struct dentry *dn;
 	struct inode *in;
-	int err = 0, ret, i;
+	int err = 0, skipped = 0, ret, i;
 	struct inode *snapdir = NULL;
 	struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
 	struct ceph_dentry_info *di;
@@ -1501,7 +1502,17 @@ retry_lookup:
 		}
 
 		if (d_really_is_negative(dn)) {
-			struct dentry *realdn = splice_dentry(dn, in, NULL);
+			struct dentry *realdn;
+
+			if (ceph_security_xattr_deadlock(in)) {
+				dout(" skip splicing dn %p to inode %p"
+				     " (security xattr deadlock)\n", dn, in);
+				iput(in);
+				skipped++;
+				goto next_item;
+			}
+
+			realdn = splice_dentry(dn, in);
 			if (IS_ERR(realdn)) {
 				err = PTR_ERR(realdn);
 				d_drop(dn);
@@ -1518,7 +1529,7 @@ retry_lookup:
 				    req->r_session,
 				    req->r_request_started);
 
-		if (err == 0 && cache_ctl.index >= 0) {
+		if (err == 0 && skipped == 0 && cache_ctl.index >= 0) {
 			ret = fill_readdir_cache(d_inode(parent), dn,
 						 &cache_ctl, req);
 			if (ret < 0)
@@ -1529,7 +1540,7 @@ next_item:
 			dput(dn);
 	}
 out:
-	if (err == 0) {
+	if (err == 0 && skipped == 0) {
 		req->r_did_prepopulate = true;
 		req->r_readdir_cache_idx = cache_ctl.index;
 	}
@@ -1959,7 +1970,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	if (dirtied) {
 		inode_dirty_flags = __ceph_mark_dirty_caps(ci, dirtied,
 							   &prealloc_cf);
-		inode->i_ctime = CURRENT_TIME;
+		inode->i_ctime = current_fs_time(inode->i_sb);
 	}
 
 	release &= issued;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index e7b130a637f9..44852c3ae531 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -100,6 +100,14 @@ static int parse_reply_info_in(void **p, void *end,
 	} else
 		info->inline_version = CEPH_INLINE_NONE;
 
+	if (features & CEPH_FEATURE_FS_FILE_LAYOUT_V2) {
+		ceph_decode_32_safe(p, end, info->pool_ns_len, bad);
+		ceph_decode_need(p, end, info->pool_ns_len, bad);
+		*p += info->pool_ns_len;
+	} else {
+		info->pool_ns_len = 0;
+	}
+
 	return 0;
 bad:
 	return err;
@@ -1721,7 +1729,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
 	init_completion(&req->r_safe_completion);
 	INIT_LIST_HEAD(&req->r_unsafe_item);
 
-	req->r_stamp = CURRENT_TIME;
+	req->r_stamp = current_fs_time(mdsc->fsc->sb);
 
 	req->r_op = op;
 	req->r_direct_mode = mode;
@@ -2298,6 +2306,14 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 		ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir),
 				  CEPH_CAP_PIN);
 
+	/* deny access to directories with pool_ns layouts */
+	if (req->r_inode && S_ISDIR(req->r_inode->i_mode) &&
+	    ceph_inode(req->r_inode)->i_pool_ns_len)
+		return -EIO;
+	if (req->r_locked_dir &&
+	    ceph_inode(req->r_locked_dir)->i_pool_ns_len)
+		return -EIO;
+
 	/* issue */
 	mutex_lock(&mdsc->mutex);
 	__register_request(mdsc, req, dir);
@@ -2524,6 +2540,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
 	/* insert trace into our cache */
 	mutex_lock(&req->r_fill_mutex);
+	current->journal_info = req;
 	err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
 	if (err == 0) {
 		if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
@@ -2531,6 +2548,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			ceph_readdir_prepopulate(req, req->r_session);
 		ceph_unreserve_caps(mdsc, &req->r_caps_reservation);
 	}
+	current->journal_info = NULL;
 	mutex_unlock(&req->r_fill_mutex);
 
 	up_read(&mdsc->snap_rwsem);
@@ -3748,7 +3766,6 @@ void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 	dout("handle_map epoch %u len %d\n", epoch, (int)maplen);
 
 	/* do we need it? */
-	ceph_monc_got_mdsmap(&mdsc->fsc->client->monc, epoch);
 	mutex_lock(&mdsc->mutex);
 	if (mdsc->mdsmap && epoch <= mdsc->mdsmap->m_epoch) {
 		dout("handle_map epoch %u <= our %u\n",
@@ -3775,6 +3792,8 @@ void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 	mdsc->fsc->sb->s_maxbytes = mdsc->mdsmap->m_max_file_size;
 
 	__wake_requests(mdsc, &mdsc->waiting_for_map);
+	ceph_monc_got_map(&mdsc->fsc->client->monc, CEPH_SUB_MDSMAP,
+			  mdsc->mdsmap->m_epoch);
 
 	mutex_unlock(&mdsc->mutex);
 	schedule_delayed(mdsc);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index ccf11ef0ca87..37712ccffcc6 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -44,6 +44,7 @@ struct ceph_mds_reply_info_in {
 	u64 inline_version;
 	u32 inline_len;
 	char *inline_data;
+	u32 pool_ns_len;
 };
 
 /*
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 4aa7122a8d38..9caaa7ffc93f 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -296,8 +296,6 @@ static int cmpu64_rev(const void *a, const void *b)
 }
 
 
-struct ceph_snap_context *ceph_empty_snapc;
-
 /*
  * build the snap context for a given realm.
  */
@@ -987,17 +985,3 @@ out:
 		up_write(&mdsc->snap_rwsem);
 	return;
 }
-
-int __init ceph_snap_init(void)
-{
-	ceph_empty_snapc = ceph_create_snap_context(0, GFP_NOFS);
-	if (!ceph_empty_snapc)
-		return -ENOMEM;
-	ceph_empty_snapc->seq = 1;
-	return 0;
-}
-
-void ceph_snap_exit(void)
-{
-	ceph_put_snap_context(ceph_empty_snapc);
-}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index ca4d5e8457f1..c973043deb0e 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -439,8 +439,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 
 	if (fsopt->flags & CEPH_MOUNT_OPT_DIRSTAT)
 		seq_puts(m, ",dirstat");
-	if ((fsopt->flags & CEPH_MOUNT_OPT_RBYTES) == 0)
-		seq_puts(m, ",norbytes");
+	if ((fsopt->flags & CEPH_MOUNT_OPT_RBYTES))
+		seq_puts(m, ",rbytes");
 	if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR)
 		seq_puts(m, ",noasyncreaddir");
 	if ((fsopt->flags & CEPH_MOUNT_OPT_DCACHE) == 0)
@@ -530,7 +530,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 		goto fail;
 	}
 	fsc->client->extra_mon_dispatch = extra_mon_dispatch;
-	fsc->client->monc.want_mdsmap = 1;
+	ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP, 0, true);
 
 	fsc->mount_options = fsopt;
 
@@ -793,22 +793,20 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 	struct dentry *root;
 	int first = 0;   /* first vfsmount for this super_block */
 
-	dout("mount start\n");
+	dout("mount start %p\n", fsc);
 	mutex_lock(&fsc->client->mount_mutex);
 
-	err = __ceph_open_session(fsc->client, started);
-	if (err < 0)
-		goto out;
+	if (!fsc->sb->s_root) {
+		err = __ceph_open_session(fsc->client, started);
+		if (err < 0)
+			goto out;
 
-	dout("mount opening root\n");
-	root = open_root_dentry(fsc, "", started);
-	if (IS_ERR(root)) {
-		err = PTR_ERR(root);
-		goto out;
-	}
-	if (fsc->sb->s_root) {
-		dput(root);
-	} else {
+		dout("mount opening root\n");
+		root = open_root_dentry(fsc, "", started);
+		if (IS_ERR(root)) {
+			err = PTR_ERR(root);
+			goto out;
+		}
 		fsc->sb->s_root = root;
 		first = 1;
 
@@ -818,6 +816,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 	}
 
 	if (path[0] == 0) {
+		root = fsc->sb->s_root;
 		dget(root);
 	} else {
 		dout("mount opening base mountpoint\n");
@@ -833,16 +832,14 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 	mutex_unlock(&fsc->client->mount_mutex);
 	return root;
 
-out:
-	mutex_unlock(&fsc->client->mount_mutex);
-	return ERR_PTR(err);
-
 fail:
 	if (first) {
 		dput(fsc->sb->s_root);
 		fsc->sb->s_root = NULL;
 	}
-	goto out;
+out:
+	mutex_unlock(&fsc->client->mount_mutex);
+	return ERR_PTR(err);
 }
 
 static int ceph_set_super(struct super_block *s, void *data)
@@ -1042,19 +1039,14 @@ static int __init init_ceph(void)
 
 	ceph_flock_init();
 	ceph_xattr_init();
-	ret = ceph_snap_init();
-	if (ret)
-		goto out_xattr;
 	ret = register_filesystem(&ceph_fs_type);
 	if (ret)
-		goto out_snap;
+		goto out_xattr;
 
 	pr_info("loaded (mds proto %d)\n", CEPH_MDSC_PROTOCOL);
 
 	return 0;
 
-out_snap:
-	ceph_snap_exit();
 out_xattr:
 	ceph_xattr_exit();
 	destroy_caches();
@@ -1066,7 +1058,6 @@ static void __exit exit_ceph(void)
 {
 	dout("exit_ceph\n");
 	unregister_filesystem(&ceph_fs_type);
-	ceph_snap_exit();
 	ceph_xattr_exit();
 	destroy_caches();
 }
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 75b7d125ce66..e705c4d612d7 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -37,8 +37,7 @@
 #define CEPH_MOUNT_OPT_FSCACHE         (1<<10) /* use fscache */
 #define CEPH_MOUNT_OPT_NOPOOLPERM      (1<<11) /* no pool permission check */
 
-#define CEPH_MOUNT_OPT_DEFAULT    (CEPH_MOUNT_OPT_RBYTES | \
-				   CEPH_MOUNT_OPT_DCACHE)
+#define CEPH_MOUNT_OPT_DEFAULT    CEPH_MOUNT_OPT_DCACHE
 
 #define ceph_set_mount_opt(fsc, opt) \
 	(fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt;
@@ -287,6 +286,7 @@ struct ceph_inode_info {
 
 	struct ceph_dir_layout i_dir_layout;
 	struct ceph_file_layout i_layout;
+	size_t i_pool_ns_len;
 	char *i_symlink;
 
 	/* for dirs */
@@ -468,7 +468,7 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
 #define CEPH_I_POOL_PERM	(1 << 4)  /* pool rd/wr bits are valid */
 #define CEPH_I_POOL_RD		(1 << 5)  /* can read from pool */
 #define CEPH_I_POOL_WR		(1 << 6)  /* can write to pool */
-
+#define CEPH_I_SEC_INITED	(1 << 7)  /* security initialized */
 
 static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
 					   long long release_count,
@@ -720,7 +720,6 @@ static inline int default_congestion_kb(void)
 
 
 /* snap.c */
-extern struct ceph_snap_context *ceph_empty_snapc;
 struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
 					       u64 ino);
 extern void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
@@ -737,8 +736,6 @@ extern void ceph_queue_cap_snap(struct ceph_inode_info *ci);
 extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 				  struct ceph_cap_snap *capsnap);
 extern void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc);
-extern int ceph_snap_init(void);
-extern void ceph_snap_exit(void);
 
 /*
  * a cap_snap is "pending" if it is still awaiting an in-progress
@@ -807,6 +804,20 @@ extern void __init ceph_xattr_init(void);
 extern void ceph_xattr_exit(void);
 extern const struct xattr_handler *ceph_xattr_handlers[];
 
+#ifdef CONFIG_SECURITY
+extern bool ceph_security_xattr_deadlock(struct inode *in);
+extern bool ceph_security_xattr_wanted(struct inode *in);
+#else
+static inline bool ceph_security_xattr_deadlock(struct inode *in)
+{
+	return false;
+}
+static inline bool ceph_security_xattr_wanted(struct inode *in)
+{
+	return false;
+}
+#endif
+
 /* acl.c */
 struct ceph_acls_info {
 	void *default_acl;
@@ -946,7 +957,6 @@ extern void ceph_dentry_lru_touch(struct dentry *dn);
 extern void ceph_dentry_lru_del(struct dentry *dn);
 extern void ceph_invalidate_dentry_lease(struct dentry *dentry);
 extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn);
-extern struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry);
 extern void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl);
 
 /*
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 819163d8313b..9410abdef3ce 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -714,31 +714,62 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
 	}
 }
 
+static inline int __get_request_mask(struct inode *in) {
+	struct ceph_mds_request *req = current->journal_info;
+	int mask = 0;
+	if (req && req->r_target_inode == in) {
+		if (req->r_op == CEPH_MDS_OP_LOOKUP ||
+		    req->r_op == CEPH_MDS_OP_LOOKUPINO ||
+		    req->r_op == CEPH_MDS_OP_LOOKUPPARENT ||
+		    req->r_op == CEPH_MDS_OP_GETATTR) {
+			mask = le32_to_cpu(req->r_args.getattr.mask);
+		} else if (req->r_op == CEPH_MDS_OP_OPEN ||
+			   req->r_op == CEPH_MDS_OP_CREATE) {
+			mask = le32_to_cpu(req->r_args.open.mask);
+		}
+	}
+	return mask;
+}
+
 ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
 		      size_t size)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	int err;
 	struct ceph_inode_xattr *xattr;
 	struct ceph_vxattr *vxattr = NULL;
+	int req_mask;
+	int err;
 
 	if (!ceph_is_valid_xattr(name))
 		return -ENODATA;
 
 	/* let's see if a virtual xattr was requested */
 	vxattr = ceph_match_vxattr(inode, name);
-	if (vxattr && !(vxattr->exists_cb && !vxattr->exists_cb(ci))) {
-		err = vxattr->getxattr_cb(ci, value, size);
+	if (vxattr) {
+		err = -ENODATA;
+		if (!(vxattr->exists_cb && !vxattr->exists_cb(ci)))
+			err = vxattr->getxattr_cb(ci, value, size);
 		return err;
 	}
 
+	req_mask = __get_request_mask(inode);
+
 	spin_lock(&ci->i_ceph_lock);
 	dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
 	     ci->i_xattrs.version, ci->i_xattrs.index_version);
 
 	if (ci->i_xattrs.version == 0 ||
-	    !__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1)) {
+	    !((req_mask & CEPH_CAP_XATTR_SHARED) ||
+	      __ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1))) {
 		spin_unlock(&ci->i_ceph_lock);
+
+		/* security module gets xattr while filling trace */
+		if (current->journal_info != NULL) {
+			pr_warn_ratelimited("sync getxattr %p "
+					    "during filling trace\n", inode);
+			return -EBUSY;
+		}
+
 		/* get xattrs from mds (if we don't already have them) */
 		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR, true);
 		if (err)
@@ -765,6 +796,9 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
 
 	memcpy(value, xattr->val, xattr->val_len);
 
+	if (current->journal_info != NULL &&
+	    !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN))
+		ci->i_ceph_flags |= CEPH_I_SEC_INITED;
 out:
 	spin_unlock(&ci->i_ceph_lock);
 	return err;
@@ -999,7 +1033,7 @@ retry:
 		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL,
 					       &prealloc_cf);
 		ci->i_xattrs.dirty = true;
-		inode->i_ctime = CURRENT_TIME;
+		inode->i_ctime = current_fs_time(inode->i_sb);
 	}
 
 	spin_unlock(&ci->i_ceph_lock);
@@ -1015,7 +1049,15 @@ do_sync:
 do_sync_unlocked:
 	if (lock_snap_rwsem)
 		up_read(&mdsc->snap_rwsem);
-	err = ceph_sync_setxattr(dentry, name, value, size, flags);
+
+	/* security module set xattr while filling trace */
+	if (current->journal_info != NULL) {
+		pr_warn_ratelimited("sync setxattr %p "
+				    "during filling trace\n", inode);
+		err = -EBUSY;
+	} else {
+		err = ceph_sync_setxattr(dentry, name, value, size, flags);
+	}
 out:
 	ceph_free_cap_flush(prealloc_cf);
 	kfree(newname);
@@ -1136,7 +1178,7 @@ retry:
 	dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL,
 				       &prealloc_cf);
 	ci->i_xattrs.dirty = true;
-	inode->i_ctime = CURRENT_TIME;
+	inode->i_ctime = current_fs_time(inode->i_sb);
 	spin_unlock(&ci->i_ceph_lock);
 	if (lock_snap_rwsem)
 		up_read(&mdsc->snap_rwsem);
@@ -1164,3 +1206,25 @@ int ceph_removexattr(struct dentry *dentry, const char *name)
 
 	return __ceph_removexattr(dentry, name);
 }
+
+#ifdef CONFIG_SECURITY
+bool ceph_security_xattr_wanted(struct inode *in)
+{
+	return in->i_security != NULL;
+}
+
+bool ceph_security_xattr_deadlock(struct inode *in)
+{
+	struct ceph_inode_info *ci;
+	bool ret;
+	if (in->i_security == NULL)
+		return false;
+	ci = ceph_inode(in);
+	spin_lock(&ci->i_ceph_lock);
+	ret = !(ci->i_ceph_flags & CEPH_I_SEC_INITED) &&
+	      !(ci->i_xattrs.version > 0 &&
+		__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0));
+	spin_unlock(&ci->i_ceph_lock);
+	return ret;
+}
+#endif
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 50b268483302..788e19195991 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -255,7 +255,6 @@ static const struct file_operations cifs_debug_data_proc_fops = {
 static ssize_t cifs_stats_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
 	bool bv;
 	int rc;
 	struct list_head *tmp1, *tmp2, *tmp3;
@@ -263,11 +262,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
 
-	rc = get_user(c, buffer);
-	if (rc)
-		return rc;
-
-	if (strtobool(&c, &bv) == 0) {
+	rc = kstrtobool_from_user(buffer, count, &bv);
+	if (rc == 0) {
 #ifdef CONFIG_CIFS_STATS2
 		atomic_set(&totBufAllocCount, 0);
 		atomic_set(&totSmBufAllocCount, 0);
@@ -290,6 +286,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 			}
 		}
 		spin_unlock(&cifs_tcp_ses_lock);
+	} else {
+		return rc;
 	}
 
 	return count;
@@ -433,17 +431,17 @@ static int cifsFYI_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer,
 		size_t count, loff_t *ppos)
 {
-	char c;
+	char c[2] = { '\0' };
 	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = get_user(c[0], buffer);
 	if (rc)
 		return rc;
-	if (strtobool(&c, &bv) == 0)
+	if (strtobool(c, &bv) == 0)
 		cifsFYI = bv;
-	else if ((c > '1') && (c <= '9'))
-		cifsFYI = (int) (c - '0'); /* see cifs_debug.h for meanings */
+	else if ((c[0] > '1') && (c[0] <= '9'))
+		cifsFYI = (int) (c[0] - '0'); /* see cifs_debug.h for meanings */
 
 	return count;
 }
@@ -471,20 +469,12 @@ static int cifs_linux_ext_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifs_linux_ext_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &linuxExtEnabled);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	linuxExtEnabled = bv;
-
 	return count;
 }
 
@@ -511,20 +501,12 @@ static int cifs_lookup_cache_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifs_lookup_cache_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &lookupCacheEnabled);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	lookupCacheEnabled = bv;
-
 	return count;
 }
 
@@ -551,20 +533,12 @@ static int traceSMB_proc_open(struct inode *inode, struct file *file)
 static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer,
 		size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &traceSMB);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	traceSMB = bv;
-
 	return count;
 }
 
@@ -622,7 +596,6 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
 	int rc;
 	unsigned int flags;
 	char flags_string[12];
-	char c;
 	bool bv;
 
 	if ((count < 1) || (count > 11))
@@ -635,11 +608,10 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
 
 	if (count < 3) {
 		/* single char or single char followed by null */
-		c = flags_string[0];
-		if (strtobool(&c, &bv) == 0) {
+		if (strtobool(flags_string, &bv) == 0) {
 			global_secflags = bv ? CIFSSEC_MAX : CIFSSEC_DEF;
 			return count;
-		} else if (!isdigit(c)) {
+		} else if (!isdigit(flags_string[0])) {
 			cifs_dbg(VFS, "Invalid SecurityFlags: %s\n",
 					flags_string);
 			return -EINVAL;
diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h
index 66cf0f9fff89..c611ca2339d7 100644
--- a/fs/cifs/cifs_debug.h
+++ b/fs/cifs/cifs_debug.h
@@ -25,7 +25,7 @@
 void cifs_dump_mem(char *label, void *data, int length);
 void cifs_dump_detail(void *);
 void cifs_dump_mids(struct TCP_Server_Info *);
-extern int traceSMB;		/* flag which enables the function below */
+extern bool traceSMB;		/* flag which enables the function below */
 void dump_smb(void *, int);
 #define CIFS_INFO	0x01
 #define CIFS_RC		0x02
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 7dc886c9a78f..e956cba94338 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -175,7 +175,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 	 * string to the length of the original string to allow for worst case.
 	 */
 	md_len = strlen(sb_mountdata) + INET6_ADDRSTRLEN;
-	mountdata = kzalloc(md_len + 1, GFP_KERNEL);
+	mountdata = kzalloc(md_len + sizeof("ip=") + 1, GFP_KERNEL);
 	if (mountdata == NULL) {
 		rc = -ENOMEM;
 		goto compose_mount_options_err;
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index afa09fce8151..4897dacf8944 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -33,6 +33,7 @@
 #include <linux/ctype.h>
 #include <linux/random.h>
 #include <linux/highmem.h>
+#include <crypto/skcipher.h>
 
 static int
 cifs_crypto_shash_md5_allocate(struct TCP_Server_Info *server)
@@ -714,7 +715,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 
 	ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL);
 	if (!ses->auth_key.response) {
-		rc = ENOMEM;
+		rc = -ENOMEM;
 		ses->auth_key.len = 0;
 		goto setup_ntlmv2_rsp_ret;
 	}
@@ -789,38 +790,46 @@ int
 calc_seckey(struct cifs_ses *ses)
 {
 	int rc;
-	struct crypto_blkcipher *tfm_arc4;
+	struct crypto_skcipher *tfm_arc4;
 	struct scatterlist sgin, sgout;
-	struct blkcipher_desc desc;
+	struct skcipher_request *req;
 	unsigned char sec_key[CIFS_SESS_KEY_SIZE]; /* a nonce */
 
 	get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE);
 
-	tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
+	tfm_arc4 = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_arc4)) {
 		rc = PTR_ERR(tfm_arc4);
 		cifs_dbg(VFS, "could not allocate crypto API arc4\n");
 		return rc;
 	}
 
-	desc.tfm = tfm_arc4;
-
-	rc = crypto_blkcipher_setkey(tfm_arc4, ses->auth_key.response,
+	rc = crypto_skcipher_setkey(tfm_arc4, ses->auth_key.response,
 					CIFS_SESS_KEY_SIZE);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not set response as a key\n",
 			 __func__);
-		return rc;
+		goto out_free_cipher;
+	}
+
+	req = skcipher_request_alloc(tfm_arc4, GFP_KERNEL);
+	if (!req) {
+		rc = -ENOMEM;
+		cifs_dbg(VFS, "could not allocate crypto API arc4 request\n");
+		goto out_free_cipher;
 	}
 
 	sg_init_one(&sgin, sec_key, CIFS_SESS_KEY_SIZE);
 	sg_init_one(&sgout, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
 
-	rc = crypto_blkcipher_encrypt(&desc, &sgout, &sgin, CIFS_CPHTXT_SIZE);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sgin, &sgout, CIFS_CPHTXT_SIZE, NULL);
+
+	rc = crypto_skcipher_encrypt(req);
+	skcipher_request_free(req);
 	if (rc) {
 		cifs_dbg(VFS, "could not encrypt session key rc: %d\n", rc);
-		crypto_free_blkcipher(tfm_arc4);
-		return rc;
+		goto out_free_cipher;
 	}
 
 	/* make secondary_key/nonce as session key */
@@ -828,7 +837,8 @@ calc_seckey(struct cifs_ses *ses)
 	/* and make len as that of session key only */
 	ses->auth_key.len = CIFS_SESS_KEY_SIZE;
 
-	crypto_free_blkcipher(tfm_arc4);
+out_free_cipher:
+	crypto_free_skcipher(tfm_arc4);
 
 	return rc;
 }
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index c48ca13673e3..1d86fc620e5c 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -54,10 +54,10 @@
 #endif
 
 int cifsFYI = 0;
-int traceSMB = 0;
+bool traceSMB;
 bool enable_oplocks = true;
-unsigned int linuxExtEnabled = 1;
-unsigned int lookupCacheEnabled = 1;
+bool linuxExtEnabled = true;
+bool lookupCacheEnabled = true;
 unsigned int global_secflags = CIFSSEC_DEF;
 /* unsigned int ntlmv2_support = 0; */
 unsigned int sign_CIFS_PDUs = 1;
@@ -642,9 +642,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 		while (*s && *s != sep)
 			s++;
 
-		inode_lock(dir);
-		child = lookup_one_len(p, dentry, s - p);
-		inode_unlock(dir);
+		child = lookup_one_len_unlocked(p, dentry, s - p);
 		dput(dentry);
 		dentry = child;
 	} while (!IS_ERR(dentry));
@@ -1013,7 +1011,6 @@ const struct file_operations cifs_file_strict_ops = {
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
 	.clone_file_range = cifs_clone_file_range,
-	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 68c4547528c4..83aac8ba50b0 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -31,19 +31,15 @@
  * so that it will fit. We use hash_64 to convert the value to 31 bits, and
  * then add 1, to ensure that we don't end up with a 0 as the value.
  */
-#if BITS_PER_LONG == 64
 static inline ino_t
 cifs_uniqueid_to_ino_t(u64 fileid)
 {
+	if ((sizeof(ino_t)) < (sizeof(u64)))
+		return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
+
 	return (ino_t)fileid;
+
 }
-#else
-static inline ino_t
-cifs_uniqueid_to_ino_t(u64 fileid)
-{
-	return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
-}
-#endif
 
 extern struct file_system_type cifs_fs_type;
 extern const struct address_space_operations cifs_addr_ops;
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index a25b2513f146..d21da9f05bae 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1596,11 +1596,11 @@ GLOBAL_EXTERN atomic_t midCount;
 
 /* Misc globals */
 GLOBAL_EXTERN bool enable_oplocks; /* enable or disable oplocks */
-GLOBAL_EXTERN unsigned int lookupCacheEnabled;
+GLOBAL_EXTERN bool lookupCacheEnabled;
 GLOBAL_EXTERN unsigned int global_secflags;	/* if on, session setup sent
 				with more secure ntlmssp2 challenge/resp */
 GLOBAL_EXTERN unsigned int sign_CIFS_PDUs;  /* enable smb packet signing */
-GLOBAL_EXTERN unsigned int linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
+GLOBAL_EXTERN bool linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
 GLOBAL_EXTERN unsigned int CIFSMaxBufSize;  /* max size not including hdr */
 GLOBAL_EXTERN unsigned int cifs_min_rcv;    /* min size of big ntwrk buf pool */
 GLOBAL_EXTERN unsigned int cifs_min_small;  /* min size of small buf pool */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 90b4f9f7de66..76fcb50295a3 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1396,11 +1396,10 @@ openRetry:
  * current bigbuf.
  */
 static int
-cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+discard_remaining_data(struct TCP_Server_Info *server)
 {
 	unsigned int rfclen = get_rfc1002_length(server->smallbuf);
 	int remaining = rfclen + 4 - server->total_read;
-	struct cifs_readdata *rdata = mid->callback_data;
 
 	while (remaining > 0) {
 		int length;
@@ -1414,10 +1413,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		remaining -= length;
 	}
 
-	dequeue_mid(mid, rdata->result);
 	return 0;
 }
 
+static int
+cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+{
+	int length;
+	struct cifs_readdata *rdata = mid->callback_data;
+
+	length = discard_remaining_data(server);
+	dequeue_mid(mid, rdata->result);
+	return length;
+}
+
 int
 cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 {
@@ -1446,6 +1455,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		return length;
 	server->total_read += length;
 
+	if (server->ops->is_status_pending &&
+	    server->ops->is_status_pending(buf, server, 0)) {
+		discard_remaining_data(server);
+		return -1;
+	}
+
 	/* Was the SMB read successful? */
 	rdata->result = server->ops->map_error(buf, false);
 	if (rdata->result != 0) {
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 4fbd92d2e113..a763cd3d9e7c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2999,8 +2999,7 @@ ip_rfc1001_connect(struct TCP_Server_Info *server)
 	if (ses_init_buf) {
 		ses_init_buf->trailer.session_req.called_len = 32;
 
-		if (server->server_RFC1001_name &&
-		    server->server_RFC1001_name[0] != 0)
+		if (server->server_RFC1001_name[0] != 0)
 			rfc1002mangle(ses_init_buf->trailer.
 				      session_req.called_name,
 				      server->server_RFC1001_name,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 10f8d5cf5681..42e1f440eb1e 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1106,21 +1106,25 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
 {
 	char *data_offset;
 	struct create_context *cc;
-	unsigned int next = 0;
+	unsigned int next;
+	unsigned int remaining;
 	char *name;
 
 	data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset);
+	remaining = le32_to_cpu(rsp->CreateContextsLength);
 	cc = (struct create_context *)data_offset;
-	do {
-		cc = (struct create_context *)((char *)cc + next);
+	while (remaining >= sizeof(struct create_context)) {
 		name = le16_to_cpu(cc->NameOffset) + (char *)cc;
-		if (le16_to_cpu(cc->NameLength) != 4 ||
-		    strncmp(name, "RqLs", 4)) {
-			next = le32_to_cpu(cc->Next);
-			continue;
-		}
-		return server->ops->parse_lease_buf(cc, epoch);
-	} while (next != 0);
+		if (le16_to_cpu(cc->NameLength) == 4 &&
+		    strncmp(name, "RqLs", 4) == 0)
+			return server->ops->parse_lease_buf(cc, epoch);
+
+		next = le32_to_cpu(cc->Next);
+		if (!next)
+			break;
+		remaining -= next;
+		cc = (struct create_context *)((char *)cc + next);
+	}
 
 	return 0;
 }
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index a4232ec4f2ba..699b7868108f 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -23,6 +23,7 @@
    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 
+#include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
@@ -70,31 +71,42 @@ smbhash(unsigned char *out, const unsigned char *in, unsigned char *key)
 {
 	int rc;
 	unsigned char key2[8];
-	struct crypto_blkcipher *tfm_des;
+	struct crypto_skcipher *tfm_des;
 	struct scatterlist sgin, sgout;
-	struct blkcipher_desc desc;
+	struct skcipher_request *req;
 
 	str_to_key(key, key2);
 
-	tfm_des = crypto_alloc_blkcipher("ecb(des)", 0, CRYPTO_ALG_ASYNC);
+	tfm_des = crypto_alloc_skcipher("ecb(des)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_des)) {
 		rc = PTR_ERR(tfm_des);
 		cifs_dbg(VFS, "could not allocate des crypto API\n");
 		goto smbhash_err;
 	}
 
-	desc.tfm = tfm_des;
+	req = skcipher_request_alloc(tfm_des, GFP_KERNEL);
+	if (!req) {
+		rc = -ENOMEM;
+		cifs_dbg(VFS, "could not allocate des crypto API\n");
+		goto smbhash_free_skcipher;
+	}
 
-	crypto_blkcipher_setkey(tfm_des, key2, 8);
+	crypto_skcipher_setkey(tfm_des, key2, 8);
 
 	sg_init_one(&sgin, in, 8);
 	sg_init_one(&sgout, out, 8);
 
-	rc = crypto_blkcipher_encrypt(&desc, &sgout, &sgin, 8);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sgin, &sgout, 8, NULL);
+
+	rc = crypto_skcipher_encrypt(req);
 	if (rc)
 		cifs_dbg(VFS, "could not encrypt crypt key rc: %d\n", rc);
 
-	crypto_free_blkcipher(tfm_des);
+	skcipher_request_free(req);
+
+smbhash_free_skcipher:
+	crypto_free_skcipher(tfm_des);
 smbhash_err:
 	return rc;
 }
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index a5b8eb69a8f4..bd01b92aad98 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1040,28 +1040,6 @@ COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS)
 /* PPPOX */
 COMPATIBLE_IOCTL(PPPOEIOCSFWD)
 COMPATIBLE_IOCTL(PPPOEIOCDFWD)
-/* ppdev */
-COMPATIBLE_IOCTL(PPSETMODE)
-COMPATIBLE_IOCTL(PPRSTATUS)
-COMPATIBLE_IOCTL(PPRCONTROL)
-COMPATIBLE_IOCTL(PPWCONTROL)
-COMPATIBLE_IOCTL(PPFCONTROL)
-COMPATIBLE_IOCTL(PPRDATA)
-COMPATIBLE_IOCTL(PPWDATA)
-COMPATIBLE_IOCTL(PPCLAIM)
-COMPATIBLE_IOCTL(PPRELEASE)
-COMPATIBLE_IOCTL(PPYIELD)
-COMPATIBLE_IOCTL(PPEXCL)
-COMPATIBLE_IOCTL(PPDATADIR)
-COMPATIBLE_IOCTL(PPNEGOT)
-COMPATIBLE_IOCTL(PPWCTLONIRQ)
-COMPATIBLE_IOCTL(PPCLRIRQ)
-COMPATIBLE_IOCTL(PPSETPHASE)
-COMPATIBLE_IOCTL(PPGETMODES)
-COMPATIBLE_IOCTL(PPGETMODE)
-COMPATIBLE_IOCTL(PPGETPHASE)
-COMPATIBLE_IOCTL(PPGETFLAGS)
-COMPATIBLE_IOCTL(PPSETFLAGS)
 /* Big A */
 /* sparc only */
 /* Big Q for sound/OSS */
@@ -1261,6 +1239,9 @@ COMPATIBLE_IOCTL(HCIUNBLOCKADDR)
 COMPATIBLE_IOCTL(HCIINQUIRY)
 COMPATIBLE_IOCTL(HCIUARTSETPROTO)
 COMPATIBLE_IOCTL(HCIUARTGETPROTO)
+COMPATIBLE_IOCTL(HCIUARTGETDEVICE)
+COMPATIBLE_IOCTL(HCIUARTSETFLAGS)
+COMPATIBLE_IOCTL(HCIUARTGETFLAGS)
 COMPATIBLE_IOCTL(RFCOMMCREATEDEV)
 COMPATIBLE_IOCTL(RFCOMMRELEASEDEV)
 COMPATIBLE_IOCTL(RFCOMMGETDEVLIST)
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index f419519ec41f..ea59c891fc53 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -432,14 +432,9 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den
 				(sd->s_type & CONFIGFS_ITEM_BIN_ATTR) ?
 					configfs_init_bin_file :
 					configfs_init_file);
-	if (error) {
+	if (error)
 		configfs_put(sd);
-		return error;
-	}
-
-	d_rehash(dentry);
-
-	return 0;
+	return error;
 }
 
 static struct dentry * configfs_lookup(struct inode *dir,
@@ -701,23 +696,29 @@ static int populate_groups(struct config_group *group)
 {
 	struct config_group *new_group;
 	int ret = 0;
-	int i;
-
-	if (group->default_groups) {
-		for (i = 0; group->default_groups[i]; i++) {
-			new_group = group->default_groups[i];
 
-			ret = create_default_group(group, new_group);
-			if (ret) {
-				detach_groups(group);
-				break;
-			}
+	list_for_each_entry(new_group, &group->default_groups, group_entry) {
+		ret = create_default_group(group, new_group);
+		if (ret) {
+			detach_groups(group);
+			break;
 		}
 	}
 
 	return ret;
 }
 
+void configfs_remove_default_groups(struct config_group *group)
+{
+	struct config_group *g, *n;
+
+	list_for_each_entry_safe(g, n, &group->default_groups, group_entry) {
+		list_del(&g->group_entry);
+		config_item_put(&g->cg_item);
+	}
+}
+EXPORT_SYMBOL(configfs_remove_default_groups);
+
 /*
  * All of link_obj/unlink_obj/link_group/unlink_group require that
  * subsys->su_mutex is held.
@@ -766,15 +767,10 @@ static void link_obj(struct config_item *parent_item, struct config_item *item)
 
 static void unlink_group(struct config_group *group)
 {
-	int i;
 	struct config_group *new_group;
 
-	if (group->default_groups) {
-		for (i = 0; group->default_groups[i]; i++) {
-			new_group = group->default_groups[i];
-			unlink_group(new_group);
-		}
-	}
+	list_for_each_entry(new_group, &group->default_groups, group_entry)
+		unlink_group(new_group);
 
 	group->cg_subsys = NULL;
 	unlink_obj(&group->cg_item);
@@ -782,7 +778,6 @@ static void unlink_group(struct config_group *group)
 
 static void link_group(struct config_group *parent_group, struct config_group *group)
 {
-	int i;
 	struct config_group *new_group;
 	struct configfs_subsystem *subsys = NULL; /* gcc is a turd */
 
@@ -796,12 +791,8 @@ static void link_group(struct config_group *parent_group, struct config_group *g
 		BUG();
 	group->cg_subsys = subsys;
 
-	if (group->default_groups) {
-		for (i = 0; group->default_groups[i]; i++) {
-			new_group = group->default_groups[i];
-			link_group(group, new_group);
-		}
-	}
+	list_for_each_entry(new_group, &group->default_groups, group_entry)
+		link_group(group, new_group);
 }
 
 /*
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index cee087d8f7e0..03d124ae27d7 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -75,7 +75,8 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr)
 		sd_iattr->ia_mode = sd->s_mode;
 		sd_iattr->ia_uid = GLOBAL_ROOT_UID;
 		sd_iattr->ia_gid = GLOBAL_ROOT_GID;
-		sd_iattr->ia_atime = sd_iattr->ia_mtime = sd_iattr->ia_ctime = CURRENT_TIME;
+		sd_iattr->ia_atime = sd_iattr->ia_mtime =
+			sd_iattr->ia_ctime = current_fs_time(inode->i_sb);
 		sd->s_iattr = sd_iattr;
 	}
 	/* attributes were changed atleast once in past */
@@ -111,7 +112,8 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr)
 static inline void set_default_inode_attr(struct inode * inode, umode_t mode)
 {
 	inode->i_mode = mode;
-	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_atime = inode->i_mtime =
+		inode->i_ctime = current_fs_time(inode->i_sb);
 }
 
 static inline void set_inode_attr(struct inode * inode, struct iattr * iattr)
@@ -195,13 +197,21 @@ int configfs_create(struct dentry * dentry, umode_t mode, void (*init)(struct in
 		return -ENOMEM;
 
 	p_inode = d_inode(dentry->d_parent);
-	p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME;
+	p_inode->i_mtime = p_inode->i_ctime = current_fs_time(p_inode->i_sb);
 	configfs_set_inode_lock_class(sd, inode);
 
 	init(inode);
-	d_instantiate(dentry, inode);
-	if (S_ISDIR(mode) || S_ISLNK(mode))
+	if (S_ISDIR(mode) || S_ISLNK(mode)) {
+		/*
+		 * ->symlink(), ->mkdir(), configfs_register_subsystem() or
+		 * create_default_group() - already hashed.
+		 */
+		d_instantiate(dentry, inode);
 		dget(dentry);  /* pin link and directory dentries in core */
+	} else {
+		/* ->lookup() */
+		d_add(dentry, inode);
+	}
 	return error;
 }
 
diff --git a/fs/configfs/item.c b/fs/configfs/item.c
index b863a09cd2f1..8b2a994042dd 100644
--- a/fs/configfs/item.c
+++ b/fs/configfs/item.c
@@ -182,6 +182,7 @@ void config_group_init(struct config_group *group)
 {
 	config_item_init(&group->cg_item);
 	INIT_LIST_HEAD(&group->cg_children);
+	INIT_LIST_HEAD(&group->default_groups);
 }
 EXPORT_SYMBOL(config_group_init);
 
diff --git a/fs/coredump.c b/fs/coredump.c
index 9ea87e9fdccf..47c32c3bfa1d 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -32,6 +32,9 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
 #include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/path.h>
 #include <linux/timekeeping.h>
 
 #include <asm/uaccess.h>
@@ -649,6 +652,8 @@ void do_coredump(const siginfo_t *siginfo)
 		}
 	} else {
 		struct inode *inode;
+		int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW |
+				 O_LARGEFILE | O_EXCL;
 
 		if (cprm.limit < binfmt->min_coredump)
 			goto fail_unlock;
@@ -687,10 +692,27 @@ void do_coredump(const siginfo_t *siginfo)
 		 * what matters is that at least one of the two processes
 		 * writes its coredump successfully, not which one.
 		 */
-		cprm.file = filp_open(cn.corename,
-				 O_CREAT | 2 | O_NOFOLLOW |
-				 O_LARGEFILE | O_EXCL,
-				 0600);
+		if (need_suid_safe) {
+			/*
+			 * Using user namespaces, normal user tasks can change
+			 * their current->fs->root to point to arbitrary
+			 * directories. Since the intention of the "only dump
+			 * with a fully qualified path" rule is to control where
+			 * coredumps may be placed using root privileges,
+			 * current->fs->root must not be used. Instead, use the
+			 * root directory of init_task.
+			 */
+			struct path root;
+
+			task_lock(&init_task);
+			get_fs_root(init_task.fs, &root);
+			task_unlock(&init_task);
+			cprm.file = file_open_root(root.dentry, root.mnt,
+				cn.corename, open_flags, 0600);
+			path_put(&root);
+		} else {
+			cprm.file = filp_open(cn.corename, open_flags, 0600);
+		}
 		if (IS_ERR(cprm.file))
 			goto fail_unlock;
 
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
new file mode 100644
index 000000000000..92348faf9865
--- /dev/null
+++ b/fs/crypto/Kconfig
@@ -0,0 +1,18 @@
+config FS_ENCRYPTION
+	tristate "FS Encryption (Per-file encryption)"
+	depends on BLOCK
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_ECB
+	select CRYPTO_XTS
+	select CRYPTO_CTS
+	select CRYPTO_CTR
+	select CRYPTO_SHA256
+	select KEYS
+	select ENCRYPTED_KEYS
+	help
+	  Enable encryption of files and directories.  This
+	  feature is similar to ecryptfs, but it is more memory
+	  efficient since it avoids caching the encrypted and
+	  decrypted pages in the page cache.
diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile
new file mode 100644
index 000000000000..f17684c48739
--- /dev/null
+++ b/fs/crypto/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_FS_ENCRYPTION)	+= fscrypto.o
+
+fscrypto-y := crypto.o fname.o policy.o keyinfo.o
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
new file mode 100644
index 000000000000..06cd1a22240b
--- /dev/null
+++ b/fs/crypto/crypto.c
@@ -0,0 +1,555 @@
+/*
+ * This contains encryption functions for per-file encryption.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ *	Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ *	Ildar Muslukhov, 2014
+ * Add fscrypt_pullback_bio_page()
+ *	Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <linux/ratelimit.h>
+#include <linux/bio.h>
+#include <linux/dcache.h>
+#include <linux/fscrypto.h>
+#include <linux/ecryptfs.h>
+
+static unsigned int num_prealloc_crypto_pages = 32;
+static unsigned int num_prealloc_crypto_ctxs = 128;
+
+module_param(num_prealloc_crypto_pages, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_pages,
+		"Number of crypto pages to preallocate");
+module_param(num_prealloc_crypto_ctxs, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
+		"Number of crypto contexts to preallocate");
+
+static mempool_t *fscrypt_bounce_page_pool = NULL;
+
+static LIST_HEAD(fscrypt_free_ctxs);
+static DEFINE_SPINLOCK(fscrypt_ctx_lock);
+
+static struct workqueue_struct *fscrypt_read_workqueue;
+static DEFINE_MUTEX(fscrypt_init_mutex);
+
+static struct kmem_cache *fscrypt_ctx_cachep;
+struct kmem_cache *fscrypt_info_cachep;
+
+/**
+ * fscrypt_release_ctx() - Releases an encryption context
+ * @ctx: The encryption context to release.
+ *
+ * If the encryption context was allocated from the pre-allocated pool, returns
+ * it to that pool. Else, frees it.
+ *
+ * If there's a bounce page in the context, this frees that.
+ */
+void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
+{
+	unsigned long flags;
+
+	if (ctx->flags & FS_WRITE_PATH_FL && ctx->w.bounce_page) {
+		mempool_free(ctx->w.bounce_page, fscrypt_bounce_page_pool);
+		ctx->w.bounce_page = NULL;
+	}
+	ctx->w.control_page = NULL;
+	if (ctx->flags & FS_CTX_REQUIRES_FREE_ENCRYPT_FL) {
+		kmem_cache_free(fscrypt_ctx_cachep, ctx);
+	} else {
+		spin_lock_irqsave(&fscrypt_ctx_lock, flags);
+		list_add(&ctx->free_list, &fscrypt_free_ctxs);
+		spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
+	}
+}
+EXPORT_SYMBOL(fscrypt_release_ctx);
+
+/**
+ * fscrypt_get_ctx() - Gets an encryption context
+ * @inode:       The inode for which we are doing the crypto
+ *
+ * Allocates and initializes an encryption context.
+ *
+ * Return: An allocated and initialized encryption context on success; error
+ * value or NULL otherwise.
+ */
+struct fscrypt_ctx *fscrypt_get_ctx(struct inode *inode)
+{
+	struct fscrypt_ctx *ctx = NULL;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	unsigned long flags;
+
+	if (ci == NULL)
+		return ERR_PTR(-ENOKEY);
+
+	/*
+	 * We first try getting the ctx from a free list because in
+	 * the common case the ctx will have an allocated and
+	 * initialized crypto tfm, so it's probably a worthwhile
+	 * optimization. For the bounce page, we first try getting it
+	 * from the kernel allocator because that's just about as fast
+	 * as getting it from a list and because a cache of free pages
+	 * should generally be a "last resort" option for a filesystem
+	 * to be able to do its job.
+	 */
+	spin_lock_irqsave(&fscrypt_ctx_lock, flags);
+	ctx = list_first_entry_or_null(&fscrypt_free_ctxs,
+					struct fscrypt_ctx, free_list);
+	if (ctx)
+		list_del(&ctx->free_list);
+	spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
+	if (!ctx) {
+		ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS);
+		if (!ctx)
+			return ERR_PTR(-ENOMEM);
+		ctx->flags |= FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+	} else {
+		ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+	}
+	ctx->flags &= ~FS_WRITE_PATH_FL;
+	return ctx;
+}
+EXPORT_SYMBOL(fscrypt_get_ctx);
+
+/**
+ * fscrypt_complete() - The completion callback for page encryption
+ * @req: The asynchronous encryption request context
+ * @res: The result of the encryption operation
+ */
+static void fscrypt_complete(struct crypto_async_request *req, int res)
+{
+	struct fscrypt_completion_result *ecr = req->data;
+
+	if (res == -EINPROGRESS)
+		return;
+	ecr->res = res;
+	complete(&ecr->completion);
+}
+
+typedef enum {
+	FS_DECRYPT = 0,
+	FS_ENCRYPT,
+} fscrypt_direction_t;
+
+static int do_page_crypto(struct inode *inode,
+			fscrypt_direction_t rw, pgoff_t index,
+			struct page *src_page, struct page *dest_page)
+{
+	u8 xts_tweak[FS_XTS_TWEAK_SIZE];
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist dst, src;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
+	int res = 0;
+
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		printk_ratelimited(KERN_ERR
+				"%s: crypto_request_alloc() failed\n",
+				__func__);
+		return -ENOMEM;
+	}
+
+	skcipher_request_set_callback(
+		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+		fscrypt_complete, &ecr);
+
+	BUILD_BUG_ON(FS_XTS_TWEAK_SIZE < sizeof(index));
+	memcpy(xts_tweak, &index, sizeof(index));
+	memset(&xts_tweak[sizeof(index)], 0,
+			FS_XTS_TWEAK_SIZE - sizeof(index));
+
+	sg_init_table(&dst, 1);
+	sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
+	sg_init_table(&src, 1);
+	sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
+	skcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
+					xts_tweak);
+	if (rw == FS_DECRYPT)
+		res = crypto_skcipher_decrypt(req);
+	else
+		res = crypto_skcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		BUG_ON(req->base.data != &ecr);
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+	skcipher_request_free(req);
+	if (res) {
+		printk_ratelimited(KERN_ERR
+			"%s: crypto_skcipher_encrypt() returned %d\n",
+			__func__, res);
+		return res;
+	}
+	return 0;
+}
+
+static struct page *alloc_bounce_page(struct fscrypt_ctx *ctx)
+{
+	ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool,
+							GFP_NOWAIT);
+	if (ctx->w.bounce_page == NULL)
+		return ERR_PTR(-ENOMEM);
+	ctx->flags |= FS_WRITE_PATH_FL;
+	return ctx->w.bounce_page;
+}
+
+/**
+ * fscypt_encrypt_page() - Encrypts a page
+ * @inode:          The inode for which the encryption should take place
+ * @plaintext_page: The page to encrypt. Must be locked.
+ *
+ * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
+ * encryption context.
+ *
+ * Called on the page write path.  The caller must call
+ * fscrypt_restore_control_page() on the returned ciphertext page to
+ * release the bounce buffer and the encryption context.
+ *
+ * Return: An allocated page with the encrypted content on success. Else, an
+ * error value or NULL.
+ */
+struct page *fscrypt_encrypt_page(struct inode *inode,
+				struct page *plaintext_page)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	int err;
+
+	BUG_ON(!PageLocked(plaintext_page));
+
+	ctx = fscrypt_get_ctx(inode);
+	if (IS_ERR(ctx))
+		return (struct page *)ctx;
+
+	/* The encryption operation will require a bounce page. */
+	ciphertext_page = alloc_bounce_page(ctx);
+	if (IS_ERR(ciphertext_page))
+		goto errout;
+
+	ctx->w.control_page = plaintext_page;
+	err = do_page_crypto(inode, FS_ENCRYPT, plaintext_page->index,
+					plaintext_page, ciphertext_page);
+	if (err) {
+		ciphertext_page = ERR_PTR(err);
+		goto errout;
+	}
+	SetPagePrivate(ciphertext_page);
+	set_page_private(ciphertext_page, (unsigned long)ctx);
+	lock_page(ciphertext_page);
+	return ciphertext_page;
+
+errout:
+	fscrypt_release_ctx(ctx);
+	return ciphertext_page;
+}
+EXPORT_SYMBOL(fscrypt_encrypt_page);
+
+/**
+ * f2crypt_decrypt_page() - Decrypts a page in-place
+ * @page: The page to decrypt. Must be locked.
+ *
+ * Decrypts page in-place using the ctx encryption context.
+ *
+ * Called from the read completion callback.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int fscrypt_decrypt_page(struct page *page)
+{
+	BUG_ON(!PageLocked(page));
+
+	return do_page_crypto(page->mapping->host,
+			FS_DECRYPT, page->index, page, page);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_page);
+
+int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk,
+				sector_t pblk, unsigned int len)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	struct bio *bio;
+	int ret, err = 0;
+
+	BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE);
+
+	ctx = fscrypt_get_ctx(inode);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	ciphertext_page = alloc_bounce_page(ctx);
+	if (IS_ERR(ciphertext_page)) {
+		err = PTR_ERR(ciphertext_page);
+		goto errout;
+	}
+
+	while (len--) {
+		err = do_page_crypto(inode, FS_ENCRYPT, lblk,
+						ZERO_PAGE(0), ciphertext_page);
+		if (err)
+			goto errout;
+
+		bio = bio_alloc(GFP_KERNEL, 1);
+		if (!bio) {
+			err = -ENOMEM;
+			goto errout;
+		}
+		bio->bi_bdev = inode->i_sb->s_bdev;
+		bio->bi_iter.bi_sector =
+			pblk << (inode->i_sb->s_blocksize_bits - 9);
+		ret = bio_add_page(bio, ciphertext_page,
+					inode->i_sb->s_blocksize, 0);
+		if (ret != inode->i_sb->s_blocksize) {
+			/* should never happen! */
+			WARN_ON(1);
+			bio_put(bio);
+			err = -EIO;
+			goto errout;
+		}
+		err = submit_bio_wait(WRITE, bio);
+		if ((err == 0) && bio->bi_error)
+			err = -EIO;
+		bio_put(bio);
+		if (err)
+			goto errout;
+		lblk++;
+		pblk++;
+	}
+	err = 0;
+errout:
+	fscrypt_release_ctx(ctx);
+	return err;
+}
+EXPORT_SYMBOL(fscrypt_zeroout_range);
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct inode *dir = d_inode(dentry->d_parent);
+	struct fscrypt_info *ci = dir->i_crypt_info;
+	int dir_has_key, cached_with_key;
+
+	if (!dir->i_sb->s_cop->is_encrypted(dir))
+		return 0;
+
+	if (ci && ci->ci_keyring_key &&
+	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					  (1 << KEY_FLAG_REVOKED) |
+					  (1 << KEY_FLAG_DEAD))))
+		ci = NULL;
+
+	/* this should eventually be an flag in d_flags */
+	spin_lock(&dentry->d_lock);
+	cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
+	spin_unlock(&dentry->d_lock);
+	dir_has_key = (ci != NULL);
+
+	/*
+	 * If the dentry was cached without the key, and it is a
+	 * negative dentry, it might be a valid name.  We can't check
+	 * if the key has since been made available due to locking
+	 * reasons, so we fail the validation so ext4_lookup() can do
+	 * this check.
+	 *
+	 * We also fail the validation if the dentry was created with
+	 * the key present, but we no longer have the key, or vice versa.
+	 */
+	if ((!cached_with_key && d_is_negative(dentry)) ||
+			(!cached_with_key && dir_has_key) ||
+			(cached_with_key && !dir_has_key))
+		return 0;
+	return 1;
+}
+
+const struct dentry_operations fscrypt_d_ops = {
+	.d_revalidate = fscrypt_d_revalidate,
+};
+EXPORT_SYMBOL(fscrypt_d_ops);
+
+/*
+ * Call fscrypt_decrypt_page on every single page, reusing the encryption
+ * context.
+ */
+static void completion_pages(struct work_struct *work)
+{
+	struct fscrypt_ctx *ctx =
+		container_of(work, struct fscrypt_ctx, r.work);
+	struct bio *bio = ctx->r.bio;
+	struct bio_vec *bv;
+	int i;
+
+	bio_for_each_segment_all(bv, bio, i) {
+		struct page *page = bv->bv_page;
+		int ret = fscrypt_decrypt_page(page);
+
+		if (ret) {
+			WARN_ON_ONCE(1);
+			SetPageError(page);
+		} else {
+			SetPageUptodate(page);
+		}
+		unlock_page(page);
+	}
+	fscrypt_release_ctx(ctx);
+	bio_put(bio);
+}
+
+void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
+{
+	INIT_WORK(&ctx->r.work, completion_pages);
+	ctx->r.bio = bio;
+	queue_work(fscrypt_read_workqueue, &ctx->r.work);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
+
+void fscrypt_pullback_bio_page(struct page **page, bool restore)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *bounce_page;
+
+	/* The bounce data pages are unmapped. */
+	if ((*page)->mapping)
+		return;
+
+	/* The bounce data page is unmapped. */
+	bounce_page = *page;
+	ctx = (struct fscrypt_ctx *)page_private(bounce_page);
+
+	/* restore control page */
+	*page = ctx->w.control_page;
+
+	if (restore)
+		fscrypt_restore_control_page(bounce_page);
+}
+EXPORT_SYMBOL(fscrypt_pullback_bio_page);
+
+void fscrypt_restore_control_page(struct page *page)
+{
+	struct fscrypt_ctx *ctx;
+
+	ctx = (struct fscrypt_ctx *)page_private(page);
+	set_page_private(page, (unsigned long)NULL);
+	ClearPagePrivate(page);
+	unlock_page(page);
+	fscrypt_release_ctx(ctx);
+}
+EXPORT_SYMBOL(fscrypt_restore_control_page);
+
+static void fscrypt_destroy(void)
+{
+	struct fscrypt_ctx *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &fscrypt_free_ctxs, free_list)
+		kmem_cache_free(fscrypt_ctx_cachep, pos);
+	INIT_LIST_HEAD(&fscrypt_free_ctxs);
+	mempool_destroy(fscrypt_bounce_page_pool);
+	fscrypt_bounce_page_pool = NULL;
+}
+
+/**
+ * fscrypt_initialize() - allocate major buffers for fs encryption.
+ *
+ * We only call this when we start accessing encrypted files, since it
+ * results in memory getting allocated that wouldn't otherwise be used.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int fscrypt_initialize(void)
+{
+	int i, res = -ENOMEM;
+
+	if (fscrypt_bounce_page_pool)
+		return 0;
+
+	mutex_lock(&fscrypt_init_mutex);
+	if (fscrypt_bounce_page_pool)
+		goto already_initialized;
+
+	for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
+		struct fscrypt_ctx *ctx;
+
+		ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS);
+		if (!ctx)
+			goto fail;
+		list_add(&ctx->free_list, &fscrypt_free_ctxs);
+	}
+
+	fscrypt_bounce_page_pool =
+		mempool_create_page_pool(num_prealloc_crypto_pages, 0);
+	if (!fscrypt_bounce_page_pool)
+		goto fail;
+
+already_initialized:
+	mutex_unlock(&fscrypt_init_mutex);
+	return 0;
+fail:
+	fscrypt_destroy();
+	mutex_unlock(&fscrypt_init_mutex);
+	return res;
+}
+EXPORT_SYMBOL(fscrypt_initialize);
+
+/**
+ * fscrypt_init() - Set up for fs encryption.
+ */
+static int __init fscrypt_init(void)
+{
+	fscrypt_read_workqueue = alloc_workqueue("fscrypt_read_queue",
+							WQ_HIGHPRI, 0);
+	if (!fscrypt_read_workqueue)
+		goto fail;
+
+	fscrypt_ctx_cachep = KMEM_CACHE(fscrypt_ctx, SLAB_RECLAIM_ACCOUNT);
+	if (!fscrypt_ctx_cachep)
+		goto fail_free_queue;
+
+	fscrypt_info_cachep = KMEM_CACHE(fscrypt_info, SLAB_RECLAIM_ACCOUNT);
+	if (!fscrypt_info_cachep)
+		goto fail_free_ctx;
+
+	return 0;
+
+fail_free_ctx:
+	kmem_cache_destroy(fscrypt_ctx_cachep);
+fail_free_queue:
+	destroy_workqueue(fscrypt_read_workqueue);
+fail:
+	return -ENOMEM;
+}
+module_init(fscrypt_init)
+
+/**
+ * fscrypt_exit() - Shutdown the fs encryption system
+ */
+static void __exit fscrypt_exit(void)
+{
+	fscrypt_destroy();
+
+	if (fscrypt_read_workqueue)
+		destroy_workqueue(fscrypt_read_workqueue);
+	kmem_cache_destroy(fscrypt_ctx_cachep);
+	kmem_cache_destroy(fscrypt_info_cachep);
+}
+module_exit(fscrypt_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/fs/f2fs/crypto_fname.c b/fs/crypto/fname.c
index ab377d496a39..5d6d49113efa 100644
--- a/fs/f2fs/crypto_fname.c
+++ b/fs/crypto/fname.c
@@ -1,46 +1,32 @@
 /*
- * linux/fs/f2fs/crypto_fname.c
- *
- * Copied from linux/fs/ext4/crypto.c
+ * This contains functions for filename crypto management
  *
  * Copyright (C) 2015, Google, Inc.
  * Copyright (C) 2015, Motorola Mobility
  *
- * This contains functions for filename crypto management in f2fs
- *
  * Written by Uday Savagaonkar, 2014.
- *
- * Adjust f2fs dentry structure
- *	Jaegeuk Kim, 2015.
+ * Modified by Jaegeuk Kim, 2015.
  *
  * This has not yet undergone a rigorous security audit.
  */
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
-#include <linux/crypto.h>
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/key.h>
-#include <linux/list.h>
-#include <linux/mempool.h>
-#include <linux/random.h>
 #include <linux/scatterlist.h>
-#include <linux/spinlock_types.h>
-#include <linux/f2fs_fs.h>
 #include <linux/ratelimit.h>
+#include <linux/fscrypto.h>
 
-#include "f2fs.h"
-#include "f2fs_crypto.h"
-#include "xattr.h"
+static u32 size_round_up(size_t size, size_t blksize)
+{
+	return ((size + blksize - 1) / blksize) * blksize;
+}
 
 /**
- * f2fs_dir_crypt_complete() -
+ * dir_crypt_complete() -
  */
-static void f2fs_dir_crypt_complete(struct crypto_async_request *req, int res)
+static void dir_crypt_complete(struct crypto_async_request *req, int res)
 {
-	struct f2fs_completion_result *ecr = req->data;
+	struct fscrypt_completion_result *ecr = req->data;
 
 	if (res == -EINPROGRESS)
 		return;
@@ -48,45 +34,35 @@ static void f2fs_dir_crypt_complete(struct crypto_async_request *req, int res)
 	complete(&ecr->completion);
 }
 
-bool f2fs_valid_filenames_enc_mode(uint32_t mode)
-{
-	return (mode == F2FS_ENCRYPTION_MODE_AES_256_CTS);
-}
-
-static unsigned max_name_len(struct inode *inode)
-{
-	return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
-					F2FS_NAME_LEN;
-}
-
 /**
- * f2fs_fname_encrypt() -
+ * fname_encrypt() -
  *
  * This function encrypts the input filename, and returns the length of the
  * ciphertext. Errors are returned as negative numbers.  We trust the caller to
  * allocate sufficient memory to oname string.
  */
-static int f2fs_fname_encrypt(struct inode *inode,
-			const struct qstr *iname, struct f2fs_str *oname)
+static int fname_encrypt(struct inode *inode,
+			const struct qstr *iname, struct fscrypt_str *oname)
 {
 	u32 ciphertext_len;
-	struct ablkcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
-	char iv[F2FS_CRYPTO_BLOCK_SIZE];
+	char iv[FS_CRYPTO_BLOCK_SIZE];
 	struct scatterlist src_sg, dst_sg;
-	int padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK);
+	int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
 	char *workbuf, buf[32], *alloc_buf = NULL;
-	unsigned lim = max_name_len(inode);
+	unsigned lim;
 
+	lim = inode->i_sb->s_cop->max_namelen(inode);
 	if (iname->len <= 0 || iname->len > lim)
 		return -EIO;
 
-	ciphertext_len = (iname->len < F2FS_CRYPTO_BLOCK_SIZE) ?
-		F2FS_CRYPTO_BLOCK_SIZE : iname->len;
-	ciphertext_len = f2fs_fname_crypto_round_up(ciphertext_len, padding);
+	ciphertext_len = (iname->len < FS_CRYPTO_BLOCK_SIZE) ?
+					FS_CRYPTO_BLOCK_SIZE : iname->len;
+	ciphertext_len = size_round_up(ciphertext_len, padding);
 	ciphertext_len = (ciphertext_len > lim) ? lim : ciphertext_len;
 
 	if (ciphertext_len <= sizeof(buf)) {
@@ -99,16 +75,16 @@ static int f2fs_fname_encrypt(struct inode *inode,
 	}
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 			"%s: crypto_request_alloc() failed\n", __func__);
 		kfree(alloc_buf);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-			f2fs_dir_crypt_complete, &ecr);
+			dir_crypt_complete, &ecr);
 
 	/* Copy the input */
 	memcpy(workbuf, iname->name, iname->len);
@@ -116,79 +92,78 @@ static int f2fs_fname_encrypt(struct inode *inode,
 		memset(workbuf + iname->len, 0, ciphertext_len - iname->len);
 
 	/* Initialize IV */
-	memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE);
+	memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
 
 	/* Create encryption request */
 	sg_init_one(&src_sg, workbuf, ciphertext_len);
 	sg_init_one(&dst_sg, oname->name, ciphertext_len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
-	res = crypto_ablkcipher_encrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
+	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 	kfree(alloc_buf);
-	ablkcipher_request_free(req);
-	if (res < 0) {
+	skcipher_request_free(req);
+	if (res < 0)
 		printk_ratelimited(KERN_ERR
 				"%s: Error (error code %d)\n", __func__, res);
-	}
+
 	oname->len = ciphertext_len;
 	return res;
 }
 
 /*
- * f2fs_fname_decrypt()
+ * fname_decrypt()
  *	This function decrypts the input filename, and returns
  *	the length of the plaintext.
  *	Errors are returned as negative numbers.
  *	We trust the caller to allocate sufficient memory to oname string.
  */
-static int f2fs_fname_decrypt(struct inode *inode,
-			const struct f2fs_str *iname, struct f2fs_str *oname)
+static int fname_decrypt(struct inode *inode,
+				const struct fscrypt_str *iname,
+				struct fscrypt_str *oname)
 {
-	struct ablkcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
-	char iv[F2FS_CRYPTO_BLOCK_SIZE];
-	unsigned lim = max_name_len(inode);
+	char iv[FS_CRYPTO_BLOCK_SIZE];
+	unsigned lim;
 
+	lim = inode->i_sb->s_cop->max_namelen(inode);
 	if (iname->len <= 0 || iname->len > lim)
 		return -EIO;
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 			"%s: crypto_request_alloc() failed\n",  __func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-		f2fs_dir_crypt_complete, &ecr);
+		dir_crypt_complete, &ecr);
 
 	/* Initialize IV */
-	memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE);
+	memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
 
 	/* Create decryption request */
 	sg_init_one(&src_sg, iname->name, iname->len);
 	sg_init_one(&dst_sg, oname->name, oname->len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
-	res = crypto_ablkcipher_decrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
+	res = crypto_skcipher_decrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(KERN_ERR
-			"%s: Error in f2fs_fname_decrypt (error code %d)\n",
-			__func__, res);
+				"%s: Error (error code %d)\n", __func__, res);
 		return res;
 	}
 
@@ -200,7 +175,7 @@ static const char *lookup_table =
 	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
 
 /**
- * f2fs_fname_encode_digest() -
+ * digest_encode() -
  *
  * Encodes the input digest using characters from the set [a-zA-Z0-9_+].
  * The encoded string is roughly 4/3 times the size of the input string.
@@ -249,148 +224,152 @@ static int digest_decode(const char *src, int len, char *dst)
 	return cp - dst;
 }
 
-/**
- * f2fs_fname_crypto_round_up() -
- *
- * Return: The next multiple of block size
- */
-u32 f2fs_fname_crypto_round_up(u32 size, u32 blksize)
+u32 fscrypt_fname_encrypted_size(struct inode *inode, u32 ilen)
 {
-	return ((size + blksize - 1) / blksize) * blksize;
+	int padding = 32;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+
+	if (ci)
+		padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
+	if (ilen < FS_CRYPTO_BLOCK_SIZE)
+		ilen = FS_CRYPTO_BLOCK_SIZE;
+	return size_round_up(ilen, padding);
 }
+EXPORT_SYMBOL(fscrypt_fname_encrypted_size);
 
 /**
- * f2fs_fname_crypto_alloc_obuff() -
+ * fscrypt_fname_crypto_alloc_obuff() -
  *
  * Allocates an output buffer that is sufficient for the crypto operation
  * specified by the context and the direction.
  */
-int f2fs_fname_crypto_alloc_buffer(struct inode *inode,
-				   u32 ilen, struct f2fs_str *crypto_str)
+int fscrypt_fname_alloc_buffer(struct inode *inode,
+				u32 ilen, struct fscrypt_str *crypto_str)
 {
-	unsigned int olen;
-	int padding = 16;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+	unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen);
 
-	if (ci)
-		padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK);
-	if (padding < F2FS_CRYPTO_BLOCK_SIZE)
-		padding = F2FS_CRYPTO_BLOCK_SIZE;
-	olen = f2fs_fname_crypto_round_up(ilen, padding);
 	crypto_str->len = olen;
-	if (olen < F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
-		olen = F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
-	/* Allocated buffer can hold one more character to null-terminate the
-	 * string */
+	if (olen < FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
+		olen = FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
+	/*
+	 * Allocated buffer can hold one more character to null-terminate the
+	 * string
+	 */
 	crypto_str->name = kmalloc(olen + 1, GFP_NOFS);
 	if (!(crypto_str->name))
 		return -ENOMEM;
 	return 0;
 }
+EXPORT_SYMBOL(fscrypt_fname_alloc_buffer);
 
 /**
- * f2fs_fname_crypto_free_buffer() -
+ * fscrypt_fname_crypto_free_buffer() -
  *
  * Frees the buffer allocated for crypto operation.
  */
-void f2fs_fname_crypto_free_buffer(struct f2fs_str *crypto_str)
+void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
 {
 	if (!crypto_str)
 		return;
 	kfree(crypto_str->name);
 	crypto_str->name = NULL;
 }
+EXPORT_SYMBOL(fscrypt_fname_free_buffer);
 
 /**
- * f2fs_fname_disk_to_usr() - converts a filename from disk space to user space
+ * fscrypt_fname_disk_to_usr() - converts a filename from disk space to user
+ * space
  */
-int f2fs_fname_disk_to_usr(struct inode *inode,
-			f2fs_hash_t *hash,
-			const struct f2fs_str *iname,
-			struct f2fs_str *oname)
+int fscrypt_fname_disk_to_usr(struct inode *inode,
+			u32 hash, u32 minor_hash,
+			const struct fscrypt_str *iname,
+			struct fscrypt_str *oname)
 {
 	const struct qstr qname = FSTR_TO_QSTR(iname);
 	char buf[24];
 	int ret;
 
-	if (is_dot_dotdot(&qname)) {
+	if (fscrypt_is_dot_dotdot(&qname)) {
 		oname->name[0] = '.';
 		oname->name[iname->len - 1] = '.';
 		oname->len = iname->len;
 		return oname->len;
 	}
 
-	if (F2FS_I(inode)->i_crypt_info)
-		return f2fs_fname_decrypt(inode, iname, oname);
+	if (iname->len < FS_CRYPTO_BLOCK_SIZE)
+		return -EUCLEAN;
 
-	if (iname->len <= F2FS_FNAME_CRYPTO_DIGEST_SIZE) {
+	if (inode->i_crypt_info)
+		return fname_decrypt(inode, iname, oname);
+
+	if (iname->len <= FS_FNAME_CRYPTO_DIGEST_SIZE) {
 		ret = digest_encode(iname->name, iname->len, oname->name);
 		oname->len = ret;
 		return ret;
 	}
 	if (hash) {
-		memcpy(buf, hash, 4);
-		memset(buf + 4, 0, 4);
-	} else
+		memcpy(buf, &hash, 4);
+		memcpy(buf + 4, &minor_hash, 4);
+	} else {
 		memset(buf, 0, 8);
+	}
 	memcpy(buf + 8, iname->name + iname->len - 16, 16);
 	oname->name[0] = '_';
 	ret = digest_encode(buf, 24, oname->name + 1);
 	oname->len = ret + 1;
 	return ret + 1;
 }
+EXPORT_SYMBOL(fscrypt_fname_disk_to_usr);
 
 /**
- * f2fs_fname_usr_to_disk() - converts a filename from user space to disk space
+ * fscrypt_fname_usr_to_disk() - converts a filename from user space to disk
+ * space
  */
-int f2fs_fname_usr_to_disk(struct inode *inode,
+int fscrypt_fname_usr_to_disk(struct inode *inode,
 			const struct qstr *iname,
-			struct f2fs_str *oname)
+			struct fscrypt_str *oname)
 {
-	int res;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (is_dot_dotdot(iname)) {
+	if (fscrypt_is_dot_dotdot(iname)) {
 		oname->name[0] = '.';
 		oname->name[iname->len - 1] = '.';
 		oname->len = iname->len;
 		return oname->len;
 	}
-
-	if (ci) {
-		res = f2fs_fname_encrypt(inode, iname, oname);
-		return res;
-	}
-	/* Without a proper key, a user is not allowed to modify the filenames
+	if (inode->i_crypt_info)
+		return fname_encrypt(inode, iname, oname);
+	/*
+	 * Without a proper key, a user is not allowed to modify the filenames
 	 * in a directory. Consequently, a user space name cannot be mapped to
-	 * a disk-space name */
+	 * a disk-space name
+	 */
 	return -EACCES;
 }
+EXPORT_SYMBOL(fscrypt_fname_usr_to_disk);
 
-int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname,
-			      int lookup, struct f2fs_filename *fname)
+int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
+			      int lookup, struct fscrypt_name *fname)
 {
-	struct f2fs_crypt_info *ci;
 	int ret = 0, bigname = 0;
 
-	memset(fname, 0, sizeof(struct f2fs_filename));
+	memset(fname, 0, sizeof(struct fscrypt_name));
 	fname->usr_fname = iname;
 
-	if (!f2fs_encrypted_inode(dir) || is_dot_dotdot(iname)) {
+	if (!dir->i_sb->s_cop->is_encrypted(dir) ||
+				fscrypt_is_dot_dotdot(iname)) {
 		fname->disk_name.name = (unsigned char *)iname->name;
 		fname->disk_name.len = iname->len;
 		return 0;
 	}
-	ret = f2fs_get_encryption_info(dir);
-	if (ret)
+	ret = get_crypt_info(dir);
+	if (ret && ret != -EOPNOTSUPP)
 		return ret;
-	ci = F2FS_I(dir)->i_crypt_info;
-	if (ci) {
-		ret = f2fs_fname_crypto_alloc_buffer(dir, iname->len,
-						     &fname->crypto_buf);
+
+	if (dir->i_crypt_info) {
+		ret = fscrypt_fname_alloc_buffer(dir, iname->len,
+							&fname->crypto_buf);
 		if (ret < 0)
 			return ret;
-		ret = f2fs_fname_encrypt(dir, iname, &fname->crypto_buf);
+		ret = fname_encrypt(dir, iname, &fname->crypto_buf);
 		if (ret < 0)
 			goto errout;
 		fname->disk_name.name = fname->crypto_buf.name;
@@ -400,18 +379,19 @@ int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname,
 	if (!lookup)
 		return -EACCES;
 
-	/* We don't have the key and we are doing a lookup; decode the
+	/*
+	 * We don't have the key and we are doing a lookup; decode the
 	 * user-supplied name
 	 */
 	if (iname->name[0] == '_')
 		bigname = 1;
-	if ((bigname && (iname->len != 33)) ||
-	    (!bigname && (iname->len > 43)))
+	if ((bigname && (iname->len != 33)) || (!bigname && (iname->len > 43)))
 		return -ENOENT;
 
 	fname->crypto_buf.name = kmalloc(32, GFP_KERNEL);
 	if (fname->crypto_buf.name == NULL)
 		return -ENOMEM;
+
 	ret = digest_decode(iname->name + bigname, iname->len - bigname,
 				fname->crypto_buf.name);
 	if (ret < 0) {
@@ -421,20 +401,24 @@ int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname,
 	fname->crypto_buf.len = ret;
 	if (bigname) {
 		memcpy(&fname->hash, fname->crypto_buf.name, 4);
+		memcpy(&fname->minor_hash, fname->crypto_buf.name + 4, 4);
 	} else {
 		fname->disk_name.name = fname->crypto_buf.name;
 		fname->disk_name.len = fname->crypto_buf.len;
 	}
 	return 0;
+
 errout:
-	f2fs_fname_crypto_free_buffer(&fname->crypto_buf);
+	fscrypt_fname_free_buffer(&fname->crypto_buf);
 	return ret;
 }
+EXPORT_SYMBOL(fscrypt_setup_filename);
 
-void f2fs_fname_free_filename(struct f2fs_filename *fname)
+void fscrypt_free_filename(struct fscrypt_name *fname)
 {
 	kfree(fname->crypto_buf.name);
 	fname->crypto_buf.name = NULL;
 	fname->usr_fname = NULL;
 	fname->disk_name.name = NULL;
 }
+EXPORT_SYMBOL(fscrypt_free_filename);
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
new file mode 100644
index 000000000000..06f5aa478bf2
--- /dev/null
+++ b/fs/crypto/keyinfo.c
@@ -0,0 +1,272 @@
+/*
+ * key management facility for FS encryption support.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions.
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+
+#include <keys/encrypted-type.h>
+#include <keys/user-type.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <uapi/linux/keyctl.h>
+#include <linux/fscrypto.h>
+
+static void derive_crypt_complete(struct crypto_async_request *req, int rc)
+{
+	struct fscrypt_completion_result *ecr = req->data;
+
+	if (rc == -EINPROGRESS)
+		return;
+
+	ecr->res = rc;
+	complete(&ecr->completion);
+}
+
+/**
+ * derive_key_aes() - Derive a key using AES-128-ECB
+ * @deriving_key: Encryption key used for derivation.
+ * @source_key:   Source key to which to apply derivation.
+ * @derived_key:  Derived key.
+ *
+ * Return: Zero on success; non-zero otherwise.
+ */
+static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
+				u8 source_key[FS_AES_256_XTS_KEY_SIZE],
+				u8 derived_key[FS_AES_256_XTS_KEY_SIZE])
+{
+	int res = 0;
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist src_sg, dst_sg;
+	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
+
+	if (IS_ERR(tfm)) {
+		res = PTR_ERR(tfm);
+		tfm = NULL;
+		goto out;
+	}
+	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		res = -ENOMEM;
+		goto out;
+	}
+	skcipher_request_set_callback(req,
+			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+			derive_crypt_complete, &ecr);
+	res = crypto_skcipher_setkey(tfm, deriving_key,
+					FS_AES_128_ECB_KEY_SIZE);
+	if (res < 0)
+		goto out;
+
+	sg_init_one(&src_sg, source_key, FS_AES_256_XTS_KEY_SIZE);
+	sg_init_one(&dst_sg, derived_key, FS_AES_256_XTS_KEY_SIZE);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
+					FS_AES_256_XTS_KEY_SIZE, NULL);
+	res = crypto_skcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+out:
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
+	return res;
+}
+
+static void put_crypt_info(struct fscrypt_info *ci)
+{
+	if (!ci)
+		return;
+
+	key_put(ci->ci_keyring_key);
+	crypto_free_skcipher(ci->ci_ctfm);
+	kmem_cache_free(fscrypt_info_cachep, ci);
+}
+
+int get_crypt_info(struct inode *inode)
+{
+	struct fscrypt_info *crypt_info;
+	u8 full_key_descriptor[FS_KEY_DESC_PREFIX_SIZE +
+				(FS_KEY_DESCRIPTOR_SIZE * 2) + 1];
+	struct key *keyring_key = NULL;
+	struct fscrypt_key *master_key;
+	struct fscrypt_context ctx;
+	const struct user_key_payload *ukp;
+	struct crypto_skcipher *ctfm;
+	const char *cipher_str;
+	u8 raw_key[FS_MAX_KEY_SIZE];
+	u8 mode;
+	int res;
+
+	res = fscrypt_initialize();
+	if (res)
+		return res;
+
+	if (!inode->i_sb->s_cop->get_context)
+		return -EOPNOTSUPP;
+retry:
+	crypt_info = ACCESS_ONCE(inode->i_crypt_info);
+	if (crypt_info) {
+		if (!crypt_info->ci_keyring_key ||
+				key_validate(crypt_info->ci_keyring_key) == 0)
+			return 0;
+		fscrypt_put_encryption_info(inode, crypt_info);
+		goto retry;
+	}
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res < 0) {
+		if (!fscrypt_dummy_context_enabled(inode))
+			return res;
+		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
+		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
+		ctx.flags = 0;
+	} else if (res != sizeof(ctx)) {
+		return -EINVAL;
+	}
+	res = 0;
+
+	crypt_info = kmem_cache_alloc(fscrypt_info_cachep, GFP_NOFS);
+	if (!crypt_info)
+		return -ENOMEM;
+
+	crypt_info->ci_flags = ctx.flags;
+	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
+	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
+	crypt_info->ci_ctfm = NULL;
+	crypt_info->ci_keyring_key = NULL;
+	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
+				sizeof(crypt_info->ci_master_key));
+	if (S_ISREG(inode->i_mode))
+		mode = crypt_info->ci_data_mode;
+	else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		mode = crypt_info->ci_filename_mode;
+	else
+		BUG();
+
+	switch (mode) {
+	case FS_ENCRYPTION_MODE_AES_256_XTS:
+		cipher_str = "xts(aes)";
+		break;
+	case FS_ENCRYPTION_MODE_AES_256_CTS:
+		cipher_str = "cts(cbc(aes))";
+		break;
+	default:
+		printk_once(KERN_WARNING
+			    "%s: unsupported key mode %d (ino %u)\n",
+			    __func__, mode, (unsigned) inode->i_ino);
+		res = -ENOKEY;
+		goto out;
+	}
+	if (fscrypt_dummy_context_enabled(inode)) {
+		memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
+		goto got_key;
+	}
+	memcpy(full_key_descriptor, FS_KEY_DESC_PREFIX,
+					FS_KEY_DESC_PREFIX_SIZE);
+	sprintf(full_key_descriptor + FS_KEY_DESC_PREFIX_SIZE,
+					"%*phN", FS_KEY_DESCRIPTOR_SIZE,
+					ctx.master_key_descriptor);
+	full_key_descriptor[FS_KEY_DESC_PREFIX_SIZE +
+					(2 * FS_KEY_DESCRIPTOR_SIZE)] = '\0';
+	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
+	if (IS_ERR(keyring_key)) {
+		res = PTR_ERR(keyring_key);
+		keyring_key = NULL;
+		goto out;
+	}
+	crypt_info->ci_keyring_key = keyring_key;
+	if (keyring_key->type != &key_type_logon) {
+		printk_once(KERN_WARNING
+				"%s: key type must be logon\n", __func__);
+		res = -ENOKEY;
+		goto out;
+	}
+	down_read(&keyring_key->sem);
+	ukp = user_key_payload(keyring_key);
+	if (ukp->datalen != sizeof(struct fscrypt_key)) {
+		res = -EINVAL;
+		up_read(&keyring_key->sem);
+		goto out;
+	}
+	master_key = (struct fscrypt_key *)ukp->data;
+	BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
+
+	if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
+		printk_once(KERN_WARNING
+				"%s: key size incorrect: %d\n",
+				__func__, master_key->size);
+		res = -ENOKEY;
+		up_read(&keyring_key->sem);
+		goto out;
+	}
+	res = derive_key_aes(ctx.nonce, master_key->raw, raw_key);
+	up_read(&keyring_key->sem);
+	if (res)
+		goto out;
+got_key:
+	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
+	if (!ctfm || IS_ERR(ctfm)) {
+		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
+		printk(KERN_DEBUG
+		       "%s: error %d (inode %u) allocating crypto tfm\n",
+		       __func__, res, (unsigned) inode->i_ino);
+		goto out;
+	}
+	crypt_info->ci_ctfm = ctfm;
+	crypto_skcipher_clear_flags(ctfm, ~0);
+	crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	res = crypto_skcipher_setkey(ctfm, raw_key, fscrypt_key_size(mode));
+	if (res)
+		goto out;
+
+	memzero_explicit(raw_key, sizeof(raw_key));
+	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) {
+		put_crypt_info(crypt_info);
+		goto retry;
+	}
+	return 0;
+
+out:
+	if (res == -ENOKEY)
+		res = 0;
+	put_crypt_info(crypt_info);
+	memzero_explicit(raw_key, sizeof(raw_key));
+	return res;
+}
+
+void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
+{
+	struct fscrypt_info *prev;
+
+	if (ci == NULL)
+		ci = ACCESS_ONCE(inode->i_crypt_info);
+	if (ci == NULL)
+		return;
+
+	prev = cmpxchg(&inode->i_crypt_info, ci, NULL);
+	if (prev != ci)
+		return;
+
+	put_crypt_info(ci);
+}
+EXPORT_SYMBOL(fscrypt_put_encryption_info);
+
+int fscrypt_get_encryption_info(struct inode *inode)
+{
+	struct fscrypt_info *ci = inode->i_crypt_info;
+
+	if (!ci ||
+		(ci->ci_keyring_key &&
+		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					       (1 << KEY_FLAG_REVOKED) |
+					       (1 << KEY_FLAG_DEAD)))))
+		return get_crypt_info(inode);
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_get_encryption_info);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
new file mode 100644
index 000000000000..0f9961eede1e
--- /dev/null
+++ b/fs/crypto/policy.c
@@ -0,0 +1,229 @@
+/*
+ * Encryption policy functions for per-file encryption support.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility.
+ *
+ * Written by Michael Halcrow, 2015.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/fscrypto.h>
+
+static int inode_has_encryption_context(struct inode *inode)
+{
+	if (!inode->i_sb->s_cop->get_context)
+		return 0;
+	return (inode->i_sb->s_cop->get_context(inode, NULL, 0L) > 0);
+}
+
+/*
+ * check whether the policy is consistent with the encryption context
+ * for the inode
+ */
+static int is_encryption_context_consistent_with_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->get_context)
+		return 0;
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res != sizeof(ctx))
+		return 0;
+
+	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
+			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+			(ctx.flags == policy->flags) &&
+			(ctx.contents_encryption_mode ==
+			 policy->contents_encryption_mode) &&
+			(ctx.filenames_encryption_mode ==
+			 policy->filenames_encryption_mode));
+}
+
+static int create_encryption_context_from_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->set_context)
+		return -EOPNOTSUPP;
+
+	if (inode->i_sb->s_cop->prepare_context) {
+		res = inode->i_sb->s_cop->prepare_context(inode);
+		if (res)
+			return res;
+	}
+
+	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
+					FS_KEY_DESCRIPTOR_SIZE);
+
+	if (!fscrypt_valid_contents_enc_mode(
+				policy->contents_encryption_mode)) {
+		printk(KERN_WARNING
+		       "%s: Invalid contents encryption mode %d\n", __func__,
+			policy->contents_encryption_mode);
+		return -EINVAL;
+	}
+
+	if (!fscrypt_valid_filenames_enc_mode(
+				policy->filenames_encryption_mode)) {
+		printk(KERN_WARNING
+			"%s: Invalid filenames encryption mode %d\n", __func__,
+			policy->filenames_encryption_mode);
+		return -EINVAL;
+	}
+
+	if (policy->flags & ~FS_POLICY_FLAGS_VALID)
+		return -EINVAL;
+
+	ctx.contents_encryption_mode = policy->contents_encryption_mode;
+	ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
+	ctx.flags = policy->flags;
+	BUILD_BUG_ON(sizeof(ctx.nonce) != FS_KEY_DERIVATION_NONCE_SIZE);
+	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+
+	return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL);
+}
+
+int fscrypt_process_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	if (policy->version != 0)
+		return -EINVAL;
+
+	if (!inode_has_encryption_context(inode)) {
+		if (!inode->i_sb->s_cop->empty_dir)
+			return -EOPNOTSUPP;
+		if (!inode->i_sb->s_cop->empty_dir(inode))
+			return -ENOTEMPTY;
+		return create_encryption_context_from_policy(inode, policy);
+	}
+
+	if (is_encryption_context_consistent_with_policy(inode, policy))
+		return 0;
+
+	printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
+	       __func__);
+	return -EINVAL;
+}
+EXPORT_SYMBOL(fscrypt_process_policy);
+
+int fscrypt_get_policy(struct inode *inode, struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->get_context ||
+			!inode->i_sb->s_cop->is_encrypted(inode))
+		return -ENODATA;
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res != sizeof(ctx))
+		return -ENODATA;
+	if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
+		return -EINVAL;
+
+	policy->version = 0;
+	policy->contents_encryption_mode = ctx.contents_encryption_mode;
+	policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
+	policy->flags = ctx.flags;
+	memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
+				FS_KEY_DESCRIPTOR_SIZE);
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_get_policy);
+
+int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
+{
+	struct fscrypt_info *parent_ci, *child_ci;
+	int res;
+
+	if ((parent == NULL) || (child == NULL)) {
+		printk(KERN_ERR	"parent %p child %p\n", parent, child);
+		BUG_ON(1);
+	}
+
+	/* no restrictions if the parent directory is not encrypted */
+	if (!parent->i_sb->s_cop->is_encrypted(parent))
+		return 1;
+	/* if the child directory is not encrypted, this is always a problem */
+	if (!parent->i_sb->s_cop->is_encrypted(child))
+		return 0;
+	res = fscrypt_get_encryption_info(parent);
+	if (res)
+		return 0;
+	res = fscrypt_get_encryption_info(child);
+	if (res)
+		return 0;
+	parent_ci = parent->i_crypt_info;
+	child_ci = child->i_crypt_info;
+	if (!parent_ci && !child_ci)
+		return 1;
+	if (!parent_ci || !child_ci)
+		return 0;
+
+	return (memcmp(parent_ci->ci_master_key,
+			child_ci->ci_master_key,
+			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
+		(parent_ci->ci_flags == child_ci->ci_flags));
+}
+EXPORT_SYMBOL(fscrypt_has_permitted_context);
+
+/**
+ * fscrypt_inherit_context() - Sets a child context from its parent
+ * @parent: Parent inode from which the context is inherited.
+ * @child:  Child inode that inherits the context from @parent.
+ * @fs_data:  private data given by FS.
+ * @preload:  preload child i_crypt_info
+ *
+ * Return: Zero on success, non-zero otherwise
+ */
+int fscrypt_inherit_context(struct inode *parent, struct inode *child,
+						void *fs_data, bool preload)
+{
+	struct fscrypt_context ctx;
+	struct fscrypt_info *ci;
+	int res;
+
+	if (!parent->i_sb->s_cop->set_context)
+		return -EOPNOTSUPP;
+
+	res = fscrypt_get_encryption_info(parent);
+	if (res < 0)
+		return res;
+
+	ci = parent->i_crypt_info;
+	if (ci == NULL)
+		return -ENOKEY;
+
+	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+	if (fscrypt_dummy_context_enabled(parent)) {
+		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
+		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
+		ctx.flags = 0;
+		memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
+		res = 0;
+	} else {
+		ctx.contents_encryption_mode = ci->ci_data_mode;
+		ctx.filenames_encryption_mode = ci->ci_filename_mode;
+		ctx.flags = ci->ci_flags;
+		memcpy(ctx.master_key_descriptor, ci->ci_master_key,
+				FS_KEY_DESCRIPTOR_SIZE);
+	}
+	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+	res = parent->i_sb->s_cop->set_context(child, &ctx,
+						sizeof(ctx), fs_data);
+	if (res)
+		return res;
+	return preload ? fscrypt_get_encryption_info(child): 0;
+}
+EXPORT_SYMBOL(fscrypt_inherit_context);
diff --git a/fs/dax.c b/fs/dax.c
index 4fd6b0c5c6b5..90322eb7498c 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -58,16 +58,35 @@ static void dax_unmap_atomic(struct block_device *bdev,
 	blk_queue_exit(bdev->bd_queue);
 }
 
+struct page *read_dax_sector(struct block_device *bdev, sector_t n)
+{
+	struct page *page = alloc_pages(GFP_KERNEL, 0);
+	struct blk_dax_ctl dax = {
+		.size = PAGE_SIZE,
+		.sector = n & ~((((int) PAGE_SIZE) / 512) - 1),
+	};
+	long rc;
+
+	if (!page)
+		return ERR_PTR(-ENOMEM);
+
+	rc = dax_map_atomic(bdev, &dax);
+	if (rc < 0)
+		return ERR_PTR(rc);
+	memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE);
+	dax_unmap_atomic(bdev, &dax);
+	return page;
+}
+
 /*
- * dax_clear_blocks() is called from within transaction context from XFS,
+ * dax_clear_sectors() is called from within transaction context from XFS,
  * and hence this means the stack from this point must follow GFP_NOFS
  * semantics for all operations.
  */
-int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
+int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
 {
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	struct blk_dax_ctl dax = {
-		.sector = block << (inode->i_blkbits - 9),
+		.sector = _sector,
 		.size = _size,
 	};
 
@@ -89,7 +108,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
 	wmb_pmem();
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dax_clear_blocks);
+EXPORT_SYMBOL_GPL(dax_clear_sectors);
 
 /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
 static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
@@ -267,8 +286,13 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
 	if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
 		inode_unlock(inode);
 
-	if ((retval > 0) && end_io)
-		end_io(iocb, pos, retval, bh.b_private);
+	if (end_io) {
+		int err;
+
+		err = end_io(iocb, pos, retval, bh.b_private);
+		if (err)
+			retval = err;
+	}
 
 	if (!(flags & DIO_SKIP_DIO_COUNT))
 		inode_dio_end(inode);
@@ -338,7 +362,8 @@ static int dax_radix_entry(struct address_space *mapping, pgoff_t index,
 	void *entry;
 
 	WARN_ON_ONCE(pmd_entry && !dirty);
-	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	if (dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
 	spin_lock_irq(&mapping->tree_lock);
 
@@ -464,11 +489,10 @@ static int dax_writeback_one(struct block_device *bdev,
  * end]. This is required by data integrity operations to ensure file data is
  * on persistent storage prior to completion of the operation.
  */
-int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
-		loff_t end)
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct block_device *bdev, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	pgoff_t start_index, end_index, pmd_index;
 	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
@@ -479,8 +503,11 @@ int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
 	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
 		return -EIO;
 
-	start_index = start >> PAGE_CACHE_SHIFT;
-	end_index = end >> PAGE_CACHE_SHIFT;
+	if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
+		return 0;
+
+	start_index = wbc->range_start >> PAGE_CACHE_SHIFT;
+	end_index = wbc->range_end >> PAGE_CACHE_SHIFT;
 	pmd_index = DAX_PMD_INDEX(start_index);
 
 	rcu_read_lock();
@@ -1034,6 +1061,7 @@ EXPORT_SYMBOL_GPL(dax_pmd_fault);
 int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct file *file = vma->vm_file;
+	int error;
 
 	/*
 	 * We pass NO_SECTOR to dax_radix_entry() because we expect that a
@@ -1043,7 +1071,13 @@ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	 * saves us from having to make a call to get_block() here to look
 	 * up the sector.
 	 */
-	dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false, true);
+	error = dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false,
+			true);
+
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (error)
+		return VM_FAULT_SIGBUS;
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
diff --git a/fs/dcache.c b/fs/dcache.c
index 92d5140de851..32ceae3e6112 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -269,9 +269,6 @@ static inline int dname_external(const struct dentry *dentry)
 	return dentry->d_name.name != dentry->d_iname;
 }
 
-/*
- * Make sure other CPUs see the inode attached before the type is set.
- */
 static inline void __d_set_inode_and_type(struct dentry *dentry,
 					  struct inode *inode,
 					  unsigned type_flags)
@@ -279,28 +276,18 @@ static inline void __d_set_inode_and_type(struct dentry *dentry,
 	unsigned flags;
 
 	dentry->d_inode = inode;
-	smp_wmb();
 	flags = READ_ONCE(dentry->d_flags);
 	flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
 	flags |= type_flags;
 	WRITE_ONCE(dentry->d_flags, flags);
 }
 
-/*
- * Ideally, we want to make sure that other CPUs see the flags cleared before
- * the inode is detached, but this is really a violation of RCU principles
- * since the ordering suggests we should always set inode before flags.
- *
- * We should instead replace or discard the entire dentry - but that sucks
- * performancewise on mass deletion/rename.
- */
 static inline void __d_clear_type_and_inode(struct dentry *dentry)
 {
 	unsigned flags = READ_ONCE(dentry->d_flags);
 
 	flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
 	WRITE_ONCE(dentry->d_flags, flags);
-	smp_wmb();
 	dentry->d_inode = NULL;
 }
 
@@ -370,9 +357,11 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	__releases(dentry->d_inode->i_lock)
 {
 	struct inode *inode = dentry->d_inode;
+
+	raw_write_seqcount_begin(&dentry->d_seq);
 	__d_clear_type_and_inode(dentry);
 	hlist_del_init(&dentry->d_u.d_alias);
-	dentry_rcuwalk_invalidate(dentry);
+	raw_write_seqcount_end(&dentry->d_seq);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
 	if (!inode->i_nlink)
@@ -1756,12 +1745,12 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	unsigned add_flags = d_flags_for_inode(inode);
 
 	spin_lock(&dentry->d_lock);
-	if (inode)
-		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
+	hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
+	raw_write_seqcount_begin(&dentry->d_seq);
 	__d_set_inode_and_type(dentry, inode, add_flags);
-	dentry_rcuwalk_invalidate(dentry);
+	raw_write_seqcount_end(&dentry->d_seq);
+	__fsnotify_d_instantiate(dentry);
 	spin_unlock(&dentry->d_lock);
-	fsnotify_d_instantiate(dentry, inode);
 }
 
 /**
@@ -1782,91 +1771,16 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 void d_instantiate(struct dentry *entry, struct inode * inode)
 {
 	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
-	if (inode)
+	if (inode) {
 		spin_lock(&inode->i_lock);
-	__d_instantiate(entry, inode);
-	if (inode)
+		__d_instantiate(entry, inode);
 		spin_unlock(&inode->i_lock);
+	}
 	security_d_instantiate(entry, inode);
 }
 EXPORT_SYMBOL(d_instantiate);
 
 /**
- * d_instantiate_unique - instantiate a non-aliased dentry
- * @entry: dentry to instantiate
- * @inode: inode to attach to this dentry
- *
- * Fill in inode information in the entry. On success, it returns NULL.
- * If an unhashed alias of "entry" already exists, then we return the
- * aliased dentry instead and drop one reference to inode.
- *
- * Note that in order to avoid conflicts with rename() etc, the caller
- * had better be holding the parent directory semaphore.
- *
- * This also assumes that the inode count has been incremented
- * (or otherwise set) by the caller to indicate that it is now
- * in use by the dcache.
- */
-static struct dentry *__d_instantiate_unique(struct dentry *entry,
-					     struct inode *inode)
-{
-	struct dentry *alias;
-	int len = entry->d_name.len;
-	const char *name = entry->d_name.name;
-	unsigned int hash = entry->d_name.hash;
-
-	if (!inode) {
-		__d_instantiate(entry, NULL);
-		return NULL;
-	}
-
-	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
-		/*
-		 * Don't need alias->d_lock here, because aliases with
-		 * d_parent == entry->d_parent are not subject to name or
-		 * parent changes, because the parent inode i_mutex is held.
-		 */
-		if (alias->d_name.hash != hash)
-			continue;
-		if (alias->d_parent != entry->d_parent)
-			continue;
-		if (alias->d_name.len != len)
-			continue;
-		if (dentry_cmp(alias, name, len))
-			continue;
-		__dget(alias);
-		return alias;
-	}
-
-	__d_instantiate(entry, inode);
-	return NULL;
-}
-
-struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
-{
-	struct dentry *result;
-
-	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
-
-	if (inode)
-		spin_lock(&inode->i_lock);
-	result = __d_instantiate_unique(entry, inode);
-	if (inode)
-		spin_unlock(&inode->i_lock);
-
-	if (!result) {
-		security_d_instantiate(entry, inode);
-		return NULL;
-	}
-
-	BUG_ON(!d_unhashed(result));
-	iput(inode);
-	return result;
-}
-
-EXPORT_SYMBOL(d_instantiate_unique);
-
-/**
  * d_instantiate_no_diralias - instantiate a non-aliased dentry
  * @entry: dentry to complete
  * @inode: inode to attach to this dentry
@@ -2446,6 +2360,86 @@ void d_rehash(struct dentry * entry)
 }
 EXPORT_SYMBOL(d_rehash);
 
+
+/* inode->i_lock held if inode is non-NULL */
+
+static inline void __d_add(struct dentry *dentry, struct inode *inode)
+{
+	if (inode) {
+		__d_instantiate(dentry, inode);
+		spin_unlock(&inode->i_lock);
+	}
+	security_d_instantiate(dentry, inode);
+	d_rehash(dentry);
+}
+
+/**
+ * d_add - add dentry to hash queues
+ * @entry: dentry to add
+ * @inode: The inode to attach to this dentry
+ *
+ * This adds the entry to the hash queues and initializes @inode.
+ * The entry was actually filled in earlier during d_alloc().
+ */
+
+void d_add(struct dentry *entry, struct inode *inode)
+{
+	if (inode)
+		spin_lock(&inode->i_lock);
+	__d_add(entry, inode);
+}
+EXPORT_SYMBOL(d_add);
+
+/**
+ * d_exact_alias - find and hash an exact unhashed alias
+ * @entry: dentry to add
+ * @inode: The inode to go with this dentry
+ *
+ * If an unhashed dentry with the same name/parent and desired
+ * inode already exists, hash and return it.  Otherwise, return
+ * NULL.
+ *
+ * Parent directory should be locked.
+ */
+struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode)
+{
+	struct dentry *alias;
+	int len = entry->d_name.len;
+	const char *name = entry->d_name.name;
+	unsigned int hash = entry->d_name.hash;
+
+	spin_lock(&inode->i_lock);
+	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
+		/*
+		 * Don't need alias->d_lock here, because aliases with
+		 * d_parent == entry->d_parent are not subject to name or
+		 * parent changes, because the parent inode i_mutex is held.
+		 */
+		if (alias->d_name.hash != hash)
+			continue;
+		if (alias->d_parent != entry->d_parent)
+			continue;
+		if (alias->d_name.len != len)
+			continue;
+		if (dentry_cmp(alias, name, len))
+			continue;
+		spin_lock(&alias->d_lock);
+		if (!d_unhashed(alias)) {
+			spin_unlock(&alias->d_lock);
+			alias = NULL;
+		} else {
+			__dget_dlock(alias);
+			_d_rehash(alias);
+			spin_unlock(&alias->d_lock);
+		}
+		spin_unlock(&inode->i_lock);
+		return alias;
+	}
+	spin_unlock(&inode->i_lock);
+	return NULL;
+}
+EXPORT_SYMBOL(d_exact_alias);
+
 /**
  * dentry_update_name_case - update case insensitive dentry with a new name
  * @dentry: dentry to be updated
@@ -2782,10 +2776,9 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
 
 	BUG_ON(!d_unhashed(dentry));
 
-	if (!inode) {
-		__d_instantiate(dentry, NULL);
+	if (!inode)
 		goto out;
-	}
+
 	spin_lock(&inode->i_lock);
 	if (S_ISDIR(inode->i_mode)) {
 		struct dentry *new = __d_find_any_alias(inode);
@@ -2819,12 +2812,8 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
 			return new;
 		}
 	}
-	/* already taking inode->i_lock, so d_add() by hand */
-	__d_instantiate(dentry, inode);
-	spin_unlock(&inode->i_lock);
 out:
-	security_d_instantiate(dentry, inode);
-	d_rehash(dentry);
+	__d_add(dentry, inode);
 	return NULL;
 }
 EXPORT_SYMBOL(d_splice_alias);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 1f107fd51328..655f21f99160 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -575,6 +575,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
 	mutex_unlock(&allocated_ptys_lock);
 }
 
+/*
+ * pty code needs to hold extra references in case of last /dev/tty close
+ */
+
+void devpts_add_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	atomic_inc(&sb->s_active);
+	ihold(ptmx_inode);
+}
+
+void devpts_del_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	iput(ptmx_inode);
+	deactivate_super(sb);
+}
+
 /**
  * devpts_pty_new -- create a new inode in /dev/pts/
  * @ptmx_inode: inode of the master
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 1b2f7ffc8b84..476f1ecbd1f0 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -253,8 +253,13 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
 	if (ret == 0)
 		ret = transferred;
 
-	if (dio->end_io && dio->result)
-		dio->end_io(dio->iocb, offset, transferred, dio->private);
+	if (dio->end_io) {
+		int err;
+
+		err = dio->end_io(dio->iocb, offset, ret, dio->private);
+		if (err)
+			ret = err;
+	}
 
 	if (!(dio->flags & DIO_SKIP_DIO_COUNT))
 		inode_dio_end(dio->inode);
@@ -445,7 +450,8 @@ static struct bio *dio_await_one(struct dio *dio)
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		dio->waiter = current;
 		spin_unlock_irqrestore(&dio->bio_lock, flags);
-		if (!blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie))
+		if (!(dio->iocb->ki_flags & IOCB_HIPRI) ||
+		    !blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie))
 			io_schedule();
 		/* wake up sets us TASK_RUNNING */
 		spin_lock_irqsave(&dio->bio_lock, flags);
@@ -472,8 +478,8 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
 		dio->io_error = -EIO;
 
 	if (dio->is_async && dio->rw == READ && dio->should_dirty) {
-		bio_check_pages_dirty(bio);	/* transfers ownership */
 		err = bio->bi_error;
+		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
 			struct page *page = bvec->bv_page;
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index 8e294fbbac39..519112168a9e 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -346,7 +346,6 @@ static struct config_group *make_cluster(struct config_group *g,
 	void *gps = NULL;
 
 	cl = kzalloc(sizeof(struct dlm_cluster), GFP_NOFS);
-	gps = kcalloc(3, sizeof(struct config_group *), GFP_NOFS);
 	sps = kzalloc(sizeof(struct dlm_spaces), GFP_NOFS);
 	cms = kzalloc(sizeof(struct dlm_comms), GFP_NOFS);
 
@@ -357,10 +356,8 @@ static struct config_group *make_cluster(struct config_group *g,
 	config_group_init_type_name(&sps->ss_group, "spaces", &spaces_type);
 	config_group_init_type_name(&cms->cs_group, "comms", &comms_type);
 
-	cl->group.default_groups = gps;
-	cl->group.default_groups[0] = &sps->ss_group;
-	cl->group.default_groups[1] = &cms->cs_group;
-	cl->group.default_groups[2] = NULL;
+	configfs_add_default_group(&sps->ss_group, &cl->group);
+	configfs_add_default_group(&cms->cs_group, &cl->group);
 
 	cl->cl_tcp_port = dlm_config.ci_tcp_port;
 	cl->cl_buffer_size = dlm_config.ci_buffer_size;
@@ -383,7 +380,6 @@ static struct config_group *make_cluster(struct config_group *g,
 
  fail:
 	kfree(cl);
-	kfree(gps);
 	kfree(sps);
 	kfree(cms);
 	return ERR_PTR(-ENOMEM);
@@ -392,14 +388,8 @@ static struct config_group *make_cluster(struct config_group *g,
 static void drop_cluster(struct config_group *g, struct config_item *i)
 {
 	struct dlm_cluster *cl = config_item_to_cluster(i);
-	struct config_item *tmp;
-	int j;
 
-	for (j = 0; cl->group.default_groups[j]; j++) {
-		tmp = &cl->group.default_groups[j]->cg_item;
-		cl->group.default_groups[j] = NULL;
-		config_item_put(tmp);
-	}
+	configfs_remove_default_groups(&cl->group);
 
 	space_list = NULL;
 	comm_list = NULL;
@@ -410,7 +400,6 @@ static void drop_cluster(struct config_group *g, struct config_item *i)
 static void release_cluster(struct config_item *i)
 {
 	struct dlm_cluster *cl = config_item_to_cluster(i);
-	kfree(cl->group.default_groups);
 	kfree(cl);
 }
 
@@ -418,21 +407,17 @@ static struct config_group *make_space(struct config_group *g, const char *name)
 {
 	struct dlm_space *sp = NULL;
 	struct dlm_nodes *nds = NULL;
-	void *gps = NULL;
 
 	sp = kzalloc(sizeof(struct dlm_space), GFP_NOFS);
-	gps = kcalloc(2, sizeof(struct config_group *), GFP_NOFS);
 	nds = kzalloc(sizeof(struct dlm_nodes), GFP_NOFS);
 
-	if (!sp || !gps || !nds)
+	if (!sp || !nds)
 		goto fail;
 
 	config_group_init_type_name(&sp->group, name, &space_type);
-	config_group_init_type_name(&nds->ns_group, "nodes", &nodes_type);
 
-	sp->group.default_groups = gps;
-	sp->group.default_groups[0] = &nds->ns_group;
-	sp->group.default_groups[1] = NULL;
+	config_group_init_type_name(&nds->ns_group, "nodes", &nodes_type);
+	configfs_add_default_group(&nds->ns_group, &sp->group);
 
 	INIT_LIST_HEAD(&sp->members);
 	mutex_init(&sp->members_lock);
@@ -441,7 +426,6 @@ static struct config_group *make_space(struct config_group *g, const char *name)
 
  fail:
 	kfree(sp);
-	kfree(gps);
 	kfree(nds);
 	return ERR_PTR(-ENOMEM);
 }
@@ -449,24 +433,16 @@ static struct config_group *make_space(struct config_group *g, const char *name)
 static void drop_space(struct config_group *g, struct config_item *i)
 {
 	struct dlm_space *sp = config_item_to_space(i);
-	struct config_item *tmp;
-	int j;
 
 	/* assert list_empty(&sp->members) */
 
-	for (j = 0; sp->group.default_groups[j]; j++) {
-		tmp = &sp->group.default_groups[j]->cg_item;
-		sp->group.default_groups[j] = NULL;
-		config_item_put(tmp);
-	}
-
+	configfs_remove_default_groups(&sp->group);
 	config_item_put(i);
 }
 
 static void release_space(struct config_item *i)
 {
 	struct dlm_space *sp = config_item_to_space(i);
-	kfree(sp->group.default_groups);
 	kfree(sp);
 }
 
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 3a37bd3f9637..00640e70ed7a 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -124,7 +124,10 @@ struct connection {
 	struct connection *othercon;
 	struct work_struct rwork; /* Receive workqueue */
 	struct work_struct swork; /* Send workqueue */
-	void (*orig_error_report)(struct sock *sk);
+	void (*orig_error_report)(struct sock *);
+	void (*orig_data_ready)(struct sock *);
+	void (*orig_state_change)(struct sock *);
+	void (*orig_write_space)(struct sock *);
 };
 #define sock2con(x) ((struct connection *)(x)->sk_user_data)
 
@@ -467,16 +470,24 @@ int dlm_lowcomms_connect_node(int nodeid)
 
 static void lowcomms_error_report(struct sock *sk)
 {
-	struct connection *con = sock2con(sk);
+	struct connection *con;
 	struct sockaddr_storage saddr;
+	int buflen;
+	void (*orig_report)(struct sock *) = NULL;
 
-	if (nodeid_to_addr(con->nodeid, &saddr, NULL, false)) {
+	read_lock_bh(&sk->sk_callback_lock);
+	con = sock2con(sk);
+	if (con == NULL)
+		goto out;
+
+	orig_report = con->orig_error_report;
+	if (con->sock == NULL ||
+	    kernel_getpeername(con->sock, (struct sockaddr *)&saddr, &buflen)) {
 		printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
 				   "sending to node %d, port %d, "
 				   "sk_err=%d/%d\n", dlm_our_nodeid(),
 				   con->nodeid, dlm_config.ci_tcp_port,
 				   sk->sk_err, sk->sk_err_soft);
-		return;
 	} else if (saddr.ss_family == AF_INET) {
 		struct sockaddr_in *sin4 = (struct sockaddr_in *)&saddr;
 
@@ -499,22 +510,54 @@ static void lowcomms_error_report(struct sock *sk)
 				   dlm_config.ci_tcp_port, sk->sk_err,
 				   sk->sk_err_soft);
 	}
-	con->orig_error_report(sk);
+out:
+	read_unlock_bh(&sk->sk_callback_lock);
+	if (orig_report)
+		orig_report(sk);
+}
+
+/* Note: sk_callback_lock must be locked before calling this function. */
+static void save_callbacks(struct connection *con, struct sock *sk)
+{
+	lock_sock(sk);
+	con->orig_data_ready = sk->sk_data_ready;
+	con->orig_state_change = sk->sk_state_change;
+	con->orig_write_space = sk->sk_write_space;
+	con->orig_error_report = sk->sk_error_report;
+	release_sock(sk);
+}
+
+static void restore_callbacks(struct connection *con, struct sock *sk)
+{
+	write_lock_bh(&sk->sk_callback_lock);
+	lock_sock(sk);
+	sk->sk_user_data = NULL;
+	sk->sk_data_ready = con->orig_data_ready;
+	sk->sk_state_change = con->orig_state_change;
+	sk->sk_write_space = con->orig_write_space;
+	sk->sk_error_report = con->orig_error_report;
+	release_sock(sk);
+	write_unlock_bh(&sk->sk_callback_lock);
 }
 
 /* Make a socket active */
 static void add_sock(struct socket *sock, struct connection *con)
 {
+	struct sock *sk = sock->sk;
+
+	write_lock_bh(&sk->sk_callback_lock);
 	con->sock = sock;
 
+	sk->sk_user_data = con;
+	if (!test_bit(CF_IS_OTHERCON, &con->flags))
+		save_callbacks(con, sk);
 	/* Install a data_ready callback */
-	con->sock->sk->sk_data_ready = lowcomms_data_ready;
-	con->sock->sk->sk_write_space = lowcomms_write_space;
-	con->sock->sk->sk_state_change = lowcomms_state_change;
-	con->sock->sk->sk_user_data = con;
-	con->sock->sk->sk_allocation = GFP_NOFS;
-	con->orig_error_report = con->sock->sk->sk_error_report;
-	con->sock->sk->sk_error_report = lowcomms_error_report;
+	sk->sk_data_ready = lowcomms_data_ready;
+	sk->sk_write_space = lowcomms_write_space;
+	sk->sk_state_change = lowcomms_state_change;
+	sk->sk_allocation = GFP_NOFS;
+	sk->sk_error_report = lowcomms_error_report;
+	write_unlock_bh(&sk->sk_callback_lock);
 }
 
 /* Add the port number to an IPv6 or 4 sockaddr and return the address
@@ -549,6 +592,8 @@ static void close_connection(struct connection *con, bool and_other,
 
 	mutex_lock(&con->sock_mutex);
 	if (con->sock) {
+		if (!test_bit(CF_IS_OTHERCON, &con->flags))
+			restore_callbacks(con, con->sock->sk);
 		sock_release(con->sock);
 		con->sock = NULL;
 	}
@@ -1190,6 +1235,8 @@ static struct socket *tcp_create_listen_sock(struct connection *con,
 	if (result < 0) {
 		log_print("Failed to set SO_REUSEADDR on socket: %d", result);
 	}
+	sock->sk->sk_user_data = con;
+
 	con->rx_action = tcp_accept_from_sock;
 	con->connect_action = tcp_connect_to_sock;
 
@@ -1271,6 +1318,7 @@ static int sctp_listen_for_all(void)
 	if (result < 0)
 		log_print("Could not set SCTP NODELAY error %d\n", result);
 
+	write_lock_bh(&sock->sk->sk_callback_lock);
 	/* Init con struct */
 	sock->sk->sk_user_data = con;
 	con->sock = sock;
@@ -1278,6 +1326,8 @@ static int sctp_listen_for_all(void)
 	con->rx_action = sctp_accept_from_sock;
 	con->connect_action = sctp_connect_to_sock;
 
+	write_unlock_bh(&sock->sk->sk_callback_lock);
+
 	/* Bind to all addresses. */
 	if (sctp_bind_addrs(con, dlm_config.ci_tcp_port))
 		goto create_delsock;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 80d6901493cf..64026e53722a 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -23,6 +23,8 @@
  * 02111-1307, USA.
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
@@ -30,7 +32,6 @@
 #include <linux/compiler.h>
 #include <linux/key.h>
 #include <linux/namei.h>
-#include <linux/crypto.h>
 #include <linux/file.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
@@ -74,6 +75,19 @@ void ecryptfs_from_hex(char *dst, char *src, int dst_size)
 	}
 }
 
+static int ecryptfs_hash_digest(struct crypto_shash *tfm,
+				char *src, int len, char *dst)
+{
+	SHASH_DESC_ON_STACK(desc, tfm);
+	int err;
+
+	desc->tfm = tfm;
+	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = crypto_shash_digest(desc, src, len, dst);
+	shash_desc_zero(desc);
+	return err;
+}
+
 /**
  * ecryptfs_calculate_md5 - calculates the md5 of @src
  * @dst: Pointer to 16 bytes of allocated memory
@@ -88,45 +102,26 @@ static int ecryptfs_calculate_md5(char *dst,
 				  struct ecryptfs_crypt_stat *crypt_stat,
 				  char *src, int len)
 {
-	struct scatterlist sg;
-	struct hash_desc desc = {
-		.tfm = crypt_stat->hash_tfm,
-		.flags = CRYPTO_TFM_REQ_MAY_SLEEP
-	};
+	struct crypto_shash *tfm;
 	int rc = 0;
 
 	mutex_lock(&crypt_stat->cs_hash_tfm_mutex);
-	sg_init_one(&sg, (u8 *)src, len);
-	if (!desc.tfm) {
-		desc.tfm = crypto_alloc_hash(ECRYPTFS_DEFAULT_HASH, 0,
-					     CRYPTO_ALG_ASYNC);
-		if (IS_ERR(desc.tfm)) {
-			rc = PTR_ERR(desc.tfm);
+	tfm = crypt_stat->hash_tfm;
+	if (!tfm) {
+		tfm = crypto_alloc_shash(ECRYPTFS_DEFAULT_HASH, 0, 0);
+		if (IS_ERR(tfm)) {
+			rc = PTR_ERR(tfm);
 			ecryptfs_printk(KERN_ERR, "Error attempting to "
 					"allocate crypto context; rc = [%d]\n",
 					rc);
 			goto out;
 		}
-		crypt_stat->hash_tfm = desc.tfm;
-	}
-	rc = crypto_hash_init(&desc);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error initializing crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out;
+		crypt_stat->hash_tfm = tfm;
 	}
-	rc = crypto_hash_update(&desc, &sg, len);
+	rc = ecryptfs_hash_digest(tfm, src, len, dst);
 	if (rc) {
 		printk(KERN_ERR
-		       "%s: Error updating crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out;
-	}
-	rc = crypto_hash_final(&desc, dst);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error finalizing crypto hash; rc = [%d]\n",
+		       "%s: Error computing crypto hash; rc = [%d]\n",
 		       __func__, rc);
 		goto out;
 	}
@@ -234,10 +229,8 @@ void ecryptfs_destroy_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat)
 {
 	struct ecryptfs_key_sig *key_sig, *key_sig_tmp;
 
-	if (crypt_stat->tfm)
-		crypto_free_ablkcipher(crypt_stat->tfm);
-	if (crypt_stat->hash_tfm)
-		crypto_free_hash(crypt_stat->hash_tfm);
+	crypto_free_skcipher(crypt_stat->tfm);
+	crypto_free_shash(crypt_stat->hash_tfm);
 	list_for_each_entry_safe(key_sig, key_sig_tmp,
 				 &crypt_stat->keysig_list, crypt_stat_list) {
 		list_del(&key_sig->crypt_stat_list);
@@ -342,7 +335,7 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 			     struct scatterlist *src_sg, int size,
 			     unsigned char *iv, int op)
 {
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	struct extent_crypt_result ecr;
 	int rc = 0;
 
@@ -358,20 +351,20 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 	init_completion(&ecr.completion);
 
 	mutex_lock(&crypt_stat->cs_tfm_mutex);
-	req = ablkcipher_request_alloc(crypt_stat->tfm, GFP_NOFS);
+	req = skcipher_request_alloc(crypt_stat->tfm, GFP_NOFS);
 	if (!req) {
 		mutex_unlock(&crypt_stat->cs_tfm_mutex);
 		rc = -ENOMEM;
 		goto out;
 	}
 
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			extent_crypt_complete, &ecr);
 	/* Consider doing this once, when the file is opened */
 	if (!(crypt_stat->flags & ECRYPTFS_KEY_SET)) {
-		rc = crypto_ablkcipher_setkey(crypt_stat->tfm, crypt_stat->key,
-					      crypt_stat->key_size);
+		rc = crypto_skcipher_setkey(crypt_stat->tfm, crypt_stat->key,
+					    crypt_stat->key_size);
 		if (rc) {
 			ecryptfs_printk(KERN_ERR,
 					"Error setting key; rc = [%d]\n",
@@ -383,9 +376,9 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 		crypt_stat->flags |= ECRYPTFS_KEY_SET;
 	}
 	mutex_unlock(&crypt_stat->cs_tfm_mutex);
-	ablkcipher_request_set_crypt(req, src_sg, dst_sg, size, iv);
-	rc = op == ENCRYPT ? crypto_ablkcipher_encrypt(req) :
-			     crypto_ablkcipher_decrypt(req);
+	skcipher_request_set_crypt(req, src_sg, dst_sg, size, iv);
+	rc = op == ENCRYPT ? crypto_skcipher_encrypt(req) :
+			     crypto_skcipher_decrypt(req);
 	if (rc == -EINPROGRESS || rc == -EBUSY) {
 		struct extent_crypt_result *ecr = req->base.data;
 
@@ -394,7 +387,7 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 		reinit_completion(&ecr->completion);
 	}
 out:
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	return rc;
 }
 
@@ -622,7 +615,7 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat)
 						    crypt_stat->cipher, "cbc");
 	if (rc)
 		goto out_unlock;
-	crypt_stat->tfm = crypto_alloc_ablkcipher(full_alg_name, 0, 0);
+	crypt_stat->tfm = crypto_alloc_skcipher(full_alg_name, 0, 0);
 	if (IS_ERR(crypt_stat->tfm)) {
 		rc = PTR_ERR(crypt_stat->tfm);
 		crypt_stat->tfm = NULL;
@@ -631,7 +624,7 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat)
 				full_alg_name);
 		goto out_free;
 	}
-	crypto_ablkcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	crypto_skcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY);
 	rc = 0;
 out_free:
 	kfree(full_alg_name);
@@ -1499,16 +1492,14 @@ out:
  */
 static int
 ecryptfs_encrypt_filename(struct ecryptfs_filename *filename,
-			  struct ecryptfs_crypt_stat *crypt_stat,
 			  struct ecryptfs_mount_crypt_stat *mount_crypt_stat)
 {
 	int rc = 0;
 
 	filename->encrypted_filename = NULL;
 	filename->encrypted_filename_size = 0;
-	if ((crypt_stat && (crypt_stat->flags & ECRYPTFS_ENCFN_USE_MOUNT_FNEK))
-	    || (mount_crypt_stat && (mount_crypt_stat->flags
-				     & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))) {
+	if (mount_crypt_stat && (mount_crypt_stat->flags
+				     & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) {
 		size_t packet_size;
 		size_t remaining_bytes;
 
@@ -1591,7 +1582,7 @@ out:
  * event, regardless of whether this function succeeds for fails.
  */
 static int
-ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
+ecryptfs_process_key_cipher(struct crypto_skcipher **key_tfm,
 			    char *cipher_name, size_t *key_size)
 {
 	char dummy_key[ECRYPTFS_MAX_KEY_BYTES];
@@ -1609,21 +1600,18 @@ ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
 						    "ecb");
 	if (rc)
 		goto out;
-	*key_tfm = crypto_alloc_blkcipher(full_alg_name, 0, CRYPTO_ALG_ASYNC);
+	*key_tfm = crypto_alloc_skcipher(full_alg_name, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(*key_tfm)) {
 		rc = PTR_ERR(*key_tfm);
 		printk(KERN_ERR "Unable to allocate crypto cipher with name "
 		       "[%s]; rc = [%d]\n", full_alg_name, rc);
 		goto out;
 	}
-	crypto_blkcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	if (*key_size == 0) {
-		struct blkcipher_alg *alg = crypto_blkcipher_alg(*key_tfm);
-
-		*key_size = alg->max_keysize;
-	}
+	crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	if (*key_size == 0)
+		*key_size = crypto_skcipher_default_keysize(*key_tfm);
 	get_random_bytes(dummy_key, *key_size);
-	rc = crypto_blkcipher_setkey(*key_tfm, dummy_key, *key_size);
+	rc = crypto_skcipher_setkey(*key_tfm, dummy_key, *key_size);
 	if (rc) {
 		printk(KERN_ERR "Error attempting to set key of size [%zd] for "
 		       "cipher [%s]; rc = [%d]\n", *key_size, full_alg_name,
@@ -1660,8 +1648,7 @@ int ecryptfs_destroy_crypto(void)
 	list_for_each_entry_safe(key_tfm, key_tfm_tmp, &key_tfm_list,
 				 key_tfm_list) {
 		list_del(&key_tfm->key_tfm_list);
-		if (key_tfm->key_tfm)
-			crypto_free_blkcipher(key_tfm->key_tfm);
+		crypto_free_skcipher(key_tfm->key_tfm);
 		kmem_cache_free(ecryptfs_key_tfm_cache, key_tfm);
 	}
 	mutex_unlock(&key_tfm_list_mutex);
@@ -1747,7 +1734,7 @@ int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm)
  * Searches for cached item first, and creates new if not found.
  * Returns 0 on success, non-zero if adding new cipher failed
  */
-int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm,
+int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_skcipher **tfm,
 					       struct mutex **tfm_mutex,
 					       char *cipher_name)
 {
@@ -1944,7 +1931,6 @@ out:
 int ecryptfs_encrypt_and_encode_filename(
 	char **encoded_name,
 	size_t *encoded_name_size,
-	struct ecryptfs_crypt_stat *crypt_stat,
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat,
 	const char *name, size_t name_size)
 {
@@ -1953,9 +1939,8 @@ int ecryptfs_encrypt_and_encode_filename(
 
 	(*encoded_name) = NULL;
 	(*encoded_name_size) = 0;
-	if ((crypt_stat && (crypt_stat->flags & ECRYPTFS_ENCRYPT_FILENAMES))
-	    || (mount_crypt_stat && (mount_crypt_stat->flags
-				     & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES))) {
+	if (mount_crypt_stat && (mount_crypt_stat->flags
+				     & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) {
 		struct ecryptfs_filename *filename;
 
 		filename = kzalloc(sizeof(*filename), GFP_KERNEL);
@@ -1968,8 +1953,7 @@ int ecryptfs_encrypt_and_encode_filename(
 		}
 		filename->filename = (char *)name;
 		filename->filename_size = name_size;
-		rc = ecryptfs_encrypt_filename(filename, crypt_stat,
-					       mount_crypt_stat);
+		rc = ecryptfs_encrypt_filename(filename, mount_crypt_stat);
 		if (rc) {
 			printk(KERN_ERR "%s: Error attempting to encrypt "
 			       "filename; rc = [%d]\n", __func__, rc);
@@ -1980,11 +1964,9 @@ int ecryptfs_encrypt_and_encode_filename(
 			NULL, &encoded_name_no_prefix_size,
 			filename->encrypted_filename,
 			filename->encrypted_filename_size);
-		if ((crypt_stat && (crypt_stat->flags
-				    & ECRYPTFS_ENCFN_USE_MOUNT_FNEK))
-		    || (mount_crypt_stat
+		if (mount_crypt_stat
 			&& (mount_crypt_stat->flags
-			    & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)))
+			    & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))
 			(*encoded_name_size) =
 				(ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE
 				 + encoded_name_no_prefix_size);
@@ -2002,11 +1984,9 @@ int ecryptfs_encrypt_and_encode_filename(
 			kfree(filename);
 			goto out;
 		}
-		if ((crypt_stat && (crypt_stat->flags
-				    & ECRYPTFS_ENCFN_USE_MOUNT_FNEK))
-		    || (mount_crypt_stat
+		if (mount_crypt_stat
 			&& (mount_crypt_stat->flags
-			    & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))) {
+			    & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) {
 			memcpy((*encoded_name),
 			       ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX,
 			       ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE);
@@ -2120,7 +2100,7 @@ out:
 int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
 			   struct ecryptfs_mount_crypt_stat *mount_crypt_stat)
 {
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *tfm;
 	struct mutex *tfm_mutex;
 	size_t cipher_blocksize;
 	int rc;
@@ -2130,7 +2110,7 @@ int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
 		return 0;
 	}
 
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&desc.tfm, &tfm_mutex,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&tfm, &tfm_mutex,
 			mount_crypt_stat->global_default_fn_cipher_name);
 	if (unlikely(rc)) {
 		(*namelen) = 0;
@@ -2138,7 +2118,7 @@ int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
 	}
 
 	mutex_lock(tfm_mutex);
-	cipher_blocksize = crypto_blkcipher_blocksize(desc.tfm);
+	cipher_blocksize = crypto_skcipher_blocksize(tfm);
 	mutex_unlock(tfm_mutex);
 
 	/* Return an exact amount for the common cases */
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 7b39260c7bba..d123fbaa28e0 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -28,6 +28,7 @@
 #ifndef ECRYPTFS_KERNEL_H
 #define ECRYPTFS_KERNEL_H
 
+#include <crypto/skcipher.h>
 #include <keys/user-type.h>
 #include <keys/encrypted-type.h>
 #include <linux/fs.h>
@@ -38,7 +39,6 @@
 #include <linux/nsproxy.h>
 #include <linux/backing-dev.h>
 #include <linux/ecryptfs.h>
-#include <linux/crypto.h>
 
 #define ECRYPTFS_DEFAULT_IV_BYTES 16
 #define ECRYPTFS_DEFAULT_EXTENT_SIZE 4096
@@ -233,9 +233,9 @@ struct ecryptfs_crypt_stat {
 	size_t extent_shift;
 	unsigned int extent_mask;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
-	struct crypto_ablkcipher *tfm;
-	struct crypto_hash *hash_tfm; /* Crypto context for generating
-				       * the initialization vectors */
+	struct crypto_skcipher *tfm;
+	struct crypto_shash *hash_tfm; /* Crypto context for generating
+					* the initialization vectors */
 	unsigned char cipher[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
 	unsigned char key[ECRYPTFS_MAX_KEY_BYTES];
 	unsigned char root_iv[ECRYPTFS_MAX_IV_BYTES];
@@ -309,7 +309,7 @@ struct ecryptfs_global_auth_tok {
  * keeps a list of crypto API contexts around to use when needed.
  */
 struct ecryptfs_key_tfm {
-	struct crypto_blkcipher *key_tfm;
+	struct crypto_skcipher *key_tfm;
 	size_t key_size;
 	struct mutex key_tfm_mutex;
 	struct list_head key_tfm_list;
@@ -569,7 +569,6 @@ int ecryptfs_fill_zeros(struct file *file, loff_t new_length);
 int ecryptfs_encrypt_and_encode_filename(
 	char **encoded_name,
 	size_t *encoded_name_size,
-	struct ecryptfs_crypt_stat *crypt_stat,
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat,
 	const char *name, size_t name_size);
 struct dentry *ecryptfs_lower_dentry(struct dentry *this_dentry);
@@ -659,7 +658,7 @@ ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name,
 int ecryptfs_init_crypto(void);
 int ecryptfs_destroy_crypto(void);
 int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm);
-int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm,
+int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_skcipher **tfm,
 					       struct mutex **tfm_mutex,
 					       char *cipher_name);
 int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 4e685ac1024d..121114e9a464 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -29,7 +29,6 @@
 #include <linux/dcache.h>
 #include <linux/namei.h>
 #include <linux/mount.h>
-#include <linux/crypto.h>
 #include <linux/fs_stack.h>
 #include <linux/slab.h>
 #include <linux/xattr.h>
@@ -397,11 +396,9 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 	int rc = 0;
 
 	lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent);
-	inode_lock(d_inode(lower_dir_dentry));
-	lower_dentry = lookup_one_len(ecryptfs_dentry->d_name.name,
+	lower_dentry = lookup_one_len_unlocked(ecryptfs_dentry->d_name.name,
 				      lower_dir_dentry,
 				      ecryptfs_dentry->d_name.len);
-	inode_unlock(d_inode(lower_dir_dentry));
 	if (IS_ERR(lower_dentry)) {
 		rc = PTR_ERR(lower_dentry);
 		ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
@@ -419,18 +416,16 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 	dput(lower_dentry);
 	rc = ecryptfs_encrypt_and_encode_filename(
 		&encrypted_and_encoded_name, &encrypted_and_encoded_name_size,
-		NULL, mount_crypt_stat, ecryptfs_dentry->d_name.name,
+		mount_crypt_stat, ecryptfs_dentry->d_name.name,
 		ecryptfs_dentry->d_name.len);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to encrypt and encode "
 		       "filename; rc = [%d]\n", __func__, rc);
 		goto out;
 	}
-	inode_lock(d_inode(lower_dir_dentry));
-	lower_dentry = lookup_one_len(encrypted_and_encoded_name,
+	lower_dentry = lookup_one_len_unlocked(encrypted_and_encoded_name,
 				      lower_dir_dentry,
 				      encrypted_and_encoded_name_size);
-	inode_unlock(d_inode(lower_dir_dentry));
 	if (IS_ERR(lower_dentry)) {
 		rc = PTR_ERR(lower_dentry);
 		ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
@@ -502,7 +497,6 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
 		dir->i_sb)->mount_crypt_stat;
 	rc = ecryptfs_encrypt_and_encode_filename(&encoded_symname,
 						  &encoded_symlen,
-						  NULL,
 						  mount_crypt_stat, symname,
 						  strlen(symname));
 	if (rc)
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 6bd67e2011f0..9893d1538122 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -25,11 +25,12 @@
  * 02111-1307, USA.
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/string.h>
 #include <linux/pagemap.h>
 #include <linux/key.h>
 #include <linux/random.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include "ecryptfs_kernel.h"
@@ -601,12 +602,13 @@ struct ecryptfs_write_tag_70_packet_silly_stack {
 	struct ecryptfs_auth_tok *auth_tok;
 	struct scatterlist src_sg[2];
 	struct scatterlist dst_sg[2];
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *skcipher_tfm;
+	struct skcipher_request *skcipher_req;
 	char iv[ECRYPTFS_MAX_IV_BYTES];
 	char hash[ECRYPTFS_TAG_70_DIGEST_SIZE];
 	char tmp_hash[ECRYPTFS_TAG_70_DIGEST_SIZE];
-	struct hash_desc hash_desc;
-	struct scatterlist hash_sg;
+	struct crypto_shash *hash_tfm;
+	struct shash_desc *hash_desc;
 };
 
 /**
@@ -629,14 +631,12 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	struct key *auth_tok_key = NULL;
 	int rc = 0;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = kzalloc(sizeof(*s), GFP_KERNEL);
 	if (!s) {
 		printk(KERN_ERR "%s: Out of memory whilst trying to kmalloc "
 		       "[%zd] bytes of kernel memory\n", __func__, sizeof(*s));
-		rc = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
-	s->desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	(*packet_size) = 0;
 	rc = ecryptfs_find_auth_tok_for_sig(
 		&auth_tok_key,
@@ -649,7 +649,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(
-		&s->desc.tfm,
+		&s->skcipher_tfm,
 		&s->tfm_mutex, mount_crypt_stat->global_default_fn_cipher_name);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Internal error whilst attempting to get "
@@ -658,7 +658,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	mutex_lock(s->tfm_mutex);
-	s->block_size = crypto_blkcipher_blocksize(s->desc.tfm);
+	s->block_size = crypto_skcipher_blocksize(s->skcipher_tfm);
 	/* Plus one for the \0 separator between the random prefix
 	 * and the plaintext filename */
 	s->num_rand_bytes = (ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES + 1);
@@ -691,6 +691,19 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		rc = -EINVAL;
 		goto out_unlock;
 	}
+
+	s->skcipher_req = skcipher_request_alloc(s->skcipher_tfm, GFP_KERNEL);
+	if (!s->skcipher_req) {
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "skcipher_request_alloc for %s\n", __func__,
+		       crypto_skcipher_driver_name(s->skcipher_tfm));
+		rc = -ENOMEM;
+		goto out_unlock;
+	}
+
+	skcipher_request_set_callback(s->skcipher_req,
+				      CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+
 	s->block_aligned_filename = kzalloc(s->block_aligned_filename_size,
 					    GFP_KERNEL);
 	if (!s->block_aligned_filename) {
@@ -700,7 +713,6 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		rc = -ENOMEM;
 		goto out_unlock;
 	}
-	s->i = 0;
 	dest[s->i++] = ECRYPTFS_TAG_70_PACKET_TYPE;
 	rc = ecryptfs_write_packet_length(&dest[s->i],
 					  (ECRYPTFS_SIG_SIZE
@@ -738,40 +750,36 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		       "password tokens\n", __func__);
 		goto out_free_unlock;
 	}
-	sg_init_one(
-		&s->hash_sg,
-		(u8 *)s->auth_tok->token.password.session_key_encryption_key,
-		s->auth_tok->token.password.session_key_encryption_key_bytes);
-	s->hash_desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-	s->hash_desc.tfm = crypto_alloc_hash(ECRYPTFS_TAG_70_DIGEST, 0,
-					     CRYPTO_ALG_ASYNC);
-	if (IS_ERR(s->hash_desc.tfm)) {
-			rc = PTR_ERR(s->hash_desc.tfm);
+	s->hash_tfm = crypto_alloc_shash(ECRYPTFS_TAG_70_DIGEST, 0, 0);
+	if (IS_ERR(s->hash_tfm)) {
+			rc = PTR_ERR(s->hash_tfm);
 			printk(KERN_ERR "%s: Error attempting to "
 			       "allocate hash crypto context; rc = [%d]\n",
 			       __func__, rc);
 			goto out_free_unlock;
 	}
-	rc = crypto_hash_init(&s->hash_desc);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error initializing crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out_release_free_unlock;
-	}
-	rc = crypto_hash_update(
-		&s->hash_desc, &s->hash_sg,
-		s->auth_tok->token.password.session_key_encryption_key_bytes);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error updating crypto hash; rc = [%d]\n",
-		       __func__, rc);
+
+	s->hash_desc = kmalloc(sizeof(*s->hash_desc) +
+			       crypto_shash_descsize(s->hash_tfm), GFP_KERNEL);
+	if (!s->hash_desc) {
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "kmalloc [%zd] bytes\n", __func__,
+		       sizeof(*s->hash_desc) +
+		       crypto_shash_descsize(s->hash_tfm));
+		rc = -ENOMEM;
 		goto out_release_free_unlock;
 	}
-	rc = crypto_hash_final(&s->hash_desc, s->hash);
+
+	s->hash_desc->tfm = s->hash_tfm;
+	s->hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	rc = crypto_shash_digest(s->hash_desc,
+				 (u8 *)s->auth_tok->token.password.session_key_encryption_key,
+				 s->auth_tok->token.password.session_key_encryption_key_bytes,
+				 s->hash);
 	if (rc) {
 		printk(KERN_ERR
-		       "%s: Error finalizing crypto hash; rc = [%d]\n",
+		       "%s: Error computing crypto hash; rc = [%d]\n",
 		       __func__, rc);
 		goto out_release_free_unlock;
 	}
@@ -780,27 +788,12 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 			s->hash[(s->j % ECRYPTFS_TAG_70_DIGEST_SIZE)];
 		if ((s->j % ECRYPTFS_TAG_70_DIGEST_SIZE)
 		    == (ECRYPTFS_TAG_70_DIGEST_SIZE - 1)) {
-			sg_init_one(&s->hash_sg, (u8 *)s->hash,
-				    ECRYPTFS_TAG_70_DIGEST_SIZE);
-			rc = crypto_hash_init(&s->hash_desc);
-			if (rc) {
-				printk(KERN_ERR
-				       "%s: Error initializing crypto hash; "
-				       "rc = [%d]\n", __func__, rc);
-				goto out_release_free_unlock;
-			}
-			rc = crypto_hash_update(&s->hash_desc, &s->hash_sg,
-						ECRYPTFS_TAG_70_DIGEST_SIZE);
+			rc = crypto_shash_digest(s->hash_desc, (u8 *)s->hash,
+						ECRYPTFS_TAG_70_DIGEST_SIZE,
+						s->tmp_hash);
 			if (rc) {
 				printk(KERN_ERR
-				       "%s: Error updating crypto hash; "
-				       "rc = [%d]\n", __func__, rc);
-				goto out_release_free_unlock;
-			}
-			rc = crypto_hash_final(&s->hash_desc, s->tmp_hash);
-			if (rc) {
-				printk(KERN_ERR
-				       "%s: Error finalizing crypto hash; "
+				       "%s: Error computing crypto hash; "
 				       "rc = [%d]\n", __func__, rc);
 				goto out_release_free_unlock;
 			}
@@ -834,10 +827,8 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	 * of the IV here, so we just use 0's for the IV. Note the
 	 * constraint that ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES
 	 * >= ECRYPTFS_MAX_IV_BYTES. */
-	memset(s->iv, 0, ECRYPTFS_MAX_IV_BYTES);
-	s->desc.info = s->iv;
-	rc = crypto_blkcipher_setkey(
-		s->desc.tfm,
+	rc = crypto_skcipher_setkey(
+		s->skcipher_tfm,
 		s->auth_tok->token.password.session_key_encryption_key,
 		mount_crypt_stat->global_default_fn_cipher_key_bytes);
 	if (rc < 0) {
@@ -850,8 +841,9 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		       mount_crypt_stat->global_default_fn_cipher_key_bytes);
 		goto out_release_free_unlock;
 	}
-	rc = crypto_blkcipher_encrypt_iv(&s->desc, s->dst_sg, s->src_sg,
-					 s->block_aligned_filename_size);
+	skcipher_request_set_crypt(s->skcipher_req, s->src_sg, s->dst_sg,
+				   s->block_aligned_filename_size, s->iv);
+	rc = crypto_skcipher_encrypt(s->skcipher_req);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to encrypt filename; "
 		       "rc = [%d]\n", __func__, rc);
@@ -861,7 +853,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	(*packet_size) = s->i;
 	(*remaining_bytes) -= (*packet_size);
 out_release_free_unlock:
-	crypto_free_hash(s->hash_desc.tfm);
+	crypto_free_shash(s->hash_tfm);
 out_free_unlock:
 	kzfree(s->block_aligned_filename);
 out_unlock:
@@ -871,6 +863,8 @@ out:
 		up_write(&(auth_tok_key->sem));
 		key_put(auth_tok_key);
 	}
+	skcipher_request_free(s->skcipher_req);
+	kzfree(s->hash_desc);
 	kfree(s);
 	return rc;
 }
@@ -888,7 +882,8 @@ struct ecryptfs_parse_tag_70_packet_silly_stack {
 	struct ecryptfs_auth_tok *auth_tok;
 	struct scatterlist src_sg[2];
 	struct scatterlist dst_sg[2];
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *skcipher_tfm;
+	struct skcipher_request *skcipher_req;
 	char fnek_sig_hex[ECRYPTFS_SIG_SIZE_HEX + 1];
 	char iv[ECRYPTFS_MAX_IV_BYTES];
 	char cipher_string[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
@@ -922,14 +917,12 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 	(*packet_size) = 0;
 	(*filename_size) = 0;
 	(*filename) = NULL;
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = kzalloc(sizeof(*s), GFP_KERNEL);
 	if (!s) {
 		printk(KERN_ERR "%s: Out of memory whilst trying to kmalloc "
 		       "[%zd] bytes of kernel memory\n", __func__, sizeof(*s));
-		rc = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
-	s->desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	if (max_packet_size < ECRYPTFS_TAG_70_MIN_METADATA_SIZE) {
 		printk(KERN_WARNING "%s: max_packet_size is [%zd]; it must be "
 		       "at least [%d]\n", __func__, max_packet_size,
@@ -992,7 +985,7 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       rc);
 		goto out;
 	}
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&s->desc.tfm,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&s->skcipher_tfm,
 							&s->tfm_mutex,
 							s->cipher_string);
 	if (unlikely(rc)) {
@@ -1030,12 +1023,23 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       __func__, rc, s->block_aligned_filename_size);
 		goto out_free_unlock;
 	}
+
+	s->skcipher_req = skcipher_request_alloc(s->skcipher_tfm, GFP_KERNEL);
+	if (!s->skcipher_req) {
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "skcipher_request_alloc for %s\n", __func__,
+		       crypto_skcipher_driver_name(s->skcipher_tfm));
+		rc = -ENOMEM;
+		goto out_free_unlock;
+	}
+
+	skcipher_request_set_callback(s->skcipher_req,
+				      CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+
 	/* The characters in the first block effectively do the job of
 	 * the IV here, so we just use 0's for the IV. Note the
 	 * constraint that ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES
 	 * >= ECRYPTFS_MAX_IV_BYTES. */
-	memset(s->iv, 0, ECRYPTFS_MAX_IV_BYTES);
-	s->desc.info = s->iv;
 	/* TODO: Support other key modules than passphrase for
 	 * filename encryption */
 	if (s->auth_tok->token_type != ECRYPTFS_PASSWORD) {
@@ -1044,8 +1048,8 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       "password tokens\n", __func__);
 		goto out_free_unlock;
 	}
-	rc = crypto_blkcipher_setkey(
-		s->desc.tfm,
+	rc = crypto_skcipher_setkey(
+		s->skcipher_tfm,
 		s->auth_tok->token.password.session_key_encryption_key,
 		mount_crypt_stat->global_default_fn_cipher_key_bytes);
 	if (rc < 0) {
@@ -1058,14 +1062,14 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       mount_crypt_stat->global_default_fn_cipher_key_bytes);
 		goto out_free_unlock;
 	}
-	rc = crypto_blkcipher_decrypt_iv(&s->desc, s->dst_sg, s->src_sg,
-					 s->block_aligned_filename_size);
+	skcipher_request_set_crypt(s->skcipher_req, s->src_sg, s->dst_sg,
+				   s->block_aligned_filename_size, s->iv);
+	rc = crypto_skcipher_decrypt(s->skcipher_req);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to decrypt filename; "
 		       "rc = [%d]\n", __func__, rc);
 		goto out_free_unlock;
 	}
-	s->i = 0;
 	while (s->decrypted_filename[s->i] != '\0'
 	       && s->i < s->block_aligned_filename_size)
 		s->i++;
@@ -1108,6 +1112,7 @@ out:
 		up_write(&(auth_tok_key->sem));
 		key_put(auth_tok_key);
 	}
+	skcipher_request_free(s->skcipher_req);
 	kfree(s);
 	return rc;
 }
@@ -1667,9 +1672,8 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 	struct scatterlist dst_sg[2];
 	struct scatterlist src_sg[2];
 	struct mutex *tfm_mutex;
-	struct blkcipher_desc desc = {
-		.flags = CRYPTO_TFM_REQ_MAY_SLEEP
-	};
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req = NULL;
 	int rc = 0;
 
 	if (unlikely(ecryptfs_verbosity > 0)) {
@@ -1680,7 +1684,7 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 			auth_tok->token.password.session_key_encryption_key,
 			auth_tok->token.password.session_key_encryption_key_bytes);
 	}
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&desc.tfm, &tfm_mutex,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&tfm, &tfm_mutex,
 							crypt_stat->cipher);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Internal error whilst attempting to get "
@@ -1711,8 +1715,20 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 		goto out;
 	}
 	mutex_lock(tfm_mutex);
-	rc = crypto_blkcipher_setkey(
-		desc.tfm, auth_tok->token.password.session_key_encryption_key,
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		mutex_unlock(tfm_mutex);
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "skcipher_request_alloc for %s\n", __func__,
+		       crypto_skcipher_driver_name(tfm));
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      NULL, NULL);
+	rc = crypto_skcipher_setkey(
+		tfm, auth_tok->token.password.session_key_encryption_key,
 		crypt_stat->key_size);
 	if (unlikely(rc < 0)) {
 		mutex_unlock(tfm_mutex);
@@ -1720,8 +1736,10 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 		rc = -EINVAL;
 		goto out;
 	}
-	rc = crypto_blkcipher_decrypt(&desc, dst_sg, src_sg,
-				      auth_tok->session_key.encrypted_key_size);
+	skcipher_request_set_crypt(req, src_sg, dst_sg,
+				   auth_tok->session_key.encrypted_key_size,
+				   NULL);
+	rc = crypto_skcipher_decrypt(req);
 	mutex_unlock(tfm_mutex);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Error decrypting; rc = [%d]\n", rc);
@@ -1738,6 +1756,7 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 				  crypt_stat->key_size);
 	}
 out:
+	skcipher_request_free(req);
 	return rc;
 }
 
@@ -2191,16 +2210,14 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 	size_t max_packet_size;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
 		crypt_stat->mount_crypt_stat;
-	struct blkcipher_desc desc = {
-		.tfm = NULL,
-		.flags = CRYPTO_TFM_REQ_MAY_SLEEP
-	};
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req;
 	int rc = 0;
 
 	(*packet_size) = 0;
 	ecryptfs_from_hex(key_rec->sig, auth_tok->token.password.signature,
 			  ECRYPTFS_SIG_SIZE);
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&desc.tfm, &tfm_mutex,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&tfm, &tfm_mutex,
 							crypt_stat->cipher);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Internal error whilst attempting to get "
@@ -2209,12 +2226,11 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	if (mount_crypt_stat->global_default_cipher_key_size == 0) {
-		struct blkcipher_alg *alg = crypto_blkcipher_alg(desc.tfm);
-
 		printk(KERN_WARNING "No key size specified at mount; "
-		       "defaulting to [%d]\n", alg->max_keysize);
+		       "defaulting to [%d]\n",
+		       crypto_skcipher_default_keysize(tfm));
 		mount_crypt_stat->global_default_cipher_key_size =
-			alg->max_keysize;
+			crypto_skcipher_default_keysize(tfm);
 	}
 	if (crypt_stat->key_size == 0)
 		crypt_stat->key_size =
@@ -2284,20 +2300,36 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	mutex_lock(tfm_mutex);
-	rc = crypto_blkcipher_setkey(desc.tfm, session_key_encryption_key,
-				     crypt_stat->key_size);
+	rc = crypto_skcipher_setkey(tfm, session_key_encryption_key,
+				    crypt_stat->key_size);
 	if (rc < 0) {
 		mutex_unlock(tfm_mutex);
 		ecryptfs_printk(KERN_ERR, "Error setting key for crypto "
 				"context; rc = [%d]\n", rc);
 		goto out;
 	}
+
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		mutex_unlock(tfm_mutex);
+		ecryptfs_printk(KERN_ERR, "Out of kernel memory whilst "
+				"attempting to skcipher_request_alloc for "
+				"%s\n", crypto_skcipher_driver_name(tfm));
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      NULL, NULL);
+
 	rc = 0;
 	ecryptfs_printk(KERN_DEBUG, "Encrypting [%zd] bytes of the key\n",
 			crypt_stat->key_size);
-	rc = crypto_blkcipher_encrypt(&desc, dst_sg, src_sg,
-				      (*key_rec).enc_key_size);
+	skcipher_request_set_crypt(req, src_sg, dst_sg,
+				   (*key_rec).enc_key_size, NULL);
+	rc = crypto_skcipher_encrypt(req);
 	mutex_unlock(tfm_mutex);
+	skcipher_request_free(req);
 	if (rc) {
 		printk(KERN_ERR "Error encrypting; rc = [%d]\n", rc);
 		goto out;
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index e25b6b06bacf..8b0b4a73116d 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -29,7 +29,6 @@
 #include <linux/module.h>
 #include <linux/namei.h>
 #include <linux/skbuff.h>
-#include <linux/crypto.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/key.h>
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index c6ced4cbf0cf..1f5865263b3e 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -30,7 +30,6 @@
 #include <linux/page-flags.h>
 #include <linux/mount.h>
 #include <linux/file.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index afa1b81c3418..77a486d3a51b 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -29,7 +29,6 @@
 #include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/file.h>
-#include <linux/crypto.h>
 #include <linux/statfs.h>
 #include <linux/magic.h>
 #include "ecryptfs_kernel.h"
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index c424e4813ec8..d48e0d261d78 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -10,6 +10,7 @@
 #include <linux/efi.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/mount.h>
 
 #include "internal.h"
 
@@ -103,9 +104,78 @@ out_free:
 	return size;
 }
 
+static int
+efivarfs_ioc_getxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int i_flags;
+	unsigned int flags = 0;
+
+	i_flags = inode->i_flags;
+	if (i_flags & S_IMMUTABLE)
+		flags |= FS_IMMUTABLE_FL;
+
+	if (copy_to_user(arg, &flags, sizeof(flags)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+efivarfs_ioc_setxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int flags;
+	unsigned int i_flags = 0;
+	int error;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (copy_from_user(&flags, arg, sizeof(flags)))
+		return -EFAULT;
+
+	if (flags & ~FS_IMMUTABLE_FL)
+		return -EOPNOTSUPP;
+
+	if (!capable(CAP_LINUX_IMMUTABLE))
+		return -EPERM;
+
+	if (flags & FS_IMMUTABLE_FL)
+		i_flags |= S_IMMUTABLE;
+
+
+	error = mnt_want_write_file(file);
+	if (error)
+		return error;
+
+	inode_lock(inode);
+	inode_set_flags(inode, i_flags, S_IMMUTABLE);
+	inode_unlock(inode);
+
+	mnt_drop_write_file(file);
+
+	return 0;
+}
+
+long
+efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p)
+{
+	void __user *arg = (void __user *)p;
+
+	switch (cmd) {
+	case FS_IOC_GETFLAGS:
+		return efivarfs_ioc_getxflags(file, arg);
+	case FS_IOC_SETFLAGS:
+		return efivarfs_ioc_setxflags(file, arg);
+	}
+
+	return -ENOTTY;
+}
+
 const struct file_operations efivarfs_file_operations = {
 	.open	= simple_open,
 	.read	= efivarfs_file_read,
 	.write	= efivarfs_file_write,
 	.llseek	= no_llseek,
+	.unlocked_ioctl = efivarfs_file_ioctl,
 };
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 3381b9da9ee6..e2ab6d0497f2 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -15,7 +15,8 @@
 #include "internal.h"
 
 struct inode *efivarfs_get_inode(struct super_block *sb,
-				const struct inode *dir, int mode, dev_t dev)
+				const struct inode *dir, int mode,
+				dev_t dev, bool is_removable)
 {
 	struct inode *inode = new_inode(sb);
 
@@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb,
 		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		inode->i_flags = is_removable ? 0 : S_IMMUTABLE;
 		switch (mode & S_IFMT) {
 		case S_IFREG:
 			inode->i_fop = &efivarfs_file_operations;
@@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid)
 static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 			  umode_t mode, bool excl)
 {
-	struct inode *inode;
+	struct inode *inode = NULL;
 	struct efivar_entry *var;
 	int namelen, i = 0, err = 0;
+	bool is_removable = false;
 
 	if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len))
 		return -EINVAL;
 
-	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0);
-	if (!inode)
-		return -ENOMEM;
-
 	var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL);
-	if (!var) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!var)
+		return -ENOMEM;
 
 	/* length of the variable name itself: remove GUID and separator */
 	namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
@@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 	efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1,
 			&var->var.VendorGuid);
 
+	if (efivar_variable_is_removable(var->var.VendorGuid,
+					 dentry->d_name.name, namelen))
+		is_removable = true;
+
+	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable);
+	if (!inode) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	for (i = 0; i < namelen; i++)
 		var->var.VariableName[i] = dentry->d_name.name[i];
 
@@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 out:
 	if (err) {
 		kfree(var);
-		iput(inode);
+		if (inode)
+			iput(inode);
 	}
 	return err;
 }
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index b5ff16addb7c..b4505188e799 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations;
 extern const struct inode_operations efivarfs_dir_inode_operations;
 extern bool efivarfs_valid_name(const char *str, int len);
 extern struct inode *efivarfs_get_inode(struct super_block *sb,
-			const struct inode *dir, int mode, dev_t dev);
+			const struct inode *dir, int mode, dev_t dev,
+			bool is_removable);
 
 extern struct list_head efivarfs_list;
 
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index b8a564f29107..dd029d13ea61 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -118,8 +118,9 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	struct dentry *dentry, *root = sb->s_root;
 	unsigned long size = 0;
 	char *name;
-	int len, i;
+	int len;
 	int err = -ENOMEM;
+	bool is_removable = false;
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
@@ -128,15 +129,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	memcpy(entry->var.VariableName, name16, name_size);
 	memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
 
-	len = ucs2_strlen(entry->var.VariableName);
+	len = ucs2_utf8size(entry->var.VariableName);
 
 	/* name, plus '-', plus GUID, plus NUL*/
 	name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL);
 	if (!name)
 		goto fail;
 
-	for (i = 0; i < len; i++)
-		name[i] = entry->var.VariableName[i] & 0xFF;
+	ucs2_as_utf8(name, entry->var.VariableName, len);
+
+	if (efivar_variable_is_removable(entry->var.VendorGuid, name, len))
+		is_removable = true;
 
 	name[len] = '-';
 
@@ -144,7 +147,8 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 
 	name[len + EFI_VARIABLE_GUID_LEN+1] = '\0';
 
-	inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0);
+	inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0,
+				   is_removable);
 	if (!inode)
 		goto fail_name;
 
@@ -200,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_d_op		= &efivarfs_d_ops;
 	sb->s_time_gran         = 1;
 
-	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true);
 	if (!inode)
 		return -ENOMEM;
 	inode->i_op = &efivarfs_dir_inode_operations;
diff --git a/fs/eventfd.c b/fs/eventfd.c
index ed70cf9fdc7b..1231cd1999d8 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -121,8 +121,46 @@ static unsigned int eventfd_poll(struct file *file, poll_table *wait)
 	u64 count;
 
 	poll_wait(file, &ctx->wqh, wait);
-	smp_rmb();
-	count = ctx->count;
+
+	/*
+	 * All writes to ctx->count occur within ctx->wqh.lock.  This read
+	 * can be done outside ctx->wqh.lock because we know that poll_wait
+	 * takes that lock (through add_wait_queue) if our caller will sleep.
+	 *
+	 * The read _can_ therefore seep into add_wait_queue's critical
+	 * section, but cannot move above it!  add_wait_queue's spin_lock acts
+	 * as an acquire barrier and ensures that the read be ordered properly
+	 * against the writes.  The following CAN happen and is safe:
+	 *
+	 *     poll                               write
+	 *     -----------------                  ------------
+	 *     lock ctx->wqh.lock (in poll_wait)
+	 *     count = ctx->count
+	 *     __add_wait_queue
+	 *     unlock ctx->wqh.lock
+	 *                                        lock ctx->qwh.lock
+	 *                                        ctx->count += n
+	 *                                        if (waitqueue_active)
+	 *                                          wake_up_locked_poll
+	 *                                        unlock ctx->qwh.lock
+	 *     eventfd_poll returns 0
+	 *
+	 * but the following, which would miss a wakeup, cannot happen:
+	 *
+	 *     poll                               write
+	 *     -----------------                  ------------
+	 *     count = ctx->count (INVALID!)
+	 *                                        lock ctx->qwh.lock
+	 *                                        ctx->count += n
+	 *                                        **waitqueue_active is false**
+	 *                                        **no wake_up_locked_poll!**
+	 *                                        unlock ctx->qwh.lock
+	 *     lock ctx->wqh.lock (in poll_wait)
+	 *     __add_wait_queue
+	 *     unlock ctx->wqh.lock
+	 *     eventfd_poll returns 0
+	 */
+	count = READ_ONCE(ctx->count);
 
 	if (count > 0)
 		events |= POLLIN;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index ae1dbcf47e97..8a74a2a52e0f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -94,6 +94,11 @@
 /* Epoll private bits inside the event mask */
 #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE)
 
+#define EPOLLINOUT_BITS (POLLIN | POLLOUT)
+
+#define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | POLLERR | POLLHUP | \
+				EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE)
+
 /* Maximum number of nesting allowed inside epoll sets */
 #define EP_MAX_NESTS 4
 
@@ -1068,7 +1073,22 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	 * wait list.
 	 */
 	if (waitqueue_active(&ep->wq)) {
-		ewake = 1;
+		if ((epi->event.events & EPOLLEXCLUSIVE) &&
+					!((unsigned long)key & POLLFREE)) {
+			switch ((unsigned long)key & EPOLLINOUT_BITS) {
+			case POLLIN:
+				if (epi->event.events & POLLIN)
+					ewake = 1;
+				break;
+			case POLLOUT:
+				if (epi->event.events & POLLOUT)
+					ewake = 1;
+				break;
+			case 0:
+				ewake = 1;
+				break;
+			}
+		}
 		wake_up_locked(&ep->wq);
 	}
 	if (waitqueue_active(&ep->poll_wait))
@@ -1596,7 +1616,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 {
 	int res = 0, eavail, timed_out = 0;
 	unsigned long flags;
-	long slack = 0;
+	u64 slack = 0;
 	wait_queue_t wait;
 	ktime_t expires, *to = NULL;
 
@@ -1875,9 +1895,13 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	 * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
 	 * Also, we do not currently supported nested exclusive wakeups.
 	 */
-	if ((epds.events & EPOLLEXCLUSIVE) && (op == EPOLL_CTL_MOD ||
-		(op == EPOLL_CTL_ADD && is_file_epoll(tf.file))))
-		goto error_tgt_fput;
+	if (epds.events & EPOLLEXCLUSIVE) {
+		if (op == EPOLL_CTL_MOD)
+			goto error_tgt_fput;
+		if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) ||
+				(epds.events & ~EPOLLEXCLUSIVE_OK_BITS)))
+			goto error_tgt_fput;
+	}
 
 	/*
 	 * At this point it is safe to assume that the "private_data" contains
@@ -1950,8 +1974,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		break;
 	case EPOLL_CTL_MOD:
 		if (epi) {
-			epds.events |= POLLERR | POLLHUP;
-			error = ep_modify(ep, epi, &epds);
+			if (!(epi->event.events & EPOLLEXCLUSIVE)) {
+				epds.events |= POLLERR | POLLHUP;
+				error = ep_modify(ep, epi, &epds);
+			}
 		} else
 			error = -ENOENT;
 		break;
diff --git a/fs/exec.c b/fs/exec.c
index dcd4ac7d3f1e..c4010b8207a1 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -56,6 +56,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
 #include <linux/compat.h>
+#include <linux/vmalloc.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -198,8 +199,12 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 			return NULL;
 	}
 #endif
-	ret = get_user_pages(current, bprm->mm, pos,
-			1, write, 1, &page, NULL);
+	/*
+	 * We are doing an exec().  'current' is the process
+	 * doing the exec and bprm->mm is the new process's mm.
+	 */
+	ret = get_user_pages_remote(current, bprm->mm, pos, 1, write,
+			1, &page, NULL);
 	if (ret <= 0)
 		return NULL;
 
@@ -831,6 +836,97 @@ int kernel_read(struct file *file, loff_t offset,
 
 EXPORT_SYMBOL(kernel_read);
 
+int kernel_read_file(struct file *file, void **buf, loff_t *size,
+		     loff_t max_size, enum kernel_read_file_id id)
+{
+	loff_t i_size, pos;
+	ssize_t bytes = 0;
+	int ret;
+
+	if (!S_ISREG(file_inode(file)->i_mode) || max_size < 0)
+		return -EINVAL;
+
+	ret = security_kernel_read_file(file, id);
+	if (ret)
+		return ret;
+
+	i_size = i_size_read(file_inode(file));
+	if (max_size > 0 && i_size > max_size)
+		return -EFBIG;
+	if (i_size <= 0)
+		return -EINVAL;
+
+	*buf = vmalloc(i_size);
+	if (!*buf)
+		return -ENOMEM;
+
+	pos = 0;
+	while (pos < i_size) {
+		bytes = kernel_read(file, pos, (char *)(*buf) + pos,
+				    i_size - pos);
+		if (bytes < 0) {
+			ret = bytes;
+			goto out;
+		}
+
+		if (bytes == 0)
+			break;
+		pos += bytes;
+	}
+
+	if (pos != i_size) {
+		ret = -EIO;
+		goto out;
+	}
+
+	ret = security_kernel_post_read_file(file, *buf, i_size, id);
+	if (!ret)
+		*size = pos;
+
+out:
+	if (ret < 0) {
+		vfree(*buf);
+		*buf = NULL;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kernel_read_file);
+
+int kernel_read_file_from_path(char *path, void **buf, loff_t *size,
+			       loff_t max_size, enum kernel_read_file_id id)
+{
+	struct file *file;
+	int ret;
+
+	if (!path || !*path)
+		return -EINVAL;
+
+	file = filp_open(path, O_RDONLY, 0);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	ret = kernel_read_file(file, buf, size, max_size, id);
+	fput(file);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kernel_read_file_from_path);
+
+int kernel_read_file_from_fd(int fd, void **buf, loff_t *size, loff_t max_size,
+			     enum kernel_read_file_id id)
+{
+	struct fd f = fdget(fd);
+	int ret = -EBADF;
+
+	if (!f.file)
+		goto out;
+
+	ret = kernel_read_file(f.file, buf, size, max_size, id);
+out:
+	fdput(f);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kernel_read_file_from_fd);
+
 ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
 {
 	ssize_t res = vfs_read(file, (void __user *)addr, len, &pos);
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 4c69c94cafd8..170939f379d7 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -61,6 +61,8 @@ struct ext2_block_alloc_info {
 #define rsv_start rsv_window._rsv_start
 #define rsv_end rsv_window._rsv_end
 
+struct mb_cache;
+
 /*
  * second extended-fs super-block data in memory
  */
@@ -111,6 +113,7 @@ struct ext2_sb_info {
 	 * of the mount options.
 	 */
 	spinlock_t s_lock;
+	struct mb_cache *s_mb_cache;
 };
 
 static inline spinlock_t *
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 2c88d683cd91..c1400b109805 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -80,23 +80,6 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return ret;
 }
 
-static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct inode *inode = file_inode(vma->vm_file);
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	int ret;
-
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
-	down_read(&ei->dax_sem);
-
-	ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL);
-
-	up_read(&ei->dax_sem);
-	sb_end_pagefault(inode->i_sb);
-	return ret;
-}
-
 static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 		struct vm_fault *vmf)
 {
@@ -124,7 +107,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
 	.pmd_fault	= ext2_dax_pmd_fault,
-	.page_mkwrite	= ext2_dax_mkwrite,
+	.page_mkwrite	= ext2_dax_fault,
 	.pfn_mkwrite	= ext2_dax_pfn_mkwrite,
 };
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 338eefda70c6..6bd58e6ff038 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -737,8 +737,10 @@ static int ext2_get_blocks(struct inode *inode,
 		 * so that it's not found by another thread before it's
 		 * initialised
 		 */
-		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
-						1 << inode->i_blkbits);
+		err = dax_clear_sectors(inode->i_sb->s_bdev,
+				le32_to_cpu(chain[depth-1].key) <<
+				(inode->i_blkbits - 9),
+				1 << inode->i_blkbits);
 		if (err) {
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
@@ -874,6 +876,14 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 static int
 ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
+#ifdef CONFIG_FS_DAX
+	if (dax_mapping(mapping)) {
+		return dax_writeback_mapping_range(mapping,
+						   mapping->host->i_sb->s_bdev,
+						   wbc);
+	}
+#endif
+
 	return mpage_writepages(mapping, wbc, ext2_get_block);
 }
 
@@ -1296,7 +1306,7 @@ 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))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
 		inode->i_flags |= S_DAX;
 }
 
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 2a188413a2b0..b78caf25f746 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -131,7 +131,10 @@ static void ext2_put_super (struct super_block * sb)
 
 	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
 
-	ext2_xattr_put_super(sb);
+	if (sbi->s_mb_cache) {
+		ext2_xattr_destroy_cache(sbi->s_mb_cache);
+		sbi->s_mb_cache = NULL;
+	}
 	if (!(sb->s_flags & MS_RDONLY)) {
 		struct ext2_super_block *es = sbi->s_es;
 
@@ -1104,6 +1107,14 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		ext2_msg(sb, KERN_ERR, "error: insufficient memory");
 		goto failed_mount3;
 	}
+
+#ifdef CONFIG_EXT2_FS_XATTR
+	sbi->s_mb_cache = ext2_xattr_create_cache();
+	if (!sbi->s_mb_cache) {
+		ext2_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+		goto failed_mount3;
+	}
+#endif
 	/*
 	 * set up enough so that it can read an inode
 	 */
@@ -1149,6 +1160,8 @@ cantfind_ext2:
 			sb->s_id);
 	goto failed_mount;
 failed_mount3:
+	if (sbi->s_mb_cache)
+		ext2_xattr_destroy_cache(sbi->s_mb_cache);
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -1555,20 +1568,17 @@ MODULE_ALIAS_FS("ext2");
 
 static int __init init_ext2_fs(void)
 {
-	int err = init_ext2_xattr();
-	if (err)
-		return err;
+	int err;
+
 	err = init_inodecache();
 	if (err)
-		goto out1;
+		return err;
         err = register_filesystem(&ext2_fs_type);
 	if (err)
 		goto out;
 	return 0;
 out:
 	destroy_inodecache();
-out1:
-	exit_ext2_xattr();
 	return err;
 }
 
@@ -1576,7 +1586,6 @@ static void __exit exit_ext2_fs(void)
 {
 	unregister_filesystem(&ext2_fs_type);
 	destroy_inodecache();
-	exit_ext2_xattr();
 }
 
 MODULE_AUTHOR("Remy Card and others");
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index f57a7aba32eb..1a5e3bff0b63 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -90,14 +90,12 @@
 static int ext2_xattr_set2(struct inode *, struct buffer_head *,
 			   struct ext2_xattr_header *);
 
-static int ext2_xattr_cache_insert(struct buffer_head *);
+static int ext2_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
 static struct buffer_head *ext2_xattr_cache_find(struct inode *,
 						 struct ext2_xattr_header *);
 static void ext2_xattr_rehash(struct ext2_xattr_header *,
 			      struct ext2_xattr_entry *);
 
-static struct mb_cache *ext2_xattr_cache;
-
 static const struct xattr_handler *ext2_xattr_handler_map[] = {
 	[EXT2_XATTR_INDEX_USER]		     = &ext2_xattr_user_handler,
 #ifdef CONFIG_EXT2_FS_POSIX_ACL
@@ -152,6 +150,7 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name,
 	size_t name_len, size;
 	char *end;
 	int error;
+	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
 
 	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
 		  name_index, name, buffer, (long)buffer_size);
@@ -196,7 +195,7 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_get",
 			goto found;
 		entry = next;
 	}
-	if (ext2_xattr_cache_insert(bh))
+	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 	error = -ENODATA;
 	goto cleanup;
@@ -209,7 +208,7 @@ found:
 	    le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize)
 		goto bad_block;
 
-	if (ext2_xattr_cache_insert(bh))
+	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 	if (buffer) {
 		error = -ERANGE;
@@ -247,6 +246,7 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	char *end;
 	size_t rest = buffer_size;
 	int error;
+	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
 
 	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
 		  buffer, (long)buffer_size);
@@ -281,7 +281,7 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_list",
 			goto bad_block;
 		entry = next;
 	}
-	if (ext2_xattr_cache_insert(bh))
+	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 
 	/* list the attribute names */
@@ -483,22 +483,23 @@ bad_block:		ext2_error(sb, "ext2_xattr_set",
 	/* Here we know that we can set the new attribute. */
 
 	if (header) {
-		struct mb_cache_entry *ce;
-
 		/* assert(header == HDR(bh)); */
-		ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev,
-					bh->b_blocknr);
 		lock_buffer(bh);
 		if (header->h_refcount == cpu_to_le32(1)) {
+			__u32 hash = le32_to_cpu(header->h_hash);
+
 			ea_bdebug(bh, "modifying in-place");
-			if (ce)
-				mb_cache_entry_free(ce);
+			/*
+			 * This must happen under buffer lock for
+			 * ext2_xattr_set2() to reliably detect modified block
+			 */
+			mb_cache_entry_delete_block(EXT2_SB(sb)->s_mb_cache,
+						    hash, bh->b_blocknr);
+
 			/* keep the buffer locked while modifying it. */
 		} else {
 			int offset;
 
-			if (ce)
-				mb_cache_entry_release(ce);
 			unlock_buffer(bh);
 			ea_bdebug(bh, "cloning");
 			header = kmalloc(bh->b_size, GFP_KERNEL);
@@ -626,6 +627,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *new_bh = NULL;
 	int error;
+	struct mb_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache;
 
 	if (header) {
 		new_bh = ext2_xattr_cache_find(inode, header);
@@ -653,7 +655,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			   don't need to change the reference count. */
 			new_bh = old_bh;
 			get_bh(new_bh);
-			ext2_xattr_cache_insert(new_bh);
+			ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
 		} else {
 			/* We need to allocate a new block */
 			ext2_fsblk_t goal = ext2_group_first_block_no(sb,
@@ -674,7 +676,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			memcpy(new_bh->b_data, header, new_bh->b_size);
 			set_buffer_uptodate(new_bh);
 			unlock_buffer(new_bh);
-			ext2_xattr_cache_insert(new_bh);
+			ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
 			
 			ext2_xattr_update_super_block(sb);
 		}
@@ -707,19 +709,21 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 
 	error = 0;
 	if (old_bh && old_bh != new_bh) {
-		struct mb_cache_entry *ce;
-
 		/*
 		 * If there was an old block and we are no longer using it,
 		 * release the old block.
 		 */
-		ce = mb_cache_entry_get(ext2_xattr_cache, old_bh->b_bdev,
-					old_bh->b_blocknr);
 		lock_buffer(old_bh);
 		if (HDR(old_bh)->h_refcount == cpu_to_le32(1)) {
+			__u32 hash = le32_to_cpu(HDR(old_bh)->h_hash);
+
+			/*
+			 * This must happen under buffer lock for
+			 * ext2_xattr_set2() to reliably detect freed block
+			 */
+			mb_cache_entry_delete_block(ext2_mb_cache,
+						    hash, old_bh->b_blocknr);
 			/* Free the old block. */
-			if (ce)
-				mb_cache_entry_free(ce);
 			ea_bdebug(old_bh, "freeing");
 			ext2_free_blocks(inode, old_bh->b_blocknr, 1);
 			mark_inode_dirty(inode);
@@ -730,8 +734,6 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 		} else {
 			/* Decrement the refcount only. */
 			le32_add_cpu(&HDR(old_bh)->h_refcount, -1);
-			if (ce)
-				mb_cache_entry_release(ce);
 			dquot_free_block_nodirty(inode, 1);
 			mark_inode_dirty(inode);
 			mark_buffer_dirty(old_bh);
@@ -757,7 +759,6 @@ void
 ext2_xattr_delete_inode(struct inode *inode)
 {
 	struct buffer_head *bh = NULL;
-	struct mb_cache_entry *ce;
 
 	down_write(&EXT2_I(inode)->xattr_sem);
 	if (!EXT2_I(inode)->i_file_acl)
@@ -777,19 +778,22 @@ ext2_xattr_delete_inode(struct inode *inode)
 			EXT2_I(inode)->i_file_acl);
 		goto cleanup;
 	}
-	ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev, bh->b_blocknr);
 	lock_buffer(bh);
 	if (HDR(bh)->h_refcount == cpu_to_le32(1)) {
-		if (ce)
-			mb_cache_entry_free(ce);
+		__u32 hash = le32_to_cpu(HDR(bh)->h_hash);
+
+		/*
+		 * This must happen under buffer lock for ext2_xattr_set2() to
+		 * reliably detect freed block
+		 */
+		mb_cache_entry_delete_block(EXT2_SB(inode->i_sb)->s_mb_cache,
+					    hash, bh->b_blocknr);
 		ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1);
 		get_bh(bh);
 		bforget(bh);
 		unlock_buffer(bh);
 	} else {
 		le32_add_cpu(&HDR(bh)->h_refcount, -1);
-		if (ce)
-			mb_cache_entry_release(ce);
 		ea_bdebug(bh, "refcount now=%d",
 			le32_to_cpu(HDR(bh)->h_refcount));
 		unlock_buffer(bh);
@@ -806,18 +810,6 @@ cleanup:
 }
 
 /*
- * ext2_xattr_put_super()
- *
- * This is called when a file system is unmounted.
- */
-void
-ext2_xattr_put_super(struct super_block *sb)
-{
-	mb_cache_shrink(sb->s_bdev);
-}
-
-
-/*
  * ext2_xattr_cache_insert()
  *
  * Create a new entry in the extended attribute cache, and insert
@@ -826,28 +818,20 @@ ext2_xattr_put_super(struct super_block *sb)
  * Returns 0, or a negative error number on failure.
  */
 static int
-ext2_xattr_cache_insert(struct buffer_head *bh)
+ext2_xattr_cache_insert(struct mb_cache *cache, struct buffer_head *bh)
 {
 	__u32 hash = le32_to_cpu(HDR(bh)->h_hash);
-	struct mb_cache_entry *ce;
 	int error;
 
-	ce = mb_cache_entry_alloc(ext2_xattr_cache, GFP_NOFS);
-	if (!ce)
-		return -ENOMEM;
-	error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash);
+	error = mb_cache_entry_create(cache, GFP_NOFS, hash, bh->b_blocknr, 1);
 	if (error) {
-		mb_cache_entry_free(ce);
 		if (error == -EBUSY) {
 			ea_bdebug(bh, "already in cache (%d cache entries)",
 				atomic_read(&ext2_xattr_cache->c_entry_count));
 			error = 0;
 		}
-	} else {
-		ea_bdebug(bh, "inserting [%x] (%d cache entries)", (int)hash,
-			  atomic_read(&ext2_xattr_cache->c_entry_count));
-		mb_cache_entry_release(ce);
-	}
+	} else
+		ea_bdebug(bh, "inserting [%x]", (int)hash);
 	return error;
 }
 
@@ -904,22 +888,16 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
 {
 	__u32 hash = le32_to_cpu(header->h_hash);
 	struct mb_cache_entry *ce;
+	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
 
 	if (!header->h_hash)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
 again:
-	ce = mb_cache_entry_find_first(ext2_xattr_cache, inode->i_sb->s_bdev,
-				       hash);
+	ce = mb_cache_entry_find_first(ext2_mb_cache, hash);
 	while (ce) {
 		struct buffer_head *bh;
 
-		if (IS_ERR(ce)) {
-			if (PTR_ERR(ce) == -EAGAIN)
-				goto again;
-			break;
-		}
-
 		bh = sb_bread(inode->i_sb, ce->e_block);
 		if (!bh) {
 			ext2_error(inode->i_sb, "ext2_xattr_cache_find",
@@ -927,7 +905,21 @@ again:
 				inode->i_ino, (unsigned long) ce->e_block);
 		} else {
 			lock_buffer(bh);
-			if (le32_to_cpu(HDR(bh)->h_refcount) >
+			/*
+			 * We have to be careful about races with freeing or
+			 * rehashing of xattr block. Once we hold buffer lock
+			 * xattr block's state is stable so we can check
+			 * whether the block got freed / rehashed or not.
+			 * Since we unhash mbcache entry under buffer lock when
+			 * freeing / rehashing xattr block, checking whether
+			 * entry is still hashed is reliable.
+			 */
+			if (hlist_bl_unhashed(&ce->e_hash_list)) {
+				mb_cache_entry_put(ext2_mb_cache, ce);
+				unlock_buffer(bh);
+				brelse(bh);
+				goto again;
+			} else if (le32_to_cpu(HDR(bh)->h_refcount) >
 				   EXT2_XATTR_REFCOUNT_MAX) {
 				ea_idebug(inode, "block %ld refcount %d>%d",
 					  (unsigned long) ce->e_block,
@@ -936,13 +928,14 @@ again:
 			} else if (!ext2_xattr_cmp(header, HDR(bh))) {
 				ea_bdebug(bh, "b_count=%d",
 					  atomic_read(&(bh->b_count)));
-				mb_cache_entry_release(ce);
+				mb_cache_entry_touch(ext2_mb_cache, ce);
+				mb_cache_entry_put(ext2_mb_cache, ce);
 				return bh;
 			}
 			unlock_buffer(bh);
 			brelse(bh);
 		}
-		ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash);
+		ce = mb_cache_entry_find_next(ext2_mb_cache, ce);
 	}
 	return NULL;
 }
@@ -1015,17 +1008,15 @@ static void ext2_xattr_rehash(struct ext2_xattr_header *header,
 
 #undef BLOCK_HASH_SHIFT
 
-int __init
-init_ext2_xattr(void)
+#define HASH_BUCKET_BITS 10
+
+struct mb_cache *ext2_xattr_create_cache(void)
 {
-	ext2_xattr_cache = mb_cache_create("ext2_xattr", 6);
-	if (!ext2_xattr_cache)
-		return -ENOMEM;
-	return 0;
+	return mb_cache_create(HASH_BUCKET_BITS);
 }
 
-void
-exit_ext2_xattr(void)
+void ext2_xattr_destroy_cache(struct mb_cache *cache)
 {
-	mb_cache_destroy(ext2_xattr_cache);
+	if (cache)
+		mb_cache_destroy(cache);
 }
diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h
index 60edf298644e..6f82ab1b00ca 100644
--- a/fs/ext2/xattr.h
+++ b/fs/ext2/xattr.h
@@ -53,6 +53,8 @@ struct ext2_xattr_entry {
 #define EXT2_XATTR_SIZE(size) \
 	(((size) + EXT2_XATTR_ROUND) & ~EXT2_XATTR_ROUND)
 
+struct mb_cache;
+
 # ifdef CONFIG_EXT2_FS_XATTR
 
 extern const struct xattr_handler ext2_xattr_user_handler;
@@ -65,10 +67,9 @@ extern int ext2_xattr_get(struct inode *, int, const char *, void *, size_t);
 extern int ext2_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
 
 extern void ext2_xattr_delete_inode(struct inode *);
-extern void ext2_xattr_put_super(struct super_block *);
 
-extern int init_ext2_xattr(void);
-extern void exit_ext2_xattr(void);
+extern struct mb_cache *ext2_xattr_create_cache(void);
+extern void ext2_xattr_destroy_cache(struct mb_cache *cache);
 
 extern const struct xattr_handler *ext2_xattr_handlers[];
 
@@ -93,19 +94,7 @@ ext2_xattr_delete_inode(struct inode *inode)
 {
 }
 
-static inline void
-ext2_xattr_put_super(struct super_block *sb)
-{
-}
-
-static inline int
-init_ext2_xattr(void)
-{
-	return 0;
-}
-
-static inline void
-exit_ext2_xattr(void)
+static inline void ext2_xattr_destroy_cache(struct mb_cache *cache)
 {
 }
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index ec0668a60678..fe1f50fe764f 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks used to prevent allocation
 	 * essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	}
 	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-
 		err = ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err)
+		if (err) {
+			ext4_error(sb, "Failed to init block bitmap for group "
+				   "%u: %d", block_group, err);
 			goto out;
+		}
 		goto verify;
 	}
 	ext4_unlock_group(sb, block_group);
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
index c8021208a7eb..edc053a81914 100644
--- a/fs/ext4/crypto.c
+++ b/fs/ext4/crypto.c
@@ -18,11 +18,9 @@
  * Special Publication 800-38E and IEEE P1619/D16.
  */
 
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/skcipher.h>
 #include <keys/user-type.h>
 #include <keys/encrypted-type.h>
-#include <linux/crypto.h>
 #include <linux/ecryptfs.h>
 #include <linux/gfp.h>
 #include <linux/kernel.h>
@@ -261,21 +259,21 @@ static int ext4_page_crypto(struct inode *inode,
 
 {
 	u8 xts_tweak[EXT4_XTS_TWEAK_SIZE];
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct scatterlist dst, src;
 	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 				   "%s: crypto_request_alloc() failed\n",
 				   __func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(
+	skcipher_request_set_callback(
 		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		ext4_crypt_complete, &ecr);
 
@@ -288,21 +286,21 @@ static int ext4_page_crypto(struct inode *inode,
 	sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
 	sg_init_table(&src, 1);
 	sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
-	ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
-				     xts_tweak);
+	skcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
+				   xts_tweak);
 	if (rw == EXT4_DECRYPT)
-		res = crypto_ablkcipher_decrypt(req);
+		res = crypto_skcipher_decrypt(req);
 	else
-		res = crypto_ablkcipher_encrypt(req);
+		res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res) {
 		printk_ratelimited(
 			KERN_ERR
-			"%s: crypto_ablkcipher_encrypt() returned %d\n",
+			"%s: crypto_skcipher_encrypt() returned %d\n",
 			__func__, res);
 		return res;
 	}
@@ -467,3 +465,59 @@ uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size)
 		return size;
 	return 0;
 }
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct inode *dir = d_inode(dentry->d_parent);
+	struct ext4_crypt_info *ci = EXT4_I(dir)->i_crypt_info;
+	int dir_has_key, cached_with_key;
+
+	if (!ext4_encrypted_inode(dir))
+		return 0;
+
+	if (ci && ci->ci_keyring_key &&
+	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					  (1 << KEY_FLAG_REVOKED) |
+					  (1 << KEY_FLAG_DEAD))))
+		ci = NULL;
+
+	/* this should eventually be an flag in d_flags */
+	cached_with_key = dentry->d_fsdata != NULL;
+	dir_has_key = (ci != NULL);
+
+	/*
+	 * If the dentry was cached without the key, and it is a
+	 * negative dentry, it might be a valid name.  We can't check
+	 * if the key has since been made available due to locking
+	 * reasons, so we fail the validation so ext4_lookup() can do
+	 * this check.
+	 *
+	 * We also fail the validation if the dentry was created with
+	 * the key present, but we no longer have the key, or vice versa.
+	 */
+	if ((!cached_with_key && d_is_negative(dentry)) ||
+	    (!cached_with_key && dir_has_key) ||
+	    (cached_with_key && !dir_has_key)) {
+#if 0				/* Revalidation debug */
+		char buf[80];
+		char *cp = simple_dname(dentry, buf, sizeof(buf));
+
+		if (IS_ERR(cp))
+			cp = (char *) "???";
+		pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata,
+		       cached_with_key, d_is_negative(dentry),
+		       dir_has_key);
+#endif
+		return 0;
+	}
+	return 1;
+}
+
+const struct dentry_operations ext4_encrypted_d_ops = {
+	.d_revalidate = ext4_d_revalidate,
+};
diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c
index 2fbef8a14760..1a2f360405db 100644
--- a/fs/ext4/crypto_fname.c
+++ b/fs/ext4/crypto_fname.c
@@ -11,11 +11,9 @@
  *
  */
 
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/skcipher.h>
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
-#include <linux/crypto.h>
 #include <linux/gfp.h>
 #include <linux/kernel.h>
 #include <linux/key.h>
@@ -65,10 +63,10 @@ static int ext4_fname_encrypt(struct inode *inode,
 			      struct ext4_str *oname)
 {
 	u32 ciphertext_len;
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 	char iv[EXT4_CRYPTO_BLOCK_SIZE];
 	struct scatterlist src_sg, dst_sg;
@@ -95,14 +93,14 @@ static int ext4_fname_encrypt(struct inode *inode,
 	}
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(
 		    KERN_ERR "%s: crypto_request_alloc() failed\n", __func__);
 		kfree(alloc_buf);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		ext4_dir_crypt_complete, &ecr);
 
@@ -117,14 +115,14 @@ static int ext4_fname_encrypt(struct inode *inode,
 	/* Create encryption request */
 	sg_init_one(&src_sg, workbuf, ciphertext_len);
 	sg_init_one(&dst_sg, oname->name, ciphertext_len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
-	res = crypto_ablkcipher_encrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
+	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 	kfree(alloc_buf);
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(
 		    KERN_ERR "%s: Error (error code %d)\n", __func__, res);
@@ -145,11 +143,11 @@ static int ext4_fname_decrypt(struct inode *inode,
 			      struct ext4_str *oname)
 {
 	struct ext4_str tmp_in[2], tmp_out[1];
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
 	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 	char iv[EXT4_CRYPTO_BLOCK_SIZE];
 	unsigned lim = max_name_len(inode);
@@ -162,13 +160,13 @@ static int ext4_fname_decrypt(struct inode *inode,
 	tmp_out[0].name = oname->name;
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(
 		    KERN_ERR "%s: crypto_request_alloc() failed\n",  __func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		ext4_dir_crypt_complete, &ecr);
 
@@ -178,13 +176,13 @@ static int ext4_fname_decrypt(struct inode *inode,
 	/* Create encryption request */
 	sg_init_one(&src_sg, iname->name, iname->len);
 	sg_init_one(&dst_sg, oname->name, oname->len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
-	res = crypto_ablkcipher_decrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
+	res = crypto_skcipher_decrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(
 		    KERN_ERR "%s: Error in ext4_fname_encrypt (error code %d)\n",
diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c
index 9a16d1e75a49..0129d688d1f7 100644
--- a/fs/ext4/crypto_key.c
+++ b/fs/ext4/crypto_key.c
@@ -8,6 +8,7 @@
  * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
  */
 
+#include <crypto/skcipher.h>
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
 #include <linux/random.h>
@@ -41,45 +42,42 @@ static int ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE],
 			       char derived_key[EXT4_AES_256_XTS_KEY_SIZE])
 {
 	int res = 0;
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
-	struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
-								0);
+	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
 
 	if (IS_ERR(tfm)) {
 		res = PTR_ERR(tfm);
 		tfm = NULL;
 		goto out;
 	}
-	crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		res = -ENOMEM;
 		goto out;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			derive_crypt_complete, &ecr);
-	res = crypto_ablkcipher_setkey(tfm, deriving_key,
-				       EXT4_AES_128_ECB_KEY_SIZE);
+	res = crypto_skcipher_setkey(tfm, deriving_key,
+				     EXT4_AES_128_ECB_KEY_SIZE);
 	if (res < 0)
 		goto out;
 	sg_init_one(&src_sg, source_key, EXT4_AES_256_XTS_KEY_SIZE);
 	sg_init_one(&dst_sg, derived_key, EXT4_AES_256_XTS_KEY_SIZE);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
-				     EXT4_AES_256_XTS_KEY_SIZE, NULL);
-	res = crypto_ablkcipher_encrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
+				   EXT4_AES_256_XTS_KEY_SIZE, NULL);
+	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 
 out:
-	if (req)
-		ablkcipher_request_free(req);
-	if (tfm)
-		crypto_free_ablkcipher(tfm);
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
 	return res;
 }
 
@@ -90,7 +88,7 @@ void ext4_free_crypt_info(struct ext4_crypt_info *ci)
 
 	if (ci->ci_keyring_key)
 		key_put(ci->ci_keyring_key);
-	crypto_free_ablkcipher(ci->ci_ctfm);
+	crypto_free_skcipher(ci->ci_ctfm);
 	kmem_cache_free(ext4_crypt_info_cachep, ci);
 }
 
@@ -122,7 +120,7 @@ int _ext4_get_encryption_info(struct inode *inode)
 	struct ext4_encryption_context ctx;
 	const struct user_key_payload *ukp;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	struct crypto_ablkcipher *ctfm;
+	struct crypto_skcipher *ctfm;
 	const char *cipher_str;
 	char raw_key[EXT4_MAX_KEY_SIZE];
 	char mode;
@@ -237,7 +235,7 @@ retry:
 	if (res)
 		goto out;
 got_key:
-	ctfm = crypto_alloc_ablkcipher(cipher_str, 0, 0);
+	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
 	if (!ctfm || IS_ERR(ctfm)) {
 		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
 		printk(KERN_DEBUG
@@ -246,11 +244,11 @@ got_key:
 		goto out;
 	}
 	crypt_info->ci_ctfm = ctfm;
-	crypto_ablkcipher_clear_flags(ctfm, ~0);
-	crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm),
+	crypto_skcipher_clear_flags(ctfm, ~0);
+	crypto_tfm_set_flags(crypto_skcipher_tfm(ctfm),
 			     CRYPTO_TFM_REQ_WEAK_KEY);
-	res = crypto_ablkcipher_setkey(ctfm, raw_key,
-				       ext4_encryption_key_size(mode));
+	res = crypto_skcipher_setkey(ctfm, raw_key,
+				     ext4_encryption_key_size(mode));
 	if (res)
 		goto out;
 	memzero_explicit(raw_key, sizeof(raw_key));
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 1d1bca74f844..50ba27cbed03 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -111,6 +111,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	int dir_has_error = 0;
 	struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
 
+	if (ext4_encrypted_inode(inode)) {
+		err = ext4_get_encryption_info(inode);
+		if (err && err != -ENOKEY)
+			return err;
+	}
+
 	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(file, ctx);
 		if (err != ERR_BAD_DX_DIR) {
@@ -157,8 +163,11 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 					index, 1);
 			file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
 			bh = ext4_bread(NULL, inode, map.m_lblk, 0);
-			if (IS_ERR(bh))
-				return PTR_ERR(bh);
+			if (IS_ERR(bh)) {
+				err = PTR_ERR(bh);
+				bh = NULL;
+				goto errout;
+			}
 		}
 
 		if (!bh) {
@@ -276,7 +285,7 @@ errout:
 static inline int is_32bit_api(void)
 {
 #ifdef CONFIG_COMPAT
-	return is_compat_task();
+	return in_compat_syscall();
 #else
 	return (BITS_PER_LONG == 32);
 #endif
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0662b285dc8a..c04743519865 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -42,6 +42,18 @@
  */
 
 /*
+ * with AGGRESSIVE_CHECK allocator runs consistency checks over
+ * structures. these checks slow things down a lot
+ */
+#define AGGRESSIVE_CHECK__
+
+/*
+ * with DOUBLE_CHECK defined mballoc creates persistent in-core
+ * bitmaps, maintains and uses them to check for double allocations
+ */
+#define DOUBLE_CHECK__
+
+/*
  * Define EXT4FS_DEBUG to produce debug messages
  */
 #undef EXT4FS_DEBUG
@@ -182,9 +194,9 @@ typedef struct ext4_io_end {
 	struct bio		*bio;		/* Linked list of completed
 						 * bios covering the extent */
 	unsigned int		flag;		/* unwritten or not */
+	atomic_t		count;		/* reference counter */
 	loff_t			offset;		/* offset in the file */
 	ssize_t			size;		/* size of the extent */
-	atomic_t		count;		/* reference counter */
 } ext4_io_end_t;
 
 struct ext4_io_submit {
@@ -1024,13 +1036,8 @@ struct ext4_inode_info {
 	 * transaction reserved
 	 */
 	struct list_head i_rsv_conversion_list;
-	/*
-	 * Completed IOs that need unwritten extents handling and don't have
-	 * transaction reserved
-	 */
-	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
-	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
 	struct work_struct i_rsv_conversion_work;
+	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
 
 	spinlock_t i_block_reservation_lock;
 
@@ -1504,25 +1511,6 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
 }
 
-static inline void ext4_set_io_unwritten_flag(struct inode *inode,
-					      struct ext4_io_end *io_end)
-{
-	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
-		io_end->flag |= EXT4_IO_END_UNWRITTEN;
-		atomic_inc(&EXT4_I(inode)->i_unwritten);
-	}
-}
-
-static inline ext4_io_end_t *ext4_inode_aio(struct inode *inode)
-{
-	return inode->i_private;
-}
-
-static inline void ext4_inode_aio_set(struct inode *inode, ext4_io_end_t *io)
-{
-	inode->i_private = io;
-}
-
 /*
  * Inode dynamic state flags
  */
@@ -2302,6 +2290,7 @@ struct page *ext4_encrypt(struct inode *inode,
 int ext4_decrypt(struct page *page);
 int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk,
 			   ext4_fsblk_t pblk, ext4_lblk_t len);
+extern const struct dentry_operations ext4_encrypted_d_ops;
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 int ext4_init_crypto(void);
@@ -2505,12 +2494,14 @@ extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
 int ext4_inode_is_fast_symlink(struct inode *inode);
 struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
 struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
-int ext4_get_block_write(struct inode *inode, sector_t iblock,
-			 struct buffer_head *bh_result, int create);
+int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
+			     struct buffer_head *bh_result, int create);
 int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
 			    struct buffer_head *bh_result, int create);
 int ext4_get_block(struct inode *inode, sector_t iblock,
-				struct buffer_head *bh_result, int create);
+		   struct buffer_head *bh_result, int create);
+int ext4_dio_get_block(struct inode *inode, sector_t iblock,
+		       struct buffer_head *bh_result, int create);
 int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 			   struct buffer_head *bh, int create);
 int ext4_walk_page_buffers(handle_t *handle,
@@ -2558,6 +2549,9 @@ extern void ext4_da_update_reserve_space(struct inode *inode,
 					int used, int quota_claim);
 extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
 			      ext4_fsblk_t pblk, ext4_lblk_t len);
+extern int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk,
+				unsigned int map_len,
+				struct extent_status *result);
 
 /* indirect.c */
 extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
@@ -3284,15 +3278,33 @@ static inline void ext4_inode_resume_unlocked_dio(struct inode *inode)
 #define EXT4_WQ_HASH_SZ		37
 #define ext4_ioend_wq(v)   (&ext4__ioend_wq[((unsigned long)(v)) %\
 					    EXT4_WQ_HASH_SZ])
-#define ext4_aio_mutex(v)  (&ext4__aio_mutex[((unsigned long)(v)) %\
-					     EXT4_WQ_HASH_SZ])
 extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
-extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
 
 #define EXT4_RESIZING	0
 extern int ext4_resize_begin(struct super_block *sb);
 extern void ext4_resize_end(struct super_block *sb);
 
+static inline void ext4_set_io_unwritten_flag(struct inode *inode,
+					      struct ext4_io_end *io_end)
+{
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		io_end->flag |= EXT4_IO_END_UNWRITTEN;
+		atomic_inc(&EXT4_I(inode)->i_unwritten);
+	}
+}
+
+static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
+{
+	struct inode *inode = io_end->inode;
+
+	if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
+		io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
+		/* Wake up anyone waiting on unwritten extent conversion */
+		if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
+			wake_up_all(ext4_ioend_wq(inode));
+	}
+}
+
 #endif	/* __KERNEL__ */
 
 #define EFSBADCRC	EBADMSG		/* Bad CRC detected */
diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h
index ac7d4e813796..1f73c29717e1 100644
--- a/fs/ext4/ext4_crypto.h
+++ b/fs/ext4/ext4_crypto.h
@@ -77,7 +77,7 @@ struct ext4_crypt_info {
 	char		ci_data_mode;
 	char		ci_filename_mode;
 	char		ci_flags;
-	struct crypto_ablkcipher *ci_ctfm;
+	struct crypto_skcipher *ci_ctfm;
 	struct key	*ci_keyring_key;
 	char		ci_master_key[EXT4_KEY_DESCRIPTOR_SIZE];
 };
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 3c9381547094..8ecf84b8f5a1 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -11,7 +11,7 @@
  * 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 Licens
+ * 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-
  */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0ffabaf90aa5..95bf4679ac54 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -15,7 +15,7 @@
  * 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 Licens
+ * 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-
  */
@@ -1736,6 +1736,12 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 	 */
 	if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
 		return 0;
+	/*
+	 * The check for IO to unwritten extent is somewhat racy as we
+	 * increment i_unwritten / set EXT4_STATE_DIO_UNWRITTEN only after
+	 * dropping i_data_sem. But reserved blocks should save us in that
+	 * case.
+	 */
 	if (ext4_ext_is_unwritten(ex1) &&
 	    (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
 	     atomic_read(&EXT4_I(inode)->i_unwritten) ||
@@ -2293,59 +2299,69 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 }
 
 /*
- * ext4_ext_put_gap_in_cache:
- * calculate boundaries of the gap that the requested block fits into
- * and cache this gap
+ * ext4_ext_determine_hole - determine hole around given block
+ * @inode:	inode we lookup in
+ * @path:	path in extent tree to @lblk
+ * @lblk:	pointer to logical block around which we want to determine hole
+ *
+ * Determine hole length (and start if easily possible) around given logical
+ * block. We don't try too hard to find the beginning of the hole but @path
+ * actually points to extent before @lblk, we provide it.
+ *
+ * The function returns the length of a hole starting at @lblk. We update @lblk
+ * to the beginning of the hole if we managed to find it.
  */
-static void
-ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
-				ext4_lblk_t block)
+static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
+					   struct ext4_ext_path *path,
+					   ext4_lblk_t *lblk)
 {
 	int depth = ext_depth(inode);
-	ext4_lblk_t len;
-	ext4_lblk_t lblock;
 	struct ext4_extent *ex;
-	struct extent_status es;
+	ext4_lblk_t len;
 
 	ex = path[depth].p_ext;
 	if (ex == NULL) {
 		/* there is no extent yet, so gap is [0;-] */
-		lblock = 0;
+		*lblk = 0;
 		len = EXT_MAX_BLOCKS;
-		ext_debug("cache gap(whole file):");
-	} else if (block < le32_to_cpu(ex->ee_block)) {
-		lblock = block;
-		len = le32_to_cpu(ex->ee_block) - block;
-		ext_debug("cache gap(before): %u [%u:%u]",
-				block,
-				le32_to_cpu(ex->ee_block),
-				 ext4_ext_get_actual_len(ex));
-	} else if (block >= le32_to_cpu(ex->ee_block)
+	} else if (*lblk < le32_to_cpu(ex->ee_block)) {
+		len = le32_to_cpu(ex->ee_block) - *lblk;
+	} else if (*lblk >= le32_to_cpu(ex->ee_block)
 			+ ext4_ext_get_actual_len(ex)) {
 		ext4_lblk_t next;
-		lblock = le32_to_cpu(ex->ee_block)
-			+ ext4_ext_get_actual_len(ex);
 
+		*lblk = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
 		next = ext4_ext_next_allocated_block(path);
-		ext_debug("cache gap(after): [%u:%u] %u",
-				le32_to_cpu(ex->ee_block),
-				ext4_ext_get_actual_len(ex),
-				block);
-		BUG_ON(next == lblock);
-		len = next - lblock;
+		BUG_ON(next == *lblk);
+		len = next - *lblk;
 	} else {
 		BUG();
 	}
+	return len;
+}
 
-	ext4_es_find_delayed_extent_range(inode, lblock, lblock + len - 1, &es);
+/*
+ * ext4_ext_put_gap_in_cache:
+ * calculate boundaries of the gap that the requested block fits into
+ * and cache this gap
+ */
+static void
+ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start,
+			  ext4_lblk_t hole_len)
+{
+	struct extent_status es;
+
+	ext4_es_find_delayed_extent_range(inode, hole_start,
+					  hole_start + hole_len - 1, &es);
 	if (es.es_len) {
 		/* There's delayed extent containing lblock? */
-		if (es.es_lblk <= lblock)
+		if (es.es_lblk <= hole_start)
 			return;
-		len = min(es.es_lblk - lblock, len);
+		hole_len = min(es.es_lblk - hole_start, hole_len);
 	}
-	ext_debug(" -> %u:%u\n", lblock, len);
-	ext4_es_insert_extent(inode, lblock, len, ~0, EXTENT_STATUS_HOLE);
+	ext_debug(" -> %u:%u\n", hole_start, hole_len);
+	ext4_es_insert_extent(inode, hole_start, hole_len, ~0,
+			      EXTENT_STATUS_HOLE);
 }
 
 /*
@@ -3927,8 +3943,8 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 static int
 convert_initialized_extent(handle_t *handle, struct inode *inode,
 			   struct ext4_map_blocks *map,
-			   struct ext4_ext_path **ppath, int flags,
-			   unsigned int allocated, ext4_fsblk_t newblock)
+			   struct ext4_ext_path **ppath,
+			   unsigned int allocated)
 {
 	struct ext4_ext_path *path = *ppath;
 	struct ext4_extent *ex;
@@ -4007,7 +4023,6 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 	struct ext4_ext_path *path = *ppath;
 	int ret = 0;
 	int err = 0;
-	ext4_io_end_t *io = ext4_inode_aio(inode);
 
 	ext_debug("ext4_ext_handle_unwritten_extents: inode %lu, logical "
 		  "block %llu, max_blocks %u, flags %x, allocated %u\n",
@@ -4030,15 +4045,6 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 					 flags | EXT4_GET_BLOCKS_CONVERT);
 		if (ret <= 0)
 			goto out;
-		/*
-		 * Flag the inode(non aio case) or end_io struct (aio case)
-		 * that this IO needs to conversion to written when IO is
-		 * completed
-		 */
-		if (io)
-			ext4_set_io_unwritten_flag(inode, io);
-		else
-			ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 		map->m_flags |= EXT4_MAP_UNWRITTEN;
 		goto out;
 	}
@@ -4283,9 +4289,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	unsigned int allocated = 0, offset = 0;
 	unsigned int allocated_clusters = 0;
 	struct ext4_allocation_request ar;
-	ext4_io_end_t *io = ext4_inode_aio(inode);
 	ext4_lblk_t cluster_offset;
-	int set_unwritten = 0;
 	bool map_from_cluster = false;
 
 	ext_debug("blocks %u/%u requested for inode %lu\n",
@@ -4347,7 +4351,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			    (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
 				allocated = convert_initialized_extent(
 						handle, inode, map, &path,
-						flags, allocated, newblock);
+						allocated);
 				goto out2;
 			} else if (!ext4_ext_is_unwritten(ex))
 				goto out;
@@ -4368,11 +4372,22 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 * we couldn't try to create block if create flag is zero
 	 */
 	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+		ext4_lblk_t hole_start, hole_len;
+
+		hole_start = map->m_lblk;
+		hole_len = ext4_ext_determine_hole(inode, path, &hole_start);
 		/*
 		 * put just found gap into cache to speed up
 		 * subsequent requests
 		 */
-		ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
+		ext4_ext_put_gap_in_cache(inode, hole_start, hole_len);
+
+		/* Update hole_len to reflect hole size after map->m_lblk */
+		if (hole_start != map->m_lblk)
+			hole_len -= map->m_lblk - hole_start;
+		map->m_pblk = 0;
+		map->m_len = min_t(unsigned int, map->m_len, hole_len);
+
 		goto out2;
 	}
 
@@ -4482,15 +4497,6 @@ got_allocated_blocks:
 	if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT){
 		ext4_ext_mark_unwritten(&newex);
 		map->m_flags |= EXT4_MAP_UNWRITTEN;
-		/*
-		 * io_end structure was created for every IO write to an
-		 * unwritten extent. To avoid unnecessary conversion,
-		 * here we flag the IO that really needs the conversion.
-		 * For non asycn direct IO case, flag the inode state
-		 * that we need to perform conversion when IO is done.
-		 */
-		if (flags & EXT4_GET_BLOCKS_PRE_IO)
-			set_unwritten = 1;
 	}
 
 	err = 0;
@@ -4501,14 +4507,6 @@ got_allocated_blocks:
 		err = ext4_ext_insert_extent(handle, inode, &path,
 					     &newex, flags);
 
-	if (!err && set_unwritten) {
-		if (io)
-			ext4_set_io_unwritten_flag(inode, io);
-		else
-			ext4_set_inode_state(inode,
-					     EXT4_STATE_DIO_UNWRITTEN);
-	}
-
 	if (err && free_on_err) {
 		int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
 			EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index ac748b3af1c1..e38b987ac7f5 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -823,8 +823,8 @@ out:
 		es->es_lblk = es1->es_lblk;
 		es->es_len = es1->es_len;
 		es->es_pblk = es1->es_pblk;
-		if (!ext4_es_is_referenced(es))
-			ext4_es_set_referenced(es);
+		if (!ext4_es_is_referenced(es1))
+			ext4_es_set_referenced(es1);
 		stats->es_stats_cache_hits++;
 	} else {
 		stats->es_stats_cache_misses++;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 1126436dada1..6659e216385e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -93,31 +93,29 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(iocb->ki_filp);
-	struct mutex *aio_mutex = NULL;
 	struct blk_plug plug;
 	int o_direct = iocb->ki_flags & IOCB_DIRECT;
+	int unaligned_aio = 0;
 	int overwrite = 0;
 	ssize_t ret;
 
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
 	/*
-	 * Unaligned direct AIO must be serialized; see comment above
-	 * In the case of O_APPEND, assume that we must always serialize
+	 * Unaligned direct AIO must be serialized among each other as zeroing
+	 * of partial blocks of two competing unaligned AIOs can result in data
+	 * corruption.
 	 */
-	if (o_direct &&
-	    ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+	if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
 	    !is_sync_kiocb(iocb) &&
-	    (iocb->ki_flags & IOCB_APPEND ||
-	     ext4_unaligned_aio(inode, from, iocb->ki_pos))) {
-		aio_mutex = ext4_aio_mutex(inode);
-		mutex_lock(aio_mutex);
+	    ext4_unaligned_aio(inode, from, iocb->ki_pos)) {
+		unaligned_aio = 1;
 		ext4_unwritten_wait(inode);
 	}
 
-	inode_lock(inode);
-	ret = generic_write_checks(iocb, from);
-	if (ret <= 0)
-		goto out;
-
 	/*
 	 * If we have encountered a bitmap-format file, the size limit
 	 * is smaller than s_maxbytes, which is for extent-mapped files.
@@ -139,7 +137,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		blk_start_plug(&plug);
 
 		/* check whether we do a DIO overwrite or not */
-		if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
+		if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
 		    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
 			struct ext4_map_blocks map;
 			unsigned int blkbits = inode->i_blkbits;
@@ -181,14 +179,10 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (o_direct)
 		blk_finish_plug(&plug);
 
-	if (aio_mutex)
-		mutex_unlock(aio_mutex);
 	return ret;
 
 out:
 	inode_unlock(inode);
-	if (aio_mutex)
-		mutex_unlock(aio_mutex);
 	return ret;
 }
 
@@ -262,23 +256,8 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return result;
 }
 
-static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	int err;
-	struct inode *inode = file_inode(vma->vm_file);
-
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-	sb_end_pagefault(inode->i_sb);
-
-	return err;
-}
-
 /*
- * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite()
+ * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault()
  * handler we check for races agaist truncate. Note that since we cycle through
  * i_mmap_sem, we are sure that also any hole punching that began before we
  * were called is finished by now and so if it included part of the file we
@@ -311,7 +290,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
 	.pmd_fault	= ext4_dax_pmd_fault,
-	.page_mkwrite	= ext4_dax_mkwrite,
+	.page_mkwrite	= ext4_dax_fault,
 	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
 };
 #else
@@ -350,6 +329,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	struct super_block *sb = inode->i_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct vfsmount *mnt = filp->f_path.mnt;
+	struct inode *dir = filp->f_path.dentry->d_parent->d_inode;
 	struct path path;
 	char buf[64], *cp;
 	int ret;
@@ -393,6 +373,14 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		if (ext4_encryption_info(inode) == NULL)
 			return -ENOKEY;
 	}
+	if (ext4_encrypted_inode(dir) &&
+	    !ext4_is_child_context_consistent_with_parent(dir, inode)) {
+		ext4_warning(inode->i_sb,
+			     "Inconsistent encryption contexts: %lu/%lu\n",
+			     (unsigned long) dir->i_ino,
+			     (unsigned long) inode->i_ino);
+		return -EPERM;
+	}
 	/*
 	 * Set up the jbd2_inode if we are opening the inode for
 	 * writing and the journal is present
@@ -423,7 +411,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
  */
 static int ext4_find_unwritten_pgoff(struct inode *inode,
 				     int whence,
-				     struct ext4_map_blocks *map,
+				     ext4_lblk_t end_blk,
 				     loff_t *offset)
 {
 	struct pagevec pvec;
@@ -438,7 +426,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 	blkbits = inode->i_sb->s_blocksize_bits;
 	startoff = *offset;
 	lastoff = startoff;
-	endoff = (loff_t)(map->m_lblk + map->m_len) << blkbits;
+	endoff = (loff_t)end_blk << blkbits;
 
 	index = startoff >> PAGE_CACHE_SHIFT;
 	end = endoff >> PAGE_CACHE_SHIFT;
@@ -556,12 +544,11 @@ out:
 static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 {
 	struct inode *inode = file->f_mapping->host;
-	struct ext4_map_blocks map;
 	struct extent_status es;
 	ext4_lblk_t start, last, end;
 	loff_t dataoff, isize;
 	int blkbits;
-	int ret = 0;
+	int ret;
 
 	inode_lock(inode);
 
@@ -578,41 +565,32 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 	dataoff = offset;
 
 	do {
-		map.m_lblk = last;
-		map.m_len = end - last + 1;
-		ret = ext4_map_blocks(NULL, inode, &map, 0);
-		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
-			if (last != start)
-				dataoff = (loff_t)last << blkbits;
-			break;
+		ret = ext4_get_next_extent(inode, last, end - last + 1, &es);
+		if (ret <= 0) {
+			/* No extent found -> no data */
+			if (ret == 0)
+				ret = -ENXIO;
+			inode_unlock(inode);
+			return ret;
 		}
 
-		/*
-		 * If there is a delay extent at this offset,
-		 * it will be as a data.
-		 */
-		ext4_es_find_delayed_extent_range(inode, last, last, &es);
-		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
-			if (last != start)
-				dataoff = (loff_t)last << blkbits;
+		last = es.es_lblk;
+		if (last != start)
+			dataoff = (loff_t)last << blkbits;
+		if (!ext4_es_is_unwritten(&es))
 			break;
-		}
 
 		/*
 		 * If there is a unwritten extent at this offset,
 		 * it will be as a data or a hole according to page
 		 * cache that has data or not.
 		 */
-		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
-			int unwritten;
-			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA,
-							      &map, &dataoff);
-			if (unwritten)
-				break;
-		}
-
-		last++;
+		if (ext4_find_unwritten_pgoff(inode, SEEK_DATA,
+					      es.es_lblk + es.es_len, &dataoff))
+			break;
+		last += es.es_len;
 		dataoff = (loff_t)last << blkbits;
+		cond_resched();
 	} while (last <= end);
 
 	inode_unlock(inode);
@@ -629,12 +607,11 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
 {
 	struct inode *inode = file->f_mapping->host;
-	struct ext4_map_blocks map;
 	struct extent_status es;
 	ext4_lblk_t start, last, end;
 	loff_t holeoff, isize;
 	int blkbits;
-	int ret = 0;
+	int ret;
 
 	inode_lock(inode);
 
@@ -651,44 +628,30 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
 	holeoff = offset;
 
 	do {
-		map.m_lblk = last;
-		map.m_len = end - last + 1;
-		ret = ext4_map_blocks(NULL, inode, &map, 0);
-		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
-			last += ret;
-			holeoff = (loff_t)last << blkbits;
-			continue;
+		ret = ext4_get_next_extent(inode, last, end - last + 1, &es);
+		if (ret < 0) {
+			inode_unlock(inode);
+			return ret;
 		}
-
-		/*
-		 * If there is a delay extent at this offset,
-		 * we will skip this extent.
-		 */
-		ext4_es_find_delayed_extent_range(inode, last, last, &es);
-		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
-			last = es.es_lblk + es.es_len;
-			holeoff = (loff_t)last << blkbits;
-			continue;
+		/* Found a hole? */
+		if (ret == 0 || es.es_lblk > last) {
+			if (last != start)
+				holeoff = (loff_t)last << blkbits;
+			break;
 		}
-
 		/*
 		 * If there is a unwritten extent at this offset,
 		 * it will be as a data or a hole according to page
 		 * cache that has data or not.
 		 */
-		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
-			int unwritten;
-			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
-							      &map, &holeoff);
-			if (!unwritten) {
-				last += ret;
-				holeoff = (loff_t)last << blkbits;
-				continue;
-			}
-		}
+		if (ext4_es_is_unwritten(&es) &&
+		    ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
+					      last + es.es_len, &holeoff))
+			break;
 
-		/* find a hole */
-		break;
+		last += es.es_len;
+		holeoff = (loff_t)last << blkbits;
+		cond_resched();
 	} while (last <= end);
 
 	inode_unlock(inode);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 3fcfd50a2e8a..237b877d316d 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks and inodes use to prevent
 	 * allocation, essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		set_buffer_verified(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err)
+		if (err) {
+			ext4_error(sb, "Failed to init inode bitmap for group "
+				   "%u: %d", block_group, err);
 			goto out;
+		}
 		return bh;
 	}
 	ext4_unlock_group(sb, block_group);
@@ -785,7 +787,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	sbi = EXT4_SB(sb);
 
 	/*
-	 * Initalize owners and quota early so that we don't have to account
+	 * Initialize owners and quota early so that we don't have to account
 	 * for quota initialization worst case in standard inode creating
 	 * transaction
 	 */
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 355ef9c36c87..3027fa681de5 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -555,8 +555,23 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 		goto got_it;
 	}
 
-	/* Next simple case - plain lookup or failed read of indirect block */
-	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO)
+	/* Next simple case - plain lookup failed */
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+		unsigned epb = inode->i_sb->s_blocksize / sizeof(u32);
+		int i;
+
+		/* Count number blocks in a subtree under 'partial' */
+		count = 1;
+		for (i = 0; partial + i != chain + depth - 1; i++)
+			count *= epb;
+		/* Fill in size of a hole we found */
+		map->m_pblk = 0;
+		map->m_len = min_t(unsigned int, map->m_len, count);
+		goto cleanup;
+	}
+
+	/* Failed read of indirect block */
+	if (err == -EIO)
 		goto cleanup;
 
 	/*
@@ -693,21 +708,21 @@ retry:
 		}
 		if (IS_DAX(inode))
 			ret = dax_do_io(iocb, inode, iter, offset,
-					ext4_get_block, NULL, 0);
+					ext4_dio_get_block, NULL, 0);
 		else
 			ret = __blockdev_direct_IO(iocb, inode,
 						   inode->i_sb->s_bdev, iter,
-						   offset, ext4_get_block, NULL,
-						   NULL, 0);
+						   offset, ext4_dio_get_block,
+						   NULL, NULL, 0);
 		inode_dio_end(inode);
 	} else {
 locked:
 		if (IS_DAX(inode))
 			ret = dax_do_io(iocb, inode, iter, offset,
-					ext4_get_block, NULL, DIO_LOCKING);
+					ext4_dio_get_block, NULL, DIO_LOCKING);
 		else
 			ret = blockdev_direct_IO(iocb, inode, iter, offset,
-						 ext4_get_block);
+						 ext4_dio_get_block);
 
 		if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
 			loff_t isize = i_size_read(inode);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index dfe3b9bafc0d..7cbdd3752ba5 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -581,9 +581,10 @@ retry:
 	if (ret)
 		goto out;
 
-	if (ext4_should_dioread_nolock(inode))
-		ret = __block_write_begin(page, from, to, ext4_get_block_write);
-	else
+	if (ext4_should_dioread_nolock(inode)) {
+		ret = __block_write_begin(page, from, to,
+					  ext4_get_block_unwritten);
+	} else
 		ret = __block_write_begin(page, from, to, ext4_get_block);
 
 	if (!ret && ext4_should_journal_data(inode)) {
@@ -1696,7 +1697,6 @@ int ext4_delete_inline_entry(handle_t *handle,
 	if (err)
 		goto out;
 
-	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
 	err = ext4_mark_inode_dirty(handle, dir);
 	if (unlikely(err))
 		goto out;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 83bc8bfb3bea..dab84a2530ff 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -216,7 +216,6 @@ void ext4_evict_inode(struct inode *inode)
 		}
 		truncate_inode_pages_final(&inode->i_data);
 
-		WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
 		goto no_delete;
 	}
 
@@ -228,8 +227,6 @@ void ext4_evict_inode(struct inode *inode)
 		ext4_begin_ordered_truncate(inode, 0);
 	truncate_inode_pages_final(&inode->i_data);
 
-	WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
-
 	/*
 	 * Protect us against freezing - iput() caller didn't have to have any
 	 * protection against it
@@ -458,13 +455,13 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
  * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
  * based files
  *
- * On success, it returns the number of blocks being mapped or allocated.
- * if create==0 and the blocks are pre-allocated and unwritten block,
- * the result buffer head is unmapped. If the create ==1, it will make sure
- * the buffer head is mapped.
+ * On success, it returns the number of blocks being mapped or allocated.  if
+ * create==0 and the blocks are pre-allocated and unwritten, the resulting @map
+ * is marked as unwritten. If the create == 1, it will mark @map as mapped.
  *
  * It returns 0 if plain look up failed (blocks have not been allocated), in
- * that case, buffer head is unmapped
+ * that case, @map is returned as unmapped but we still do fill map->m_len to
+ * indicate the length of a hole starting at map->m_lblk.
  *
  * It returns the error in case of allocation failure.
  */
@@ -507,6 +504,11 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 				retval = map->m_len;
 			map->m_len = retval;
 		} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
+			map->m_pblk = 0;
+			retval = es.es_len - (map->m_lblk - es.es_lblk);
+			if (retval > map->m_len)
+				retval = map->m_len;
+			map->m_len = retval;
 			retval = 0;
 		} else {
 			BUG_ON(1);
@@ -686,16 +688,39 @@ out_sem:
 	return retval;
 }
 
-/* Maximum number of blocks we map for direct IO at once. */
-#define DIO_MAX_BLOCKS 4096
+/*
+ * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
+ * we have to be careful as someone else may be manipulating b_state as well.
+ */
+static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
+{
+	unsigned long old_state;
+	unsigned long new_state;
+
+	flags &= EXT4_MAP_FLAGS;
+
+	/* Dummy buffer_head? Set non-atomically. */
+	if (!bh->b_page) {
+		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
+		return;
+	}
+	/*
+	 * Someone else may be modifying b_state. Be careful! This is ugly but
+	 * once we get rid of using bh as a container for mapping information
+	 * to pass to / from get_block functions, this can go away.
+	 */
+	do {
+		old_state = READ_ONCE(bh->b_state);
+		new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
+	} while (unlikely(
+		 cmpxchg(&bh->b_state, old_state, new_state) != old_state));
+}
 
 static int _ext4_get_block(struct inode *inode, sector_t iblock,
 			   struct buffer_head *bh, int flags)
 {
-	handle_t *handle = ext4_journal_current_handle();
 	struct ext4_map_blocks map;
-	int ret = 0, started = 0;
-	int dio_credits;
+	int ret = 0;
 
 	if (ext4_has_inline_data(inode))
 		return -ERANGE;
@@ -703,33 +728,14 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
 
-	if (flags && !handle) {
-		/* Direct IO write... */
-		if (map.m_len > DIO_MAX_BLOCKS)
-			map.m_len = DIO_MAX_BLOCKS;
-		dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
-		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
-					    dio_credits);
-		if (IS_ERR(handle)) {
-			ret = PTR_ERR(handle);
-			return ret;
-		}
-		started = 1;
-	}
-
-	ret = ext4_map_blocks(handle, inode, &map, flags);
+	ret = ext4_map_blocks(ext4_journal_current_handle(), inode, &map,
+			      flags);
 	if (ret > 0) {
-		ext4_io_end_t *io_end = ext4_inode_aio(inode);
-
 		map_bh(bh, inode->i_sb, map.m_pblk);
-		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
-		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
-			set_buffer_defer_completion(bh);
+		ext4_update_bh_state(bh, map.m_flags);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
 		ret = 0;
 	}
-	if (started)
-		ext4_journal_stop(handle);
 	return ret;
 }
 
@@ -741,6 +747,155 @@ int ext4_get_block(struct inode *inode, sector_t iblock,
 }
 
 /*
+ * Get block function used when preparing for buffered write if we require
+ * creating an unwritten extent if blocks haven't been allocated.  The extent
+ * will be converted to written after the IO is complete.
+ */
+int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
+			     struct buffer_head *bh_result, int create)
+{
+	ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n",
+		   inode->i_ino, create);
+	return _ext4_get_block(inode, iblock, bh_result,
+			       EXT4_GET_BLOCKS_IO_CREATE_EXT);
+}
+
+/* Maximum number of blocks we map for direct IO at once. */
+#define DIO_MAX_BLOCKS 4096
+
+static handle_t *start_dio_trans(struct inode *inode,
+				 struct buffer_head *bh_result)
+{
+	int dio_credits;
+
+	/* Trim mapping request to maximum we can map at once for DIO */
+	if (bh_result->b_size >> inode->i_blkbits > DIO_MAX_BLOCKS)
+		bh_result->b_size = DIO_MAX_BLOCKS << inode->i_blkbits;
+	dio_credits = ext4_chunk_trans_blocks(inode,
+				      bh_result->b_size >> inode->i_blkbits);
+	return ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
+}
+
+/* Get block function for DIO reads and writes to inodes without extents */
+int ext4_dio_get_block(struct inode *inode, sector_t iblock,
+		       struct buffer_head *bh, int create)
+{
+	handle_t *handle;
+	int ret;
+
+	/* We don't expect handle for direct IO */
+	WARN_ON_ONCE(ext4_journal_current_handle());
+
+	if (create) {
+		handle = start_dio_trans(inode, bh);
+		if (IS_ERR(handle))
+			return PTR_ERR(handle);
+	}
+	ret = _ext4_get_block(inode, iblock, bh,
+			      create ? EXT4_GET_BLOCKS_CREATE : 0);
+	if (create)
+		ext4_journal_stop(handle);
+	return ret;
+}
+
+/*
+ * Get block function for AIO DIO writes when we create unwritten extent if
+ * blocks are not allocated yet. The extent will be converted to written
+ * after IO is complete.
+ */
+static int ext4_dio_get_block_unwritten_async(struct inode *inode,
+		sector_t iblock, struct buffer_head *bh_result,	int create)
+{
+	handle_t *handle;
+	int ret;
+
+	/* We don't expect handle for direct IO */
+	WARN_ON_ONCE(ext4_journal_current_handle());
+
+	handle = start_dio_trans(inode, bh_result);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	ret = _ext4_get_block(inode, iblock, bh_result,
+			      EXT4_GET_BLOCKS_IO_CREATE_EXT);
+	ext4_journal_stop(handle);
+
+	/*
+	 * When doing DIO using unwritten extents, we need io_end to convert
+	 * unwritten extents to written on IO completion. We allocate io_end
+	 * once we spot unwritten extent and store it in b_private. Generic
+	 * DIO code keeps b_private set and furthermore passes the value to
+	 * our completion callback in 'private' argument.
+	 */
+	if (!ret && buffer_unwritten(bh_result)) {
+		if (!bh_result->b_private) {
+			ext4_io_end_t *io_end;
+
+			io_end = ext4_init_io_end(inode, GFP_KERNEL);
+			if (!io_end)
+				return -ENOMEM;
+			bh_result->b_private = io_end;
+			ext4_set_io_unwritten_flag(inode, io_end);
+		}
+		set_buffer_defer_completion(bh_result);
+	}
+
+	return ret;
+}
+
+/*
+ * Get block function for non-AIO DIO writes when we create unwritten extent if
+ * blocks are not allocated yet. The extent will be converted to written
+ * after IO is complete from ext4_ext_direct_IO() function.
+ */
+static int ext4_dio_get_block_unwritten_sync(struct inode *inode,
+		sector_t iblock, struct buffer_head *bh_result,	int create)
+{
+	handle_t *handle;
+	int ret;
+
+	/* We don't expect handle for direct IO */
+	WARN_ON_ONCE(ext4_journal_current_handle());
+
+	handle = start_dio_trans(inode, bh_result);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	ret = _ext4_get_block(inode, iblock, bh_result,
+			      EXT4_GET_BLOCKS_IO_CREATE_EXT);
+	ext4_journal_stop(handle);
+
+	/*
+	 * Mark inode as having pending DIO writes to unwritten extents.
+	 * ext4_ext_direct_IO() checks this flag and converts extents to
+	 * written.
+	 */
+	if (!ret && buffer_unwritten(bh_result))
+		ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
+
+	return ret;
+}
+
+static int ext4_dio_get_block_overwrite(struct inode *inode, sector_t iblock,
+		   struct buffer_head *bh_result, int create)
+{
+	int ret;
+
+	ext4_debug("ext4_dio_get_block_overwrite: inode %lu, create flag %d\n",
+		   inode->i_ino, create);
+	/* We don't expect handle for direct IO */
+	WARN_ON_ONCE(ext4_journal_current_handle());
+
+	ret = _ext4_get_block(inode, iblock, bh_result, 0);
+	/*
+	 * Blocks should have been preallocated! ext4_file_write_iter() checks
+	 * that.
+	 */
+	WARN_ON_ONCE(!buffer_mapped(bh_result) || buffer_unwritten(bh_result));
+
+	return ret;
+}
+
+
+/*
  * `handle' can be NULL if create is zero
  */
 struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
@@ -1051,13 +1206,14 @@ retry_journal:
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 	if (ext4_should_dioread_nolock(inode))
 		ret = ext4_block_write_begin(page, pos, len,
-					     ext4_get_block_write);
+					     ext4_get_block_unwritten);
 	else
 		ret = ext4_block_write_begin(page, pos, len,
 					     ext4_get_block);
 #else
 	if (ext4_should_dioread_nolock(inode))
-		ret = __block_write_begin(page, pos, len, ext4_get_block_write);
+		ret = __block_write_begin(page, pos, len,
+					  ext4_get_block_unwritten);
 	else
 		ret = __block_write_begin(page, pos, len, ext4_get_block);
 #endif
@@ -1685,7 +1841,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		return ret;
 
 	map_bh(bh, inode->i_sb, map.m_pblk);
-	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+	ext4_update_bh_state(bh, map.m_flags);
 
 	if (buffer_unwritten(bh)) {
 		/* A delayed write to unwritten bh should be marked
@@ -2450,6 +2606,10 @@ static int ext4_writepages(struct address_space *mapping,
 
 	trace_ext4_writepages(inode, wbc);
 
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
+						   wbc);
+
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
 	 * a transaction for special inodes like journal inode on last iput()
@@ -3056,37 +3216,6 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 		return try_to_free_buffers(page);
 }
 
-/*
- * ext4_get_block used when preparing for a DIO write or buffer write.
- * We allocate an uinitialized extent if blocks haven't been allocated.
- * The extent will be converted to initialized after the IO is complete.
- */
-int ext4_get_block_write(struct inode *inode, sector_t iblock,
-		   struct buffer_head *bh_result, int create)
-{
-	ext4_debug("ext4_get_block_write: inode %lu, create flag %d\n",
-		   inode->i_ino, create);
-	return _ext4_get_block(inode, iblock, bh_result,
-			       EXT4_GET_BLOCKS_IO_CREATE_EXT);
-}
-
-static int ext4_get_block_overwrite(struct inode *inode, sector_t iblock,
-		   struct buffer_head *bh_result, int create)
-{
-	int ret;
-
-	ext4_debug("ext4_get_block_overwrite: inode %lu, create flag %d\n",
-		   inode->i_ino, create);
-	ret = _ext4_get_block(inode, iblock, bh_result, 0);
-	/*
-	 * Blocks should have been preallocated! ext4_file_write_iter() checks
-	 * that.
-	 */
-	WARN_ON_ONCE(!buffer_mapped(bh_result));
-
-	return ret;
-}
-
 #ifdef CONFIG_FS_DAX
 int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
 			    struct buffer_head *bh_result, int create)
@@ -3147,13 +3276,12 @@ out:
 	WARN_ON_ONCE(ret == 0 && create);
 	if (ret > 0) {
 		map_bh(bh_result, inode->i_sb, map.m_pblk);
-		bh_result->b_state = (bh_result->b_state & ~EXT4_MAP_FLAGS) |
-					map.m_flags;
 		/*
 		 * At least for now we have to clear BH_New so that DAX code
 		 * doesn't attempt to zero blocks again in a racy way.
 		 */
-		bh_result->b_state &= ~(1 << BH_New);
+		map.m_flags &= ~EXT4_MAP_NEW;
+		ext4_update_bh_state(bh_result, map.m_flags);
 		bh_result->b_size = map.m_len << inode->i_blkbits;
 		ret = 0;
 	}
@@ -3161,24 +3289,32 @@ out:
 }
 #endif
 
-static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
+static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 			    ssize_t size, void *private)
 {
-        ext4_io_end_t *io_end = iocb->private;
+        ext4_io_end_t *io_end = private;
 
 	/* if not async direct IO just return */
 	if (!io_end)
-		return;
+		return 0;
 
 	ext_debug("ext4_end_io_dio(): io_end 0x%p "
 		  "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
- 		  iocb->private, io_end->inode->i_ino, iocb, offset,
-		  size);
+		  io_end, io_end->inode->i_ino, iocb, offset, size);
 
-	iocb->private = NULL;
+	/*
+	 * Error during AIO DIO. We cannot convert unwritten extents as the
+	 * data was not written. Just clear the unwritten flag and drop io_end.
+	 */
+	if (size <= 0) {
+		ext4_clear_io_unwritten_flag(io_end);
+		size = 0;
+	}
 	io_end->offset = offset;
 	io_end->size = size;
 	ext4_put_io_end(io_end);
+
+	return 0;
 }
 
 /*
@@ -3211,7 +3347,6 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	get_block_t *get_block_func = NULL;
 	int dio_flags = 0;
 	loff_t final_size = offset + count;
-	ext4_io_end_t *io_end = NULL;
 
 	/* Use the old path for reads and writes beyond i_size. */
 	if (iov_iter_rw(iter) != WRITE || final_size > inode->i_size)
@@ -3236,16 +3371,17 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	/*
 	 * We could direct write to holes and fallocate.
 	 *
-	 * Allocated blocks to fill the hole are marked as
-	 * unwritten to prevent parallel buffered read to expose
-	 * the stale data before DIO complete the data IO.
+	 * Allocated blocks to fill the hole are marked as unwritten to prevent
+	 * parallel buffered read to expose the stale data before DIO complete
+	 * the data IO.
 	 *
-	 * As to previously fallocated extents, ext4 get_block will
-	 * just simply mark the buffer mapped but still keep the
-	 * extents unwritten.
+	 * As to previously fallocated extents, ext4 get_block will just simply
+	 * mark the buffer mapped but still keep the extents unwritten.
 	 *
-	 * For non AIO case, we will convert those unwritten extents
-	 * to written after return back from blockdev_direct_IO.
+	 * For non AIO case, we will convert those unwritten extents to written
+	 * after return back from blockdev_direct_IO. That way we save us from
+	 * allocating io_end structure and also the overhead of offloading
+	 * the extent convertion to a workqueue.
 	 *
 	 * For async DIO, the conversion needs to be deferred when the
 	 * IO is completed. The ext4 end_io callback function will be
@@ -3253,30 +3389,13 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	 * case, we allocate an io_end structure to hook to the iocb.
 	 */
 	iocb->private = NULL;
-	ext4_inode_aio_set(inode, NULL);
-	if (!is_sync_kiocb(iocb)) {
-		io_end = ext4_init_io_end(inode, GFP_NOFS);
-		if (!io_end) {
-			ret = -ENOMEM;
-			goto retake_lock;
-		}
-		/*
-		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
-		 */
-		iocb->private = ext4_get_io_end(io_end);
-		/*
-		 * we save the io structure for current async direct
-		 * IO, so that later ext4_map_blocks() could flag the
-		 * io structure whether there is a unwritten extents
-		 * needs to be converted when IO is completed.
-		 */
-		ext4_inode_aio_set(inode, io_end);
-	}
-
-	if (overwrite) {
-		get_block_func = ext4_get_block_overwrite;
+	if (overwrite)
+		get_block_func = ext4_dio_get_block_overwrite;
+	else if (is_sync_kiocb(iocb)) {
+		get_block_func = ext4_dio_get_block_unwritten_sync;
+		dio_flags = DIO_LOCKING;
 	} else {
-		get_block_func = ext4_get_block_write;
+		get_block_func = ext4_dio_get_block_unwritten_async;
 		dio_flags = DIO_LOCKING;
 	}
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
@@ -3291,27 +3410,6 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 					   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.
-	 * in sync IO case or in case of error. It can even perform extent
-	 * conversion if all bios we submitted finished before we got here.
-	 * Note that in that case iocb->private can be already set to NULL
-	 * here.
-	 */
-	if (io_end) {
-		ext4_inode_aio_set(inode, NULL);
-		ext4_put_io_end(io_end);
-		/*
-		 * When no IO was submitted ext4_end_io_dio() was not
-		 * called so we have to put iocb's reference.
-		 */
-		if (ret <= 0 && ret != -EIOCBQUEUED && iocb->private) {
-			WARN_ON(iocb->private != io_end);
-			WARN_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
-			ext4_put_io_end(io_end);
-			iocb->private = NULL;
-		}
-	}
 	if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
 						EXT4_STATE_DIO_UNWRITTEN)) {
 		int err;
@@ -3326,7 +3424,6 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 	}
 
-retake_lock:
 	if (iov_iter_rw(iter) == WRITE)
 		inode_dio_end(inode);
 	/* take i_mutex locking again if we do a ovewrite dio */
@@ -4127,7 +4224,7 @@ 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))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
 		new_fl |= S_DAX;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
@@ -5229,6 +5326,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 	might_sleep();
 	trace_ext4_mark_inode_dirty(inode, _RET_IP_);
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		return err;
 	if (ext4_handle_valid(handle) &&
 	    EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
 	    !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
@@ -5259,9 +5358,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 			}
 		}
 	}
-	if (!err)
-		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-	return err;
+	return ext4_mark_iloc_dirty(handle, inode, &iloc);
 }
 
 /*
@@ -5470,7 +5567,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	unlock_page(page);
 	/* OK, we need to fill the hole... */
 	if (ext4_should_dioread_nolock(inode))
-		get_block = ext4_get_block_write;
+		get_block = ext4_get_block_unwritten;
 	else
 		get_block = ext4_get_block;
 retry_alloc:
@@ -5513,3 +5610,70 @@ int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	return err;
 }
+
+/*
+ * Find the first extent at or after @lblk in an inode that is not a hole.
+ * Search for @map_len blocks at most. The extent is returned in @result.
+ *
+ * The function returns 1 if we found an extent. The function returns 0 in
+ * case there is no extent at or after @lblk and in that case also sets
+ * @result->es_len to 0. In case of error, the error code is returned.
+ */
+int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk,
+			 unsigned int map_len, struct extent_status *result)
+{
+	struct ext4_map_blocks map;
+	struct extent_status es = {};
+	int ret;
+
+	map.m_lblk = lblk;
+	map.m_len = map_len;
+
+	/*
+	 * For non-extent based files this loop may iterate several times since
+	 * we do not determine full hole size.
+	 */
+	while (map.m_len > 0) {
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0)
+			return ret;
+		/* There's extent covering m_lblk? Just return it. */
+		if (ret > 0) {
+			int status;
+
+			ext4_es_store_pblock(result, map.m_pblk);
+			result->es_lblk = map.m_lblk;
+			result->es_len = map.m_len;
+			if (map.m_flags & EXT4_MAP_UNWRITTEN)
+				status = EXTENT_STATUS_UNWRITTEN;
+			else
+				status = EXTENT_STATUS_WRITTEN;
+			ext4_es_store_status(result, status);
+			return 1;
+		}
+		ext4_es_find_delayed_extent_range(inode, map.m_lblk,
+						  map.m_lblk + map.m_len - 1,
+						  &es);
+		/* Is delalloc data before next block in extent tree? */
+		if (es.es_len && es.es_lblk < map.m_lblk + map.m_len) {
+			ext4_lblk_t offset = 0;
+
+			if (es.es_lblk < lblk)
+				offset = lblk - es.es_lblk;
+			result->es_lblk = es.es_lblk + offset;
+			ext4_es_store_pblock(result,
+					     ext4_es_pblock(&es) + offset);
+			result->es_len = es.es_len - offset;
+			ext4_es_store_status(result, ext4_es_status(&es));
+
+			return 1;
+		}
+		/* There's a hole at m_lblk, advance us after it */
+		map.m_lblk += map.m_len;
+		map_len -= map.m_len;
+		map.m_len = map_len;
+		cond_resched();
+	}
+	result->es_len = 0;
+	return 0;
+}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 0f6c36922c24..eae5917c534e 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -208,7 +208,7 @@ static int ext4_ioctl_setflags(struct inode *inode,
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	handle_t *handle = NULL;
-	int err = EPERM, migrate = 0;
+	int err = -EPERM, migrate = 0;
 	struct ext4_iloc iloc;
 	unsigned int oldflags, mask, i;
 	unsigned int jflag;
@@ -583,6 +583,11 @@ group_extend_out:
 				 "Online defrag not supported with bigalloc");
 			err = -EOPNOTSUPP;
 			goto mext_out;
+		} else if (IS_DAX(inode)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Online defrag not supported with DAX");
+			err = -EOPNOTSUPP;
+			goto mext_out;
 		}
 
 		err = mnt_want_write_file(filp);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 61eaf74dca37..50e05df28f66 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -11,7 +11,7 @@
  * 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 Licens
+ * 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-
  */
@@ -815,7 +815,7 @@ static void mb_regenerate_buddy(struct ext4_buddy *e4b)
  * for this page; do not hold this lock when calling this routine!
  */
 
-static int ext4_mb_init_cache(struct page *page, char *incore)
+static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 {
 	ext4_group_t ngroups;
 	int blocksize;
@@ -848,7 +848,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	/* allocate buffer_heads to read bitmaps */
 	if (groups_per_page > 1) {
 		i = sizeof(struct buffer_head *) * groups_per_page;
-		bh = kzalloc(i, GFP_NOFS);
+		bh = kzalloc(i, gfp);
 		if (bh == NULL) {
 			err = -ENOMEM;
 			goto out;
@@ -983,7 +983,7 @@ out:
  * are on the same page e4b->bd_buddy_page is NULL and return value is 0.
  */
 static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
-		ext4_group_t group, struct ext4_buddy *e4b)
+		ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp)
 {
 	struct inode *inode = EXT4_SB(sb)->s_buddy_cache;
 	int block, pnum, poff;
@@ -1002,7 +1002,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 	block = group * 2;
 	pnum = block / blocks_per_page;
 	poff = block % blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	page = find_or_create_page(inode->i_mapping, pnum, gfp);
 	if (!page)
 		return -ENOMEM;
 	BUG_ON(page->mapping != inode->i_mapping);
@@ -1016,7 +1016,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 
 	block++;
 	pnum = block / blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	page = find_or_create_page(inode->i_mapping, pnum, gfp);
 	if (!page)
 		return -ENOMEM;
 	BUG_ON(page->mapping != inode->i_mapping);
@@ -1042,7 +1042,7 @@ static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b)
  * calling this routine!
  */
 static noinline_for_stack
-int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
+int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp)
 {
 
 	struct ext4_group_info *this_grp;
@@ -1062,7 +1062,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	 * The call to ext4_mb_get_buddy_page_lock will mark the
 	 * page accessed.
 	 */
-	ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
+	ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b, gfp);
 	if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
 		/*
 		 * somebody initialized the group
@@ -1072,7 +1072,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	}
 
 	page = e4b.bd_bitmap_page;
-	ret = ext4_mb_init_cache(page, NULL);
+	ret = ext4_mb_init_cache(page, NULL, gfp);
 	if (ret)
 		goto err;
 	if (!PageUptodate(page)) {
@@ -1091,7 +1091,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	}
 	/* init buddy cache */
 	page = e4b.bd_buddy_page;
-	ret = ext4_mb_init_cache(page, e4b.bd_bitmap);
+	ret = ext4_mb_init_cache(page, e4b.bd_bitmap, gfp);
 	if (ret)
 		goto err;
 	if (!PageUptodate(page)) {
@@ -1109,8 +1109,8 @@ err:
  * calling this routine!
  */
 static noinline_for_stack int
-ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
-					struct ext4_buddy *e4b)
+ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
+		       struct ext4_buddy *e4b, gfp_t gfp)
 {
 	int blocks_per_page;
 	int block;
@@ -1140,7 +1140,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 		 * we need full data about the group
 		 * to make a good selection
 		 */
-		ret = ext4_mb_init_group(sb, group);
+		ret = ext4_mb_init_group(sb, group, gfp);
 		if (ret)
 			return ret;
 	}
@@ -1168,11 +1168,11 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 			 * wait for it to initialize.
 			 */
 			page_cache_release(page);
-		page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+		page = find_or_create_page(inode->i_mapping, pnum, gfp);
 		if (page) {
 			BUG_ON(page->mapping != inode->i_mapping);
 			if (!PageUptodate(page)) {
-				ret = ext4_mb_init_cache(page, NULL);
+				ret = ext4_mb_init_cache(page, NULL, gfp);
 				if (ret) {
 					unlock_page(page);
 					goto err;
@@ -1204,11 +1204,12 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 	if (page == NULL || !PageUptodate(page)) {
 		if (page)
 			page_cache_release(page);
-		page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+		page = find_or_create_page(inode->i_mapping, pnum, gfp);
 		if (page) {
 			BUG_ON(page->mapping != inode->i_mapping);
 			if (!PageUptodate(page)) {
-				ret = ext4_mb_init_cache(page, e4b->bd_bitmap);
+				ret = ext4_mb_init_cache(page, e4b->bd_bitmap,
+							 gfp);
 				if (ret) {
 					unlock_page(page);
 					goto err;
@@ -1247,6 +1248,12 @@ err:
 	return ret;
 }
 
+static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
+			      struct ext4_buddy *e4b)
+{
+	return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS);
+}
+
 static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 {
 	if (e4b->bd_bitmap_page)
@@ -2045,7 +2052,7 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
 
 	/* We only do this if the grp has never been initialized */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-		int ret = ext4_mb_init_group(ac->ac_sb, group);
+		int ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS);
 		if (ret)
 			return ret;
 	}
@@ -2285,7 +2292,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	if (group == 0)
 		seq_puts(seq, "#group: free  frags first ["
 			      " 2^0   2^1   2^2   2^3   2^4   2^5   2^6  "
-			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]");
+			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]\n");
 
 	i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
 		sizeof(struct ext4_group_info);
@@ -4695,16 +4702,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	}
 
 	/*
-	 * We need to make sure we don't reuse the freed block until
-	 * after the transaction is committed, which we can do by
-	 * treating the block as metadata, below.  We make an
-	 * exception if the inode is to be written in writeback mode
-	 * since writeback mode has weak data consistency guarantees.
-	 */
-	if (!ext4_should_writeback_data(inode))
-		flags |= EXT4_FREE_BLOCKS_METADATA;
-
-	/*
 	 * If the extent to be freed does not begin on a cluster
 	 * boundary, we need to deal with partial clusters at the
 	 * beginning and end of the extent.  Normally we will free
@@ -4738,14 +4735,13 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 
 	if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
 		int i;
+		int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA;
 
 		for (i = 0; i < count; i++) {
 			cond_resched();
-			bh = sb_find_get_block(inode->i_sb, block + i);
-			if (!bh)
-				continue;
-			ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
-				    inode, bh, block + i);
+			if (is_metadata)
+				bh = sb_find_get_block(inode->i_sb, block + i);
+			ext4_forget(handle, is_metadata, inode, bh, block + i);
 		}
 	}
 
@@ -4815,16 +4811,23 @@ do_more:
 #endif
 	trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters);
 
-	err = ext4_mb_load_buddy(sb, block_group, &e4b);
+	/* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */
+	err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b,
+				     GFP_NOFS|__GFP_NOFAIL);
 	if (err)
 		goto error_return;
 
-	if ((flags & EXT4_FREE_BLOCKS_METADATA) && ext4_handle_valid(handle)) {
+	/*
+	 * We need to make sure we don't reuse the freed block until after the
+	 * transaction is committed. We make an exception if the inode is to be
+	 * written in writeback mode since writeback mode has weak data
+	 * consistency guarantees.
+	 */
+	if (ext4_handle_valid(handle) &&
+	    ((flags & EXT4_FREE_BLOCKS_METADATA) ||
+	     !ext4_should_writeback_data(inode))) {
 		struct ext4_free_data *new_entry;
 		/*
-		 * blocks being freed are metadata. these blocks shouldn't
-		 * be used until this transaction is committed
-		 *
 		 * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed
 		 * to fail.
 		 */
@@ -5217,7 +5220,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		grp = ext4_get_group_info(sb, group);
 		/* We only do this if the grp has never been initialized */
 		if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-			ret = ext4_mb_init_group(sb, group);
+			ret = ext4_mb_init_group(sb, group, GFP_NOFS);
 			if (ret)
 				break;
 		}
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index d634e183b4d4..3ef1df6ae9ec 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -23,18 +23,6 @@
 #include "ext4.h"
 
 /*
- * with AGGRESSIVE_CHECK allocator runs consistency checks over
- * structures. these checks slow things down a lot
- */
-#define AGGRESSIVE_CHECK__
-
-/*
- * with DOUBLE_CHECK defined mballoc creates persistent in-core
- * bitmaps, maintains and uses them to check for double allocations
- */
-#define DOUBLE_CHECK__
-
-/*
  */
 #ifdef CONFIG_EXT4_DEBUG
 extern ushort ext4_mballoc_debug;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index a4651894cc33..364ea4d4a943 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -361,7 +361,7 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
 	 * blocks.
 	 *
 	 * While converting to extents we need not
-	 * update the orignal inode i_blocks for extent blocks
+	 * update the original inode i_blocks for extent blocks
 	 * via quota APIs. The quota update happened via tmp_inode already.
 	 */
 	spin_lock(&inode->i_lock);
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 0a512aa81bf7..24445275d330 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -91,21 +91,22 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
 	submit_bh(READ_SYNC | REQ_META | REQ_PRIO, *bh);
 	wait_on_buffer(*bh);
 	if (!buffer_uptodate(*bh)) {
-		brelse(*bh);
-		*bh = NULL;
 		ret = -EIO;
 		goto warn_exit;
 	}
-
 	mmp = (struct mmp_struct *)((*bh)->b_data);
-	if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC)
+	if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC) {
 		ret = -EFSCORRUPTED;
-	else if (!ext4_mmp_csum_verify(sb, mmp))
+		goto warn_exit;
+	}
+	if (!ext4_mmp_csum_verify(sb, mmp)) {
 		ret = -EFSBADCRC;
-	else
-		return 0;
-
+		goto warn_exit;
+	}
+	return 0;
 warn_exit:
+	brelse(*bh);
+	*bh = NULL;
 	ext4_warning(sb, "Error %d while reading MMP block %llu",
 		     ret, mmp_block);
 	return ret;
@@ -181,15 +182,13 @@ static int kmmpd(void *data)
 		    EXT4_FEATURE_INCOMPAT_MMP)) {
 			ext4_warning(sb, "kmmpd being stopped since MMP feature"
 				     " has been disabled.");
-			EXT4_SB(sb)->s_mmp_tsk = NULL;
-			goto failed;
+			goto exit_thread;
 		}
 
 		if (sb->s_flags & MS_RDONLY) {
 			ext4_warning(sb, "kmmpd being stopped since filesystem "
 				     "has been remounted as readonly.");
-			EXT4_SB(sb)->s_mmp_tsk = NULL;
-			goto failed;
+			goto exit_thread;
 		}
 
 		diff = jiffies - last_update_time;
@@ -211,9 +210,7 @@ static int kmmpd(void *data)
 			if (retval) {
 				ext4_error(sb, "error reading MMP data: %d",
 					   retval);
-
-				EXT4_SB(sb)->s_mmp_tsk = NULL;
-				goto failed;
+				goto exit_thread;
 			}
 
 			mmp_check = (struct mmp_struct *)(bh_check->b_data);
@@ -225,7 +222,9 @@ static int kmmpd(void *data)
 					     "The filesystem seems to have been"
 					     " multiply mounted.");
 				ext4_error(sb, "abort");
-				goto failed;
+				put_bh(bh_check);
+				retval = -EBUSY;
+				goto exit_thread;
 			}
 			put_bh(bh_check);
 		}
@@ -248,7 +247,8 @@ static int kmmpd(void *data)
 
 	retval = write_mmp_block(sb, bh);
 
-failed:
+exit_thread:
+	EXT4_SB(sb)->s_mmp_tsk = NULL;
 	kfree(data);
 	brelse(bh);
 	return retval;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index fb6f11709ae6..4098acc701c3 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 	ext4_lblk_t orig_blk_offset, donor_blk_offset;
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
 	unsigned int tmp_data_size, data_size, replaced_size;
-	int err2, jblocks, retries = 0;
+	int i, err2, jblocks, retries = 0;
 	int replaced_count = 0;
 	int from = data_offset_in_page << orig_inode->i_blkbits;
 	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
 	struct super_block *sb = orig_inode->i_sb;
+	struct buffer_head *bh = NULL;
 
 	/*
 	 * It needs twice the amount of ordinary journal buffers because
@@ -380,8 +381,17 @@ data_copy:
 	}
 	/* Perform all necessary steps similar write_begin()/write_end()
 	 * but keeping in mind that i_size will not change */
-	*err = __block_write_begin(pagep[0], from, replaced_size,
-				   ext4_get_block);
+	if (!page_has_buffers(pagep[0]))
+		create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0);
+	bh = page_buffers(pagep[0]);
+	for (i = 0; i < data_offset_in_page; i++)
+		bh = bh->b_this_page;
+	for (i = 0; i < block_len_in_page; i++) {
+		*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
+		if (*err < 0)
+			break;
+		bh = bh->b_this_page;
+	}
 	if (!*err)
 		*err = block_commit_write(pagep[0], from, from + replaced_size);
 
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 06574dd77614..48e4b8907826 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1558,6 +1558,24 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 	struct ext4_dir_entry_2 *de;
 	struct buffer_head *bh;
 
+       if (ext4_encrypted_inode(dir)) {
+               int res = ext4_get_encryption_info(dir);
+
+		/*
+		 * This should be a properly defined flag for
+		 * dentry->d_flags when we uplift this to the VFS.
+		 * d_fsdata is set to (void *) 1 if if the dentry is
+		 * created while the directory was encrypted and we
+		 * don't have access to the key.
+		 */
+	       dentry->d_fsdata = NULL;
+	       if (ext4_encryption_info(dir))
+		       dentry->d_fsdata = (void *) 1;
+	       d_set_d_op(dentry, &ext4_encrypted_d_ops);
+	       if (res && res != -ENOKEY)
+		       return ERR_PTR(res);
+       }
+
 	if (dentry->d_name.len > EXT4_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
@@ -1585,11 +1603,15 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 			return ERR_PTR(-EFSCORRUPTED);
 		}
 		if (!IS_ERR(inode) && ext4_encrypted_inode(dir) &&
-		    (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-		     S_ISLNK(inode->i_mode)) &&
+		    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
 		    !ext4_is_child_context_consistent_with_parent(dir,
 								  inode)) {
+			int nokey = ext4_encrypted_inode(inode) &&
+				!ext4_encryption_info(inode);
+
 			iput(inode);
+			if (nokey)
+				return ERR_PTR(-ENOKEY);
 			ext4_warning(inode->i_sb,
 				     "Inconsistent encryption contexts: %lu/%lu\n",
 				     (unsigned long) dir->i_ino,
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 090b3498638e..d77d15f4b674 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -128,9 +128,6 @@ static void ext4_release_io_end(ext4_io_end_t *io_end)
 	BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
 	WARN_ON(io_end->handle);
 
-	if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count))
-		wake_up_all(ext4_ioend_wq(io_end->inode));
-
 	for (bio = io_end->bio; bio; bio = next_bio) {
 		next_bio = bio->bi_private;
 		ext4_finish_bio(bio);
@@ -139,16 +136,6 @@ static void ext4_release_io_end(ext4_io_end_t *io_end)
 	kmem_cache_free(io_end_cachep, io_end);
 }
 
-static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
-{
-	struct inode *inode = io_end->inode;
-
-	io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
-	/* Wake up anyone waiting on unwritten extent conversion */
-	if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
-		wake_up_all(ext4_ioend_wq(inode));
-}
-
 /*
  * Check a range of space and convert unwritten extents to written. Note that
  * we are protected from truncate touching same part of extent tree by the
@@ -265,7 +252,6 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
 {
 	ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags);
 	if (io) {
-		atomic_inc(&EXT4_I(inode)->i_ioend_count);
 		io->inode = inode;
 		INIT_LIST_HEAD(&io->list);
 		atomic_set(&io->count, 1);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index ad62d7acc315..34038e3598d5 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
 	if (flex_gd == NULL)
 		goto out3;
 
-	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
+	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
 		goto out2;
 	flex_gd->count = flexbg_size;
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3ed01ec011d7..539297515896 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -55,7 +55,6 @@
 
 static struct ext4_lazy_init *ext4_li_info;
 static struct mutex ext4_li_mtx;
-static int ext4_mballoc_ready;
 static struct ratelimit_state ext4_mount_msg_ratelimit;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
@@ -844,7 +843,6 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_release_system_zone(sb);
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
-	ext4_xattr_put_super(sb);
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		ext4_clear_feature_journal_needs_recovery(sb);
@@ -944,7 +942,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	spin_lock_init(&ei->i_completed_io_lock);
 	ei->i_sync_tid = 0;
 	ei->i_datasync_tid = 0;
-	atomic_set(&ei->i_ioend_count, 0);
 	atomic_set(&ei->i_unwritten, 0);
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
@@ -1132,6 +1129,7 @@ static const struct dquot_operations ext4_quota_operations = {
 	.alloc_dquot	= dquot_alloc,
 	.destroy_dquot	= dquot_destroy,
 	.get_projid	= ext4_get_projid,
+	.get_next_id	= dquot_get_next_id,
 };
 
 static const struct quotactl_ops ext4_qctl_operations = {
@@ -1141,7 +1139,8 @@ static const struct quotactl_ops ext4_qctl_operations = {
 	.get_state	= dquot_get_state,
 	.set_info	= dquot_set_dqinfo,
 	.get_dqblk	= dquot_get_dqblk,
-	.set_dqblk	= dquot_set_dqblk
+	.set_dqblk	= dquot_set_dqblk,
+	.get_nextdqblk	= dquot_get_next_dqblk,
 };
 #endif
 
@@ -1425,9 +1424,9 @@ static const struct mount_opts {
 	{Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR},
 	{Opt_err_cont, EXT4_MOUNT_ERRORS_CONT, MOPT_SET | MOPT_CLEAR_ERR},
 	{Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT,
-	 MOPT_NO_EXT2 | MOPT_SET},
+	 MOPT_NO_EXT2},
 	{Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT,
-	 MOPT_NO_EXT2 | MOPT_CLEAR},
+	 MOPT_NO_EXT2},
 	{Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET},
 	{Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR},
 	{Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET},
@@ -1705,6 +1704,10 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		ext4_msg(sb, KERN_INFO, "dax option not supported");
 		return -1;
 #endif
+	} else if (token == Opt_data_err_abort) {
+		sbi->s_mount_opt |= m->mount_opt;
+	} else if (token == Opt_data_err_ignore) {
+		sbi->s_mount_opt &= ~m->mount_opt;
 	} else {
 		if (!args->from)
 			arg = 1;
@@ -1914,6 +1917,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult);
 	if (nodefs || sbi->s_max_dir_size_kb)
 		SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb);
+	if (test_opt(sb, DATA_ERR_ABORT))
+		SEQ_OPTS_PUTS("data_err=abort");
 
 	ext4_show_quota_options(seq, sb);
 	return 0;
@@ -3796,12 +3801,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
 
 no_journal:
-	if (ext4_mballoc_ready) {
-		sbi->s_mb_cache = ext4_xattr_create_cache(sb->s_id);
-		if (!sbi->s_mb_cache) {
-			ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
-			goto failed_mount_wq;
-		}
+	sbi->s_mb_cache = ext4_xattr_create_cache();
+	if (!sbi->s_mb_cache) {
+		ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+		goto failed_mount_wq;
 	}
 
 	if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) &&
@@ -4027,6 +4030,10 @@ failed_mount4:
 	if (EXT4_SB(sb)->rsv_conversion_wq)
 		destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
 failed_mount_wq:
+	if (sbi->s_mb_cache) {
+		ext4_xattr_destroy_cache(sbi->s_mb_cache);
+		sbi->s_mb_cache = NULL;
+	}
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
@@ -5321,7 +5328,6 @@ MODULE_ALIAS_FS("ext4");
 
 /* Shared across all ext4 file systems */
 wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
-struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
 
 static int __init ext4_init_fs(void)
 {
@@ -5334,10 +5340,8 @@ static int __init ext4_init_fs(void)
 	/* Build-time check for flags consistency */
 	ext4_check_flag_values();
 
-	for (i = 0; i < EXT4_WQ_HASH_SZ; i++) {
-		mutex_init(&ext4__aio_mutex[i]);
+	for (i = 0; i < EXT4_WQ_HASH_SZ; i++)
 		init_waitqueue_head(&ext4__ioend_wq[i]);
-	}
 
 	err = ext4_init_es();
 	if (err)
@@ -5358,8 +5362,6 @@ static int __init ext4_init_fs(void)
 	err = ext4_init_mballoc();
 	if (err)
 		goto out2;
-	else
-		ext4_mballoc_ready = 1;
 	err = init_inodecache();
 	if (err)
 		goto out1;
@@ -5375,7 +5377,6 @@ out:
 	unregister_as_ext3();
 	destroy_inodecache();
 out1:
-	ext4_mballoc_ready = 0;
 	ext4_exit_mballoc();
 out2:
 	ext4_exit_sysfs();
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index a95151e875bd..0441e055c8e8 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -545,30 +545,44 @@ static void
 ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 			 struct buffer_head *bh)
 {
-	struct mb_cache_entry *ce = NULL;
-	int error = 0;
 	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+	u32 hash, ref;
+	int error = 0;
 
-	ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr);
 	BUFFER_TRACE(bh, "get_write_access");
 	error = ext4_journal_get_write_access(handle, bh);
 	if (error)
 		goto out;
 
 	lock_buffer(bh);
-	if (BHDR(bh)->h_refcount == cpu_to_le32(1)) {
+	hash = le32_to_cpu(BHDR(bh)->h_hash);
+	ref = le32_to_cpu(BHDR(bh)->h_refcount);
+	if (ref == 1) {
 		ea_bdebug(bh, "refcount now=0; freeing");
-		if (ce)
-			mb_cache_entry_free(ce);
+		/*
+		 * This must happen under buffer lock for
+		 * ext4_xattr_block_set() to reliably detect freed block
+		 */
+		mb_cache_entry_delete_block(ext4_mb_cache, hash, bh->b_blocknr);
 		get_bh(bh);
 		unlock_buffer(bh);
 		ext4_free_blocks(handle, inode, bh, 0, 1,
 				 EXT4_FREE_BLOCKS_METADATA |
 				 EXT4_FREE_BLOCKS_FORGET);
 	} else {
-		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
-		if (ce)
-			mb_cache_entry_release(ce);
+		ref--;
+		BHDR(bh)->h_refcount = cpu_to_le32(ref);
+		if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) {
+			struct mb_cache_entry *ce;
+
+			ce = mb_cache_entry_get(ext4_mb_cache, hash,
+						bh->b_blocknr);
+			if (ce) {
+				ce->e_reusable = 1;
+				mb_cache_entry_put(ext4_mb_cache, ce);
+			}
+		}
+
 		/*
 		 * Beware of this ugliness: Releasing of xattr block references
 		 * from different inodes can race and so we have to protect
@@ -790,8 +804,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 	if (i->value && i->value_len > sb->s_blocksize)
 		return -ENOSPC;
 	if (s->base) {
-		ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev,
-					bs->bh->b_blocknr);
 		BUFFER_TRACE(bs->bh, "get_write_access");
 		error = ext4_journal_get_write_access(handle, bs->bh);
 		if (error)
@@ -799,10 +811,15 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 		lock_buffer(bs->bh);
 
 		if (header(s->base)->h_refcount == cpu_to_le32(1)) {
-			if (ce) {
-				mb_cache_entry_free(ce);
-				ce = NULL;
-			}
+			__u32 hash = le32_to_cpu(BHDR(bs->bh)->h_hash);
+
+			/*
+			 * This must happen under buffer lock for
+			 * ext4_xattr_block_set() to reliably detect modified
+			 * block
+			 */
+			mb_cache_entry_delete_block(ext4_mb_cache, hash,
+						    bs->bh->b_blocknr);
 			ea_bdebug(bs->bh, "modifying in-place");
 			error = ext4_xattr_set_entry(i, s);
 			if (!error) {
@@ -826,10 +843,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			int offset = (char *)s->here - bs->bh->b_data;
 
 			unlock_buffer(bs->bh);
-			if (ce) {
-				mb_cache_entry_release(ce);
-				ce = NULL;
-			}
 			ea_bdebug(bs->bh, "cloning");
 			s->base = kmalloc(bs->bh->b_size, GFP_NOFS);
 			error = -ENOMEM;
@@ -872,6 +885,8 @@ inserted:
 			if (new_bh == bs->bh)
 				ea_bdebug(new_bh, "keeping");
 			else {
+				u32 ref;
+
 				/* The old block is released after updating
 				   the inode. */
 				error = dquot_alloc_block(inode,
@@ -884,9 +899,40 @@ inserted:
 				if (error)
 					goto cleanup_dquot;
 				lock_buffer(new_bh);
-				le32_add_cpu(&BHDR(new_bh)->h_refcount, 1);
+				/*
+				 * We have to be careful about races with
+				 * freeing, rehashing or adding references to
+				 * xattr block. Once we hold buffer lock xattr
+				 * block's state is stable so we can check
+				 * whether the block got freed / rehashed or
+				 * not.  Since we unhash mbcache entry under
+				 * buffer lock when freeing / rehashing xattr
+				 * block, checking whether entry is still
+				 * hashed is reliable. Same rules hold for
+				 * e_reusable handling.
+				 */
+				if (hlist_bl_unhashed(&ce->e_hash_list) ||
+				    !ce->e_reusable) {
+					/*
+					 * Undo everything and check mbcache
+					 * again.
+					 */
+					unlock_buffer(new_bh);
+					dquot_free_block(inode,
+							 EXT4_C2B(EXT4_SB(sb),
+								  1));
+					brelse(new_bh);
+					mb_cache_entry_put(ext4_mb_cache, ce);
+					ce = NULL;
+					new_bh = NULL;
+					goto inserted;
+				}
+				ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
+				BHDR(new_bh)->h_refcount = cpu_to_le32(ref);
+				if (ref >= EXT4_XATTR_REFCOUNT_MAX)
+					ce->e_reusable = 0;
 				ea_bdebug(new_bh, "reusing; refcount now=%d",
-					le32_to_cpu(BHDR(new_bh)->h_refcount));
+					  ref);
 				unlock_buffer(new_bh);
 				error = ext4_handle_dirty_xattr_block(handle,
 								      inode,
@@ -894,7 +940,8 @@ inserted:
 				if (error)
 					goto cleanup_dquot;
 			}
-			mb_cache_entry_release(ce);
+			mb_cache_entry_touch(ext4_mb_cache, ce);
+			mb_cache_entry_put(ext4_mb_cache, ce);
 			ce = NULL;
 		} else if (bs->bh && s->base == bs->bh->b_data) {
 			/* We were modifying this block in-place. */
@@ -959,7 +1006,7 @@ getblk_failed:
 
 cleanup:
 	if (ce)
-		mb_cache_entry_release(ce);
+		mb_cache_entry_put(ext4_mb_cache, ce);
 	brelse(new_bh);
 	if (!(bs->bh && s->base == bs->bh->b_data))
 		kfree(s->base);
@@ -1070,6 +1117,17 @@ static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
 	return 0;
 }
 
+static int ext4_xattr_value_same(struct ext4_xattr_search *s,
+				 struct ext4_xattr_info *i)
+{
+	void *value;
+
+	if (le32_to_cpu(s->here->e_value_size) != i->value_len)
+		return 0;
+	value = ((void *)s->base) + le16_to_cpu(s->here->e_value_offs);
+	return !memcmp(value, i->value, i->value_len);
+}
+
 /*
  * ext4_xattr_set_handle()
  *
@@ -1146,6 +1204,13 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		else if (!bs.s.not_found)
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
 	} else {
+		error = 0;
+		/* Xattr value did not change? Save us some work and bail out */
+		if (!is.s.not_found && ext4_xattr_value_same(&is.s, &i))
+			goto cleanup;
+		if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i))
+			goto cleanup;
+
 		error = ext4_xattr_ibody_set(handle, inode, &i, &is);
 		if (!error && !bs.s.not_found) {
 			i.value = NULL;
@@ -1512,17 +1577,6 @@ cleanup:
 }
 
 /*
- * ext4_xattr_put_super()
- *
- * This is called when a file system is unmounted.
- */
-void
-ext4_xattr_put_super(struct super_block *sb)
-{
-	mb_cache_shrink(sb->s_bdev);
-}
-
-/*
  * ext4_xattr_cache_insert()
  *
  * Create a new entry in the extended attribute cache, and insert
@@ -1533,26 +1587,19 @@ ext4_xattr_put_super(struct super_block *sb)
 static void
 ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
 {
-	__u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
-	struct mb_cache_entry *ce;
+	struct ext4_xattr_header *header = BHDR(bh);
+	__u32 hash = le32_to_cpu(header->h_hash);
+	int reusable = le32_to_cpu(header->h_refcount) <
+		       EXT4_XATTR_REFCOUNT_MAX;
 	int error;
 
-	ce = mb_cache_entry_alloc(ext4_mb_cache, GFP_NOFS);
-	if (!ce) {
-		ea_bdebug(bh, "out of memory");
-		return;
-	}
-	error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash);
+	error = mb_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash,
+				      bh->b_blocknr, reusable);
 	if (error) {
-		mb_cache_entry_free(ce);
-		if (error == -EBUSY) {
+		if (error == -EBUSY)
 			ea_bdebug(bh, "already in cache");
-			error = 0;
-		}
-	} else {
+	} else
 		ea_bdebug(bh, "inserting [%x]", (int)hash);
-		mb_cache_entry_release(ce);
-	}
 }
 
 /*
@@ -1614,33 +1661,20 @@ ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
 	if (!header->h_hash)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
-again:
-	ce = mb_cache_entry_find_first(ext4_mb_cache, inode->i_sb->s_bdev,
-				       hash);
+	ce = mb_cache_entry_find_first(ext4_mb_cache, hash);
 	while (ce) {
 		struct buffer_head *bh;
 
-		if (IS_ERR(ce)) {
-			if (PTR_ERR(ce) == -EAGAIN)
-				goto again;
-			break;
-		}
 		bh = sb_bread(inode->i_sb, ce->e_block);
 		if (!bh) {
 			EXT4_ERROR_INODE(inode, "block %lu read error",
 					 (unsigned long) ce->e_block);
-		} else if (le32_to_cpu(BHDR(bh)->h_refcount) >=
-				EXT4_XATTR_REFCOUNT_MAX) {
-			ea_idebug(inode, "block %lu refcount %d>=%d",
-				  (unsigned long) ce->e_block,
-				  le32_to_cpu(BHDR(bh)->h_refcount),
-					  EXT4_XATTR_REFCOUNT_MAX);
 		} else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) {
 			*pce = ce;
 			return bh;
 		}
 		brelse(bh);
-		ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash);
+		ce = mb_cache_entry_find_next(ext4_mb_cache, ce);
 	}
 	return NULL;
 }
@@ -1716,9 +1750,9 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *header,
 #define	HASH_BUCKET_BITS	10
 
 struct mb_cache *
-ext4_xattr_create_cache(char *name)
+ext4_xattr_create_cache(void)
 {
-	return mb_cache_create(name, HASH_BUCKET_BITS);
+	return mb_cache_create(HASH_BUCKET_BITS);
 }
 
 void ext4_xattr_destroy_cache(struct mb_cache *cache)
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index ddc0957760ba..69dd3e6566e0 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -108,7 +108,6 @@ extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_
 extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
 
 extern void ext4_xattr_delete_inode(handle_t *, struct inode *);
-extern void ext4_xattr_put_super(struct super_block *);
 
 extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			    struct ext4_inode *raw_inode, handle_t *handle);
@@ -124,7 +123,7 @@ extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 				       struct ext4_xattr_info *i,
 				       struct ext4_xattr_ibody_find *is);
 
-extern struct mb_cache *ext4_xattr_create_cache(char *name);
+extern struct mb_cache *ext4_xattr_create_cache(void);
 extern void ext4_xattr_destroy_cache(struct mb_cache *);
 
 #ifdef CONFIG_EXT4_FS_SECURITY
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index b0a9dc929f88..1f8982a957f1 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -1,6 +1,8 @@
 config F2FS_FS
 	tristate "F2FS filesystem support"
 	depends on BLOCK
+	select CRYPTO
+	select CRYPTO_CRC32
 	help
 	  F2FS is based on Log-structured File System (LFS), which supports
 	  versatile "flash-friendly" features. The design has been focused on
@@ -76,15 +78,7 @@ config F2FS_FS_ENCRYPTION
 	bool "F2FS Encryption"
 	depends on F2FS_FS
 	depends on F2FS_FS_XATTR
-	select CRYPTO_AES
-	select CRYPTO_CBC
-	select CRYPTO_ECB
-	select CRYPTO_XTS
-	select CRYPTO_CTS
-	select CRYPTO_CTR
-	select CRYPTO_SHA256
-	select KEYS
-	select ENCRYPTED_KEYS
+	select FS_ENCRYPTION
 	help
 	  Enable encryption of f2fs files and directories.  This
 	  feature is similar to ecryptfs, but it is more memory
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index 08e101ed914c..ca949ea7c02f 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -7,5 +7,3 @@ 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
-f2fs-$(CONFIG_F2FS_FS_ENCRYPTION) += crypto_policy.o crypto.o \
-		crypto_key.o crypto_fname.o
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 3842af954cd5..0955312e5ca0 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -39,7 +39,7 @@ repeat:
 		cond_resched();
 		goto repeat;
 	}
-	f2fs_wait_on_page_writeback(page, META);
+	f2fs_wait_on_page_writeback(page, META, true);
 	SetPageUptodate(page);
 	return page;
 }
@@ -56,7 +56,8 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 		.sbi = sbi,
 		.type = META,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO,
-		.blk_addr = index,
+		.old_blkaddr = index,
+		.new_blkaddr = index,
 		.encrypted_page = NULL,
 	};
 
@@ -143,7 +144,6 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
 int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 							int type, bool sync)
 {
-	block_t prev_blk_addr = 0;
 	struct page *page;
 	block_t blkno = start;
 	struct f2fs_io_info fio = {
@@ -152,10 +152,12 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		.rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
 		.encrypted_page = NULL,
 	};
+	struct blk_plug plug;
 
 	if (unlikely(type == META_POR))
 		fio.rw &= ~REQ_META;
 
+	blk_start_plug(&plug);
 	for (; nrpages-- > 0; blkno++) {
 
 		if (!is_valid_blkaddr(sbi, blkno, type))
@@ -167,27 +169,24 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 					NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
 				blkno = 0;
 			/* get nat block addr */
-			fio.blk_addr = current_nat_addr(sbi,
+			fio.new_blkaddr = current_nat_addr(sbi,
 					blkno * NAT_ENTRY_PER_BLOCK);
 			break;
 		case META_SIT:
 			/* get sit block addr */
-			fio.blk_addr = current_sit_addr(sbi,
+			fio.new_blkaddr = current_sit_addr(sbi,
 					blkno * SIT_ENTRY_PER_BLOCK);
-			if (blkno != start && prev_blk_addr + 1 != fio.blk_addr)
-				goto out;
-			prev_blk_addr = fio.blk_addr;
 			break;
 		case META_SSA:
 		case META_CP:
 		case META_POR:
-			fio.blk_addr = blkno;
+			fio.new_blkaddr = blkno;
 			break;
 		default:
 			BUG();
 		}
 
-		page = grab_cache_page(META_MAPPING(sbi), fio.blk_addr);
+		page = grab_cache_page(META_MAPPING(sbi), fio.new_blkaddr);
 		if (!page)
 			continue;
 		if (PageUptodate(page)) {
@@ -196,11 +195,13 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		}
 
 		fio.page = page;
+		fio.old_blkaddr = fio.new_blkaddr;
 		f2fs_submit_page_mbio(&fio);
 		f2fs_put_page(page, 0);
 	}
 out:
 	f2fs_submit_merged_bio(sbi, META, READ);
+	blk_finish_plug(&plug);
 	return blkno - start;
 }
 
@@ -232,13 +233,17 @@ static int f2fs_write_meta_page(struct page *page,
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto redirty_out;
 
-	f2fs_wait_on_page_writeback(page, META);
 	write_meta_page(sbi, page);
 	dec_page_count(sbi, F2FS_DIRTY_META);
+
+	if (wbc->for_reclaim)
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, META, WRITE);
+
 	unlock_page(page);
 
-	if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi)))
 		f2fs_submit_merged_bio(sbi, META, WRITE);
+
 	return 0;
 
 redirty_out:
@@ -252,13 +257,13 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
 	long diff, written;
 
-	trace_f2fs_writepages(mapping->host, wbc, META);
-
 	/* collect a number of dirty meta pages and write together */
 	if (wbc->for_kupdate ||
 		get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
 		goto skip_write;
 
+	trace_f2fs_writepages(mapping->host, wbc, META);
+
 	/* if mounting is failed, skip writing node pages */
 	mutex_lock(&sbi->cp_mutex);
 	diff = nr_pages_to_write(sbi, META, wbc);
@@ -269,6 +274,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 
 skip_write:
 	wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_META);
+	trace_f2fs_writepages(mapping->host, wbc, META);
 	return 0;
 }
 
@@ -276,15 +282,18 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 						long nr_to_write)
 {
 	struct address_space *mapping = META_MAPPING(sbi);
-	pgoff_t index = 0, end = LONG_MAX, prev = LONG_MAX;
+	pgoff_t index = 0, end = ULONG_MAX, prev = ULONG_MAX;
 	struct pagevec pvec;
 	long nwritten = 0;
 	struct writeback_control wbc = {
 		.for_reclaim = 0,
 	};
+	struct blk_plug plug;
 
 	pagevec_init(&pvec, 0);
 
+	blk_start_plug(&plug);
+
 	while (index <= end) {
 		int i, nr_pages;
 		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
@@ -296,7 +305,7 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
-			if (prev == LONG_MAX)
+			if (prev == ULONG_MAX)
 				prev = page->index - 1;
 			if (nr_to_write != LONG_MAX && page->index != prev + 1) {
 				pagevec_release(&pvec);
@@ -315,6 +324,9 @@ continue_unlock:
 				goto continue_unlock;
 			}
 
+			f2fs_wait_on_page_writeback(page, META, true);
+
+			BUG_ON(PageWriteback(page));
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
@@ -334,6 +346,8 @@ stop:
 	if (nwritten)
 		f2fs_submit_merged_bio(sbi, type, WRITE);
 
+	blk_finish_plug(&plug);
+
 	return nwritten;
 }
 
@@ -621,7 +635,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 		goto invalid_cp1;
 
 	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
+	if (!f2fs_crc_valid(sbi, crc, cp_block, crc_offset))
 		goto invalid_cp1;
 
 	pre_version = cur_cp_version(cp_block);
@@ -636,7 +650,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 		goto invalid_cp2;
 
 	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
+	if (!f2fs_crc_valid(sbi, crc, cp_block, crc_offset))
 		goto invalid_cp2;
 
 	cur_version = cur_cp_version(cp_block);
@@ -696,6 +710,10 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
 	memcpy(sbi->ckpt, cp_block, blk_size);
 
+	/* Sanity checking of checkpoint */
+	if (sanity_check_ckpt(sbi))
+		goto fail_no_cp;
+
 	if (cp_blks <= 1)
 		goto done;
 
@@ -902,7 +920,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 		if (!get_pages(sbi, F2FS_WRITEBACK))
 			break;
 
-		io_schedule();
+		io_schedule_timeout(5*HZ);
 	}
 	finish_wait(&sbi->cp_wait, &wait);
 }
@@ -921,6 +939,9 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	int cp_payload_blks = __cp_payload(sbi);
 	block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
 	bool invalidate = false;
+	struct super_block *sb = sbi->sb;
+	struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+	u64 kbytes_written;
 
 	/*
 	 * This avoids to conduct wrong roll-forward operations and uses
@@ -1008,7 +1029,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
 	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
 
-	crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset));
+	crc32 = f2fs_crc32(sbi, ckpt, le32_to_cpu(ckpt->checksum_offset));
 	*((__le32 *)((unsigned char *)ckpt +
 				le32_to_cpu(ckpt->checksum_offset)))
 				= cpu_to_le32(crc32);
@@ -1034,6 +1055,14 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	write_data_summaries(sbi, start_blk);
 	start_blk += data_sum_blocks;
+
+	/* Record write statistics in the hot node summary */
+	kbytes_written = sbi->kbytes_written;
+	if (sb->s_bdev->bd_part)
+		kbytes_written += BD_PART_WRITTEN(sbi);
+
+	seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
+
 	if (__remain_node_summaries(cpc->reason)) {
 		write_node_summaries(sbi, start_blk);
 		start_blk += NR_CURSEG_NODE_TYPE;
@@ -1048,8 +1077,8 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
-	filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LONG_MAX);
-	filemap_fdatawait_range(META_MAPPING(sbi), 0, LONG_MAX);
+	filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LLONG_MAX);
+	filemap_fdatawait_range(META_MAPPING(sbi), 0, LLONG_MAX);
 
 	/* update user_block_counts */
 	sbi->last_valid_block_count = sbi->total_valid_block_count;
@@ -1112,9 +1141,7 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
 
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
-	f2fs_submit_merged_bio(sbi, NODE, WRITE);
-	f2fs_submit_merged_bio(sbi, META, WRITE);
+	f2fs_flush_merged_bios(sbi);
 
 	/*
 	 * update checkpoint pack index
diff --git a/fs/f2fs/crypto.c b/fs/f2fs/crypto.c
deleted file mode 100644
index 4a62ef14e932..000000000000
--- a/fs/f2fs/crypto.c
+++ /dev/null
@@ -1,491 +0,0 @@
-/*
- * linux/fs/f2fs/crypto.c
- *
- * Copied from linux/fs/ext4/crypto.c
- *
- * Copyright (C) 2015, Google, Inc.
- * Copyright (C) 2015, Motorola Mobility
- *
- * This contains encryption functions for f2fs
- *
- * Written by Michael Halcrow, 2014.
- *
- * Filename encryption additions
- *	Uday Savagaonkar, 2014
- * Encryption policy handling additions
- *	Ildar Muslukhov, 2014
- * Remove ext4_encrypted_zeroout(),
- *   add f2fs_restore_and_release_control_page()
- *	Jaegeuk Kim, 2015.
- *
- * This has not yet undergone a rigorous security audit.
- *
- * The usage of AES-XTS should conform to recommendations in NIST
- * Special Publication 800-38E and IEEE P1619/D16.
- */
-#include <crypto/hash.h>
-#include <crypto/sha.h>
-#include <keys/user-type.h>
-#include <keys/encrypted-type.h>
-#include <linux/crypto.h>
-#include <linux/ecryptfs.h>
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/key.h>
-#include <linux/list.h>
-#include <linux/mempool.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/random.h>
-#include <linux/scatterlist.h>
-#include <linux/spinlock_types.h>
-#include <linux/f2fs_fs.h>
-#include <linux/ratelimit.h>
-#include <linux/bio.h>
-
-#include "f2fs.h"
-#include "xattr.h"
-
-/* Encryption added and removed here! (L: */
-
-static unsigned int num_prealloc_crypto_pages = 32;
-static unsigned int num_prealloc_crypto_ctxs = 128;
-
-module_param(num_prealloc_crypto_pages, uint, 0444);
-MODULE_PARM_DESC(num_prealloc_crypto_pages,
-		"Number of crypto pages to preallocate");
-module_param(num_prealloc_crypto_ctxs, uint, 0444);
-MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
-		"Number of crypto contexts to preallocate");
-
-static mempool_t *f2fs_bounce_page_pool;
-
-static LIST_HEAD(f2fs_free_crypto_ctxs);
-static DEFINE_SPINLOCK(f2fs_crypto_ctx_lock);
-
-static struct workqueue_struct *f2fs_read_workqueue;
-static DEFINE_MUTEX(crypto_init);
-
-static struct kmem_cache *f2fs_crypto_ctx_cachep;
-struct kmem_cache *f2fs_crypt_info_cachep;
-
-/**
- * f2fs_release_crypto_ctx() - Releases an encryption context
- * @ctx: The encryption context to release.
- *
- * If the encryption context was allocated from the pre-allocated pool, returns
- * it to that pool. Else, frees it.
- *
- * If there's a bounce page in the context, this frees that.
- */
-void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *ctx)
-{
-	unsigned long flags;
-
-	if (ctx->flags & F2FS_WRITE_PATH_FL && ctx->w.bounce_page) {
-		mempool_free(ctx->w.bounce_page, f2fs_bounce_page_pool);
-		ctx->w.bounce_page = NULL;
-	}
-	ctx->w.control_page = NULL;
-	if (ctx->flags & F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL) {
-		kmem_cache_free(f2fs_crypto_ctx_cachep, ctx);
-	} else {
-		spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags);
-		list_add(&ctx->free_list, &f2fs_free_crypto_ctxs);
-		spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags);
-	}
-}
-
-/**
- * f2fs_get_crypto_ctx() - Gets an encryption context
- * @inode:       The inode for which we are doing the crypto
- *
- * Allocates and initializes an encryption context.
- *
- * Return: An allocated and initialized encryption context on success; error
- * value or NULL otherwise.
- */
-struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *inode)
-{
-	struct f2fs_crypto_ctx *ctx = NULL;
-	unsigned long flags;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (ci == NULL)
-		return ERR_PTR(-ENOKEY);
-
-	/*
-	 * We first try getting the ctx from a free list because in
-	 * the common case the ctx will have an allocated and
-	 * initialized crypto tfm, so it's probably a worthwhile
-	 * optimization. For the bounce page, we first try getting it
-	 * from the kernel allocator because that's just about as fast
-	 * as getting it from a list and because a cache of free pages
-	 * should generally be a "last resort" option for a filesystem
-	 * to be able to do its job.
-	 */
-	spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags);
-	ctx = list_first_entry_or_null(&f2fs_free_crypto_ctxs,
-					struct f2fs_crypto_ctx, free_list);
-	if (ctx)
-		list_del(&ctx->free_list);
-	spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags);
-	if (!ctx) {
-		ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_NOFS);
-		if (!ctx)
-			return ERR_PTR(-ENOMEM);
-		ctx->flags |= F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
-	} else {
-		ctx->flags &= ~F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
-	}
-	ctx->flags &= ~F2FS_WRITE_PATH_FL;
-	return ctx;
-}
-
-/*
- * Call f2fs_decrypt on every single page, reusing the encryption
- * context.
- */
-static void completion_pages(struct work_struct *work)
-{
-	struct f2fs_crypto_ctx *ctx =
-		container_of(work, struct f2fs_crypto_ctx, r.work);
-	struct bio *bio = ctx->r.bio;
-	struct bio_vec *bv;
-	int i;
-
-	bio_for_each_segment_all(bv, bio, i) {
-		struct page *page = bv->bv_page;
-		int ret = f2fs_decrypt(ctx, page);
-
-		if (ret) {
-			WARN_ON_ONCE(1);
-			SetPageError(page);
-		} else
-			SetPageUptodate(page);
-		unlock_page(page);
-	}
-	f2fs_release_crypto_ctx(ctx);
-	bio_put(bio);
-}
-
-void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *ctx, struct bio *bio)
-{
-	INIT_WORK(&ctx->r.work, completion_pages);
-	ctx->r.bio = bio;
-	queue_work(f2fs_read_workqueue, &ctx->r.work);
-}
-
-static void f2fs_crypto_destroy(void)
-{
-	struct f2fs_crypto_ctx *pos, *n;
-
-	list_for_each_entry_safe(pos, n, &f2fs_free_crypto_ctxs, free_list)
-		kmem_cache_free(f2fs_crypto_ctx_cachep, pos);
-	INIT_LIST_HEAD(&f2fs_free_crypto_ctxs);
-	if (f2fs_bounce_page_pool)
-		mempool_destroy(f2fs_bounce_page_pool);
-	f2fs_bounce_page_pool = NULL;
-}
-
-/**
- * f2fs_crypto_initialize() - Set up for f2fs encryption.
- *
- * We only call this when we start accessing encrypted files, since it
- * results in memory getting allocated that wouldn't otherwise be used.
- *
- * Return: Zero on success, non-zero otherwise.
- */
-int f2fs_crypto_initialize(void)
-{
-	int i, res = -ENOMEM;
-
-	if (f2fs_bounce_page_pool)
-		return 0;
-
-	mutex_lock(&crypto_init);
-	if (f2fs_bounce_page_pool)
-		goto already_initialized;
-
-	for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
-		struct f2fs_crypto_ctx *ctx;
-
-		ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_KERNEL);
-		if (!ctx)
-			goto fail;
-		list_add(&ctx->free_list, &f2fs_free_crypto_ctxs);
-	}
-
-	/* must be allocated at the last step to avoid race condition above */
-	f2fs_bounce_page_pool =
-		mempool_create_page_pool(num_prealloc_crypto_pages, 0);
-	if (!f2fs_bounce_page_pool)
-		goto fail;
-
-already_initialized:
-	mutex_unlock(&crypto_init);
-	return 0;
-fail:
-	f2fs_crypto_destroy();
-	mutex_unlock(&crypto_init);
-	return res;
-}
-
-/**
- * f2fs_exit_crypto() - Shutdown the f2fs encryption system
- */
-void f2fs_exit_crypto(void)
-{
-	f2fs_crypto_destroy();
-
-	if (f2fs_read_workqueue)
-		destroy_workqueue(f2fs_read_workqueue);
-	if (f2fs_crypto_ctx_cachep)
-		kmem_cache_destroy(f2fs_crypto_ctx_cachep);
-	if (f2fs_crypt_info_cachep)
-		kmem_cache_destroy(f2fs_crypt_info_cachep);
-}
-
-int __init f2fs_init_crypto(void)
-{
-	int res = -ENOMEM;
-
-	f2fs_read_workqueue = alloc_workqueue("f2fs_crypto", WQ_HIGHPRI, 0);
-	if (!f2fs_read_workqueue)
-		goto fail;
-
-	f2fs_crypto_ctx_cachep = KMEM_CACHE(f2fs_crypto_ctx,
-						SLAB_RECLAIM_ACCOUNT);
-	if (!f2fs_crypto_ctx_cachep)
-		goto fail;
-
-	f2fs_crypt_info_cachep = KMEM_CACHE(f2fs_crypt_info,
-						SLAB_RECLAIM_ACCOUNT);
-	if (!f2fs_crypt_info_cachep)
-		goto fail;
-
-	return 0;
-fail:
-	f2fs_exit_crypto();
-	return res;
-}
-
-void f2fs_restore_and_release_control_page(struct page **page)
-{
-	struct f2fs_crypto_ctx *ctx;
-	struct page *bounce_page;
-
-	/* The bounce data pages are unmapped. */
-	if ((*page)->mapping)
-		return;
-
-	/* The bounce data page is unmapped. */
-	bounce_page = *page;
-	ctx = (struct f2fs_crypto_ctx *)page_private(bounce_page);
-
-	/* restore control page */
-	*page = ctx->w.control_page;
-
-	f2fs_restore_control_page(bounce_page);
-}
-
-void f2fs_restore_control_page(struct page *data_page)
-{
-	struct f2fs_crypto_ctx *ctx =
-		(struct f2fs_crypto_ctx *)page_private(data_page);
-
-	set_page_private(data_page, (unsigned long)NULL);
-	ClearPagePrivate(data_page);
-	unlock_page(data_page);
-	f2fs_release_crypto_ctx(ctx);
-}
-
-/**
- * f2fs_crypt_complete() - The completion callback for page encryption
- * @req: The asynchronous encryption request context
- * @res: The result of the encryption operation
- */
-static void f2fs_crypt_complete(struct crypto_async_request *req, int res)
-{
-	struct f2fs_completion_result *ecr = req->data;
-
-	if (res == -EINPROGRESS)
-		return;
-	ecr->res = res;
-	complete(&ecr->completion);
-}
-
-typedef enum {
-	F2FS_DECRYPT = 0,
-	F2FS_ENCRYPT,
-} f2fs_direction_t;
-
-static int f2fs_page_crypto(struct f2fs_crypto_ctx *ctx,
-				struct inode *inode,
-				f2fs_direction_t rw,
-				pgoff_t index,
-				struct page *src_page,
-				struct page *dest_page)
-{
-	u8 xts_tweak[F2FS_XTS_TWEAK_SIZE];
-	struct ablkcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
-	struct scatterlist dst, src;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
-	int res = 0;
-
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		printk_ratelimited(KERN_ERR
-				"%s: crypto_request_alloc() failed\n",
-				__func__);
-		return -ENOMEM;
-	}
-	ablkcipher_request_set_callback(
-		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-		f2fs_crypt_complete, &ecr);
-
-	BUILD_BUG_ON(F2FS_XTS_TWEAK_SIZE < sizeof(index));
-	memcpy(xts_tweak, &index, sizeof(index));
-	memset(&xts_tweak[sizeof(index)], 0,
-			F2FS_XTS_TWEAK_SIZE - sizeof(index));
-
-	sg_init_table(&dst, 1);
-	sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
-	sg_init_table(&src, 1);
-	sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
-	ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
-					xts_tweak);
-	if (rw == F2FS_DECRYPT)
-		res = crypto_ablkcipher_decrypt(req);
-	else
-		res = crypto_ablkcipher_encrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-	ablkcipher_request_free(req);
-	if (res) {
-		printk_ratelimited(KERN_ERR
-			"%s: crypto_ablkcipher_encrypt() returned %d\n",
-			__func__, res);
-		return res;
-	}
-	return 0;
-}
-
-static struct page *alloc_bounce_page(struct f2fs_crypto_ctx *ctx)
-{
-	ctx->w.bounce_page = mempool_alloc(f2fs_bounce_page_pool, GFP_NOWAIT);
-	if (ctx->w.bounce_page == NULL)
-		return ERR_PTR(-ENOMEM);
-	ctx->flags |= F2FS_WRITE_PATH_FL;
-	return ctx->w.bounce_page;
-}
-
-/**
- * f2fs_encrypt() - Encrypts a page
- * @inode:          The inode for which the encryption should take place
- * @plaintext_page: The page to encrypt. Must be locked.
- *
- * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
- * encryption context.
- *
- * Called on the page write path.  The caller must call
- * f2fs_restore_control_page() on the returned ciphertext page to
- * release the bounce buffer and the encryption context.
- *
- * Return: An allocated page with the encrypted content on success. Else, an
- * error value or NULL.
- */
-struct page *f2fs_encrypt(struct inode *inode,
-			  struct page *plaintext_page)
-{
-	struct f2fs_crypto_ctx *ctx;
-	struct page *ciphertext_page = NULL;
-	int err;
-
-	BUG_ON(!PageLocked(plaintext_page));
-
-	ctx = f2fs_get_crypto_ctx(inode);
-	if (IS_ERR(ctx))
-		return (struct page *)ctx;
-
-	/* The encryption operation will require a bounce page. */
-	ciphertext_page = alloc_bounce_page(ctx);
-	if (IS_ERR(ciphertext_page))
-		goto err_out;
-
-	ctx->w.control_page = plaintext_page;
-	err = f2fs_page_crypto(ctx, inode, F2FS_ENCRYPT, plaintext_page->index,
-					plaintext_page, ciphertext_page);
-	if (err) {
-		ciphertext_page = ERR_PTR(err);
-		goto err_out;
-	}
-
-	SetPagePrivate(ciphertext_page);
-	set_page_private(ciphertext_page, (unsigned long)ctx);
-	lock_page(ciphertext_page);
-	return ciphertext_page;
-
-err_out:
-	f2fs_release_crypto_ctx(ctx);
-	return ciphertext_page;
-}
-
-/**
- * f2fs_decrypt() - Decrypts a page in-place
- * @ctx:  The encryption context.
- * @page: The page to decrypt. Must be locked.
- *
- * Decrypts page in-place using the ctx encryption context.
- *
- * Called from the read completion callback.
- *
- * Return: Zero on success, non-zero otherwise.
- */
-int f2fs_decrypt(struct f2fs_crypto_ctx *ctx, struct page *page)
-{
-	BUG_ON(!PageLocked(page));
-
-	return f2fs_page_crypto(ctx, page->mapping->host,
-				F2FS_DECRYPT, page->index, page, page);
-}
-
-/*
- * Convenience function which takes care of allocating and
- * deallocating the encryption context
- */
-int f2fs_decrypt_one(struct inode *inode, struct page *page)
-{
-	struct f2fs_crypto_ctx *ctx = f2fs_get_crypto_ctx(inode);
-	int ret;
-
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-	ret = f2fs_decrypt(ctx, page);
-	f2fs_release_crypto_ctx(ctx);
-	return ret;
-}
-
-bool f2fs_valid_contents_enc_mode(uint32_t mode)
-{
-	return (mode == F2FS_ENCRYPTION_MODE_AES_256_XTS);
-}
-
-/**
- * f2fs_validate_encryption_key_size() - Validate the encryption key size
- * @mode: The key mode.
- * @size: The key size to validate.
- *
- * Return: The validated key size for @mode. Zero if invalid.
- */
-uint32_t f2fs_validate_encryption_key_size(uint32_t mode, uint32_t size)
-{
-	if (size == f2fs_encryption_key_size(mode))
-		return size;
-	return 0;
-}
diff --git a/fs/f2fs/crypto_key.c b/fs/f2fs/crypto_key.c
deleted file mode 100644
index 5de2d866a25c..000000000000
--- a/fs/f2fs/crypto_key.c
+++ /dev/null
@@ -1,254 +0,0 @@
-/*
- * linux/fs/f2fs/crypto_key.c
- *
- * Copied from linux/fs/f2fs/crypto_key.c
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains encryption key functions for f2fs
- *
- * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
- */
-#include <keys/encrypted-type.h>
-#include <keys/user-type.h>
-#include <linux/random.h>
-#include <linux/scatterlist.h>
-#include <uapi/linux/keyctl.h>
-#include <crypto/hash.h>
-#include <linux/f2fs_fs.h>
-
-#include "f2fs.h"
-#include "xattr.h"
-
-static void derive_crypt_complete(struct crypto_async_request *req, int rc)
-{
-	struct f2fs_completion_result *ecr = req->data;
-
-	if (rc == -EINPROGRESS)
-		return;
-
-	ecr->res = rc;
-	complete(&ecr->completion);
-}
-
-/**
- * f2fs_derive_key_aes() - Derive a key using AES-128-ECB
- * @deriving_key: Encryption key used for derivatio.
- * @source_key:   Source key to which to apply derivation.
- * @derived_key:  Derived key.
- *
- * Return: Zero on success; non-zero otherwise.
- */
-static int f2fs_derive_key_aes(char deriving_key[F2FS_AES_128_ECB_KEY_SIZE],
-				char source_key[F2FS_AES_256_XTS_KEY_SIZE],
-				char derived_key[F2FS_AES_256_XTS_KEY_SIZE])
-{
-	int res = 0;
-	struct ablkcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
-	struct scatterlist src_sg, dst_sg;
-	struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
-								0);
-
-	if (IS_ERR(tfm)) {
-		res = PTR_ERR(tfm);
-		tfm = NULL;
-		goto out;
-	}
-	crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		res = -ENOMEM;
-		goto out;
-	}
-	ablkcipher_request_set_callback(req,
-			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-			derive_crypt_complete, &ecr);
-	res = crypto_ablkcipher_setkey(tfm, deriving_key,
-				F2FS_AES_128_ECB_KEY_SIZE);
-	if (res < 0)
-		goto out;
-
-	sg_init_one(&src_sg, source_key, F2FS_AES_256_XTS_KEY_SIZE);
-	sg_init_one(&dst_sg, derived_key, F2FS_AES_256_XTS_KEY_SIZE);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
-					F2FS_AES_256_XTS_KEY_SIZE, NULL);
-	res = crypto_ablkcipher_encrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-out:
-	if (req)
-		ablkcipher_request_free(req);
-	if (tfm)
-		crypto_free_ablkcipher(tfm);
-	return res;
-}
-
-static void f2fs_free_crypt_info(struct f2fs_crypt_info *ci)
-{
-	if (!ci)
-		return;
-
-	key_put(ci->ci_keyring_key);
-	crypto_free_ablkcipher(ci->ci_ctfm);
-	kmem_cache_free(f2fs_crypt_info_cachep, ci);
-}
-
-void f2fs_free_encryption_info(struct inode *inode, struct f2fs_crypt_info *ci)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct f2fs_crypt_info *prev;
-
-	if (ci == NULL)
-		ci = ACCESS_ONCE(fi->i_crypt_info);
-	if (ci == NULL)
-		return;
-	prev = cmpxchg(&fi->i_crypt_info, ci, NULL);
-	if (prev != ci)
-		return;
-
-	f2fs_free_crypt_info(ci);
-}
-
-int _f2fs_get_encryption_info(struct inode *inode)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct f2fs_crypt_info *crypt_info;
-	char full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE +
-				(F2FS_KEY_DESCRIPTOR_SIZE * 2) + 1];
-	struct key *keyring_key = NULL;
-	struct f2fs_encryption_key *master_key;
-	struct f2fs_encryption_context ctx;
-	const struct user_key_payload *ukp;
-	struct crypto_ablkcipher *ctfm;
-	const char *cipher_str;
-	char raw_key[F2FS_MAX_KEY_SIZE];
-	char mode;
-	int res;
-
-	res = f2fs_crypto_initialize();
-	if (res)
-		return res;
-retry:
-	crypt_info = ACCESS_ONCE(fi->i_crypt_info);
-	if (crypt_info) {
-		if (!crypt_info->ci_keyring_key ||
-				key_validate(crypt_info->ci_keyring_key) == 0)
-			return 0;
-		f2fs_free_encryption_info(inode, crypt_info);
-		goto retry;
-	}
-
-	res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
-				&ctx, sizeof(ctx), NULL);
-	if (res < 0)
-		return res;
-	else if (res != sizeof(ctx))
-		return -EINVAL;
-	res = 0;
-
-	crypt_info = kmem_cache_alloc(f2fs_crypt_info_cachep, GFP_NOFS);
-	if (!crypt_info)
-		return -ENOMEM;
-
-	crypt_info->ci_flags = ctx.flags;
-	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
-	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
-	crypt_info->ci_ctfm = NULL;
-	crypt_info->ci_keyring_key = NULL;
-	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
-				sizeof(crypt_info->ci_master_key));
-	if (S_ISREG(inode->i_mode))
-		mode = crypt_info->ci_data_mode;
-	else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
-		mode = crypt_info->ci_filename_mode;
-	else
-		BUG();
-
-	switch (mode) {
-	case F2FS_ENCRYPTION_MODE_AES_256_XTS:
-		cipher_str = "xts(aes)";
-		break;
-	case F2FS_ENCRYPTION_MODE_AES_256_CTS:
-		cipher_str = "cts(cbc(aes))";
-		break;
-	default:
-		printk_once(KERN_WARNING
-			    "f2fs: unsupported key mode %d (ino %u)\n",
-			    mode, (unsigned) inode->i_ino);
-		res = -ENOKEY;
-		goto out;
-	}
-
-	memcpy(full_key_descriptor, F2FS_KEY_DESC_PREFIX,
-					F2FS_KEY_DESC_PREFIX_SIZE);
-	sprintf(full_key_descriptor + F2FS_KEY_DESC_PREFIX_SIZE,
-					"%*phN", F2FS_KEY_DESCRIPTOR_SIZE,
-					ctx.master_key_descriptor);
-	full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE +
-					(2 * F2FS_KEY_DESCRIPTOR_SIZE)] = '\0';
-	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
-	if (IS_ERR(keyring_key)) {
-		res = PTR_ERR(keyring_key);
-		keyring_key = NULL;
-		goto out;
-	}
-	crypt_info->ci_keyring_key = keyring_key;
-	BUG_ON(keyring_key->type != &key_type_logon);
-	ukp = user_key_payload(keyring_key);
-	if (ukp->datalen != sizeof(struct f2fs_encryption_key)) {
-		res = -EINVAL;
-		goto out;
-	}
-	master_key = (struct f2fs_encryption_key *)ukp->data;
-	BUILD_BUG_ON(F2FS_AES_128_ECB_KEY_SIZE !=
-				F2FS_KEY_DERIVATION_NONCE_SIZE);
-	BUG_ON(master_key->size != F2FS_AES_256_XTS_KEY_SIZE);
-	res = f2fs_derive_key_aes(ctx.nonce, master_key->raw,
-				  raw_key);
-	if (res)
-		goto out;
-
-	ctfm = crypto_alloc_ablkcipher(cipher_str, 0, 0);
-	if (!ctfm || IS_ERR(ctfm)) {
-		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
-		printk(KERN_DEBUG
-		       "%s: error %d (inode %u) allocating crypto tfm\n",
-		       __func__, res, (unsigned) inode->i_ino);
-		goto out;
-	}
-	crypt_info->ci_ctfm = ctfm;
-	crypto_ablkcipher_clear_flags(ctfm, ~0);
-	crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm),
-			     CRYPTO_TFM_REQ_WEAK_KEY);
-	res = crypto_ablkcipher_setkey(ctfm, raw_key,
-					f2fs_encryption_key_size(mode));
-	if (res)
-		goto out;
-
-	memzero_explicit(raw_key, sizeof(raw_key));
-	if (cmpxchg(&fi->i_crypt_info, NULL, crypt_info) != NULL) {
-		f2fs_free_crypt_info(crypt_info);
-		goto retry;
-	}
-	return 0;
-
-out:
-	if (res == -ENOKEY && !S_ISREG(inode->i_mode))
-		res = 0;
-
-	f2fs_free_crypt_info(crypt_info);
-	memzero_explicit(raw_key, sizeof(raw_key));
-	return res;
-}
-
-int f2fs_has_encryption_key(struct inode *inode)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-
-	return (fi->i_crypt_info != NULL);
-}
diff --git a/fs/f2fs/crypto_policy.c b/fs/f2fs/crypto_policy.c
deleted file mode 100644
index d4a96af513c2..000000000000
--- a/fs/f2fs/crypto_policy.c
+++ /dev/null
@@ -1,209 +0,0 @@
-/*
- * copied from linux/fs/ext4/crypto_policy.c
- *
- * Copyright (C) 2015, Google, Inc.
- * Copyright (C) 2015, Motorola Mobility.
- *
- * This contains encryption policy functions for f2fs with some modifications
- * to support f2fs-specific xattr APIs.
- *
- * Written by Michael Halcrow, 2015.
- * Modified by Jaegeuk Kim, 2015.
- */
-#include <linux/random.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/f2fs_fs.h>
-
-#include "f2fs.h"
-#include "xattr.h"
-
-static int f2fs_inode_has_encryption_context(struct inode *inode)
-{
-	int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-			F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0, NULL);
-	return (res > 0);
-}
-
-/*
- * check whether the policy is consistent with the encryption context
- * for the inode
- */
-static int f2fs_is_encryption_context_consistent_with_policy(
-	struct inode *inode, const struct f2fs_encryption_policy *policy)
-{
-	struct f2fs_encryption_context ctx;
-	int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-				sizeof(ctx), NULL);
-
-	if (res != sizeof(ctx))
-		return 0;
-
-	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
-				F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
-			(ctx.flags == policy->flags) &&
-			(ctx.contents_encryption_mode ==
-			 policy->contents_encryption_mode) &&
-			(ctx.filenames_encryption_mode ==
-			 policy->filenames_encryption_mode));
-}
-
-static int f2fs_create_encryption_context_from_policy(
-	struct inode *inode, const struct f2fs_encryption_policy *policy)
-{
-	struct f2fs_encryption_context ctx;
-
-	ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1;
-	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
-			F2FS_KEY_DESCRIPTOR_SIZE);
-
-	if (!f2fs_valid_contents_enc_mode(policy->contents_encryption_mode)) {
-		printk(KERN_WARNING
-		       "%s: Invalid contents encryption mode %d\n", __func__,
-			policy->contents_encryption_mode);
-		return -EINVAL;
-	}
-
-	if (!f2fs_valid_filenames_enc_mode(policy->filenames_encryption_mode)) {
-		printk(KERN_WARNING
-		       "%s: Invalid filenames encryption mode %d\n", __func__,
-			policy->filenames_encryption_mode);
-		return -EINVAL;
-	}
-
-	if (policy->flags & ~F2FS_POLICY_FLAGS_VALID)
-		return -EINVAL;
-
-	ctx.contents_encryption_mode = policy->contents_encryption_mode;
-	ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
-	ctx.flags = policy->flags;
-	BUILD_BUG_ON(sizeof(ctx.nonce) != F2FS_KEY_DERIVATION_NONCE_SIZE);
-	get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE);
-
-	return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-			F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-			sizeof(ctx), NULL, XATTR_CREATE);
-}
-
-int f2fs_process_policy(const struct f2fs_encryption_policy *policy,
-			struct inode *inode)
-{
-	if (policy->version != 0)
-		return -EINVAL;
-
-	if (!S_ISDIR(inode->i_mode))
-		return -EINVAL;
-
-	if (!f2fs_inode_has_encryption_context(inode)) {
-		if (!f2fs_empty_dir(inode))
-			return -ENOTEMPTY;
-		return f2fs_create_encryption_context_from_policy(inode,
-								  policy);
-	}
-
-	if (f2fs_is_encryption_context_consistent_with_policy(inode, policy))
-		return 0;
-
-	printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
-	       __func__);
-	return -EINVAL;
-}
-
-int f2fs_get_policy(struct inode *inode, struct f2fs_encryption_policy *policy)
-{
-	struct f2fs_encryption_context ctx;
-	int res;
-
-	if (!f2fs_encrypted_inode(inode))
-		return -ENODATA;
-
-	res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
-				&ctx, sizeof(ctx), NULL);
-	if (res != sizeof(ctx))
-		return -ENODATA;
-	if (ctx.format != F2FS_ENCRYPTION_CONTEXT_FORMAT_V1)
-		return -EINVAL;
-
-	policy->version = 0;
-	policy->contents_encryption_mode = ctx.contents_encryption_mode;
-	policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
-	policy->flags = ctx.flags;
-	memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
-			F2FS_KEY_DESCRIPTOR_SIZE);
-	return 0;
-}
-
-int f2fs_is_child_context_consistent_with_parent(struct inode *parent,
-						struct inode *child)
-{
-	struct f2fs_crypt_info *parent_ci, *child_ci;
-	int res;
-
-	if ((parent == NULL) || (child == NULL)) {
-		pr_err("parent %p child %p\n", parent, child);
-		BUG_ON(1);
-	}
-
-	/* no restrictions if the parent directory is not encrypted */
-	if (!f2fs_encrypted_inode(parent))
-		return 1;
-	/* if the child directory is not encrypted, this is always a problem */
-	if (!f2fs_encrypted_inode(child))
-		return 0;
-	res = f2fs_get_encryption_info(parent);
-	if (res)
-		return 0;
-	res = f2fs_get_encryption_info(child);
-	if (res)
-		return 0;
-	parent_ci = F2FS_I(parent)->i_crypt_info;
-	child_ci = F2FS_I(child)->i_crypt_info;
-	if (!parent_ci && !child_ci)
-		return 1;
-	if (!parent_ci || !child_ci)
-		return 0;
-
-	return (memcmp(parent_ci->ci_master_key,
-			child_ci->ci_master_key,
-			F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
-		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
-		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
-		(parent_ci->ci_flags == child_ci->ci_flags));
-}
-
-/**
- * f2fs_inherit_context() - Sets a child context from its parent
- * @parent: Parent inode from which the context is inherited.
- * @child:  Child inode that inherits the context from @parent.
- *
- * Return: Zero on success, non-zero otherwise
- */
-int f2fs_inherit_context(struct inode *parent, struct inode *child,
-						struct page *ipage)
-{
-	struct f2fs_encryption_context ctx;
-	struct f2fs_crypt_info *ci;
-	int res;
-
-	res = f2fs_get_encryption_info(parent);
-	if (res < 0)
-		return res;
-
-	ci = F2FS_I(parent)->i_crypt_info;
-	BUG_ON(ci == NULL);
-
-	ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1;
-
-	ctx.contents_encryption_mode = ci->ci_data_mode;
-	ctx.filenames_encryption_mode = ci->ci_filename_mode;
-	ctx.flags = ci->ci_flags;
-	memcpy(ctx.master_key_descriptor, ci->ci_master_key,
-			F2FS_KEY_DESCRIPTOR_SIZE);
-
-	get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE);
-	return f2fs_setxattr(child, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-				sizeof(ctx), ipage, XATTR_CREATE);
-}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 5c06db17e41f..e5c762b37239 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -34,9 +34,9 @@ static void f2fs_read_end_io(struct bio *bio)
 
 	if (f2fs_bio_encrypted(bio)) {
 		if (bio->bi_error) {
-			f2fs_release_crypto_ctx(bio->bi_private);
+			fscrypt_release_ctx(bio->bi_private);
 		} else {
-			f2fs_end_io_crypto_work(bio->bi_private, bio);
+			fscrypt_decrypt_bio_pages(bio->bi_private, bio);
 			return;
 		}
 	}
@@ -64,10 +64,9 @@ static void f2fs_write_end_io(struct bio *bio)
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 
-		f2fs_restore_and_release_control_page(&page);
+		fscrypt_pullback_bio_page(&page, true);
 
 		if (unlikely(bio->bi_error)) {
-			set_page_dirty(page);
 			set_bit(AS_EIO, &page->mapping->flags);
 			f2fs_stop_checkpoint(sbi);
 		}
@@ -75,8 +74,7 @@ static void f2fs_write_end_io(struct bio *bio)
 		dec_page_count(sbi, F2FS_WRITEBACK);
 	}
 
-	if (!get_pages(sbi, F2FS_WRITEBACK) &&
-			!list_empty(&sbi->cp_wait.task_list))
+	if (!get_pages(sbi, F2FS_WRITEBACK) && wq_has_sleeper(&sbi->cp_wait))
 		wake_up(&sbi->cp_wait);
 
 	bio_put(bio);
@@ -116,8 +114,54 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 	io->bio = NULL;
 }
 
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
-				enum page_type type, int rw)
+static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
+						struct page *page, nid_t ino)
+{
+	struct bio_vec *bvec;
+	struct page *target;
+	int i;
+
+	if (!io->bio)
+		return false;
+
+	if (!inode && !page && !ino)
+		return true;
+
+	bio_for_each_segment_all(bvec, io->bio, i) {
+
+		if (bvec->bv_page->mapping)
+			target = bvec->bv_page;
+		else
+			target = fscrypt_control_page(bvec->bv_page);
+
+		if (inode && inode == target->mapping->host)
+			return true;
+		if (page && page == target)
+			return true;
+		if (ino && ino == ino_of_node(target))
+			return true;
+	}
+
+	return false;
+}
+
+static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
+						struct page *page, nid_t ino,
+						enum page_type type)
+{
+	enum page_type btype = PAGE_TYPE_OF_BIO(type);
+	struct f2fs_bio_info *io = &sbi->write_io[btype];
+	bool ret;
+
+	down_read(&io->io_rwsem);
+	ret = __has_merged_page(io, inode, page, ino);
+	up_read(&io->io_rwsem);
+	return ret;
+}
+
+static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
+				struct inode *inode, struct page *page,
+				nid_t ino, enum page_type type, int rw)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
 	struct f2fs_bio_info *io;
@@ -126,6 +170,9 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 
 	down_write(&io->io_rwsem);
 
+	if (!__has_merged_page(io, inode, page, ino))
+		goto out;
+
 	/* change META to META_FLUSH in the checkpoint procedure */
 	if (type >= META_FLUSH) {
 		io->fio.type = META_FLUSH;
@@ -135,9 +182,31 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 			io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO;
 	}
 	__submit_merged_bio(io);
+out:
 	up_write(&io->io_rwsem);
 }
 
+void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
+									int rw)
+{
+	__f2fs_submit_merged_bio(sbi, NULL, NULL, 0, type, rw);
+}
+
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+				struct inode *inode, struct page *page,
+				nid_t ino, enum page_type type, int rw)
+{
+	if (has_merged_page(sbi, inode, page, ino, type))
+		__f2fs_submit_merged_bio(sbi, inode, page, ino, type, rw);
+}
+
+void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi)
+{
+	f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	f2fs_submit_merged_bio(sbi, NODE, WRITE);
+	f2fs_submit_merged_bio(sbi, META, WRITE);
+}
+
 /*
  * Fill the locked page with data located in the block address.
  * Return unlocked page.
@@ -145,13 +214,14 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 {
 	struct bio *bio;
-	struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+	struct page *page = fio->encrypted_page ?
+			fio->encrypted_page : fio->page;
 
 	trace_f2fs_submit_page_bio(page, fio);
 	f2fs_trace_ios(fio, 0);
 
 	/* Allocate a new bio */
-	bio = __bio_alloc(fio->sbi, fio->blk_addr, 1, is_read_io(fio->rw));
+	bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->rw));
 
 	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
 		bio_put(bio);
@@ -172,21 +242,24 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 
 	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
 
-	verify_block_addr(sbi, fio->blk_addr);
+	if (fio->old_blkaddr != NEW_ADDR)
+		verify_block_addr(sbi, fio->old_blkaddr);
+	verify_block_addr(sbi, fio->new_blkaddr);
 
 	down_write(&io->io_rwsem);
 
 	if (!is_read)
 		inc_page_count(sbi, F2FS_WRITEBACK);
 
-	if (io->bio && (io->last_block_in_bio != fio->blk_addr - 1 ||
+	if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 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, fio->blk_addr, bio_blocks, is_read);
+		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
+						bio_blocks, is_read);
 		io->fio = *fio;
 	}
 
@@ -198,7 +271,7 @@ alloc_new:
 		goto alloc_new;
 	}
 
-	io->last_block_in_bio = fio->blk_addr;
+	io->last_block_in_bio = fio->new_blkaddr;
 	f2fs_trace_ios(fio, 0);
 
 	up_write(&io->io_rwsem);
@@ -218,7 +291,7 @@ void set_data_blkaddr(struct dnode_of_data *dn)
 	struct page *node_page = dn->node_page;
 	unsigned int ofs_in_node = dn->ofs_in_node;
 
-	f2fs_wait_on_page_writeback(node_page, NODE);
+	f2fs_wait_on_page_writeback(node_page, NODE, true);
 
 	rn = F2FS_NODE(node_page);
 
@@ -229,6 +302,13 @@ void set_data_blkaddr(struct dnode_of_data *dn)
 		dn->node_changed = true;
 }
 
+void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
+{
+	dn->data_blkaddr = blkaddr;
+	set_data_blkaddr(dn);
+	f2fs_update_extent_cache(dn);
+}
+
 int reserve_new_block(struct dnode_of_data *dn)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
@@ -332,7 +412,7 @@ got_it:
 		return page;
 	}
 
-	fio.blk_addr = dn.data_blkaddr;
+	fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
 	fio.page = page;
 	err = f2fs_submit_page_bio(&fio);
 	if (err)
@@ -461,7 +541,6 @@ got_it:
 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;
 	struct node_info ni;
 	int seg = CURSEG_WARM_DATA;
@@ -489,7 +568,7 @@ alloc:
 	set_data_blkaddr(dn);
 
 	/* update i_size */
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
 							dn->ofs_in_node;
 	if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT))
 		i_size_write(dn->inode,
@@ -497,67 +576,33 @@ alloc:
 	return 0;
 }
 
-static int __allocate_data_blocks(struct inode *inode, loff_t offset,
-							size_t count)
+ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 {
-	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;
-	int err = 0;
-
-	while (len) {
-		f2fs_lock_op(sbi);
-
-		/* When reading holes, we need its node page */
-		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		err = get_dnode_of_data(&dn, start, ALLOC_NODE);
-		if (err)
-			goto out;
-
-		allocated = false;
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
-
-		while (dn.ofs_in_node < end_offset && len) {
-			block_t blkaddr;
-
-			if (unlikely(f2fs_cp_error(sbi))) {
-				err = -EIO;
-				goto sync_out;
-			}
-
-			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
-			if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) {
-				err = __allocate_data_block(&dn);
-				if (err)
-					goto sync_out;
-				allocated = true;
-			}
-			len--;
-			start++;
-			dn.ofs_in_node++;
-		}
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct f2fs_map_blocks map;
+	ssize_t ret = 0;
 
-		if (allocated)
-			sync_inode_page(&dn);
+	map.m_lblk = F2FS_BYTES_TO_BLK(iocb->ki_pos);
+	map.m_len = F2FS_BLK_ALIGN(iov_iter_count(from));
+	map.m_next_pgofs = NULL;
 
-		f2fs_put_dnode(&dn);
-		f2fs_unlock_op(sbi);
+	if (f2fs_encrypted_inode(inode))
+		return 0;
 
-		f2fs_balance_fs(sbi, dn.node_changed);
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		ret = f2fs_convert_inline_inode(inode);
+		if (ret)
+			return ret;
+		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
 	}
-	return err;
-
-sync_out:
-	if (allocated)
-		sync_inode_page(&dn);
-	f2fs_put_dnode(&dn);
-out:
-	f2fs_unlock_op(sbi);
-	f2fs_balance_fs(sbi, dn.node_changed);
-	return err;
+	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) {
+		ret = f2fs_convert_inline_inode(inode);
+		if (ret)
+			return ret;
+	}
+	if (!f2fs_has_inline_data(inode))
+		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+	return ret;
 }
 
 /*
@@ -588,13 +633,14 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	/* it only supports block size == page size */
 	pgofs =	(pgoff_t)map->m_lblk;
 
-	if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
+	if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
 		map->m_pblk = ei.blk + pgofs - ei.fofs;
 		map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
 		map->m_flags = F2FS_MAP_MAPPED;
 		goto out;
 	}
 
+next_dnode:
 	if (create)
 		f2fs_lock_op(sbi);
 
@@ -602,120 +648,98 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, pgofs, mode);
 	if (err) {
-		if (err == -ENOENT)
+		if (err == -ENOENT) {
 			err = 0;
+			if (map->m_next_pgofs)
+				*map->m_next_pgofs =
+					get_next_page_offset(&dn, pgofs);
+		}
 		goto unlock_out;
 	}
 
-	if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) {
+	end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+
+next_block:
+	blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+
+	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
 		if (create) {
 			if (unlikely(f2fs_cp_error(sbi))) {
 				err = -EIO;
-				goto put_out;
+				goto sync_out;
+			}
+			if (flag == F2FS_GET_BLOCK_PRE_AIO) {
+				if (blkaddr == NULL_ADDR)
+					err = reserve_new_block(&dn);
+			} else {
+				err = __allocate_data_block(&dn);
 			}
-			err = __allocate_data_block(&dn);
 			if (err)
-				goto put_out;
+				goto sync_out;
 			allocated = true;
 			map->m_flags = F2FS_MAP_NEW;
+			blkaddr = dn.data_blkaddr;
 		} else {
+			if (flag == F2FS_GET_BLOCK_FIEMAP &&
+						blkaddr == NULL_ADDR) {
+				if (map->m_next_pgofs)
+					*map->m_next_pgofs = pgofs + 1;
+			}
 			if (flag != F2FS_GET_BLOCK_FIEMAP ||
-						dn.data_blkaddr != NEW_ADDR) {
+						blkaddr != NEW_ADDR) {
 				if (flag == F2FS_GET_BLOCK_BMAP)
 					err = -ENOENT;
-				goto put_out;
+				goto sync_out;
 			}
-
-			/*
-			 * preallocated unwritten block should be mapped
-			 * for fiemap.
-			 */
-			if (dn.data_blkaddr == NEW_ADDR)
-				map->m_flags = F2FS_MAP_UNWRITTEN;
 		}
 	}
 
-	map->m_flags |= F2FS_MAP_MAPPED;
-	map->m_pblk = dn.data_blkaddr;
-	map->m_len = 1;
+	if (map->m_len == 0) {
+		/* preallocated unwritten block should be mapped for fiemap. */
+		if (blkaddr == NEW_ADDR)
+			map->m_flags |= F2FS_MAP_UNWRITTEN;
+		map->m_flags |= F2FS_MAP_MAPPED;
+
+		map->m_pblk = blkaddr;
+		map->m_len = 1;
+	} else if ((map->m_pblk != NEW_ADDR &&
+			blkaddr == (map->m_pblk + ofs)) ||
+			(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
+			flag == F2FS_GET_BLOCK_PRE_DIO ||
+			flag == F2FS_GET_BLOCK_PRE_AIO) {
+		ofs++;
+		map->m_len++;
+	} else {
+		goto sync_out;
+	}
 
-	end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
 	dn.ofs_in_node++;
 	pgofs++;
 
-get_next:
-	if (map->m_len >= maxblocks)
-		goto sync_out;
+	if (map->m_len < maxblocks) {
+		if (dn.ofs_in_node < end_offset)
+			goto next_block;
 
-	if (dn.ofs_in_node >= end_offset) {
 		if (allocated)
 			sync_inode_page(&dn);
-		allocated = false;
 		f2fs_put_dnode(&dn);
 
 		if (create) {
 			f2fs_unlock_op(sbi);
-			f2fs_balance_fs(sbi, dn.node_changed);
-			f2fs_lock_op(sbi);
-		}
-
-		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		err = get_dnode_of_data(&dn, pgofs, mode);
-		if (err) {
-			if (err == -ENOENT)
-				err = 0;
-			goto unlock_out;
-		}
-
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
-	}
-
-	blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
-
-	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
-		if (create) {
-			if (unlikely(f2fs_cp_error(sbi))) {
-				err = -EIO;
-				goto sync_out;
-			}
-			err = __allocate_data_block(&dn);
-			if (err)
-				goto sync_out;
-			allocated = true;
-			map->m_flags |= F2FS_MAP_NEW;
-			blkaddr = dn.data_blkaddr;
-		} else {
-			/*
-			 * we only merge preallocated unwritten blocks
-			 * for fiemap.
-			 */
-			if (flag != F2FS_GET_BLOCK_FIEMAP ||
-					blkaddr != NEW_ADDR)
-				goto sync_out;
+			f2fs_balance_fs(sbi, allocated);
 		}
-	}
-
-	/* Give more consecutive addresses for the readahead */
-	if ((map->m_pblk != NEW_ADDR &&
-			blkaddr == (map->m_pblk + ofs)) ||
-			(map->m_pblk == NEW_ADDR &&
-			blkaddr == NEW_ADDR)) {
-		ofs++;
-		dn.ofs_in_node++;
-		pgofs++;
-		map->m_len++;
-		goto get_next;
+		allocated = false;
+		goto next_dnode;
 	}
 
 sync_out:
 	if (allocated)
 		sync_inode_page(&dn);
-put_out:
 	f2fs_put_dnode(&dn);
 unlock_out:
 	if (create) {
 		f2fs_unlock_op(sbi);
-		f2fs_balance_fs(sbi, dn.node_changed);
+		f2fs_balance_fs(sbi, allocated);
 	}
 out:
 	trace_f2fs_map_blocks(inode, map, err);
@@ -723,13 +747,15 @@ out:
 }
 
 static int __get_data_block(struct inode *inode, sector_t iblock,
-			struct buffer_head *bh, int create, int flag)
+			struct buffer_head *bh, int create, int flag,
+			pgoff_t *next_pgofs)
 {
 	struct f2fs_map_blocks map;
 	int ret;
 
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
+	map.m_next_pgofs = next_pgofs;
 
 	ret = f2fs_map_blocks(inode, &map, create, flag);
 	if (!ret) {
@@ -741,16 +767,18 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 }
 
 static int get_data_block(struct inode *inode, sector_t iblock,
-			struct buffer_head *bh_result, int create, int flag)
+			struct buffer_head *bh_result, int create, int flag,
+			pgoff_t *next_pgofs)
 {
-	return __get_data_block(inode, iblock, bh_result, create, flag);
+	return __get_data_block(inode, iblock, bh_result, create,
+							flag, next_pgofs);
 }
 
 static int get_data_block_dio(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create)
 {
 	return __get_data_block(inode, iblock, bh_result, create,
-						F2FS_GET_BLOCK_DIO);
+						F2FS_GET_BLOCK_DIO, NULL);
 }
 
 static int get_data_block_bmap(struct inode *inode, sector_t iblock,
@@ -761,7 +789,7 @@ static int get_data_block_bmap(struct inode *inode, sector_t iblock,
 		return -EFBIG;
 
 	return __get_data_block(inode, iblock, bh_result, create,
-						F2FS_GET_BLOCK_BMAP);
+						F2FS_GET_BLOCK_BMAP, NULL);
 }
 
 static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
@@ -779,6 +807,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 {
 	struct buffer_head map_bh;
 	sector_t start_blk, last_blk;
+	pgoff_t next_pgofs;
 	loff_t isize;
 	u64 logical = 0, phys = 0, size = 0;
 	u32 flags = 0;
@@ -814,14 +843,15 @@ next:
 	map_bh.b_size = len;
 
 	ret = get_data_block(inode, start_blk, &map_bh, 0,
-					F2FS_GET_BLOCK_FIEMAP);
+					F2FS_GET_BLOCK_FIEMAP, &next_pgofs);
 	if (ret)
 		goto out;
 
 	/* HOLE */
 	if (!buffer_mapped(&map_bh)) {
+		start_blk = next_pgofs;
 		/* Go through holes util pass the EOF */
-		if (blk_to_logical(inode, start_blk++) < isize)
+		if (blk_to_logical(inode, start_blk) < isize)
 			goto prep_next;
 		/* Found a hole beyond isize means no more extents.
 		 * Note that the premise is that filesystems don't
@@ -889,6 +919,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 	map.m_lblk = 0;
 	map.m_len = 0;
 	map.m_flags = 0;
+	map.m_next_pgofs = NULL;
 
 	for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
 
@@ -927,7 +958,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 			map.m_len = last_block - block_in_file;
 
 			if (f2fs_map_blocks(inode, &map, 0,
-							F2FS_GET_BLOCK_READ))
+						F2FS_GET_BLOCK_READ))
 				goto set_error_page;
 		}
 got_it:
@@ -956,12 +987,12 @@ submit_and_realloc:
 			bio = NULL;
 		}
 		if (bio == NULL) {
-			struct f2fs_crypto_ctx *ctx = NULL;
+			struct fscrypt_ctx *ctx = NULL;
 
 			if (f2fs_encrypted_inode(inode) &&
 					S_ISREG(inode->i_mode)) {
 
-				ctx = f2fs_get_crypto_ctx(inode);
+				ctx = fscrypt_get_ctx(inode);
 				if (IS_ERR(ctx))
 					goto set_error_page;
 
@@ -974,7 +1005,7 @@ submit_and_realloc:
 				min_t(int, nr_pages, BIO_MAX_PAGES));
 			if (!bio) {
 				if (ctx)
-					f2fs_release_crypto_ctx(ctx);
+					fscrypt_release_ctx(ctx);
 				goto set_error_page;
 			}
 			bio->bi_bdev = bdev;
@@ -1052,10 +1083,10 @@ int do_write_data_page(struct f2fs_io_info *fio)
 	if (err)
 		return err;
 
-	fio->blk_addr = dn.data_blkaddr;
+	fio->old_blkaddr = dn.data_blkaddr;
 
 	/* This page is already truncated */
-	if (fio->blk_addr == NULL_ADDR) {
+	if (fio->old_blkaddr == NULL_ADDR) {
 		ClearPageUptodate(page);
 		goto out_writepage;
 	}
@@ -1064,9 +1095,9 @@ int do_write_data_page(struct f2fs_io_info *fio)
 
 		/* wait for GCed encrypted page writeback */
 		f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode),
-							fio->blk_addr);
+							fio->old_blkaddr);
 
-		fio->encrypted_page = f2fs_encrypt(inode, fio->page);
+		fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page);
 		if (IS_ERR(fio->encrypted_page)) {
 			err = PTR_ERR(fio->encrypted_page);
 			goto out_writepage;
@@ -1079,7 +1110,7 @@ int do_write_data_page(struct f2fs_io_info *fio)
 	 * If current allocation needs SSR,
 	 * it had better in-place writes for updated data.
 	 */
-	if (unlikely(fio->blk_addr != NEW_ADDR &&
+	if (unlikely(fio->old_blkaddr != NEW_ADDR &&
 			!is_cold_data(page) &&
 			!IS_ATOMIC_WRITTEN_PAGE(page) &&
 			need_inplace_update(inode))) {
@@ -1088,8 +1119,6 @@ int do_write_data_page(struct f2fs_io_info *fio)
 		trace_f2fs_do_write_data_page(page, IPU);
 	} else {
 		write_data_page(&dn, fio);
-		set_data_blkaddr(&dn);
-		f2fs_update_extent_cache(&dn);
 		trace_f2fs_do_write_data_page(page, OPU);
 		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 		if (page->index == 0)
@@ -1177,12 +1206,18 @@ out:
 	inode_dec_dirty_pages(inode);
 	if (err)
 		ClearPageUptodate(page);
+
+	if (wbc->for_reclaim) {
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, DATA, WRITE);
+		remove_dirty_inode(inode);
+	}
+
 	unlock_page(page);
 	f2fs_balance_fs(sbi, need_balance_fs);
-	if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi))) {
+
+	if (unlikely(f2fs_cp_error(sbi)))
 		f2fs_submit_merged_bio(sbi, DATA, WRITE);
-		remove_dirty_inode(inode);
-	}
+
 	return 0;
 
 redirty_out:
@@ -1282,7 +1317,8 @@ continue_unlock:
 
 			if (PageWriteback(page)) {
 				if (wbc->sync_mode != WB_SYNC_NONE)
-					f2fs_wait_on_page_writeback(page, DATA);
+					f2fs_wait_on_page_writeback(page,
+								DATA, true);
 				else
 					goto continue_unlock;
 			}
@@ -1339,8 +1375,6 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	int ret;
 	long diff;
 
-	trace_f2fs_writepages(mapping->host, wbc, DATA);
-
 	/* deal with chardevs and other special file */
 	if (!mapping->a_ops->writepage)
 		return 0;
@@ -1362,14 +1396,16 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto skip_write;
 
+	trace_f2fs_writepages(mapping->host, wbc, DATA);
+
 	diff = nr_pages_to_write(sbi, DATA, wbc);
 
-	if (!S_ISDIR(inode->i_mode)) {
+	if (!S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_ALL) {
 		mutex_lock(&sbi->writepages);
 		locked = true;
 	}
 	ret = f2fs_write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
 	if (locked)
 		mutex_unlock(&sbi->writepages);
 
@@ -1380,6 +1416,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 
 skip_write:
 	wbc->pages_skipped += get_dirty_pages(inode);
+	trace_f2fs_writepages(mapping->host, wbc, DATA);
 	return 0;
 }
 
@@ -1406,6 +1443,14 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
 	struct extent_info ei;
 	int err = 0;
 
+	/*
+	 * we already allocated all the blocks, so we don't need to get
+	 * the block addresses when there is no need to fill the page.
+	 */
+	if (!f2fs_has_inline_data(inode) && !f2fs_encrypted_inode(inode) &&
+					len == PAGE_CACHE_SIZE)
+		return 0;
+
 	if (f2fs_has_inline_data(inode) ||
 			(pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
 		f2fs_lock_op(sbi);
@@ -1425,7 +1470,7 @@ restart:
 		if (pos + len <= MAX_INLINE_DATA) {
 			read_inline_data(page, ipage);
 			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
-			sync_inode_page(&dn);
+			set_inline_node(ipage);
 		} else {
 			err = f2fs_convert_inline_page(&dn, page);
 			if (err)
@@ -1439,13 +1484,9 @@ restart:
 		if (f2fs_lookup_extent_cache(inode, index, &ei)) {
 			dn.data_blkaddr = ei.blk + index - ei.fofs;
 		} else {
-			bool restart = false;
-
 			/* hole case */
 			err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
-			if (err || (!err && dn.data_blkaddr == NULL_ADDR))
-				restart = true;
-			if (restart) {
+			if (err || (!err && dn.data_blkaddr == NULL_ADDR)) {
 				f2fs_put_dnode(&dn);
 				f2fs_lock_op(sbi);
 				locked = true;
@@ -1514,7 +1555,7 @@ repeat:
 		}
 	}
 
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, false);
 
 	/* wait for GCed encrypted page writeback */
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
@@ -1541,7 +1582,8 @@ repeat:
 			.sbi = sbi,
 			.type = DATA,
 			.rw = READ_SYNC,
-			.blk_addr = blkaddr,
+			.old_blkaddr = blkaddr,
+			.new_blkaddr = blkaddr,
 			.page = page,
 			.encrypted_page = NULL,
 		};
@@ -1561,7 +1603,7 @@ repeat:
 
 		/* avoid symlink page */
 		if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
-			err = f2fs_decrypt_one(inode, page);
+			err = fscrypt_decrypt_page(page);
 			if (err)
 				goto fail;
 		}
@@ -1592,7 +1634,6 @@ static int f2fs_write_end(struct file *file,
 	if (pos + copied > i_size_read(inode)) {
 		i_size_write(inode, pos + copied);
 		mark_inode_dirty(inode);
-		update_inode_page(inode);
 	}
 
 	f2fs_put_page(page, 1);
@@ -1617,34 +1658,21 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
 static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			      loff_t offset)
 {
-	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = mapping->host;
 	size_t count = iov_iter_count(iter);
 	int err;
 
-	/* we don't need to use inline_data strictly */
-	err = f2fs_convert_inline_inode(inode);
+	err = check_direct_IO(inode, iter, offset);
 	if (err)
 		return err;
 
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 		return 0;
 
-	err = check_direct_IO(inode, iter, offset);
-	if (err)
-		return err;
-
 	trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 
-	if (iov_iter_rw(iter) == WRITE) {
-		err = __allocate_data_blocks(inode, offset, count);
-		if (err)
-			goto out;
-	}
-
 	err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio);
-out:
 	if (err < 0 && iov_iter_rw(iter) == WRITE)
 		f2fs_write_failed(mapping, offset + count);
 
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index faa7495e2d7e..80641ad82745 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -77,7 +77,7 @@ static unsigned long dir_block_index(unsigned int level,
 }
 
 static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
-				struct f2fs_filename *fname,
+				struct fscrypt_name *fname,
 				f2fs_hash_t namehash,
 				int *max_slots,
 				struct page **res_page)
@@ -103,15 +103,15 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
 	return de;
 }
 
-struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname,
+struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
 			f2fs_hash_t namehash, int *max_slots,
 			struct f2fs_dentry_ptr *d)
 {
 	struct f2fs_dir_entry *de;
 	unsigned long bit_pos = 0;
 	int max_len = 0;
-	struct f2fs_str de_name = FSTR_INIT(NULL, 0);
-	struct f2fs_str *name = &fname->disk_name;
+	struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
+	struct fscrypt_str *name = &fname->disk_name;
 
 	if (max_slots)
 		*max_slots = 0;
@@ -157,7 +157,7 @@ found:
 
 static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 					unsigned int level,
-					struct f2fs_filename *fname,
+					struct fscrypt_name *fname,
 					struct page **res_page)
 {
 	struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
@@ -218,12 +218,12 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 	struct f2fs_dir_entry *de = NULL;
 	unsigned int max_depth;
 	unsigned int level;
-	struct f2fs_filename fname;
+	struct fscrypt_name fname;
 	int err;
 
 	*res_page = NULL;
 
-	err = f2fs_fname_setup_filename(dir, child, 1, &fname);
+	err = fscrypt_setup_filename(dir, child, 1, &fname);
 	if (err)
 		return NULL;
 
@@ -251,7 +251,7 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 			break;
 	}
 out:
-	f2fs_fname_free_filename(&fname);
+	fscrypt_free_filename(&fname);
 	return de;
 }
 
@@ -296,7 +296,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 {
 	enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA;
 	lock_page(page);
-	f2fs_wait_on_page_writeback(page, type);
+	f2fs_wait_on_page_writeback(page, type, true);
 	de->ino = cpu_to_le32(inode->i_ino);
 	set_de_type(de, inode->i_mode);
 	f2fs_dentry_kunmap(dir, page);
@@ -311,7 +311,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
 {
 	struct f2fs_inode *ri;
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 	/* copy name info. to this inode page */
 	ri = F2FS_INODE(ipage);
@@ -341,24 +341,14 @@ int update_dent_inode(struct inode *inode, struct inode *to,
 void do_make_empty_dir(struct inode *inode, struct inode *parent,
 					struct f2fs_dentry_ptr *d)
 {
-	struct f2fs_dir_entry *de;
-
-	de = &d->dentry[0];
-	de->name_len = cpu_to_le16(1);
-	de->hash_code = 0;
-	de->ino = cpu_to_le32(inode->i_ino);
-	memcpy(d->filename[0], ".", 1);
-	set_de_type(de, inode->i_mode);
+	struct qstr dot = QSTR_INIT(".", 1);
+	struct qstr dotdot = QSTR_INIT("..", 2);
 
-	de = &d->dentry[1];
-	de->hash_code = 0;
-	de->name_len = cpu_to_le16(2);
-	de->ino = cpu_to_le32(parent->i_ino);
-	memcpy(d->filename[1], "..", 2);
-	set_de_type(de, parent->i_mode);
+	/* update dirent of "." */
+	f2fs_update_dentry(inode->i_ino, inode->i_mode, d, &dot, 0, 0);
 
-	test_and_set_bit_le(0, (void *)d->bitmap);
-	test_and_set_bit_le(1, (void *)d->bitmap);
+	/* update dirent of ".." */
+	f2fs_update_dentry(parent->i_ino, parent->i_mode, d, &dotdot, 0, 1);
 }
 
 static int make_empty_dir(struct inode *inode,
@@ -413,7 +403,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 			goto put_error;
 
 		if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) {
-			err = f2fs_inherit_context(dir, inode, page);
+			err = fscrypt_inherit_context(dir, inode, page, false);
 			if (err)
 				goto put_error;
 		}
@@ -511,8 +501,12 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
 	memcpy(d->filename[bit_pos], name->name, name->len);
 	de->ino = cpu_to_le32(ino);
 	set_de_type(de, mode);
-	for (i = 0; i < slots; i++)
+	for (i = 0; i < slots; i++) {
 		test_and_set_bit_le(bit_pos + i, (void *)d->bitmap);
+		/* avoid wrong garbage data for readdir */
+		if (i)
+			(de + i)->name_len = 0;
+	}
 }
 
 /*
@@ -532,11 +526,11 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	struct f2fs_dentry_ptr d;
 	struct page *page = NULL;
-	struct f2fs_filename fname;
+	struct fscrypt_name fname;
 	struct qstr new_name;
 	int slots, err;
 
-	err = f2fs_fname_setup_filename(dir, name, 0, &fname);
+	err = fscrypt_setup_filename(dir, name, 0, &fname);
 	if (err)
 		return err;
 
@@ -598,7 +592,7 @@ start:
 	++level;
 	goto start;
 add_dentry:
-	f2fs_wait_on_page_writeback(dentry_page, DATA);
+	f2fs_wait_on_page_writeback(dentry_page, DATA, true);
 
 	if (inode) {
 		down_write(&F2FS_I(inode)->i_sem);
@@ -635,7 +629,7 @@ fail:
 	kunmap(dentry_page);
 	f2fs_put_page(dentry_page, 1);
 out:
-	f2fs_fname_free_filename(&fname);
+	fscrypt_free_filename(&fname);
 	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
 	return err;
 }
@@ -709,7 +703,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 		return f2fs_delete_inline_entry(dentry, page, dir, inode);
 
 	lock_page(page);
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 
 	dentry_blk = page_address(page);
 	bit_pos = dentry - dentry_blk->dentry;
@@ -777,12 +771,12 @@ bool f2fs_empty_dir(struct inode *dir)
 }
 
 bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
-				unsigned int start_pos, struct f2fs_str *fstr)
+			unsigned int start_pos, struct fscrypt_str *fstr)
 {
 	unsigned char d_type = DT_UNKNOWN;
 	unsigned int bit_pos;
 	struct f2fs_dir_entry *de = NULL;
-	struct f2fs_str de_name = FSTR_INIT(NULL, 0);
+	struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
 
 	bit_pos = ((unsigned long)ctx->pos % d->max);
 
@@ -792,6 +786,12 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			break;
 
 		de = &d->dentry[bit_pos];
+		if (de->name_len == 0) {
+			bit_pos++;
+			ctx->pos = start_pos + bit_pos;
+			continue;
+		}
+
 		if (de->file_type < F2FS_FT_MAX)
 			d_type = f2fs_filetype_table[de->file_type];
 		else
@@ -810,8 +810,9 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 
 			memcpy(de_name.name, d->filename[bit_pos], de_name.len);
 
-			ret = f2fs_fname_disk_to_usr(d->inode, &de->hash_code,
-							&de_name, fstr);
+			ret = fscrypt_fname_disk_to_usr(d->inode,
+						(u32)de->hash_code, 0,
+						&de_name, fstr);
 			kfree(de_name.name);
 			if (ret < 0)
 				return true;
@@ -839,16 +840,15 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 	struct file_ra_state *ra = &file->f_ra;
 	unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
 	struct f2fs_dentry_ptr d;
-	struct f2fs_str fstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
 	int err = 0;
 
 	if (f2fs_encrypted_inode(inode)) {
-		err = f2fs_get_encryption_info(inode);
-		if (err)
+		err = fscrypt_get_encryption_info(inode);
+		if (err && err != -ENOKEY)
 			return err;
 
-		err = f2fs_fname_crypto_alloc_buffer(inode, F2FS_NAME_LEN,
-								&fstr);
+		err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
 		if (err < 0)
 			return err;
 	}
@@ -888,15 +888,23 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 		f2fs_put_page(dentry_page, 1);
 	}
 out:
-	f2fs_fname_crypto_free_buffer(&fstr);
+	fscrypt_fname_free_buffer(&fstr);
 	return err;
 }
 
+static int f2fs_dir_open(struct inode *inode, struct file *filp)
+{
+	if (f2fs_encrypted_inode(inode))
+		return fscrypt_get_encryption_info(inode) ? -EACCES : 0;
+	return 0;
+}
+
 const struct file_operations f2fs_dir_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
 	.iterate	= f2fs_readdir,
 	.fsync		= f2fs_sync_file,
+	.open		= f2fs_dir_open,
 	.unlocked_ioctl	= f2fs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl   = f2fs_compat_ioctl,
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index ccd5c636d3fe..c859bb044728 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -33,6 +33,7 @@ static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi,
 
 	en->ei = *ei;
 	INIT_LIST_HEAD(&en->list);
+	en->et = et;
 
 	rb_link_node(&en->rb_node, parent, p);
 	rb_insert_color(&en->rb_node, &et->root);
@@ -50,6 +51,24 @@ static void __detach_extent_node(struct f2fs_sb_info *sbi,
 
 	if (et->cached_en == en)
 		et->cached_en = NULL;
+	kmem_cache_free(extent_node_slab, en);
+}
+
+/*
+ * Flow to release an extent_node:
+ * 1. list_del_init
+ * 2. __detach_extent_node
+ * 3. kmem_cache_free.
+ */
+static void __release_extent_node(struct f2fs_sb_info *sbi,
+			struct extent_tree *et, struct extent_node *en)
+{
+	spin_lock(&sbi->extent_lock);
+	f2fs_bug_on(sbi, list_empty(&en->list));
+	list_del_init(&en->list);
+	spin_unlock(&sbi->extent_lock);
+
+	__detach_extent_node(sbi, et, en);
 }
 
 static struct extent_tree *__grab_extent_tree(struct inode *inode)
@@ -129,7 +148,7 @@ static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi,
 }
 
 static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
-					struct extent_tree *et, bool free_all)
+					struct extent_tree *et)
 {
 	struct rb_node *node, *next;
 	struct extent_node *en;
@@ -139,18 +158,7 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
 	while (node) {
 		next = rb_next(node);
 		en = rb_entry(node, struct extent_node, rb_node);
-
-		if (free_all) {
-			spin_lock(&sbi->extent_lock);
-			if (!list_empty(&en->list))
-				list_del_init(&en->list);
-			spin_unlock(&sbi->extent_lock);
-		}
-
-		if (free_all || list_empty(&en->list)) {
-			__detach_extent_node(sbi, et, en);
-			kmem_cache_free(extent_node_slab, en);
-		}
+		__release_extent_node(sbi, et, en);
 		node = next;
 	}
 
@@ -232,9 +240,10 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 	if (en) {
 		*ei = en->ei;
 		spin_lock(&sbi->extent_lock);
-		if (!list_empty(&en->list))
+		if (!list_empty(&en->list)) {
 			list_move_tail(&en->list, &sbi->extent_list);
-		et->cached_en = en;
+			et->cached_en = en;
+		}
 		spin_unlock(&sbi->extent_lock);
 		ret = true;
 	}
@@ -329,7 +338,6 @@ lookup_neighbors:
 
 static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
 				struct extent_tree *et, struct extent_info *ei,
-				struct extent_node **den,
 				struct extent_node *prev_ex,
 				struct extent_node *next_ex)
 {
@@ -342,20 +350,25 @@ static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
 	}
 
 	if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
-		if (en) {
-			__detach_extent_node(sbi, et, prev_ex);
-			*den = prev_ex;
-		}
+		if (en)
+			__release_extent_node(sbi, et, prev_ex);
 		next_ex->ei.fofs = ei->fofs;
 		next_ex->ei.blk = ei->blk;
 		next_ex->ei.len += ei->len;
 		en = next_ex;
 	}
 
-	if (en) {
-		__try_update_largest_extent(et, en);
+	if (!en)
+		return NULL;
+
+	__try_update_largest_extent(et, en);
+
+	spin_lock(&sbi->extent_lock);
+	if (!list_empty(&en->list)) {
+		list_move_tail(&en->list, &sbi->extent_list);
 		et->cached_en = en;
 	}
+	spin_unlock(&sbi->extent_lock);
 	return en;
 }
 
@@ -391,7 +404,12 @@ do_insert:
 		return NULL;
 
 	__try_update_largest_extent(et, en);
+
+	/* update in global extent list */
+	spin_lock(&sbi->extent_lock);
+	list_add_tail(&en->list, &sbi->extent_list);
 	et->cached_en = en;
+	spin_unlock(&sbi->extent_lock);
 	return en;
 }
 
@@ -479,7 +497,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 		if (parts)
 			__try_update_largest_extent(et, en);
 		else
-			__detach_extent_node(sbi, et, en);
+			__release_extent_node(sbi, et, en);
 
 		/*
 		 * if original extent is split into zero or two parts, extent
@@ -490,31 +508,15 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 			insert_p = NULL;
 			insert_parent = NULL;
 		}
-
-		/* update in global extent list */
-		spin_lock(&sbi->extent_lock);
-		if (!parts && !list_empty(&en->list))
-			list_del(&en->list);
-		if (en1)
-			list_add_tail(&en1->list, &sbi->extent_list);
-		spin_unlock(&sbi->extent_lock);
-
-		/* release extent node */
-		if (!parts)
-			kmem_cache_free(extent_node_slab, en);
-
 		en = next_en;
 	}
 
 	/* 3. update extent in extent cache */
 	if (blkaddr) {
-		struct extent_node *den = NULL;
 
 		set_extent_info(&ei, fofs, blkaddr, len);
-		en1 = __try_merge_extent_node(sbi, et, &ei, &den,
-							prev_en, next_en);
-		if (!en1)
-			en1 = __insert_extent_tree(sbi, et, &ei,
+		if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
+			__insert_extent_tree(sbi, et, &ei,
 						insert_p, insert_parent);
 
 		/* give up extent_cache, if split and small updates happen */
@@ -524,24 +526,10 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 			et->largest.len = 0;
 			set_inode_flag(F2FS_I(inode), FI_NO_EXTENT);
 		}
-
-		spin_lock(&sbi->extent_lock);
-		if (en1) {
-			if (list_empty(&en1->list))
-				list_add_tail(&en1->list, &sbi->extent_list);
-			else
-				list_move_tail(&en1->list, &sbi->extent_list);
-		}
-		if (den && !list_empty(&den->list))
-			list_del(&den->list);
-		spin_unlock(&sbi->extent_lock);
-
-		if (den)
-			kmem_cache_free(extent_node_slab, den);
 	}
 
 	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
-		__free_extent_tree(sbi, et, true);
+		__free_extent_tree(sbi, et);
 
 	write_unlock(&et->lock);
 
@@ -550,14 +538,10 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 {
-	struct extent_tree *treevec[EXT_TREE_VEC_SIZE];
 	struct extent_tree *et, *next;
-	struct extent_node *en, *tmp;
-	unsigned long ino = F2FS_ROOT_INO(sbi);
-	unsigned int found;
+	struct extent_node *en;
 	unsigned int node_cnt = 0, tree_cnt = 0;
 	int remained;
-	bool do_free = false;
 
 	if (!test_opt(sbi, EXTENT_CACHE))
 		return 0;
@@ -572,10 +556,10 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 	list_for_each_entry_safe(et, next, &sbi->zombie_list, list) {
 		if (atomic_read(&et->node_cnt)) {
 			write_lock(&et->lock);
-			node_cnt += __free_extent_tree(sbi, et, true);
+			node_cnt += __free_extent_tree(sbi, et);
 			write_unlock(&et->lock);
 		}
-
+		f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
 		list_del_init(&et->list);
 		radix_tree_delete(&sbi->extent_tree_root, et->ino);
 		kmem_cache_free(extent_tree_slab, et);
@@ -585,6 +569,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 
 		if (node_cnt + tree_cnt >= nr_shrink)
 			goto unlock_out;
+		cond_resched();
 	}
 	up_write(&sbi->extent_tree_lock);
 
@@ -596,42 +581,29 @@ free_node:
 	remained = nr_shrink - (node_cnt + tree_cnt);
 
 	spin_lock(&sbi->extent_lock);
-	list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) {
-		if (!remained--)
+	for (; remained > 0; remained--) {
+		if (list_empty(&sbi->extent_list))
 			break;
-		list_del_init(&en->list);
-		do_free = true;
-	}
-	spin_unlock(&sbi->extent_lock);
-
-	if (do_free == false)
-		goto unlock_out;
-
-	/*
-	 * reset ino for searching victims from beginning of global extent tree.
-	 */
-	ino = F2FS_ROOT_INO(sbi);
-
-	while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root,
-				(void **)treevec, ino, EXT_TREE_VEC_SIZE))) {
-		unsigned i;
-
-		ino = treevec[found - 1]->ino + 1;
-		for (i = 0; i < found; i++) {
-			struct extent_tree *et = treevec[i];
+		en = list_first_entry(&sbi->extent_list,
+					struct extent_node, list);
+		et = en->et;
+		if (!write_trylock(&et->lock)) {
+			/* refresh this extent node's position in extent list */
+			list_move_tail(&en->list, &sbi->extent_list);
+			continue;
+		}
 
-			if (!atomic_read(&et->node_cnt))
-				continue;
+		list_del_init(&en->list);
+		spin_unlock(&sbi->extent_lock);
 
-			if (write_trylock(&et->lock)) {
-				node_cnt += __free_extent_tree(sbi, et, false);
-				write_unlock(&et->lock);
-			}
+		__detach_extent_node(sbi, et, en);
 
-			if (node_cnt + tree_cnt >= nr_shrink)
-				goto unlock_out;
-		}
+		write_unlock(&et->lock);
+		node_cnt++;
+		spin_lock(&sbi->extent_lock);
 	}
+	spin_unlock(&sbi->extent_lock);
+
 unlock_out:
 	up_write(&sbi->extent_tree_lock);
 out:
@@ -650,7 +622,7 @@ unsigned int f2fs_destroy_extent_node(struct inode *inode)
 		return 0;
 
 	write_lock(&et->lock);
-	node_cnt = __free_extent_tree(sbi, et, true);
+	node_cnt = __free_extent_tree(sbi, et);
 	write_unlock(&et->lock);
 
 	return node_cnt;
@@ -701,19 +673,21 @@ bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
 
 void f2fs_update_extent_cache(struct dnode_of_data *dn)
 {
-	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	pgoff_t fofs;
+	block_t blkaddr;
 
 	if (!f2fs_may_extent_tree(dn->inode))
 		return;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
-
+	if (dn->data_blkaddr == NEW_ADDR)
+		blkaddr = NULL_ADDR;
+	else
+		blkaddr = dn->data_blkaddr;
 
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
-							dn->ofs_in_node;
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
+								dn->ofs_in_node;
 
-	if (f2fs_update_extent_tree_range(dn->inode, fofs, dn->data_blkaddr, 1))
+	if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1))
 		sync_inode_page(dn);
 }
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ff79054c6cf6..bbe2cd1265d0 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -22,10 +22,11 @@
 #include <linux/vmalloc.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/fscrypto.h>
+#include <crypto/hash.h>
 
 #ifdef CONFIG_F2FS_CHECK_FS
 #define f2fs_bug_on(sbi, condition)	BUG_ON(condition)
-#define f2fs_down_write(x, y)	down_write_nest_lock(x, y)
 #else
 #define f2fs_bug_on(sbi, condition)					\
 	do {								\
@@ -34,7 +35,6 @@
 			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
 		}							\
 	} while (0)
-#define f2fs_down_write(x, y)	down_write(x)
 #endif
 
 /*
@@ -84,27 +84,6 @@ struct f2fs_mount_info {
 #define F2FS_CLEAR_FEATURE(sb, mask)					\
 	F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask)
 
-#define CRCPOLY_LE 0xedb88320
-
-static inline __u32 f2fs_crc32(void *buf, size_t len)
-{
-	unsigned char *p = (unsigned char *)buf;
-	__u32 crc = F2FS_SUPER_MAGIC;
-	int i;
-
-	while (len--) {
-		crc ^= *p++;
-		for (i = 0; i < 8; i++)
-			crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
-	}
-	return crc;
-}
-
-static inline bool f2fs_crc_valid(__u32 blk_crc, void *buf, size_t buf_size)
-{
-	return f2fs_crc32(buf, buf_size) == blk_crc;
-}
-
 /*
  * For checkpoint manager
  */
@@ -183,37 +162,37 @@ struct fsync_inode_entry {
 	block_t last_inode;	/* block address locating the last inode */
 };
 
-#define nats_in_cursum(sum)		(le16_to_cpu(sum->n_nats))
-#define sits_in_cursum(sum)		(le16_to_cpu(sum->n_sits))
+#define nats_in_cursum(jnl)		(le16_to_cpu(jnl->n_nats))
+#define sits_in_cursum(jnl)		(le16_to_cpu(jnl->n_sits))
 
-#define nat_in_journal(sum, i)		(sum->nat_j.entries[i].ne)
-#define nid_in_journal(sum, i)		(sum->nat_j.entries[i].nid)
-#define sit_in_journal(sum, i)		(sum->sit_j.entries[i].se)
-#define segno_in_journal(sum, i)	(sum->sit_j.entries[i].segno)
+#define nat_in_journal(jnl, i)		(jnl->nat_j.entries[i].ne)
+#define nid_in_journal(jnl, i)		(jnl->nat_j.entries[i].nid)
+#define sit_in_journal(jnl, i)		(jnl->sit_j.entries[i].se)
+#define segno_in_journal(jnl, i)	(jnl->sit_j.entries[i].segno)
 
-#define MAX_NAT_JENTRIES(sum)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(sum))
-#define MAX_SIT_JENTRIES(sum)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(sum))
+#define MAX_NAT_JENTRIES(jnl)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
+#define MAX_SIT_JENTRIES(jnl)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))
 
-static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i)
+static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
 {
-	int before = nats_in_cursum(rs);
-	rs->n_nats = cpu_to_le16(before + i);
+	int before = nats_in_cursum(journal);
+	journal->n_nats = cpu_to_le16(before + i);
 	return before;
 }
 
-static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
+static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
 {
-	int before = sits_in_cursum(rs);
-	rs->n_sits = cpu_to_le16(before + i);
+	int before = sits_in_cursum(journal);
+	journal->n_sits = cpu_to_le16(before + i);
 	return before;
 }
 
-static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
-								int type)
+static inline bool __has_cursum_space(struct f2fs_journal *journal,
+							int size, int type)
 {
 	if (type == NAT_JOURNAL)
-		return size <= MAX_NAT_JENTRIES(sum);
-	return size <= MAX_SIT_JENTRIES(sum);
+		return size <= MAX_NAT_JENTRIES(journal);
+	return size <= MAX_SIT_JENTRIES(journal);
 }
 
 /*
@@ -233,12 +212,9 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
 #define F2FS_IOC_WRITE_CHECKPOINT	_IO(F2FS_IOCTL_MAGIC, 7)
 #define F2FS_IOC_DEFRAGMENT		_IO(F2FS_IOCTL_MAGIC, 8)
 
-#define F2FS_IOC_SET_ENCRYPTION_POLICY					\
-		_IOR('f', 19, struct f2fs_encryption_policy)
-#define F2FS_IOC_GET_ENCRYPTION_PWSALT					\
-		_IOW('f', 20, __u8[16])
-#define F2FS_IOC_GET_ENCRYPTION_POLICY					\
-		_IOW('f', 21, struct f2fs_encryption_policy)
+#define F2FS_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
+#define F2FS_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
+#define F2FS_IOC_GET_ENCRYPTION_PWSALT	FS_IOC_GET_ENCRYPTION_PWSALT
 
 /*
  * should be same as XFS_IOC_GOINGDOWN.
@@ -268,25 +244,6 @@ struct f2fs_defragment {
  * For INODE and NODE manager
  */
 /* for directory operations */
-struct f2fs_str {
-	unsigned char *name;
-	u32 len;
-};
-
-struct f2fs_filename {
-	const struct qstr *usr_fname;
-	struct f2fs_str disk_name;
-	f2fs_hash_t hash;
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	struct f2fs_str crypto_buf;
-#endif
-};
-
-#define FSTR_INIT(n, l)		{ .name = n, .len = l }
-#define FSTR_TO_QSTR(f)		QSTR_INIT((f)->name, (f)->len)
-#define fname_name(p)		((p)->disk_name.name)
-#define fname_len(p)		((p)->disk_name.len)
-
 struct f2fs_dentry_ptr {
 	struct inode *inode;
 	const void *bitmap;
@@ -354,6 +311,7 @@ struct extent_node {
 	struct rb_node rb_node;		/* rb node located in rb-tree */
 	struct list_head list;		/* node in global extent list of sbi */
 	struct extent_info ei;		/* extent info */
+	struct extent_tree *et;		/* extent tree pointer */
 };
 
 struct extent_tree {
@@ -382,6 +340,7 @@ struct f2fs_map_blocks {
 	block_t m_lblk;
 	unsigned int m_len;
 	unsigned int m_flags;
+	pgoff_t *m_next_pgofs;		/* point next possible non-hole pgofs */
 };
 
 /* for flag in get_data_block */
@@ -389,6 +348,8 @@ struct f2fs_map_blocks {
 #define F2FS_GET_BLOCK_DIO		1
 #define F2FS_GET_BLOCK_FIEMAP		2
 #define F2FS_GET_BLOCK_BMAP		3
+#define F2FS_GET_BLOCK_PRE_DIO		4
+#define F2FS_GET_BLOCK_PRE_AIO		5
 
 /*
  * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
@@ -410,15 +371,6 @@ struct f2fs_map_blocks {
 #define file_enc_name(inode)	is_file(inode, FADVISE_ENC_NAME_BIT)
 #define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
 
-/* Encryption algorithms */
-#define F2FS_ENCRYPTION_MODE_INVALID		0
-#define F2FS_ENCRYPTION_MODE_AES_256_XTS	1
-#define F2FS_ENCRYPTION_MODE_AES_256_GCM	2
-#define F2FS_ENCRYPTION_MODE_AES_256_CBC	3
-#define F2FS_ENCRYPTION_MODE_AES_256_CTS	4
-
-#include "f2fs_crypto.h"
-
 #define DEF_DIR_LEVEL		0
 
 struct f2fs_inode_info {
@@ -442,13 +394,7 @@ struct f2fs_inode_info {
 	struct list_head dirty_list;	/* linked in global dirty list */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
 	struct mutex inmem_lock;	/* lock for inmemory pages */
-
 	struct extent_tree *extent_tree;	/* cached extent_tree entry */
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	/* Encryption params */
-	struct f2fs_crypt_info *i_crypt_info;
-#endif
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -515,6 +461,7 @@ struct f2fs_nm_info {
 	nid_t next_scan_nid;		/* the next nid to be scanned */
 	unsigned int ram_thresh;	/* control the memory footprint */
 	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */
+	unsigned int dirty_nats_ratio;	/* control dirty nats ratio threshold */
 
 	/* NAT cache management */
 	struct radix_tree_root nat_root;/* root of the nat entry cache */
@@ -549,6 +496,8 @@ struct dnode_of_data {
 	unsigned int ofs_in_node;	/* data offset in the node page */
 	bool inode_page_locked;		/* inode page is locked or not */
 	bool node_changed;		/* is node block changed */
+	char cur_level;			/* level of hole node page */
+	char max_level;			/* level of current page located */
 	block_t	data_blkaddr;		/* block address of the node block */
 };
 
@@ -679,6 +628,7 @@ enum page_type {
 	META_FLUSH,
 	INMEM,		/* the below types are used by tracepoints only. */
 	INMEM_DROP,
+	INMEM_REVOKE,
 	IPU,
 	OPU,
 };
@@ -687,7 +637,8 @@ struct f2fs_io_info {
 	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
 	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 */
+	block_t new_blkaddr;	/* new block address to be written */
+	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */
 	struct page *encrypted_page;	/* encrypted page */
 };
@@ -844,8 +795,22 @@ struct f2fs_sb_info {
 	struct list_head s_list;
 	struct mutex umount_mutex;
 	unsigned int shrinker_run_no;
+
+	/* For write statistics */
+	u64 sectors_written_start;
+	u64 kbytes_written;
+
+	/* Reference to checksum algorithm driver via cryptoapi */
+	struct crypto_shash *s_chksum_driver;
 };
 
+/* For write statistics. Suppose sector size is 512 bytes,
+ * and the return value is in kbytes. s is of struct f2fs_sb_info.
+ */
+#define BD_PART_WRITTEN(s)						 \
+(((u64)part_stat_read(s->sb->s_bdev->bd_part, sectors[1]) -		 \
+		s->sectors_written_start) >> 1)
+
 static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
 {
 	sbi->last_time[type] = jiffies;
@@ -874,6 +839,29 @@ static inline bool is_idle(struct f2fs_sb_info *sbi)
 /*
  * Inline functions
  */
+static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
+			   unsigned int length)
+{
+	SHASH_DESC_ON_STACK(shash, sbi->s_chksum_driver);
+	u32 *ctx = (u32 *)shash_desc_ctx(shash);
+	int err;
+
+	shash->tfm = sbi->s_chksum_driver;
+	shash->flags = 0;
+	*ctx = F2FS_SUPER_MAGIC;
+
+	err = crypto_shash_update(shash, address, length);
+	BUG_ON(err);
+
+	return *ctx;
+}
+
+static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
+				  void *buf, size_t buf_size)
+{
+	return f2fs_crc32(sbi, buf, buf_size) == blk_crc;
+}
+
 static inline struct f2fs_inode_info *F2FS_I(struct inode *inode)
 {
 	return container_of(inode, struct f2fs_inode_info, vfs_inode);
@@ -1006,7 +994,7 @@ static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 
 static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
 {
-	f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex);
+	down_write(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
@@ -1525,9 +1513,9 @@ static inline int f2fs_has_inline_xattr(struct inode *inode)
 	return is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR);
 }
 
-static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi)
+static inline unsigned int addrs_per_inode(struct inode *inode)
 {
-	if (f2fs_has_inline_xattr(&fi->vfs_inode))
+	if (f2fs_has_inline_xattr(inode))
 		return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS;
 	return DEF_ADDRS_PER_INODE;
 }
@@ -1681,10 +1669,10 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
 
 /* get offset of first page in next direct node */
-#define PGOFS_OF_NEXT_DNODE(pgofs, fi)				\
-	((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) :	\
-	(pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) /	\
-	ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
+#define PGOFS_OF_NEXT_DNODE(pgofs, inode)				\
+	((pgofs < ADDRS_PER_INODE(inode)) ? ADDRS_PER_INODE(inode) :	\
+	(pgofs - ADDRS_PER_INODE(inode) + ADDRS_PER_BLOCK) /	\
+	ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode))
 
 /*
  * file.c
@@ -1723,10 +1711,10 @@ struct dentry *f2fs_get_parent(struct dentry *child);
 extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
 void set_de_type(struct f2fs_dir_entry *, umode_t);
 
-struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *,
+struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *,
 			f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
 bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
-			unsigned int, struct f2fs_str *);
+			unsigned int, struct fscrypt_str *);
 void do_make_empty_dir(struct inode *, struct inode *,
 			struct f2fs_dentry_ptr *);
 struct page *init_inode_metadata(struct inode *, struct inode *,
@@ -1763,6 +1751,7 @@ int f2fs_commit_super(struct f2fs_sb_info *, bool);
 int f2fs_sync_fs(struct super_block *, int);
 extern __printf(3, 4)
 void f2fs_msg(struct super_block *, const char *, const char *, ...);
+int sanity_check_ckpt(struct f2fs_sb_info *sbi);
 
 /*
  * hash.c
@@ -1780,6 +1769,7 @@ int need_dentry_mark(struct f2fs_sb_info *, nid_t);
 bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
 bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
 void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
+pgoff_t get_next_page_offset(struct dnode_of_data *, pgoff_t);
 int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
 int truncate_inode_blocks(struct inode *, pgoff_t);
 int truncate_xattr_node(struct inode *, struct page *);
@@ -1811,7 +1801,8 @@ void destroy_node_manager_caches(void);
  * segment.c
  */
 void register_inmem_page(struct inode *, struct page *);
-int commit_inmem_pages(struct inode *, bool);
+void drop_inmem_pages(struct inode *);
+int commit_inmem_pages(struct inode *);
 void f2fs_balance_fs(struct f2fs_sb_info *, bool);
 void f2fs_balance_fs_bg(struct f2fs_sb_info *);
 int f2fs_issue_flush(struct f2fs_sb_info *);
@@ -1832,16 +1823,17 @@ void write_meta_page(struct f2fs_sb_info *, struct page *);
 void write_node_page(unsigned int, struct f2fs_io_info *);
 void write_data_page(struct dnode_of_data *, struct f2fs_io_info *);
 void rewrite_data_page(struct f2fs_io_info *);
+void __f2fs_replace_block(struct f2fs_sb_info *, struct f2fs_summary *,
+					block_t, block_t, bool, bool);
 void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *,
-				block_t, block_t, unsigned char, bool);
+				block_t, block_t, unsigned char, bool, bool);
 void allocate_data_block(struct f2fs_sb_info *, struct page *,
 		block_t, block_t *, struct f2fs_summary *, int);
-void f2fs_wait_on_page_writeback(struct page *, enum page_type);
+void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool);
 void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t);
 void write_data_summaries(struct f2fs_sb_info *, block_t);
 void write_node_summaries(struct f2fs_sb_info *, block_t);
-int lookup_journal_in_cursum(struct f2fs_summary_block *,
-					int, unsigned int, int);
+int lookup_journal_in_cursum(struct f2fs_journal *, int, unsigned int, int);
 void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
 int build_segment_manager(struct f2fs_sb_info *);
 void destroy_segment_manager(struct f2fs_sb_info *);
@@ -1881,11 +1873,16 @@ void destroy_checkpoint_caches(void);
  * data.c
  */
 void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *, struct inode *,
+				struct page *, nid_t, enum page_type, int);
+void f2fs_flush_merged_bios(struct f2fs_sb_info *);
 int f2fs_submit_page_bio(struct f2fs_io_info *);
 void f2fs_submit_page_mbio(struct f2fs_io_info *);
 void set_data_blkaddr(struct dnode_of_data *);
+void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_get_block(struct dnode_of_data *, pgoff_t);
+ssize_t f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
 struct page *get_read_data_page(struct inode *, pgoff_t, int, bool);
 struct page *find_data_page(struct inode *, pgoff_t);
@@ -1902,7 +1899,7 @@ int f2fs_release_page(struct page *, gfp_t);
  */
 int start_gc_thread(struct f2fs_sb_info *);
 void stop_gc_thread(struct f2fs_sb_info *);
-block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
+block_t start_bidx_of_node(unsigned int, struct inode *);
 int f2fs_gc(struct f2fs_sb_info *, bool);
 void build_gc_manager(struct f2fs_sb_info *);
 
@@ -2093,7 +2090,7 @@ int f2fs_convert_inline_inode(struct inode *);
 int f2fs_write_inline_data(struct inode *, struct page *);
 bool recover_inline_data(struct inode *, struct page *);
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *,
-				struct f2fs_filename *, struct page **);
+				struct fscrypt_name *, struct page **);
 struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **);
 int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *);
 int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *,
@@ -2102,7 +2099,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *,
 						struct inode *, struct inode *);
 bool f2fs_empty_inline_dir(struct inode *);
 int f2fs_read_inline_dir(struct file *, struct dir_context *,
-						struct f2fs_str *);
+						struct fscrypt_str *);
 int f2fs_inline_data_fiemap(struct inode *,
 		struct fiemap_extent_info *, __u64, __u64);
 
@@ -2132,13 +2129,9 @@ void destroy_extent_cache(void);
 /*
  * crypto support
  */
-static inline int f2fs_encrypted_inode(struct inode *inode)
+static inline bool f2fs_encrypted_inode(struct inode *inode)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
 	return file_is_encrypt(inode);
-#else
-	return 0;
-#endif
 }
 
 static inline void f2fs_set_encrypted_inode(struct inode *inode)
@@ -2150,20 +2143,12 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode)
 
 static inline bool f2fs_bio_encrypted(struct bio *bio)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	return unlikely(bio->bi_private != NULL);
-#else
-	return false;
-#endif
+	return bio->bi_private != NULL;
 }
 
 static inline int f2fs_sb_has_crypto(struct super_block *sb)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
 	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
-#else
-	return 0;
-#endif
 }
 
 static inline bool f2fs_may_encrypt(struct inode *inode)
@@ -2177,86 +2162,28 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
 #endif
 }
 
-/* crypto_policy.c */
-int f2fs_is_child_context_consistent_with_parent(struct inode *,
-							struct inode *);
-int f2fs_inherit_context(struct inode *, struct inode *, struct page *);
-int f2fs_process_policy(const struct f2fs_encryption_policy *, struct inode *);
-int f2fs_get_policy(struct inode *, struct f2fs_encryption_policy *);
-
-/* crypt.c */
-extern struct kmem_cache *f2fs_crypt_info_cachep;
-bool f2fs_valid_contents_enc_mode(uint32_t);
-uint32_t f2fs_validate_encryption_key_size(uint32_t, uint32_t);
-struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *);
-void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *);
-struct page *f2fs_encrypt(struct inode *, struct page *);
-int f2fs_decrypt(struct f2fs_crypto_ctx *, struct page *);
-int f2fs_decrypt_one(struct inode *, struct page *);
-void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *, struct bio *);
-
-/* crypto_key.c */
-void f2fs_free_encryption_info(struct inode *, struct f2fs_crypt_info *);
-int _f2fs_get_encryption_info(struct inode *inode);
-
-/* crypto_fname.c */
-bool f2fs_valid_filenames_enc_mode(uint32_t);
-u32 f2fs_fname_crypto_round_up(u32, u32);
-int f2fs_fname_crypto_alloc_buffer(struct inode *, u32, struct f2fs_str *);
-int f2fs_fname_disk_to_usr(struct inode *, f2fs_hash_t *,
-			const struct f2fs_str *, struct f2fs_str *);
-int f2fs_fname_usr_to_disk(struct inode *, const struct qstr *,
-			struct f2fs_str *);
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-void f2fs_restore_and_release_control_page(struct page **);
-void f2fs_restore_control_page(struct page *);
-
-int __init f2fs_init_crypto(void);
-int f2fs_crypto_initialize(void);
-void f2fs_exit_crypto(void);
-
-int f2fs_has_encryption_key(struct inode *);
-
-static inline int f2fs_get_encryption_info(struct inode *inode)
-{
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (!ci ||
-		(ci->ci_keyring_key &&
-		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					       (1 << KEY_FLAG_REVOKED) |
-					       (1 << KEY_FLAG_DEAD)))))
-		return _f2fs_get_encryption_info(inode);
-	return 0;
-}
-
-void f2fs_fname_crypto_free_buffer(struct f2fs_str *);
-int f2fs_fname_setup_filename(struct inode *, const struct qstr *,
-				int lookup, struct f2fs_filename *);
-void f2fs_fname_free_filename(struct f2fs_filename *);
-#else
-static inline void f2fs_restore_and_release_control_page(struct page **p) { }
-static inline void f2fs_restore_control_page(struct page *p) { }
-
-static inline int __init f2fs_init_crypto(void) { return 0; }
-static inline void f2fs_exit_crypto(void) { }
-
-static inline int f2fs_has_encryption_key(struct inode *i) { return 0; }
-static inline int f2fs_get_encryption_info(struct inode *i) { return 0; }
-static inline void f2fs_fname_crypto_free_buffer(struct f2fs_str *p) { }
-
-static inline int f2fs_fname_setup_filename(struct inode *dir,
-					const struct qstr *iname,
-					int lookup, struct f2fs_filename *fname)
-{
-	memset(fname, 0, sizeof(struct f2fs_filename));
-	fname->usr_fname = iname;
-	fname->disk_name.name = (unsigned char *)iname->name;
-	fname->disk_name.len = iname->len;
-	return 0;
-}
-
-static inline void f2fs_fname_free_filename(struct f2fs_filename *fname) { }
+#ifndef CONFIG_F2FS_FS_ENCRYPTION
+#define fscrypt_set_d_op(i)
+#define fscrypt_get_ctx			fscrypt_notsupp_get_ctx
+#define fscrypt_release_ctx		fscrypt_notsupp_release_ctx
+#define fscrypt_encrypt_page		fscrypt_notsupp_encrypt_page
+#define fscrypt_decrypt_page		fscrypt_notsupp_decrypt_page
+#define fscrypt_decrypt_bio_pages	fscrypt_notsupp_decrypt_bio_pages
+#define fscrypt_pullback_bio_page	fscrypt_notsupp_pullback_bio_page
+#define fscrypt_restore_control_page	fscrypt_notsupp_restore_control_page
+#define fscrypt_zeroout_range		fscrypt_notsupp_zeroout_range
+#define fscrypt_process_policy		fscrypt_notsupp_process_policy
+#define fscrypt_get_policy		fscrypt_notsupp_get_policy
+#define fscrypt_has_permitted_context	fscrypt_notsupp_has_permitted_context
+#define fscrypt_inherit_context		fscrypt_notsupp_inherit_context
+#define fscrypt_get_encryption_info	fscrypt_notsupp_get_encryption_info
+#define fscrypt_put_encryption_info	fscrypt_notsupp_put_encryption_info
+#define fscrypt_setup_filename		fscrypt_notsupp_setup_filename
+#define fscrypt_free_filename		fscrypt_notsupp_free_filename
+#define fscrypt_fname_encrypted_size	fscrypt_notsupp_fname_encrypted_size
+#define fscrypt_fname_alloc_buffer	fscrypt_notsupp_fname_alloc_buffer
+#define fscrypt_fname_free_buffer	fscrypt_notsupp_fname_free_buffer
+#define fscrypt_fname_disk_to_usr	fscrypt_notsupp_fname_disk_to_usr
+#define fscrypt_fname_usr_to_disk	fscrypt_notsupp_fname_usr_to_disk
 #endif
 #endif
diff --git a/fs/f2fs/f2fs_crypto.h b/fs/f2fs/f2fs_crypto.h
deleted file mode 100644
index c2c1c2b63b25..000000000000
--- a/fs/f2fs/f2fs_crypto.h
+++ /dev/null
@@ -1,151 +0,0 @@
-/*
- * linux/fs/f2fs/f2fs_crypto.h
- *
- * Copied from linux/fs/ext4/ext4_crypto.h
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains encryption header content for f2fs
- *
- * Written by Michael Halcrow, 2015.
- * Modified by Jaegeuk Kim, 2015.
- */
-#ifndef _F2FS_CRYPTO_H
-#define _F2FS_CRYPTO_H
-
-#include <linux/fs.h>
-
-#define F2FS_KEY_DESCRIPTOR_SIZE	8
-
-/* Policy provided via an ioctl on the topmost directory */
-struct f2fs_encryption_policy {
-	char version;
-	char contents_encryption_mode;
-	char filenames_encryption_mode;
-	char flags;
-	char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE];
-} __attribute__((__packed__));
-
-#define F2FS_ENCRYPTION_CONTEXT_FORMAT_V1	1
-#define F2FS_KEY_DERIVATION_NONCE_SIZE		16
-
-#define F2FS_POLICY_FLAGS_PAD_4		0x00
-#define F2FS_POLICY_FLAGS_PAD_8		0x01
-#define F2FS_POLICY_FLAGS_PAD_16	0x02
-#define F2FS_POLICY_FLAGS_PAD_32	0x03
-#define F2FS_POLICY_FLAGS_PAD_MASK	0x03
-#define F2FS_POLICY_FLAGS_VALID		0x03
-
-/**
- * Encryption context for inode
- *
- * Protector format:
- *  1 byte: Protector format (1 = this version)
- *  1 byte: File contents encryption mode
- *  1 byte: File names encryption mode
- *  1 byte: Flags
- *  8 bytes: Master Key descriptor
- *  16 bytes: Encryption Key derivation nonce
- */
-struct f2fs_encryption_context {
-	char format;
-	char contents_encryption_mode;
-	char filenames_encryption_mode;
-	char flags;
-	char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE];
-	char nonce[F2FS_KEY_DERIVATION_NONCE_SIZE];
-} __attribute__((__packed__));
-
-/* Encryption parameters */
-#define F2FS_XTS_TWEAK_SIZE 16
-#define F2FS_AES_128_ECB_KEY_SIZE 16
-#define F2FS_AES_256_GCM_KEY_SIZE 32
-#define F2FS_AES_256_CBC_KEY_SIZE 32
-#define F2FS_AES_256_CTS_KEY_SIZE 32
-#define F2FS_AES_256_XTS_KEY_SIZE 64
-#define F2FS_MAX_KEY_SIZE 64
-
-#define F2FS_KEY_DESC_PREFIX "f2fs:"
-#define F2FS_KEY_DESC_PREFIX_SIZE 5
-
-struct f2fs_encryption_key {
-	__u32 mode;
-	char raw[F2FS_MAX_KEY_SIZE];
-	__u32 size;
-} __attribute__((__packed__));
-
-struct f2fs_crypt_info {
-	char		ci_data_mode;
-	char		ci_filename_mode;
-	char		ci_flags;
-	struct crypto_ablkcipher *ci_ctfm;
-	struct key	*ci_keyring_key;
-	char		ci_master_key[F2FS_KEY_DESCRIPTOR_SIZE];
-};
-
-#define F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL             0x00000001
-#define F2FS_WRITE_PATH_FL			      0x00000002
-
-struct f2fs_crypto_ctx {
-	union {
-		struct {
-			struct page *bounce_page;       /* Ciphertext page */
-			struct page *control_page;      /* Original page  */
-		} w;
-		struct {
-			struct bio *bio;
-			struct work_struct work;
-		} r;
-		struct list_head free_list;     /* Free list */
-	};
-	char flags;                      /* Flags */
-};
-
-struct f2fs_completion_result {
-	struct completion completion;
-	int res;
-};
-
-#define DECLARE_F2FS_COMPLETION_RESULT(ecr) \
-	struct f2fs_completion_result ecr = { \
-		COMPLETION_INITIALIZER((ecr).completion), 0 }
-
-static inline int f2fs_encryption_key_size(int mode)
-{
-	switch (mode) {
-	case F2FS_ENCRYPTION_MODE_AES_256_XTS:
-		return F2FS_AES_256_XTS_KEY_SIZE;
-	case F2FS_ENCRYPTION_MODE_AES_256_GCM:
-		return F2FS_AES_256_GCM_KEY_SIZE;
-	case F2FS_ENCRYPTION_MODE_AES_256_CBC:
-		return F2FS_AES_256_CBC_KEY_SIZE;
-	case F2FS_ENCRYPTION_MODE_AES_256_CTS:
-		return F2FS_AES_256_CTS_KEY_SIZE;
-	default:
-		BUG();
-	}
-	return 0;
-}
-
-#define F2FS_FNAME_NUM_SCATTER_ENTRIES	4
-#define F2FS_CRYPTO_BLOCK_SIZE		16
-#define F2FS_FNAME_CRYPTO_DIGEST_SIZE	32
-
-/**
- * For encrypted symlinks, the ciphertext length is stored at the beginning
- * of the string in little-endian format.
- */
-struct f2fs_encrypted_symlink_data {
-	__le16 len;
-	char encrypted_path[1];
-} __attribute__((__packed__));
-
-/**
- * This function is used to calculate the disk space required to
- * store a filename of length l in encrypted symlink format.
- */
-static inline u32 encrypted_symlink_data_len(u32 l)
-{
-	return (l + sizeof(struct f2fs_encrypted_symlink_data) - 1);
-}
-#endif	/* _F2FS_CRYPTO_H */
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index ea272be62677..b41c3579ea9e 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -86,7 +86,7 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	trace_f2fs_vm_page_mkwrite(page, DATA);
 mapped:
 	/* fill the page */
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, false);
 
 	/* wait for GCed encrypted page writeback */
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
@@ -301,7 +301,7 @@ static pgoff_t __get_first_dirty_index(struct address_space *mapping,
 	pagevec_init(&pvec, 0);
 	nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
 					PAGECACHE_TAG_DIRTY, 1);
-	pgofs = nr_pages ? pvec.pages[0]->index : LONG_MAX;
+	pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX;
 	pagevec_release(&pvec);
 	return pgofs;
 }
@@ -358,15 +358,14 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 		} else if (err == -ENOENT) {
 			/* direct node does not exists */
 			if (whence == SEEK_DATA) {
-				pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
-							F2FS_I(inode));
+				pgofs = get_next_page_offset(&dn, pgofs);
 				continue;
 			} else {
 				goto found;
 			}
 		}
 
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 
 		/* find data/hole in dnode block */
 		for (; dn.ofs_in_node < end_offset;
@@ -422,9 +421,11 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	int err;
 
 	if (f2fs_encrypted_inode(inode)) {
-		err = f2fs_get_encryption_info(inode);
+		err = fscrypt_get_encryption_info(inode);
 		if (err)
 			return 0;
+		if (!f2fs_encrypted_inode(inode))
+			return -ENOKEY;
 	}
 
 	/* we don't need to use inline_data strictly */
@@ -440,12 +441,18 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 static int f2fs_file_open(struct inode *inode, struct file *filp)
 {
 	int ret = generic_file_open(inode, filp);
+	struct inode *dir = filp->f_path.dentry->d_parent->d_inode;
 
 	if (!ret && f2fs_encrypted_inode(inode)) {
-		ret = f2fs_get_encryption_info(inode);
+		ret = fscrypt_get_encryption_info(inode);
 		if (ret)
-			ret = -EACCES;
+			return -EACCES;
+		if (!fscrypt_has_encryption_key(inode))
+			return -ENOKEY;
 	}
+	if (f2fs_encrypted_inode(dir) &&
+			!fscrypt_has_permitted_context(dir, inode))
+		return -EPERM;
 	return ret;
 }
 
@@ -480,7 +487,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		 * we will invalidate all blkaddr in the whole range.
 		 */
 		fofs = start_bidx_of_node(ofs_of_node(dn->node_page),
-						F2FS_I(dn->inode)) + ofs;
+							dn->inode) + ofs;
 		f2fs_update_extent_cache_range(dn, fofs, 0, len);
 		dec_valid_block_count(sbi, dn->inode, nr_free);
 		sync_inode_page(dn);
@@ -521,9 +528,10 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
 	if (IS_ERR(page))
 		return 0;
 truncate_out:
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
-	if (!cache_only || !f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode))
+	if (!cache_only || !f2fs_encrypted_inode(inode) ||
+					!S_ISREG(inode->i_mode))
 		set_page_dirty(page);
 	f2fs_put_page(page, 1);
 	return 0;
@@ -568,7 +576,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 		goto out;
 	}
 
-	count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+	count = ADDRS_PER_PAGE(dn.node_page, inode);
 
 	count -= dn.ofs_in_node;
 	f2fs_bug_on(sbi, count < 0);
@@ -671,7 +679,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if (attr->ia_valid & ATTR_SIZE) {
 		if (f2fs_encrypted_inode(inode) &&
-				f2fs_get_encryption_info(inode))
+				fscrypt_get_encryption_info(inode))
 			return -EACCES;
 
 		if (attr->ia_size <= i_size_read(inode)) {
@@ -743,7 +751,7 @@ static int fill_zero(struct inode *inode, pgoff_t index,
 	if (IS_ERR(page))
 		return PTR_ERR(page);
 
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 	zero_user(page, start, len);
 	set_page_dirty(page);
 	f2fs_put_page(page, 1);
@@ -768,7 +776,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 			return err;
 		}
 
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 		count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
 
 		f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
@@ -854,10 +862,8 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 	} else {
 		new_addr = dn.data_blkaddr;
 		if (!is_checkpointed_data(sbi, new_addr)) {
-			dn.data_blkaddr = NULL_ADDR;
 			/* do not invalidate this block address */
-			set_data_blkaddr(&dn);
-			f2fs_update_extent_cache(&dn);
+			f2fs_update_data_blkaddr(&dn, NULL_ADDR);
 			do_replace = true;
 		}
 		f2fs_put_dnode(&dn);
@@ -884,7 +890,7 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 
 		get_node_info(sbi, dn.nid, &ni);
 		f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr,
-				ni.version, true);
+				ni.version, true, false);
 		f2fs_put_dnode(&dn);
 	} else {
 		struct page *psrc, *pdst;
@@ -892,7 +898,7 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 		psrc = get_lock_data_page(inode, src, true);
 		if (IS_ERR(psrc))
 			return PTR_ERR(psrc);
-		pdst = get_new_data_page(inode, NULL, dst, false);
+		pdst = get_new_data_page(inode, NULL, dst, true);
 		if (IS_ERR(pdst)) {
 			f2fs_put_page(psrc, 1);
 			return PTR_ERR(pdst);
@@ -908,9 +914,7 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 
 err_out:
 	if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) {
-		dn.data_blkaddr = new_addr;
-		set_data_blkaddr(&dn);
-		f2fs_update_extent_cache(&dn);
+		f2fs_update_data_blkaddr(&dn, new_addr);
 		f2fs_put_dnode(&dn);
 	}
 	return ret;
@@ -1050,12 +1054,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 
 			if (dn.data_blkaddr != NEW_ADDR) {
 				invalidate_blocks(sbi, dn.data_blkaddr);
-
-				dn.data_blkaddr = NEW_ADDR;
-				set_data_blkaddr(&dn);
-
-				dn.data_blkaddr = NULL_ADDR;
-				f2fs_update_extent_cache(&dn);
+				f2fs_update_data_blkaddr(&dn, NEW_ADDR);
 			}
 			f2fs_put_dnode(&dn);
 			f2fs_unlock_op(sbi);
@@ -1253,7 +1252,7 @@ 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);
+		drop_inmem_pages(inode);
 	if (f2fs_is_volatile_file(inode)) {
 		set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
 		filemap_fdatawrite(inode->i_mapping);
@@ -1377,7 +1376,7 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 
 	if (f2fs_is_atomic_file(inode)) {
 		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
-		ret = commit_inmem_pages(inode, false);
+		ret = commit_inmem_pages(inode);
 		if (ret) {
 			set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 			goto err_out;
@@ -1440,7 +1439,7 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
 
 	if (f2fs_is_atomic_file(inode)) {
 		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
-		commit_inmem_pages(inode, true);
+		drop_inmem_pages(inode);
 	}
 	if (f2fs_is_volatile_file(inode)) {
 		clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
@@ -1535,39 +1534,30 @@ static bool uuid_is_nonzero(__u8 u[16])
 
 static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	struct f2fs_encryption_policy policy;
+	struct fscrypt_policy policy;
 	struct inode *inode = file_inode(filp);
 
-	if (copy_from_user(&policy, (struct f2fs_encryption_policy __user *)arg,
-				sizeof(policy)))
+	if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
+							sizeof(policy)))
 		return -EFAULT;
 
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
-	return f2fs_process_policy(&policy, inode);
-#else
-	return -EOPNOTSUPP;
-#endif
+	return fscrypt_process_policy(inode, &policy);
 }
 
 static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	struct f2fs_encryption_policy policy;
+	struct fscrypt_policy policy;
 	struct inode *inode = file_inode(filp);
 	int err;
 
-	err = f2fs_get_policy(inode, &policy);
+	err = fscrypt_get_policy(inode, &policy);
 	if (err)
 		return err;
 
-	if (copy_to_user((struct f2fs_encryption_policy __user *)arg, &policy,
-							sizeof(policy)))
+	if (copy_to_user((struct fscrypt_policy __user *)arg, &policy, sizeof(policy)))
 		return -EFAULT;
 	return 0;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
 static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
@@ -1648,7 +1638,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
 					struct f2fs_defragment *range)
 {
 	struct inode *inode = file_inode(filp);
-	struct f2fs_map_blocks map;
+	struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
 	struct extent_info ei;
 	pgoff_t pg_start, pg_end;
 	unsigned int blk_per_seg = sbi->blocks_per_seg;
@@ -1874,14 +1864,32 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
-	struct inode *inode = file_inode(iocb->ki_filp);
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	ssize_t ret;
 
 	if (f2fs_encrypted_inode(inode) &&
-				!f2fs_has_encryption_key(inode) &&
-				f2fs_get_encryption_info(inode))
+				!fscrypt_has_encryption_key(inode) &&
+				fscrypt_get_encryption_info(inode))
 		return -EACCES;
 
-	return generic_file_write_iter(iocb, from);
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret > 0) {
+		ret = f2fs_preallocate_blocks(iocb, from);
+		if (!ret)
+			ret = __generic_file_write_iter(iocb, from);
+	}
+	inode_unlock(inode);
+
+	if (ret > 0) {
+		ssize_t err;
+
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+		if (err < 0)
+			ret = err;
+	}
+	return ret;
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index f610c2a9bdde..b0051a97824c 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -245,6 +245,18 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 		return get_cb_cost(sbi, segno);
 }
 
+static unsigned int count_bits(const unsigned long *addr,
+				unsigned int offset, unsigned int len)
+{
+	unsigned int end = offset + len, sum = 0;
+
+	while (offset < end) {
+		if (test_bit(offset++, addr))
+			++sum;
+	}
+	return sum;
+}
+
 /*
  * This function is called from two paths.
  * One is garbage collection and the other is SSR segment selection.
@@ -258,9 +270,9 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct victim_sel_policy p;
-	unsigned int secno, max_cost;
+	unsigned int secno, max_cost, last_victim;
 	unsigned int last_segment = MAIN_SEGS(sbi);
-	int nsearched = 0;
+	unsigned int nsearched = 0;
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -273,6 +285,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 	if (p.max_search == 0)
 		goto out;
 
+	last_victim = sbi->last_victim[p.gc_mode];
 	if (p.alloc_mode == LFS && gc_type == FG_GC) {
 		p.min_segno = check_bg_victims(sbi);
 		if (p.min_segno != NULL_SEGNO)
@@ -295,27 +308,35 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 		}
 
 		p.offset = segno + p.ofs_unit;
-		if (p.ofs_unit > 1)
+		if (p.ofs_unit > 1) {
 			p.offset -= segno % p.ofs_unit;
+			nsearched += count_bits(p.dirty_segmap,
+						p.offset - p.ofs_unit,
+						p.ofs_unit);
+		} else {
+			nsearched++;
+		}
+
 
 		secno = GET_SECNO(sbi, segno);
 
 		if (sec_usage_check(sbi, secno))
-			continue;
+			goto next;
 		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
-			continue;
+			goto next;
 
 		cost = get_gc_cost(sbi, segno, &p);
 
 		if (p.min_cost > cost) {
 			p.min_segno = segno;
 			p.min_cost = cost;
-		} else if (unlikely(cost == max_cost)) {
-			continue;
 		}
-
-		if (nsearched++ >= p.max_search) {
-			sbi->last_victim[p.gc_mode] = segno;
+next:
+		if (nsearched >= p.max_search) {
+			if (!sbi->last_victim[p.gc_mode] && segno <= last_victim)
+				sbi->last_victim[p.gc_mode] = last_victim + 1;
+			else
+				sbi->last_victim[p.gc_mode] = segno + 1;
 			break;
 		}
 	}
@@ -399,7 +420,7 @@ static int check_valid_map(struct f2fs_sb_info *sbi,
  * On validity, copy that node with cold status, otherwise (invalid node)
  * ignore that.
  */
-static int gc_node_segment(struct f2fs_sb_info *sbi,
+static void gc_node_segment(struct f2fs_sb_info *sbi,
 		struct f2fs_summary *sum, unsigned int segno, int gc_type)
 {
 	bool initial = true;
@@ -419,7 +440,7 @@ next_step:
 
 		/* stop BG_GC if there is not enough free sections. */
 		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
-			return 0;
+			return;
 
 		if (check_valid_map(sbi, segno, off) == 0)
 			continue;
@@ -446,7 +467,7 @@ next_step:
 
 		/* set page dirty and write it */
 		if (gc_type == FG_GC) {
-			f2fs_wait_on_page_writeback(node_page, NODE);
+			f2fs_wait_on_page_writeback(node_page, NODE, true);
 			set_page_dirty(node_page);
 		} else {
 			if (!PageWriteback(node_page))
@@ -460,20 +481,6 @@ next_step:
 		initial = false;
 		goto next_step;
 	}
-
-	if (gc_type == FG_GC) {
-		struct writeback_control wbc = {
-			.sync_mode = WB_SYNC_ALL,
-			.nr_to_write = LONG_MAX,
-			.for_reclaim = 0,
-		};
-		sync_node_pages(sbi, 0, &wbc);
-
-		/* return 1 only if FG_GC succefully reclaimed one */
-		if (get_valid_blocks(sbi, segno, 1) == 0)
-			return 1;
-	}
-	return 0;
 }
 
 /*
@@ -483,7 +490,7 @@ next_step:
  * as indirect or double indirect node blocks, are given, it must be a caller's
  * bug.
  */
-block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
+block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode)
 {
 	unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
 	unsigned int bidx;
@@ -500,7 +507,7 @@ block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
 		int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
 		bidx = node_ofs - 5 - dec;
 	}
-	return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi);
+	return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode);
 }
 
 static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
@@ -546,6 +553,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	struct f2fs_summary sum;
 	struct node_info ni;
 	struct page *page;
+	block_t newaddr;
 	int err;
 
 	/* do not read out */
@@ -567,21 +575,24 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	 * don't cache encrypted data into meta inode until previous dirty
 	 * data were writebacked to avoid racing between GC and flush.
 	 */
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 
 	get_node_info(fio.sbi, dn.nid, &ni);
 	set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
 
 	/* read page */
 	fio.page = page;
-	fio.blk_addr = dn.data_blkaddr;
+	fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
 
-	fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi),
-					fio.blk_addr,
-					FGP_LOCK|FGP_CREAT,
-					GFP_NOFS);
-	if (!fio.encrypted_page)
-		goto put_out;
+	allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
+							&sum, CURSEG_COLD_DATA);
+
+	fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr,
+					FGP_LOCK | FGP_CREAT, GFP_NOFS);
+	if (!fio.encrypted_page) {
+		err = -ENOMEM;
+		goto recover_block;
+	}
 
 	err = f2fs_submit_page_bio(&fio);
 	if (err)
@@ -590,33 +601,39 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	/* write page */
 	lock_page(fio.encrypted_page);
 
-	if (unlikely(!PageUptodate(fio.encrypted_page)))
+	if (unlikely(!PageUptodate(fio.encrypted_page))) {
+		err = -EIO;
 		goto put_page_out;
-	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi)))
+	}
+	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
+		err = -EIO;
 		goto put_page_out;
+	}
 
 	set_page_dirty(fio.encrypted_page);
-	f2fs_wait_on_page_writeback(fio.encrypted_page, DATA);
+	f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true);
 	if (clear_page_dirty_for_io(fio.encrypted_page))
 		dec_page_count(fio.sbi, F2FS_DIRTY_META);
 
 	set_page_writeback(fio.encrypted_page);
 
 	/* allocate block address */
-	f2fs_wait_on_page_writeback(dn.node_page, NODE);
-	allocate_data_block(fio.sbi, NULL, fio.blk_addr,
-					&fio.blk_addr, &sum, CURSEG_COLD_DATA);
+	f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
+
 	fio.rw = WRITE_SYNC;
+	fio.new_blkaddr = newaddr;
 	f2fs_submit_page_mbio(&fio);
 
-	dn.data_blkaddr = fio.blk_addr;
-	set_data_blkaddr(&dn);
-	f2fs_update_extent_cache(&dn);
+	f2fs_update_data_blkaddr(&dn, newaddr);
 	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 	if (page->index == 0)
 		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
 put_page_out:
 	f2fs_put_page(fio.encrypted_page, 1);
+recover_block:
+	if (err)
+		__f2fs_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr,
+								true, true);
 put_out:
 	f2fs_put_dnode(&dn);
 out:
@@ -645,7 +662,7 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
 			.encrypted_page = NULL,
 		};
 		set_page_dirty(page);
-		f2fs_wait_on_page_writeback(page, DATA);
+		f2fs_wait_on_page_writeback(page, DATA, true);
 		if (clear_page_dirty_for_io(page))
 			inode_dec_dirty_pages(inode);
 		set_cold_data(page);
@@ -663,7 +680,7 @@ out:
  * If the parent node is not valid or the data block address is different,
  * the victim data block is ignored.
  */
-static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		struct gc_inode_list *gc_list, unsigned int segno, int gc_type)
 {
 	struct super_block *sb = sbi->sb;
@@ -686,7 +703,7 @@ next_step:
 
 		/* stop BG_GC if there is not enough free sections. */
 		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
-			return 0;
+			return;
 
 		if (check_valid_map(sbi, segno, off) == 0)
 			continue;
@@ -719,7 +736,7 @@ next_step:
 				continue;
 			}
 
-			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
+			start_bidx = start_bidx_of_node(nofs, inode);
 			data_page = get_read_data_page(inode,
 					start_bidx + ofs_in_node, READA, true);
 			if (IS_ERR(data_page)) {
@@ -735,7 +752,7 @@ next_step:
 		/* phase 3 */
 		inode = find_gc_inode(gc_list, dni.ino);
 		if (inode) {
-			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode))
+			start_bidx = start_bidx_of_node(nofs, inode)
 								+ ofs_in_node;
 			if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 				move_encrypted_block(inode, start_bidx);
@@ -747,15 +764,6 @@ next_step:
 
 	if (++phase < 4)
 		goto next_step;
-
-	if (gc_type == FG_GC) {
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
-
-		/* return 1 only if FG_GC succefully reclaimed one */
-		if (get_valid_blocks(sbi, segno, 1) == 0)
-			return 1;
-	}
-	return 0;
 }
 
 static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
@@ -771,53 +779,92 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
 	return ret;
 }
 
-static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
+static int do_garbage_collect(struct f2fs_sb_info *sbi,
+				unsigned int start_segno,
 				struct gc_inode_list *gc_list, int gc_type)
 {
 	struct page *sum_page;
 	struct f2fs_summary_block *sum;
 	struct blk_plug plug;
-	int nfree = 0;
+	unsigned int segno = start_segno;
+	unsigned int end_segno = start_segno + sbi->segs_per_sec;
+	int seg_freed = 0;
+	unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
+						SUM_TYPE_DATA : SUM_TYPE_NODE;
 
-	/* read segment summary of victim */
-	sum_page = get_sum_page(sbi, segno);
+	/* readahead multi ssa blocks those have contiguous address */
+	if (sbi->segs_per_sec > 1)
+		ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno),
+					sbi->segs_per_sec, META_SSA, true);
+
+	/* reference all summary page */
+	while (segno < end_segno) {
+		sum_page = get_sum_page(sbi, segno++);
+		unlock_page(sum_page);
+	}
 
 	blk_start_plug(&plug);
 
-	sum = page_address(sum_page);
+	for (segno = start_segno; segno < end_segno; segno++) {
+		/* find segment summary of victim */
+		sum_page = find_get_page(META_MAPPING(sbi),
+					GET_SUM_BLOCK(sbi, segno));
+		f2fs_bug_on(sbi, !PageUptodate(sum_page));
+		f2fs_put_page(sum_page, 0);
 
-	/*
-	 * this is to avoid deadlock:
-	 * - lock_page(sum_page)         - f2fs_replace_block
-	 *  - check_valid_map()            - mutex_lock(sentry_lock)
-	 *   - mutex_lock(sentry_lock)     - change_curseg()
-	 *                                  - lock_page(sum_page)
-	 */
-	unlock_page(sum_page);
-
-	switch (GET_SUM_TYPE((&sum->footer))) {
-	case SUM_TYPE_NODE:
-		nfree = gc_node_segment(sbi, sum->entries, segno, gc_type);
-		break;
-	case SUM_TYPE_DATA:
-		nfree = gc_data_segment(sbi, sum->entries, gc_list,
-							segno, gc_type);
-		break;
+		sum = page_address(sum_page);
+		f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer)));
+
+		/*
+		 * this is to avoid deadlock:
+		 * - lock_page(sum_page)         - f2fs_replace_block
+		 *  - check_valid_map()            - mutex_lock(sentry_lock)
+		 *   - mutex_lock(sentry_lock)     - change_curseg()
+		 *                                  - lock_page(sum_page)
+		 */
+
+		if (type == SUM_TYPE_NODE)
+			gc_node_segment(sbi, sum->entries, segno, gc_type);
+		else
+			gc_data_segment(sbi, sum->entries, gc_list, segno,
+								gc_type);
+
+		stat_inc_seg_count(sbi, type, gc_type);
+
+		f2fs_put_page(sum_page, 0);
+	}
+
+	if (gc_type == FG_GC) {
+		if (type == SUM_TYPE_NODE) {
+			struct writeback_control wbc = {
+				.sync_mode = WB_SYNC_ALL,
+				.nr_to_write = LONG_MAX,
+				.for_reclaim = 0,
+			};
+			sync_node_pages(sbi, 0, &wbc);
+		} else {
+			f2fs_submit_merged_bio(sbi, DATA, WRITE);
+		}
 	}
+
 	blk_finish_plug(&plug);
 
-	stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)), gc_type);
+	if (gc_type == FG_GC) {
+		while (start_segno < end_segno)
+			if (get_valid_blocks(sbi, start_segno++, 1) == 0)
+				seg_freed++;
+	}
+
 	stat_inc_call_count(sbi->stat_info);
 
-	f2fs_put_page(sum_page, 0);
-	return nfree;
+	return seg_freed;
 }
 
 int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
 {
-	unsigned int segno, i;
+	unsigned int segno;
 	int gc_type = sync ? FG_GC : BG_GC;
-	int sec_freed = 0;
+	int sec_freed = 0, seg_freed;
 	int ret = -EINVAL;
 	struct cp_control cpc;
 	struct gc_inode_list gc_list = {
@@ -838,30 +885,24 @@ gc_more:
 
 	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) {
 		gc_type = FG_GC;
+		/*
+		 * If there is no victim and no prefree segment but still not
+		 * enough free sections, we should flush dent/node blocks and do
+		 * garbage collections.
+		 */
 		if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi))
 			write_checkpoint(sbi, &cpc);
+		else if (has_not_enough_free_secs(sbi, 0))
+			write_checkpoint(sbi, &cpc);
 	}
 
 	if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
 		goto stop;
 	ret = 0;
 
-	/* readahead multi ssa blocks those have contiguous address */
-	if (sbi->segs_per_sec > 1)
-		ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), sbi->segs_per_sec,
-							META_SSA, true);
-
-	for (i = 0; i < sbi->segs_per_sec; i++) {
-		/*
-		 * for FG_GC case, halt gcing left segments once failed one
-		 * of segments in selected section to avoid long latency.
-		 */
-		if (!do_garbage_collect(sbi, segno + i, &gc_list, gc_type) &&
-				gc_type == FG_GC)
-			break;
-	}
+	seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
 
-	if (i == sbi->segs_per_sec && gc_type == FG_GC)
+	if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
 		sec_freed++;
 
 	if (gc_type == FG_GC)
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index c3f0b7d4cfca..358214e9f707 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -71,7 +71,7 @@ bool truncate_inline_inode(struct page *ipage, u64 from)
 
 	addr = inline_data_addr(ipage);
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 	memset(addr + from, 0, MAX_INLINE_DATA - from);
 
 	return true;
@@ -105,7 +105,6 @@ 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;
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(dn->inode),
 		.type = DATA,
@@ -115,8 +114,6 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	};
 	int dirty, err;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), page->index);
-
 	if (!f2fs_exist_data(dn->inode))
 		goto clear_out;
 
@@ -124,21 +121,9 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	if (err)
 		return err;
 
-	f2fs_wait_on_page_writeback(page, DATA);
-
-	if (PageUptodate(page))
-		goto no_update;
-
-	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
+	f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
 
-	/* Copy the whole inline data block */
-	src_addr = inline_data_addr(dn->inode_page);
-	dst_addr = kmap_atomic(page);
-	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
-	flush_dcache_page(page);
-	kunmap_atomic(dst_addr);
-	SetPageUptodate(page);
-no_update:
+	read_inline_data(page, dn->inode_page);
 	set_page_dirty(page);
 
 	/* clear dirty state */
@@ -146,11 +131,9 @@ no_update:
 
 	/* write data page to try to make data consistent */
 	set_page_writeback(page);
-	fio.blk_addr = dn->data_blkaddr;
+	fio.old_blkaddr = dn->data_blkaddr;
 	write_data_page(dn, &fio);
-	set_data_blkaddr(dn);
-	f2fs_update_extent_cache(dn);
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 	if (dirty)
 		inode_dec_dirty_pages(dn->inode);
 
@@ -159,6 +142,7 @@ no_update:
 
 	/* clear inline data and flag after data writeback */
 	truncate_inline_inode(dn->inode_page, 0);
+	clear_inline_node(dn->inode_page);
 clear_out:
 	stat_dec_inline_inode(dn->inode);
 	f2fs_clear_inline_inode(dn->inode);
@@ -223,7 +207,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
 
 	f2fs_bug_on(F2FS_I_SB(inode), page->index);
 
-	f2fs_wait_on_page_writeback(dn.inode_page, NODE);
+	f2fs_wait_on_page_writeback(dn.inode_page, NODE, true);
 	src_addr = kmap_atomic(page);
 	dst_addr = inline_data_addr(dn.inode_page);
 	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
@@ -233,6 +217,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
 	set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
 
 	sync_inode_page(&dn);
+	clear_inline_node(dn.inode_page);
 	f2fs_put_dnode(&dn);
 	return 0;
 }
@@ -261,7 +246,7 @@ process_inline:
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(sbi, IS_ERR(ipage));
 
-		f2fs_wait_on_page_writeback(ipage, NODE);
+		f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 		src_addr = inline_data_addr(npage);
 		dst_addr = inline_data_addr(ipage);
@@ -292,7 +277,7 @@ process_inline:
 }
 
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
-			struct f2fs_filename *fname, struct page **res_page)
+			struct fscrypt_name *fname, struct page **res_page)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
 	struct f2fs_inline_dentry *inline_dentry;
@@ -389,7 +374,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	if (err)
 		goto out;
 
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
 
 	dentry_blk = kmap_atomic(page);
@@ -469,7 +454,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
 		}
 	}
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 	name_hash = f2fs_dentry_hash(name);
 	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
@@ -507,7 +492,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	int i;
 
 	lock_page(page);
-	f2fs_wait_on_page_writeback(page, NODE);
+	f2fs_wait_on_page_writeback(page, NODE, true);
 
 	inline_dentry = inline_data_addr(page);
 	bit_pos = dentry - inline_dentry->dentry;
@@ -550,7 +535,7 @@ bool f2fs_empty_inline_dir(struct inode *dir)
 }
 
 int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
-				struct f2fs_str *fstr)
+				struct fscrypt_str *fstr)
 {
 	struct inode *inode = file_inode(file);
 	struct f2fs_inline_dentry *inline_dentry = NULL;
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 2adeff26be11..cb269c46ac25 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -83,7 +83,7 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
 
 	while (start < end) {
 		if (*start++) {
-			f2fs_wait_on_page_writeback(ipage, NODE);
+			f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
 			set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
@@ -227,7 +227,7 @@ int update_inode(struct inode *inode, struct page *node_page)
 {
 	struct f2fs_inode *ri;
 
-	f2fs_wait_on_page_writeback(node_page, NODE);
+	f2fs_wait_on_page_writeback(node_page, NODE, true);
 
 	ri = F2FS_INODE(node_page);
 
@@ -263,6 +263,10 @@ int update_inode(struct inode *inode, struct page *node_page)
 	set_cold_node(inode, node_page);
 	clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
 
+	/* deleted inode */
+	if (inode->i_nlink == 0)
+		clear_inline_node(node_page);
+
 	return set_page_dirty(node_page);
 }
 
@@ -320,7 +324,7 @@ void f2fs_evict_inode(struct inode *inode)
 
 	/* some remained atomic pages should discarded */
 	if (f2fs_is_atomic_file(inode))
-		commit_inmem_pages(inode, true);
+		drop_inmem_pages(inode);
 
 	trace_f2fs_evict_inode(inode);
 	truncate_inode_pages_final(&inode->i_data);
@@ -385,10 +389,7 @@ no_delete:
 		}
 	}
 out_clear:
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	if (fi->i_crypt_info)
-		f2fs_free_encryption_info(inode, fi->i_crypt_info);
-#endif
+	fscrypt_put_encryption_info(inode, NULL);
 	clear_inode(inode);
 }
 
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 6f944e5eb76e..7876f1052101 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -169,7 +169,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 	int err;
 
 	if (f2fs_encrypted_inode(dir) &&
-		!f2fs_is_child_context_consistent_with_parent(dir, inode))
+			!fscrypt_has_permitted_context(dir, inode))
 		return -EPERM;
 
 	f2fs_balance_fs(sbi, true);
@@ -260,6 +260,22 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	struct page *page;
 	nid_t ino;
 	int err = 0;
+	unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
+
+	if (f2fs_encrypted_inode(dir)) {
+		int res = fscrypt_get_encryption_info(dir);
+
+		/*
+		 * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
+		 * created while the directory was encrypted and we
+		 * don't have access to the key.
+		 */
+		if (fscrypt_has_encryption_key(dir))
+			fscrypt_set_encrypted_dentry(dentry);
+		fscrypt_set_d_op(dentry);
+		if (res && res != -ENOKEY)
+			return ERR_PTR(res);
+	}
 
 	if (dentry->d_name.len > F2FS_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -276,15 +292,29 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
+	if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) {
+		err = __recover_dot_dentries(dir, root_ino);
+		if (err)
+			goto err_out;
+	}
+
 	if (f2fs_has_inline_dots(inode)) {
 		err = __recover_dot_dentries(inode, dir->i_ino);
 		if (err)
 			goto err_out;
 	}
+	if (!IS_ERR(inode) && f2fs_encrypted_inode(dir) &&
+			(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+			!fscrypt_has_permitted_context(dir, inode)) {
+		bool nokey = f2fs_encrypted_inode(inode) &&
+			!fscrypt_has_encryption_key(inode);
+		err = nokey ? -ENOKEY : -EPERM;
+		goto err_out;
+	}
 	return d_splice_alias(inode, dentry);
 
 err_out:
-	iget_failed(inode);
+	iput(inode);
 	return ERR_PTR(err);
 }
 
@@ -345,13 +375,23 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 	struct inode *inode;
 	size_t len = strlen(symname);
-	size_t p_len;
-	char *p_str;
-	struct f2fs_str disk_link = FSTR_INIT(NULL, 0);
-	struct f2fs_encrypted_symlink_data *sd = NULL;
+	struct fscrypt_str disk_link = FSTR_INIT((char *)symname, len + 1);
+	struct fscrypt_symlink_data *sd = NULL;
 	int err;
 
-	if (len > dir->i_sb->s_blocksize)
+	if (f2fs_encrypted_inode(dir)) {
+		err = fscrypt_get_encryption_info(dir);
+		if (err)
+			return err;
+
+		if (!fscrypt_has_encryption_key(dir))
+			return -EPERM;
+
+		disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
+				sizeof(struct fscrypt_symlink_data));
+	}
+
+	if (disk_link.len > dir->i_sb->s_blocksize)
 		return -ENAMETOOLONG;
 
 	inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
@@ -374,42 +414,36 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	f2fs_unlock_op(sbi);
 	alloc_nid_done(sbi, inode->i_ino);
 
-	if (f2fs_encrypted_inode(dir)) {
+	if (f2fs_encrypted_inode(inode)) {
 		struct qstr istr = QSTR_INIT(symname, len);
+		struct fscrypt_str ostr;
 
-		err = f2fs_get_encryption_info(inode);
-		if (err)
+		sd = kzalloc(disk_link.len, GFP_NOFS);
+		if (!sd) {
+			err = -ENOMEM;
 			goto err_out;
+		}
 
-		err = f2fs_fname_crypto_alloc_buffer(inode, len, &disk_link);
+		err = fscrypt_get_encryption_info(inode);
 		if (err)
 			goto err_out;
 
-		err = f2fs_fname_usr_to_disk(inode, &istr, &disk_link);
-		if (err < 0)
-			goto err_out;
-
-		p_len = encrypted_symlink_data_len(disk_link.len) + 1;
-
-		if (p_len > dir->i_sb->s_blocksize) {
-			err = -ENAMETOOLONG;
+		if (!fscrypt_has_encryption_key(inode)) {
+			err = -EPERM;
 			goto err_out;
 		}
 
-		sd = kzalloc(p_len, GFP_NOFS);
-		if (!sd) {
-			err = -ENOMEM;
+		ostr.name = sd->encrypted_path;
+		ostr.len = disk_link.len;
+		err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
+		if (err < 0)
 			goto err_out;
-		}
-		memcpy(sd->encrypted_path, disk_link.name, disk_link.len);
-		sd->len = cpu_to_le16(disk_link.len);
-		p_str = (char *)sd;
-	} else {
-		p_len = len + 1;
-		p_str = (char *)symname;
+
+		sd->len = cpu_to_le16(ostr.len);
+		disk_link.name = (char *)sd;
 	}
 
-	err = page_symlink(inode, p_str, p_len);
+	err = page_symlink(inode, disk_link.name, disk_link.len);
 
 err_out:
 	d_instantiate(dentry, inode);
@@ -425,7 +459,8 @@ err_out:
 	 * performance regression.
 	 */
 	if (!err) {
-		filemap_write_and_wait_range(inode->i_mapping, 0, p_len - 1);
+		filemap_write_and_wait_range(inode->i_mapping, 0,
+							disk_link.len - 1);
 
 		if (IS_DIRSYNC(dir))
 			f2fs_sync_fs(sbi->sb, 1);
@@ -434,7 +469,6 @@ err_out:
 	}
 
 	kfree(sd);
-	f2fs_fname_crypto_free_buffer(&disk_link);
 	return err;
 out:
 	handle_failed_inode(inode);
@@ -582,7 +616,7 @@ out:
 static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	if (f2fs_encrypted_inode(dir)) {
-		int err = f2fs_get_encryption_info(dir);
+		int err = fscrypt_get_encryption_info(dir);
 		if (err)
 			return err;
 	}
@@ -608,11 +642,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct f2fs_dir_entry *old_dir_entry = NULL;
 	struct f2fs_dir_entry *old_entry;
 	struct f2fs_dir_entry *new_entry;
+	bool is_old_inline = f2fs_has_inline_dentry(old_dir);
 	int err = -ENOENT;
 
 	if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
-		!f2fs_is_child_context_consistent_with_parent(new_dir,
-							old_inode)) {
+			!fscrypt_has_permitted_context(new_dir, old_inode)) {
 		err = -EPERM;
 		goto out;
 	}
@@ -654,8 +688,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (err)
 			goto put_out_dir;
 
-		if (update_dent_inode(old_inode, new_inode,
-						&new_dentry->d_name)) {
+		err = update_dent_inode(old_inode, new_inode,
+						&new_dentry->d_name);
+		if (err) {
 			release_orphan_inode(sbi);
 			goto put_out_dir;
 		}
@@ -693,6 +728,26 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			inc_nlink(new_dir);
 			update_inode_page(new_dir);
 		}
+
+		/*
+		 * old entry and new entry can locate in the same inline
+		 * dentry in inode, when attaching new entry in inline dentry,
+		 * it could force inline dentry conversion, after that,
+		 * old_entry and old_page will point to wrong address, in
+		 * order to avoid this, let's do the check and update here.
+		 */
+		if (is_old_inline && !f2fs_has_inline_dentry(old_dir)) {
+			f2fs_put_page(old_page, 0);
+			old_page = NULL;
+
+			old_entry = f2fs_find_entry(old_dir,
+						&old_dentry->d_name, &old_page);
+			if (!old_entry) {
+				err = -EIO;
+				f2fs_unlock_op(sbi);
+				goto out_whiteout;
+			}
+		}
 	}
 
 	down_write(&F2FS_I(old_inode)->i_sem);
@@ -771,11 +826,9 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int err = -ENOENT;
 
 	if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
-		(old_dir != new_dir) &&
-		(!f2fs_is_child_context_consistent_with_parent(new_dir,
-								old_inode) ||
-		!f2fs_is_child_context_consistent_with_parent(old_dir,
-								new_inode)))
+			(old_dir != new_dir) &&
+			(!fscrypt_has_permitted_context(new_dir, old_inode) ||
+			 !fscrypt_has_permitted_context(old_dir, new_inode)))
 		return -EPERM;
 
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
@@ -937,16 +990,15 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry,
 	return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
 }
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
 static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 					   struct inode *inode,
 					   struct delayed_call *done)
 {
 	struct page *cpage = NULL;
 	char *caddr, *paddr = NULL;
-	struct f2fs_str cstr = FSTR_INIT(NULL, 0);
-	struct f2fs_str pstr = FSTR_INIT(NULL, 0);
-	struct f2fs_encrypted_symlink_data *sd;
+	struct fscrypt_str cstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_str pstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_symlink_data *sd;
 	loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
 	u32 max_size = inode->i_sb->s_blocksize;
 	int res;
@@ -954,7 +1006,7 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 	if (!dentry)
 		return ERR_PTR(-ECHILD);
 
-	res = f2fs_get_encryption_info(inode);
+	res = fscrypt_get_encryption_info(inode);
 	if (res)
 		return ERR_PTR(res);
 
@@ -965,7 +1017,8 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 	caddr[size] = 0;
 
 	/* Symlink is encrypted */
-	sd = (struct f2fs_encrypted_symlink_data *)caddr;
+	sd = (struct fscrypt_symlink_data *)caddr;
+	cstr.name = sd->encrypted_path;
 	cstr.len = le16_to_cpu(sd->len);
 
 	/* this is broken symlink case */
@@ -973,12 +1026,6 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 		res = -ENOENT;
 		goto errout;
 	}
-	cstr.name = kmalloc(cstr.len, GFP_NOFS);
-	if (!cstr.name) {
-		res = -ENOMEM;
-		goto errout;
-	}
-	memcpy(cstr.name, sd->encrypted_path, cstr.len);
 
 	/* this is broken symlink case */
 	if (unlikely(cstr.name[0] == 0)) {
@@ -986,22 +1033,19 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 		goto errout;
 	}
 
-	if ((cstr.len + sizeof(struct f2fs_encrypted_symlink_data) - 1) >
-								max_size) {
+	if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) {
 		/* Symlink data on the disk is corrupted */
 		res = -EIO;
 		goto errout;
 	}
-	res = f2fs_fname_crypto_alloc_buffer(inode, cstr.len, &pstr);
+	res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
 	if (res)
 		goto errout;
 
-	res = f2fs_fname_disk_to_usr(inode, NULL, &cstr, &pstr);
+	res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
 	if (res < 0)
 		goto errout;
 
-	kfree(cstr.name);
-
 	paddr = pstr.name;
 
 	/* Null-terminate the name */
@@ -1011,8 +1055,7 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 	set_delayed_call(done, kfree_link, paddr);
 	return paddr;
 errout:
-	kfree(cstr.name);
-	f2fs_fname_crypto_free_buffer(&pstr);
+	fscrypt_fname_free_buffer(&pstr);
 	page_cache_release(cpage);
 	return ERR_PTR(res);
 }
@@ -1029,7 +1072,6 @@ const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
 	.removexattr	= generic_removexattr,
 #endif
 };
-#endif
 
 const struct inode_operations f2fs_dir_inode_operations = {
 	.create		= f2fs_create,
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 342597a5897f..118321bd1a7f 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -257,15 +257,20 @@ static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
 	return new;
 }
 
-static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
+static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
 						struct f2fs_nat_entry *ne)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct nat_entry *e;
 
 	e = __lookup_nat_cache(nm_i, nid);
 	if (!e) {
 		e = grab_nat_entry(nm_i, nid);
 		node_info_from_raw_nat(&e->ni, ne);
+	} else {
+		f2fs_bug_on(sbi, nat_get_ino(e) != ne->ino ||
+				nat_get_blkaddr(e) != ne->block_addr ||
+				nat_get_version(e) != ne->version);
 	}
 }
 
@@ -354,7 +359,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 {
 	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 f2fs_journal *journal = curseg->journal;
 	nid_t start_nid = START_NID(nid);
 	struct f2fs_nat_block *nat_blk;
 	struct page *page = NULL;
@@ -371,23 +376,20 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 		ni->ino = nat_get_ino(e);
 		ni->blk_addr = nat_get_blkaddr(e);
 		ni->version = nat_get_version(e);
-	}
-	up_read(&nm_i->nat_tree_lock);
-	if (e)
+		up_read(&nm_i->nat_tree_lock);
 		return;
+	}
 
 	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
 
-	down_write(&nm_i->nat_tree_lock);
-
 	/* Check current segment summary */
-	mutex_lock(&curseg->curseg_mutex);
-	i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
+	down_read(&curseg->journal_rwsem);
+	i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
 	if (i >= 0) {
-		ne = nat_in_journal(sum, i);
+		ne = nat_in_journal(journal, i);
 		node_info_from_raw_nat(ni, &ne);
 	}
-	mutex_unlock(&curseg->curseg_mutex);
+	up_read(&curseg->journal_rwsem);
 	if (i >= 0)
 		goto cache;
 
@@ -398,19 +400,52 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	node_info_from_raw_nat(ni, &ne);
 	f2fs_put_page(page, 1);
 cache:
+	up_read(&nm_i->nat_tree_lock);
 	/* cache nat entry */
-	cache_nat_entry(NM_I(sbi), nid, &ne);
+	down_write(&nm_i->nat_tree_lock);
+	cache_nat_entry(sbi, nid, &ne);
 	up_write(&nm_i->nat_tree_lock);
 }
 
+pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
+{
+	const long direct_index = ADDRS_PER_INODE(dn->inode);
+	const long direct_blks = ADDRS_PER_BLOCK;
+	const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
+	unsigned int skipped_unit = ADDRS_PER_BLOCK;
+	int cur_level = dn->cur_level;
+	int max_level = dn->max_level;
+	pgoff_t base = 0;
+
+	if (!dn->max_level)
+		return pgofs + 1;
+
+	while (max_level-- > cur_level)
+		skipped_unit *= NIDS_PER_BLOCK;
+
+	switch (dn->max_level) {
+	case 3:
+		base += 2 * indirect_blks;
+	case 2:
+		base += 2 * direct_blks;
+	case 1:
+		base += direct_index;
+		break;
+	default:
+		f2fs_bug_on(F2FS_I_SB(dn->inode), 1);
+	}
+
+	return ((pgofs - base) / skipped_unit + 1) * skipped_unit + base;
+}
+
 /*
  * The maximum depth is four.
  * Offset[0] will have raw inode offset.
  */
-static int get_node_path(struct f2fs_inode_info *fi, long block,
+static int get_node_path(struct inode *inode, long block,
 				int offset[4], unsigned int noffset[4])
 {
-	const long direct_index = ADDRS_PER_INODE(fi);
+	const long direct_index = ADDRS_PER_INODE(inode);
 	const long direct_blks = ADDRS_PER_BLOCK;
 	const long dptrs_per_blk = NIDS_PER_BLOCK;
 	const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
@@ -495,10 +530,10 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 	int offset[4];
 	unsigned int noffset[4];
 	nid_t nids[4];
-	int level, i;
+	int level, i = 0;
 	int err = 0;
 
-	level = get_node_path(F2FS_I(dn->inode), index, offset, noffset);
+	level = get_node_path(dn->inode, index, offset, noffset);
 
 	nids[0] = dn->inode->i_ino;
 	npage[0] = dn->inode_page;
@@ -585,6 +620,10 @@ release_pages:
 release_out:
 	dn->inode_page = NULL;
 	dn->node_page = NULL;
+	if (err == -ENOENT) {
+		dn->cur_level = i;
+		dn->max_level = level;
+	}
 	return err;
 }
 
@@ -792,7 +831,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
 
 	trace_f2fs_truncate_inode_blocks_enter(inode, from);
 
-	level = get_node_path(F2FS_I(inode), from, offset, noffset);
+	level = get_node_path(inode, from, offset, noffset);
 restart:
 	page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(page)) {
@@ -861,7 +900,7 @@ skip_partial:
 				f2fs_put_page(page, 1);
 				goto restart;
 			}
-			f2fs_wait_on_page_writeback(page, NODE);
+			f2fs_wait_on_page_writeback(page, NODE, true);
 			ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
 			set_page_dirty(page);
 			unlock_page(page);
@@ -976,7 +1015,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	new_ni.ino = dn->inode->i_ino;
 	set_node_addr(sbi, &new_ni, NEW_ADDR, false);
 
-	f2fs_wait_on_page_writeback(page, NODE);
+	f2fs_wait_on_page_writeback(page, NODE, true);
 	fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
 	set_cold_node(dn->inode, page);
 	SetPageUptodate(page);
@@ -1029,7 +1068,7 @@ static int read_node_page(struct page *page, int rw)
 	if (PageUptodate(page))
 		return LOCKED_PAGE;
 
-	fio.blk_addr = ni.blk_addr;
+	fio.new_blkaddr = fio.old_blkaddr = ni.blk_addr;
 	return f2fs_submit_page_bio(&fio);
 }
 
@@ -1045,12 +1084,11 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 		return;
 	f2fs_bug_on(sbi, check_nid_range(sbi, nid));
 
-	apage = find_get_page(NODE_MAPPING(sbi), nid);
-	if (apage && PageUptodate(apage)) {
-		f2fs_put_page(apage, 0);
+	rcu_read_lock();
+	apage = radix_tree_lookup(&NODE_MAPPING(sbi)->page_tree, nid);
+	rcu_read_unlock();
+	if (apage)
 		return;
-	}
-	f2fs_put_page(apage, 0);
 
 	apage = grab_cache_page(NODE_MAPPING(sbi), nid);
 	if (!apage)
@@ -1063,7 +1101,7 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 /*
  * readahead MAX_RA_NODE number of node pages.
  */
-void ra_node_pages(struct page *parent, int start)
+static void ra_node_pages(struct page *parent, int start)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
 	struct blk_plug plug;
@@ -1083,7 +1121,7 @@ void ra_node_pages(struct page *parent, int start)
 	blk_finish_plug(&plug);
 }
 
-struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
+static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
 					struct page *parent, int start)
 {
 	struct page *page;
@@ -1154,19 +1192,57 @@ void sync_inode_page(struct dnode_of_data *dn)
 	dn->node_changed = ret ? true: false;
 }
 
+static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
+{
+	struct inode *inode;
+	struct page *page;
+
+	/* should flush inline_data before evict_inode */
+	inode = ilookup(sbi->sb, ino);
+	if (!inode)
+		return;
+
+	page = pagecache_get_page(inode->i_mapping, 0, FGP_NOWAIT, 0);
+	if (!page)
+		goto iput_out;
+
+	if (!trylock_page(page))
+		goto release_out;
+
+	if (!PageUptodate(page))
+		goto page_out;
+
+	if (!PageDirty(page))
+		goto page_out;
+
+	if (!clear_page_dirty_for_io(page))
+		goto page_out;
+
+	if (!f2fs_write_inline_data(inode, page))
+		inode_dec_dirty_pages(inode);
+	else
+		set_page_dirty(page);
+page_out:
+	unlock_page(page);
+release_out:
+	f2fs_put_page(page, 0);
+iput_out:
+	iput(inode);
+}
+
 int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
 					struct writeback_control *wbc)
 {
 	pgoff_t index, end;
 	struct pagevec pvec;
 	int step = ino ? 2 : 0;
-	int nwritten = 0, wrote = 0;
+	int nwritten = 0;
 
 	pagevec_init(&pvec, 0);
 
 next_step:
 	index = 0;
-	end = LONG_MAX;
+	end = ULONG_MAX;
 
 	while (index <= end) {
 		int i, nr_pages;
@@ -1203,6 +1279,7 @@ next_step:
 			 * If an fsync mode,
 			 * we should not skip writing node pages.
 			 */
+lock_node:
 			if (ino && ino_of_node(page) == ino)
 				lock_page(page);
 			else if (!trylock_page(page))
@@ -1221,6 +1298,17 @@ continue_unlock:
 				goto continue_unlock;
 			}
 
+			/* flush inline_data */
+			if (!ino && is_inline_node(page)) {
+				clear_inline_node(page);
+				unlock_page(page);
+				flush_inline_data(sbi, ino_of_node(page));
+				goto lock_node;
+			}
+
+			f2fs_wait_on_page_writeback(page, NODE, true);
+
+			BUG_ON(PageWriteback(page));
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
@@ -1238,8 +1326,6 @@ continue_unlock:
 
 			if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
 				unlock_page(page);
-			else
-				wrote++;
 
 			if (--wbc->nr_to_write == 0)
 				break;
@@ -1257,15 +1343,12 @@ continue_unlock:
 		step++;
 		goto next_step;
 	}
-
-	if (wrote)
-		f2fs_submit_merged_bio(sbi, NODE, WRITE);
 	return nwritten;
 }
 
 int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
 {
-	pgoff_t index = 0, end = LONG_MAX;
+	pgoff_t index = 0, end = ULONG_MAX;
 	struct pagevec pvec;
 	int ret2 = 0, ret = 0;
 
@@ -1287,7 +1370,7 @@ int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
 				continue;
 
 			if (ino && ino_of_node(page) == ino) {
-				f2fs_wait_on_page_writeback(page, NODE);
+				f2fs_wait_on_page_writeback(page, NODE, true);
 				if (TestClearPageError(page))
 					ret = -EIO;
 			}
@@ -1326,8 +1409,6 @@ static int f2fs_write_node_page(struct page *page,
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto redirty_out;
 
-	f2fs_wait_on_page_writeback(page, NODE);
-
 	/* get old block addr of this node page */
 	nid = nid_of_node(page);
 	f2fs_bug_on(sbi, page->index != nid);
@@ -1351,14 +1432,18 @@ static int f2fs_write_node_page(struct page *page,
 	}
 
 	set_page_writeback(page);
-	fio.blk_addr = ni.blk_addr;
+	fio.old_blkaddr = ni.blk_addr;
 	write_node_page(nid, &fio);
-	set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page));
+	set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
 	dec_page_count(sbi, F2FS_DIRTY_NODES);
 	up_read(&sbi->node_write);
+
+	if (wbc->for_reclaim)
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, NODE, WRITE);
+
 	unlock_page(page);
 
-	if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi)))
 		f2fs_submit_merged_bio(sbi, NODE, WRITE);
 
 	return 0;
@@ -1374,8 +1459,6 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
 	long diff;
 
-	trace_f2fs_writepages(mapping->host, wbc, NODE);
-
 	/* balancing f2fs's metadata in background */
 	f2fs_balance_fs_bg(sbi);
 
@@ -1383,6 +1466,8 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE))
 		goto skip_write;
 
+	trace_f2fs_writepages(mapping->host, wbc, NODE);
+
 	diff = nr_pages_to_write(sbi, NODE, wbc);
 	wbc->sync_mode = WB_SYNC_NONE;
 	sync_node_pages(sbi, 0, wbc);
@@ -1391,6 +1476,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 
 skip_write:
 	wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_NODES);
+	trace_f2fs_writepages(mapping->host, wbc, NODE);
 	return 0;
 }
 
@@ -1526,7 +1612,7 @@ static void build_free_nids(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 f2fs_journal *journal = curseg->journal;
 	int i = 0;
 	nid_t nid = nm_i->next_scan_nid;
 
@@ -1558,16 +1644,18 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 	nm_i->next_scan_nid = nid;
 
 	/* find free nids from current sum_pages */
-	mutex_lock(&curseg->curseg_mutex);
-	for (i = 0; i < nats_in_cursum(sum); i++) {
-		block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr);
-		nid = le32_to_cpu(nid_in_journal(sum, i));
+	down_read(&curseg->journal_rwsem);
+	for (i = 0; i < nats_in_cursum(journal); i++) {
+		block_t addr;
+
+		addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
+		nid = le32_to_cpu(nid_in_journal(journal, i));
 		if (addr == NULL_ADDR)
 			add_free_nid(sbi, nid, true);
 		else
 			remove_free_nid(nm_i, nid);
 	}
-	mutex_unlock(&curseg->curseg_mutex);
+	up_read(&curseg->journal_rwsem);
 	up_read(&nm_i->nat_tree_lock);
 
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
@@ -1703,7 +1791,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
 	src_addr = inline_xattr_addr(page);
 	inline_size = inline_xattr_size(inode);
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 	memcpy(dst_addr, src_addr, inline_size);
 update_inode:
 	update_inode(inode, ipage);
@@ -1831,16 +1919,16 @@ static void remove_nats_in_journal(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 f2fs_journal *journal = curseg->journal;
 	int i;
 
-	mutex_lock(&curseg->curseg_mutex);
-	for (i = 0; i < nats_in_cursum(sum); i++) {
+	down_write(&curseg->journal_rwsem);
+	for (i = 0; i < nats_in_cursum(journal); i++) {
 		struct nat_entry *ne;
 		struct f2fs_nat_entry raw_ne;
-		nid_t nid = le32_to_cpu(nid_in_journal(sum, i));
+		nid_t nid = le32_to_cpu(nid_in_journal(journal, i));
 
-		raw_ne = nat_in_journal(sum, i);
+		raw_ne = nat_in_journal(journal, i);
 
 		ne = __lookup_nat_cache(nm_i, nid);
 		if (!ne) {
@@ -1849,8 +1937,8 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 		}
 		__set_nat_cache_dirty(nm_i, ne);
 	}
-	update_nats_in_cursum(sum, -i);
-	mutex_unlock(&curseg->curseg_mutex);
+	update_nats_in_cursum(journal, -i);
+	up_write(&curseg->journal_rwsem);
 }
 
 static void __adjust_nat_entry_set(struct nat_entry_set *nes,
@@ -1875,7 +1963,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 					struct nat_entry_set *set)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	nid_t start_nid = set->set * NAT_ENTRY_PER_BLOCK;
 	bool to_journal = true;
 	struct f2fs_nat_block *nat_blk;
@@ -1887,11 +1975,11 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 	 * #1, flush nat entries to journal in current hot data summary block.
 	 * #2, flush nat entries to nat page.
 	 */
-	if (!__has_cursum_space(sum, set->entry_cnt, NAT_JOURNAL))
+	if (!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
 		to_journal = false;
 
 	if (to_journal) {
-		mutex_lock(&curseg->curseg_mutex);
+		down_write(&curseg->journal_rwsem);
 	} else {
 		page = get_next_nat_page(sbi, start_nid);
 		nat_blk = page_address(page);
@@ -1908,11 +1996,11 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 			continue;
 
 		if (to_journal) {
-			offset = lookup_journal_in_cursum(sum,
+			offset = lookup_journal_in_cursum(journal,
 							NAT_JOURNAL, nid, 1);
 			f2fs_bug_on(sbi, offset < 0);
-			raw_ne = &nat_in_journal(sum, offset);
-			nid_in_journal(sum, offset) = cpu_to_le32(nid);
+			raw_ne = &nat_in_journal(journal, offset);
+			nid_in_journal(journal, offset) = cpu_to_le32(nid);
 		} else {
 			raw_ne = &nat_blk->entries[nid - start_nid];
 		}
@@ -1924,7 +2012,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 	}
 
 	if (to_journal)
-		mutex_unlock(&curseg->curseg_mutex);
+		up_write(&curseg->journal_rwsem);
 	else
 		f2fs_put_page(page, 1);
 
@@ -1941,7 +2029,7 @@ 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 f2fs_journal *journal = curseg->journal;
 	struct nat_entry_set *setvec[SETVEC_SIZE];
 	struct nat_entry_set *set, *tmp;
 	unsigned int found;
@@ -1958,7 +2046,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 	 * entries, remove all entries from journal and merge them
 	 * into nat entry set.
 	 */
-	if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+	if (!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
 		remove_nats_in_journal(sbi);
 
 	while ((found = __gang_lookup_nat_set(nm_i,
@@ -1967,7 +2055,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 		set_idx = setvec[found - 1]->set + 1;
 		for (idx = 0; idx < found; idx++)
 			__adjust_nat_entry_set(setvec[idx], &sets,
-							MAX_NAT_JENTRIES(sum));
+						MAX_NAT_JENTRIES(journal));
 	}
 
 	/* flush dirty nats in nat entry set */
@@ -2000,6 +2088,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	nm_i->nat_cnt = 0;
 	nm_i->ram_thresh = DEF_RAM_THRESHOLD;
 	nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
+	nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
 
 	INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
 	INIT_LIST_HEAD(&nm_i->free_nid_list);
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index d4d1f636fe1c..1f4f9d4569d9 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -25,6 +25,9 @@
 /* control the memory footprint threshold (10MB per 1GB ram) */
 #define DEF_RAM_THRESHOLD	10
 
+/* control dirty nats ratio threshold (default: 10% over max nid count) */
+#define DEF_DIRTY_NAT_RATIO_THRESHOLD		10
+
 /* vector size for gang look-up from nat cache that consists of radix tree */
 #define NATVEC_SIZE	64
 #define SETVEC_SIZE	32
@@ -117,6 +120,12 @@ static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
 	raw_ne->version = ni->version;
 }
 
+static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
+{
+	return NM_I(sbi)->dirty_nat_cnt >= NM_I(sbi)->max_nid *
+					NM_I(sbi)->dirty_nats_ratio / 100;
+}
+
 enum mem_type {
 	FREE_NIDS,	/* indicates the free nid list */
 	NAT_ENTRIES,	/* indicates the cached nat entry */
@@ -321,7 +330,7 @@ static inline int set_nid(struct page *p, int off, nid_t nid, bool i)
 {
 	struct f2fs_node *rn = F2FS_NODE(p);
 
-	f2fs_wait_on_page_writeback(p, NODE);
+	f2fs_wait_on_page_writeback(p, NODE, true);
 
 	if (i)
 		rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
@@ -370,6 +379,21 @@ static inline int is_node(struct page *page, int type)
 #define is_fsync_dnode(page)	is_node(page, FSYNC_BIT_SHIFT)
 #define is_dent_dnode(page)	is_node(page, DENT_BIT_SHIFT)
 
+static inline int is_inline_node(struct page *page)
+{
+	return PageChecked(page);
+}
+
+static inline void set_inline_node(struct page *page)
+{
+	SetPageChecked(page);
+}
+
+static inline void clear_inline_node(struct page *page)
+{
+	ClearPageChecked(page);
+}
+
 static inline void set_cold_node(struct inode *inode, struct page *page)
 {
 	struct f2fs_node *rn = F2FS_NODE(page);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 589b20b8677b..0b30cd2aeebd 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -350,8 +350,7 @@ got_it:
 		inode = dn->inode;
 	}
 
-	bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
-			le16_to_cpu(sum.ofs_in_node);
+	bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node);
 
 	/*
 	 * if inode page is locked, unlock temporarily, but its reference
@@ -386,10 +385,9 @@ truncate_out:
 static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 					struct page *page, block_t blkaddr)
 {
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	unsigned int start, end;
 	struct dnode_of_data dn;
 	struct node_info ni;
+	unsigned int start, end;
 	int err = 0, recovered = 0;
 
 	/* step 1: recover xattr */
@@ -409,8 +407,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 		goto out;
 
 	/* step 3: recover data indices */
-	start = start_bidx_of_node(ofs_of_node(page), fi);
-	end = start + ADDRS_PER_PAGE(page, fi);
+	start = start_bidx_of_node(ofs_of_node(page), inode);
+	end = start + ADDRS_PER_PAGE(page, inode);
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 
@@ -418,7 +416,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	if (err)
 		goto out;
 
-	f2fs_wait_on_page_writeback(dn.node_page, NODE);
+	f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
 
 	get_node_info(sbi, dn.nid, &ni);
 	f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
@@ -467,7 +465,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 			/* write dummy data page */
 			f2fs_replace_block(sbi, &dn, src, dest,
-							ni.version, false);
+						ni.version, false, false);
 			recovered++;
 		}
 	}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 5904a411c86f..6f16b39f0b52 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -191,70 +191,145 @@ void register_inmem_page(struct inode *inode, struct page *page)
 	trace_f2fs_register_inmem_page(page, INMEM);
 }
 
-int commit_inmem_pages(struct inode *inode, bool abort)
+static int __revoke_inmem_pages(struct inode *inode,
+				struct list_head *head, bool drop, bool recover)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct inmem_pages *cur, *tmp;
+	int err = 0;
+
+	list_for_each_entry_safe(cur, tmp, head, list) {
+		struct page *page = cur->page;
+
+		if (drop)
+			trace_f2fs_commit_inmem_page(page, INMEM_DROP);
+
+		lock_page(page);
+
+		if (recover) {
+			struct dnode_of_data dn;
+			struct node_info ni;
+
+			trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
+
+			set_new_dnode(&dn, inode, NULL, NULL, 0);
+			if (get_dnode_of_data(&dn, page->index, LOOKUP_NODE)) {
+				err = -EAGAIN;
+				goto next;
+			}
+			get_node_info(sbi, dn.nid, &ni);
+			f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+					cur->old_addr, ni.version, true, true);
+			f2fs_put_dnode(&dn);
+		}
+next:
+		ClearPageUptodate(page);
+		set_page_private(page, 0);
+		ClearPageUptodate(page);
+		f2fs_put_page(page, 1);
+
+		list_del(&cur->list);
+		kmem_cache_free(inmem_entry_slab, cur);
+		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+	}
+	return err;
+}
+
+void drop_inmem_pages(struct inode *inode)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+
+	mutex_lock(&fi->inmem_lock);
+	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
+	mutex_unlock(&fi->inmem_lock);
+}
+
+static int __commit_inmem_pages(struct inode *inode,
+					struct list_head *revoke_list)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct inmem_pages *cur, *tmp;
-	bool submit_bio = false;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
 		.encrypted_page = NULL,
 	};
+	bool submit_bio = false;
 	int err = 0;
 
-	/*
-	 * The abort is true only when f2fs_evict_inode is called.
-	 * Basically, the f2fs_evict_inode doesn't produce any data writes, so
-	 * that we don't need to call f2fs_balance_fs.
-	 * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this
-	 * inode becomes free by iget_locked in f2fs_iget.
-	 */
-	if (!abort) {
-		f2fs_balance_fs(sbi, true);
-		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) {
-			if (cur->page->mapping == inode->i_mapping) {
-				set_page_dirty(cur->page);
-				f2fs_wait_on_page_writeback(cur->page, DATA);
-				if (clear_page_dirty_for_io(cur->page))
-					inode_dec_dirty_pages(inode);
-				trace_f2fs_commit_inmem_page(cur->page, INMEM);
-				fio.page = cur->page;
-				err = do_write_data_page(&fio);
-				if (err) {
-					unlock_page(cur->page);
-					break;
-				}
-				clear_cold_data(cur->page);
-				submit_bio = true;
+		struct page *page = cur->page;
+
+		lock_page(page);
+		if (page->mapping == inode->i_mapping) {
+			trace_f2fs_commit_inmem_page(page, INMEM);
+
+			set_page_dirty(page);
+			f2fs_wait_on_page_writeback(page, DATA, true);
+			if (clear_page_dirty_for_io(page))
+				inode_dec_dirty_pages(inode);
+
+			fio.page = page;
+			err = do_write_data_page(&fio);
+			if (err) {
+				unlock_page(page);
+				break;
 			}
-		} else {
-			ClearPageUptodate(cur->page);
-			trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP);
+
+			/* record old blkaddr for revoking */
+			cur->old_addr = fio.old_blkaddr;
+
+			clear_cold_data(page);
+			submit_bio = true;
 		}
-		set_page_private(cur->page, 0);
-		ClearPagePrivate(cur->page);
-		f2fs_put_page(cur->page, 1);
+		unlock_page(page);
+		list_move_tail(&cur->list, revoke_list);
+	}
 
-		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_cond(sbi, inode, NULL, 0, DATA, WRITE);
+
+	if (!err)
+		__revoke_inmem_pages(inode, revoke_list, false, false);
+
+	return err;
+}
+
+int commit_inmem_pages(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct list_head revoke_list;
+	int err;
+
+	INIT_LIST_HEAD(&revoke_list);
+	f2fs_balance_fs(sbi, true);
+	f2fs_lock_op(sbi);
+
+	mutex_lock(&fi->inmem_lock);
+	err = __commit_inmem_pages(inode, &revoke_list);
+	if (err) {
+		int ret;
+		/*
+		 * try to revoke all committed pages, but still we could fail
+		 * due to no memory or other reason, if that happened, EAGAIN
+		 * will be returned, which means in such case, transaction is
+		 * already not integrity, caller should use journal to do the
+		 * recovery or rewrite & commit last transaction. For other
+		 * error number, revoking was done by filesystem itself.
+		 */
+		ret = __revoke_inmem_pages(inode, &revoke_list, false, true);
+		if (ret)
+			err = ret;
+
+		/* drop all uncommitted pages */
+		__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
 	}
 	mutex_unlock(&fi->inmem_lock);
 
-	if (!abort) {
-		f2fs_unlock_op(sbi);
-		if (submit_bio)
-			f2fs_submit_merged_bio(sbi, DATA, WRITE);
-	}
+	f2fs_unlock_op(sbi);
 	return err;
 }
 
@@ -291,11 +366,17 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 
 	/* checkpoint is the only way to shrink partial cached entries */
 	if (!available_free_memory(sbi, NAT_ENTRIES) ||
-			excess_prefree_segs(sbi) ||
 			!available_free_memory(sbi, INO_ENTRIES) ||
+			excess_prefree_segs(sbi) ||
+			excess_dirty_nats(sbi) ||
 			(is_idle(sbi) && f2fs_time_over(sbi, CP_TIME))) {
-		if (test_opt(sbi, DATA_FLUSH))
+		if (test_opt(sbi, DATA_FLUSH)) {
+			struct blk_plug plug;
+
+			blk_start_plug(&plug);
 			sync_dirty_inodes(sbi, FILE_INODE);
+			blk_finish_plug(&plug);
+		}
 		f2fs_sync_fs(sbi->sb, true);
 		stat_inc_bg_cp_count(sbi->stat_info);
 	}
@@ -502,7 +583,7 @@ static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 
 bool discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
 {
-	int err = -ENOTSUPP;
+	int err = -EOPNOTSUPP;
 
 	if (test_opt(sbi, DISCARD)) {
 		struct seg_entry *se = get_seg_entry(sbi,
@@ -841,6 +922,31 @@ static void write_sum_page(struct f2fs_sb_info *sbi,
 	update_meta_page(sbi, (void *)sum_blk, blk_addr);
 }
 
+static void write_current_sum_page(struct f2fs_sb_info *sbi,
+						int type, block_t blk_addr)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	struct page *page = grab_meta_page(sbi, blk_addr);
+	struct f2fs_summary_block *src = curseg->sum_blk;
+	struct f2fs_summary_block *dst;
+
+	dst = (struct f2fs_summary_block *)page_address(page);
+
+	mutex_lock(&curseg->curseg_mutex);
+
+	down_read(&curseg->journal_rwsem);
+	memcpy(&dst->journal, curseg->journal, SUM_JOURNAL_SIZE);
+	up_read(&curseg->journal_rwsem);
+
+	memcpy(dst->entries, src->entries, SUM_ENTRY_SIZE);
+	memcpy(&dst->footer, &src->footer, SUM_FOOTER_SIZE);
+
+	mutex_unlock(&curseg->curseg_mutex);
+
+	set_page_dirty(page);
+	f2fs_put_page(page, 1);
+}
+
 static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -873,9 +979,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 
 	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
 		segno = find_next_zero_bit(free_i->free_segmap,
-					MAIN_SEGS(sbi), *newseg + 1);
-		if (segno - *newseg < sbi->segs_per_sec -
-					(*newseg % sbi->segs_per_sec))
+				(hint + 1) * sbi->segs_per_sec, *newseg + 1);
+		if (segno < (hint + 1) * sbi->segs_per_sec)
 			goto got_it;
 	}
 find_other_zone:
@@ -1280,8 +1385,8 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(fio->page, fio->type);
 
-	allocate_data_block(fio->sbi, fio->page, fio->blk_addr,
-					&fio->blk_addr, sum, type);
+	allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
+					&fio->new_blkaddr, sum, type);
 
 	/* writeout dirty page into bdev */
 	f2fs_submit_page_mbio(fio);
@@ -1293,7 +1398,8 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 		.sbi = sbi,
 		.type = META,
 		.rw = WRITE_SYNC | REQ_META | REQ_PRIO,
-		.blk_addr = page->index,
+		.old_blkaddr = page->index,
+		.new_blkaddr = page->index,
 		.page = page,
 		.encrypted_page = NULL,
 	};
@@ -1323,19 +1429,19 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 	do_write_page(&sum, fio);
-	dn->data_blkaddr = fio->blk_addr;
+	f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
 }
 
 void rewrite_data_page(struct f2fs_io_info *fio)
 {
+	fio->new_blkaddr = fio->old_blkaddr;
 	stat_inc_inplace_blocks(fio->sbi);
 	f2fs_submit_page_mbio(fio);
 }
 
-static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
-				struct f2fs_summary *sum,
+void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 				block_t old_blkaddr, block_t new_blkaddr,
-				bool recover_curseg)
+				bool recover_curseg, bool recover_newaddr)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg;
@@ -1378,7 +1484,7 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
 	curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
 	__add_sum_entry(sbi, type, sum);
 
-	if (!recover_curseg)
+	if (!recover_curseg || recover_newaddr)
 		update_sit_entry(sbi, new_blkaddr, 1);
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
 		update_sit_entry(sbi, old_blkaddr, -1);
@@ -1402,66 +1508,30 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
 
 void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 				block_t old_addr, block_t new_addr,
-				unsigned char version, bool recover_curseg)
+				unsigned char version, bool recover_curseg,
+				bool recover_newaddr)
 {
 	struct f2fs_summary sum;
 
 	set_summary(&sum, dn->nid, dn->ofs_in_node, version);
 
-	__f2fs_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg);
+	__f2fs_replace_block(sbi, &sum, old_addr, new_addr,
+					recover_curseg, recover_newaddr);
 
-	dn->data_blkaddr = new_addr;
-	set_data_blkaddr(dn);
-	f2fs_update_extent_cache(dn);
-}
-
-static inline bool is_merged_page(struct f2fs_sb_info *sbi,
-					struct page *page, enum page_type type)
-{
-	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io = &sbi->write_io[btype];
-	struct bio_vec *bvec;
-	struct page *target;
-	int i;
-
-	down_read(&io->io_rwsem);
-	if (!io->bio) {
-		up_read(&io->io_rwsem);
-		return false;
-	}
-
-	bio_for_each_segment_all(bvec, io->bio, i) {
-
-		if (bvec->bv_page->mapping) {
-			target = bvec->bv_page;
-		} else {
-			struct f2fs_crypto_ctx *ctx;
-
-			/* encrypted page */
-			ctx = (struct f2fs_crypto_ctx *)page_private(
-								bvec->bv_page);
-			target = ctx->w.control_page;
-		}
-
-		if (page == target) {
-			up_read(&io->io_rwsem);
-			return true;
-		}
-	}
-
-	up_read(&io->io_rwsem);
-	return false;
+	f2fs_update_data_blkaddr(dn, new_addr);
 }
 
 void f2fs_wait_on_page_writeback(struct page *page,
-				enum page_type type)
+				enum page_type type, bool ordered)
 {
 	if (PageWriteback(page)) {
 		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 
-		if (is_merged_page(sbi, page, type))
-			f2fs_submit_merged_bio(sbi, type, WRITE);
-		wait_on_page_writeback(page);
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, type, WRITE);
+		if (ordered)
+			wait_on_page_writeback(page);
+		else
+			wait_for_stable_page(page);
 	}
 }
 
@@ -1477,7 +1547,7 @@ void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
 
 	cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
 	if (cpage) {
-		f2fs_wait_on_page_writeback(cpage, DATA);
+		f2fs_wait_on_page_writeback(cpage, DATA, true);
 		f2fs_put_page(cpage, 1);
 	}
 }
@@ -1498,12 +1568,11 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
 
 	/* Step 1: restore nat cache */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	memcpy(&seg_i->sum_blk->n_nats, kaddr, SUM_JOURNAL_SIZE);
+	memcpy(seg_i->journal, kaddr, SUM_JOURNAL_SIZE);
 
 	/* Step 2: restore sit cache */
 	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	memcpy(&seg_i->sum_blk->n_sits, kaddr + SUM_JOURNAL_SIZE,
-						SUM_JOURNAL_SIZE);
+	memcpy(seg_i->journal, kaddr + SUM_JOURNAL_SIZE, SUM_JOURNAL_SIZE);
 	offset = 2 * SUM_JOURNAL_SIZE;
 
 	/* Step 3: restore summary entries */
@@ -1599,7 +1668,14 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	/* set uncompleted segment to curseg */
 	curseg = CURSEG_I(sbi, type);
 	mutex_lock(&curseg->curseg_mutex);
-	memcpy(curseg->sum_blk, sum, PAGE_CACHE_SIZE);
+
+	/* update journal info */
+	down_write(&curseg->journal_rwsem);
+	memcpy(curseg->journal, &sum->journal, SUM_JOURNAL_SIZE);
+	up_write(&curseg->journal_rwsem);
+
+	memcpy(curseg->sum_blk->entries, sum->entries, SUM_ENTRY_SIZE);
+	memcpy(&curseg->sum_blk->footer, &sum->footer, SUM_FOOTER_SIZE);
 	curseg->next_segno = segno;
 	reset_curseg(sbi, type, 0);
 	curseg->alloc_type = ckpt->alloc_type[type];
@@ -1654,13 +1730,12 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
 
 	/* Step 1: write nat cache */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	memcpy(kaddr, &seg_i->sum_blk->n_nats, SUM_JOURNAL_SIZE);
+	memcpy(kaddr, seg_i->journal, SUM_JOURNAL_SIZE);
 	written_size += SUM_JOURNAL_SIZE;
 
 	/* Step 2: write sit cache */
 	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	memcpy(kaddr + written_size, &seg_i->sum_blk->n_sits,
-						SUM_JOURNAL_SIZE);
+	memcpy(kaddr + written_size, seg_i->journal, SUM_JOURNAL_SIZE);
 	written_size += SUM_JOURNAL_SIZE;
 
 	/* Step 3: write summary entries */
@@ -1706,12 +1781,8 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi,
 	else
 		end = type + NR_CURSEG_NODE_TYPE;
 
-	for (i = type; i < end; i++) {
-		struct curseg_info *sum = CURSEG_I(sbi, i);
-		mutex_lock(&sum->curseg_mutex);
-		write_sum_page(sbi, sum->sum_blk, blkaddr + (i - type));
-		mutex_unlock(&sum->curseg_mutex);
-	}
+	for (i = type; i < end; i++)
+		write_current_sum_page(sbi, i, blkaddr + (i - type));
 }
 
 void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
@@ -1727,24 +1798,24 @@ void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 	write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
 }
 
-int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
+int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
 					unsigned int val, int alloc)
 {
 	int i;
 
 	if (type == NAT_JOURNAL) {
-		for (i = 0; i < nats_in_cursum(sum); i++) {
-			if (le32_to_cpu(nid_in_journal(sum, i)) == val)
+		for (i = 0; i < nats_in_cursum(journal); i++) {
+			if (le32_to_cpu(nid_in_journal(journal, i)) == val)
 				return i;
 		}
-		if (alloc && __has_cursum_space(sum, 1, NAT_JOURNAL))
-			return update_nats_in_cursum(sum, 1);
+		if (alloc && __has_cursum_space(journal, 1, NAT_JOURNAL))
+			return update_nats_in_cursum(journal, 1);
 	} else if (type == SIT_JOURNAL) {
-		for (i = 0; i < sits_in_cursum(sum); i++)
-			if (le32_to_cpu(segno_in_journal(sum, i)) == val)
+		for (i = 0; i < sits_in_cursum(journal); i++)
+			if (le32_to_cpu(segno_in_journal(journal, i)) == val)
 				return i;
-		if (alloc && __has_cursum_space(sum, 1, SIT_JOURNAL))
-			return update_sits_in_cursum(sum, 1);
+		if (alloc && __has_cursum_space(journal, 1, SIT_JOURNAL))
+			return update_sits_in_cursum(journal, 1);
 	}
 	return -1;
 }
@@ -1848,20 +1919,22 @@ static void add_sits_in_set(struct f2fs_sb_info *sbi)
 static void remove_sits_in_journal(struct f2fs_sb_info *sbi)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	int i;
 
-	for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
+	down_write(&curseg->journal_rwsem);
+	for (i = 0; i < sits_in_cursum(journal); i++) {
 		unsigned int segno;
 		bool dirtied;
 
-		segno = le32_to_cpu(segno_in_journal(sum, i));
+		segno = le32_to_cpu(segno_in_journal(journal, i));
 		dirtied = __mark_sit_entry_dirty(sbi, segno);
 
 		if (!dirtied)
 			add_sit_entry(segno, &SM_I(sbi)->sit_entry_set);
 	}
-	update_sits_in_cursum(sum, -sits_in_cursum(sum));
+	update_sits_in_cursum(journal, -i);
+	up_write(&curseg->journal_rwsem);
 }
 
 /*
@@ -1873,13 +1946,12 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct sit_info *sit_i = SIT_I(sbi);
 	unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	struct sit_entry_set *ses, *tmp;
 	struct list_head *head = &SM_I(sbi)->sit_entry_set;
 	bool to_journal = true;
 	struct seg_entry *se;
 
-	mutex_lock(&curseg->curseg_mutex);
 	mutex_lock(&sit_i->sentry_lock);
 
 	if (!sit_i->dirty_sentries)
@@ -1896,7 +1968,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 * entries, remove all entries from journal and add and account
 	 * them in sit entry set.
 	 */
-	if (!__has_cursum_space(sum, sit_i->dirty_sentries, SIT_JOURNAL))
+	if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL))
 		remove_sits_in_journal(sbi);
 
 	/*
@@ -1913,10 +1985,12 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		unsigned int segno = start_segno;
 
 		if (to_journal &&
-			!__has_cursum_space(sum, ses->entry_cnt, SIT_JOURNAL))
+			!__has_cursum_space(journal, ses->entry_cnt, SIT_JOURNAL))
 			to_journal = false;
 
-		if (!to_journal) {
+		if (to_journal) {
+			down_write(&curseg->journal_rwsem);
+		} else {
 			page = get_next_sit_page(sbi, start_segno);
 			raw_sit = page_address(page);
 		}
@@ -1934,13 +2008,13 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			}
 
 			if (to_journal) {
-				offset = lookup_journal_in_cursum(sum,
+				offset = lookup_journal_in_cursum(journal,
 							SIT_JOURNAL, segno, 1);
 				f2fs_bug_on(sbi, offset < 0);
-				segno_in_journal(sum, offset) =
+				segno_in_journal(journal, offset) =
 							cpu_to_le32(segno);
 				seg_info_to_raw_sit(se,
-						&sit_in_journal(sum, offset));
+					&sit_in_journal(journal, offset));
 			} else {
 				sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
 				seg_info_to_raw_sit(se,
@@ -1952,7 +2026,9 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			ses->entry_cnt--;
 		}
 
-		if (!to_journal)
+		if (to_journal)
+			up_write(&curseg->journal_rwsem);
+		else
 			f2fs_put_page(page, 1);
 
 		f2fs_bug_on(sbi, ses->entry_cnt);
@@ -1967,7 +2043,6 @@ out:
 			add_discard_addrs(sbi, cpc);
 	}
 	mutex_unlock(&sit_i->sentry_lock);
-	mutex_unlock(&curseg->curseg_mutex);
 
 	set_prefree_as_free_segments(sbi);
 }
@@ -2099,6 +2174,11 @@ static int build_curseg(struct f2fs_sb_info *sbi)
 		array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
 		if (!array[i].sum_blk)
 			return -ENOMEM;
+		init_rwsem(&array[i].journal_rwsem);
+		array[i].journal = kzalloc(sizeof(struct f2fs_journal),
+							GFP_KERNEL);
+		if (!array[i].journal)
+			return -ENOMEM;
 		array[i].segno = NULL_SEGNO;
 		array[i].next_blkoff = 0;
 	}
@@ -2109,11 +2189,11 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	int sit_blk_cnt = SIT_BLK_CNT(sbi);
 	unsigned int i, start, end;
 	unsigned int readed, start_blk = 0;
-	int nrpages = MAX_BIO_BLOCKS(sbi);
+	int nrpages = MAX_BIO_BLOCKS(sbi) * 8;
 
 	do {
 		readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
@@ -2127,16 +2207,16 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 			struct f2fs_sit_entry sit;
 			struct page *page;
 
-			mutex_lock(&curseg->curseg_mutex);
-			for (i = 0; i < sits_in_cursum(sum); i++) {
-				if (le32_to_cpu(segno_in_journal(sum, i))
+			down_read(&curseg->journal_rwsem);
+			for (i = 0; i < sits_in_cursum(journal); i++) {
+				if (le32_to_cpu(segno_in_journal(journal, i))
 								== start) {
-					sit = sit_in_journal(sum, i);
-					mutex_unlock(&curseg->curseg_mutex);
+					sit = sit_in_journal(journal, i);
+					up_read(&curseg->journal_rwsem);
 					goto got_it;
 				}
 			}
-			mutex_unlock(&curseg->curseg_mutex);
+			up_read(&curseg->journal_rwsem);
 
 			page = get_current_sit_page(sbi, start);
 			sit_blk = (struct f2fs_sit_block *)page_address(page);
@@ -2371,8 +2451,10 @@ static void destroy_curseg(struct f2fs_sb_info *sbi)
 	if (!array)
 		return;
 	SM_I(sbi)->curseg_array = NULL;
-	for (i = 0; i < NR_CURSEG_TYPE; i++)
+	for (i = 0; i < NR_CURSEG_TYPE; i++) {
 		kfree(array[i].sum_blk);
+		kfree(array[i].journal);
+	}
 	kfree(array);
 }
 
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index ee44d346ea44..975c33df65c7 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -183,7 +183,7 @@ struct segment_allocation {
  * this value is set in page as a private data which indicate that
  * the page is atomically written, and it is in inmem_pages list.
  */
-#define ATOMIC_WRITTEN_PAGE		0x0000ffff
+#define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
 
 #define IS_ATOMIC_WRITTEN_PAGE(page)			\
 		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
@@ -191,6 +191,7 @@ struct segment_allocation {
 struct inmem_pages {
 	struct list_head list;
 	struct page *page;
+	block_t old_addr;		/* for revoking when fail to commit */
 };
 
 struct sit_info {
@@ -257,6 +258,8 @@ struct victim_selection {
 struct curseg_info {
 	struct mutex curseg_mutex;		/* lock for consistency */
 	struct f2fs_summary_block *sum_blk;	/* cached summary block */
+	struct rw_semaphore journal_rwsem;	/* protect journal area */
+	struct f2fs_journal *journal;		/* cached journal info */
 	unsigned char alloc_type;		/* current allocation type */
 	unsigned int segno;			/* current segment number */
 	unsigned short next_blkoff;		/* next block offset to write */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 6134832baaaf..15bb81f8dac2 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -126,6 +126,19 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
 	return NULL;
 }
 
+static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	struct super_block *sb = sbi->sb;
+
+	if (!sb->s_bdev->bd_part)
+		return snprintf(buf, PAGE_SIZE, "0\n");
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+		(unsigned long long)(sbi->kbytes_written +
+			BD_PART_WRITTEN(sbi)));
+}
+
 static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 			struct f2fs_sb_info *sbi, char *buf)
 {
@@ -204,6 +217,9 @@ static struct f2fs_attr f2fs_attr_##_name = {			\
 		f2fs_sbi_show, f2fs_sbi_store,			\
 		offsetof(struct struct_name, elname))
 
+#define F2FS_GENERAL_RO_ATTR(name) \
+static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
+
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
@@ -216,10 +232,12 @@ 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);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
@@ -237,8 +255,10 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(dir_level),
 	ATTR_LIST(ram_thresh),
 	ATTR_LIST(ra_nid_pages),
+	ATTR_LIST(dirty_nats_ratio),
 	ATTR_LIST(cp_interval),
 	ATTR_LIST(idle_interval),
+	ATTR_LIST(lifetime_write_kbytes),
 	NULL,
 };
 
@@ -450,10 +470,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 
 	/* Will be used by directory only */
 	fi->i_dir_level = F2FS_SB(sb)->dir_level;
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	fi->i_crypt_info = NULL;
-#endif
 	return &fi->vfs_inode;
 }
 
@@ -474,7 +490,7 @@ static int f2fs_drop_inode(struct inode *inode)
 
 			/* some remained atomic pages should discarded */
 			if (f2fs_is_atomic_file(inode))
-				commit_inmem_pages(inode, true);
+				drop_inmem_pages(inode);
 
 			/* should remain fi->extent_tree for writepage */
 			f2fs_destroy_extent_node(inode);
@@ -487,11 +503,7 @@ static int f2fs_drop_inode(struct inode *inode)
 
 			sb_end_intwrite(inode->i_sb);
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-			if (F2FS_I(inode)->i_crypt_info)
-				f2fs_free_encryption_info(inode,
-					F2FS_I(inode)->i_crypt_info);
-#endif
+			fscrypt_put_encryption_info(inode, NULL);
 			spin_lock(&inode->i_lock);
 			atomic_dec(&inode->i_count);
 		}
@@ -562,6 +574,10 @@ static void f2fs_put_super(struct super_block *sb)
 	f2fs_leave_shrinker(sbi);
 	mutex_unlock(&sbi->umount_mutex);
 
+	/* our cp_error case, we can wait for any writeback page */
+	if (get_pages(sbi, F2FS_WRITEBACK))
+		f2fs_flush_merged_bios(sbi);
+
 	iput(sbi->node_inode);
 	iput(sbi->meta_inode);
 
@@ -574,6 +590,8 @@ static void f2fs_put_super(struct super_block *sb)
 	wait_for_completion(&sbi->s_kobj_unregister);
 
 	sb->s_fs_info = NULL;
+	if (sbi->s_chksum_driver)
+		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->raw_super);
 	kfree(sbi);
 }
@@ -766,8 +784,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	bool need_stop_gc = false;
 	bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
 
-	sync_filesystem(sb);
-
 	/*
 	 * Save the old mount options in case we
 	 * need to restore them.
@@ -775,6 +791,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	org_mount_opt = sbi->mount_opt;
 	active_logs = sbi->active_logs;
 
+	if (*flags & MS_RDONLY) {
+		set_opt(sbi, FASTBOOT);
+		set_sbi_flag(sbi, SBI_IS_DIRTY);
+	}
+
+	sync_filesystem(sb);
+
 	sbi->mount_opt.opt = 0;
 	default_options(sbi);
 
@@ -862,6 +885,41 @@ static struct super_operations f2fs_sops = {
 	.remount_fs	= f2fs_remount,
 };
 
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+static int f2fs_get_context(struct inode *inode, void *ctx, size_t len)
+{
+	return f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+				ctx, len, NULL);
+}
+
+static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
+							void *fs_data)
+{
+	return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+				ctx, len, fs_data, XATTR_CREATE);
+}
+
+static unsigned f2fs_max_namelen(struct inode *inode)
+{
+	return S_ISLNK(inode->i_mode) ?
+			inode->i_sb->s_blocksize : F2FS_NAME_LEN;
+}
+
+static struct fscrypt_operations f2fs_cryptops = {
+	.get_context	= f2fs_get_context,
+	.set_context	= f2fs_set_context,
+	.is_encrypted	= f2fs_encrypted_inode,
+	.empty_dir	= f2fs_empty_dir,
+	.max_namelen	= f2fs_max_namelen,
+};
+#else
+static struct fscrypt_operations f2fs_cryptops = {
+	.is_encrypted	= f2fs_encrypted_inode,
+};
+#endif
+
 static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
 		u64 ino, u32 generation)
 {
@@ -1074,7 +1132,7 @@ static int sanity_check_raw_super(struct super_block *sb,
 	return 0;
 }
 
-static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
+int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 {
 	unsigned int total, fsmeta;
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
@@ -1134,14 +1192,15 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 
 /*
  * Read f2fs raw super block.
- * Because we have two copies of super block, so read the first one at first,
- * if the first one is invalid, move to read the second one.
+ * Because we have two copies of super block, so read both of them
+ * to get the first valid one. If any one of them is broken, we pass
+ * them recovery flag back to the caller.
  */
 static int read_raw_super_block(struct super_block *sb,
 			struct f2fs_super_block **raw_super,
 			int *valid_super_block, int *recovery)
 {
-	int block = 0;
+	int block;
 	struct buffer_head *bh;
 	struct f2fs_super_block *super, *buf;
 	int err = 0;
@@ -1149,50 +1208,48 @@ static int read_raw_super_block(struct super_block *sb,
 	super = kzalloc(sizeof(struct f2fs_super_block), GFP_KERNEL);
 	if (!super)
 		return -ENOMEM;
-retry:
-	bh = sb_bread(sb, block);
-	if (!bh) {
-		*recovery = 1;
-		f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
+
+	for (block = 0; block < 2; block++) {
+		bh = sb_bread(sb, block);
+		if (!bh) {
+			f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
 				block + 1);
-		err = -EIO;
-		goto next;
-	}
+			err = -EIO;
+			continue;
+		}
 
-	buf = (struct f2fs_super_block *)(bh->b_data + F2FS_SUPER_OFFSET);
+		buf = (struct f2fs_super_block *)
+				(bh->b_data + F2FS_SUPER_OFFSET);
 
-	/* sanity checking of raw super */
-	if (sanity_check_raw_super(sb, buf)) {
-		brelse(bh);
-		*recovery = 1;
-		f2fs_msg(sb, KERN_ERR,
-			"Can't find valid F2FS filesystem in %dth superblock",
-								block + 1);
-		err = -EINVAL;
-		goto next;
-	}
+		/* sanity checking of raw super */
+		if (sanity_check_raw_super(sb, buf)) {
+			f2fs_msg(sb, KERN_ERR,
+				"Can't find valid F2FS filesystem in %dth superblock",
+				block + 1);
+			err = -EINVAL;
+			brelse(bh);
+			continue;
+		}
 
-	if (!*raw_super) {
-		memcpy(super, buf, sizeof(*super));
-		*valid_super_block = block;
-		*raw_super = super;
+		if (!*raw_super) {
+			memcpy(super, buf, sizeof(*super));
+			*valid_super_block = block;
+			*raw_super = super;
+		}
+		brelse(bh);
 	}
-	brelse(bh);
 
-next:
-	/* check the validity of the second superblock */
-	if (block == 0) {
-		block++;
-		goto retry;
-	}
+	/* Fail to read any one of the superblocks*/
+	if (err < 0)
+		*recovery = 1;
 
 	/* No valid superblock */
-	if (!*raw_super) {
+	if (!*raw_super)
 		kfree(super);
-		return err;
-	}
+	else
+		err = 0;
 
-	return 0;
+	return err;
 }
 
 static int __f2fs_commit_super(struct f2fs_sb_info *sbi, int block)
@@ -1242,6 +1299,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	bool retry = true, need_fsck = false;
 	char *options = NULL;
 	int recovery, i, valid_super_block;
+	struct curseg_info *seg_i;
 
 try_onemore:
 	err = -EINVAL;
@@ -1254,6 +1312,15 @@ try_onemore:
 	if (!sbi)
 		return -ENOMEM;
 
+	/* Load the checksum driver */
+	sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0);
+	if (IS_ERR(sbi->s_chksum_driver)) {
+		f2fs_msg(sb, KERN_ERR, "Cannot load crc32 driver.");
+		err = PTR_ERR(sbi->s_chksum_driver);
+		sbi->s_chksum_driver = NULL;
+		goto free_sbi;
+	}
+
 	/* set a block size */
 	if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) {
 		f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
@@ -1285,6 +1352,7 @@ try_onemore:
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 
 	sb->s_op = &f2fs_sops;
+	sb->s_cop = &f2fs_cryptops;
 	sb->s_xattr = f2fs_xattr_handlers;
 	sb->s_export_op = &f2fs_export_ops;
 	sb->s_magic = F2FS_SUPER_MAGIC;
@@ -1333,13 +1401,6 @@ try_onemore:
 		goto free_meta_inode;
 	}
 
-	/* sanity checking of checkpoint */
-	err = -EINVAL;
-	if (sanity_check_ckpt(sbi)) {
-		f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
-		goto free_cp;
-	}
-
 	sbi->total_valid_node_count =
 				le32_to_cpu(sbi->ckpt->valid_node_count);
 	sbi->total_valid_inode_count =
@@ -1372,6 +1433,17 @@ try_onemore:
 		goto free_nm;
 	}
 
+	/* For write statistics */
+	if (sb->s_bdev->bd_part)
+		sbi->sectors_written_start =
+			(u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+
+	/* Read accumulated write IO statistics if exists */
+	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+	if (__exist_node_summaries(sbi))
+		sbi->kbytes_written =
+			le64_to_cpu(seg_i->sum_blk->journal.info.kbytes_written);
+
 	build_gc_manager(sbi);
 
 	/* get an inode for node space */
@@ -1466,8 +1538,10 @@ try_onemore:
 
 	/* recover broken superblock */
 	if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
-		f2fs_msg(sb, KERN_INFO, "Recover invalid superblock");
-		f2fs_commit_super(sbi, true);
+		err = f2fs_commit_super(sbi, true);
+		f2fs_msg(sb, KERN_INFO,
+			"Try to recover %dth superblock, ret: %ld",
+			sbi->valid_super_block ? 1 : 2, err);
 	}
 
 	f2fs_update_time(sbi, CP_TIME);
@@ -1496,7 +1570,6 @@ free_nm:
 	destroy_node_manager(sbi);
 free_sm:
 	destroy_segment_manager(sbi);
-free_cp:
 	kfree(sbi->ckpt);
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
@@ -1506,6 +1579,8 @@ free_options:
 free_sb_buf:
 	kfree(raw_super);
 free_sbi:
+	if (sbi->s_chksum_driver)
+		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi);
 
 	/* give only one another chance */
@@ -1585,13 +1660,9 @@ static int __init init_f2fs_fs(void)
 		err = -ENOMEM;
 		goto free_extent_cache;
 	}
-	err = f2fs_init_crypto();
-	if (err)
-		goto free_kset;
-
 	err = register_shrinker(&f2fs_shrinker_info);
 	if (err)
-		goto free_crypto;
+		goto free_kset;
 
 	err = register_filesystem(&f2fs_fs_type);
 	if (err)
@@ -1606,8 +1677,6 @@ free_filesystem:
 	unregister_filesystem(&f2fs_fs_type);
 free_shrinker:
 	unregister_shrinker(&f2fs_shrinker_info);
-free_crypto:
-	f2fs_exit_crypto();
 free_kset:
 	kset_unregister(f2fs_kset);
 free_extent_cache:
@@ -1630,7 +1699,6 @@ static void __exit exit_f2fs_fs(void)
 	f2fs_destroy_root_stats();
 	unregister_shrinker(&f2fs_shrinker_info);
 	unregister_filesystem(&f2fs_fs_type);
-	f2fs_exit_crypto();
 	destroy_extent_cache();
 	destroy_checkpoint_caches();
 	destroy_segment_manager_caches();
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
index 145fb659ad44..562ce0821559 100644
--- a/fs/f2fs/trace.c
+++ b/fs/f2fs/trace.c
@@ -29,7 +29,8 @@ static inline void __print_last_io(void)
 			last_io.major, last_io.minor,
 			last_io.pid, "----------------",
 			last_io.type,
-			last_io.fio.rw, last_io.fio.blk_addr,
+			last_io.fio.rw,
+			last_io.fio.new_blkaddr,
 			last_io.len);
 	memset(&last_io, 0, sizeof(last_io));
 }
@@ -101,7 +102,8 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
 			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.fio.new_blkaddr + last_io.len ==
+							fio->new_blkaddr) {
 		last_io.len++;
 		return;
 	}
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 10f1e784fa23..06a72dc0191a 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -300,7 +300,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 
 		if (ipage) {
 			inline_addr = inline_xattr_addr(ipage);
-			f2fs_wait_on_page_writeback(ipage, NODE);
+			f2fs_wait_on_page_writeback(ipage, NODE, true);
 		} else {
 			page = get_node_page(sbi, inode->i_ino);
 			if (IS_ERR(page)) {
@@ -308,7 +308,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 				return PTR_ERR(page);
 			}
 			inline_addr = inline_xattr_addr(page);
-			f2fs_wait_on_page_writeback(page, NODE);
+			f2fs_wait_on_page_writeback(page, NODE, true);
 		}
 		memcpy(inline_addr, txattr_addr, inline_size);
 		f2fs_put_page(page, 1);
@@ -329,7 +329,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 			return PTR_ERR(xpage);
 		}
 		f2fs_bug_on(sbi, new_nid);
-		f2fs_wait_on_page_writeback(xpage, NODE);
+		f2fs_wait_on_page_writeback(xpage, NODE, true);
 	} else {
 		struct dnode_of_data dn;
 		set_new_dnode(&dn, inode, NULL, NULL, new_nid);
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index 79dccc8252dd..f990de20cdcd 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -126,7 +126,8 @@ extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
 
 #define f2fs_xattr_handlers	NULL
 static inline int f2fs_setxattr(struct inode *inode, int index,
-		const char *name, const void *value, size_t size, int flags)
+		const char *name, const void *value, size_t size,
+		struct page *page, int flags)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig
index 182f9ffe2b51..3ff1772f612e 100644
--- a/fs/fat/Kconfig
+++ b/fs/fat/Kconfig
@@ -93,8 +93,24 @@ config FAT_DEFAULT_IOCHARSET
 	  that most of your FAT filesystems use, and can be overridden
 	  with the "iocharset" mount option for FAT filesystems.
 	  Note that "utf8" is not recommended for FAT filesystems.
-	  If unsure, you shouldn't set "utf8" here.
+	  If unsure, you shouldn't set "utf8" here - select the next option
+	  instead if you would like to use UTF-8 encoded file names by default.
 	  See <file:Documentation/filesystems/vfat.txt> for more information.
 
 	  Enable any character sets you need in File Systems/Native Language
 	  Support.
+
+config FAT_DEFAULT_UTF8
+	bool "Enable FAT UTF-8 option by default"
+	depends on VFAT_FS
+	default n
+	help
+	  Set this if you would like to have "utf8" mount option set
+	  by default when mounting FAT filesystems.
+
+	  Even if you say Y here can always disable UTF-8 for
+	  particular mount by adding "utf8=0" to mount options.
+
+	  Say Y if you use UTF-8 encoding for file names, N otherwise.
+
+	  See <file:Documentation/filesystems/vfat.txt> for more information.
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index a5599052116c..226281068a46 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1127,7 +1127,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 	}
 	opts->name_check = 'n';
 	opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK =  0;
-	opts->utf8 = opts->unicode_xlate = 0;
+	opts->unicode_xlate = 0;
 	opts->numtail = 1;
 	opts->usefree = opts->nocase = 0;
 	opts->tz_set = 0;
@@ -1135,6 +1135,8 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 	opts->errors = FAT_ERRORS_RO;
 	*debug = 0;
 
+	opts->utf8 = IS_ENABLED(CONFIG_FAT_DEFAULT_UTF8) && is_vfat;
+
 	if (!options)
 		goto out;
 
diff --git a/fs/fhandle.c b/fs/fhandle.c
index d59712dfa3e7..ca3c3dd01789 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -228,7 +228,7 @@ long do_handle_open(int mountdirfd,
 		path_put(&path);
 		return fd;
 	}
-	file = file_open_root(path.dentry, path.mnt, "", open_flag);
+	file = file_open_root(path.dentry, path.mnt, "", open_flag, 0);
 	if (IS_ERR(file)) {
 		put_unused_fd(fd);
 		retval =  PTR_ERR(file);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 6915c950e6e8..fee81e8768c9 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -223,6 +223,9 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi,
 #define WB_FRN_HIST_MAX_SLOTS	(WB_FRN_HIST_THR_SLOTS / 2 + 1)
 					/* one round can affect upto 5 slots */
 
+static atomic_t isw_nr_in_flight = ATOMIC_INIT(0);
+static struct workqueue_struct *isw_wq;
+
 void __inode_attach_wb(struct inode *inode, struct page *page)
 {
 	struct backing_dev_info *bdi = inode_to_bdi(inode);
@@ -278,13 +281,15 @@ locked_inode_to_wb_and_lock_list(struct inode *inode)
 		wb_get(wb);
 		spin_unlock(&inode->i_lock);
 		spin_lock(&wb->list_lock);
-		wb_put(wb);		/* not gonna deref it anymore */
 
 		/* i_wb may have changed inbetween, can't use inode_to_wb() */
-		if (likely(wb == inode->i_wb))
-			return wb;	/* @inode already has ref */
+		if (likely(wb == inode->i_wb)) {
+			wb_put(wb);	/* @inode already has ref */
+			return wb;
+		}
 
 		spin_unlock(&wb->list_lock);
+		wb_put(wb);
 		cpu_relax();
 		spin_lock(&inode->i_lock);
 	}
@@ -424,6 +429,8 @@ skip_switch:
 
 	iput(inode);
 	kfree(isw);
+
+	atomic_dec(&isw_nr_in_flight);
 }
 
 static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
@@ -433,7 +440,7 @@ static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
 
 	/* needs to grab bh-unsafe locks, bounce to work item */
 	INIT_WORK(&isw->work, inode_switch_wbs_work_fn);
-	schedule_work(&isw->work);
+	queue_work(isw_wq, &isw->work);
 }
 
 /**
@@ -469,7 +476,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 
 	/* while holding I_WB_SWITCH, no one else can update the association */
 	spin_lock(&inode->i_lock);
-	if (inode->i_state & (I_WB_SWITCH | I_FREEING) ||
+	if (!(inode->i_sb->s_flags & MS_ACTIVE) ||
+	    inode->i_state & (I_WB_SWITCH | I_FREEING) ||
 	    inode_to_wb(inode) == isw->new_wb) {
 		spin_unlock(&inode->i_lock);
 		goto out_free;
@@ -480,6 +488,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 	ihold(inode);
 	isw->inode = inode;
 
+	atomic_inc(&isw_nr_in_flight);
+
 	/*
 	 * In addition to synchronizing among switchers, I_WB_SWITCH tells
 	 * the RCU protected stat update paths to grab the mapping's
@@ -840,6 +850,33 @@ restart:
 		wb_put(last_wb);
 }
 
+/**
+ * cgroup_writeback_umount - flush inode wb switches for umount
+ *
+ * This function is called when a super_block is about to be destroyed and
+ * flushes in-flight inode wb switches.  An inode wb switch goes through
+ * RCU and then workqueue, so the two need to be flushed in order to ensure
+ * that all previously scheduled switches are finished.  As wb switches are
+ * rare occurrences and synchronize_rcu() can take a while, perform
+ * flushing iff wb switches are in flight.
+ */
+void cgroup_writeback_umount(void)
+{
+	if (atomic_read(&isw_nr_in_flight)) {
+		synchronize_rcu();
+		flush_workqueue(isw_wq);
+	}
+}
+
+static int __init cgroup_writeback_init(void)
+{
+	isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0);
+	if (!isw_wq)
+		return -ENOMEM;
+	return 0;
+}
+fs_initcall(cgroup_writeback_init);
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static struct bdi_writeback *
@@ -1302,10 +1339,10 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
  * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode()
  * and does more profound writeback list handling in writeback_sb_inodes().
  */
-static int
-writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
-		       struct writeback_control *wbc)
+static int writeback_single_inode(struct inode *inode,
+				  struct writeback_control *wbc)
 {
+	struct bdi_writeback *wb;
 	int ret = 0;
 
 	spin_lock(&inode->i_lock);
@@ -1343,7 +1380,8 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	ret = __writeback_single_inode(inode, wbc);
 
 	wbc_detach_inode(wbc);
-	spin_lock(&wb->list_lock);
+
+	wb = inode_to_wb_and_lock_list(inode);
 	spin_lock(&inode->i_lock);
 	/*
 	 * If inode is clean, remove it from writeback lists. Otherwise don't
@@ -1418,6 +1456,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
+		struct bdi_writeback *tmp_wb;
 
 		if (inode->i_sb != sb) {
 			if (work->sb) {
@@ -1508,15 +1547,23 @@ static long writeback_sb_inodes(struct super_block *sb,
 			cond_resched();
 		}
 
-
-		spin_lock(&wb->list_lock);
+		/*
+		 * Requeue @inode if still dirty.  Be careful as @inode may
+		 * have been switched to another wb in the meantime.
+		 */
+		tmp_wb = inode_to_wb_and_lock_list(inode);
 		spin_lock(&inode->i_lock);
 		if (!(inode->i_state & I_DIRTY_ALL))
 			wrote++;
-		requeue_inode(inode, wb, &wbc);
+		requeue_inode(inode, tmp_wb, &wbc);
 		inode_sync_complete(inode);
 		spin_unlock(&inode->i_lock);
 
+		if (unlikely(tmp_wb != wb)) {
+			spin_unlock(&tmp_wb->list_lock);
+			spin_lock(&wb->list_lock);
+		}
+
 		/*
 		 * bail out to wb_writeback() often enough to check
 		 * background threshold and other termination conditions.
@@ -2303,7 +2350,6 @@ EXPORT_SYMBOL(sync_inodes_sb);
  */
 int write_inode_now(struct inode *inode, int sync)
 {
-	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 	struct writeback_control wbc = {
 		.nr_to_write = LONG_MAX,
 		.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
@@ -2315,7 +2361,7 @@ int write_inode_now(struct inode *inode, int sync)
 		wbc.nr_to_write = 0;
 
 	might_sleep();
-	return writeback_single_inode(inode, wb, &wbc);
+	return writeback_single_inode(inode, &wbc);
 }
 EXPORT_SYMBOL(write_inode_now);
 
@@ -2332,7 +2378,7 @@ EXPORT_SYMBOL(write_inode_now);
  */
 int sync_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc);
+	return writeback_single_inode(inode, wbc);
 }
 EXPORT_SYMBOL(sync_inode);
 
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 8e3ee1936c7e..c5b6b7165489 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -90,7 +90,7 @@ static struct list_head *cuse_conntbl_head(dev_t devt)
 
 static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to)
 {
-	struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp);
 	loff_t pos = 0;
 
 	return fuse_direct_io(&io, to, &pos, FUSE_DIO_CUSE);
@@ -98,7 +98,7 @@ static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to)
 
 static ssize_t cuse_write_iter(struct kiocb *kiocb, struct iov_iter *from)
 {
-	struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp);
 	loff_t pos = 0;
 	/*
 	 * No locking or generic_write_checks(), the server is
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index b03d253ece15..9dde38f12c07 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -528,6 +528,11 @@ static void fuse_release_user_pages(struct fuse_req *req, int write)
 	}
 }
 
+static void fuse_io_release(struct kref *kref)
+{
+	kfree(container_of(kref, struct fuse_io_priv, refcnt));
+}
+
 static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io)
 {
 	if (io->err)
@@ -585,8 +590,9 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
 		}
 
 		io->iocb->ki_complete(io->iocb, res, 0);
-		kfree(io);
 	}
+
+	kref_put(&io->refcnt, fuse_io_release);
 }
 
 static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req)
@@ -613,6 +619,7 @@ static size_t fuse_async_req_send(struct fuse_conn *fc, struct fuse_req *req,
 		size_t num_bytes, struct fuse_io_priv *io)
 {
 	spin_lock(&io->lock);
+	kref_get(&io->refcnt);
 	io->size += num_bytes;
 	io->reqs++;
 	spin_unlock(&io->lock);
@@ -691,7 +698,7 @@ static void fuse_short_read(struct fuse_req *req, struct inode *inode,
 
 static int fuse_do_readpage(struct file *file, struct page *page)
 {
-	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
 	struct inode *inode = page->mapping->host;
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_req *req;
@@ -984,7 +991,7 @@ static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
 	size_t res;
 	unsigned offset;
 	unsigned i;
-	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
 
 	for (i = 0; i < req->num_pages; i++)
 		fuse_wait_on_page_writeback(inode, req->pages[i]->index);
@@ -1240,6 +1247,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 			       size_t *nbytesp, int write)
 {
 	size_t nbytes = 0;  /* # bytes already packed in req */
+	ssize_t ret = 0;
 
 	/* Special case for kernel I/O: can copy directly into the buffer */
 	if (ii->type & ITER_KVEC) {
@@ -1259,13 +1267,12 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 	while (nbytes < *nbytesp && req->num_pages < req->max_pages) {
 		unsigned npages;
 		size_t start;
-		ssize_t ret = iov_iter_get_pages(ii,
-					&req->pages[req->num_pages],
+		ret = iov_iter_get_pages(ii, &req->pages[req->num_pages],
 					*nbytesp - nbytes,
 					req->max_pages - req->num_pages,
 					&start);
 		if (ret < 0)
-			return ret;
+			break;
 
 		iov_iter_advance(ii, ret);
 		nbytes += ret;
@@ -1288,7 +1295,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 
 	*nbytesp = nbytes;
 
-	return 0;
+	return ret;
 }
 
 static inline int fuse_iter_npages(const struct iov_iter *ii_p)
@@ -1312,6 +1319,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	pgoff_t idx_to = (pos + count - 1) >> PAGE_CACHE_SHIFT;
 	ssize_t res = 0;
 	struct fuse_req *req;
+	int err = 0;
 
 	if (io->async)
 		req = fuse_get_req_for_background(fc, fuse_iter_npages(iter));
@@ -1332,11 +1340,9 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		size_t nres;
 		fl_owner_t owner = current->files;
 		size_t nbytes = min(count, nmax);
-		int err = fuse_get_user_pages(req, iter, &nbytes, write);
-		if (err) {
-			res = err;
+		err = fuse_get_user_pages(req, iter, &nbytes, write);
+		if (err && !nbytes)
 			break;
-		}
 
 		if (write)
 			nres = fuse_send_write(req, io, pos, nbytes, owner);
@@ -1346,11 +1352,11 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		if (!io->async)
 			fuse_release_user_pages(req, !write);
 		if (req->out.h.error) {
-			if (!res)
-				res = req->out.h.error;
+			err = req->out.h.error;
 			break;
 		} else if (nres > nbytes) {
-			res = -EIO;
+			res = 0;
+			err = -EIO;
 			break;
 		}
 		count -= nres;
@@ -1374,7 +1380,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	if (res > 0)
 		*ppos = pos;
 
-	return res;
+	return res > 0 ? res : err;
 }
 EXPORT_SYMBOL_GPL(fuse_direct_io);
 
@@ -1398,7 +1404,7 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
 
 static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
-	struct fuse_io_priv io = { .async = 0, .file = iocb->ki_filp };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb->ki_filp);
 	return __fuse_direct_read(&io, to, &iocb->ki_pos);
 }
 
@@ -1406,7 +1412,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
 	ssize_t res;
 
 	if (is_bad_inode(inode))
@@ -2843,6 +2849,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	loff_t i_size;
 	size_t count = iov_iter_count(iter);
 	struct fuse_io_priv *io;
+	bool is_sync = is_sync_kiocb(iocb);
 
 	pos = offset;
 	inode = file->f_mapping->host;
@@ -2863,6 +2870,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	if (!io)
 		return -ENOMEM;
 	spin_lock_init(&io->lock);
+	kref_init(&io->refcnt);
 	io->reqs = 1;
 	io->bytes = -1;
 	io->size = 0;
@@ -2882,12 +2890,18 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	 * to wait on real async I/O requests, so we must submit this request
 	 * synchronously.
 	 */
-	if (!is_sync_kiocb(iocb) && (offset + count > i_size) &&
+	if (!is_sync && (offset + count > i_size) &&
 	    iov_iter_rw(iter) == WRITE)
 		io->async = false;
 
-	if (io->async && is_sync_kiocb(iocb))
+	if (io->async && is_sync) {
+		/*
+		 * Additional reference to keep io around after
+		 * calling fuse_aio_complete()
+		 */
+		kref_get(&io->refcnt);
 		io->done = &wait;
+	}
 
 	if (iov_iter_rw(iter) == WRITE) {
 		ret = fuse_direct_io(io, iter, &pos, FUSE_DIO_WRITE);
@@ -2900,14 +2914,14 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 		fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
 
 		/* we have a non-extending, async request, so return */
-		if (!is_sync_kiocb(iocb))
+		if (!is_sync)
 			return -EIOCBQUEUED;
 
 		wait_for_completion(&wait);
 		ret = fuse_get_res_by_io(io);
 	}
 
-	kfree(io);
+	kref_put(&io->refcnt, fuse_io_release);
 
 	if (iov_iter_rw(iter) == WRITE) {
 		if (ret > 0)
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index ce394b5fe6b4..eddbe02c4028 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -22,6 +22,7 @@
 #include <linux/rbtree.h>
 #include <linux/poll.h>
 #include <linux/workqueue.h>
+#include <linux/kref.h>
 
 /** Max number of pages that can be used in a single read request */
 #define FUSE_MAX_PAGES_PER_REQ 32
@@ -243,6 +244,7 @@ struct fuse_args {
 
 /** The request IO state (for asynchronous processing) */
 struct fuse_io_priv {
+	struct kref refcnt;
 	int async;
 	spinlock_t lock;
 	unsigned reqs;
@@ -256,6 +258,13 @@ struct fuse_io_priv {
 	struct completion *done;
 };
 
+#define FUSE_IO_PRIV_SYNC(f) \
+{					\
+	.refcnt = { ATOMIC_INIT(1) },	\
+	.async = 0,			\
+	.file = f,			\
+}
+
 /**
  * Request flags
  *
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 93f07465e5a6..aa016e4b8bec 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -1082,7 +1082,7 @@ static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	 * the first place, mapping->nr_pages will always be zero.
 	 */
 	if (mapping->nrpages) {
-		loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
+		loff_t lstart = offset & ~(PAGE_CACHE_SIZE - 1);
 		loff_t len = iov_iter_count(iter);
 		loff_t end = PAGE_ALIGN(offset + len) - 1;
 
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 6a92592304fb..4a01f30e9995 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -798,7 +798,7 @@ static int get_first_leaf(struct gfs2_inode *dip, u32 index,
 	int error;
 
 	error = get_leaf_nr(dip, index, &leaf_no);
-	if (!error)
+	if (!IS_ERR_VALUE(error))
 		error = get_leaf(dip, leaf_no, bh_out);
 
 	return error;
@@ -1014,7 +1014,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 
 	index = name->hash >> (32 - dip->i_depth);
 	error = get_leaf_nr(dip, index, &leaf_no);
-	if (error)
+	if (IS_ERR_VALUE(error))
 		return error;
 
 	/*  Get the old leaf block  */
@@ -1660,7 +1660,7 @@ struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name,
 		brelse(bh);
 		if (fail_on_exist)
 			return ERR_PTR(-EEXIST);
-		inode = gfs2_inode_lookup(dir->i_sb, dtype, addr, formal_ino, 0);
+		inode = gfs2_inode_lookup(dir->i_sb, dtype, addr, formal_ino);
 		if (!IS_ERR(inode))
 			GFS2_I(inode)->i_rahead = rahead;
 		return inode;
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 5d15e9498b48..d5bda8513457 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -137,7 +137,7 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb,
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct inode *inode;
 
-	inode = gfs2_ilookup(sb, inum->no_addr, 0);
+	inode = gfs2_ilookup(sb, inum->no_addr);
 	if (inode) {
 		if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
 			iput(inode);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index a4ff7b56f5cd..6539131c52a2 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -572,17 +572,24 @@ static void delete_work_func(struct work_struct *work)
 	struct inode *inode;
 	u64 no_addr = gl->gl_name.ln_number;
 
+	/* If someone's using this glock to create a new dinode, the block must
+	   have been freed by another node, then re-used, in which case our
+	   iopen callback is too late after the fact. Ignore it. */
+	if (test_bit(GLF_INODE_CREATING, &gl->gl_flags))
+		goto out;
+
 	ip = gl->gl_object;
 	/* Note: Unsafe to dereference ip as we don't hold right refs/locks */
 
 	if (ip)
-		inode = gfs2_ilookup(sdp->sd_vfs, no_addr, 1);
+		inode = gfs2_ilookup(sdp->sd_vfs, no_addr);
 	else
 		inode = gfs2_lookup_by_inum(sdp, no_addr, NULL, GFS2_BLKST_UNLINKED);
 	if (inode && !IS_ERR(inode)) {
 		d_prune_aliases(inode);
 		iput(inode);
 	}
+out:
 	gfs2_glock_put(gl);
 }
 
@@ -1015,6 +1022,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 		handle_callback(gl, LM_ST_UNLOCKED, 0, false);
 
 	list_del_init(&gh->gh_list);
+	clear_bit(HIF_HOLDER, &gh->gh_iflags);
 	if (find_first_holder(gl) == NULL) {
 		if (glops->go_unlock) {
 			GLOCK_BUG_ON(gl, test_and_set_bit(GLF_LOCK, &gl->gl_flags));
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 845fb09cc606..a6a3389a07fc 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -328,6 +328,7 @@ enum {
 	GLF_LRU				= 13,
 	GLF_OBJECT			= 14, /* Used only for tracing */
 	GLF_BLOCKING			= 15,
+	GLF_INODE_CREATING		= 16, /* Inode creation occurring */
 };
 
 struct gfs2_glock {
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 352f958769e1..bb30f9a72c65 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -37,61 +37,9 @@
 #include "super.h"
 #include "glops.h"
 
-struct gfs2_skip_data {
-	u64 no_addr;
-	int skipped;
-	int non_block;
-};
-
-static int iget_test(struct inode *inode, void *opaque)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_skip_data *data = opaque;
-
-	if (ip->i_no_addr == data->no_addr) {
-		if (data->non_block &&
-		    inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) {
-			data->skipped = 1;
-			return 0;
-		}
-		return 1;
-	}
-	return 0;
-}
-
-static int iget_set(struct inode *inode, void *opaque)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_skip_data *data = opaque;
-
-	if (data->skipped)
-		return -ENOENT;
-	inode->i_ino = (unsigned long)(data->no_addr);
-	ip->i_no_addr = data->no_addr;
-	return 0;
-}
-
-struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int non_block)
+struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr)
 {
-	unsigned long hash = (unsigned long)no_addr;
-	struct gfs2_skip_data data;
-
-	data.no_addr = no_addr;
-	data.skipped = 0;
-	data.non_block = non_block;
-	return ilookup5(sb, hash, iget_test, &data);
-}
-
-static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr,
-			       int non_block)
-{
-	struct gfs2_skip_data data;
-	unsigned long hash = (unsigned long)no_addr;
-
-	data.no_addr = no_addr;
-	data.skipped = 0;
-	data.non_block = non_block;
-	return iget5_locked(sb, hash, iget_test, iget_set, &data);
+	return ilookup(sb, (unsigned long)no_addr);
 }
 
 /**
@@ -132,21 +80,21 @@ static void gfs2_set_iop(struct inode *inode)
  * @sb: The super block
  * @no_addr: The inode number
  * @type: The type of the inode
- * non_block: Can we block on inodes that are being freed?
  *
  * Returns: A VFS inode, or an error
  */
 
 struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
-				u64 no_addr, u64 no_formal_ino, int non_block)
+				u64 no_addr, u64 no_formal_ino)
 {
 	struct inode *inode;
 	struct gfs2_inode *ip;
 	struct gfs2_glock *io_gl = NULL;
 	int error;
 
-	inode = gfs2_iget(sb, no_addr, non_block);
+	inode = iget_locked(sb, (unsigned long)no_addr);
 	ip = GFS2_I(inode);
+	ip->i_no_addr = no_addr;
 
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
@@ -221,7 +169,7 @@ struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
 	if (error)
 		goto fail;
 
-	inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0, 1);
+	inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0);
 	if (IS_ERR(inode))
 		goto fail;
 
@@ -592,7 +540,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	struct inode *inode = NULL;
 	struct gfs2_inode *dip = GFS2_I(dir), *ip;
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
-	struct gfs2_glock *io_gl;
+	struct gfs2_glock *io_gl = NULL;
 	int error, free_vfs_inode = 1;
 	u32 aflags = 0;
 	unsigned blocks = 1;
@@ -729,6 +677,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (error)
 		goto fail_gunlock2;
 
+	BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags));
+
 	error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
 	if (error)
 		goto fail_gunlock2;
@@ -771,12 +721,15 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	}
 	gfs2_glock_dq_uninit(ghs);
 	gfs2_glock_dq_uninit(ghs + 1);
+	clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
 	return error;
 
 fail_gunlock3:
 	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
 	gfs2_glock_put(io_gl);
 fail_gunlock2:
+	if (io_gl)
+		clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
 	gfs2_glock_dq_uninit(ghs + 1);
 fail_free_inode:
 	if (ip->i_gl)
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index ba4d9492d422..e1af0d4aa308 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -94,12 +94,11 @@ err:
 }
 
 extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
-				       u64 no_addr, u64 no_formal_ino,
-				       int non_block);
+				       u64 no_addr, u64 no_formal_ino);
 extern struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
 					 u64 *no_formal_ino,
 					 unsigned int blktype);
-extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int nonblock);
+extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
 
 extern int gfs2_inode_refresh(struct gfs2_inode *ip);
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index dbed9e243ea2..49b0bff18fe3 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -454,7 +454,7 @@ static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
 	struct dentry *dentry;
 	struct inode *inode;
 
-	inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
+	inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0);
 	if (IS_ERR(inode)) {
 		fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
 		return PTR_ERR(inode);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 8f960a51a9a0..f8a0cd821290 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1551,12 +1551,16 @@ static void gfs2_evict_inode(struct inode *inode)
 			goto out_truncate;
 	}
 
-	ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-	gfs2_glock_dq_wait(&ip->i_iopen_gh);
-	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
-	error = gfs2_glock_nq(&ip->i_iopen_gh);
-	if (error)
-		goto out_truncate;
+	if (ip->i_iopen_gh.gh_gl &&
+	    test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
+		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
+		gfs2_glock_dq_wait(&ip->i_iopen_gh);
+		gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE,
+				   &ip->i_iopen_gh);
+		error = gfs2_glock_nq(&ip->i_iopen_gh);
+		if (error)
+			goto out_truncate;
+	}
 
 	/* Case 1 starts here */
 
@@ -1606,11 +1610,13 @@ out_unlock:
 	if (gfs2_rs_active(&ip->i_res))
 		gfs2_rs_deltree(&ip->i_res);
 
-	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
-		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_wait(&ip->i_iopen_gh);
+	if (ip->i_iopen_gh.gh_gl) {
+		if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
+			ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
+			gfs2_glock_dq_wait(&ip->i_iopen_gh);
+		}
+		gfs2_holder_uninit(&ip->i_iopen_gh);
 	}
-	gfs2_holder_uninit(&ip->i_iopen_gh);
 	gfs2_glock_dq_uninit(&gh);
 	if (error && error != GLR_TRYFAILED && error != -EROFS)
 		fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 506765afa1a3..bb8d67e2740a 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -376,12 +376,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct inode *inode = d_inode(dentry);
 	dnode_secno dno;
 	int r;
-	int rep = 0;
 	int err;
 
 	hpfs_lock(dir->i_sb);
 	hpfs_adjust_length(name, &len);
-again:
+
 	err = -ENOENT;
 	de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh);
 	if (!de)
@@ -401,33 +400,9 @@ again:
 		hpfs_error(dir->i_sb, "there was error when removing dirent");
 		err = -EFSERROR;
 		break;
-	case 2:		/* no space for deleting, try to truncate file */
-
+	case 2:		/* no space for deleting */
 		err = -ENOSPC;
-		if (rep++)
-			break;
-
-		dentry_unhash(dentry);
-		if (!d_unhashed(dentry)) {
-			hpfs_unlock(dir->i_sb);
-			return -ENOSPC;
-		}
-		if (generic_permission(inode, MAY_WRITE) ||
-		    !S_ISREG(inode->i_mode) ||
-		    get_write_access(inode)) {
-			d_rehash(dentry);
-		} else {
-			struct iattr newattrs;
-			/*pr_info("truncating file before delete.\n");*/
-			newattrs.ia_size = 0;
-			newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
-			err = notify_change(dentry, &newattrs, NULL);
-			put_write_access(inode);
-			if (!err)
-				goto again;
-		}
-		hpfs_unlock(dir->i_sb);
-		return -ENOSPC;
+		break;
 	default:
 		drop_nlink(inode);
 		err = 0;
diff --git a/fs/inode.c b/fs/inode.c
index 9f62db3bcc3e..69b8b526c194 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -154,6 +154,12 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_rdev = 0;
 	inode->dirtied_when = 0;
 
+#ifdef CONFIG_CGROUP_WRITEBACK
+	inode->i_wb_frn_winner = 0;
+	inode->i_wb_frn_avg_time = 0;
+	inode->i_wb_frn_history = 0;
+#endif
+
 	if (security_inode_alloc(inode))
 		goto out;
 	spin_lock_init(&inode->i_lock);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 36345fefa3ff..517f2de784cf 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -131,14 +131,12 @@ static int journal_submit_commit_record(journal_t *journal,
 	if (is_journal_aborted(journal))
 		return 0;
 
-	bh = jbd2_journal_get_descriptor_buffer(journal);
+	bh = jbd2_journal_get_descriptor_buffer(commit_transaction,
+						JBD2_COMMIT_BLOCK);
 	if (!bh)
 		return 1;
 
 	tmp = (struct commit_header *)bh->b_data;
-	tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
-	tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
-	tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid);
 	tmp->h_commit_sec = cpu_to_be64(now.tv_sec);
 	tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec);
 
@@ -222,7 +220,7 @@ static int journal_submit_data_buffers(journal_t *journal,
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
 		mapping = jinode->i_vfs_inode->i_mapping;
-		set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
+		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
 		/*
 		 * submit the inode data buffers. We use writepage
@@ -236,8 +234,8 @@ static int journal_submit_data_buffers(journal_t *journal,
 			ret = err;
 		spin_lock(&journal->j_list_lock);
 		J_ASSERT(jinode->i_transaction == commit_transaction);
-		clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
-		smp_mb__after_atomic();
+		jinode->i_flags &= ~JI_COMMIT_RUNNING;
+		smp_mb();
 		wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
 	}
 	spin_unlock(&journal->j_list_lock);
@@ -258,7 +256,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 	/* For locking, see the comment in journal_submit_data_buffers() */
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
-		set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
+		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
 		err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
 		if (err) {
@@ -274,8 +272,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 				ret = err;
 		}
 		spin_lock(&journal->j_list_lock);
-		clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
-		smp_mb__after_atomic();
+		jinode->i_flags &= ~JI_COMMIT_RUNNING;
+		smp_mb();
 		wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
 	}
 
@@ -319,22 +317,6 @@ static void write_tag_block(journal_t *j, journal_block_tag_t *tag,
 		tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);
 }
 
-static void jbd2_descr_block_csum_set(journal_t *j,
-				      struct buffer_head *bh)
-{
-	struct jbd2_journal_block_tail *tail;
-	__u32 csum;
-
-	if (!jbd2_journal_has_csum_v2or3(j))
-		return;
-
-	tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
-			sizeof(struct jbd2_journal_block_tail));
-	tail->t_checksum = 0;
-	csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
-	tail->t_checksum = cpu_to_be32(csum);
-}
-
 static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 				    struct buffer_head *bh, __u32 sequence)
 {
@@ -379,7 +361,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	ktime_t start_time;
 	u64 commit_time;
 	char *tagp = NULL;
-	journal_header_t *header;
 	journal_block_tag_t *tag = NULL;
 	int space_left = 0;
 	int first_tag = 0;
@@ -554,8 +535,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		jbd2_journal_abort(journal, err);
 
 	blk_start_plug(&plug);
-	jbd2_journal_write_revoke_records(journal, commit_transaction,
-					  &log_bufs, WRITE_SYNC);
+	jbd2_journal_write_revoke_records(commit_transaction, &log_bufs);
 
 	jbd_debug(3, "JBD2: commit phase 2b\n");
 
@@ -616,7 +596,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 
 			jbd_debug(4, "JBD2: get descriptor\n");
 
-			descriptor = jbd2_journal_get_descriptor_buffer(journal);
+			descriptor = jbd2_journal_get_descriptor_buffer(
+							commit_transaction,
+							JBD2_DESCRIPTOR_BLOCK);
 			if (!descriptor) {
 				jbd2_journal_abort(journal, -EIO);
 				continue;
@@ -625,11 +607,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			jbd_debug(4, "JBD2: got buffer %llu (%p)\n",
 				(unsigned long long)descriptor->b_blocknr,
 				descriptor->b_data);
-			header = (journal_header_t *)descriptor->b_data;
-			header->h_magic     = cpu_to_be32(JBD2_MAGIC_NUMBER);
-			header->h_blocktype = cpu_to_be32(JBD2_DESCRIPTOR_BLOCK);
-			header->h_sequence  = cpu_to_be32(commit_transaction->t_tid);
-
 			tagp = &descriptor->b_data[sizeof(journal_header_t)];
 			space_left = descriptor->b_size -
 						sizeof(journal_header_t);
@@ -721,7 +698,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 
 			tag->t_flags |= cpu_to_be16(JBD2_FLAG_LAST_TAG);
 
-			jbd2_descr_block_csum_set(journal, descriptor);
+			jbd2_descriptor_block_csum_set(journal, descriptor);
 start_journal_io:
 			for (i = 0; i < bufs; i++) {
 				struct buffer_head *bh = wbuf[i];
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 81e622681c82..de73a9516a54 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -805,10 +805,13 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
  * But we don't bother doing that, so there will be coherency problems with
  * mmaps of blockdevs which hold live JBD-controlled filesystems.
  */
-struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
+struct buffer_head *
+jbd2_journal_get_descriptor_buffer(transaction_t *transaction, int type)
 {
+	journal_t *journal = transaction->t_journal;
 	struct buffer_head *bh;
 	unsigned long long blocknr;
+	journal_header_t *header;
 	int err;
 
 	err = jbd2_journal_next_log_block(journal, &blocknr);
@@ -821,12 +824,31 @@ struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
 		return NULL;
 	lock_buffer(bh);
 	memset(bh->b_data, 0, journal->j_blocksize);
+	header = (journal_header_t *)bh->b_data;
+	header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
+	header->h_blocktype = cpu_to_be32(type);
+	header->h_sequence = cpu_to_be32(transaction->t_tid);
 	set_buffer_uptodate(bh);
 	unlock_buffer(bh);
 	BUFFER_TRACE(bh, "return this buffer");
 	return bh;
 }
 
+void jbd2_descriptor_block_csum_set(journal_t *j, struct buffer_head *bh)
+{
+	struct jbd2_journal_block_tail *tail;
+	__u32 csum;
+
+	if (!jbd2_journal_has_csum_v2or3(j))
+		return;
+
+	tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
+			sizeof(struct jbd2_journal_block_tail));
+	tail->t_checksum = 0;
+	csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
+	tail->t_checksum = cpu_to_be32(csum);
+}
+
 /*
  * Return tid of the oldest transaction in the journal and block in the journal
  * where the transaction starts.
@@ -1408,11 +1430,12 @@ out:
 /**
  * jbd2_mark_journal_empty() - Mark on disk journal as empty.
  * @journal: The journal to update.
+ * @write_op: With which operation should we write the journal sb
  *
  * Update a journal's dynamic superblock fields to show that journal is empty.
  * Write updated superblock to disk waiting for IO to complete.
  */
-static void jbd2_mark_journal_empty(journal_t *journal)
+static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 {
 	journal_superblock_t *sb = journal->j_superblock;
 
@@ -1430,7 +1453,7 @@ static void jbd2_mark_journal_empty(journal_t *journal)
 	sb->s_start    = cpu_to_be32(0);
 	read_unlock(&journal->j_state_lock);
 
-	jbd2_write_superblock(journal, WRITE_FUA);
+	jbd2_write_superblock(journal, write_op);
 
 	/* Log is no longer empty */
 	write_lock(&journal->j_state_lock);
@@ -1716,7 +1739,13 @@ int jbd2_journal_destroy(journal_t *journal)
 	if (journal->j_sb_buffer) {
 		if (!is_journal_aborted(journal)) {
 			mutex_lock(&journal->j_checkpoint_mutex);
-			jbd2_mark_journal_empty(journal);
+
+			write_lock(&journal->j_state_lock);
+			journal->j_tail_sequence =
+				++journal->j_transaction_sequence;
+			write_unlock(&journal->j_state_lock);
+
+			jbd2_mark_journal_empty(journal, WRITE_FLUSH_FUA);
 			mutex_unlock(&journal->j_checkpoint_mutex);
 		} else
 			err = -EIO;
@@ -1975,7 +2004,7 @@ int jbd2_journal_flush(journal_t *journal)
 	 * the magic code for a fully-recovered superblock.  Any future
 	 * commits of data to the journal will restore the current
 	 * s_start value. */
-	jbd2_mark_journal_empty(journal);
+	jbd2_mark_journal_empty(journal, WRITE_FUA);
 	mutex_unlock(&journal->j_checkpoint_mutex);
 	write_lock(&journal->j_state_lock);
 	J_ASSERT(!journal->j_running_transaction);
@@ -2021,7 +2050,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	if (write) {
 		/* Lock to make assertions happy... */
 		mutex_lock(&journal->j_checkpoint_mutex);
-		jbd2_mark_journal_empty(journal);
+		jbd2_mark_journal_empty(journal, WRITE_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 
@@ -2565,7 +2594,7 @@ void jbd2_journal_release_jbd_inode(journal_t *journal,
 restart:
 	spin_lock(&journal->j_list_lock);
 	/* Is commit writing out inode - we have to wait */
-	if (test_bit(__JI_COMMIT_RUNNING, &jinode->i_flags)) {
+	if (jinode->i_flags & JI_COMMIT_RUNNING) {
 		wait_queue_head_t *wq;
 		DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING);
 		wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING);
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 7f277e49fe88..08a456b96e4e 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -174,8 +174,7 @@ static int jread(struct buffer_head **bhp, journal_t *journal,
 	return 0;
 }
 
-static int jbd2_descr_block_csum_verify(journal_t *j,
-					void *buf)
+static int jbd2_descriptor_block_csum_verify(journal_t *j, void *buf)
 {
 	struct jbd2_journal_block_tail *tail;
 	__be32 provided;
@@ -522,8 +521,8 @@ static int do_one_pass(journal_t *journal,
 				descr_csum_size =
 					sizeof(struct jbd2_journal_block_tail);
 			if (descr_csum_size > 0 &&
-			    !jbd2_descr_block_csum_verify(journal,
-							  bh->b_data)) {
+			    !jbd2_descriptor_block_csum_verify(journal,
+							       bh->b_data)) {
 				printk(KERN_ERR "JBD2: Invalid checksum "
 				       "recovering block %lu in log\n",
 				       next_log_block);
@@ -811,26 +810,6 @@ static int do_one_pass(journal_t *journal,
 	return err;
 }
 
-static int jbd2_revoke_block_csum_verify(journal_t *j,
-					 void *buf)
-{
-	struct jbd2_journal_revoke_tail *tail;
-	__be32 provided;
-	__u32 calculated;
-
-	if (!jbd2_journal_has_csum_v2or3(j))
-		return 1;
-
-	tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize -
-			sizeof(struct jbd2_journal_revoke_tail));
-	provided = tail->r_checksum;
-	tail->r_checksum = 0;
-	calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize);
-	tail->r_checksum = provided;
-
-	return provided == cpu_to_be32(calculated);
-}
-
 /* Scan a revoke record, marking all blocks mentioned as revoked. */
 
 static int scan_revoke_records(journal_t *journal, struct buffer_head *bh,
@@ -846,11 +825,11 @@ static int scan_revoke_records(journal_t *journal, struct buffer_head *bh,
 	offset = sizeof(jbd2_journal_revoke_header_t);
 	rcount = be32_to_cpu(header->r_count);
 
-	if (!jbd2_revoke_block_csum_verify(journal, header))
+	if (!jbd2_descriptor_block_csum_verify(journal, header))
 		return -EFSBADCRC;
 
 	if (jbd2_journal_has_csum_v2or3(journal))
-		csum_size = sizeof(struct jbd2_journal_revoke_tail);
+		csum_size = sizeof(struct jbd2_journal_block_tail);
 	if (rcount > journal->j_blocksize - csum_size)
 		return -EINVAL;
 	max = rcount;
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 705ae577882b..91171dc352cb 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -122,11 +122,11 @@ struct jbd2_revoke_table_s
 
 
 #ifdef __KERNEL__
-static void write_one_revoke_record(journal_t *, transaction_t *,
+static void write_one_revoke_record(transaction_t *,
 				    struct list_head *,
 				    struct buffer_head **, int *,
-				    struct jbd2_revoke_record_s *, int);
-static void flush_descriptor(journal_t *, struct buffer_head *, int, int);
+				    struct jbd2_revoke_record_s *);
+static void flush_descriptor(journal_t *, struct buffer_head *, int);
 #endif
 
 /* Utility functions to maintain the revoke table */
@@ -519,11 +519,10 @@ void jbd2_journal_switch_revoke_table(journal_t *journal)
  * Write revoke records to the journal for all entries in the current
  * revoke hash, deleting the entries as we go.
  */
-void jbd2_journal_write_revoke_records(journal_t *journal,
-				       transaction_t *transaction,
-				       struct list_head *log_bufs,
-				       int write_op)
+void jbd2_journal_write_revoke_records(transaction_t *transaction,
+				       struct list_head *log_bufs)
 {
+	journal_t *journal = transaction->t_journal;
 	struct buffer_head *descriptor;
 	struct jbd2_revoke_record_s *record;
 	struct jbd2_revoke_table_s *revoke;
@@ -544,16 +543,15 @@ void jbd2_journal_write_revoke_records(journal_t *journal,
 		while (!list_empty(hash_list)) {
 			record = (struct jbd2_revoke_record_s *)
 				hash_list->next;
-			write_one_revoke_record(journal, transaction, log_bufs,
-						&descriptor, &offset,
-						record, write_op);
+			write_one_revoke_record(transaction, log_bufs,
+						&descriptor, &offset, record);
 			count++;
 			list_del(&record->hash);
 			kmem_cache_free(jbd2_revoke_record_cache, record);
 		}
 	}
 	if (descriptor)
-		flush_descriptor(journal, descriptor, offset, write_op);
+		flush_descriptor(journal, descriptor, offset);
 	jbd_debug(1, "Wrote %d revoke records\n", count);
 }
 
@@ -562,18 +560,16 @@ void jbd2_journal_write_revoke_records(journal_t *journal,
  * block if the old one is full or if we have not already created one.
  */
 
-static void write_one_revoke_record(journal_t *journal,
-				    transaction_t *transaction,
+static void write_one_revoke_record(transaction_t *transaction,
 				    struct list_head *log_bufs,
 				    struct buffer_head **descriptorp,
 				    int *offsetp,
-				    struct jbd2_revoke_record_s *record,
-				    int write_op)
+				    struct jbd2_revoke_record_s *record)
 {
+	journal_t *journal = transaction->t_journal;
 	int csum_size = 0;
 	struct buffer_head *descriptor;
 	int sz, offset;
-	journal_header_t *header;
 
 	/* If we are already aborting, this all becomes a noop.  We
            still need to go round the loop in
@@ -587,7 +583,7 @@ static void write_one_revoke_record(journal_t *journal,
 
 	/* Do we need to leave space at the end for a checksum? */
 	if (jbd2_journal_has_csum_v2or3(journal))
-		csum_size = sizeof(struct jbd2_journal_revoke_tail);
+		csum_size = sizeof(struct jbd2_journal_block_tail);
 
 	if (jbd2_has_feature_64bit(journal))
 		sz = 8;
@@ -597,19 +593,16 @@ static void write_one_revoke_record(journal_t *journal,
 	/* Make sure we have a descriptor with space left for the record */
 	if (descriptor) {
 		if (offset + sz > journal->j_blocksize - csum_size) {
-			flush_descriptor(journal, descriptor, offset, write_op);
+			flush_descriptor(journal, descriptor, offset);
 			descriptor = NULL;
 		}
 	}
 
 	if (!descriptor) {
-		descriptor = jbd2_journal_get_descriptor_buffer(journal);
+		descriptor = jbd2_journal_get_descriptor_buffer(transaction,
+							JBD2_REVOKE_BLOCK);
 		if (!descriptor)
 			return;
-		header = (journal_header_t *)descriptor->b_data;
-		header->h_magic     = cpu_to_be32(JBD2_MAGIC_NUMBER);
-		header->h_blocktype = cpu_to_be32(JBD2_REVOKE_BLOCK);
-		header->h_sequence  = cpu_to_be32(transaction->t_tid);
 
 		/* Record it so that we can wait for IO completion later */
 		BUFFER_TRACE(descriptor, "file in log_bufs");
@@ -630,21 +623,6 @@ static void write_one_revoke_record(journal_t *journal,
 	*offsetp = offset;
 }
 
-static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh)
-{
-	struct jbd2_journal_revoke_tail *tail;
-	__u32 csum;
-
-	if (!jbd2_journal_has_csum_v2or3(j))
-		return;
-
-	tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize -
-			sizeof(struct jbd2_journal_revoke_tail));
-	tail->r_checksum = 0;
-	csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
-	tail->r_checksum = cpu_to_be32(csum);
-}
-
 /*
  * Flush a revoke descriptor out to the journal.  If we are aborting,
  * this is a noop; otherwise we are generating a buffer which needs to
@@ -654,7 +632,7 @@ static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh)
 
 static void flush_descriptor(journal_t *journal,
 			     struct buffer_head *descriptor,
-			     int offset, int write_op)
+			     int offset)
 {
 	jbd2_journal_revoke_header_t *header;
 
@@ -665,12 +643,12 @@ static void flush_descriptor(journal_t *journal,
 
 	header = (jbd2_journal_revoke_header_t *)descriptor->b_data;
 	header->r_count = cpu_to_be32(offset);
-	jbd2_revoke_csum_set(journal, descriptor);
+	jbd2_descriptor_block_csum_set(journal, descriptor);
 
 	set_buffer_jwrite(descriptor);
 	BUFFER_TRACE(descriptor, "write");
 	set_buffer_dirty(descriptor);
-	write_dirty_buffer(descriptor, write_op);
+	write_dirty_buffer(descriptor, WRITE_SYNC);
 }
 #endif
 
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 081dff087fc0..01e4652d88f6 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -966,14 +966,8 @@ repeat:
 		if (!frozen_buffer) {
 			JBUFFER_TRACE(jh, "allocate memory for buffer");
 			jbd_unlock_bh_state(bh);
-			frozen_buffer = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS);
-			if (!frozen_buffer) {
-				printk(KERN_ERR "%s: OOM for frozen_buffer\n",
-				       __func__);
-				JBUFFER_TRACE(jh, "oom!");
-				error = -ENOMEM;
-				goto out;
-			}
+			frozen_buffer = jbd2_alloc(jh2bh(jh)->b_size,
+						   GFP_NOFS | __GFP_NOFAIL);
 			goto repeat;
 		}
 		jh->b_frozen_data = frozen_buffer;
@@ -1226,15 +1220,9 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 		goto out;
 
 repeat:
-	if (!jh->b_committed_data) {
-		committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS);
-		if (!committed_data) {
-			printk(KERN_ERR "%s: No memory for committed data\n",
-				__func__);
-			err = -ENOMEM;
-			goto out;
-		}
-	}
+	if (!jh->b_committed_data)
+		committed_data = jbd2_alloc(jh2bh(jh)->b_size,
+					    GFP_NOFS|__GFP_NOFAIL);
 
 	jbd_lock_bh_state(bh);
 	if (!jh->b_committed_data) {
diff --git a/fs/jffs2/README.Locking b/fs/jffs2/README.Locking
index 3ea36554107f..8918ac905a3b 100644
--- a/fs/jffs2/README.Locking
+++ b/fs/jffs2/README.Locking
@@ -2,10 +2,6 @@
 	JFFS2 LOCKING DOCUMENTATION
 	---------------------------
 
-At least theoretically, JFFS2 does not require the Big Kernel Lock
-(BKL), which was always helpfully obtained for it by Linux 2.4 VFS
-code. It has its own locking, as described below.
-
 This document attempts to describe the existing locking rules for
 JFFS2. It is not expected to remain perfectly up to date, but ought to
 be fairly close.
@@ -69,6 +65,7 @@ Ordering constraints:
 	   any f->sem held.
 	2. Never attempt to lock two file mutexes in one thread.
 	   No ordering rules have been made for doing so.
+	3. Never lock a page cache page with f->sem held.
 
 
 	erase_completion_lock spinlock
diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c
index 0ae91ad6df2d..b288c8ae1236 100644
--- a/fs/jffs2/build.c
+++ b/fs/jffs2/build.c
@@ -50,7 +50,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c)
 
 
 static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
-				    struct jffs2_inode_cache *ic)
+				    struct jffs2_inode_cache *ic,
+				    int *dir_hardlinks)
 {
 	struct jffs2_full_dirent *fd;
 
@@ -69,19 +70,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
 			dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n",
 				  fd->name, fd->ino, ic->ino);
 			jffs2_mark_node_obsolete(c, fd->raw);
+			/* Clear the ic/raw union so it doesn't cause problems later. */
+			fd->ic = NULL;
 			continue;
 		}
 
+		/* From this point, fd->raw is no longer used so we can set fd->ic */
+		fd->ic = child_ic;
+		child_ic->pino_nlink++;
+		/* If we appear (at this stage) to have hard-linked directories,
+		 * set a flag to trigger a scan later */
 		if (fd->type == DT_DIR) {
-			if (child_ic->pino_nlink) {
-				JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n",
-					    fd->name, fd->ino, ic->ino);
-				/* TODO: What do we do about it? */
-			} else {
-				child_ic->pino_nlink = ic->ino;
-			}
-		} else
-			child_ic->pino_nlink++;
+			child_ic->flags |= INO_FLAGS_IS_DIR;
+			if (child_ic->pino_nlink > 1)
+				*dir_hardlinks = 1;
+		}
 
 		dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino);
 		/* Can't free scan_dents so far. We might need them in pass 2 */
@@ -95,8 +98,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
 */
 static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 {
-	int ret;
-	int i;
+	int ret, i, dir_hardlinks = 0;
 	struct jffs2_inode_cache *ic;
 	struct jffs2_full_dirent *fd;
 	struct jffs2_full_dirent *dead_fds = NULL;
@@ -120,7 +122,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 	/* Now scan the directory tree, increasing nlink according to every dirent found. */
 	for_each_inode(i, c, ic) {
 		if (ic->scan_dents) {
-			jffs2_build_inode_pass1(c, ic);
+			jffs2_build_inode_pass1(c, ic, &dir_hardlinks);
 			cond_resched();
 		}
 	}
@@ -156,6 +158,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 	}
 
 	dbg_fsbuild("pass 2a complete\n");
+
+	if (dir_hardlinks) {
+		/* If we detected directory hardlinks earlier, *hopefully*
+		 * they are gone now because some of the links were from
+		 * dead directories which still had some old dirents lying
+		 * around and not yet garbage-collected, but which have
+		 * been discarded above. So clear the pino_nlink field
+		 * in each directory, so that the final scan below can
+		 * print appropriate warnings. */
+		for_each_inode(i, c, ic) {
+			if (ic->flags & INO_FLAGS_IS_DIR)
+				ic->pino_nlink = 0;
+		}
+	}
 	dbg_fsbuild("freeing temporary data structures\n");
 
 	/* Finally, we can scan again and free the dirent structs */
@@ -163,6 +179,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 		while(ic->scan_dents) {
 			fd = ic->scan_dents;
 			ic->scan_dents = fd->next;
+			/* We do use the pino_nlink field to count nlink of
+			 * directories during fs build, so set it to the
+			 * parent ino# now. Now that there's hopefully only
+			 * one. */
+			if (fd->type == DT_DIR) {
+				if (!fd->ic) {
+					/* We'll have complained about it and marked the coresponding
+					   raw node obsolete already. Just skip it. */
+					continue;
+				}
+
+				/* We *have* to have set this in jffs2_build_inode_pass1() */
+				BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR));
+
+				/* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks
+				 * is set. Otherwise, we know this should never trigger anyway, so
+				 * we don't do the check. And ic->pino_nlink still contains the nlink
+				 * value (which is 1). */
+				if (dir_hardlinks && fd->ic->pino_nlink) {
+					JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n",
+						    fd->name, fd->ino, ic->ino, fd->ic->pino_nlink);
+					/* Should we unlink it from its previous parent? */
+				}
+
+				/* For directories, ic->pino_nlink holds that parent inode # */
+				fd->ic->pino_nlink = ic->ino;
+			}
 			jffs2_free_full_dirent(fd);
 		}
 		ic->scan_dents = NULL;
@@ -241,11 +284,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c,
 
 			/* Reduce nlink of the child. If it's now zero, stick it on the
 			   dead_fds list to be cleaned up later. Else just free the fd */
-
-			if (fd->type == DT_DIR)
-				child_ic->pino_nlink = 0;
-			else
-				child_ic->pino_nlink--;
+			child_ic->pino_nlink--;
 
 			if (!child_ic->pino_nlink) {
 				dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n",
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index d211b8e18566..30c4c9ebb693 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -843,9 +843,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 
 		pr_notice("%s(): Link succeeded, unlink failed (err %d). You now have a hard link\n",
 			  __func__, ret);
-		/* Might as well let the VFS know */
-		d_instantiate(new_dentry, d_inode(old_dentry));
-		ihold(d_inode(old_dentry));
+		/*
+		 * We can't keep the target in dcache after that.
+		 * For one thing, we can't afford dentry aliases for directories.
+		 * For another, if there was a victim, we _can't_ set new inode
+		 * for that sucker and we have to trigger mount eviction - the
+		 * caller won't do it on its own since we are returning an error.
+		 */
+		d_invalidate(new_dentry);
 		new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now);
 		return ret;
 	}
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index c5ac5944bc1b..cad86bac3453 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -137,39 +137,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	struct page *pg;
 	struct inode *inode = mapping->host;
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
-	struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
-	struct jffs2_raw_inode ri;
-	uint32_t alloc_len = 0;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 	uint32_t pageofs = index << PAGE_CACHE_SHIFT;
 	int ret = 0;
 
-	jffs2_dbg(1, "%s()\n", __func__);
-
-	if (pageofs > inode->i_size) {
-		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
-					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
-		if (ret)
-			return ret;
-	}
-
-	mutex_lock(&f->sem);
 	pg = grab_cache_page_write_begin(mapping, index, flags);
-	if (!pg) {
-		if (alloc_len)
-			jffs2_complete_reservation(c);
-		mutex_unlock(&f->sem);
+	if (!pg)
 		return -ENOMEM;
-	}
 	*pagep = pg;
 
-	if (alloc_len) {
+	jffs2_dbg(1, "%s()\n", __func__);
+
+	if (pageofs > inode->i_size) {
 		/* Make new hole frag from old EOF to new page */
+		struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
+		struct jffs2_raw_inode ri;
 		struct jffs2_full_dnode *fn;
+		uint32_t alloc_len;
 
 		jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
 			  (unsigned int)inode->i_size, pageofs);
 
+		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
+					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
+		if (ret)
+			goto out_page;
+
+		mutex_lock(&f->sem);
 		memset(&ri, 0, sizeof(ri));
 
 		ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
@@ -196,6 +190,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		if (IS_ERR(fn)) {
 			ret = PTR_ERR(fn);
 			jffs2_complete_reservation(c);
+			mutex_unlock(&f->sem);
 			goto out_page;
 		}
 		ret = jffs2_add_full_dnode_to_inode(c, f, fn);
@@ -210,10 +205,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 			jffs2_mark_node_obsolete(c, fn->raw);
 			jffs2_free_full_dnode(fn);
 			jffs2_complete_reservation(c);
+			mutex_unlock(&f->sem);
 			goto out_page;
 		}
 		jffs2_complete_reservation(c);
 		inode->i_size = pageofs;
+		mutex_unlock(&f->sem);
 	}
 
 	/*
@@ -222,18 +219,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	 * case of a short-copy.
 	 */
 	if (!PageUptodate(pg)) {
+		mutex_lock(&f->sem);
 		ret = jffs2_do_readpage_nolock(inode, pg);
+		mutex_unlock(&f->sem);
 		if (ret)
 			goto out_page;
 	}
-	mutex_unlock(&f->sem);
 	jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
 	return ret;
 
 out_page:
 	unlock_page(pg);
 	page_cache_release(pg);
-	mutex_unlock(&f->sem);
 	return ret;
 }
 
diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c
index 5a2dec2b064c..7e553f286775 100644
--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -134,37 +134,59 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 	if (mutex_lock_interruptible(&c->alloc_sem))
 		return -EINTR;
 
+
 	for (;;) {
+		/* We can't start doing GC until we've finished checking
+		   the node CRCs etc. */
+		int bucket, want_ino;
+
 		spin_lock(&c->erase_completion_lock);
 		if (!c->unchecked_size)
 			break;
-
-		/* We can't start doing GC yet. We haven't finished checking
-		   the node CRCs etc. Do it now. */
-
-		/* checked_ino is protected by the alloc_sem */
-		if (c->checked_ino > c->highest_ino && xattr) {
-			pr_crit("Checked all inodes but still 0x%x bytes of unchecked space?\n",
-				c->unchecked_size);
-			jffs2_dbg_dump_block_lists_nolock(c);
-			spin_unlock(&c->erase_completion_lock);
-			mutex_unlock(&c->alloc_sem);
-			return -ENOSPC;
-		}
-
 		spin_unlock(&c->erase_completion_lock);
 
 		if (!xattr)
 			xattr = jffs2_verify_xattr(c);
 
 		spin_lock(&c->inocache_lock);
+		/* Instead of doing the inodes in numeric order, doing a lookup
+		 * in the hash for each possible number, just walk the hash
+		 * buckets of *existing* inodes. This means that we process
+		 * them out-of-order, but it can be a lot faster if there's
+		 * a sparse inode# space. Which there often is. */
+		want_ino = c->check_ino;
+		for (bucket = c->check_ino % c->inocache_hashsize ; bucket < c->inocache_hashsize; bucket++) {
+			for (ic = c->inocache_list[bucket]; ic; ic = ic->next) {
+				if (ic->ino < want_ino)
+					continue;
+
+				if (ic->state != INO_STATE_CHECKEDABSENT &&
+				    ic->state != INO_STATE_PRESENT)
+					goto got_next; /* with inocache_lock held */
+
+				jffs2_dbg(1, "Skipping ino #%u already checked\n",
+					  ic->ino);
+			}
+			want_ino = 0;
+		}
 
-		ic = jffs2_get_ino_cache(c, c->checked_ino++);
+		/* Point c->check_ino past the end of the last bucket. */
+		c->check_ino = ((c->highest_ino + c->inocache_hashsize + 1) &
+				~c->inocache_hashsize) - 1;
 
-		if (!ic) {
-			spin_unlock(&c->inocache_lock);
-			continue;
-		}
+		spin_unlock(&c->inocache_lock);
+
+		pr_crit("Checked all inodes but still 0x%x bytes of unchecked space?\n",
+			c->unchecked_size);
+		jffs2_dbg_dump_block_lists_nolock(c);
+		mutex_unlock(&c->alloc_sem);
+		return -ENOSPC;
+
+	got_next:
+		/* For next time round the loop, we want c->checked_ino to indicate
+		 * the *next* one we want to check. And since we're walking the
+		 * buckets rather than doing it sequentially, it's: */
+		c->check_ino = ic->ino + c->inocache_hashsize;
 
 		if (!ic->pino_nlink) {
 			jffs2_dbg(1, "Skipping check of ino #%d with nlink/pino zero\n",
@@ -176,8 +198,6 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 		switch(ic->state) {
 		case INO_STATE_CHECKEDABSENT:
 		case INO_STATE_PRESENT:
-			jffs2_dbg(1, "Skipping ino #%u already checked\n",
-				  ic->ino);
 			spin_unlock(&c->inocache_lock);
 			continue;
 
@@ -196,7 +216,7 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 				  ic->ino);
 			/* We need to come back again for the _same_ inode. We've
 			 made no progress in this case, but that should be OK */
-			c->checked_ino--;
+			c->check_ino = ic->ino;
 
 			mutex_unlock(&c->alloc_sem);
 			sleep_on_spinunlock(&c->inocache_wq, &c->inocache_lock);
@@ -1296,14 +1316,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 		BUG_ON(start > orig_start);
 	}
 
-	/* First, use readpage() to read the appropriate page into the page cache */
-	/* Q: What happens if we actually try to GC the _same_ page for which commit_write()
-	 *    triggered garbage collection in the first place?
-	 * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the
-	 *    page OK. We'll actually write it out again in commit_write, which is a little
-	 *    suboptimal, but at least we're correct.
-	 */
+	/* The rules state that we must obtain the page lock *before* f->sem, so
+	 * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's
+	 * actually going to *change* so we're safe; we only allow reading.
+	 *
+	 * It is important to note that jffs2_write_begin() will ensure that its
+	 * page is marked Uptodate before allocating space. That means that if we
+	 * end up here trying to GC the *same* page that jffs2_write_begin() is
+	 * trying to write out, read_cache_page() will not deadlock. */
+	mutex_unlock(&f->sem);
 	pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg);
+	mutex_lock(&f->sem);
 
 	if (IS_ERR(pg_ptr)) {
 		pr_warn("read_cache_page() returned error: %ld\n",
diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h
index 046fee8b6e9b..778275f48a87 100644
--- a/fs/jffs2/jffs2_fs_sb.h
+++ b/fs/jffs2/jffs2_fs_sb.h
@@ -49,7 +49,7 @@ struct jffs2_sb_info {
 	struct mtd_info *mtd;
 
 	uint32_t highest_ino;
-	uint32_t checked_ino;
+	uint32_t check_ino;		/* *NEXT* inode to be checked */
 
 	unsigned int flags;
 
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index fa35ff79ab35..0637271f3770 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -194,6 +194,7 @@ struct jffs2_inode_cache {
 #define INO_STATE_CLEARING	6	/* In clear_inode() */
 
 #define INO_FLAGS_XATTR_CHECKED	0x01	/* has no duplicate xattr_ref */
+#define INO_FLAGS_IS_DIR	0x02	/* is a directory */
 
 #define RAWNODE_CLASS_INODE_CACHE	0
 #define RAWNODE_CLASS_XATTR_DATUM	1
@@ -249,7 +250,10 @@ struct jffs2_readinode_info
 
 struct jffs2_full_dirent
 {
-	struct jffs2_raw_node_ref *raw;
+	union {
+		struct jffs2_raw_node_ref *raw;
+		struct jffs2_inode_cache *ic; /* Just during part of build */
+	};
 	struct jffs2_full_dirent *next;
 	uint32_t version;
 	uint32_t ino; /* == zero for unlink */
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index b6bd4affd9ad..cda0774c2c9c 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -846,8 +846,8 @@ int jffs2_thread_should_wake(struct jffs2_sb_info *c)
 		return 1;
 
 	if (c->unchecked_size) {
-		jffs2_dbg(1, "jffs2_thread_should_wake(): unchecked_size %d, checked_ino #%d\n",
-			  c->unchecked_size, c->checked_ino);
+		jffs2_dbg(1, "jffs2_thread_should_wake(): unchecked_size %d, check_ino #%d\n",
+			  c->unchecked_size, c->check_ino);
 		return 1;
 	}
 
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index 5a3da3f52908..b25d28a21212 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -1183,22 +1183,20 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c)
 
 int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
 {
-	struct nand_ecclayout *oinfo = c->mtd->ecclayout;
-
 	if (!c->mtd->oobsize)
 		return 0;
 
 	/* Cleanmarker is out-of-band, so inline size zero */
 	c->cleanmarker_size = 0;
 
-	if (!oinfo || oinfo->oobavail == 0) {
+	if (c->mtd->oobavail == 0) {
 		pr_err("inconsistent device description\n");
 		return -EINVAL;
 	}
 
 	jffs2_dbg(1, "using OOB on NAND\n");
 
-	c->oobavail = oinfo->oobavail;
+	c->oobavail = c->mtd->oobavail;
 
 	/* Initialise write buffer */
 	init_rwsem(&c->wbuf_sem);
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 996b7742c90b..03b688d19f69 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -44,28 +44,122 @@ static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
 	return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
 }
 
-static char * __must_check kernfs_path_locked(struct kernfs_node *kn, char *buf,
-					      size_t buflen)
+/* kernfs_node_depth - compute depth from @from to @to */
+static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to)
 {
-	char *p = buf + buflen;
-	int len;
+	size_t depth = 0;
 
-	*--p = '\0';
+	while (to->parent && to != from) {
+		depth++;
+		to = to->parent;
+	}
+	return depth;
+}
 
-	do {
-		len = strlen(kn->name);
-		if (p - buf < len + 1) {
-			buf[0] = '\0';
-			p = NULL;
-			break;
-		}
-		p -= len;
-		memcpy(p, kn->name, len);
-		*--p = '/';
-		kn = kn->parent;
-	} while (kn && kn->parent);
+static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a,
+						  struct kernfs_node *b)
+{
+	size_t da, db;
+	struct kernfs_root *ra = kernfs_root(a), *rb = kernfs_root(b);
+
+	if (ra != rb)
+		return NULL;
+
+	da = kernfs_depth(ra->kn, a);
+	db = kernfs_depth(rb->kn, b);
+
+	while (da > db) {
+		a = a->parent;
+		da--;
+	}
+	while (db > da) {
+		b = b->parent;
+		db--;
+	}
+
+	/* worst case b and a will be the same at root */
+	while (b != a) {
+		b = b->parent;
+		a = a->parent;
+	}
+
+	return a;
+}
+
+/**
+ * kernfs_path_from_node_locked - find a pseudo-absolute path to @kn_to,
+ * where kn_from is treated as root of the path.
+ * @kn_from: kernfs node which should be treated as root for the path
+ * @kn_to: kernfs node to which path is needed
+ * @buf: buffer to copy the path into
+ * @buflen: size of @buf
+ *
+ * We need to handle couple of scenarios here:
+ * [1] when @kn_from is an ancestor of @kn_to at some level
+ * kn_from: /n1/n2/n3
+ * kn_to:   /n1/n2/n3/n4/n5
+ * result:  /n4/n5
+ *
+ * [2] when @kn_from is on a different hierarchy and we need to find common
+ * ancestor between @kn_from and @kn_to.
+ * kn_from: /n1/n2/n3/n4
+ * kn_to:   /n1/n2/n5
+ * result:  /../../n5
+ * OR
+ * kn_from: /n1/n2/n3/n4/n5   [depth=5]
+ * kn_to:   /n1/n2/n3         [depth=3]
+ * result:  /../..
+ *
+ * return value: length of the string.  If greater than buflen,
+ * then contents of buf are undefined.  On error, -1 is returned.
+ */
+static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
+					struct kernfs_node *kn_from,
+					char *buf, size_t buflen)
+{
+	struct kernfs_node *kn, *common;
+	const char parent_str[] = "/..";
+	size_t depth_from, depth_to, len = 0, nlen = 0;
+	char *p;
+	int i;
+
+	if (!kn_from)
+		kn_from = kernfs_root(kn_to)->kn;
+
+	if (kn_from == kn_to)
+		return strlcpy(buf, "/", buflen);
+
+	common = kernfs_common_ancestor(kn_from, kn_to);
+	if (WARN_ON(!common))
+		return -1;
+
+	depth_to = kernfs_depth(common, kn_to);
+	depth_from = kernfs_depth(common, kn_from);
+
+	if (buf)
+		buf[0] = '\0';
+
+	for (i = 0; i < depth_from; i++)
+		len += strlcpy(buf + len, parent_str,
+			       len < buflen ? buflen - len : 0);
+
+	/* Calculate how many bytes we need for the rest */
+	for (kn = kn_to; kn != common; kn = kn->parent)
+		nlen += strlen(kn->name) + 1;
+
+	if (len + nlen >= buflen)
+		return len + nlen;
+
+	p = buf + len + nlen;
+	*p = '\0';
+	for (kn = kn_to; kn != common; kn = kn->parent) {
+		nlen = strlen(kn->name);
+		p -= nlen;
+		memcpy(p, kn->name, nlen);
+		*(--p) = '/';
+	}
 
-	return p;
+	return len + nlen;
 }
 
 /**
@@ -115,6 +209,34 @@ size_t kernfs_path_len(struct kernfs_node *kn)
 }
 
 /**
+ * kernfs_path_from_node - build path of node @to relative to @from.
+ * @from: parent kernfs_node relative to which we need to build the path
+ * @to: kernfs_node of interest
+ * @buf: buffer to copy @to's path into
+ * @buflen: size of @buf
+ *
+ * Builds @to's path relative to @from in @buf. @from and @to must
+ * be on the same kernfs-root. If @from is not parent of @to, then a relative
+ * path (which includes '..'s) as needed to reach from @from to @to is
+ * returned.
+ *
+ * If @buf isn't long enough, the return value will be greater than @buflen
+ * and @buf contents are undefined.
+ */
+int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from,
+			  char *buf, size_t buflen)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	ret = kernfs_path_from_node_locked(to, from, buf, buflen);
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kernfs_path_from_node);
+
+/**
  * kernfs_path - build full path of a given node
  * @kn: kernfs_node of interest
  * @buf: buffer to copy @kn's name into
@@ -127,13 +249,12 @@ size_t kernfs_path_len(struct kernfs_node *kn)
  */
 char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
 {
-	unsigned long flags;
-	char *p;
+	int ret;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
-	p = kernfs_path_locked(kn, buf, buflen);
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
-	return p;
+	ret = kernfs_path_from_node(kn, NULL, buf, buflen);
+	if (ret < 0 || ret >= buflen)
+		return NULL;
+	return buf;
 }
 EXPORT_SYMBOL_GPL(kernfs_path);
 
@@ -164,17 +285,25 @@ void pr_cont_kernfs_name(struct kernfs_node *kn)
 void pr_cont_kernfs_path(struct kernfs_node *kn)
 {
 	unsigned long flags;
-	char *p;
+	int sz;
 
 	spin_lock_irqsave(&kernfs_rename_lock, flags);
 
-	p = kernfs_path_locked(kn, kernfs_pr_cont_buf,
-			       sizeof(kernfs_pr_cont_buf));
-	if (p)
-		pr_cont("%s", p);
-	else
-		pr_cont("<name too long>");
+	sz = kernfs_path_from_node_locked(kn, NULL, kernfs_pr_cont_buf,
+					  sizeof(kernfs_pr_cont_buf));
+	if (sz < 0) {
+		pr_cont("(error)");
+		goto out;
+	}
+
+	if (sz >= sizeof(kernfs_pr_cont_buf)) {
+		pr_cont("(name too long)");
+		goto out;
+	}
 
+	pr_cont("%s", kernfs_pr_cont_buf);
+
+out:
 	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
 }
 
@@ -691,15 +820,22 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 					  const unsigned char *path,
 					  const void *ns)
 {
-	static char path_buf[PATH_MAX];	/* protected by kernfs_mutex */
-	size_t len = strlcpy(path_buf, path, PATH_MAX);
-	char *p = path_buf;
-	char *name;
+	size_t len;
+	char *p, *name;
 
 	lockdep_assert_held(&kernfs_mutex);
 
-	if (len >= PATH_MAX)
+	/* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */
+	spin_lock_irq(&kernfs_rename_lock);
+
+	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
+
+	if (len >= sizeof(kernfs_pr_cont_buf)) {
+		spin_unlock_irq(&kernfs_rename_lock);
 		return NULL;
+	}
+
+	p = kernfs_pr_cont_buf;
 
 	while ((name = strsep(&p, "/")) && parent) {
 		if (*name == '\0')
@@ -707,6 +843,8 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 		parent = kernfs_find_ns(parent, name, ns);
 	}
 
+	spin_unlock_irq(&kernfs_rename_lock);
+
 	return parent;
 }
 
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 8eaf417187f1..b67dbccdaf88 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -14,6 +14,7 @@
 #include <linux/magic.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include <linux/namei.h>
 
 #include "kernfs-internal.h"
 
@@ -62,6 +63,74 @@ struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
 	return NULL;
 }
 
+/*
+ * find the next ancestor in the path down to @child, where @parent was the
+ * ancestor whose descendant we want to find.
+ *
+ * Say the path is /a/b/c/d.  @child is d, @parent is NULL.  We return the root
+ * node.  If @parent is b, then we return the node for c.
+ * Passing in d as @parent is not ok.
+ */
+static struct kernfs_node *find_next_ancestor(struct kernfs_node *child,
+					      struct kernfs_node *parent)
+{
+	if (child == parent) {
+		pr_crit_once("BUG in find_next_ancestor: called with parent == child");
+		return NULL;
+	}
+
+	while (child->parent != parent) {
+		if (!child->parent)
+			return NULL;
+		child = child->parent;
+	}
+
+	return child;
+}
+
+/**
+ * kernfs_node_dentry - get a dentry for the given kernfs_node
+ * @kn: kernfs_node for which a dentry is needed
+ * @sb: the kernfs super_block
+ */
+struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
+				  struct super_block *sb)
+{
+	struct dentry *dentry;
+	struct kernfs_node *knparent = NULL;
+
+	BUG_ON(sb->s_op != &kernfs_sops);
+
+	dentry = dget(sb->s_root);
+
+	/* Check if this is the root kernfs_node */
+	if (!kn->parent)
+		return dentry;
+
+	knparent = find_next_ancestor(kn, NULL);
+	if (WARN_ON(!knparent))
+		return ERR_PTR(-EINVAL);
+
+	do {
+		struct dentry *dtmp;
+		struct kernfs_node *kntmp;
+
+		if (kn == knparent)
+			return dentry;
+		kntmp = find_next_ancestor(kn, knparent);
+		if (WARN_ON(!kntmp))
+			return ERR_PTR(-EINVAL);
+		mutex_lock(&d_inode(dentry)->i_mutex);
+		dtmp = lookup_one_len(kntmp->name, dentry, strlen(kntmp->name));
+		mutex_unlock(&d_inode(dentry)->i_mutex);
+		dput(dentry);
+		if (IS_ERR(dtmp))
+			return dtmp;
+		knparent = kntmp;
+		dentry = dtmp;
+	} while (true);
+}
+
 static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 187477ded6b3..eccda3a02de6 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -1,858 +1,433 @@
-/*
- * linux/fs/mbcache.c
- * (C) 2001-2002 Andreas Gruenbacher, <a.gruenbacher@computer.org>
- */
-
-/*
- * Filesystem Meta Information Block Cache (mbcache)
- *
- * The mbcache caches blocks of block devices that need to be located
- * by their device/block number, as well as by other criteria (such
- * as the block's contents).
- *
- * There can only be one cache entry in a cache per device and block number.
- * Additional indexes need not be unique in this sense. The number of
- * additional indexes (=other criteria) can be hardwired at compile time
- * or specified at cache create time.
- *
- * Each cache entry is of fixed size. An entry may be `valid' or `invalid'
- * in the cache. A valid entry is in the main hash tables of the cache,
- * and may also be in the lru list. An invalid entry is not in any hashes
- * or lists.
- *
- * A valid cache entry is only in the lru list if no handles refer to it.
- * Invalid cache entries will be freed when the last handle to the cache
- * entry is released. Entries that cannot be freed immediately are put
- * back on the lru list.
- */
-
-/*
- * Lock descriptions and usage:
- *
- * Each hash chain of both the block and index hash tables now contains
- * a built-in lock used to serialize accesses to the hash chain.
- *
- * Accesses to global data structures mb_cache_list and mb_cache_lru_list
- * are serialized via the global spinlock mb_cache_spinlock.
- *
- * Each mb_cache_entry contains a spinlock, e_entry_lock, to serialize
- * accesses to its local data, such as e_used and e_queued.
- *
- * Lock ordering:
- *
- * Each block hash chain's lock has the highest lock order, followed by an
- * index hash chain's lock, mb_cache_bg_lock (used to implement mb_cache_entry's
- * lock), and mb_cach_spinlock, with the lowest order.  While holding
- * either a block or index hash chain lock, a thread can acquire an
- * mc_cache_bg_lock, which in turn can also acquire mb_cache_spinlock.
- *
- * Synchronization:
- *
- * Since both mb_cache_entry_get and mb_cache_entry_find scan the block and
- * index hash chian, it needs to lock the corresponding hash chain.  For each
- * mb_cache_entry within the chain, it needs to lock the mb_cache_entry to
- * prevent either any simultaneous release or free on the entry and also
- * to serialize accesses to either the e_used or e_queued member of the entry.
- *
- * To avoid having a dangling reference to an already freed
- * mb_cache_entry, an mb_cache_entry is only freed when it is not on a
- * block hash chain and also no longer being referenced, both e_used,
- * and e_queued are 0's.  When an mb_cache_entry is explicitly freed it is
- * first removed from a block hash chain.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include <linux/hash.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
+#include <linux/spinlock.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/list.h>
 #include <linux/list_bl.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/workqueue.h>
 #include <linux/mbcache.h>
-#include <linux/init.h>
-#include <linux/blockgroup_lock.h>
-#include <linux/log2.h>
-
-#ifdef MB_CACHE_DEBUG
-# define mb_debug(f...) do { \
-		printk(KERN_DEBUG f); \
-		printk("\n"); \
-	} while (0)
-#define mb_assert(c) do { if (!(c)) \
-		printk(KERN_ERR "assertion " #c " failed\n"); \
-	} while(0)
-#else
-# define mb_debug(f...) do { } while(0)
-# define mb_assert(c) do { } while(0)
-#endif
-#define mb_error(f...) do { \
-		printk(KERN_ERR f); \
-		printk("\n"); \
-	} while(0)
-
-#define MB_CACHE_WRITER ((unsigned short)~0U >> 1)
-
-#define MB_CACHE_ENTRY_LOCK_BITS	ilog2(NR_BG_LOCKS)
-#define	MB_CACHE_ENTRY_LOCK_INDEX(ce)			\
-	(hash_long((unsigned long)ce, MB_CACHE_ENTRY_LOCK_BITS))
-
-static DECLARE_WAIT_QUEUE_HEAD(mb_cache_queue);
-static struct blockgroup_lock *mb_cache_bg_lock;
-static struct kmem_cache *mb_cache_kmem_cache;
-
-MODULE_AUTHOR("Andreas Gruenbacher <a.gruenbacher@computer.org>");
-MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
-MODULE_LICENSE("GPL");
-
-EXPORT_SYMBOL(mb_cache_create);
-EXPORT_SYMBOL(mb_cache_shrink);
-EXPORT_SYMBOL(mb_cache_destroy);
-EXPORT_SYMBOL(mb_cache_entry_alloc);
-EXPORT_SYMBOL(mb_cache_entry_insert);
-EXPORT_SYMBOL(mb_cache_entry_release);
-EXPORT_SYMBOL(mb_cache_entry_free);
-EXPORT_SYMBOL(mb_cache_entry_get);
-#if !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0)
-EXPORT_SYMBOL(mb_cache_entry_find_first);
-EXPORT_SYMBOL(mb_cache_entry_find_next);
-#endif
 
 /*
- * Global data: list of all mbcache's, lru list, and a spinlock for
- * accessing cache data structures on SMP machines. The lru list is
- * global across all mbcaches.
+ * Mbcache is a simple key-value store. Keys need not be unique, however
+ * key-value pairs are expected to be unique (we use this fact in
+ * mb_cache_entry_delete_block()).
+ *
+ * Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
+ * They use hash of a block contents as a key and block number as a value.
+ * That's why keys need not be unique (different xattr blocks may end up having
+ * the same hash). However block number always uniquely identifies a cache
+ * entry.
+ *
+ * We provide functions for creation and removal of entries, search by key,
+ * and a special "delete entry with given key-value pair" operation. Fixed
+ * size hash table is used for fast key lookups.
  */
 
-static LIST_HEAD(mb_cache_list);
-static LIST_HEAD(mb_cache_lru_list);
-static DEFINE_SPINLOCK(mb_cache_spinlock);
-
-static inline void
-__spin_lock_mb_cache_entry(struct mb_cache_entry *ce)
-{
-	spin_lock(bgl_lock_ptr(mb_cache_bg_lock,
-		MB_CACHE_ENTRY_LOCK_INDEX(ce)));
-}
-
-static inline void
-__spin_unlock_mb_cache_entry(struct mb_cache_entry *ce)
-{
-	spin_unlock(bgl_lock_ptr(mb_cache_bg_lock,
-		MB_CACHE_ENTRY_LOCK_INDEX(ce)));
-}
-
-static inline int
-__mb_cache_entry_is_block_hashed(struct mb_cache_entry *ce)
-{
-	return !hlist_bl_unhashed(&ce->e_block_list);
-}
+struct mb_cache {
+	/* Hash table of entries */
+	struct hlist_bl_head	*c_hash;
+	/* log2 of hash table size */
+	int			c_bucket_bits;
+	/* Maximum entries in cache to avoid degrading hash too much */
+	int			c_max_entries;
+	/* Protects c_list, c_entry_count */
+	spinlock_t		c_list_lock;
+	struct list_head	c_list;
+	/* Number of entries in cache */
+	unsigned long		c_entry_count;
+	struct shrinker		c_shrink;
+	/* Work for shrinking when the cache has too many entries */
+	struct work_struct	c_shrink_work;
+};
 
+static struct kmem_cache *mb_entry_cache;
 
-static inline void
-__mb_cache_entry_unhash_block(struct mb_cache_entry *ce)
-{
-	if (__mb_cache_entry_is_block_hashed(ce))
-		hlist_bl_del_init(&ce->e_block_list);
-}
+static unsigned long mb_cache_shrink(struct mb_cache *cache,
+				     unsigned int nr_to_scan);
 
-static inline int
-__mb_cache_entry_is_index_hashed(struct mb_cache_entry *ce)
+static inline struct hlist_bl_head *mb_cache_entry_head(struct mb_cache *cache,
+							u32 key)
 {
-	return !hlist_bl_unhashed(&ce->e_index.o_list);
+	return &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
 }
 
-static inline void
-__mb_cache_entry_unhash_index(struct mb_cache_entry *ce)
-{
-	if (__mb_cache_entry_is_index_hashed(ce))
-		hlist_bl_del_init(&ce->e_index.o_list);
-}
+/*
+ * Number of entries to reclaim synchronously when there are too many entries
+ * in cache
+ */
+#define SYNC_SHRINK_BATCH 64
 
 /*
- * __mb_cache_entry_unhash_unlock()
- *
- * This function is called to unhash both the block and index hash
- * chain.
- * It assumes both the block and index hash chain is locked upon entry.
- * It also unlock both hash chains both exit
+ * mb_cache_entry_create - create entry in cache
+ * @cache - cache where the entry should be created
+ * @mask - gfp mask with which the entry should be allocated
+ * @key - key of the entry
+ * @block - block that contains data
+ * @reusable - is the block reusable by other inodes?
+ *
+ * Creates entry in @cache with key @key and records that data is stored in
+ * block @block. The function returns -EBUSY if entry with the same key
+ * and for the same block already exists in cache. Otherwise 0 is returned.
  */
-static inline void
-__mb_cache_entry_unhash_unlock(struct mb_cache_entry *ce)
+int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
+			  sector_t block, bool reusable)
 {
-	__mb_cache_entry_unhash_index(ce);
-	hlist_bl_unlock(ce->e_index_hash_p);
-	__mb_cache_entry_unhash_block(ce);
-	hlist_bl_unlock(ce->e_block_hash_p);
+	struct mb_cache_entry *entry, *dup;
+	struct hlist_bl_node *dup_node;
+	struct hlist_bl_head *head;
+
+	/* Schedule background reclaim if there are too many entries */
+	if (cache->c_entry_count >= cache->c_max_entries)
+		schedule_work(&cache->c_shrink_work);
+	/* Do some sync reclaim if background reclaim cannot keep up */
+	if (cache->c_entry_count >= 2*cache->c_max_entries)
+		mb_cache_shrink(cache, SYNC_SHRINK_BATCH);
+
+	entry = kmem_cache_alloc(mb_entry_cache, mask);
+	if (!entry)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&entry->e_list);
+	/* One ref for hash, one ref returned */
+	atomic_set(&entry->e_refcnt, 1);
+	entry->e_key = key;
+	entry->e_block = block;
+	entry->e_reusable = reusable;
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) {
+		if (dup->e_key == key && dup->e_block == block) {
+			hlist_bl_unlock(head);
+			kmem_cache_free(mb_entry_cache, entry);
+			return -EBUSY;
+		}
+	}
+	hlist_bl_add_head(&entry->e_hash_list, head);
+	hlist_bl_unlock(head);
+
+	spin_lock(&cache->c_list_lock);
+	list_add_tail(&entry->e_list, &cache->c_list);
+	/* Grab ref for LRU list */
+	atomic_inc(&entry->e_refcnt);
+	cache->c_entry_count++;
+	spin_unlock(&cache->c_list_lock);
+
+	return 0;
 }
+EXPORT_SYMBOL(mb_cache_entry_create);
 
-static void
-__mb_cache_entry_forget(struct mb_cache_entry *ce, gfp_t gfp_mask)
+void __mb_cache_entry_free(struct mb_cache_entry *entry)
 {
-	struct mb_cache *cache = ce->e_cache;
-
-	mb_assert(!(ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt)));
-	kmem_cache_free(cache->c_entry_cache, ce);
-	atomic_dec(&cache->c_entry_count);
+	kmem_cache_free(mb_entry_cache, entry);
 }
+EXPORT_SYMBOL(__mb_cache_entry_free);
 
-static void
-__mb_cache_entry_release(struct mb_cache_entry *ce)
+static struct mb_cache_entry *__entry_find(struct mb_cache *cache,
+					   struct mb_cache_entry *entry,
+					   u32 key)
 {
-	/* First lock the entry to serialize access to its local data. */
-	__spin_lock_mb_cache_entry(ce);
-	/* Wake up all processes queuing for this cache entry. */
-	if (ce->e_queued)
-		wake_up_all(&mb_cache_queue);
-	if (ce->e_used >= MB_CACHE_WRITER)
-		ce->e_used -= MB_CACHE_WRITER;
-	/*
-	 * Make sure that all cache entries on lru_list have
-	 * both e_used and e_qued of 0s.
-	 */
-	ce->e_used--;
-	if (!(ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt))) {
-		if (!__mb_cache_entry_is_block_hashed(ce)) {
-			__spin_unlock_mb_cache_entry(ce);
-			goto forget;
+	struct mb_cache_entry *old_entry = entry;
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	if (entry && !hlist_bl_unhashed(&entry->e_hash_list))
+		node = entry->e_hash_list.next;
+	else
+		node = hlist_bl_first(head);
+	while (node) {
+		entry = hlist_bl_entry(node, struct mb_cache_entry,
+				       e_hash_list);
+		if (entry->e_key == key && entry->e_reusable) {
+			atomic_inc(&entry->e_refcnt);
+			goto out;
 		}
-		/*
-		 * Need access to lru list, first drop entry lock,
-		 * then reacquire the lock in the proper order.
-		 */
-		spin_lock(&mb_cache_spinlock);
-		if (list_empty(&ce->e_lru_list))
-			list_add_tail(&ce->e_lru_list, &mb_cache_lru_list);
-		spin_unlock(&mb_cache_spinlock);
+		node = node->next;
 	}
-	__spin_unlock_mb_cache_entry(ce);
-	return;
-forget:
-	mb_assert(list_empty(&ce->e_lru_list));
-	__mb_cache_entry_forget(ce, GFP_KERNEL);
+	entry = NULL;
+out:
+	hlist_bl_unlock(head);
+	if (old_entry)
+		mb_cache_entry_put(cache, old_entry);
+
+	return entry;
 }
 
 /*
- * mb_cache_shrink_scan()  memory pressure callback
- *
- * This function is called by the kernel memory management when memory
- * gets low.
+ * mb_cache_entry_find_first - find the first entry in cache with given key
+ * @cache: cache where we should search
+ * @key: key to look for
  *
- * @shrink: (ignored)
- * @sc: shrink_control passed from reclaim
- *
- * Returns the number of objects freed.
+ * Search in @cache for entry with key @key. Grabs reference to the first
+ * entry found and returns the entry.
  */
-static unsigned long
-mb_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache,
+						 u32 key)
 {
-	LIST_HEAD(free_list);
-	struct mb_cache_entry *entry, *tmp;
-	int nr_to_scan = sc->nr_to_scan;
-	gfp_t gfp_mask = sc->gfp_mask;
-	unsigned long freed = 0;
-
-	mb_debug("trying to free %d entries", nr_to_scan);
-	spin_lock(&mb_cache_spinlock);
-	while ((nr_to_scan-- > 0) && !list_empty(&mb_cache_lru_list)) {
-		struct mb_cache_entry *ce =
-			list_entry(mb_cache_lru_list.next,
-				struct mb_cache_entry, e_lru_list);
-		list_del_init(&ce->e_lru_list);
-		if (ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt))
-			continue;
-		spin_unlock(&mb_cache_spinlock);
-		/* Prevent any find or get operation on the entry */
-		hlist_bl_lock(ce->e_block_hash_p);
-		hlist_bl_lock(ce->e_index_hash_p);
-		/* Ignore if it is touched by a find/get */
-		if (ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt) ||
-			!list_empty(&ce->e_lru_list)) {
-			hlist_bl_unlock(ce->e_index_hash_p);
-			hlist_bl_unlock(ce->e_block_hash_p);
-			spin_lock(&mb_cache_spinlock);
-			continue;
-		}
-		__mb_cache_entry_unhash_unlock(ce);
-		list_add_tail(&ce->e_lru_list, &free_list);
-		spin_lock(&mb_cache_spinlock);
-	}
-	spin_unlock(&mb_cache_spinlock);
-
-	list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) {
-		__mb_cache_entry_forget(entry, gfp_mask);
-		freed++;
-	}
-	return freed;
+	return __entry_find(cache, NULL, key);
 }
+EXPORT_SYMBOL(mb_cache_entry_find_first);
 
-static unsigned long
-mb_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+/*
+ * mb_cache_entry_find_next - find next entry in cache with the same
+ * @cache: cache where we should search
+ * @entry: entry to start search from
+ *
+ * Finds next entry in the hash chain which has the same key as @entry.
+ * If @entry is unhashed (which can happen when deletion of entry races
+ * with the search), finds the first entry in the hash chain. The function
+ * drops reference to @entry and returns with a reference to the found entry.
+ */
+struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache,
+						struct mb_cache_entry *entry)
 {
-	struct mb_cache *cache;
-	unsigned long count = 0;
-
-	spin_lock(&mb_cache_spinlock);
-	list_for_each_entry(cache, &mb_cache_list, c_cache_list) {
-		mb_debug("cache %s (%d)", cache->c_name,
-			  atomic_read(&cache->c_entry_count));
-		count += atomic_read(&cache->c_entry_count);
-	}
-	spin_unlock(&mb_cache_spinlock);
-
-	return vfs_pressure_ratio(count);
+	return __entry_find(cache, entry, entry->e_key);
 }
-
-static struct shrinker mb_cache_shrinker = {
-	.count_objects = mb_cache_shrink_count,
-	.scan_objects = mb_cache_shrink_scan,
-	.seeks = DEFAULT_SEEKS,
-};
+EXPORT_SYMBOL(mb_cache_entry_find_next);
 
 /*
- * mb_cache_create()  create a new cache
- *
- * All entries in one cache are equal size. Cache entries may be from
- * multiple devices. If this is the first mbcache created, registers
- * the cache with kernel memory management. Returns NULL if no more
- * memory was available.
- *
- * @name: name of the cache (informal)
- * @bucket_bits: log2(number of hash buckets)
+ * mb_cache_entry_get - get a cache entry by block number (and key)
+ * @cache - cache we work with
+ * @key - key of block number @block
+ * @block - block number
  */
-struct mb_cache *
-mb_cache_create(const char *name, int bucket_bits)
+struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key,
+					  sector_t block)
 {
-	int n, bucket_count = 1 << bucket_bits;
-	struct mb_cache *cache = NULL;
-
-	if (!mb_cache_bg_lock) {
-		mb_cache_bg_lock = kmalloc(sizeof(struct blockgroup_lock),
-			GFP_KERNEL);
-		if (!mb_cache_bg_lock)
-			return NULL;
-		bgl_lock_init(mb_cache_bg_lock);
-	}
-
-	cache = kmalloc(sizeof(struct mb_cache), GFP_KERNEL);
-	if (!cache)
-		return NULL;
-	cache->c_name = name;
-	atomic_set(&cache->c_entry_count, 0);
-	cache->c_bucket_bits = bucket_bits;
-	cache->c_block_hash = kmalloc(bucket_count *
-		sizeof(struct hlist_bl_head), GFP_KERNEL);
-	if (!cache->c_block_hash)
-		goto fail;
-	for (n=0; n<bucket_count; n++)
-		INIT_HLIST_BL_HEAD(&cache->c_block_hash[n]);
-	cache->c_index_hash = kmalloc(bucket_count *
-		sizeof(struct hlist_bl_head), GFP_KERNEL);
-	if (!cache->c_index_hash)
-		goto fail;
-	for (n=0; n<bucket_count; n++)
-		INIT_HLIST_BL_HEAD(&cache->c_index_hash[n]);
-	if (!mb_cache_kmem_cache) {
-		mb_cache_kmem_cache = kmem_cache_create(name,
-			sizeof(struct mb_cache_entry), 0,
-			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
-		if (!mb_cache_kmem_cache)
-			goto fail2;
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+	struct mb_cache_entry *entry;
+
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+		if (entry->e_key == key && entry->e_block == block) {
+			atomic_inc(&entry->e_refcnt);
+			goto out;
+		}
 	}
-	cache->c_entry_cache = mb_cache_kmem_cache;
-
-	/*
-	 * Set an upper limit on the number of cache entries so that the hash
-	 * chains won't grow too long.
-	 */
-	cache->c_max_entries = bucket_count << 4;
-
-	spin_lock(&mb_cache_spinlock);
-	list_add(&cache->c_cache_list, &mb_cache_list);
-	spin_unlock(&mb_cache_spinlock);
-	return cache;
-
-fail2:
-	kfree(cache->c_index_hash);
-
-fail:
-	kfree(cache->c_block_hash);
-	kfree(cache);
-	return NULL;
+	entry = NULL;
+out:
+	hlist_bl_unlock(head);
+	return entry;
 }
+EXPORT_SYMBOL(mb_cache_entry_get);
 
-
-/*
- * mb_cache_shrink()
- *
- * Removes all cache entries of a device from the cache. All cache entries
- * currently in use cannot be freed, and thus remain in the cache. All others
- * are freed.
+/* mb_cache_entry_delete_block - remove information about block from cache
+ * @cache - cache we work with
+ * @key - key of block @block
+ * @block - block number
  *
- * @bdev: which device's cache entries to shrink
+ * Remove entry from cache @cache with key @key with data stored in @block.
  */
-void
-mb_cache_shrink(struct block_device *bdev)
+void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key,
+				 sector_t block)
 {
-	LIST_HEAD(free_list);
-	struct list_head *l;
-	struct mb_cache_entry *ce, *tmp;
-
-	l = &mb_cache_lru_list;
-	spin_lock(&mb_cache_spinlock);
-	while (!list_is_last(l, &mb_cache_lru_list)) {
-		l = l->next;
-		ce = list_entry(l, struct mb_cache_entry, e_lru_list);
-		if (ce->e_bdev == bdev) {
-			list_del_init(&ce->e_lru_list);
-			if (ce->e_used || ce->e_queued ||
-				atomic_read(&ce->e_refcnt))
-				continue;
-			spin_unlock(&mb_cache_spinlock);
-			/*
-			 * Prevent any find or get operation on the entry.
-			 */
-			hlist_bl_lock(ce->e_block_hash_p);
-			hlist_bl_lock(ce->e_index_hash_p);
-			/* Ignore if it is touched by a find/get */
-			if (ce->e_used || ce->e_queued ||
-				atomic_read(&ce->e_refcnt) ||
-				!list_empty(&ce->e_lru_list)) {
-				hlist_bl_unlock(ce->e_index_hash_p);
-				hlist_bl_unlock(ce->e_block_hash_p);
-				l = &mb_cache_lru_list;
-				spin_lock(&mb_cache_spinlock);
-				continue;
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+	struct mb_cache_entry *entry;
+
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+		if (entry->e_key == key && entry->e_block == block) {
+			/* We keep hash list reference to keep entry alive */
+			hlist_bl_del_init(&entry->e_hash_list);
+			hlist_bl_unlock(head);
+			spin_lock(&cache->c_list_lock);
+			if (!list_empty(&entry->e_list)) {
+				list_del_init(&entry->e_list);
+				cache->c_entry_count--;
+				atomic_dec(&entry->e_refcnt);
 			}
-			__mb_cache_entry_unhash_unlock(ce);
-			mb_assert(!(ce->e_used || ce->e_queued ||
-				atomic_read(&ce->e_refcnt)));
-			list_add_tail(&ce->e_lru_list, &free_list);
-			l = &mb_cache_lru_list;
-			spin_lock(&mb_cache_spinlock);
+			spin_unlock(&cache->c_list_lock);
+			mb_cache_entry_put(cache, entry);
+			return;
 		}
 	}
-	spin_unlock(&mb_cache_spinlock);
-
-	list_for_each_entry_safe(ce, tmp, &free_list, e_lru_list) {
-		__mb_cache_entry_forget(ce, GFP_KERNEL);
-	}
+	hlist_bl_unlock(head);
 }
+EXPORT_SYMBOL(mb_cache_entry_delete_block);
 
-
-/*
- * mb_cache_destroy()
+/* mb_cache_entry_touch - cache entry got used
+ * @cache - cache the entry belongs to
+ * @entry - entry that got used
  *
- * Shrinks the cache to its minimum possible size (hopefully 0 entries),
- * and then destroys it. If this was the last mbcache, un-registers the
- * mbcache from kernel memory management.
+ * Marks entry as used to give hit higher chances of surviving in cache.
  */
-void
-mb_cache_destroy(struct mb_cache *cache)
+void mb_cache_entry_touch(struct mb_cache *cache,
+			  struct mb_cache_entry *entry)
 {
-	LIST_HEAD(free_list);
-	struct mb_cache_entry *ce, *tmp;
-
-	spin_lock(&mb_cache_spinlock);
-	list_for_each_entry_safe(ce, tmp, &mb_cache_lru_list, e_lru_list) {
-		if (ce->e_cache == cache)
-			list_move_tail(&ce->e_lru_list, &free_list);
-	}
-	list_del(&cache->c_cache_list);
-	spin_unlock(&mb_cache_spinlock);
-
-	list_for_each_entry_safe(ce, tmp, &free_list, e_lru_list) {
-		list_del_init(&ce->e_lru_list);
-		/*
-		 * Prevent any find or get operation on the entry.
-		 */
-		hlist_bl_lock(ce->e_block_hash_p);
-		hlist_bl_lock(ce->e_index_hash_p);
-		mb_assert(!(ce->e_used || ce->e_queued ||
-			atomic_read(&ce->e_refcnt)));
-		__mb_cache_entry_unhash_unlock(ce);
-		__mb_cache_entry_forget(ce, GFP_KERNEL);
-	}
-
-	if (atomic_read(&cache->c_entry_count) > 0) {
-		mb_error("cache %s: %d orphaned entries",
-			  cache->c_name,
-			  atomic_read(&cache->c_entry_count));
-	}
-
-	if (list_empty(&mb_cache_list)) {
-		kmem_cache_destroy(mb_cache_kmem_cache);
-		mb_cache_kmem_cache = NULL;
-	}
-	kfree(cache->c_index_hash);
-	kfree(cache->c_block_hash);
-	kfree(cache);
+	entry->e_referenced = 1;
 }
+EXPORT_SYMBOL(mb_cache_entry_touch);
 
-/*
- * mb_cache_entry_alloc()
- *
- * Allocates a new cache entry. The new entry will not be valid initially,
- * and thus cannot be looked up yet. It should be filled with data, and
- * then inserted into the cache using mb_cache_entry_insert(). Returns NULL
- * if no more memory was available.
- */
-struct mb_cache_entry *
-mb_cache_entry_alloc(struct mb_cache *cache, gfp_t gfp_flags)
+static unsigned long mb_cache_count(struct shrinker *shrink,
+				    struct shrink_control *sc)
 {
-	struct mb_cache_entry *ce;
-
-	if (atomic_read(&cache->c_entry_count) >= cache->c_max_entries) {
-		struct list_head *l;
-
-		l = &mb_cache_lru_list;
-		spin_lock(&mb_cache_spinlock);
-		while (!list_is_last(l, &mb_cache_lru_list)) {
-			l = l->next;
-			ce = list_entry(l, struct mb_cache_entry, e_lru_list);
-			if (ce->e_cache == cache) {
-				list_del_init(&ce->e_lru_list);
-				if (ce->e_used || ce->e_queued ||
-					atomic_read(&ce->e_refcnt))
-					continue;
-				spin_unlock(&mb_cache_spinlock);
-				/*
-				 * Prevent any find or get operation on the
-				 * entry.
-				 */
-				hlist_bl_lock(ce->e_block_hash_p);
-				hlist_bl_lock(ce->e_index_hash_p);
-				/* Ignore if it is touched by a find/get */
-				if (ce->e_used || ce->e_queued ||
-					atomic_read(&ce->e_refcnt) ||
-					!list_empty(&ce->e_lru_list)) {
-					hlist_bl_unlock(ce->e_index_hash_p);
-					hlist_bl_unlock(ce->e_block_hash_p);
-					l = &mb_cache_lru_list;
-					spin_lock(&mb_cache_spinlock);
-					continue;
-				}
-				mb_assert(list_empty(&ce->e_lru_list));
-				mb_assert(!(ce->e_used || ce->e_queued ||
-					atomic_read(&ce->e_refcnt)));
-				__mb_cache_entry_unhash_unlock(ce);
-				goto found;
-			}
-		}
-		spin_unlock(&mb_cache_spinlock);
-	}
+	struct mb_cache *cache = container_of(shrink, struct mb_cache,
+					      c_shrink);
 
-	ce = kmem_cache_alloc(cache->c_entry_cache, gfp_flags);
-	if (!ce)
-		return NULL;
-	atomic_inc(&cache->c_entry_count);
-	INIT_LIST_HEAD(&ce->e_lru_list);
-	INIT_HLIST_BL_NODE(&ce->e_block_list);
-	INIT_HLIST_BL_NODE(&ce->e_index.o_list);
-	ce->e_cache = cache;
-	ce->e_queued = 0;
-	atomic_set(&ce->e_refcnt, 0);
-found:
-	ce->e_block_hash_p = &cache->c_block_hash[0];
-	ce->e_index_hash_p = &cache->c_index_hash[0];
-	ce->e_used = 1 + MB_CACHE_WRITER;
-	return ce;
+	return cache->c_entry_count;
 }
 
-
-/*
- * mb_cache_entry_insert()
- *
- * Inserts an entry that was allocated using mb_cache_entry_alloc() into
- * the cache. After this, the cache entry can be looked up, but is not yet
- * in the lru list as the caller still holds a handle to it. Returns 0 on
- * success, or -EBUSY if a cache entry for that device + inode exists
- * already (this may happen after a failed lookup, but when another process
- * has inserted the same cache entry in the meantime).
- *
- * @bdev: device the cache entry belongs to
- * @block: block number
- * @key: lookup key
- */
-int
-mb_cache_entry_insert(struct mb_cache_entry *ce, struct block_device *bdev,
-		      sector_t block, unsigned int key)
+/* Shrink number of entries in cache */
+static unsigned long mb_cache_shrink(struct mb_cache *cache,
+				     unsigned int nr_to_scan)
 {
-	struct mb_cache *cache = ce->e_cache;
-	unsigned int bucket;
-	struct hlist_bl_node *l;
-	struct hlist_bl_head *block_hash_p;
-	struct hlist_bl_head *index_hash_p;
-	struct mb_cache_entry *lce;
-
-	mb_assert(ce);
-	bucket = hash_long((unsigned long)bdev + (block & 0xffffffff), 
-			   cache->c_bucket_bits);
-	block_hash_p = &cache->c_block_hash[bucket];
-	hlist_bl_lock(block_hash_p);
-	hlist_bl_for_each_entry(lce, l, block_hash_p, e_block_list) {
-		if (lce->e_bdev == bdev && lce->e_block == block) {
-			hlist_bl_unlock(block_hash_p);
-			return -EBUSY;
+	struct mb_cache_entry *entry;
+	struct hlist_bl_head *head;
+	unsigned int shrunk = 0;
+
+	spin_lock(&cache->c_list_lock);
+	while (nr_to_scan-- && !list_empty(&cache->c_list)) {
+		entry = list_first_entry(&cache->c_list,
+					 struct mb_cache_entry, e_list);
+		if (entry->e_referenced) {
+			entry->e_referenced = 0;
+			list_move_tail(&cache->c_list, &entry->e_list);
+			continue;
 		}
+		list_del_init(&entry->e_list);
+		cache->c_entry_count--;
+		/*
+		 * We keep LRU list reference so that entry doesn't go away
+		 * from under us.
+		 */
+		spin_unlock(&cache->c_list_lock);
+		head = mb_cache_entry_head(cache, entry->e_key);
+		hlist_bl_lock(head);
+		if (!hlist_bl_unhashed(&entry->e_hash_list)) {
+			hlist_bl_del_init(&entry->e_hash_list);
+			atomic_dec(&entry->e_refcnt);
+		}
+		hlist_bl_unlock(head);
+		if (mb_cache_entry_put(cache, entry))
+			shrunk++;
+		cond_resched();
+		spin_lock(&cache->c_list_lock);
 	}
-	mb_assert(!__mb_cache_entry_is_block_hashed(ce));
-	__mb_cache_entry_unhash_block(ce);
-	__mb_cache_entry_unhash_index(ce);
-	ce->e_bdev = bdev;
-	ce->e_block = block;
-	ce->e_block_hash_p = block_hash_p;
-	ce->e_index.o_key = key;
-	hlist_bl_add_head(&ce->e_block_list, block_hash_p);
-	hlist_bl_unlock(block_hash_p);
-	bucket = hash_long(key, cache->c_bucket_bits);
-	index_hash_p = &cache->c_index_hash[bucket];
-	hlist_bl_lock(index_hash_p);
-	ce->e_index_hash_p = index_hash_p;
-	hlist_bl_add_head(&ce->e_index.o_list, index_hash_p);
-	hlist_bl_unlock(index_hash_p);
-	return 0;
-}
+	spin_unlock(&cache->c_list_lock);
 
+	return shrunk;
+}
 
-/*
- * mb_cache_entry_release()
- *
- * Release a handle to a cache entry. When the last handle to a cache entry
- * is released it is either freed (if it is invalid) or otherwise inserted
- * in to the lru list.
- */
-void
-mb_cache_entry_release(struct mb_cache_entry *ce)
+static unsigned long mb_cache_scan(struct shrinker *shrink,
+				   struct shrink_control *sc)
 {
-	__mb_cache_entry_release(ce);
+	int nr_to_scan = sc->nr_to_scan;
+	struct mb_cache *cache = container_of(shrink, struct mb_cache,
+					      c_shrink);
+	return mb_cache_shrink(cache, nr_to_scan);
 }
 
+/* We shrink 1/X of the cache when we have too many entries in it */
+#define SHRINK_DIVISOR 16
 
-/*
- * mb_cache_entry_free()
- *
- */
-void
-mb_cache_entry_free(struct mb_cache_entry *ce)
+static void mb_cache_shrink_worker(struct work_struct *work)
 {
-	mb_assert(ce);
-	mb_assert(list_empty(&ce->e_lru_list));
-	hlist_bl_lock(ce->e_index_hash_p);
-	__mb_cache_entry_unhash_index(ce);
-	hlist_bl_unlock(ce->e_index_hash_p);
-	hlist_bl_lock(ce->e_block_hash_p);
-	__mb_cache_entry_unhash_block(ce);
-	hlist_bl_unlock(ce->e_block_hash_p);
-	__mb_cache_entry_release(ce);
+	struct mb_cache *cache = container_of(work, struct mb_cache,
+					      c_shrink_work);
+	mb_cache_shrink(cache, cache->c_max_entries / SHRINK_DIVISOR);
 }
 
-
 /*
- * mb_cache_entry_get()
+ * mb_cache_create - create cache
+ * @bucket_bits: log2 of the hash table size
  *
- * Get a cache entry  by device / block number. (There can only be one entry
- * in the cache per device and block.) Returns NULL if no such cache entry
- * exists. The returned cache entry is locked for exclusive access ("single
- * writer").
+ * Create cache for keys with 2^bucket_bits hash entries.
  */
-struct mb_cache_entry *
-mb_cache_entry_get(struct mb_cache *cache, struct block_device *bdev,
-		   sector_t block)
+struct mb_cache *mb_cache_create(int bucket_bits)
 {
-	unsigned int bucket;
-	struct hlist_bl_node *l;
-	struct mb_cache_entry *ce;
-	struct hlist_bl_head *block_hash_p;
-
-	bucket = hash_long((unsigned long)bdev + (block & 0xffffffff),
-			   cache->c_bucket_bits);
-	block_hash_p = &cache->c_block_hash[bucket];
-	/* First serialize access to the block corresponding hash chain. */
-	hlist_bl_lock(block_hash_p);
-	hlist_bl_for_each_entry(ce, l, block_hash_p, e_block_list) {
-		mb_assert(ce->e_block_hash_p == block_hash_p);
-		if (ce->e_bdev == bdev && ce->e_block == block) {
-			/*
-			 * Prevent a free from removing the entry.
-			 */
-			atomic_inc(&ce->e_refcnt);
-			hlist_bl_unlock(block_hash_p);
-			__spin_lock_mb_cache_entry(ce);
-			atomic_dec(&ce->e_refcnt);
-			if (ce->e_used > 0) {
-				DEFINE_WAIT(wait);
-				while (ce->e_used > 0) {
-					ce->e_queued++;
-					prepare_to_wait(&mb_cache_queue, &wait,
-							TASK_UNINTERRUPTIBLE);
-					__spin_unlock_mb_cache_entry(ce);
-					schedule();
-					__spin_lock_mb_cache_entry(ce);
-					ce->e_queued--;
-				}
-				finish_wait(&mb_cache_queue, &wait);
-			}
-			ce->e_used += 1 + MB_CACHE_WRITER;
-			__spin_unlock_mb_cache_entry(ce);
+	struct mb_cache *cache;
+	int bucket_count = 1 << bucket_bits;
+	int i;
 
-			if (!list_empty(&ce->e_lru_list)) {
-				spin_lock(&mb_cache_spinlock);
-				list_del_init(&ce->e_lru_list);
-				spin_unlock(&mb_cache_spinlock);
-			}
-			if (!__mb_cache_entry_is_block_hashed(ce)) {
-				__mb_cache_entry_release(ce);
-				return NULL;
-			}
-			return ce;
-		}
+	if (!try_module_get(THIS_MODULE))
+		return NULL;
+
+	cache = kzalloc(sizeof(struct mb_cache), GFP_KERNEL);
+	if (!cache)
+		goto err_out;
+	cache->c_bucket_bits = bucket_bits;
+	cache->c_max_entries = bucket_count << 4;
+	INIT_LIST_HEAD(&cache->c_list);
+	spin_lock_init(&cache->c_list_lock);
+	cache->c_hash = kmalloc(bucket_count * sizeof(struct hlist_bl_head),
+				GFP_KERNEL);
+	if (!cache->c_hash) {
+		kfree(cache);
+		goto err_out;
 	}
-	hlist_bl_unlock(block_hash_p);
-	return NULL;
-}
+	for (i = 0; i < bucket_count; i++)
+		INIT_HLIST_BL_HEAD(&cache->c_hash[i]);
 
-#if !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0)
+	cache->c_shrink.count_objects = mb_cache_count;
+	cache->c_shrink.scan_objects = mb_cache_scan;
+	cache->c_shrink.seeks = DEFAULT_SEEKS;
+	register_shrinker(&cache->c_shrink);
 
-static struct mb_cache_entry *
-__mb_cache_entry_find(struct hlist_bl_node *l, struct hlist_bl_head *head,
-		      struct block_device *bdev, unsigned int key)
-{
+	INIT_WORK(&cache->c_shrink_work, mb_cache_shrink_worker);
 
-	/* The index hash chain is alredy acquire by caller. */
-	while (l != NULL) {
-		struct mb_cache_entry *ce =
-			hlist_bl_entry(l, struct mb_cache_entry,
-				e_index.o_list);
-		mb_assert(ce->e_index_hash_p == head);
-		if (ce->e_bdev == bdev && ce->e_index.o_key == key) {
-			/*
-			 * Prevent a free from removing the entry.
-			 */
-			atomic_inc(&ce->e_refcnt);
-			hlist_bl_unlock(head);
-			__spin_lock_mb_cache_entry(ce);
-			atomic_dec(&ce->e_refcnt);
-			ce->e_used++;
-			/* Incrementing before holding the lock gives readers
-			   priority over writers. */
-			if (ce->e_used >= MB_CACHE_WRITER) {
-				DEFINE_WAIT(wait);
-
-				while (ce->e_used >= MB_CACHE_WRITER) {
-					ce->e_queued++;
-					prepare_to_wait(&mb_cache_queue, &wait,
-							TASK_UNINTERRUPTIBLE);
-					__spin_unlock_mb_cache_entry(ce);
-					schedule();
-					__spin_lock_mb_cache_entry(ce);
-					ce->e_queued--;
-				}
-				finish_wait(&mb_cache_queue, &wait);
-			}
-			__spin_unlock_mb_cache_entry(ce);
-			if (!list_empty(&ce->e_lru_list)) {
-				spin_lock(&mb_cache_spinlock);
-				list_del_init(&ce->e_lru_list);
-				spin_unlock(&mb_cache_spinlock);
-			}
-			if (!__mb_cache_entry_is_block_hashed(ce)) {
-				__mb_cache_entry_release(ce);
-				return ERR_PTR(-EAGAIN);
-			}
-			return ce;
-		}
-		l = l->next;
-	}
-	hlist_bl_unlock(head);
+	return cache;
+
+err_out:
+	module_put(THIS_MODULE);
 	return NULL;
 }
-
+EXPORT_SYMBOL(mb_cache_create);
 
 /*
- * mb_cache_entry_find_first()
- *
- * Find the first cache entry on a given device with a certain key in
- * an additional index. Additional matches can be found with
- * mb_cache_entry_find_next(). Returns NULL if no match was found. The
- * returned cache entry is locked for shared access ("multiple readers").
+ * mb_cache_destroy - destroy cache
+ * @cache: the cache to destroy
  *
- * @cache: the cache to search
- * @bdev: the device the cache entry should belong to
- * @key: the key in the index
+ * Free all entries in cache and cache itself. Caller must make sure nobody
+ * (except shrinker) can reach @cache when calling this.
  */
-struct mb_cache_entry *
-mb_cache_entry_find_first(struct mb_cache *cache, struct block_device *bdev,
-			  unsigned int key)
+void mb_cache_destroy(struct mb_cache *cache)
 {
-	unsigned int bucket = hash_long(key, cache->c_bucket_bits);
-	struct hlist_bl_node *l;
-	struct mb_cache_entry *ce = NULL;
-	struct hlist_bl_head *index_hash_p;
-
-	index_hash_p = &cache->c_index_hash[bucket];
-	hlist_bl_lock(index_hash_p);
-	if (!hlist_bl_empty(index_hash_p)) {
-		l = hlist_bl_first(index_hash_p);
-		ce = __mb_cache_entry_find(l, index_hash_p, bdev, key);
-	} else
-		hlist_bl_unlock(index_hash_p);
-	return ce;
-}
+	struct mb_cache_entry *entry, *next;
 
+	unregister_shrinker(&cache->c_shrink);
 
-/*
- * mb_cache_entry_find_next()
- *
- * Find the next cache entry on a given device with a certain key in an
- * additional index. Returns NULL if no match could be found. The previous
- * entry is atomatically released, so that mb_cache_entry_find_next() can
- * be called like this:
- *
- * entry = mb_cache_entry_find_first();
- * while (entry) {
- * 	...
- *	entry = mb_cache_entry_find_next(entry, ...);
- * }
- *
- * @prev: The previous match
- * @bdev: the device the cache entry should belong to
- * @key: the key in the index
- */
-struct mb_cache_entry *
-mb_cache_entry_find_next(struct mb_cache_entry *prev,
-			 struct block_device *bdev, unsigned int key)
-{
-	struct mb_cache *cache = prev->e_cache;
-	unsigned int bucket = hash_long(key, cache->c_bucket_bits);
-	struct hlist_bl_node *l;
-	struct mb_cache_entry *ce;
-	struct hlist_bl_head *index_hash_p;
-
-	index_hash_p = &cache->c_index_hash[bucket];
-	mb_assert(prev->e_index_hash_p == index_hash_p);
-	hlist_bl_lock(index_hash_p);
-	mb_assert(!hlist_bl_empty(index_hash_p));
-	l = prev->e_index.o_list.next;
-	ce = __mb_cache_entry_find(l, index_hash_p, bdev, key);
-	__mb_cache_entry_release(prev);
-	return ce;
+	/*
+	 * We don't bother with any locking. Cache must not be used at this
+	 * point.
+	 */
+	list_for_each_entry_safe(entry, next, &cache->c_list, e_list) {
+		if (!hlist_bl_unhashed(&entry->e_hash_list)) {
+			hlist_bl_del_init(&entry->e_hash_list);
+			atomic_dec(&entry->e_refcnt);
+		} else
+			WARN_ON(1);
+		list_del(&entry->e_list);
+		WARN_ON(atomic_read(&entry->e_refcnt) != 1);
+		mb_cache_entry_put(cache, entry);
+	}
+	kfree(cache->c_hash);
+	kfree(cache);
+	module_put(THIS_MODULE);
 }
+EXPORT_SYMBOL(mb_cache_destroy);
 
-#endif  /* !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0) */
-
-static int __init init_mbcache(void)
+static int __init mbcache_init(void)
 {
-	register_shrinker(&mb_cache_shrinker);
+	mb_entry_cache = kmem_cache_create("mbcache",
+				sizeof(struct mb_cache_entry), 0,
+				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
+	BUG_ON(!mb_entry_cache);
 	return 0;
 }
 
-static void __exit exit_mbcache(void)
+static void __exit mbcache_exit(void)
 {
-	unregister_shrinker(&mb_cache_shrinker);
+	kmem_cache_destroy(mb_entry_cache);
 }
 
-module_init(init_mbcache)
-module_exit(exit_mbcache)
+module_init(mbcache_init)
+module_exit(mbcache_exit)
 
+MODULE_AUTHOR("Jan Kara <jack@suse.cz>");
+MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
+MODULE_LICENSE("GPL");
diff --git a/fs/mpage.c b/fs/mpage.c
index 1480d3a18037..6bd9fd90964e 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -24,6 +24,7 @@
 #include <linux/highmem.h>
 #include <linux/prefetch.h>
 #include <linux/mpage.h>
+#include <linux/mm_inline.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
@@ -366,7 +367,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
-		struct page *page = list_entry(pages->prev, struct page, lru);
+		struct page *page = lru_to_page(pages);
 
 		prefetchw(&page->flags);
 		list_del(&page->lru);
diff --git a/fs/namei.c b/fs/namei.c
index f624d132e01e..794f81dce766 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1220,8 +1220,8 @@ static int follow_managed(struct path *path, struct nameidata *nd)
 
 	if (need_mntput && path->mnt == mnt)
 		mntput(path->mnt);
-	if (ret == -EISDIR)
-		ret = 0;
+	if (ret == -EISDIR || !ret)
+		ret = 1;
 	if (need_mntput)
 		nd->flags |= LOOKUP_JUMPED;
 	if (unlikely(ret < 0))
@@ -1444,40 +1444,26 @@ static int follow_dotdot(struct nameidata *nd)
  * This looks up the name in dcache, possibly revalidates the old dentry and
  * allocates a new one if not found or not valid.  In the need_lookup argument
  * returns whether i_op->lookup is necessary.
- *
- * dir->d_inode->i_mutex must be held
  */
-static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
-				    unsigned int flags, bool *need_lookup)
+static struct dentry *lookup_dcache(const struct qstr *name,
+				    struct dentry *dir,
+				    unsigned int flags)
 {
 	struct dentry *dentry;
 	int error;
 
-	*need_lookup = false;
 	dentry = d_lookup(dir, name);
 	if (dentry) {
 		if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
 			error = d_revalidate(dentry, flags);
 			if (unlikely(error <= 0)) {
-				if (error < 0) {
-					dput(dentry);
-					return ERR_PTR(error);
-				} else {
+				if (!error)
 					d_invalidate(dentry);
-					dput(dentry);
-					dentry = NULL;
-				}
+				dput(dentry);
+				return ERR_PTR(error);
 			}
 		}
 	}
-
-	if (!dentry) {
-		dentry = d_alloc(dir, name);
-		if (unlikely(!dentry))
-			return ERR_PTR(-ENOMEM);
-
-		*need_lookup = true;
-	}
 	return dentry;
 }
 
@@ -1506,45 +1492,44 @@ static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry,
 	return dentry;
 }
 
-static struct dentry *__lookup_hash(struct qstr *name,
+static struct dentry *__lookup_hash(const struct qstr *name,
 		struct dentry *base, unsigned int flags)
 {
-	bool need_lookup;
-	struct dentry *dentry;
+	struct dentry *dentry = lookup_dcache(name, base, flags);
 
-	dentry = lookup_dcache(name, base, flags, &need_lookup);
-	if (!need_lookup)
+	if (dentry)
 		return dentry;
 
+	dentry = d_alloc(base, name);
+	if (unlikely(!dentry))
+		return ERR_PTR(-ENOMEM);
+
 	return lookup_real(base->d_inode, dentry, flags);
 }
 
-/*
- *  It's more convoluted than I'd like it to be, but... it's still fairly
- *  small and for now I'd prefer to have fast path as straight as possible.
- *  It _is_ time-critical.
- */
 static int lookup_fast(struct nameidata *nd,
 		       struct path *path, struct inode **inode,
 		       unsigned *seqp)
 {
 	struct vfsmount *mnt = nd->path.mnt;
 	struct dentry *dentry, *parent = nd->path.dentry;
-	int need_reval = 1;
 	int status = 1;
 	int err;
 
 	/*
 	 * Rename seqlock is not required here because in the off chance
-	 * of a false negative due to a concurrent rename, we're going to
-	 * do the non-racy lookup, below.
+	 * of a false negative due to a concurrent rename, the caller is
+	 * going to fall back to non-racy lookup.
 	 */
 	if (nd->flags & LOOKUP_RCU) {
 		unsigned seq;
 		bool negative;
 		dentry = __d_lookup_rcu(parent, &nd->last, &seq);
-		if (!dentry)
-			goto unlazy;
+		if (unlikely(!dentry)) {
+			if (unlazy_walk(nd, NULL, 0))
+				return -ECHILD;
+			return 0;
+		}
 
 		/*
 		 * This sequence count validates that the inode matches
@@ -1552,7 +1537,7 @@ static int lookup_fast(struct nameidata *nd,
 		 */
 		*inode = d_backing_inode(dentry);
 		negative = d_is_negative(dentry);
-		if (read_seqcount_retry(&dentry->d_seq, seq))
+		if (unlikely(read_seqcount_retry(&dentry->d_seq, seq)))
 			return -ECHILD;
 
 		/*
@@ -1562,81 +1547,89 @@ static int lookup_fast(struct nameidata *nd,
 		 * The memory barrier in read_seqcount_begin of child is
 		 *  enough, we can use __read_seqcount_retry here.
 		 */
-		if (__read_seqcount_retry(&parent->d_seq, nd->seq))
+		if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq)))
 			return -ECHILD;
 
 		*seqp = seq;
-		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
+		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
 			status = d_revalidate(dentry, nd->flags);
-			if (unlikely(status <= 0)) {
-				if (status != -ECHILD)
-					need_reval = 0;
-				goto unlazy;
-			}
+		if (unlikely(status <= 0)) {
+			if (unlazy_walk(nd, dentry, seq))
+				return -ECHILD;
+			if (status == -ECHILD)
+				status = d_revalidate(dentry, nd->flags);
+		} else {
+			/*
+			 * Note: do negative dentry check after revalidation in
+			 * case that drops it.
+			 */
+			if (unlikely(negative))
+				return -ENOENT;
+			path->mnt = mnt;
+			path->dentry = dentry;
+			if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
+				return 1;
+			if (unlazy_walk(nd, dentry, seq))
+				return -ECHILD;
 		}
-		/*
-		 * Note: do negative dentry check after revalidation in
-		 * case that drops it.
-		 */
-		if (negative)
-			return -ENOENT;
-		path->mnt = mnt;
-		path->dentry = dentry;
-		if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
-			return 0;
-unlazy:
-		if (unlazy_walk(nd, dentry, seq))
-			return -ECHILD;
 	} else {
 		dentry = __d_lookup(parent, &nd->last);
+		if (unlikely(!dentry))
+			return 0;
+		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
+			status = d_revalidate(dentry, nd->flags);
 	}
-
-	if (unlikely(!dentry))
-		goto need_lookup;
-
-	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
-		status = d_revalidate(dentry, nd->flags);
 	if (unlikely(status <= 0)) {
-		if (status < 0) {
-			dput(dentry);
-			return status;
-		}
-		d_invalidate(dentry);
+		if (!status)
+			d_invalidate(dentry);
 		dput(dentry);
-		goto need_lookup;
+		return status;
 	}
-
 	if (unlikely(d_is_negative(dentry))) {
 		dput(dentry);
 		return -ENOENT;
 	}
+
 	path->mnt = mnt;
 	path->dentry = dentry;
 	err = follow_managed(path, nd);
-	if (likely(!err))
+	if (likely(err > 0))
 		*inode = d_backing_inode(path->dentry);
 	return err;
-
-need_lookup:
-	return 1;
 }
 
 /* Fast lookup failed, do it the slow way */
-static int lookup_slow(struct nameidata *nd, struct path *path)
+static struct dentry *lookup_slow(const struct qstr *name,
+				  struct dentry *dir,
+				  unsigned int flags)
 {
-	struct dentry *dentry, *parent;
-
-	parent = nd->path.dentry;
-	BUG_ON(nd->inode != parent->d_inode);
-
-	inode_lock(parent->d_inode);
-	dentry = __lookup_hash(&nd->last, parent, nd->flags);
-	inode_unlock(parent->d_inode);
-	if (IS_ERR(dentry))
-		return PTR_ERR(dentry);
-	path->mnt = nd->path.mnt;
-	path->dentry = dentry;
-	return follow_managed(path, nd);
+	struct dentry *dentry;
+	inode_lock(dir->d_inode);
+	dentry = d_lookup(dir, name);
+	if (unlikely(dentry)) {
+		if ((dentry->d_flags & DCACHE_OP_REVALIDATE) &&
+		    !(flags & LOOKUP_NO_REVAL)) {
+			int error = d_revalidate(dentry, flags);
+			if (unlikely(error <= 0)) {
+				if (!error)
+					d_invalidate(dentry);
+				dput(dentry);
+				dentry = ERR_PTR(error);
+			}
+		}
+		if (dentry) {
+			inode_unlock(dir->d_inode);
+			return dentry;
+		}
+	}
+	dentry = d_alloc(dir, name);
+	if (unlikely(!dentry)) {
+		inode_unlock(dir->d_inode);
+		return ERR_PTR(-ENOMEM);
+	}
+	dentry = lookup_real(dir->d_inode, dentry, flags);
+	inode_unlock(dir->d_inode);
+	return dentry;
 }
 
 static inline int may_lookup(struct nameidata *nd)
@@ -1712,6 +1705,11 @@ static inline int should_follow_link(struct nameidata *nd, struct path *link,
 		return 0;
 	if (!follow)
 		return 0;
+	/* make sure that d_is_symlink above matches inode */
+	if (nd->flags & LOOKUP_RCU) {
+		if (read_seqcount_retry(&link->dentry->d_seq, seq))
+			return -ECHILD;
+	}
 	return pick_link(nd, link, inode, seq);
 }
 
@@ -1735,19 +1733,24 @@ static int walk_component(struct nameidata *nd, int flags)
 		return err;
 	}
 	err = lookup_fast(nd, &path, &inode, &seq);
-	if (unlikely(err)) {
+	if (unlikely(err <= 0)) {
 		if (err < 0)
 			return err;
-
-		err = lookup_slow(nd, &path);
-		if (err < 0)
+		path.dentry = lookup_slow(&nd->last, nd->path.dentry,
+					  nd->flags);
+		if (IS_ERR(path.dentry))
+			return PTR_ERR(path.dentry);
+		if (unlikely(d_is_negative(path.dentry))) {
+			dput(path.dentry);
+			return -ENOENT;
+		}
+		path.mnt = nd->path.mnt;
+		err = follow_managed(&path, nd);
+		if (unlikely(err < 0))
 			return err;
 
-		inode = d_backing_inode(path.dentry);
 		seq = 0;	/* we are already out of RCU mode */
-		err = -ENOENT;
-		if (d_is_negative(path.dentry))
-			goto out_path_put;
+		inode = d_backing_inode(path.dentry);
 	}
 
 	if (flags & WALK_PUT)
@@ -1759,10 +1762,6 @@ static int walk_component(struct nameidata *nd, int flags)
 	nd->inode = inode;
 	nd->seq = seq;
 	return 0;
-
-out_path_put:
-	path_to_nameidata(&path, nd);
-	return err;
 }
 
 /*
@@ -2368,21 +2367,9 @@ struct dentry *lookup_one_len_unlocked(const char *name,
 	if (err)
 		return ERR_PTR(err);
 
-	/*
-	 * __d_lookup() is used to try to get a quick answer and avoid the
-	 * mutex.  A false-negative does no harm.
-	 */
-	ret = __d_lookup(base, &this);
-	if (ret && unlikely(ret->d_flags & DCACHE_OP_REVALIDATE)) {
-		dput(ret);
-		ret = NULL;
-	}
-	if (ret)
-		return ret;
-
-	inode_lock(base->d_inode);
-	ret =  __lookup_hash(&this, base, 0);
-	inode_unlock(base->d_inode);
+	ret = lookup_dcache(&this, base, 0);
+	if (!ret)
+		ret = lookup_slow(&this, base, 0);
 	return ret;
 }
 EXPORT_SYMBOL(lookup_one_len_unlocked);
@@ -2460,31 +2447,21 @@ mountpoint_last(struct nameidata *nd, struct path *path)
 		if (error)
 			return error;
 		dentry = dget(nd->path.dentry);
-		goto done;
-	}
-
-	inode_lock(dir->d_inode);
-	dentry = d_lookup(dir, &nd->last);
-	if (!dentry) {
-		/*
-		 * No cached dentry. Mounted dentries are pinned in the cache,
-		 * so that means that this dentry is probably a symlink or the
-		 * path doesn't actually point to a mounted dentry.
-		 */
-		dentry = d_alloc(dir, &nd->last);
+	} else {
+		dentry = d_lookup(dir, &nd->last);
 		if (!dentry) {
-			inode_unlock(dir->d_inode);
-			return -ENOMEM;
-		}
-		dentry = lookup_real(dir->d_inode, dentry, nd->flags);
-		if (IS_ERR(dentry)) {
-			inode_unlock(dir->d_inode);
-			return PTR_ERR(dentry);
+			/*
+			 * No cached dentry. Mounted dentries are pinned in the
+			 * cache, so that means that this dentry is probably
+			 * a symlink or the path doesn't actually point
+			 * to a mounted dentry.
+			 */
+			dentry = lookup_slow(&nd->last, dir,
+					     nd->flags | LOOKUP_NO_REVAL);
+			if (IS_ERR(dentry))
+				return PTR_ERR(dentry);
 		}
 	}
-	inode_unlock(dir->d_inode);
-
-done:
 	if (d_is_negative(dentry)) {
 		dput(dentry);
 		return -ENOENT;
@@ -3013,16 +2990,22 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 	struct inode *dir_inode = dir->d_inode;
 	struct dentry *dentry;
 	int error;
-	bool need_lookup;
+	bool need_lookup = false;
 
 	*opened &= ~FILE_CREATED;
-	dentry = lookup_dcache(&nd->last, dir, nd->flags, &need_lookup);
+	dentry = lookup_dcache(&nd->last, dir, nd->flags);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	/* Cached positive dentry: will open in f_op->open */
-	if (!need_lookup && dentry->d_inode)
+	if (!dentry) {
+		dentry = d_alloc(dir, &nd->last);
+		if (unlikely(!dentry))
+			return -ENOMEM;
+		need_lookup = true;
+	} else if (dentry->d_inode) {
+		/* Cached positive dentry: will open in f_op->open */
 		goto out_no_open;
+	}
 
 	if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) {
 		return atomic_open(nd, dentry, path, file, op, got_write,
@@ -3106,13 +3089,14 @@ static int do_last(struct nameidata *nd,
 			nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 		/* we _can_ be in RCU mode here */
 		error = lookup_fast(nd, &path, &inode, &seq);
-		if (likely(!error))
+		if (likely(error > 0))
 			goto finish_lookup;
 
 		if (error < 0)
 			return error;
 
 		BUG_ON(nd->inode != dir->d_inode);
+		BUG_ON(nd->flags & LOOKUP_RCU);
 	} else {
 		/* create side of things */
 		/*
@@ -3167,12 +3151,6 @@ retry_lookup:
 	}
 
 	/*
-	 * create/update audit record if it already exists.
-	 */
-	if (d_is_positive(path.dentry))
-		audit_inode(nd->name, path.dentry, 0);
-
-	/*
 	 * If atomic_open() acquired write access it is dropped now due to
 	 * possible mount and symlink following (this might be optimized away if
 	 * necessary...)
@@ -3182,6 +3160,16 @@ retry_lookup:
 		got_write = false;
 	}
 
+	if (unlikely(d_is_negative(path.dentry))) {
+		path_to_nameidata(&path, nd);
+		return -ENOENT;
+	}
+
+	/*
+	 * create/update audit record if it already exists.
+	 */
+	audit_inode(nd->name, path.dentry, 0);
+
 	if (unlikely((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))) {
 		path_to_nameidata(&path, nd);
 		return -EEXIST;
@@ -3191,13 +3179,8 @@ retry_lookup:
 	if (unlikely(error < 0))
 		return error;
 
-	BUG_ON(nd->flags & LOOKUP_RCU);
-	inode = d_backing_inode(path.dentry);
 	seq = 0;	/* out of RCU mode, so the value doesn't matter */
-	if (unlikely(d_is_negative(path.dentry))) {
-		path_to_nameidata(&path, nd);
-		return -ENOENT;
-	}
+	inode = d_backing_inode(path.dentry);
 finish_lookup:
 	if (nd->depth)
 		put_link(nd);
@@ -3206,11 +3189,6 @@ finish_lookup:
 	if (unlikely(error))
 		return error;
 
-	if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) {
-		path_to_nameidata(&path, nd);
-		return -ELOOP;
-	}
-
 	if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) {
 		path_to_nameidata(&path, nd);
 	} else {
@@ -3229,6 +3207,10 @@ finish_open:
 		return error;
 	}
 	audit_inode(nd->name, nd->path.dentry, 0);
+	if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) {
+		error = -ELOOP;
+		goto out;
+	}
 	error = -EISDIR;
 	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
 		goto out;
@@ -3273,6 +3255,10 @@ opened:
 			goto exit_fput;
 	}
 out:
+	if (unlikely(error > 0)) {
+		WARN_ON(1);
+		error = -EINVAL;
+	}
 	if (got_write)
 		mnt_drop_write(nd->path.mnt);
 	path_put(&save_parent);
@@ -3699,31 +3685,6 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
 	return sys_mkdirat(AT_FDCWD, pathname, mode);
 }
 
-/*
- * The dentry_unhash() helper will try to drop the dentry early: we
- * should have a usage count of 1 if we're the only user of this
- * dentry, and if that is true (possibly after pruning the dcache),
- * then we drop the dentry now.
- *
- * A low-level filesystem can, if it choses, legally
- * do a
- *
- *	if (!d_unhashed(dentry))
- *		return -EBUSY;
- *
- * if it cannot handle the case of removing a directory
- * that is still in use by something else..
- */
-void dentry_unhash(struct dentry *dentry)
-{
-	shrink_dcache_parent(dentry);
-	spin_lock(&dentry->d_lock);
-	if (dentry->d_lockref.count == 1)
-		__d_drop(dentry);
-	spin_unlock(&dentry->d_lock);
-}
-EXPORT_SYMBOL(dentry_unhash);
-
 int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	int error = may_delete(dir, dentry, 1);
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 26c2de2de13f..b7f8eaeea5d8 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -633,7 +633,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx,
 				d_rehash(newdent);
 		} else {
 			spin_lock(&dentry->d_lock);
-			NCP_FINFO(inode)->flags &= ~NCPI_DIR_CACHE;
+			NCP_FINFO(dir)->flags &= ~NCPI_DIR_CACHE;
 			spin_unlock(&dentry->d_lock);
 		}
 	} else {
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index ddd0138f410c..02e4d87d2ed3 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -446,8 +446,8 @@ static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo)
 	kfree(bl);
 }
 
-static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
-						   gfp_t gfp_flags)
+static struct pnfs_layout_hdr *__bl_alloc_layout_hdr(struct inode *inode,
+		gfp_t gfp_flags, bool is_scsi_layout)
 {
 	struct pnfs_block_layout *bl;
 
@@ -460,9 +460,22 @@ static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
 	bl->bl_ext_ro = RB_ROOT;
 	spin_lock_init(&bl->bl_ext_lock);
 
+	bl->bl_scsi_layout = is_scsi_layout;
 	return &bl->bl_layout;
 }
 
+static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
+						   gfp_t gfp_flags)
+{
+	return __bl_alloc_layout_hdr(inode, gfp_flags, false);
+}
+
+static struct pnfs_layout_hdr *sl_alloc_layout_hdr(struct inode *inode,
+						   gfp_t gfp_flags)
+{
+	return __bl_alloc_layout_hdr(inode, gfp_flags, true);
+}
+
 static void bl_free_lseg(struct pnfs_layout_segment *lseg)
 {
 	dprintk("%s enter\n", __func__);
@@ -743,7 +756,7 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
 
 static bool
 is_aligned_req(struct nfs_pageio_descriptor *pgio,
-		struct nfs_page *req, unsigned int alignment)
+		struct nfs_page *req, unsigned int alignment, bool is_write)
 {
 	/*
 	 * Always accept buffered writes, higher layers take care of the
@@ -758,7 +771,8 @@ is_aligned_req(struct nfs_pageio_descriptor *pgio,
 	if (IS_ALIGNED(req->wb_bytes, alignment))
 		return true;
 
-	if (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode)) {
+	if (is_write &&
+	    (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode))) {
 		/*
 		 * If the write goes up to the inode size, just write
 		 * the full page.  Data past the inode size is
@@ -775,7 +789,7 @@ is_aligned_req(struct nfs_pageio_descriptor *pgio,
 static void
 bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
-	if (!is_aligned_req(pgio, req, SECTOR_SIZE)) {
+	if (!is_aligned_req(pgio, req, SECTOR_SIZE, false)) {
 		nfs_pageio_reset_read_mds(pgio);
 		return;
 	}
@@ -791,7 +805,7 @@ static size_t
 bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		struct nfs_page *req)
 {
-	if (!is_aligned_req(pgio, req, SECTOR_SIZE))
+	if (!is_aligned_req(pgio, req, SECTOR_SIZE, false))
 		return 0;
 	return pnfs_generic_pg_test(pgio, prev, req);
 }
@@ -824,7 +838,7 @@ bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
 	u64 wb_size;
 
-	if (!is_aligned_req(pgio, req, PAGE_SIZE)) {
+	if (!is_aligned_req(pgio, req, PAGE_SIZE, true)) {
 		nfs_pageio_reset_write_mds(pgio);
 		return;
 	}
@@ -846,7 +860,7 @@ static size_t
 bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		 struct nfs_page *req)
 {
-	if (!is_aligned_req(pgio, req, PAGE_SIZE))
+	if (!is_aligned_req(pgio, req, PAGE_SIZE, true))
 		return 0;
 	return pnfs_generic_pg_test(pgio, prev, req);
 }
@@ -888,22 +902,53 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 	.sync				= pnfs_generic_sync,
 };
 
+static struct pnfs_layoutdriver_type scsilayout_type = {
+	.id				= LAYOUT_SCSI,
+	.name				= "LAYOUT_SCSI",
+	.owner				= THIS_MODULE,
+	.flags				= PNFS_LAYOUTRET_ON_SETATTR |
+					  PNFS_READ_WHOLE_PAGE,
+	.read_pagelist			= bl_read_pagelist,
+	.write_pagelist			= bl_write_pagelist,
+	.alloc_layout_hdr		= sl_alloc_layout_hdr,
+	.free_layout_hdr		= bl_free_layout_hdr,
+	.alloc_lseg			= bl_alloc_lseg,
+	.free_lseg			= bl_free_lseg,
+	.return_range			= bl_return_range,
+	.prepare_layoutcommit		= bl_prepare_layoutcommit,
+	.cleanup_layoutcommit		= bl_cleanup_layoutcommit,
+	.set_layoutdriver		= bl_set_layoutdriver,
+	.alloc_deviceid_node		= bl_alloc_deviceid_node,
+	.free_deviceid_node		= bl_free_deviceid_node,
+	.pg_read_ops			= &bl_pg_read_ops,
+	.pg_write_ops			= &bl_pg_write_ops,
+	.sync				= pnfs_generic_sync,
+};
+
+
 static int __init nfs4blocklayout_init(void)
 {
 	int ret;
 
 	dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__);
 
-	ret = pnfs_register_layoutdriver(&blocklayout_type);
+	ret = bl_init_pipefs();
 	if (ret)
 		goto out;
-	ret = bl_init_pipefs();
+
+	ret = pnfs_register_layoutdriver(&blocklayout_type);
 	if (ret)
-		goto out_unregister;
+		goto out_cleanup_pipe;
+
+	ret = pnfs_register_layoutdriver(&scsilayout_type);
+	if (ret)
+		goto out_unregister_block;
 	return 0;
 
-out_unregister:
+out_unregister_block:
 	pnfs_unregister_layoutdriver(&blocklayout_type);
+out_cleanup_pipe:
+	bl_cleanup_pipefs();
 out:
 	return ret;
 }
@@ -913,8 +958,9 @@ static void __exit nfs4blocklayout_exit(void)
 	dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n",
 	       __func__);
 
-	bl_cleanup_pipefs();
+	pnfs_unregister_layoutdriver(&scsilayout_type);
 	pnfs_unregister_layoutdriver(&blocklayout_type);
+	bl_cleanup_pipefs();
 }
 
 MODULE_ALIAS("nfs-layouttype4-3");
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index c556640dcf3b..bc21205309e0 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -55,7 +55,6 @@ struct pnfs_block_dev;
  */
 #define PNFS_BLOCK_UUID_LEN	128
 
-
 struct pnfs_block_volume {
 	enum pnfs_block_volume_type	type;
 	union {
@@ -82,6 +81,13 @@ struct pnfs_block_volume {
 			u32		volumes_count;
 			u32		volumes[PNFS_BLOCK_MAX_DEVICES];
 		} stripe;
+		struct {
+			enum scsi_code_set		code_set;
+			enum scsi_designator_type	designator_type;
+			int				designator_len;
+			u8				designator[256];
+			u64				pr_key;
+		} scsi;
 	};
 };
 
@@ -106,6 +112,9 @@ struct pnfs_block_dev {
 	struct block_device		*bdev;
 	u64				disk_offset;
 
+	u64				pr_key;
+	bool				pr_registered;
+
 	bool (*map)(struct pnfs_block_dev *dev, u64 offset,
 			struct pnfs_block_dev_map *map);
 };
@@ -131,6 +140,7 @@ struct pnfs_block_layout {
 	struct rb_root		bl_ext_rw;
 	struct rb_root		bl_ext_ro;
 	spinlock_t		bl_ext_lock;   /* Protects list manipulation */
+	bool			bl_scsi_layout;
 };
 
 static inline struct pnfs_block_layout *
@@ -182,6 +192,6 @@ void ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status);
 dev_t bl_resolve_deviceid(struct nfs_server *server,
 		struct pnfs_block_volume *b, gfp_t gfp_mask);
 int __init bl_init_pipefs(void);
-void __exit bl_cleanup_pipefs(void);
+void bl_cleanup_pipefs(void);
 
 #endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index a861bbdfe577..e5b89675263e 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -1,11 +1,12 @@
 /*
- * Copyright (c) 2014 Christoph Hellwig.
+ * Copyright (c) 2014-2016 Christoph Hellwig.
  */
 #include <linux/sunrpc/svc.h>
 #include <linux/blkdev.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_xdr.h>
+#include <linux/pr.h>
 
 #include "blocklayout.h"
 
@@ -21,6 +22,17 @@ bl_free_device(struct pnfs_block_dev *dev)
 			bl_free_device(&dev->children[i]);
 		kfree(dev->children);
 	} else {
+		if (dev->pr_registered) {
+			const struct pr_ops *ops =
+				dev->bdev->bd_disk->fops->pr_ops;
+			int error;
+
+			error = ops->pr_register(dev->bdev, dev->pr_key, 0,
+				false);
+			if (error)
+				pr_err("failed to unregister PR key.\n");
+		}
+
 		if (dev->bdev)
 			blkdev_put(dev->bdev, FMODE_READ | FMODE_WRITE);
 	}
@@ -113,6 +125,24 @@ nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 		for (i = 0; i < b->stripe.volumes_count; i++)
 			b->stripe.volumes[i] = be32_to_cpup(p++);
 		break;
+	case PNFS_BLOCK_VOLUME_SCSI:
+		p = xdr_inline_decode(xdr, 4 + 4 + 4);
+		if (!p)
+			return -EIO;
+		b->scsi.code_set = be32_to_cpup(p++);
+		b->scsi.designator_type = be32_to_cpup(p++);
+		b->scsi.designator_len = be32_to_cpup(p++);
+		p = xdr_inline_decode(xdr, b->scsi.designator_len);
+		if (!p)
+			return -EIO;
+		if (b->scsi.designator_len > 256)
+			return -EIO;
+		memcpy(&b->scsi.designator, p, b->scsi.designator_len);
+		p = xdr_inline_decode(xdr, 8);
+		if (!p)
+			return -EIO;
+		p = xdr_decode_hyper(p, &b->scsi.pr_key);
+		break;
 	default:
 		dprintk("unknown volume type!\n");
 		return -EIO;
@@ -216,6 +246,116 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d,
 	return 0;
 }
 
+static bool
+bl_validate_designator(struct pnfs_block_volume *v)
+{
+	switch (v->scsi.designator_type) {
+	case PS_DESIGNATOR_EUI64:
+		if (v->scsi.code_set != PS_CODE_SET_BINARY)
+			return false;
+
+		if (v->scsi.designator_len != 8 &&
+		    v->scsi.designator_len != 10 &&
+		    v->scsi.designator_len != 16)
+			return false;
+
+		return true;
+	case PS_DESIGNATOR_NAA:
+		if (v->scsi.code_set != PS_CODE_SET_BINARY)
+			return false;
+
+		if (v->scsi.designator_len != 8 &&
+		    v->scsi.designator_len != 16)
+			return false;
+
+		return true;
+	case PS_DESIGNATOR_T10:
+	case PS_DESIGNATOR_NAME:
+		pr_err("pNFS: unsupported designator "
+			"(code set %d, type %d, len %d.\n",
+			v->scsi.code_set,
+			v->scsi.designator_type,
+			v->scsi.designator_len);
+		return false;
+	default:
+		pr_err("pNFS: invalid designator "
+			"(code set %d, type %d, len %d.\n",
+			v->scsi.code_set,
+			v->scsi.designator_type,
+			v->scsi.designator_len);
+		return false;
+	}
+}
+
+static int
+bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
+		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
+{
+	struct pnfs_block_volume *v = &volumes[idx];
+	const struct pr_ops *ops;
+	const char *devname;
+	int error;
+
+	if (!bl_validate_designator(v))
+		return -EINVAL;
+
+	switch (v->scsi.designator_len) {
+	case 8:
+		devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%8phN",
+				v->scsi.designator);
+		break;
+	case 12:
+		devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%12phN",
+				v->scsi.designator);
+		break;
+	case 16:
+		devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%16phN",
+				v->scsi.designator);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	d->bdev = blkdev_get_by_path(devname, FMODE_READ, NULL);
+	if (IS_ERR(d->bdev)) {
+		pr_warn("pNFS: failed to open device %s (%ld)\n",
+			devname, PTR_ERR(d->bdev));
+		kfree(devname);
+		return PTR_ERR(d->bdev);
+	}
+
+	kfree(devname);
+
+	d->len = i_size_read(d->bdev->bd_inode);
+	d->map = bl_map_simple;
+	d->pr_key = v->scsi.pr_key;
+
+	pr_info("pNFS: using block device %s (reservation key 0x%llx)\n",
+		d->bdev->bd_disk->disk_name, d->pr_key);
+
+	ops = d->bdev->bd_disk->fops->pr_ops;
+	if (!ops) {
+		pr_err("pNFS: block device %s does not support reservations.",
+				d->bdev->bd_disk->disk_name);
+		error = -EINVAL;
+		goto out_blkdev_put;
+	}
+
+	error = ops->pr_register(d->bdev, 0, d->pr_key, true);
+	if (error) {
+		pr_err("pNFS: failed to register key for block device %s.",
+				d->bdev->bd_disk->disk_name);
+		goto out_blkdev_put;
+	}
+
+	d->pr_registered = true;
+	return 0;
+
+out_blkdev_put:
+	blkdev_put(d->bdev, FMODE_READ);
+	return error;
+}
+
 static int
 bl_parse_slice(struct nfs_server *server, struct pnfs_block_dev *d,
 		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
@@ -303,6 +443,8 @@ bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d,
 		return bl_parse_concat(server, d, volumes, idx, gfp_mask);
 	case PNFS_BLOCK_VOLUME_STRIPE:
 		return bl_parse_stripe(server, d, volumes, idx, gfp_mask);
+	case PNFS_BLOCK_VOLUME_SCSI:
+		return bl_parse_scsi(server, d, volumes, idx, gfp_mask);
 	default:
 		dprintk("unsupported volume type: %d\n", volumes[idx].type);
 		return -EIO;
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
index c59a59c37f3d..720b3ff55fa9 100644
--- a/fs/nfs/blocklayout/extent_tree.c
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2014 Christoph Hellwig.
+ * Copyright (c) 2014-2016 Christoph Hellwig.
  */
 
 #include <linux/vmalloc.h>
@@ -462,10 +462,12 @@ out:
 	return err;
 }
 
-static size_t ext_tree_layoutupdate_size(size_t count)
+static size_t ext_tree_layoutupdate_size(struct pnfs_block_layout *bl, size_t count)
 {
-	return sizeof(__be32) /* number of entries */ +
-		PNFS_BLOCK_EXTENT_SIZE * count;
+	if (bl->bl_scsi_layout)
+		return sizeof(__be32) + PNFS_SCSI_RANGE_SIZE * count;
+	else
+		return sizeof(__be32) + PNFS_BLOCK_EXTENT_SIZE * count;
 }
 
 static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg,
@@ -476,12 +478,30 @@ static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg,
 
 		for (i = 0; i < nr_pages; i++)
 			put_page(arg->layoutupdate_pages[i]);
+		vfree(arg->start_p);
 		kfree(arg->layoutupdate_pages);
 	} else {
 		put_page(arg->layoutupdate_page);
 	}
 }
 
+static __be32 *encode_block_extent(struct pnfs_block_extent *be, __be32 *p)
+{
+	p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data,
+			NFS4_DEVICEID4_SIZE);
+	p = xdr_encode_hyper(p, be->be_f_offset << SECTOR_SHIFT);
+	p = xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
+	p = xdr_encode_hyper(p, 0LL);
+	*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
+	return p;
+}
+
+static __be32 *encode_scsi_range(struct pnfs_block_extent *be, __be32 *p)
+{
+	p = xdr_encode_hyper(p, be->be_f_offset << SECTOR_SHIFT);
+	return xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
+}
+
 static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
 		size_t buffer_size, size_t *count)
 {
@@ -495,19 +515,16 @@ static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
 			continue;
 
 		(*count)++;
-		if (ext_tree_layoutupdate_size(*count) > buffer_size) {
+		if (ext_tree_layoutupdate_size(bl, *count) > buffer_size) {
 			/* keep counting.. */
 			ret = -ENOSPC;
 			continue;
 		}
 
-		p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data,
-				NFS4_DEVICEID4_SIZE);
-		p = xdr_encode_hyper(p, be->be_f_offset << SECTOR_SHIFT);
-		p = xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
-		p = xdr_encode_hyper(p, 0LL);
-		*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
-
+		if (bl->bl_scsi_layout)
+			p = encode_scsi_range(be, p);
+		else
+			p = encode_block_extent(be, p);
 		be->be_tag = EXTENT_COMMITTING;
 	}
 	spin_unlock(&bl->bl_ext_lock);
@@ -536,7 +553,7 @@ retry:
 	if (unlikely(ret)) {
 		ext_tree_free_commitdata(arg, buffer_size);
 
-		buffer_size = ext_tree_layoutupdate_size(count);
+		buffer_size = ext_tree_layoutupdate_size(bl, count);
 		count = 0;
 
 		arg->layoutupdate_pages =
@@ -555,14 +572,19 @@ retry:
 	}
 
 	*start_p = cpu_to_be32(count);
-	arg->layoutupdate_len = ext_tree_layoutupdate_size(count);
+	arg->layoutupdate_len = ext_tree_layoutupdate_size(bl, count);
 
 	if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) {
 		void *p = start_p, *end = p + arg->layoutupdate_len;
+		struct page *page = NULL;
 		int i = 0;
 
-		for ( ; p < end; p += PAGE_SIZE)
-			arg->layoutupdate_pages[i++] = vmalloc_to_page(p);
+		arg->start_p = start_p;
+		for ( ; p < end; p += PAGE_SIZE) {
+			page = vmalloc_to_page(p);
+			arg->layoutupdate_pages[i++] = page;
+			get_page(page);
+		}
 	}
 
 	dprintk("%s found %zu ranges\n", __func__, count);
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index dbe5839cdeba..9fb067a6f7e0 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -281,7 +281,7 @@ out:
 	return ret;
 }
 
-void __exit bl_cleanup_pipefs(void)
+void bl_cleanup_pipefs(void)
 {
 	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
 	unregister_pernet_subsys(&nfs4blocklayout_net_ops);
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index ff8195bd75ea..5fe1cecbf9f0 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -37,10 +37,11 @@ enum nfs4_callback_opnum {
 	OP_CB_ILLEGAL = 10044,
 };
 
+struct nfs4_slot;
 struct cb_process_state {
 	__be32			drc_status;
 	struct nfs_client	*clp;
-	u32			slotid;
+	struct nfs4_slot	*slot;
 	u32			minorversion;
 	struct net		*net;
 };
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index f0939d097406..618ced381a14 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -354,47 +354,38 @@ out:
  * a single outstanding callback request at a time.
  */
 static __be32
-validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
+validate_seqid(const struct nfs4_slot_table *tbl, const struct nfs4_slot *slot,
+		const struct cb_sequenceargs * args)
 {
-	struct nfs4_slot *slot;
-
-	dprintk("%s enter. slotid %u seqid %u\n",
-		__func__, args->csa_slotid, args->csa_sequenceid);
+	dprintk("%s enter. slotid %u seqid %u, slot table seqid: %u\n",
+		__func__, args->csa_slotid, args->csa_sequenceid, slot->seq_nr);
 
-	if (args->csa_slotid >= NFS41_BC_MAX_CALLBACKS)
+	if (args->csa_slotid > tbl->server_highest_slotid)
 		return htonl(NFS4ERR_BADSLOT);
 
-	slot = tbl->slots + args->csa_slotid;
-	dprintk("%s slot table seqid: %u\n", __func__, slot->seq_nr);
-
-	/* Normal */
-	if (likely(args->csa_sequenceid == slot->seq_nr + 1))
-		goto out_ok;
-
 	/* Replay */
 	if (args->csa_sequenceid == slot->seq_nr) {
 		dprintk("%s seqid %u is a replay\n",
 			__func__, args->csa_sequenceid);
+		if (nfs4_test_locked_slot(tbl, slot->slot_nr))
+			return htonl(NFS4ERR_DELAY);
 		/* Signal process_op to set this error on next op */
 		if (args->csa_cachethis == 0)
 			return htonl(NFS4ERR_RETRY_UNCACHED_REP);
 
-		/* The ca_maxresponsesize_cached is 0 with no DRC */
-		else if (args->csa_cachethis == 1)
-			return htonl(NFS4ERR_REP_TOO_BIG_TO_CACHE);
+		/* Liar! We never allowed you to set csa_cachethis != 0 */
+		return htonl(NFS4ERR_SEQ_FALSE_RETRY);
 	}
 
 	/* Wraparound */
-	if (args->csa_sequenceid == 1 && (slot->seq_nr + 1) == 0) {
-		slot->seq_nr = 1;
-		goto out_ok;
-	}
+	if (unlikely(slot->seq_nr == 0xFFFFFFFFU)) {
+		if (args->csa_sequenceid == 1)
+			return htonl(NFS4_OK);
+	} else if (likely(args->csa_sequenceid == slot->seq_nr + 1))
+		return htonl(NFS4_OK);
 
 	/* Misordered request */
 	return htonl(NFS4ERR_SEQ_MISORDERED);
-out_ok:
-	tbl->highest_used_slotid = args->csa_slotid;
-	return htonl(NFS4_OK);
 }
 
 /*
@@ -473,6 +464,12 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 	tbl = &clp->cl_session->bc_slot_table;
 	slot = tbl->slots + args->csa_slotid;
 
+	/* Set up res before grabbing the spinlock */
+	memcpy(&res->csr_sessionid, &args->csa_sessionid,
+	       sizeof(res->csr_sessionid));
+	res->csr_sequenceid = args->csa_sequenceid;
+	res->csr_slotid = args->csa_slotid;
+
 	spin_lock(&tbl->slot_tbl_lock);
 	/* state manager is resetting the session */
 	if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
@@ -485,18 +482,26 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 		goto out_unlock;
 	}
 
-	memcpy(&res->csr_sessionid, &args->csa_sessionid,
-	       sizeof(res->csr_sessionid));
-	res->csr_sequenceid = args->csa_sequenceid;
-	res->csr_slotid = args->csa_slotid;
-	res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
-	res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
+	status = htonl(NFS4ERR_BADSLOT);
+	slot = nfs4_lookup_slot(tbl, args->csa_slotid);
+	if (IS_ERR(slot))
+		goto out_unlock;
+
+	res->csr_highestslotid = tbl->server_highest_slotid;
+	res->csr_target_highestslotid = tbl->target_highest_slotid;
 
-	status = validate_seqid(tbl, args);
+	status = validate_seqid(tbl, slot, args);
 	if (status)
 		goto out_unlock;
+	if (!nfs4_try_to_lock_slot(tbl, slot)) {
+		status = htonl(NFS4ERR_DELAY);
+		goto out_unlock;
+	}
+	cps->slot = slot;
 
-	cps->slotid = args->csa_slotid;
+	/* The ca_maxresponsesize_cached is 0 with no DRC */
+	if (args->csa_cachethis != 0)
+		return htonl(NFS4ERR_REP_TOO_BIG_TO_CACHE);
 
 	/*
 	 * Check for pending referring calls.  If a match is found, a
@@ -513,7 +518,7 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 	 * If CB_SEQUENCE returns an error, then the state of the slot
 	 * (sequence ID, cached reply) MUST NOT change.
 	 */
-	slot->seq_nr++;
+	slot->seq_nr = args->csa_sequenceid;
 out_unlock:
 	spin_unlock(&tbl->slot_tbl_lock);
 
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 646cdac73488..976c90608e56 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -752,7 +752,8 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
 	return htonl(NFS_OK);
 }
 
-static void nfs4_callback_free_slot(struct nfs4_session *session)
+static void nfs4_callback_free_slot(struct nfs4_session *session,
+		struct nfs4_slot *slot)
 {
 	struct nfs4_slot_table *tbl = &session->bc_slot_table;
 
@@ -761,15 +762,17 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
 	 * Let the state manager know callback processing done.
 	 * A single slot, so highest used slotid is either 0 or -1
 	 */
-	tbl->highest_used_slotid = NFS4_NO_SLOT;
+	nfs4_free_slot(tbl, slot);
 	nfs4_slot_tbl_drain_complete(tbl);
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 
 static void nfs4_cb_free_slot(struct cb_process_state *cps)
 {
-	if (cps->slotid != NFS4_NO_SLOT)
-		nfs4_callback_free_slot(cps->clp->cl_session);
+	if (cps->slot) {
+		nfs4_callback_free_slot(cps->clp->cl_session, cps->slot);
+		cps->slot = NULL;
+	}
 }
 
 #else /* CONFIG_NFS_V4_1 */
@@ -893,7 +896,6 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	struct cb_process_state cps = {
 		.drc_status = 0,
 		.clp = NULL,
-		.slotid = NFS4_NO_SLOT,
 		.net = SVC_NET(rqstp),
 	};
 	unsigned int nops = 0;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 9cce67043f92..4bfa7d8bcade 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1360,19 +1360,15 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
 	dfprintk(VFS, "NFS: lookup(%pd2)\n", dentry);
 	nfs_inc_stats(dir, NFSIOS_VFSLOOKUP);
 
-	res = ERR_PTR(-ENAMETOOLONG);
-	if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
-		goto out;
+	if (unlikely(dentry->d_name.len > NFS_SERVER(dir)->namelen))
+		return ERR_PTR(-ENAMETOOLONG);
 
 	/*
 	 * If we're doing an exclusive create, optimize away the lookup
 	 * but don't hash the dentry.
 	 */
-	if (nfs_is_exclusive_create(dir, flags)) {
-		d_instantiate(dentry, NULL);
-		res = NULL;
-		goto out;
-	}
+	if (nfs_is_exclusive_create(dir, flags))
+		return NULL;
 
 	res = ERR_PTR(-ENOMEM);
 	fhandle = nfs_alloc_fhandle();
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 748bb813b8ec..89bf093d342a 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -233,7 +233,7 @@ EXPORT_SYMBOL_GPL(nfs_file_mmap);
  * nfs_file_write() that a write error occurred, and hence cause it to
  * fall back to doing a synchronous write.
  */
-int
+static int
 nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
@@ -263,9 +263,8 @@ nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
 out:
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nfs_file_fsync_commit);
 
-static int
+int
 nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	int ret;
@@ -273,13 +272,15 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 	trace_nfs_fsync_enter(inode);
 
-	nfs_inode_dio_wait(inode);
+	inode_dio_wait(inode);
 	do {
 		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 		if (ret != 0)
 			break;
 		inode_lock(inode);
 		ret = nfs_file_fsync_commit(file, start, end, datasync);
+		if (!ret)
+			ret = pnfs_sync_inode(inode, !!datasync);
 		inode_unlock(inode);
 		/*
 		 * If nfs_file_fsync_commit detected a server reboot, then
@@ -293,6 +294,7 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	trace_nfs_fsync_exit(inode, ret);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_file_fsync);
 
 /*
  * Decide whether a read/modify/write cycle may be more efficient
@@ -368,7 +370,7 @@ start:
 	/*
 	 * Wait for O_DIRECT to complete
 	 */
-	nfs_inode_dio_wait(mapping->host);
+	inode_dio_wait(mapping->host);
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 5bcd92d50e82..0cb1abd535e3 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1215,7 +1215,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 					hdr->pgio_mirror_idx + 1,
 					&hdr->pgio_mirror_idx))
 			goto out_eagain;
-		set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+		set_bit(NFS_LAYOUT_RETURN_REQUESTED,
 			&hdr->lseg->pls_layout->plh_flags);
 		pnfs_read_resend_pnfs(hdr);
 		return task->tk_status;
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 29898a9550fa..add0e5a70bd6 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -412,12 +412,14 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
 					 OP_ILLEGAL, GFP_NOIO);
 		if (!fail_return) {
 			if (ff_layout_has_available_ds(lseg))
-				set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+				set_bit(NFS_LAYOUT_RETURN_REQUESTED,
 					&lseg->pls_layout->plh_flags);
 			else
 				pnfs_error_mark_layout_for_return(ino, lseg);
 		} else
 			pnfs_error_mark_layout_for_return(ino, lseg);
+		ds = NULL;
+		goto out;
 	}
 out_update_creds:
 	if (ff_layout_update_mirror_cred(mirror, ds))
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 86faecf8f328..33d18c411905 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -141,7 +141,7 @@ void nfs_evict_inode(struct inode *inode)
 
 int nfs_sync_inode(struct inode *inode)
 {
-	nfs_inode_dio_wait(inode);
+	inode_dio_wait(inode);
 	return nfs_wb_all(inode);
 }
 EXPORT_SYMBOL_GPL(nfs_sync_inode);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 9a547aa3ec8e..565f8135ae1f 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -358,7 +358,7 @@ int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
 
 /* file.c */
-int nfs_file_fsync_commit(struct file *, loff_t, loff_t, int);
+int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync);
 loff_t nfs_file_llseek(struct file *, loff_t, int);
 ssize_t nfs_file_read(struct kiocb *, struct iov_iter *);
 ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *,
@@ -515,10 +515,6 @@ extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry);
 /* direct.c */
 void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 			      struct nfs_direct_req *dreq);
-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);
 
 /* nfs4proc.c */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index bd25dc7077f7..dff83460e5a6 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -16,29 +16,8 @@
 
 #define NFSDBG_FACILITY NFSDBG_PROC
 
-static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file,
-				fmode_t fmode)
-{
-	struct nfs_open_context *open;
-	struct nfs_lock_context *lock;
-	int ret;
-
-	open = get_nfs_open_context(nfs_file_open_context(file));
-	lock = nfs_get_lock_context(open);
-	if (IS_ERR(lock)) {
-		put_nfs_open_context(open);
-		return PTR_ERR(lock);
-	}
-
-	ret = nfs4_set_rw_stateid(dst, open, lock, fmode);
-
-	nfs_put_lock_context(lock);
-	put_nfs_open_context(open);
-	return ret;
-}
-
 static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
-				 loff_t offset, loff_t len)
+		struct nfs_lock_context *lock, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs_server *server = NFS_SERVER(inode);
@@ -56,7 +35,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	msg->rpc_argp = &args;
 	msg->rpc_resp = &res;
 
-	status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE);
+	status = nfs4_set_rw_stateid(&args.falloc_stateid, lock->open_context,
+			lock, FMODE_WRITE);
 	if (status)
 		return status;
 
@@ -78,15 +58,26 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
+	struct nfs_lock_context *lock;
 	int err;
 
+	lock = nfs_get_lock_context(nfs_file_open_context(filep));
+	if (IS_ERR(lock))
+		return PTR_ERR(lock);
+
+	exception.inode = file_inode(filep);
+	exception.state = lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_fallocate(msg, filep, offset, len);
-		if (err == -ENOTSUPP)
-			return -EOPNOTSUPP;
+		err = _nfs42_proc_fallocate(msg, filep, lock, offset, len);
+		if (err == -ENOTSUPP) {
+			err = -EOPNOTSUPP;
+			break;
+		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 
+	nfs_put_lock_context(lock);
 	return err;
 }
 
@@ -135,7 +126,8 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	return err;
 }
 
-static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+static loff_t _nfs42_proc_llseek(struct file *filep,
+		struct nfs_lock_context *lock, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs42_seek_args args = {
@@ -156,7 +148,8 @@ static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 	if (!nfs_server_capable(inode, NFS_CAP_SEEK))
 		return -ENOTSUPP;
 
-	status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ);
+	status = nfs4_set_rw_stateid(&args.sa_stateid, lock->open_context,
+			lock, FMODE_READ);
 	if (status)
 		return status;
 
@@ -175,17 +168,28 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
+	struct nfs_lock_context *lock;
 	loff_t err;
 
+	lock = nfs_get_lock_context(nfs_file_open_context(filep));
+	if (IS_ERR(lock))
+		return PTR_ERR(lock);
+
+	exception.inode = file_inode(filep);
+	exception.state = lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_llseek(filep, offset, whence);
+		err = _nfs42_proc_llseek(filep, lock, offset, whence);
 		if (err >= 0)
 			break;
-		if (err == -ENOTSUPP)
-			return -EOPNOTSUPP;
+		if (err == -ENOTSUPP) {
+			err = -EOPNOTSUPP;
+			break;
+		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 
+	nfs_put_lock_context(lock);
 	return err;
 }
 
@@ -298,8 +302,9 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server,
 }
 
 static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
-			     struct file *dst_f, loff_t src_offset,
-			     loff_t dst_offset, loff_t count)
+		struct file *dst_f, struct nfs_lock_context *src_lock,
+		struct nfs_lock_context *dst_lock, loff_t src_offset,
+		loff_t dst_offset, loff_t count)
 {
 	struct inode *src_inode = file_inode(src_f);
 	struct inode *dst_inode = file_inode(dst_f);
@@ -320,11 +325,13 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
 	msg->rpc_argp = &args;
 	msg->rpc_resp = &res;
 
-	status = nfs42_set_rw_stateid(&args.src_stateid, src_f, FMODE_READ);
+	status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context,
+			src_lock, FMODE_READ);
 	if (status)
 		return status;
 
-	status = nfs42_set_rw_stateid(&args.dst_stateid, dst_f, FMODE_WRITE);
+	status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
+			dst_lock, FMODE_WRITE);
 	if (status)
 		return status;
 
@@ -349,22 +356,48 @@ int nfs42_proc_clone(struct file *src_f, struct file *dst_f,
 	};
 	struct inode *inode = file_inode(src_f);
 	struct nfs_server *server = NFS_SERVER(file_inode(src_f));
-	struct nfs4_exception exception = { };
-	int err;
+	struct nfs_lock_context *src_lock;
+	struct nfs_lock_context *dst_lock;
+	struct nfs4_exception src_exception = { };
+	struct nfs4_exception dst_exception = { };
+	int err, err2;
 
 	if (!nfs_server_capable(inode, NFS_CAP_CLONE))
 		return -EOPNOTSUPP;
 
+	src_lock = nfs_get_lock_context(nfs_file_open_context(src_f));
+	if (IS_ERR(src_lock))
+		return PTR_ERR(src_lock);
+
+	src_exception.inode = file_inode(src_f);
+	src_exception.state = src_lock->open_context->state;
+
+	dst_lock = nfs_get_lock_context(nfs_file_open_context(dst_f));
+	if (IS_ERR(dst_lock)) {
+		err = PTR_ERR(dst_lock);
+		goto out_put_src_lock;
+	}
+
+	dst_exception.inode = file_inode(dst_f);
+	dst_exception.state = dst_lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_clone(&msg, src_f, dst_f, src_offset,
-					dst_offset, count);
+		err = _nfs42_proc_clone(&msg, src_f, dst_f, src_lock, dst_lock,
+					src_offset, dst_offset, count);
 		if (err == -ENOTSUPP || err == -EOPNOTSUPP) {
 			NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE;
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			break;
 		}
-		err = nfs4_handle_exception(server, err, &exception);
-	} while (exception.retry);
 
-	return err;
+		err2 = nfs4_handle_exception(server, err, &src_exception);
+		err = nfs4_handle_exception(server, err, &dst_exception);
+		if (!err)
+			err = err2;
+	} while (src_exception.retry || dst_exception.retry);
 
+	nfs_put_lock_context(dst_lock);
+out_put_src_lock:
+	nfs_put_lock_context(src_lock);
+	return err;
 }
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 57ca1c8039c1..22c35abbee9d 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -128,37 +128,6 @@ nfs4_file_flush(struct file *file, fl_owner_t id)
 	return vfs_fsync(file, 0);
 }
 
-static int
-nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
-{
-	int ret;
-	struct inode *inode = file_inode(file);
-
-	trace_nfs_fsync_enter(inode);
-
-	nfs_inode_dio_wait(inode);
-	do {
-		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-		if (ret != 0)
-			break;
-		inode_lock(inode);
-		ret = nfs_file_fsync_commit(file, start, end, datasync);
-		if (!ret)
-			ret = pnfs_sync_inode(inode, !!datasync);
-		inode_unlock(inode);
-		/*
-		 * If nfs_file_fsync_commit detected a server reboot, then
-		 * resend all dirty pages that might have been covered by
-		 * the NFS_CONTEXT_RESEND_WRITES flag
-		 */
-		start = 0;
-		end = LLONG_MAX;
-	} while (ret == -EAGAIN);
-
-	trace_nfs_fsync_exit(inode, ret);
-	return ret;
-}
-
 #ifdef CONFIG_NFS_V4_2
 static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
 {
@@ -266,7 +235,7 @@ const struct file_operations nfs4_file_operations = {
 	.open		= nfs4_file_open,
 	.flush		= nfs4_file_flush,
 	.release	= nfs_file_release,
-	.fsync		= nfs4_file_fsync,
+	.fsync		= nfs_file_fsync,
 	.lock		= nfs_lock,
 	.flock		= nfs_flock,
 	.splice_read	= nfs_file_splice_read,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4bfc33ad0563..327b8c34d360 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2461,14 +2461,15 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 
 	dentry = opendata->dentry;
 	if (d_really_is_negative(dentry)) {
-		/* FIXME: Is this d_drop() ever needed? */
+		struct dentry *alias;
 		d_drop(dentry);
-		dentry = d_add_unique(dentry, igrab(state->inode));
-		if (dentry == NULL) {
-			dentry = opendata->dentry;
-		} else if (dentry != ctx->dentry) {
+		alias = d_exact_alias(dentry, state->inode);
+		if (!alias)
+			alias = d_splice_alias(igrab(state->inode), dentry);
+		/* d_splice_alias() can't fail here - it's a non-directory */
+		if (alias) {
 			dput(ctx->dentry);
-			ctx->dentry = dget(dentry);
+			ctx->dentry = dentry = alias;
 		}
 		nfs_set_verifier(dentry,
 				nfs_save_change_attribute(d_inode(opendata->dir)));
@@ -6782,13 +6783,26 @@ nfs41_same_server_scope(struct nfs41_server_scope *a,
 	return false;
 }
 
+static void
+nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
+{
+}
+
+static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
+	.rpc_call_done =  &nfs4_bind_one_conn_to_session_done,
+};
+
 /*
- * nfs4_proc_bind_conn_to_session()
+ * nfs4_proc_bind_one_conn_to_session()
  *
  * The 4.1 client currently uses the same TCP connection for the
  * fore and backchannel.
  */
-int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred)
+static
+int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
+		struct rpc_xprt *xprt,
+		struct nfs_client *clp,
+		struct rpc_cred *cred)
 {
 	int status;
 	struct nfs41_bind_conn_to_session_args args = {
@@ -6803,6 +6817,14 @@ int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred
 		.rpc_resp = &res,
 		.rpc_cred = cred,
 	};
+	struct rpc_task_setup task_setup_data = {
+		.rpc_client = clnt,
+		.rpc_xprt = xprt,
+		.callback_ops = &nfs4_bind_one_conn_to_session_ops,
+		.rpc_message = &msg,
+		.flags = RPC_TASK_TIMEOUT,
+	};
+	struct rpc_task *task;
 
 	dprintk("--> %s\n", __func__);
 
@@ -6810,7 +6832,16 @@ int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred
 	if (!(clp->cl_session->flags & SESSION4_BACK_CHAN))
 		args.dir = NFS4_CDFC4_FORE;
 
-	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+	/* Do not set the backchannel flag unless this is clnt->cl_xprt */
+	if (xprt != rcu_access_pointer(clnt->cl_xprt))
+		args.dir = NFS4_CDFC4_FORE;
+
+	task = rpc_run_task(&task_setup_data);
+	if (!IS_ERR(task)) {
+		status = task->tk_status;
+		rpc_put_task(task);
+	} else
+		status = PTR_ERR(task);
 	trace_nfs4_bind_conn_to_session(clp, status);
 	if (status == 0) {
 		if (memcmp(res.sessionid.data,
@@ -6837,6 +6868,31 @@ out:
 	return status;
 }
 
+struct rpc_bind_conn_calldata {
+	struct nfs_client *clp;
+	struct rpc_cred *cred;
+};
+
+static int
+nfs4_proc_bind_conn_to_session_callback(struct rpc_clnt *clnt,
+		struct rpc_xprt *xprt,
+		void *calldata)
+{
+	struct rpc_bind_conn_calldata *p = calldata;
+
+	return nfs4_proc_bind_one_conn_to_session(clnt, xprt, p->clp, p->cred);
+}
+
+int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred)
+{
+	struct rpc_bind_conn_calldata data = {
+		.clp = clp,
+		.cred = cred,
+	};
+	return rpc_clnt_iterate_for_each_xprt(clp->cl_rpcclient,
+			nfs4_proc_bind_conn_to_session_callback, &data);
+}
+
 /*
  * Minimum set of SP4_MACH_CRED operations from RFC 5661 in the enforce map
  * and operations we'd like to see to enable certain features in the allow map
@@ -7319,7 +7375,7 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
 	args->bc_attrs.max_resp_sz = PAGE_SIZE;
 	args->bc_attrs.max_resp_sz_cached = 0;
 	args->bc_attrs.max_ops = NFS4_MAX_BACK_CHANNEL_OPS;
-	args->bc_attrs.max_reqs = 1;
+	args->bc_attrs.max_reqs = NFS41_BC_MAX_CALLBACKS;
 
 	dprintk("%s: Back Channel : max_rqst_sz=%u max_resp_sz=%u "
 		"max_resp_sz_cached=%u max_ops=%u max_reqs=%u\n",
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index e23366effcfb..332d06e64fa9 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -135,6 +135,43 @@ static struct nfs4_slot *nfs4_find_or_create_slot(struct nfs4_slot_table  *tbl,
 	return ERR_PTR(-ENOMEM);
 }
 
+static void nfs4_lock_slot(struct nfs4_slot_table *tbl,
+		struct nfs4_slot *slot)
+{
+	u32 slotid = slot->slot_nr;
+
+	__set_bit(slotid, tbl->used_slots);
+	if (slotid > tbl->highest_used_slotid ||
+	    tbl->highest_used_slotid == NFS4_NO_SLOT)
+		tbl->highest_used_slotid = slotid;
+	slot->generation = tbl->generation;
+}
+
+/*
+ * nfs4_try_to_lock_slot - Given a slot try to allocate it
+ *
+ * Note: must be called with the slot_tbl_lock held.
+ */
+bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot)
+{
+	if (nfs4_test_locked_slot(tbl, slot->slot_nr))
+		return false;
+	nfs4_lock_slot(tbl, slot);
+	return true;
+}
+
+/*
+ * nfs4_lookup_slot - Find a slot but don't allocate it
+ *
+ * Note: must be called with the slot_tbl_lock held.
+ */
+struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid)
+{
+	if (slotid <= tbl->max_slotid)
+		return nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
+	return ERR_PTR(-E2BIG);
+}
+
 /*
  * nfs4_alloc_slot - efficiently look for a free slot
  *
@@ -153,18 +190,11 @@ struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl)
 		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
 		tbl->max_slotid + 1);
 	slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slotid + 1);
-	if (slotid > tbl->max_slotid)
-		goto out;
-	ret = nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
-	if (IS_ERR(ret))
-		goto out;
-	__set_bit(slotid, tbl->used_slots);
-	if (slotid > tbl->highest_used_slotid ||
-			tbl->highest_used_slotid == NFS4_NO_SLOT)
-		tbl->highest_used_slotid = slotid;
-	ret->generation = tbl->generation;
-
-out:
+	if (slotid <= tbl->max_slotid) {
+		ret = nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
+		if (!IS_ERR(ret))
+			nfs4_lock_slot(tbl, ret);
+	}
 	dprintk("<-- %s used_slots=%04lx highest_used=%u slotid=%u\n",
 		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
 		!IS_ERR(ret) ? ret->slot_nr : NFS4_NO_SLOT);
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index e3ea2c5324d6..5b51298d1d03 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -77,6 +77,8 @@ extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
 		unsigned int max_reqs, const char *queue);
 extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl);
 extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
+extern struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid);
+extern bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
 extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
 extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
 bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl,
@@ -88,6 +90,12 @@ static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl)
 	return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
 }
 
+static inline bool nfs4_test_locked_slot(const struct nfs4_slot_table *tbl,
+		u32 slotid)
+{
+	return !!test_bit(slotid, tbl->used_slots);
+}
+
 #if defined(CONFIG_NFS_V4_1)
 extern void nfs41_set_target_slotid(struct nfs4_slot_table *tbl,
 		u32 target_highest_slotid);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index a3592cc34a20..2fa483e6dbe2 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -52,9 +52,7 @@ static DEFINE_SPINLOCK(pnfs_spinlock);
  */
 static LIST_HEAD(pnfs_modules_tbl);
 
-static int
-pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid,
-		       enum pnfs_iomode iomode, bool sync);
+static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo);
 
 /* Return the registered pnfs layout driver module matching given id */
 static struct pnfs_layoutdriver_type *
@@ -243,6 +241,8 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 {
 	struct inode *inode = lo->plh_inode;
 
+	pnfs_layoutreturn_before_put_layout_hdr(lo);
+
 	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");
@@ -252,6 +252,27 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 	}
 }
 
+/*
+ * Mark a pnfs_layout_hdr and all associated layout segments as invalid
+ *
+ * In order to continue using the pnfs_layout_hdr, a full recovery
+ * is required.
+ * Note that caller must hold inode->i_lock.
+ */
+static int
+pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
+		struct list_head *lseg_list)
+{
+	struct pnfs_layout_range range = {
+		.iomode = IOMODE_ANY,
+		.offset = 0,
+		.length = NFS4_MAX_UINT64,
+	};
+
+	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+	return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range);
+}
+
 static int
 pnfs_iomode_to_fail_bit(u32 iomode)
 {
@@ -345,58 +366,6 @@ 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_and_clear_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 bool
-pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
-{
-	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
-		return false;
-	lo->plh_return_iomode = 0;
-	pnfs_get_layout_hdr(lo);
-	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
-	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;
-		bool send;
-
-		nfs4_stateid_copy(&stateid, &lo->plh_stateid);
-		iomode = lo->plh_return_iomode;
-		send = pnfs_prepare_layoutreturn(lo);
-		spin_unlock(&inode->i_lock);
-		if (send) {
-			/* 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)
 {
@@ -410,15 +379,8 @@ pnfs_put_lseg(struct pnfs_layout_segment *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)) {
 		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
@@ -613,9 +575,8 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 	spin_lock(&nfsi->vfs_inode.i_lock);
 	lo = nfsi->layout;
 	if (lo) {
-		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
 		pnfs_get_layout_hdr(lo);
+		pnfs_mark_layout_stateid_invalid(lo, &tmp_list);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
 		spin_unlock(&nfsi->vfs_inode.i_lock);
@@ -676,11 +637,6 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
 {
 	struct pnfs_layout_hdr *lo;
 	struct inode *inode;
-	struct pnfs_layout_range range = {
-		.iomode = IOMODE_ANY,
-		.offset = 0,
-		.length = NFS4_MAX_UINT64,
-	};
 	LIST_HEAD(lseg_list);
 	int ret = 0;
 
@@ -695,11 +651,11 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
 
 		spin_lock(&inode->i_lock);
 		list_del_init(&lo->plh_bulk_destroy);
-		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		if (is_bulk_recall)
-			set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
-		if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range))
+		if (pnfs_mark_layout_stateid_invalid(lo, &lseg_list)) {
+			if (is_bulk_recall)
+				set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
 			ret = -EAGAIN;
+		}
 		spin_unlock(&inode->i_lock);
 		pnfs_free_lseg_list(&lseg_list);
 		/* Free all lsegs that are attached to commit buckets */
@@ -937,6 +893,17 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
 	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 }
 
+static bool
+pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
+{
+	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		return false;
+	lo->plh_return_iomode = 0;
+	pnfs_get_layout_hdr(lo);
+	clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+	return true;
+}
+
 static int
 pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid,
 		       enum pnfs_iomode iomode, bool sync)
@@ -971,6 +938,48 @@ out:
 	return status;
 }
 
+/* Return true if layoutreturn is needed */
+static bool
+pnfs_layout_need_return(struct pnfs_layout_hdr *lo)
+{
+	struct pnfs_layout_segment *s;
+
+	if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+		return false;
+
+	/* Defer layoutreturn until all lsegs are done */
+	list_for_each_entry(s, &lo->plh_segs, pls_list) {
+		if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
+			return false;
+	}
+
+	return true;
+}
+
+static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	struct inode *inode= lo->plh_inode;
+
+	if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+		return;
+	spin_lock(&inode->i_lock);
+	if (pnfs_layout_need_return(lo)) {
+		nfs4_stateid stateid;
+		enum pnfs_iomode iomode;
+		bool send;
+
+		nfs4_stateid_copy(&stateid, &lo->plh_stateid);
+		iomode = lo->plh_return_iomode;
+		send = pnfs_prepare_layoutreturn(lo);
+		spin_unlock(&inode->i_lock);
+		if (send) {
+			/* Send an async layoutreturn so we dont deadlock */
+			pnfs_send_layoutreturn(lo, &stateid, iomode, false);
+		}
+	} else
+		spin_unlock(&inode->i_lock);
+}
+
 /*
  * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
  * when the layout segment list is empty.
@@ -1091,7 +1100,7 @@ bool pnfs_roc(struct inode *ino)
 
 	nfs4_stateid_copy(&stateid, &lo->plh_stateid);
 	/* always send layoutreturn if being marked so */
-	if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+	if (test_and_clear_bit(NFS_LAYOUT_RETURN_REQUESTED,
 				   &lo->plh_flags))
 		layoutreturn = pnfs_prepare_layoutreturn(lo);
 
@@ -1744,8 +1753,19 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
 	if (lo->plh_return_iomode != 0)
 		iomode = IOMODE_ANY;
 	lo->plh_return_iomode = iomode;
+	set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
 }
 
+/**
+ * pnfs_mark_matching_lsegs_return - Free or return matching layout segments
+ * @lo: pointer to layout header
+ * @tmp_list: list header to be used with pnfs_free_lseg_list()
+ * @return_range: describe layout segment ranges to be returned
+ *
+ * This function is mainly intended for use by layoutrecall. It attempts
+ * to free the layout segment immediately, or else to mark it for return
+ * as soon as its reference count drops to zero.
+ */
 int
 pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
@@ -1768,12 +1788,11 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				lseg, lseg->pls_range.iomode,
 				lseg->pls_range.offset,
 				lseg->pls_range.length);
+			if (mark_lseg_invalid(lseg, tmp_list))
+				continue;
+			remaining++;
 			set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
 			pnfs_set_plh_return_iomode(lo, return_range->iomode);
-			if (!mark_lseg_invalid(lseg, tmp_list))
-				remaining++;
-			set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
-					&lo->plh_flags);
 		}
 	return remaining;
 }
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 9f4e2a47f4aa..1ac1db5f6dad 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -94,8 +94,8 @@ 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_RETURN,		/* Return this layout ASAP */
-	NFS_LAYOUT_RETURN_BEFORE_CLOSE,	/* Return this layout before close */
+	NFS_LAYOUT_RETURN,		/* layoutreturn in progress */
+	NFS_LAYOUT_RETURN_REQUESTED,	/* Return this layout ASAP */
 	NFS_LAYOUT_INVALID_STID,	/* layout stateid id is invalid */
 	NFS_LAYOUT_FIRST_LAYOUTGET,	/* Serialize first layoutget */
 };
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 81ac6480f9e7..4aaed890048f 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -606,12 +606,22 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 		dprintk("%s: DS %s: trying address %s\n",
 			__func__, ds->ds_remotestr, da->da_remotestr);
 
-		clp = get_v3_ds_connect(mds_srv->nfs_client,
+		if (!IS_ERR(clp)) {
+			struct xprt_create xprt_args = {
+				.ident = XPRT_TRANSPORT_TCP,
+				.net = clp->cl_net,
+				.dstaddr = (struct sockaddr *)&da->da_addr,
+				.addrlen = da->da_addrlen,
+				.servername = clp->cl_hostname,
+			};
+			/* Add this address as an alias */
+			rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
+					rpc_clnt_test_and_add_xprt, NULL);
+		} else
+			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)) {
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index a0b77fc1bd39..c9f583d7bac8 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -84,12 +84,30 @@ config NFSD_V4
 	  If unsure, say N.
 
 config NFSD_PNFS
-	bool "NFSv4.1 server support for Parallel NFS (pNFS)"
-	depends on NFSD_V4
+	bool
+
+config NFSD_BLOCKLAYOUT
+	bool "NFSv4.1 server support for pNFS block layouts"
+	depends on NFSD_V4 && BLOCK
+	select NFSD_PNFS
+	help
+	  This option enables support for the exporting pNFS block layouts
+	  in the kernel's NFS server. The pNFS block layout enables NFS
+	  clients to directly perform I/O to block devices accesible to both
+	  the server and the clients.  See RFC 5663 for more details.
+
+	  If unsure, say N.
+
+config NFSD_SCSILAYOUT
+	bool "NFSv4.1 server support for pNFS SCSI layouts"
+	depends on NFSD_V4 && BLOCK
+	select NFSD_PNFS
 	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.
+	  This option enables support for the exporting pNFS SCSI layouts
+	  in the kernel's NFS server. The pNFS SCSI layout enables NFS
+	  clients to directly perform I/O to SCSI devices accesible to both
+	  the server and the clients.  See draft-ietf-nfsv4-scsi-layout for
+	  more details.
 
 	  If unsure, say N.
 
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index 9a6028e120c6..3ae5f3c77e28 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -17,4 +17,6 @@ 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
+nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
+nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
+nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index c29d9421bd5e..e55b5242614d 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -1,11 +1,14 @@
 /*
- * Copyright (c) 2014 Christoph Hellwig.
+ * Copyright (c) 2014-2016 Christoph Hellwig.
  */
 #include <linux/exportfs.h>
 #include <linux/genhd.h>
 #include <linux/slab.h>
+#include <linux/pr.h>
 
 #include <linux/nfsd/debug.h>
+#include <scsi/scsi_proto.h>
+#include <scsi/scsi_common.h>
 
 #include "blocklayoutxdr.h"
 #include "pnfs.h"
@@ -13,37 +16,6 @@
 #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)
@@ -141,20 +113,13 @@ out_layoutunavailable:
 }
 
 static __be32
-nfsd4_block_proc_layoutcommit(struct inode *inode,
-		struct nfsd4_layoutcommit *lcp)
+nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp,
+		struct iomap *iomaps, int nr_iomaps)
 {
 	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);
@@ -172,6 +137,54 @@ nfsd4_block_proc_layoutcommit(struct inode *inode,
 	return nfserrno(error);
 }
 
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
+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 nfs4_client *clp,
+		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_layoutcommit(struct inode *inode,
+		struct nfsd4_layoutcommit *lcp)
+{
+	struct iomap *iomaps;
+	int nr_iomaps;
+
+	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);
+
+	return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps);
+}
+
 const struct nfsd4_layout_ops bl_layout_ops = {
 	/*
 	 * Pretend that we send notification to the client.  This is a blatant
@@ -190,3 +203,206 @@ const struct nfsd4_layout_ops bl_layout_ops = {
 	.encode_layoutget	= nfsd4_block_encode_layoutget,
 	.proc_layoutcommit	= nfsd4_block_proc_layoutcommit,
 };
+#endif /* CONFIG_NFSD_BLOCKLAYOUT */
+
+#ifdef CONFIG_NFSD_SCSILAYOUT
+static int nfsd4_scsi_identify_device(struct block_device *bdev,
+		struct pnfs_block_volume *b)
+{
+	struct request_queue *q = bdev->bd_disk->queue;
+	struct request *rq;
+	size_t bufflen = 252, len, id_len;
+	u8 *buf, *d, type, assoc;
+	int error;
+
+	buf = kzalloc(bufflen, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	rq = blk_get_request(q, READ, GFP_KERNEL);
+	if (IS_ERR(rq)) {
+		error = -ENOMEM;
+		goto out_free_buf;
+	}
+	blk_rq_set_block_pc(rq);
+
+	error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL);
+	if (error)
+		goto out_put_request;
+
+	rq->cmd[0] = INQUIRY;
+	rq->cmd[1] = 1;
+	rq->cmd[2] = 0x83;
+	rq->cmd[3] = bufflen >> 8;
+	rq->cmd[4] = bufflen & 0xff;
+	rq->cmd_len = COMMAND_SIZE(INQUIRY);
+
+	error = blk_execute_rq(rq->q, NULL, rq, 1);
+	if (error) {
+		pr_err("pNFS: INQUIRY 0x83 failed with: %x\n",
+			rq->errors);
+		goto out_put_request;
+	}
+
+	len = (buf[2] << 8) + buf[3] + 4;
+	if (len > bufflen) {
+		pr_err("pNFS: INQUIRY 0x83 response invalid (len = %zd)\n",
+			len);
+		goto out_put_request;
+	}
+
+	d = buf + 4;
+	for (d = buf + 4; d < buf + len; d += id_len + 4) {
+		id_len = d[3];
+		type = d[1] & 0xf;
+		assoc = (d[1] >> 4) & 0x3;
+
+		/*
+		 * We only care about a EUI-64 and NAA designator types
+		 * with LU association.
+		 */
+		if (assoc != 0x00)
+			continue;
+		if (type != 0x02 && type != 0x03)
+			continue;
+		if (id_len != 8 && id_len != 12 && id_len != 16)
+			continue;
+
+		b->scsi.code_set = PS_CODE_SET_BINARY;
+		b->scsi.designator_type = type == 0x02 ?
+			PS_DESIGNATOR_EUI64 : PS_DESIGNATOR_NAA;
+		b->scsi.designator_len = id_len;
+		memcpy(b->scsi.designator, d + 4, id_len);
+
+		/*
+		 * If we found a 8 or 12 byte descriptor continue on to
+		 * see if a 16 byte one is available.  If we find a
+		 * 16 byte descriptor we're done.
+		 */
+		if (id_len == 16)
+			break;
+	}
+
+out_put_request:
+	blk_put_request(rq);
+out_free_buf:
+	kfree(buf);
+	return error;
+}
+
+#define NFSD_MDS_PR_KEY		0x0100000000000000
+
+/*
+ * We use the client ID as a unique key for the reservations.
+ * This allows us to easily fence a client when recalls fail.
+ */
+static u64 nfsd4_scsi_pr_key(struct nfs4_client *clp)
+{
+	return ((u64)clp->cl_clientid.cl_boot << 32) | clp->cl_clientid.cl_id;
+}
+
+static int
+nfsd4_block_get_device_info_scsi(struct super_block *sb,
+		struct nfs4_client *clp,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev;
+	struct pnfs_block_volume *b;
+	const struct pr_ops *ops;
+	int error;
+
+	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_SCSI;
+	b->scsi.pr_key = nfsd4_scsi_pr_key(clp);
+
+	error = nfsd4_scsi_identify_device(sb->s_bdev, b);
+	if (error)
+		return error;
+
+	ops = sb->s_bdev->bd_disk->fops->pr_ops;
+	if (!ops) {
+		pr_err("pNFS: device %s does not support PRs.\n",
+			sb->s_id);
+		return -EINVAL;
+	}
+
+	error = ops->pr_register(sb->s_bdev, 0, NFSD_MDS_PR_KEY, true);
+	if (error) {
+		pr_err("pNFS: failed to register key for device %s.\n",
+			sb->s_id);
+		return -EINVAL;
+	}
+
+	error = ops->pr_reserve(sb->s_bdev, NFSD_MDS_PR_KEY,
+			PR_EXCLUSIVE_ACCESS_REG_ONLY, 0);
+	if (error) {
+		pr_err("pNFS: failed to reserve device %s.\n",
+			sb->s_id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static __be32
+nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
+		struct nfs4_client *clp,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	if (sb->s_bdev != sb->s_bdev->bd_contains)
+		return nfserr_inval;
+	return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp));
+}
+static __be32
+nfsd4_scsi_proc_layoutcommit(struct inode *inode,
+		struct nfsd4_layoutcommit *lcp)
+{
+	struct iomap *iomaps;
+	int nr_iomaps;
+
+	nr_iomaps = nfsd4_scsi_decode_layoutupdate(lcp->lc_up_layout,
+			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+	if (nr_iomaps < 0)
+		return nfserrno(nr_iomaps);
+
+	return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps);
+}
+
+static void
+nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls)
+{
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	struct block_device *bdev = ls->ls_file->f_path.mnt->mnt_sb->s_bdev;
+
+	bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY,
+			nfsd4_scsi_pr_key(clp), 0, true);
+}
+
+const struct nfsd4_layout_ops scsi_layout_ops = {
+	/*
+	 * Pretend that we send notification to the client.  This is a blatant
+	 * lie to force recent Linux clients to cache our device IDs.
+	 * We rarely ever change the device ID, so the harm of leaking deviceids
+	 * for a while isn't too bad.  Unfortunately RFC5661 is a complete mess
+	 * in this regard, but I filed errata 4119 for this a while ago, and
+	 * hopefully the Linux client will eventually start caching deviceids
+	 * without this again.
+	 */
+	.notify_types		=
+			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
+	.proc_getdeviceinfo	= nfsd4_scsi_proc_getdeviceinfo,
+	.encode_getdeviceinfo	= nfsd4_block_encode_getdeviceinfo,
+	.proc_layoutget		= nfsd4_block_proc_layoutget,
+	.encode_layoutget	= nfsd4_block_encode_layoutget,
+	.proc_layoutcommit	= nfsd4_scsi_proc_layoutcommit,
+	.fence_client		= nfsd4_scsi_fence_client,
+};
+#endif /* CONFIG_NFSD_SCSILAYOUT */
diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c
index 6d834dc9bbc8..6c3b316f932e 100644
--- a/fs/nfsd/blocklayoutxdr.c
+++ b/fs/nfsd/blocklayoutxdr.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2014 Christoph Hellwig.
+ * Copyright (c) 2014-2016 Christoph Hellwig.
  */
 #include <linux/sunrpc/svc.h>
 #include <linux/exportfs.h>
@@ -53,6 +53,18 @@ nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 		p = xdr_encode_hyper(p, b->simple.offset);
 		p = xdr_encode_opaque(p, b->simple.sig, b->simple.sig_len);
 		break;
+	case PNFS_BLOCK_VOLUME_SCSI:
+		len = 4 + 4 + 4 + 4 + b->scsi.designator_len + 8;
+		p = xdr_reserve_space(xdr, len);
+		if (!p)
+			return -ETOOSMALL;
+
+		*p++ = cpu_to_be32(b->type);
+		*p++ = cpu_to_be32(b->scsi.code_set);
+		*p++ = cpu_to_be32(b->scsi.designator_type);
+		p = xdr_encode_opaque(p, b->scsi.designator, b->scsi.designator_len);
+		p = xdr_encode_hyper(p, b->scsi.pr_key);
+		break;
 	default:
 		return -ENOTSUPP;
 	}
@@ -93,18 +105,22 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
 		u32 block_size)
 {
 	struct iomap *iomaps;
-	u32 nr_iomaps, expected, i;
+	u32 nr_iomaps, i;
 
 	if (len < sizeof(u32)) {
 		dprintk("%s: extent array too small: %u\n", __func__, len);
 		return -EINVAL;
 	}
+	len -= sizeof(u32);
+	if (len % PNFS_BLOCK_EXTENT_SIZE) {
+		dprintk("%s: extent array invalid: %u\n", __func__, len);
+		return -EINVAL;
+	}
 
 	nr_iomaps = be32_to_cpup(p++);
-	expected = sizeof(__be32) + nr_iomaps * PNFS_BLOCK_EXTENT_SIZE;
-	if (len != expected) {
+	if (nr_iomaps != len / PNFS_BLOCK_EXTENT_SIZE) {
 		dprintk("%s: extent array size mismatch: %u/%u\n",
-			__func__, len, expected);
+			__func__, len, nr_iomaps);
 		return -EINVAL;
 	}
 
@@ -155,3 +171,54 @@ fail:
 	kfree(iomaps);
 	return -EINVAL;
 }
+
+int
+nfsd4_scsi_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 * PNFS_SCSI_RANGE_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++) {
+		u64 val;
+
+		p = xdr_decode_hyper(p, &val);
+		if (val & (block_size - 1)) {
+			dprintk("%s: unaligned offset 0x%llx\n", __func__, val);
+			goto fail;
+		}
+		iomaps[i].offset = val;
+
+		p = xdr_decode_hyper(p, &val);
+		if (val & (block_size - 1)) {
+			dprintk("%s: unaligned length 0x%llx\n", __func__, val);
+			goto fail;
+		}
+		iomaps[i].length = val;
+	}
+
+	*iomapp = iomaps;
+	return nr_iomaps;
+fail:
+	kfree(iomaps);
+	return -EINVAL;
+}
diff --git a/fs/nfsd/blocklayoutxdr.h b/fs/nfsd/blocklayoutxdr.h
index 6de925fe8499..397bc7563a49 100644
--- a/fs/nfsd/blocklayoutxdr.h
+++ b/fs/nfsd/blocklayoutxdr.h
@@ -15,6 +15,11 @@ struct pnfs_block_extent {
 	enum pnfs_block_extent_state	es;
 };
 
+struct pnfs_block_range {
+	u64				foff;
+	u64				len;
+};
+
 /*
  * Random upper cap for the uuid length to avoid unbounded allocation.
  * Not actually limited by the protocol.
@@ -29,6 +34,13 @@ struct pnfs_block_volume {
 			u32		sig_len;
 			u8		sig[PNFS_BLOCK_UUID_LEN];
 		} simple;
+		struct {
+			enum scsi_code_set		code_set;
+			enum scsi_designator_type	designator_type;
+			int				designator_len;
+			u8				designator[256];
+			u64				pr_key;
+		} scsi;
 	};
 };
 
@@ -43,5 +55,7 @@ __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);
+int nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+		u32 block_size);
 
 #endif /* _NFSD_BLOCKLAYOUTXDR_H */
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 7b755b7f785c..51c3b06e8036 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -147,6 +147,7 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
 {
 	__be32	nfserr;
 	u32	max_blocksize = svc_max_payload(rqstp);
+	unsigned long cnt = min(argp->count, max_blocksize);
 
 	dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n",
 				SVCFH_fmt(&argp->fh),
@@ -157,7 +158,7 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
 	 * 1 (status) + 22 (post_op_attr) + 1 (count) + 1 (eof)
 	 * + 1 (xdr opaque byte count) = 26
 	 */
-	resp->count = min(argp->count, max_blocksize);
+	resp->count = cnt;
 	svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3)<<2) + resp->count +4);
 
 	fh_copy(&resp->fh, &argp->fh);
@@ -167,8 +168,8 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
 				  &resp->count);
 	if (nfserr == 0) {
 		struct inode	*inode = d_inode(resp->fh.fh_dentry);
-
-		resp->eof = (argp->offset + resp->count) >= inode->i_size;
+		resp->eof = nfsd_eof_on_read(cnt, resp->count, argp->offset,
+							inode->i_size);
 	}
 
 	RETURN_STATUS(nfserr);
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index ce2d010d3b17..825c7bc8d789 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -1,6 +1,7 @@
 /*
  * Copyright (c) 2014 Christoph Hellwig.
  */
+#include <linux/blkdev.h>
 #include <linux/kmod.h>
 #include <linux/file.h>
 #include <linux/jhash.h>
@@ -26,7 +27,12 @@ static const 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] =  {
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
 	[LAYOUT_BLOCK_VOLUME]	= &bl_layout_ops,
+#endif
+#ifdef CONFIG_NFSD_SCSILAYOUT
+	[LAYOUT_SCSI]		= &scsi_layout_ops,
+#endif
 };
 
 /* pNFS device ID to export fsid mapping */
@@ -121,10 +127,24 @@ void nfsd4_setup_layout_type(struct svc_export *exp)
 	if (!(exp->ex_flags & NFSEXP_PNFS))
 		return;
 
+	/*
+	 * Check if the file system supports exporting a block-like layout.
+	 * If the block device supports reservations prefer the SCSI layout,
+	 * otherwise advertise the block layout.
+	 */
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
 	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;
+#endif
+#ifdef CONFIG_NFSD_SCSILAYOUT
+	/* overwrite block layout selection if needed */
+	if (sb->s_export_op->map_blocks &&
+	    sb->s_export_op->commit_blocks &&
+	    sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops)
+		exp->ex_layout_type = LAYOUT_SCSI;
+#endif
 }
 
 static void
@@ -590,8 +610,6 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
 
 	rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str));
 
-	trace_layout_recall_fail(&ls->ls_stid.sc_stateid);
-
 	printk(KERN_WARNING
 		"nfsd: client %s failed to respond to layout recall. "
 		"  Fencing..\n", addr_str);
@@ -626,6 +644,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 		container_of(cb, struct nfs4_layout_stateid, ls_recall);
 	struct nfsd_net *nn;
 	ktime_t now, cutoff;
+	const struct nfsd4_layout_ops *ops;
 	LIST_HEAD(reaplist);
 
 
@@ -661,7 +680,13 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 		/*
 		 * Unknown error or non-responding client, we'll need to fence.
 		 */
-		nfsd4_cb_layout_fail(ls);
+		trace_layout_recall_fail(&ls->ls_stid.sc_stateid);
+
+		ops = nfsd4_layout_ops[ls->ls_layout_type];
+		if (ops->fence_client)
+			ops->fence_client(ls);
+		else
+			nfsd4_cb_layout_fail(ls);
 		return -1;
 	}
 }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 4cba7865f496..de1ff1d98bb1 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -864,12 +864,10 @@ static __be32
 nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	      struct nfsd4_secinfo *secinfo)
 {
-	struct svc_fh resfh;
 	struct svc_export *exp;
 	struct dentry *dentry;
 	__be32 err;
 
-	fh_init(&resfh, NFS4_FHSIZE);
 	err = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, NFSD_MAY_EXEC);
 	if (err)
 		return err;
@@ -878,6 +876,7 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 				    &exp, &dentry);
 	if (err)
 		return err;
+	fh_unlock(&cstate->current_fh);
 	if (d_really_is_negative(dentry)) {
 		exp_put(exp);
 		err = nfserr_noent;
@@ -1269,8 +1268,10 @@ nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
 		goto out;
 
 	nfserr = nfs_ok;
-	if (gdp->gd_maxcount != 0)
-		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp);
+	if (gdp->gd_maxcount != 0) {
+		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb,
+					cstate->session->se_client, gdp);
+	}
 
 	gdp->gd_notify_types &= ops->notify_types;
 out:
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index dc8ebecf5618..66eaeb1e8c2c 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -32,10 +32,10 @@
 *
 */
 
+#include <crypto/hash.h>
 #include <linux/file.h>
 #include <linux/slab.h>
 #include <linux/namei.h>
-#include <linux/crypto.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/module.h>
@@ -104,29 +104,35 @@ static int
 nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
 {
 	struct xdr_netobj cksum;
-	struct hash_desc desc;
-	struct scatterlist sg;
+	struct crypto_shash *tfm;
 	int status;
 
 	dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
 			clname->len, clname->data);
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-	desc.tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(desc.tfm)) {
-		status = PTR_ERR(desc.tfm);
+	tfm = crypto_alloc_shash("md5", 0, 0);
+	if (IS_ERR(tfm)) {
+		status = PTR_ERR(tfm);
 		goto out_no_tfm;
 	}
 
-	cksum.len = crypto_hash_digestsize(desc.tfm);
+	cksum.len = crypto_shash_digestsize(tfm);
 	cksum.data = kmalloc(cksum.len, GFP_KERNEL);
 	if (cksum.data == NULL) {
 		status = -ENOMEM;
  		goto out;
 	}
 
-	sg_init_one(&sg, clname->data, clname->len);
+	{
+		SHASH_DESC_ON_STACK(desc, tfm);
+
+		desc->tfm = tfm;
+		desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+		status = crypto_shash_digest(desc, clname->data, clname->len,
+					     cksum.data);
+		shash_desc_zero(desc);
+	}
 
-	status = crypto_hash_digest(&desc, &sg, sg.length, cksum.data);
 	if (status)
 		goto out;
 
@@ -135,7 +141,7 @@ nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
 	status = 0;
 out:
 	kfree(cksum.data);
-	crypto_free_hash(desc.tfm);
+	crypto_free_shash(tfm);
 out_no_tfm:
 	return status;
 }
@@ -1260,6 +1266,7 @@ nfsd4_umh_cltrack_init(struct net *net)
 	/* XXX: The usermode helper s not working in container yet. */
 	if (net != &init_net) {
 		pr_warn("NFSD: attempt to initialize umh client tracking in a container ignored.\n");
+		kfree(grace_start);
 		return -EINVAL;
 	}
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c484a2b6cd10..0462eeddfff9 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2408,7 +2408,8 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 	default:				/* checked by xdr code */
 		WARN_ON_ONCE(1);
 	case SP4_SSV:
-		return nfserr_encr_alg_unsupp;
+		status = nfserr_encr_alg_unsupp;
+		goto out_nolock;
 	}
 
 	/* Cases below refer to rfc 5661 section 18.35.4: */
@@ -2586,21 +2587,26 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs
 	return nfs_ok;
 }
 
+/*
+ * Server's NFSv4.1 backchannel support is AUTH_SYS-only for now.
+ * These are based on similar macros in linux/sunrpc/msg_prot.h .
+ */
+#define RPC_MAX_HEADER_WITH_AUTH_SYS \
+	(RPC_CALLHDRSIZE + 2 * (2 + UNX_CALLSLACK))
+
+#define RPC_MAX_REPHEADER_WITH_AUTH_SYS \
+	(RPC_REPHDRSIZE + (2 + NUL_REPLYSLACK))
+
 #define NFSD_CB_MAX_REQ_SZ	((NFS4_enc_cb_recall_sz + \
-				 RPC_MAX_HEADER_WITH_AUTH) * sizeof(__be32))
+				 RPC_MAX_HEADER_WITH_AUTH_SYS) * sizeof(__be32))
 #define NFSD_CB_MAX_RESP_SZ	((NFS4_dec_cb_recall_sz + \
-				 RPC_MAX_REPHEADER_WITH_AUTH) * sizeof(__be32))
+				 RPC_MAX_REPHEADER_WITH_AUTH_SYS) * \
+				 sizeof(__be32))
 
 static __be32 check_backchannel_attrs(struct nfsd4_channel_attrs *ca)
 {
 	ca->headerpadsz = 0;
 
-	/*
-	 * These RPC_MAX_HEADER macros are overkill, especially since we
-	 * don't even do gss on the backchannel yet.  But this is still
-	 * less than 1k.  Tighten up this estimate in the unlikely event
-	 * it turns out to be a problem for some client:
-	 */
 	if (ca->maxreq_sz < NFSD_CB_MAX_REQ_SZ)
 		return nfserr_toosmall;
 	if (ca->maxresp_sz < NFSD_CB_MAX_RESP_SZ)
@@ -2710,10 +2716,9 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 		goto out_free_conn;
 	}
 	status = nfs_ok;
-	/*
-	 * We do not support RDMA or persistent sessions
-	 */
+	/* Persistent sessions are not supported */
 	cr_ses->flags &= ~SESSION4_PERSIST;
+	/* Upshifting from TCP to RDMA is not supported */
 	cr_ses->flags &= ~SESSION4_RDMA;
 
 	init_session(rqstp, new, conf, cr_ses);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index d6ef0955a979..9df898ba648f 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1072,8 +1072,9 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename
 
 	READ_BUF(4);
 	rename->rn_snamelen = be32_to_cpup(p++);
-	READ_BUF(rename->rn_snamelen + 4);
+	READ_BUF(rename->rn_snamelen);
 	SAVEMEM(rename->rn_sname, rename->rn_snamelen);
+	READ_BUF(4);
 	rename->rn_tnamelen = be32_to_cpup(p++);
 	READ_BUF(rename->rn_tnamelen);
 	SAVEMEM(rename->rn_tname, rename->rn_tnamelen);
@@ -1155,13 +1156,14 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient
 	READ_BUF(8);
 	setclientid->se_callback_prog = be32_to_cpup(p++);
 	setclientid->se_callback_netid_len = be32_to_cpup(p++);
-
-	READ_BUF(setclientid->se_callback_netid_len + 4);
+	READ_BUF(setclientid->se_callback_netid_len);
 	SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len);
+	READ_BUF(4);
 	setclientid->se_callback_addr_len = be32_to_cpup(p++);
 
-	READ_BUF(setclientid->se_callback_addr_len + 4);
+	READ_BUF(setclientid->se_callback_addr_len);
 	SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len);
+	READ_BUF(4);
 	setclientid->se_callback_ident = be32_to_cpup(p++);
 
 	DECODE_TAIL;
@@ -1835,8 +1837,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 
 	READ_BUF(4);
 	argp->taglen = be32_to_cpup(p++);
-	READ_BUF(argp->taglen + 8);
+	READ_BUF(argp->taglen);
 	SAVEMEM(argp->tag, argp->taglen);
+	READ_BUF(8);
 	argp->minorversion = be32_to_cpup(p++);
 	argp->opcnt = be32_to_cpup(p++);
 	max_reply += 4 + (XDR_QUADLEN(argp->taglen) << 2);
@@ -3060,7 +3063,7 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp,
 		p = xdr_encode_opaque_fixed(p, bcts->sessionid.data,
 						NFS4_MAX_SESSIONID_LEN);
 		*p++ = cpu_to_be32(bcts->dir);
-		/* Sorry, we do not yet support RDMA over 4.1: */
+		/* Upshifting from TCP to RDMA is not supported */
 		*p++ = cpu_to_be32(0);
 	}
 	return nfserr;
@@ -3362,6 +3365,7 @@ static __be32 nfsd4_encode_splice_read(
 	struct xdr_stream *xdr = &resp->xdr;
 	struct xdr_buf *buf = xdr->buf;
 	u32 eof;
+	long len;
 	int space_left;
 	__be32 nfserr;
 	__be32 *p = xdr->p - 2;
@@ -3370,6 +3374,7 @@ static __be32 nfsd4_encode_splice_read(
 	if (xdr->end - xdr->p < 1)
 		return nfserr_resource;
 
+	len = maxcount;
 	nfserr = nfsd_splice_read(read->rd_rqstp, file,
 				  read->rd_offset, &maxcount);
 	if (nfserr) {
@@ -3382,8 +3387,8 @@ static __be32 nfsd4_encode_splice_read(
 		return nfserr;
 	}
 
-	eof = (read->rd_offset + maxcount >=
-	       d_inode(read->rd_fhp->fh_dentry)->i_size);
+	eof = nfsd_eof_on_read(len, maxcount, read->rd_offset,
+				d_inode(read->rd_fhp->fh_dentry)->i_size);
 
 	*(p++) = htonl(eof);
 	*(p++) = htonl(maxcount);
@@ -3453,14 +3458,15 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 	}
 	read->rd_vlen = v;
 
+	len = maxcount;
 	nfserr = nfsd_readv(file, read->rd_offset, resp->rqstp->rq_vec,
 			read->rd_vlen, &maxcount);
 	if (nfserr)
 		return nfserr;
 	xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3));
 
-	eof = (read->rd_offset + maxcount >=
-	       d_inode(read->rd_fhp->fh_dentry)->i_size);
+	eof = nfsd_eof_on_read(len, maxcount, read->rd_offset,
+				d_inode(read->rd_fhp->fh_dentry)->i_size);
 
 	tmp = htonl(eof);
 	write_bytes_to_xdr_buf(xdr->buf, starting_len    , &tmp, 4);
diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
index d4c4453674c6..7d073b9b1553 100644
--- a/fs/nfsd/pnfs.h
+++ b/fs/nfsd/pnfs.h
@@ -21,6 +21,7 @@ struct nfsd4_layout_ops {
 	u32		notify_types;
 
 	__be32 (*proc_getdeviceinfo)(struct super_block *sb,
+			struct nfs4_client *clp,
 			struct nfsd4_getdeviceinfo *gdevp);
 	__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
 			struct nfsd4_getdeviceinfo *gdevp);
@@ -32,10 +33,17 @@ struct nfsd4_layout_ops {
 
 	__be32 (*proc_layoutcommit)(struct inode *inode,
 			struct nfsd4_layoutcommit *lcp);
+
+	void (*fence_client)(struct nfs4_layout_stateid *ls);
 };
 
 extern const struct nfsd4_layout_ops *nfsd4_layout_ops[];
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
 extern const struct nfsd4_layout_ops bl_layout_ops;
+#endif
+#ifdef CONFIG_NFSD_SCSILAYOUT
+extern const struct nfsd4_layout_ops scsi_layout_ops;
+#endif
 
 __be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, stateid_t *stateid,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 5d2a57e4c03a..d40010e4f1a9 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -870,7 +870,7 @@ __be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen,
 
 	oldfs = get_fs();
 	set_fs(KERNEL_DS);
-	host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
+	host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset, 0);
 	set_fs(oldfs);
 	return nfsd_finish_read(file, count, host_err);
 }
@@ -957,7 +957,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 
 	/* Write the data. */
 	oldfs = get_fs(); set_fs(KERNEL_DS);
-	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos);
+	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, 0);
 	set_fs(oldfs);
 	if (host_err < 0)
 		goto out_nfserr;
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index c11ba316f23f..2d573ec057f8 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -139,4 +139,23 @@ static inline int nfsd_create_is_exclusive(int createmode)
 	       || createmode == NFS4_CREATE_EXCLUSIVE4_1;
 }
 
+static inline bool nfsd_eof_on_read(long requested, long read,
+				loff_t offset, loff_t size)
+{
+	/* We assume a short read means eof: */
+	if (requested > read)
+		return true;
+	/*
+	 * A non-short read might also reach end of file.  The spec
+	 * still requires us to set eof in that case.
+	 *
+	 * Further operations may have modified the file size since
+	 * the read, so the following check is not atomic with the read.
+	 * We've only seen that cause a problem for a client in the case
+	 * where the read returned a count of 0 without setting eof.
+	 * That case was fixed by the addition of the above check.
+	 */
+	return (offset + read >= size);
+}
+
 #endif /* LINUX_NFSD_VFS_H */
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 45d650addd56..c20df77eff99 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -180,7 +180,7 @@ void nilfs_page_bug(struct page *page)
 
 	printk(KERN_CRIT "NILFS_PAGE_BUG(%p): cnt=%d index#=%llu flags=0x%lx "
 	       "mapping=%p ino=%lu\n",
-	       page, atomic_read(&page->_count),
+	       page, page_ref_count(page),
 	       (unsigned long long)page->index, page->flags, m, ino);
 
 	if (page_has_buffers(page)) {
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index cfcbf114676e..7115c5d7d373 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -91,7 +91,14 @@
 #include <linux/fsnotify_backend.h>
 #include "fsnotify.h"
 
+#define FSNOTIFY_REAPER_DELAY	(1)	/* 1 jiffy */
+
 struct srcu_struct fsnotify_mark_srcu;
+static DEFINE_SPINLOCK(destroy_lock);
+static LIST_HEAD(destroy_list);
+
+static void fsnotify_mark_destroy(struct work_struct *work);
+static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy);
 
 void fsnotify_get_mark(struct fsnotify_mark *mark)
 {
@@ -165,19 +172,10 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark)
 	atomic_dec(&group->num_marks);
 }
 
-static void
-fsnotify_mark_free_rcu(struct rcu_head *rcu)
-{
-	struct fsnotify_mark	*mark;
-
-	mark = container_of(rcu, struct fsnotify_mark, g_rcu);
-	fsnotify_put_mark(mark);
-}
-
 /*
- * Free fsnotify mark. The freeing is actually happening from a call_srcu
- * callback. Caller must have a reference to the mark or be protected by
- * fsnotify_mark_srcu.
+ * Free fsnotify mark. The freeing is actually happening from a kthread which
+ * first waits for srcu period end. Caller must have a reference to the mark
+ * or be protected by fsnotify_mark_srcu.
  */
 void fsnotify_free_mark(struct fsnotify_mark *mark)
 {
@@ -192,7 +190,11 @@ void fsnotify_free_mark(struct fsnotify_mark *mark)
 	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
 	spin_unlock(&mark->lock);
 
-	call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu);
+	spin_lock(&destroy_lock);
+	list_add(&mark->g_list, &destroy_list);
+	spin_unlock(&destroy_lock);
+	queue_delayed_work(system_unbound_wq, &reaper_work,
+				FSNOTIFY_REAPER_DELAY);
 
 	/*
 	 * Some groups like to know that marks are being freed.  This is a
@@ -388,7 +390,12 @@ err:
 
 	spin_unlock(&mark->lock);
 
-	call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu);
+	spin_lock(&destroy_lock);
+	list_add(&mark->g_list, &destroy_list);
+	spin_unlock(&destroy_lock);
+	queue_delayed_work(system_unbound_wq, &reaper_work,
+				FSNOTIFY_REAPER_DELAY);
+
 	return ret;
 }
 
@@ -491,3 +498,21 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
 	atomic_set(&mark->refcnt, 1);
 	mark->free_mark = free_mark;
 }
+
+static void fsnotify_mark_destroy(struct work_struct *work)
+{
+	struct fsnotify_mark *mark, *next;
+	struct list_head private_destroy_list;
+
+	spin_lock(&destroy_lock);
+	/* exchange the list head */
+	list_replace_init(&destroy_list, &private_destroy_list);
+	spin_unlock(&destroy_lock);
+
+	synchronize_srcu(&fsnotify_mark_srcu);
+
+	list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
+		list_del_init(&mark->g_list);
+		fsnotify_put_mark(mark);
+	}
+}
diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index ce210d4951a1..e27e6527912b 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -41,7 +41,8 @@ ocfs2-objs := \
 	quota_local.o		\
 	quota_global.o		\
 	xattr.o			\
-	acl.o
+	acl.o	\
+	filecheck.o
 
 ocfs2_stackglue-objs := stackglue.o
 ocfs2_stack_o2cb-objs := stack_o2cb.o
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index d002579c6f2b..70907d638b60 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -2516,21 +2516,6 @@ static int ocfs2_update_edge_lengths(handle_t *handle,
 	struct ocfs2_extent_block *eb;
 	u32 range;
 
-	/*
-	 * In normal tree rotation process, we will never touch the
-	 * tree branch above subtree_index and ocfs2_extend_rotate_transaction
-	 * doesn't reserve the credits for them either.
-	 *
-	 * But we do have a special case here which will update the rightmost
-	 * records for all the bh in the path.
-	 * So we have to allocate extra credits and access them.
-	 */
-	ret = ocfs2_extend_trans(handle, subtree_index);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
-
 	ret = ocfs2_journal_access_path(et->et_ci, handle, path);
 	if (ret) {
 		mlog_errno(ret);
@@ -2956,7 +2941,7 @@ static int __ocfs2_rotate_tree_left(handle_t *handle,
 		     right_path->p_node[subtree_root].bh->b_blocknr,
 		     right_path->p_tree_depth);
 
-		ret = ocfs2_extend_rotate_transaction(handle, subtree_root,
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
 						      orig_credits, left_path);
 		if (ret) {
 			mlog_errno(ret);
@@ -3029,21 +3014,9 @@ static int ocfs2_remove_rightmost_path(handle_t *handle,
 	struct ocfs2_extent_block *eb;
 	struct ocfs2_extent_list *el;
 
-
 	ret = ocfs2_et_sanity_check(et);
 	if (ret)
 		goto out;
-	/*
-	 * There's two ways we handle this depending on
-	 * whether path is the only existing one.
-	 */
-	ret = ocfs2_extend_rotate_transaction(handle, 0,
-					      handle->h_buffer_credits,
-					      path);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
 
 	ret = ocfs2_journal_access_path(et->et_ci, handle, path);
 	if (ret) {
@@ -3641,6 +3614,14 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path,
 		 */
 		if (le16_to_cpu(right_rec->e_leaf_clusters) == 0 &&
 		    le16_to_cpu(el->l_next_free_rec) == 1) {
+			/* extend credit for ocfs2_remove_rightmost_path */
+			ret = ocfs2_extend_rotate_transaction(handle, 0,
+					handle->h_buffer_credits,
+					right_path);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
 
 			ret = ocfs2_remove_rightmost_path(handle, et,
 							  right_path,
@@ -3679,6 +3660,14 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 	BUG_ON(ctxt->c_contig_type == CONTIG_NONE);
 
 	if (ctxt->c_split_covers_rec && ctxt->c_has_empty_extent) {
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+				handle->h_buffer_credits,
+				path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
 		/*
 		 * The merge code will need to create an empty
 		 * extent to take the place of the newly
@@ -3727,6 +3716,15 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 		 */
 		BUG_ON(!ocfs2_is_empty_extent(&el->l_recs[0]));
 
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+					handle->h_buffer_credits,
+					path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		/* The merge left us with an empty extent, remove it. */
 		ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
 		if (ret) {
@@ -3748,6 +3746,15 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 			goto out;
 		}
 
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+				handle->h_buffer_credits,
+				path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
 		/*
 		 * Error from this last rotate is not critical, so
@@ -3783,6 +3790,16 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 		}
 
 		if (ctxt->c_split_covers_rec) {
+			/* extend credit for ocfs2_remove_rightmost_path */
+			ret = ocfs2_extend_rotate_transaction(handle, 0,
+					handle->h_buffer_credits,
+					path);
+			if (ret) {
+				mlog_errno(ret);
+				ret = 0;
+				goto out;
+			}
+
 			/*
 			 * The merge may have left an empty extent in
 			 * our leaf. Try to rotate it away.
@@ -5342,6 +5359,15 @@ static int ocfs2_truncate_rec(handle_t *handle,
 	struct ocfs2_extent_block *eb;
 
 	if (ocfs2_is_empty_extent(&el->l_recs[0]) && index > 0) {
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+				handle->h_buffer_credits,
+				path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
 		if (ret) {
 			mlog_errno(ret);
@@ -5928,16 +5954,6 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 
 		ocfs2_journal_dirty(handle, tl_bh);
 
-		/* TODO: Perhaps we can calculate the bulk of the
-		 * credits up front rather than extending like
-		 * this. */
-		status = ocfs2_extend_trans(handle,
-					    OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
-		if (status < 0) {
-			mlog_errno(status);
-			goto bail;
-		}
-
 		rec = tl->tl_recs[i];
 		start_blk = ocfs2_clusters_to_blocks(data_alloc_inode->i_sb,
 						    le32_to_cpu(rec.t_start));
@@ -5958,6 +5974,13 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 				goto bail;
 			}
 		}
+
+		status = ocfs2_extend_trans(handle,
+				OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
 		i--;
 	}
 
@@ -6016,7 +6039,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 		goto out_mutex;
 	}
 
-	handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_UPDATE);
+	handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		mlog_errno(status);
@@ -6079,7 +6102,7 @@ void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
 		if (cancel)
 			cancel_delayed_work(&osb->osb_truncate_log_wq);
 
-		queue_delayed_work(ocfs2_wq, &osb->osb_truncate_log_wq,
+		queue_delayed_work(osb->ocfs2_wq, &osb->osb_truncate_log_wq,
 				   OCFS2_TRUNCATE_LOG_FLUSH_INTERVAL);
 	}
 }
@@ -6253,7 +6276,7 @@ void ocfs2_truncate_log_shutdown(struct ocfs2_super *osb)
 
 	if (tl_inode) {
 		cancel_delayed_work(&osb->osb_truncate_log_wq);
-		flush_workqueue(ocfs2_wq);
+		flush_workqueue(osb->ocfs2_wq);
 
 		status = ocfs2_flush_truncate_log(osb);
 		if (status < 0)
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 794fd1587f34..1581240a7ca0 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -499,153 +499,6 @@ bail:
 	return status;
 }
 
-/*
- * TODO: Make this into a generic get_blocks function.
- *
- * From do_direct_io in direct-io.c:
- *  "So what we do is to permit the ->get_blocks function to populate
- *   bh.b_size with the size of IO which is permitted at this offset and
- *   this i_blkbits."
- *
- * This function is called directly from get_more_blocks in direct-io.c.
- *
- * called like this: dio->get_blocks(dio->inode, fs_startblk,
- * 					fs_count, map_bh, dio->rw == WRITE);
- */
-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, contig_clusters = 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
-	 * for us to check any of that. */
-
-	inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
-
-	down_read(&OCFS2_I(inode)->ip_alloc_sem);
-
-	/* This figures out the size of the next contiguous block, and
-	 * our logical offset */
-	ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
-					  &contig_blocks, &ext_flags);
-	up_read(&OCFS2_I(inode)->ip_alloc_sem);
-
-	if (ret) {
-		mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
-		     (unsigned long long)iblock);
-		ret = -EIO;
-		goto bail;
-	}
-
-	/* 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;
-
-		down_write(&OCFS2_I(inode)->ip_alloc_sem);
-
-		/* 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);
-		contig_clusters = ocfs2_clusters_for_blocks(inode->i_sb,
-				contig_blocks);
-		if (clusters_to_alloc > contig_clusters)
-			clusters_to_alloc = contig_clusters;
-
-		/* allocate extent and insert them into the extent tree */
-		ret = ocfs2_extend_allocation(inode, cpos,
-				clusters_to_alloc, 0);
-		if (ret < 0) {
-			up_write(&OCFS2_I(inode)->ip_alloc_sem);
-			mlog_errno(ret);
-			goto bail;
-		}
-
-		ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
-				&contig_blocks, &ext_flags);
-		if (ret < 0) {
-			up_write(&OCFS2_I(inode)->ip_alloc_sem);
-			mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
-					(unsigned long long)iblock);
-			ret = -EIO;
-			goto bail;
-		}
-		set_buffer_new(bh_result);
-		up_write(&OCFS2_I(inode)->ip_alloc_sem);
-	}
-
-	/*
-	 * get_more_blocks() expects us to describe a hole by clearing
-	 * the mapped bit on bh_result().
-	 *
-	 * Consider an unwritten extent as a hole.
-	 */
-	if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
-		map_bh(bh_result, inode->i_sb, p_blkno);
-	else
-		clear_buffer_mapped(bh_result);
-
-	/* make sure we don't map more than max_blocks blocks here as
-	   that's all the kernel will handle at this point. */
-	if (max_blocks < contig_blocks)
-		contig_blocks = max_blocks;
-	bh_result->b_size = contig_blocks << blocksize_bits;
-bail:
-	if (alloc_locked)
-		ocfs2_inode_unlock(inode, 1);
-	return ret;
-}
-
-/*
- * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
- * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
- * to protect io on one node from truncation on another.
- */
-static void ocfs2_dio_end_io(struct kiocb *iocb,
-			     loff_t offset,
-			     ssize_t bytes,
-			     void *private)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	int level;
-
-	/* this io's submitter should not have unlocked this before we could */
-	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
-
-	if (ocfs2_iocb_is_unaligned_aio(iocb)) {
-		ocfs2_iocb_clear_unaligned_aio(iocb);
-
-		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
-	}
-
-	/* Let rw unlock to be done later to protect append direct io write */
-	if (offset + bytes <= i_size_read(inode)) {
-		ocfs2_iocb_clear_rw_locked(iocb);
-
-		level = ocfs2_iocb_rw_locked_level(iocb);
-		ocfs2_rw_unlock(inode, level);
-	}
-}
-
 static int ocfs2_releasepage(struct page *page, gfp_t wait)
 {
 	if (!page_has_buffers(page))
@@ -653,362 +506,6 @@ 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 int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb,
-		struct inode *inode, loff_t offset,
-		u64 zero_len, int cluster_align)
-{
-	u32 p_cpos = 0;
-	u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
-	unsigned int num_clusters = 0;
-	unsigned int ext_flags = 0;
-	int ret = 0;
-
-	if (offset <= i_size_read(inode) || cluster_align)
-		return 0;
-
-	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)) {
-		u64 s = i_size_read(inode);
-		sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) +
-			(do_div(s, osb->s_clustersize) >> 9);
-
-		ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector,
-				zero_len >> 9, GFP_NOFS, false);
-		if (ret < 0)
-			mlog_errno(ret);
-	}
-
-	return ret;
-}
-
-static int ocfs2_direct_IO_extend_no_holes(struct ocfs2_super *osb,
-		struct inode *inode, loff_t offset)
-{
-	u64 zero_start, zero_len, total_zero_len;
-	u32 p_cpos = 0, clusters_to_add;
-	u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
-	unsigned int num_clusters = 0;
-	unsigned int ext_flags = 0;
-	u32 size_div, offset_div;
-	int ret = 0;
-
-	{
-		u64 o = offset;
-		u64 s = i_size_read(inode);
-
-		offset_div = do_div(o, osb->s_clustersize);
-		size_div = do_div(s, osb->s_clustersize);
-	}
-
-	if (offset <= i_size_read(inode))
-		return 0;
-
-	clusters_to_add = ocfs2_bytes_to_clusters(inode->i_sb, offset) -
-		ocfs2_bytes_to_clusters(inode->i_sb, i_size_read(inode));
-	total_zero_len = offset - i_size_read(inode);
-	if (clusters_to_add)
-		total_zero_len -= offset_div;
-
-	/* Allocate clusters to fill out holes, and this is only needed
-	 * when we add more than one clusters. Otherwise the cluster will
-	 * be allocated during direct IO */
-	if (clusters_to_add > 1) {
-		ret = ocfs2_extend_allocation(inode,
-				OCFS2_I(inode)->ip_clusters,
-				clusters_to_add - 1, 0);
-		if (ret) {
-			mlog_errno(ret);
-			goto out;
-		}
-	}
-
-	while (total_zero_len) {
-		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
-				&ext_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-
-		zero_start = ocfs2_clusters_to_bytes(osb->sb, p_cpos) +
-			size_div;
-		zero_len = ocfs2_clusters_to_bytes(osb->sb, num_clusters) -
-			size_div;
-		zero_len = min(total_zero_len, zero_len);
-
-		if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
-			ret = blkdev_issue_zeroout(osb->sb->s_bdev,
-					zero_start >> 9, zero_len >> 9,
-					GFP_NOFS, false);
-			if (ret < 0) {
-				mlog_errno(ret);
-				goto out;
-			}
-		}
-
-		total_zero_len -= zero_len;
-		v_cpos += ocfs2_bytes_to_clusters(osb->sb, zero_len + size_div);
-
-		/* Only at first iteration can be cluster not aligned.
-		 * So set size_div to 0 for the rest */
-		size_div = 0;
-	}
-
-out:
-	return ret;
-}
-
-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;
-	u64 zero_len_head, zero_len_tail;
-	int cluster_align_head, cluster_align_tail;
-	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;
-		u64 s = i_size_read(inode);
-
-		zero_len_head = do_div(o, 1 << osb->s_clustersize_bits);
-		cluster_align_head = !zero_len_head;
-
-		zero_len_tail = osb->s_clustersize -
-			do_div(s, osb->s_clustersize);
-		if ((offset - i_size_read(inode)) < zero_len_tail)
-			zero_len_tail = offset - i_size_read(inode);
-		cluster_align_tail = !zero_len_tail;
-	}
-
-	/*
-	 * 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, NULL, 1);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto clean_orphan;
-		}
-
-		/* zeroing out the previously allocated cluster tail
-		 * that but not zeroed */
-		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) {
-			down_read(&OCFS2_I(inode)->ip_alloc_sem);
-			ret = ocfs2_direct_IO_zero_extend(osb, inode, offset,
-					zero_len_tail, cluster_align_tail);
-			up_read(&OCFS2_I(inode)->ip_alloc_sem);
-		} else {
-			down_write(&OCFS2_I(inode)->ip_alloc_sem);
-			ret = ocfs2_direct_IO_extend_no_holes(osb, inode,
-					offset);
-			up_write(&OCFS2_I(inode)->ip_alloc_sem);
-		}
-		if (ret < 0) {
-			mlog_errno(ret);
-			ocfs2_inode_unlock(inode, 1);
-			goto clean_orphan;
-		}
-
-		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
-		if (is_overwrite < 0) {
-			mlog_errno(is_overwrite);
-			ret = is_overwrite;
-			ocfs2_inode_unlock(inode, 1);
-			goto clean_orphan;
-		}
-
-		ocfs2_inode_unlock(inode, 1);
-	}
-
-	written = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
-				       offset, ocfs2_direct_IO_get_blocks,
-				       ocfs2_dio_end_io, NULL, 0);
-	/* overwrite aio may return -EIOCBQUEUED, and it is not an error */
-	if ((written < 0) && (written != -EIOCBQUEUED)) {
-		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);
-					di_bh = NULL;
-					goto clean_orphan;
-				}
-			}
-
-			ocfs2_inode_unlock(inode, 1);
-			brelse(di_bh);
-			di_bh = NULL;
-
-			ret = jbd2_journal_force_commit(journal);
-			if (ret < 0)
-				mlog_errno(ret);
-		}
-	} else if (written > 0 && append_write && !is_overwrite &&
-			!cluster_align_head) {
-		/* zeroing out the allocated cluster head */
-		u32 p_cpos = 0;
-		u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
-
-		ret = ocfs2_inode_lock(inode, NULL, 0);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto clean_orphan;
-		}
-
-		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
-				&num_clusters, &ext_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			ocfs2_inode_unlock(inode, 0);
-			goto clean_orphan;
-		}
-
-		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
-
-		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
-				(u64)p_cpos << (osb->s_clustersize_bits - 9),
-				zero_len_head >> 9, GFP_NOFS, false);
-		if (ret < 0)
-			mlog_errno(ret);
-
-		ocfs2_inode_unlock(inode, 0);
-	}
-
-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_inode_lock(inode, &di_bh, 1);
-		if (tmp_ret < 0) {
-			ret = tmp_ret;
-			mlog_errno(ret);
-			goto out;
-		}
-
-		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
-				update_isize, end);
-		if (tmp_ret < 0) {
-			ret = tmp_ret;
-			mlog_errno(ret);
-			brelse(di_bh);
-			goto out;
-		}
-
-		ocfs2_inode_unlock(inode, 1);
-		brelse(di_bh);
-
-		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(struct kiocb *iocb, struct iov_iter *iter,
-			       loff_t offset)
-{
-	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
-	 * extents.
-	 */
-	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
-		return 0;
-
-	/* 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;
-
-	if (iov_iter_rw(iter) == READ)
-		return __blockdev_direct_IO(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,
 					    u32 cpos,
 					    unsigned int *start,
@@ -1195,6 +692,13 @@ next_bh:
 
 #define OCFS2_MAX_CLUSTERS_PER_PAGE	(PAGE_CACHE_SIZE / OCFS2_MIN_CLUSTERSIZE)
 
+struct ocfs2_unwritten_extent {
+	struct list_head	ue_node;
+	struct list_head	ue_ip_node;
+	u32			ue_cpos;
+	u32			ue_phys;
+};
+
 /*
  * Describe the state of a single cluster to be written to.
  */
@@ -1206,7 +710,7 @@ struct ocfs2_write_cluster_desc {
 	 * filled.
 	 */
 	unsigned	c_new;
-	unsigned	c_unwritten;
+	unsigned	c_clear_unwritten;
 	unsigned	c_needs_zero;
 };
 
@@ -1218,6 +722,9 @@ struct ocfs2_write_ctxt {
 	/* First cluster allocated in a nonsparse extend */
 	u32				w_first_new_cpos;
 
+	/* Type of caller. Must be one of buffer, mmap, direct.  */
+	ocfs2_write_type_t		w_type;
+
 	struct ocfs2_write_cluster_desc	w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE];
 
 	/*
@@ -1266,6 +773,8 @@ struct ocfs2_write_ctxt {
 	struct buffer_head		*w_di_bh;
 
 	struct ocfs2_cached_dealloc_ctxt w_dealloc;
+
+	struct list_head		w_unwritten_list;
 };
 
 void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
@@ -1304,8 +813,25 @@ static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
 }
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_free_unwritten_list(struct inode *inode,
+				 struct list_head *head)
 {
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_unwritten_extent *ue = NULL, *tmp = NULL;
+
+	list_for_each_entry_safe(ue, tmp, head, ue_node) {
+		list_del(&ue->ue_node);
+		spin_lock(&oi->ip_lock);
+		list_del(&ue->ue_ip_node);
+		spin_unlock(&oi->ip_lock);
+		kfree(ue);
+	}
+}
+
+static void ocfs2_free_write_ctxt(struct inode *inode,
+				  struct ocfs2_write_ctxt *wc)
+{
+	ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list);
 	ocfs2_unlock_pages(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
@@ -1313,7 +839,8 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 
 static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
 				  struct ocfs2_super *osb, loff_t pos,
-				  unsigned len, struct buffer_head *di_bh)
+				  unsigned len, ocfs2_write_type_t type,
+				  struct buffer_head *di_bh)
 {
 	u32 cend;
 	struct ocfs2_write_ctxt *wc;
@@ -1328,6 +855,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
 	wc->w_clen = cend - wc->w_cpos + 1;
 	get_bh(di_bh);
 	wc->w_di_bh = di_bh;
+	wc->w_type = type;
 
 	if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits))
 		wc->w_large_pages = 1;
@@ -1335,6 +863,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
 		wc->w_large_pages = 0;
 
 	ocfs2_init_dealloc_ctxt(&wc->w_dealloc);
+	INIT_LIST_HEAD(&wc->w_unwritten_list);
 
 	*wcp = wc;
 
@@ -1395,12 +924,13 @@ static void ocfs2_write_failure(struct inode *inode,
 		to = user_pos + user_len;
 	struct page *tmppage;
 
-	ocfs2_zero_new_buffers(wc->w_target_page, from, to);
+	if (wc->w_target_page)
+		ocfs2_zero_new_buffers(wc->w_target_page, from, to);
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		tmppage = wc->w_pages[i];
 
-		if (page_has_buffers(tmppage)) {
+		if (tmppage && page_has_buffers(tmppage)) {
 			if (ocfs2_should_order_data(inode))
 				ocfs2_jbd2_file_inode(wc->w_handle, inode);
 
@@ -1530,11 +1060,13 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 		wc->w_num_pages = 1;
 		start = target_index;
 	}
+	end_index = (user_pos + user_len - 1) >> PAGE_CACHE_SHIFT;
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		index = start + i;
 
-		if (index == target_index && mmap_page) {
+		if (index >= target_index && index <= end_index &&
+		    wc->w_type == OCFS2_WRITE_MMAP) {
 			/*
 			 * ocfs2_pagemkwrite() is a little different
 			 * and wants us to directly use the page
@@ -1553,6 +1085,11 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 			page_cache_get(mmap_page);
 			wc->w_pages[i] = mmap_page;
 			wc->w_target_locked = true;
+		} else if (index >= target_index && index <= end_index &&
+			   wc->w_type == OCFS2_WRITE_DIRECT) {
+			/* Direct write has no mapping page. */
+			wc->w_pages[i] = NULL;
+			continue;
 		} else {
 			wc->w_pages[i] = find_or_create_page(mapping, index,
 							     GFP_NOFS);
@@ -1577,19 +1114,20 @@ out:
  * Prepare a single cluster for write one cluster into the file.
  */
 static int ocfs2_write_cluster(struct address_space *mapping,
-			       u32 phys, unsigned int unwritten,
+			       u32 *phys, unsigned int new,
+			       unsigned int clear_unwritten,
 			       unsigned int should_zero,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       struct ocfs2_write_ctxt *wc, u32 cpos,
 			       loff_t user_pos, unsigned user_len)
 {
-	int ret, i, new;
-	u64 v_blkno, p_blkno;
+	int ret, i;
+	u64 p_blkno;
 	struct inode *inode = mapping->host;
 	struct ocfs2_extent_tree et;
+	int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
 
-	new = phys == 0 ? 1 : 0;
 	if (new) {
 		u32 tmp_pos;
 
@@ -1599,9 +1137,9 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 		 */
 		tmp_pos = cpos;
 		ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode,
-					   &tmp_pos, 1, 0, wc->w_di_bh,
-					   wc->w_handle, data_ac,
-					   meta_ac, NULL);
+					   &tmp_pos, 1, !clear_unwritten,
+					   wc->w_di_bh, wc->w_handle,
+					   data_ac, meta_ac, NULL);
 		/*
 		 * This shouldn't happen because we must have already
 		 * calculated the correct meta data allocation required. The
@@ -1618,11 +1156,11 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 			mlog_errno(ret);
 			goto out;
 		}
-	} else if (unwritten) {
+	} else if (clear_unwritten) {
 		ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
 					      wc->w_di_bh);
 		ret = ocfs2_mark_extent_written(inode, &et,
-						wc->w_handle, cpos, 1, phys,
+						wc->w_handle, cpos, 1, *phys,
 						meta_ac, &wc->w_dealloc);
 		if (ret < 0) {
 			mlog_errno(ret);
@@ -1630,30 +1168,33 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 		}
 	}
 
-	if (should_zero)
-		v_blkno = ocfs2_clusters_to_blocks(inode->i_sb, cpos);
-	else
-		v_blkno = user_pos >> inode->i_sb->s_blocksize_bits;
-
 	/*
 	 * The only reason this should fail is due to an inability to
 	 * find the extent added.
 	 */
-	ret = ocfs2_extent_map_get_blocks(inode, v_blkno, &p_blkno, NULL,
-					  NULL);
+	ret = ocfs2_get_clusters(inode, cpos, phys, NULL, NULL);
 	if (ret < 0) {
 		mlog(ML_ERROR, "Get physical blkno failed for inode %llu, "
-			    "at logical block %llu",
-			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
-			    (unsigned long long)v_blkno);
+			    "at logical cluster %u",
+			    (unsigned long long)OCFS2_I(inode)->ip_blkno, cpos);
 		goto out;
 	}
 
-	BUG_ON(p_blkno == 0);
+	BUG_ON(*phys == 0);
+
+	p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *phys);
+	if (!should_zero)
+		p_blkno += (user_pos >> inode->i_sb->s_blocksize_bits) & (u64)(bpc - 1);
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		int tmpret;
 
+		/* This is the direct io target page. */
+		if (wc->w_pages[i] == NULL) {
+			p_blkno++;
+			continue;
+		}
+
 		tmpret = ocfs2_prepare_page_for_write(inode, &p_blkno, wc,
 						      wc->w_pages[i], cpos,
 						      user_pos, user_len,
@@ -1700,8 +1241,9 @@ static int ocfs2_write_cluster_by_desc(struct address_space *mapping,
 		if ((cluster_off + local_len) > osb->s_clustersize)
 			local_len = osb->s_clustersize - cluster_off;
 
-		ret = ocfs2_write_cluster(mapping, desc->c_phys,
-					  desc->c_unwritten,
+		ret = ocfs2_write_cluster(mapping, &desc->c_phys,
+					  desc->c_new,
+					  desc->c_clear_unwritten,
 					  desc->c_needs_zero,
 					  data_ac, meta_ac,
 					  wc, desc->c_cpos, pos, local_len);
@@ -1772,6 +1314,66 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb,
 }
 
 /*
+ * Check if this extent is marked UNWRITTEN by direct io. If so, we need not to
+ * do the zero work. And should not to clear UNWRITTEN since it will be cleared
+ * by the direct io procedure.
+ * If this is a new extent that allocated by direct io, we should mark it in
+ * the ip_unwritten_list.
+ */
+static int ocfs2_unwritten_check(struct inode *inode,
+				 struct ocfs2_write_ctxt *wc,
+				 struct ocfs2_write_cluster_desc *desc)
+{
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_unwritten_extent *ue = NULL, *new = NULL;
+	int ret = 0;
+
+	if (!desc->c_needs_zero)
+		return 0;
+
+retry:
+	spin_lock(&oi->ip_lock);
+	/* Needs not to zero no metter buffer or direct. The one who is zero
+	 * the cluster is doing zero. And he will clear unwritten after all
+	 * cluster io finished. */
+	list_for_each_entry(ue, &oi->ip_unwritten_list, ue_ip_node) {
+		if (desc->c_cpos == ue->ue_cpos) {
+			BUG_ON(desc->c_new);
+			desc->c_needs_zero = 0;
+			desc->c_clear_unwritten = 0;
+			goto unlock;
+		}
+	}
+
+	if (wc->w_type != OCFS2_WRITE_DIRECT)
+		goto unlock;
+
+	if (new == NULL) {
+		spin_unlock(&oi->ip_lock);
+		new = kmalloc(sizeof(struct ocfs2_unwritten_extent),
+			     GFP_NOFS);
+		if (new == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		goto retry;
+	}
+	/* This direct write will doing zero. */
+	new->ue_cpos = desc->c_cpos;
+	new->ue_phys = desc->c_phys;
+	desc->c_clear_unwritten = 0;
+	list_add_tail(&new->ue_ip_node, &oi->ip_unwritten_list);
+	list_add_tail(&new->ue_node, &wc->w_unwritten_list);
+	new = NULL;
+unlock:
+	spin_unlock(&oi->ip_lock);
+out:
+	if (new)
+		kfree(new);
+	return ret;
+}
+
+/*
  * Populate each single-cluster write descriptor in the write context
  * with information about the i/o to be done.
  *
@@ -1846,14 +1448,21 @@ static int ocfs2_populate_write_desc(struct inode *inode,
 		if (phys == 0) {
 			desc->c_new = 1;
 			desc->c_needs_zero = 1;
+			desc->c_clear_unwritten = 1;
 			*clusters_to_alloc = *clusters_to_alloc + 1;
 		}
 
 		if (ext_flags & OCFS2_EXT_UNWRITTEN) {
-			desc->c_unwritten = 1;
+			desc->c_clear_unwritten = 1;
 			desc->c_needs_zero = 1;
 		}
 
+		ret = ocfs2_unwritten_check(inode, wc, desc);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		num_clusters--;
 	}
 
@@ -2016,8 +1625,10 @@ static int ocfs2_expand_nonsparse_inode(struct inode *inode,
 	if (ret)
 		mlog_errno(ret);
 
-	wc->w_first_new_cpos =
-		ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
+	/* There is no wc if this is call from direct. */
+	if (wc)
+		wc->w_first_new_cpos =
+			ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
 
 	return ret;
 }
@@ -2071,9 +1682,8 @@ out:
 	return ret;
 }
 
-int ocfs2_write_begin_nolock(struct file *filp,
-			     struct address_space *mapping,
-			     loff_t pos, unsigned len, unsigned flags,
+int ocfs2_write_begin_nolock(struct address_space *mapping,
+			     loff_t pos, unsigned len, ocfs2_write_type_t type,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page)
 {
@@ -2090,7 +1700,7 @@ int ocfs2_write_begin_nolock(struct file *filp,
 	int try_free = 1, ret1;
 
 try_again:
-	ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, di_bh);
+	ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, type, di_bh);
 	if (ret) {
 		mlog_errno(ret);
 		return ret;
@@ -2109,14 +1719,17 @@ try_again:
 		}
 	}
 
-	if (ocfs2_sparse_alloc(osb))
-		ret = ocfs2_zero_tail(inode, di_bh, pos);
-	else
-		ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len,
-						   wc);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
+	/* Direct io change i_size late, should not zero tail here. */
+	if (type != OCFS2_WRITE_DIRECT) {
+		if (ocfs2_sparse_alloc(osb))
+			ret = ocfs2_zero_tail(inode, di_bh, pos);
+		else
+			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
+							   len, wc);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
 	}
 
 	ret = ocfs2_check_range_for_refcount(inode, pos, len);
@@ -2147,7 +1760,7 @@ try_again:
 			(unsigned long long)OCFS2_I(inode)->ip_blkno,
 			(long long)i_size_read(inode),
 			le32_to_cpu(di->i_clusters),
-			pos, len, flags, mmap_page,
+			pos, len, type, mmap_page,
 			clusters_to_alloc, extents_to_split);
 
 	/*
@@ -2177,17 +1790,17 @@ try_again:
 
 		credits = ocfs2_calc_extend_credits(inode->i_sb,
 						    &di->id2.i_list);
-
-	}
+	} else if (type == OCFS2_WRITE_DIRECT)
+		/* direct write needs not to start trans if no extents alloc. */
+		goto success;
 
 	/*
 	 * We have to zero sparse allocated clusters, unwritten extent clusters,
 	 * and non-sparse clusters we just extended.  For non-sparse writes,
 	 * we know zeros will only be needed in the first and/or last cluster.
 	 */
-	if (clusters_to_alloc || extents_to_split ||
-	    (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
-			    wc->w_desc[wc->w_clen - 1].c_needs_zero)))
+	if (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
+			   wc->w_desc[wc->w_clen - 1].c_needs_zero))
 		cluster_of_pages = 1;
 	else
 		cluster_of_pages = 0;
@@ -2254,7 +1867,8 @@ try_again:
 		ocfs2_free_alloc_context(meta_ac);
 
 success:
-	*pagep = wc->w_target_page;
+	if (pagep)
+		*pagep = wc->w_target_page;
 	*fsdata = wc;
 	return 0;
 out_quota:
@@ -2265,7 +1879,7 @@ out_commit:
 	ocfs2_commit_trans(osb, handle);
 
 out:
-	ocfs2_free_write_ctxt(wc);
+	ocfs2_free_write_ctxt(inode, wc);
 
 	if (data_ac) {
 		ocfs2_free_alloc_context(data_ac);
@@ -2317,8 +1931,8 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
-	ret = ocfs2_write_begin_nolock(file, mapping, pos, len, flags, pagep,
-				       fsdata, di_bh, NULL);
+	ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_BUFFER,
+				       pagep, fsdata, di_bh, NULL);
 	if (ret) {
 		mlog_errno(ret);
 		goto out_fail;
@@ -2375,12 +1989,16 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 	handle_t *handle = wc->w_handle;
 	struct page *tmppage;
 
-	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
-			OCFS2_JOURNAL_ACCESS_WRITE);
-	if (ret) {
-		copied = ret;
-		mlog_errno(ret);
-		goto out;
+	BUG_ON(!list_empty(&wc->w_unwritten_list));
+
+	if (handle) {
+		ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
+				wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE);
+		if (ret) {
+			copied = ret;
+			mlog_errno(ret);
+			goto out;
+		}
 	}
 
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
@@ -2388,18 +2006,23 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		goto out_write_size;
 	}
 
-	if (unlikely(copied < len)) {
+	if (unlikely(copied < len) && wc->w_target_page) {
 		if (!PageUptodate(wc->w_target_page))
 			copied = 0;
 
 		ocfs2_zero_new_buffers(wc->w_target_page, start+copied,
 				       start+len);
 	}
-	flush_dcache_page(wc->w_target_page);
+	if (wc->w_target_page)
+		flush_dcache_page(wc->w_target_page);
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		tmppage = wc->w_pages[i];
 
+		/* This is the direct io target page. */
+		if (tmppage == NULL)
+			continue;
+
 		if (tmppage == wc->w_target_page) {
 			from = wc->w_target_from;
 			to = wc->w_target_to;
@@ -2418,25 +2041,29 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		}
 
 		if (page_has_buffers(tmppage)) {
-			if (ocfs2_should_order_data(inode))
-				ocfs2_jbd2_file_inode(wc->w_handle, inode);
+			if (handle && ocfs2_should_order_data(inode))
+				ocfs2_jbd2_file_inode(handle, inode);
 			block_commit_write(tmppage, from, to);
 		}
 	}
 
 out_write_size:
-	pos += copied;
-	if (pos > i_size_read(inode)) {
-		i_size_write(inode, pos);
-		mark_inode_dirty(inode);
-	}
-	inode->i_blocks = ocfs2_inode_sector_count(inode);
-	di->i_size = cpu_to_le64((u64)i_size_read(inode));
-	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-	di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
-	di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
-	ocfs2_update_inode_fsync_trans(handle, inode, 1);
-	ocfs2_journal_dirty(handle, wc->w_di_bh);
+	/* Direct io do not update i_size here. */
+	if (wc->w_type != OCFS2_WRITE_DIRECT) {
+		pos += copied;
+		if (pos > i_size_read(inode)) {
+			i_size_write(inode, pos);
+			mark_inode_dirty(inode);
+		}
+		inode->i_blocks = ocfs2_inode_sector_count(inode);
+		di->i_size = cpu_to_le64((u64)i_size_read(inode));
+		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+		di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+		ocfs2_update_inode_fsync_trans(handle, inode, 1);
+	}
+	if (handle)
+		ocfs2_journal_dirty(handle, wc->w_di_bh);
 
 out:
 	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
@@ -2446,7 +2073,8 @@ out:
 	 */
 	ocfs2_unlock_pages(wc);
 
-	ocfs2_commit_trans(osb, handle);
+	if (handle)
+		ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
 
@@ -2471,6 +2099,360 @@ static int ocfs2_write_end(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
+struct ocfs2_dio_write_ctxt {
+	struct list_head	dw_zero_list;
+	unsigned		dw_zero_count;
+	int			dw_orphaned;
+	pid_t			dw_writer_pid;
+};
+
+static struct ocfs2_dio_write_ctxt *
+ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc)
+{
+	struct ocfs2_dio_write_ctxt *dwc = NULL;
+
+	if (bh->b_private)
+		return bh->b_private;
+
+	dwc = kmalloc(sizeof(struct ocfs2_dio_write_ctxt), GFP_NOFS);
+	if (dwc == NULL)
+		return NULL;
+	INIT_LIST_HEAD(&dwc->dw_zero_list);
+	dwc->dw_zero_count = 0;
+	dwc->dw_orphaned = 0;
+	dwc->dw_writer_pid = task_pid_nr(current);
+	bh->b_private = dwc;
+	*alloc = 1;
+
+	return dwc;
+}
+
+static void ocfs2_dio_free_write_ctx(struct inode *inode,
+				     struct ocfs2_dio_write_ctxt *dwc)
+{
+	ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list);
+	kfree(dwc);
+}
+
+/*
+ * TODO: Make this into a generic get_blocks function.
+ *
+ * From do_direct_io in direct-io.c:
+ *  "So what we do is to permit the ->get_blocks function to populate
+ *   bh.b_size with the size of IO which is permitted at this offset and
+ *   this i_blkbits."
+ *
+ * This function is called directly from get_more_blocks in direct-io.c.
+ *
+ * called like this: dio->get_blocks(dio->inode, fs_startblk,
+ * 					fs_count, map_bh, dio->rw == WRITE);
+ */
+static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock,
+			       struct buffer_head *bh_result, int create)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_write_ctxt *wc;
+	struct ocfs2_write_cluster_desc *desc = NULL;
+	struct ocfs2_dio_write_ctxt *dwc = NULL;
+	struct buffer_head *di_bh = NULL;
+	u64 p_blkno;
+	loff_t pos = iblock << inode->i_sb->s_blocksize_bits;
+	unsigned len, total_len = bh_result->b_size;
+	int ret = 0, first_get_block = 0;
+
+	len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
+	len = min(total_len, len);
+
+	mlog(0, "get block of %lu at %llu:%u req %u\n",
+			inode->i_ino, pos, len, total_len);
+
+	/*
+	 * Because we need to change file size in ocfs2_dio_end_io_write(), or
+	 * we may need to add it to orphan dir. So can not fall to fast path
+	 * while file size will be changed.
+	 */
+	if (pos + total_len <= i_size_read(inode)) {
+		down_read(&oi->ip_alloc_sem);
+		/* This is the fast path for re-write. */
+		ret = ocfs2_get_block(inode, iblock, bh_result, create);
+
+		up_read(&oi->ip_alloc_sem);
+
+		if (buffer_mapped(bh_result) &&
+		    !buffer_new(bh_result) &&
+		    ret == 0)
+			goto out;
+
+		/* Clear state set by ocfs2_get_block. */
+		bh_result->b_state = 0;
+	}
+
+	dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block);
+	if (unlikely(dwc == NULL)) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) >
+	    ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) &&
+	    !dwc->dw_orphaned) {
+		/*
+		 * when we are going to alloc extents beyond file size, add the
+		 * inode to orphan dir, so we can recall those spaces when
+		 * system crashed during write.
+		 */
+		ret = ocfs2_add_inode_to_orphan(osb, inode);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+		dwc->dw_orphaned = 1;
+	}
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	down_write(&oi->ip_alloc_sem);
+
+	if (first_get_block) {
+		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+			ret = ocfs2_zero_tail(inode, di_bh, pos);
+		else
+			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
+							   total_len, NULL);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto unlock;
+		}
+	}
+
+	ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len,
+				       OCFS2_WRITE_DIRECT, NULL,
+				       (void **)&wc, di_bh, NULL);
+	if (ret) {
+		mlog_errno(ret);
+		goto unlock;
+	}
+
+	desc = &wc->w_desc[0];
+
+	p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys);
+	BUG_ON(p_blkno == 0);
+	p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1);
+
+	map_bh(bh_result, inode->i_sb, p_blkno);
+	bh_result->b_size = len;
+	if (desc->c_needs_zero)
+		set_buffer_new(bh_result);
+
+	/* May sleep in end_io. It should not happen in a irq context. So defer
+	 * it to dio work queue. */
+	set_buffer_defer_completion(bh_result);
+
+	if (!list_empty(&wc->w_unwritten_list)) {
+		struct ocfs2_unwritten_extent *ue = NULL;
+
+		ue = list_first_entry(&wc->w_unwritten_list,
+				      struct ocfs2_unwritten_extent,
+				      ue_node);
+		BUG_ON(ue->ue_cpos != desc->c_cpos);
+		/* The physical address may be 0, fill it. */
+		ue->ue_phys = desc->c_phys;
+
+		list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list);
+		dwc->dw_zero_count++;
+	}
+
+	ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, NULL, wc);
+	BUG_ON(ret != len);
+	ret = 0;
+unlock:
+	up_write(&oi->ip_alloc_sem);
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+out:
+	if (ret < 0)
+		ret = -EIO;
+	return ret;
+}
+
+static void ocfs2_dio_end_io_write(struct inode *inode,
+				   struct ocfs2_dio_write_ctxt *dwc,
+				   loff_t offset,
+				   ssize_t bytes)
+{
+	struct ocfs2_cached_dealloc_ctxt dealloc;
+	struct ocfs2_extent_tree et;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_unwritten_extent *ue = NULL;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di;
+	struct ocfs2_alloc_context *data_ac = NULL;
+	struct ocfs2_alloc_context *meta_ac = NULL;
+	handle_t *handle = NULL;
+	loff_t end = offset + bytes;
+	int ret = 0, credits = 0, locked = 0;
+
+	ocfs2_init_dealloc_ctxt(&dealloc);
+
+	/* We do clear unwritten, delete orphan, change i_size here. If neither
+	 * of these happen, we can skip all this. */
+	if (list_empty(&dwc->dw_zero_list) &&
+	    end <= i_size_read(inode) &&
+	    !dwc->dw_orphaned)
+		goto out;
+
+	/* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
+	 * are in that context. */
+	if (dwc->dw_writer_pid != task_pid_nr(current)) {
+		mutex_lock(&inode->i_mutex);
+		locked = 1;
+	}
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	down_write(&oi->ip_alloc_sem);
+
+	/* Delete orphan before acquire i_mutex. */
+	if (dwc->dw_orphaned) {
+		BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));
+
+		end = end > i_size_read(inode) ? end : 0;
+
+		ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
+				!!end, end);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+	di = (struct ocfs2_dinode *)di_bh;
+
+	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
+
+	ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2,
+				    &data_ac, &meta_ac);
+	if (ret) {
+		mlog_errno(ret);
+		goto unlock;
+	}
+
+	credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list);
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto unlock;
+	}
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto commit;
+	}
+
+	list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
+		ret = ocfs2_mark_extent_written(inode, &et, handle,
+						ue->ue_cpos, 1,
+						ue->ue_phys,
+						meta_ac, &dealloc);
+		if (ret < 0) {
+			mlog_errno(ret);
+			break;
+		}
+	}
+
+	if (end > i_size_read(inode)) {
+		ret = ocfs2_set_inode_size(handle, inode, di_bh, end);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+commit:
+	ocfs2_commit_trans(osb, handle);
+unlock:
+	up_write(&oi->ip_alloc_sem);
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+out:
+	if (data_ac)
+		ocfs2_free_alloc_context(data_ac);
+	if (meta_ac)
+		ocfs2_free_alloc_context(meta_ac);
+	ocfs2_run_deallocs(osb, &dealloc);
+	if (locked)
+		mutex_unlock(&inode->i_mutex);
+	ocfs2_dio_free_write_ctx(inode, dwc);
+}
+
+/*
+ * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
+ * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
+ * to protect io on one node from truncation on another.
+ */
+static int ocfs2_dio_end_io(struct kiocb *iocb,
+			    loff_t offset,
+			    ssize_t bytes,
+			    void *private)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	int level;
+
+	if (bytes <= 0)
+		return 0;
+
+	/* this io's submitter should not have unlocked this before we could */
+	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
+
+	if (private)
+		ocfs2_dio_end_io_write(inode, private, offset, bytes);
+
+	ocfs2_iocb_clear_rw_locked(iocb);
+
+	level = ocfs2_iocb_rw_locked_level(iocb);
+	ocfs2_rw_unlock(inode, level);
+	return 0;
+}
+
+static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			       loff_t offset)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	loff_t end = offset + iter->count;
+	get_block_t *get_block;
+
+	/*
+	 * Fallback to buffered I/O if we see an inode without
+	 * extents.
+	 */
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		return 0;
+
+	/* Fallback to buffered I/O if we do not support append dio. */
+	if (end > i_size_read(inode) && !ocfs2_supports_append_dio(osb))
+		return 0;
+
+	if (iov_iter_rw(iter) == READ)
+		get_block = ocfs2_get_block;
+	else
+		get_block = ocfs2_dio_get_block;
+
+	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+				    iter, offset, get_block,
+				    ocfs2_dio_end_io, NULL, 0);
+}
+
 const struct address_space_operations ocfs2_aops = {
 	.readpage		= ocfs2_readpage,
 	.readpages		= ocfs2_readpages,
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 24e496d6bdcd..b1c9f28a57b1 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -47,9 +47,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata);
 
-int ocfs2_write_begin_nolock(struct file *filp,
-			     struct address_space *mapping,
-			     loff_t pos, unsigned len, unsigned flags,
+typedef enum {
+	OCFS2_WRITE_BUFFER = 0,
+	OCFS2_WRITE_DIRECT,
+	OCFS2_WRITE_MMAP,
+} ocfs2_write_type_t;
+
+int ocfs2_write_begin_nolock(struct address_space *mapping,
+			     loff_t pos, unsigned len, ocfs2_write_type_t type,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page);
 
@@ -79,7 +84,6 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
 enum ocfs2_iocb_lock_bits {
 	OCFS2_IOCB_RW_LOCK = 0,
 	OCFS2_IOCB_RW_LOCK_LEVEL,
-	OCFS2_IOCB_UNALIGNED_IO,
 	OCFS2_IOCB_NUM_LOCKS
 };
 
@@ -88,11 +92,4 @@ enum ocfs2_iocb_lock_bits {
 #define ocfs2_iocb_rw_locked_level(iocb) \
 	test_bit(OCFS2_IOCB_RW_LOCK_LEVEL, (unsigned long *)&iocb->private)
 
-#define ocfs2_iocb_set_unaligned_aio(iocb) \
-	set_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_clear_unaligned_aio(iocb) \
-	clear_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_is_unaligned_aio(iocb) \
-	test_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
-
 #endif /* OCFS2_FILE_H */
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index a3cc6d2fc896..bd15929b5f92 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -287,7 +287,6 @@ struct o2hb_bio_wait_ctxt {
 static void o2hb_write_timeout(struct work_struct *work)
 {
 	int failed, quorum;
-	unsigned long flags;
 	struct o2hb_region *reg =
 		container_of(work, struct o2hb_region,
 			     hr_write_timeout_work.work);
@@ -297,14 +296,14 @@ static void o2hb_write_timeout(struct work_struct *work)
 	     jiffies_to_msecs(jiffies - reg->hr_last_timeout_start));
 
 	if (o2hb_global_heartbeat_active()) {
-		spin_lock_irqsave(&o2hb_live_lock, flags);
+		spin_lock(&o2hb_live_lock);
 		if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
 			set_bit(reg->hr_region_num, o2hb_failed_region_bitmap);
 		failed = bitmap_weight(o2hb_failed_region_bitmap,
 					O2NM_MAX_REGIONS);
 		quorum = bitmap_weight(o2hb_quorum_region_bitmap,
 					O2NM_MAX_REGIONS);
-		spin_unlock_irqrestore(&o2hb_live_lock, flags);
+		spin_unlock(&o2hb_live_lock);
 
 		mlog(ML_HEARTBEAT, "Number of regions %d, failed regions %d\n",
 		     quorum, failed);
@@ -1254,15 +1253,15 @@ static const struct file_operations o2hb_debug_fops = {
 
 void o2hb_exit(void)
 {
-	kfree(o2hb_db_livenodes);
-	kfree(o2hb_db_liveregions);
-	kfree(o2hb_db_quorumregions);
-	kfree(o2hb_db_failedregions);
 	debugfs_remove(o2hb_debug_failedregions);
 	debugfs_remove(o2hb_debug_quorumregions);
 	debugfs_remove(o2hb_debug_liveregions);
 	debugfs_remove(o2hb_debug_livenodes);
 	debugfs_remove(o2hb_debug_dir);
+	kfree(o2hb_db_livenodes);
+	kfree(o2hb_db_liveregions);
+	kfree(o2hb_db_quorumregions);
+	kfree(o2hb_db_failedregions);
 }
 
 static struct dentry *o2hb_debug_create(const char *name, struct dentry *dir,
@@ -1438,13 +1437,15 @@ static void o2hb_region_release(struct config_item *item)
 
 	kfree(reg->hr_slots);
 
-	kfree(reg->hr_db_regnum);
-	kfree(reg->hr_db_livenodes);
 	debugfs_remove(reg->hr_debug_livenodes);
 	debugfs_remove(reg->hr_debug_regnum);
 	debugfs_remove(reg->hr_debug_elapsed_time);
 	debugfs_remove(reg->hr_debug_pinned);
 	debugfs_remove(reg->hr_debug_dir);
+	kfree(reg->hr_db_livenodes);
+	kfree(reg->hr_db_regnum);
+	kfree(reg->hr_db_elapsed_time);
+	kfree(reg->hr_db_pinned);
 
 	spin_lock(&o2hb_live_lock);
 	list_del(&reg->hr_all_item);
@@ -2423,11 +2424,10 @@ EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating);
 int o2hb_check_node_heartbeating_no_sem(u8 node_num)
 {
 	unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
-	unsigned long flags;
 
-	spin_lock_irqsave(&o2hb_live_lock, flags);
+	spin_lock(&o2hb_live_lock);
 	o2hb_fill_node_map_from_callback(testing_map, sizeof(testing_map));
-	spin_unlock_irqrestore(&o2hb_live_lock, flags);
+	spin_unlock(&o2hb_live_lock);
 	if (!test_bit(node_num, testing_map)) {
 		mlog(ML_HEARTBEAT,
 		     "node (%u) does not have heartbeating enabled.\n",
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index ebe543894db0..b17d180bdc16 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -630,7 +630,6 @@ static void o2nm_cluster_release(struct config_item *item)
 {
 	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
 
-	kfree(cluster->cl_group.default_groups);
 	kfree(cluster);
 }
 
@@ -666,7 +665,6 @@ static struct config_group *o2nm_cluster_group_make_group(struct config_group *g
 	struct o2nm_cluster *cluster = NULL;
 	struct o2nm_node_group *ns = NULL;
 	struct config_group *o2hb_group = NULL, *ret = NULL;
-	void *defs = NULL;
 
 	/* this runs under the parent dir's i_mutex; there can be only
 	 * one caller in here at a time */
@@ -675,20 +673,18 @@ static struct config_group *o2nm_cluster_group_make_group(struct config_group *g
 
 	cluster = kzalloc(sizeof(struct o2nm_cluster), GFP_KERNEL);
 	ns = kzalloc(sizeof(struct o2nm_node_group), GFP_KERNEL);
-	defs = kcalloc(3, sizeof(struct config_group *), GFP_KERNEL);
 	o2hb_group = o2hb_alloc_hb_set();
-	if (cluster == NULL || ns == NULL || o2hb_group == NULL || defs == NULL)
+	if (cluster == NULL || ns == NULL || o2hb_group == NULL)
 		goto out;
 
 	config_group_init_type_name(&cluster->cl_group, name,
 				    &o2nm_cluster_type);
+	configfs_add_default_group(&ns->ns_group, &cluster->cl_group);
+
 	config_group_init_type_name(&ns->ns_group, "node",
 				    &o2nm_node_group_type);
+	configfs_add_default_group(o2hb_group, &cluster->cl_group);
 
-	cluster->cl_group.default_groups = defs;
-	cluster->cl_group.default_groups[0] = &ns->ns_group;
-	cluster->cl_group.default_groups[1] = o2hb_group;
-	cluster->cl_group.default_groups[2] = NULL;
 	rwlock_init(&cluster->cl_nodes_lock);
 	cluster->cl_node_ip_tree = RB_ROOT;
 	cluster->cl_reconnect_delay_ms = O2NET_RECONNECT_DELAY_MS_DEFAULT;
@@ -704,7 +700,6 @@ out:
 		kfree(cluster);
 		kfree(ns);
 		o2hb_free_hb_set(o2hb_group);
-		kfree(defs);
 		ret = ERR_PTR(-ENOMEM);
 	}
 
@@ -714,18 +709,11 @@ out:
 static void o2nm_cluster_group_drop_item(struct config_group *group, struct config_item *item)
 {
 	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
-	int i;
-	struct config_item *killme;
 
 	BUG_ON(o2nm_single_cluster != cluster);
 	o2nm_single_cluster = NULL;
 
-	for (i = 0; cluster->cl_group.default_groups[i]; i++) {
-		killme = &cluster->cl_group.default_groups[i]->cg_item;
-		cluster->cl_group.default_groups[i] = NULL;
-		config_item_put(killme);
-	}
-
+	configfs_remove_default_groups(&cluster->cl_group);
 	config_item_put(item);
 }
 
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 68c607e63ff6..004f2cbe8f71 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -282,6 +282,7 @@ static inline void __dlm_set_joining_node(struct dlm_ctxt *dlm,
 #define DLM_LOCK_RES_DROPPING_REF         0x00000040
 #define DLM_LOCK_RES_BLOCK_DIRTY          0x00001000
 #define DLM_LOCK_RES_SETREF_INPROG        0x00002000
+#define DLM_LOCK_RES_RECOVERY_WAITING     0x00004000
 
 /* max milliseconds to wait to sync up a network failure with a node death */
 #define DLM_NODE_DEATH_WAIT_MAX (5 * 1000)
@@ -451,6 +452,7 @@ enum {
 	DLM_QUERY_REGION		= 519,
 	DLM_QUERY_NODEINFO		= 520,
 	DLM_BEGIN_EXIT_DOMAIN_MSG	= 521,
+	DLM_DEREF_LOCKRES_DONE		= 522,
 };
 
 struct dlm_reco_node_data
@@ -545,7 +547,7 @@ struct dlm_master_requery
  * };
  *
  * from ../cluster/tcp.h
- *    NET_MAX_PAYLOAD_BYTES  (4096 - sizeof(net_msg))
+ *    O2NET_MAX_PAYLOAD_BYTES  (4096 - sizeof(net_msg))
  *    (roughly 4080 bytes)
  * and sizeof(dlm_migratable_lockres) = 112 bytes
  * and sizeof(dlm_migratable_lock) = 16 bytes
@@ -586,7 +588,7 @@ struct dlm_migratable_lockres
 
 /* from above, 128 bytes
  * for some undetermined future use */
-#define DLM_MIG_LOCKRES_RESERVED   (NET_MAX_PAYLOAD_BYTES - \
+#define DLM_MIG_LOCKRES_RESERVED   (O2NET_MAX_PAYLOAD_BYTES - \
 				    DLM_MIG_LOCKRES_MAX_LEN)
 
 struct dlm_create_lock
@@ -782,6 +784,20 @@ struct dlm_deref_lockres
 	u8 name[O2NM_MAX_NAME_LEN];
 };
 
+enum {
+	DLM_DEREF_RESPONSE_DONE = 0,
+	DLM_DEREF_RESPONSE_INPROG = 1,
+};
+
+struct dlm_deref_lockres_done {
+	u32 pad1;
+	u16 pad2;
+	u8 node_idx;
+	u8 namelen;
+
+	u8 name[O2NM_MAX_NAME_LEN];
+};
+
 static inline enum dlm_status
 __dlm_lockres_state_to_status(struct dlm_lock_resource *res)
 {
@@ -789,7 +805,8 @@ __dlm_lockres_state_to_status(struct dlm_lock_resource *res)
 
 	assert_spin_locked(&res->spinlock);
 
-	if (res->state & DLM_LOCK_RES_RECOVERING)
+	if (res->state & (DLM_LOCK_RES_RECOVERING|
+			DLM_LOCK_RES_RECOVERY_WAITING))
 		status = DLM_RECOVERING;
 	else if (res->state & DLM_LOCK_RES_MIGRATING)
 		status = DLM_MIGRATING;
@@ -968,6 +985,8 @@ int dlm_assert_master_handler(struct o2net_msg *msg, u32 len, void *data,
 void dlm_assert_master_post_handler(int status, void *data, void *ret_data);
 int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 			      void **ret_data);
+int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data,
+			      void **ret_data);
 int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data,
 				void **ret_data);
 int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
@@ -1009,6 +1028,7 @@ static inline void __dlm_wait_on_lockres(struct dlm_lock_resource *res)
 {
 	__dlm_wait_on_lockres_flags(res, (DLM_LOCK_RES_IN_PROGRESS|
 				    	  DLM_LOCK_RES_RECOVERING|
+					  DLM_LOCK_RES_RECOVERY_WAITING|
 					  DLM_LOCK_RES_MIGRATING));
 }
 
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index e36d63ff1783..cdeafb4e7ed6 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -212,6 +212,12 @@ grant:
 	if (lock->lksb->flags & DLM_LKSB_PUT_LVB)
 		memcpy(res->lvb, lock->lksb->lvb, DLM_LVB_LEN);
 
+	/*
+	 * Move the lock to the tail because it may be the only lock which has
+	 * an invalid lvb.
+	 */
+	list_move_tail(&lock->list, &res->granted);
+
 	status = DLM_NORMAL;
 	*call_ast = 1;
 	goto unlock_exit;
@@ -262,6 +268,7 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 				  struct dlm_lock *lock, int flags, int type)
 {
 	enum dlm_status status;
+	u8 old_owner = res->owner;
 
 	mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type,
 	     lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS);
@@ -287,6 +294,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 		status = DLM_DENIED;
 		goto bail;
 	}
+
+	if (lock->ml.type == type && lock->ml.convert_type == LKM_IVMODE) {
+		mlog(0, "last convert request returned DLM_RECOVERING, but "
+		     "owner has already queued and sent ast to me. res %.*s, "
+		     "(cookie=%u:%llu, type=%d, conv=%d)\n",
+		     res->lockname.len, res->lockname.name,
+		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
+		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
+		     lock->ml.type, lock->ml.convert_type);
+		status = DLM_NORMAL;
+		goto bail;
+	}
+
 	res->state |= DLM_LOCK_RES_IN_PROGRESS;
 	/* move lock to local convert queue */
 	/* do not alter lock refcount.  switching lists. */
@@ -316,11 +336,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 	spin_lock(&res->spinlock);
 	res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
 	lock->convert_pending = 0;
-	/* if it failed, move it back to granted queue */
+	/* if it failed, move it back to granted queue.
+	 * if master returns DLM_NORMAL and then down before sending ast,
+	 * it may have already been moved to granted queue, reset to
+	 * DLM_RECOVERING and retry convert */
 	if (status != DLM_NORMAL) {
 		if (status != DLM_NOTQUEUED)
 			dlm_error(status);
 		dlm_revert_pending_convert(res, lock);
+	} else if ((res->state & DLM_LOCK_RES_RECOVERING) ||
+			(old_owner != res->owner)) {
+		mlog(0, "res %.*s is in recovering or has been recovered.\n",
+				res->lockname.len, res->lockname.name);
+		status = DLM_RECOVERING;
 	}
 bail:
 	spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 2ee7fe747cea..12e064b8be9a 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -132,10 +132,13 @@ static DECLARE_WAIT_QUEUE_HEAD(dlm_domain_events);
  *	- Message DLM_QUERY_NODEINFO added to allow online node removes
  * New in version 1.2:
  * 	- Message DLM_BEGIN_EXIT_DOMAIN_MSG added to mark start of exit domain
+ * New in version 1.3:
+ *	- Message DLM_DEREF_LOCKRES_DONE added to inform non-master that the
+ *	  refmap is cleared
  */
 static const struct dlm_protocol_version dlm_protocol = {
 	.pv_major = 1,
-	.pv_minor = 2,
+	.pv_minor = 3,
 };
 
 #define DLM_DOMAIN_BACKOFF_MS 200
@@ -1396,7 +1399,7 @@ static int dlm_send_join_cancels(struct dlm_ctxt *dlm,
 				 unsigned int map_size)
 {
 	int status, tmpstat;
-	unsigned int node;
+	int node;
 
 	if (map_size != (BITS_TO_LONGS(O2NM_MAX_NODES) *
 			 sizeof(unsigned long))) {
@@ -1853,7 +1856,13 @@ static int dlm_register_domain_handlers(struct dlm_ctxt *dlm)
 					sizeof(struct dlm_exit_domain),
 					dlm_begin_exit_domain_handler,
 					dlm, NULL, &dlm->dlm_domain_handlers);
+	if (status)
+		goto bail;
 
+	status = o2net_register_handler(DLM_DEREF_LOCKRES_DONE, dlm->key,
+					sizeof(struct dlm_deref_lockres_done),
+					dlm_deref_lockres_done_handler,
+					dlm, NULL, &dlm->dlm_domain_handlers);
 bail:
 	if (status)
 		dlm_unregister_domain_handlers(dlm);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 9477d6e1de37..9aed6e202201 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2278,7 +2278,7 @@ int dlm_drop_lockres_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 		dlm_print_one_lock_resource(res);
 		BUG();
 	}
-	return ret;
+	return ret ? ret : r;
 }
 
 int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
@@ -2345,7 +2345,7 @@ int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 		     	res->lockname.len, res->lockname.name, node);
 			dlm_print_one_lock_resource(res);
 		}
-		ret = 0;
+		ret = DLM_DEREF_RESPONSE_DONE;
 		goto done;
 	}
 
@@ -2365,7 +2365,7 @@ int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	spin_unlock(&dlm->work_lock);
 
 	queue_work(dlm->dlm_worker, &dlm->dispatched_work);
-	return 0;
+	return DLM_DEREF_RESPONSE_INPROG;
 
 done:
 	if (res)
@@ -2375,6 +2375,122 @@ done:
 	return ret;
 }
 
+int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data,
+			      void **ret_data)
+{
+	struct dlm_ctxt *dlm = data;
+	struct dlm_deref_lockres_done *deref
+			= (struct dlm_deref_lockres_done *)msg->buf;
+	struct dlm_lock_resource *res = NULL;
+	char *name;
+	unsigned int namelen;
+	int ret = -EINVAL;
+	u8 node;
+	unsigned int hash;
+
+	if (!dlm_grab(dlm))
+		return 0;
+
+	name = deref->name;
+	namelen = deref->namelen;
+	node = deref->node_idx;
+
+	if (namelen > DLM_LOCKID_NAME_MAX) {
+		mlog(ML_ERROR, "Invalid name length!");
+		goto done;
+	}
+	if (deref->node_idx >= O2NM_MAX_NODES) {
+		mlog(ML_ERROR, "Invalid node number: %u\n", node);
+		goto done;
+	}
+
+	hash = dlm_lockid_hash(name, namelen);
+
+	spin_lock(&dlm->spinlock);
+	res = __dlm_lookup_lockres_full(dlm, name, namelen, hash);
+	if (!res) {
+		spin_unlock(&dlm->spinlock);
+		mlog(ML_ERROR, "%s:%.*s: bad lockres name\n",
+		     dlm->name, namelen, name);
+		goto done;
+	}
+
+	spin_lock(&res->spinlock);
+	BUG_ON(!(res->state & DLM_LOCK_RES_DROPPING_REF));
+	if (!list_empty(&res->purge)) {
+		mlog(0, "%s: Removing res %.*s from purgelist\n",
+			dlm->name, res->lockname.len, res->lockname.name);
+		list_del_init(&res->purge);
+		dlm_lockres_put(res);
+		dlm->purge_count--;
+	}
+
+	if (!__dlm_lockres_unused(res)) {
+		mlog(ML_ERROR, "%s: res %.*s in use after deref\n",
+			dlm->name, res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+		BUG();
+	}
+
+	__dlm_unhash_lockres(dlm, res);
+
+	spin_lock(&dlm->track_lock);
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "%s: Resource %.*s not on the Tracking list\n",
+		     dlm->name, res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+	}
+	spin_unlock(&dlm->track_lock);
+
+	/* lockres is not in the hash now. drop the flag and wake up
+	 * any processes waiting in dlm_get_lock_resource.
+	 */
+	res->state &= ~DLM_LOCK_RES_DROPPING_REF;
+	spin_unlock(&res->spinlock);
+	wake_up(&res->wq);
+
+	dlm_lockres_put(res);
+
+	spin_unlock(&dlm->spinlock);
+
+done:
+	dlm_put(dlm);
+	return ret;
+}
+
+static void dlm_drop_lockres_ref_done(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res, u8 node)
+{
+	struct dlm_deref_lockres_done deref;
+	int ret = 0, r;
+	const char *lockname;
+	unsigned int namelen;
+
+	lockname = res->lockname.name;
+	namelen = res->lockname.len;
+	BUG_ON(namelen > O2NM_MAX_NAME_LEN);
+
+	memset(&deref, 0, sizeof(deref));
+	deref.node_idx = dlm->node_num;
+	deref.namelen = namelen;
+	memcpy(deref.name, lockname, namelen);
+
+	ret = o2net_send_message(DLM_DEREF_LOCKRES_DONE, dlm->key,
+				 &deref, sizeof(deref), node, &r);
+	if (ret < 0) {
+		mlog(ML_ERROR, "%s: res %.*s, error %d send DEREF DONE "
+				" to node %u\n", dlm->name, namelen,
+				lockname, ret, node);
+	} else if (r < 0) {
+		/* ignore the error */
+		mlog(ML_ERROR, "%s: res %.*s, DEREF to node %u got %d\n",
+		     dlm->name, namelen, lockname, node, r);
+		dlm_print_one_lock_resource(res);
+	}
+}
+
 static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 {
 	struct dlm_ctxt *dlm;
@@ -2395,6 +2511,8 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 	}
 	spin_unlock(&res->spinlock);
 
+	dlm_drop_lockres_ref_done(dlm, res, node);
+
 	if (cleared) {
 		mlog(0, "%s:%.*s node %u ref dropped in dispatch\n",
 		     dlm->name, res->lockname.len, res->lockname.name, node);
@@ -2432,7 +2550,8 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 		return 0;
 
 	/* delay migration when the lockres is in RECOCERING state */
-	if (res->state & DLM_LOCK_RES_RECOVERING)
+	if (res->state & (DLM_LOCK_RES_RECOVERING|
+			DLM_LOCK_RES_RECOVERY_WAITING))
 		return 0;
 
 	if (res->owner != dlm->node_num)
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index c5bdf02c213b..f6b313898763 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1403,12 +1403,24 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	 * and RECOVERY flag changed when it completes. */
 	hash = dlm_lockid_hash(mres->lockname, mres->lockname_len);
 	spin_lock(&dlm->spinlock);
-	res = __dlm_lookup_lockres(dlm, mres->lockname, mres->lockname_len,
+	res = __dlm_lookup_lockres_full(dlm, mres->lockname, mres->lockname_len,
 			hash);
 	if (res) {
 	 	/* this will get a ref on res */
 		/* mark it as recovering/migrating and hash it */
 		spin_lock(&res->spinlock);
+		if (res->state & DLM_LOCK_RES_DROPPING_REF) {
+			mlog(0, "%s: node is attempting to migrate "
+				"lockres %.*s, but marked as dropping "
+				" ref!\n", dlm->name,
+				mres->lockname_len, mres->lockname);
+			ret = -EINVAL;
+			spin_unlock(&res->spinlock);
+			spin_unlock(&dlm->spinlock);
+			dlm_lockres_put(res);
+			goto leave;
+		}
+
 		if (mres->flags & DLM_MRES_RECOVERY) {
 			res->state |= DLM_LOCK_RES_RECOVERING;
 		} else {
@@ -2071,7 +2083,6 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm,
 			dlm_lock_get(lock);
 			if (lock->convert_pending) {
 				/* move converting lock back to granted */
-				BUG_ON(i != DLM_CONVERTING_LIST);
 				mlog(0, "node died with convert pending "
 				     "on %.*s. move back to granted list.\n",
 				     res->lockname.len, res->lockname.name);
@@ -2163,6 +2174,13 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm,
 	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
 		bucket = dlm_lockres_hash(dlm, i);
 		hlist_for_each_entry(res, bucket, hash_node) {
+			if (res->state & DLM_LOCK_RES_RECOVERY_WAITING) {
+				spin_lock(&res->spinlock);
+				res->state &= ~DLM_LOCK_RES_RECOVERY_WAITING;
+				spin_unlock(&res->spinlock);
+				wake_up(&res->wq);
+			}
+
 			if (!(res->state & DLM_LOCK_RES_RECOVERING))
 				continue;
 
@@ -2300,6 +2318,7 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm,
 			     res->lockname.len, res->lockname.name, freed, dead_node);
 			__dlm_print_one_lock_resource(res);
 		}
+		res->state |= DLM_LOCK_RES_RECOVERY_WAITING;
 		dlm_lockres_clear_refmap_bit(dlm, res, dead_node);
 	} else if (test_bit(dead_node, res->refmap)) {
 		mlog(0, "%s:%.*s: dead node %u had a ref, but had "
@@ -2367,6 +2386,8 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 						break;
 					}
 				}
+				dlm_lockres_clear_refmap_bit(dlm, res,
+						dead_node);
 				spin_unlock(&res->spinlock);
 				continue;
 			}
@@ -2375,14 +2396,16 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 			dlm_revalidate_lvb(dlm, res, dead_node);
 			if (res->owner == dead_node) {
 				if (res->state & DLM_LOCK_RES_DROPPING_REF) {
-					mlog(ML_NOTICE, "%s: res %.*s, Skip "
-					     "recovery as it is being freed\n",
-					     dlm->name, res->lockname.len,
-					     res->lockname.name);
-				} else
-					dlm_move_lockres_to_recovery_list(dlm,
-									  res);
-
+					mlog(0, "%s:%.*s: owned by "
+						"dead node %u, this node was "
+						"dropping its ref when it died. "
+						"continue, dropping the flag.\n",
+						dlm->name, res->lockname.len,
+						res->lockname.name, dead_node);
+				}
+				res->state &= ~DLM_LOCK_RES_DROPPING_REF;
+				dlm_move_lockres_to_recovery_list(dlm,
+						res);
 			} else if (res->owner == dlm->node_num) {
 				dlm_free_dead_locks(dlm, res, dead_node);
 				__dlm_lockres_calc_usage(dlm, res);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index c5f6c241ecd7..68d239ba0c63 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -106,7 +106,8 @@ int __dlm_lockres_unused(struct dlm_lock_resource *res)
 	if (!list_empty(&res->dirty) || res->state & DLM_LOCK_RES_DIRTY)
 		return 0;
 
-	if (res->state & DLM_LOCK_RES_RECOVERING)
+	if (res->state & (DLM_LOCK_RES_RECOVERING|
+			DLM_LOCK_RES_RECOVERY_WAITING))
 		return 0;
 
 	/* Another node has this resource with this node as the master */
@@ -202,6 +203,13 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 		dlm->purge_count--;
 	}
 
+	if (!master && ret != 0) {
+		mlog(0, "%s: deref %.*s in progress or master goes down\n",
+			dlm->name, res->lockname.len, res->lockname.name);
+		spin_unlock(&res->spinlock);
+		return;
+	}
+
 	if (!__dlm_lockres_unused(res)) {
 		mlog(ML_ERROR, "%s: res %.*s in use after deref\n",
 		     dlm->name, res->lockname.len, res->lockname.name);
@@ -700,7 +708,8 @@ static int dlm_thread(void *data)
 			 * dirty for a short while. */
 			BUG_ON(res->state & DLM_LOCK_RES_MIGRATING);
 			if (res->state & (DLM_LOCK_RES_IN_PROGRESS |
-					  DLM_LOCK_RES_RECOVERING)) {
+					  DLM_LOCK_RES_RECOVERING |
+					  DLM_LOCK_RES_RECOVERY_WAITING)) {
 				/* move it to the tail and keep going */
 				res->state &= ~DLM_LOCK_RES_DIRTY;
 				spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 7cb38fdca229..c18ab45f8d21 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1381,44 +1381,6 @@ out:
 	return ret;
 }
 
-/*
- * Will look for holes and unwritten extents in the range starting at
- * pos for count bytes (inclusive).
- */
-static int ocfs2_check_range_for_holes(struct inode *inode, loff_t pos,
-				       size_t count)
-{
-	int ret = 0;
-	unsigned int extent_flags;
-	u32 cpos, clusters, extent_len, phys_cpos;
-	struct super_block *sb = inode->i_sb;
-
-	cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits;
-	clusters = ocfs2_clusters_for_bytes(sb, pos + count) - cpos;
-
-	while (clusters) {
-		ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &extent_len,
-					 &extent_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-
-		if (phys_cpos == 0 || (extent_flags & OCFS2_EXT_UNWRITTEN)) {
-			ret = 1;
-			break;
-		}
-
-		if (extent_len > clusters)
-			extent_len = clusters;
-
-		clusters -= extent_len;
-		cpos += extent_len;
-	}
-out:
-	return ret;
-}
-
 static int ocfs2_write_remove_suid(struct inode *inode)
 {
 	int ret;
@@ -2129,18 +2091,12 @@ out:
 
 static int ocfs2_prepare_inode_for_write(struct file *file,
 					 loff_t pos,
-					 size_t count,
-					 int appending,
-					 int *direct_io,
-					 int *has_refcount)
+					 size_t count)
 {
 	int ret = 0, meta_level = 0;
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = d_inode(dentry);
 	loff_t 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
@@ -2189,10 +2145,6 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 							       pos,
 							       count,
 							       &meta_level);
-			if (has_refcount)
-				*has_refcount = 1;
-			if (direct_io)
-				*direct_io = 0;
 		}
 
 		if (ret < 0) {
@@ -2200,67 +2152,12 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 			goto out_unlock;
 		}
 
-		/*
-		 * Skip the O_DIRECT checks if we don't need
-		 * them.
-		 */
-		if (!direct_io || !(*direct_io))
-			break;
-
-		/*
-		 * There's no sane way to do direct writes to an inode
-		 * with inline data.
-		 */
-		if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
-			*direct_io = 0;
-			break;
-		}
-
-		/*
-		 * Allowing concurrent direct writes means
-		 * i_size changes wouldn't be synchronized, so
-		 * one node could wind up truncating another
-		 * nodes writes.
-		 */
-		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;
-		}
-
-		/*
-		 * We don't fill holes during direct io, so
-		 * check for them here. If any are found, the
-		 * caller will have to retake some cluster
-		 * locks and initiate the io as buffered.
-		 */
-		ret = ocfs2_check_range_for_holes(inode, pos, count);
-		if (ret == 1) {
-			/*
-			 * 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);
 		break;
 	}
 
 out_unlock:
 	trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno,
-					    pos, appending, count,
-					    direct_io, has_refcount);
+					    pos, count);
 
 	if (meta_level >= 0)
 		ocfs2_inode_unlock(inode, meta_level);
@@ -2272,18 +2169,16 @@ out:
 static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 				    struct iov_iter *from)
 {
-	int direct_io, appending, rw_level;
-	int can_do_direct, has_refcount = 0;
+	int direct_io, rw_level;
 	ssize_t written = 0;
 	ssize_t ret;
-	size_t count = iov_iter_count(from), orig_count;
+	size_t count = iov_iter_count(from);
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int full_coherency = !(osb->s_mount_opt &
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
-	int unaligned_dio = 0;
-	int dropped_dio = 0;
+	void *saved_ki_complete = NULL;
 	int append_write = ((iocb->ki_pos + count) >=
 			i_size_read(inode) ? 1 : 0);
 
@@ -2296,12 +2191,10 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	if (count == 0)
 		return 0;
 
-	appending = iocb->ki_flags & IOCB_APPEND ? 1 : 0;
 	direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
 
 	inode_lock(inode);
 
-relock:
 	/*
 	 * Concurrent O_DIRECT writes are allowed with
 	 * mount_option "coherency=buffered".
@@ -2334,7 +2227,6 @@ relock:
 		ocfs2_inode_unlock(inode, 1);
 	}
 
-	orig_count = iov_iter_count(from);
 	ret = generic_write_checks(iocb, from);
 	if (ret <= 0) {
 		if (ret)
@@ -2343,41 +2235,18 @@ relock:
 	}
 	count = ret;
 
-	can_do_direct = direct_io;
-	ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count, appending,
-					    &can_do_direct, &has_refcount);
+	ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out;
 	}
 
-	if (direct_io && !is_sync_kiocb(iocb))
-		unaligned_dio = ocfs2_is_io_unaligned(inode, count, iocb->ki_pos);
-
-	/*
-	 * We can't complete the direct I/O as requested, fall back to
-	 * buffered I/O.
-	 */
-	if (direct_io && !can_do_direct) {
-		ocfs2_rw_unlock(inode, rw_level);
-
-		rw_level = -1;
-
-		direct_io = 0;
-		iocb->ki_flags &= ~IOCB_DIRECT;
-		iov_iter_reexpand(from, orig_count);
-		dropped_dio = 1;
-		goto relock;
-	}
-
-	if (unaligned_dio) {
+	if (direct_io && !is_sync_kiocb(iocb) &&
+	    ocfs2_is_io_unaligned(inode, count, iocb->ki_pos)) {
 		/*
-		 * Wait on previous unaligned aio to complete before
-		 * proceeding.
+		 * Make it a sync io if it's an unaligned aio.
 		 */
-		mutex_lock(&OCFS2_I(inode)->ip_unaligned_aio);
-		/* Mark the iocb as needing an unlock in ocfs2_dio_end_io */
-		ocfs2_iocb_set_unaligned_aio(iocb);
+		saved_ki_complete = xchg(&iocb->ki_complete, NULL);
 	}
 
 	/* communicate with ocfs2_dio_end_io */
@@ -2398,14 +2267,13 @@ relock:
 	 */
 	if ((written == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) {
 		rw_level = -1;
-		unaligned_dio = 0;
 	}
 
 	if (unlikely(written <= 0))
-		goto no_sync;
+		goto out;
 
 	if (((file->f_flags & O_DSYNC) && !direct_io) ||
-	    IS_SYNC(inode) || dropped_dio) {
+	    IS_SYNC(inode)) {
 		ret = filemap_fdatawrite_range(file->f_mapping,
 					       iocb->ki_pos - written,
 					       iocb->ki_pos - 1);
@@ -2424,13 +2292,10 @@ relock:
 						      iocb->ki_pos - 1);
 	}
 
-no_sync:
-	if (unaligned_dio && ocfs2_iocb_is_unaligned_aio(iocb)) {
-		ocfs2_iocb_clear_unaligned_aio(iocb);
-		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
-	}
-
 out:
+	if (saved_ki_complete)
+		xchg(&iocb->ki_complete, saved_ki_complete);
+
 	if (rw_level != -1)
 		ocfs2_rw_unlock(inode, rw_level);
 
diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c
new file mode 100644
index 000000000000..2cabbcf2f28e
--- /dev/null
+++ b/fs/ocfs2/filecheck.c
@@ -0,0 +1,606 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * filecheck.c
+ *
+ * Code which implements online file check.
+ *
+ * Copyright (C) 2016 SuSE.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation, version 2.
+ *
+ * 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/list.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/fs.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/sysctl.h>
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+#include "ocfs2_fs.h"
+#include "stackglue.h"
+#include "inode.h"
+
+#include "filecheck.h"
+
+
+/* File check error strings,
+ * must correspond with error number in header file.
+ */
+static const char * const ocfs2_filecheck_errs[] = {
+	"SUCCESS",
+	"FAILED",
+	"INPROGRESS",
+	"READONLY",
+	"INJBD",
+	"INVALIDINO",
+	"BLOCKECC",
+	"BLOCKNO",
+	"VALIDFLAG",
+	"GENERATION",
+	"UNSUPPORTED"
+};
+
+static DEFINE_SPINLOCK(ocfs2_filecheck_sysfs_lock);
+static LIST_HEAD(ocfs2_filecheck_sysfs_list);
+
+struct ocfs2_filecheck {
+	struct list_head fc_head;	/* File check entry list head */
+	spinlock_t fc_lock;
+	unsigned int fc_max;	/* Maximum number of entry in list */
+	unsigned int fc_size;	/* Current entry count in list */
+	unsigned int fc_done;	/* Finished entry count in list */
+};
+
+struct ocfs2_filecheck_sysfs_entry {	/* sysfs entry per mounting */
+	struct list_head fs_list;
+	atomic_t fs_count;
+	struct super_block *fs_sb;
+	struct kset *fs_devicekset;
+	struct kset *fs_fcheckkset;
+	struct ocfs2_filecheck *fs_fcheck;
+};
+
+#define OCFS2_FILECHECK_MAXSIZE		100
+#define OCFS2_FILECHECK_MINSIZE		10
+
+/* File check operation type */
+enum {
+	OCFS2_FILECHECK_TYPE_CHK = 0,	/* Check a file(inode) */
+	OCFS2_FILECHECK_TYPE_FIX,	/* Fix a file(inode) */
+	OCFS2_FILECHECK_TYPE_SET = 100	/* Set entry list maximum size */
+};
+
+struct ocfs2_filecheck_entry {
+	struct list_head fe_list;
+	unsigned long fe_ino;
+	unsigned int fe_type;
+	unsigned int fe_done:1;
+	unsigned int fe_status:31;
+};
+
+struct ocfs2_filecheck_args {
+	unsigned int fa_type;
+	union {
+		unsigned long fa_ino;
+		unsigned int fa_len;
+	};
+};
+
+static const char *
+ocfs2_filecheck_error(int errno)
+{
+	if (!errno)
+		return ocfs2_filecheck_errs[errno];
+
+	BUG_ON(errno < OCFS2_FILECHECK_ERR_START ||
+	       errno > OCFS2_FILECHECK_ERR_END);
+	return ocfs2_filecheck_errs[errno - OCFS2_FILECHECK_ERR_START + 1];
+}
+
+static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+				    struct kobj_attribute *attr,
+				    char *buf);
+static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+				     struct kobj_attribute *attr,
+				     const char *buf, size_t count);
+static struct kobj_attribute ocfs2_attr_filecheck_chk =
+					__ATTR(check, S_IRUSR | S_IWUSR,
+					ocfs2_filecheck_show,
+					ocfs2_filecheck_store);
+static struct kobj_attribute ocfs2_attr_filecheck_fix =
+					__ATTR(fix, S_IRUSR | S_IWUSR,
+					ocfs2_filecheck_show,
+					ocfs2_filecheck_store);
+static struct kobj_attribute ocfs2_attr_filecheck_set =
+					__ATTR(set, S_IRUSR | S_IWUSR,
+					ocfs2_filecheck_show,
+					ocfs2_filecheck_store);
+
+static int ocfs2_filecheck_sysfs_wait(atomic_t *p)
+{
+	schedule();
+	return 0;
+}
+
+static void
+ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	if (!atomic_dec_and_test(&entry->fs_count))
+		wait_on_atomic_t(&entry->fs_count, ocfs2_filecheck_sysfs_wait,
+				 TASK_UNINTERRUPTIBLE);
+
+	spin_lock(&entry->fs_fcheck->fc_lock);
+	while (!list_empty(&entry->fs_fcheck->fc_head)) {
+		p = list_first_entry(&entry->fs_fcheck->fc_head,
+				     struct ocfs2_filecheck_entry, fe_list);
+		list_del(&p->fe_list);
+		BUG_ON(!p->fe_done); /* To free a undone file check entry */
+		kfree(p);
+	}
+	spin_unlock(&entry->fs_fcheck->fc_lock);
+
+	kset_unregister(entry->fs_fcheckkset);
+	kset_unregister(entry->fs_devicekset);
+	kfree(entry->fs_fcheck);
+	kfree(entry);
+}
+
+static void
+ocfs2_filecheck_sysfs_add(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_add_tail(&entry->fs_list, &ocfs2_filecheck_sysfs_list);
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+}
+
+static int ocfs2_filecheck_sysfs_del(const char *devname)
+{
+	struct ocfs2_filecheck_sysfs_entry *p;
+
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
+		if (!strcmp(p->fs_sb->s_id, devname)) {
+			list_del(&p->fs_list);
+			spin_unlock(&ocfs2_filecheck_sysfs_lock);
+			ocfs2_filecheck_sysfs_free(p);
+			return 0;
+		}
+	}
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	return 1;
+}
+
+static void
+ocfs2_filecheck_sysfs_put(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	if (atomic_dec_and_test(&entry->fs_count))
+		wake_up_atomic_t(&entry->fs_count);
+}
+
+static struct ocfs2_filecheck_sysfs_entry *
+ocfs2_filecheck_sysfs_get(const char *devname)
+{
+	struct ocfs2_filecheck_sysfs_entry *p = NULL;
+
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
+		if (!strcmp(p->fs_sb->s_id, devname)) {
+			atomic_inc(&p->fs_count);
+			spin_unlock(&ocfs2_filecheck_sysfs_lock);
+			return p;
+		}
+	}
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	return NULL;
+}
+
+int ocfs2_filecheck_create_sysfs(struct super_block *sb)
+{
+	int ret = 0;
+	struct kset *device_kset = NULL;
+	struct kset *fcheck_kset = NULL;
+	struct ocfs2_filecheck *fcheck = NULL;
+	struct ocfs2_filecheck_sysfs_entry *entry = NULL;
+	struct attribute **attrs = NULL;
+	struct attribute_group attrgp;
+
+	if (!ocfs2_kset)
+		return -ENOMEM;
+
+	attrs = kmalloc(sizeof(struct attribute *) * 4, GFP_NOFS);
+	if (!attrs) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		attrs[0] = &ocfs2_attr_filecheck_chk.attr;
+		attrs[1] = &ocfs2_attr_filecheck_fix.attr;
+		attrs[2] = &ocfs2_attr_filecheck_set.attr;
+		attrs[3] = NULL;
+		memset(&attrgp, 0, sizeof(attrgp));
+		attrgp.attrs = attrs;
+	}
+
+	fcheck = kmalloc(sizeof(struct ocfs2_filecheck), GFP_NOFS);
+	if (!fcheck) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		INIT_LIST_HEAD(&fcheck->fc_head);
+		spin_lock_init(&fcheck->fc_lock);
+		fcheck->fc_max = OCFS2_FILECHECK_MINSIZE;
+		fcheck->fc_size = 0;
+		fcheck->fc_done = 0;
+	}
+
+	if (strlen(sb->s_id) <= 0) {
+		mlog(ML_ERROR,
+		"Cannot get device basename when create filecheck sysfs\n");
+		ret = -ENODEV;
+		goto error;
+	}
+
+	device_kset = kset_create_and_add(sb->s_id, NULL, &ocfs2_kset->kobj);
+	if (!device_kset) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	fcheck_kset = kset_create_and_add("filecheck", NULL,
+					  &device_kset->kobj);
+	if (!fcheck_kset) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ret = sysfs_create_group(&fcheck_kset->kobj, &attrgp);
+	if (ret)
+		goto error;
+
+	entry = kmalloc(sizeof(struct ocfs2_filecheck_sysfs_entry), GFP_NOFS);
+	if (!entry) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		atomic_set(&entry->fs_count, 1);
+		entry->fs_sb = sb;
+		entry->fs_devicekset = device_kset;
+		entry->fs_fcheckkset = fcheck_kset;
+		entry->fs_fcheck = fcheck;
+		ocfs2_filecheck_sysfs_add(entry);
+	}
+
+	kfree(attrs);
+	return 0;
+
+error:
+	kfree(attrs);
+	kfree(entry);
+	kfree(fcheck);
+	kset_unregister(fcheck_kset);
+	kset_unregister(device_kset);
+	return ret;
+}
+
+int ocfs2_filecheck_remove_sysfs(struct super_block *sb)
+{
+	return ocfs2_filecheck_sysfs_del(sb->s_id);
+}
+
+static int
+ocfs2_filecheck_erase_entries(struct ocfs2_filecheck_sysfs_entry *ent,
+			      unsigned int count);
+static int
+ocfs2_filecheck_adjust_max(struct ocfs2_filecheck_sysfs_entry *ent,
+			   unsigned int len)
+{
+	int ret;
+
+	if ((len < OCFS2_FILECHECK_MINSIZE) || (len > OCFS2_FILECHECK_MAXSIZE))
+		return -EINVAL;
+
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	if (len < (ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done)) {
+		mlog(ML_ERROR,
+		"Cannot set online file check maximum entry number "
+		"to %u due to too many pending entries(%u)\n",
+		len, ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done);
+		ret = -EBUSY;
+	} else {
+		if (len < ent->fs_fcheck->fc_size)
+			BUG_ON(!ocfs2_filecheck_erase_entries(ent,
+				ent->fs_fcheck->fc_size - len));
+
+		ent->fs_fcheck->fc_max = len;
+		ret = 0;
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+	return ret;
+}
+
+#define OCFS2_FILECHECK_ARGS_LEN	24
+static int
+ocfs2_filecheck_args_get_long(const char *buf, size_t count,
+			      unsigned long *val)
+{
+	char buffer[OCFS2_FILECHECK_ARGS_LEN];
+
+	memcpy(buffer, buf, count);
+	buffer[count] = '\0';
+
+	if (kstrtoul(buffer, 0, val))
+		return 1;
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_type_parse(const char *name, unsigned int *type)
+{
+	if (!strncmp(name, "fix", 4))
+		*type = OCFS2_FILECHECK_TYPE_FIX;
+	else if (!strncmp(name, "check", 6))
+		*type = OCFS2_FILECHECK_TYPE_CHK;
+	else if (!strncmp(name, "set", 4))
+		*type = OCFS2_FILECHECK_TYPE_SET;
+	else
+		return 1;
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_args_parse(const char *name, const char *buf, size_t count,
+			   struct ocfs2_filecheck_args *args)
+{
+	unsigned long val = 0;
+	unsigned int type;
+
+	/* too short/long args length */
+	if ((count < 1) || (count >= OCFS2_FILECHECK_ARGS_LEN))
+		return 1;
+
+	if (ocfs2_filecheck_type_parse(name, &type))
+		return 1;
+	if (ocfs2_filecheck_args_get_long(buf, count, &val))
+		return 1;
+
+	if (val <= 0)
+		return 1;
+
+	args->fa_type = type;
+	if (type == OCFS2_FILECHECK_TYPE_SET)
+		args->fa_len = (unsigned int)val;
+	else
+		args->fa_ino = val;
+
+	return 0;
+}
+
+static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+				    struct kobj_attribute *attr,
+				    char *buf)
+{
+
+	ssize_t ret = 0, total = 0, remain = PAGE_SIZE;
+	unsigned int type;
+	struct ocfs2_filecheck_entry *p;
+	struct ocfs2_filecheck_sysfs_entry *ent;
+
+	if (ocfs2_filecheck_type_parse(attr->attr.name, &type))
+		return -EINVAL;
+
+	ent = ocfs2_filecheck_sysfs_get(kobj->parent->name);
+	if (!ent) {
+		mlog(ML_ERROR,
+		"Cannot get the corresponding entry via device basename %s\n",
+		kobj->name);
+		return -ENODEV;
+	}
+
+	if (type == OCFS2_FILECHECK_TYPE_SET) {
+		spin_lock(&ent->fs_fcheck->fc_lock);
+		total = snprintf(buf, remain, "%u\n", ent->fs_fcheck->fc_max);
+		spin_unlock(&ent->fs_fcheck->fc_lock);
+		goto exit;
+	}
+
+	ret = snprintf(buf, remain, "INO\t\tDONE\tERROR\n");
+	total += ret;
+	remain -= ret;
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		if (p->fe_type != type)
+			continue;
+
+		ret = snprintf(buf + total, remain, "%lu\t\t%u\t%s\n",
+			       p->fe_ino, p->fe_done,
+			       ocfs2_filecheck_error(p->fe_status));
+		if (ret < 0) {
+			total = ret;
+			break;
+		}
+		if (ret == remain) {
+			/* snprintf() didn't fit */
+			total = -E2BIG;
+			break;
+		}
+		total += ret;
+		remain -= ret;
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+exit:
+	ocfs2_filecheck_sysfs_put(ent);
+	return total;
+}
+
+static int
+ocfs2_filecheck_erase_entry(struct ocfs2_filecheck_sysfs_entry *ent)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		if (p->fe_done) {
+			list_del(&p->fe_list);
+			kfree(p);
+			ent->fs_fcheck->fc_size--;
+			ent->fs_fcheck->fc_done--;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_erase_entries(struct ocfs2_filecheck_sysfs_entry *ent,
+			      unsigned int count)
+{
+	unsigned int i = 0;
+	unsigned int ret = 0;
+
+	while (i++ < count) {
+		if (ocfs2_filecheck_erase_entry(ent))
+			ret++;
+		else
+			break;
+	}
+
+	return (ret == count ? 1 : 0);
+}
+
+static void
+ocfs2_filecheck_done_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+			   struct ocfs2_filecheck_entry *entry)
+{
+	entry->fe_done = 1;
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	ent->fs_fcheck->fc_done++;
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+}
+
+static unsigned int
+ocfs2_filecheck_handle(struct super_block *sb,
+		       unsigned long ino, unsigned int flags)
+{
+	unsigned int ret = OCFS2_FILECHECK_ERR_SUCCESS;
+	struct inode *inode = NULL;
+	int rc;
+
+	inode = ocfs2_iget(OCFS2_SB(sb), ino, flags, 0);
+	if (IS_ERR(inode)) {
+		rc = (int)(-(long)inode);
+		if (rc >= OCFS2_FILECHECK_ERR_START &&
+		    rc < OCFS2_FILECHECK_ERR_END)
+			ret = rc;
+		else
+			ret = OCFS2_FILECHECK_ERR_FAILED;
+	} else
+		iput(inode);
+
+	return ret;
+}
+
+static void
+ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+			     struct ocfs2_filecheck_entry *entry)
+{
+	if (entry->fe_type == OCFS2_FILECHECK_TYPE_CHK)
+		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_CHK);
+	else if (entry->fe_type == OCFS2_FILECHECK_TYPE_FIX)
+		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_FIX);
+	else
+		entry->fe_status = OCFS2_FILECHECK_ERR_UNSUPPORTED;
+
+	ocfs2_filecheck_done_entry(ent, entry);
+}
+
+static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+				     struct kobj_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct ocfs2_filecheck_args args;
+	struct ocfs2_filecheck_entry *entry;
+	struct ocfs2_filecheck_sysfs_entry *ent;
+	ssize_t ret = 0;
+
+	if (count == 0)
+		return count;
+
+	if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args)) {
+		mlog(ML_ERROR, "Invalid arguments for online file check\n");
+		return -EINVAL;
+	}
+
+	ent = ocfs2_filecheck_sysfs_get(kobj->parent->name);
+	if (!ent) {
+		mlog(ML_ERROR,
+		"Cannot get the corresponding entry via device basename %s\n",
+		kobj->parent->name);
+		return -ENODEV;
+	}
+
+	if (args.fa_type == OCFS2_FILECHECK_TYPE_SET) {
+		ret = ocfs2_filecheck_adjust_max(ent, args.fa_len);
+		goto exit;
+	}
+
+	entry = kmalloc(sizeof(struct ocfs2_filecheck_entry), GFP_NOFS);
+	if (!entry) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
+	    (ent->fs_fcheck->fc_done == 0)) {
+		mlog(ML_ERROR,
+		"Cannot do more file check "
+		"since file check queue(%u) is full now\n",
+		ent->fs_fcheck->fc_max);
+		ret = -EBUSY;
+		kfree(entry);
+	} else {
+		if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
+		    (ent->fs_fcheck->fc_done > 0)) {
+			/* Delete the oldest entry which was done,
+			 * make sure the entry size in list does
+			 * not exceed maximum value
+			 */
+			BUG_ON(!ocfs2_filecheck_erase_entry(ent));
+		}
+
+		entry->fe_ino = args.fa_ino;
+		entry->fe_type = args.fa_type;
+		entry->fe_done = 0;
+		entry->fe_status = OCFS2_FILECHECK_ERR_INPROGRESS;
+		list_add_tail(&entry->fe_list, &ent->fs_fcheck->fc_head);
+		ent->fs_fcheck->fc_size++;
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+	if (!ret)
+		ocfs2_filecheck_handle_entry(ent, entry);
+
+exit:
+	ocfs2_filecheck_sysfs_put(ent);
+	return (!ret ? count : ret);
+}
diff --git a/fs/ocfs2/filecheck.h b/fs/ocfs2/filecheck.h
new file mode 100644
index 000000000000..e5cd002a2c09
--- /dev/null
+++ b/fs/ocfs2/filecheck.h
@@ -0,0 +1,49 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * filecheck.h
+ *
+ * Online file check.
+ *
+ * Copyright (C) 2016 SuSE.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation, version 2.
+ *
+ * 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.
+ */
+
+
+#ifndef FILECHECK_H
+#define FILECHECK_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+
+
+/* File check errno */
+enum {
+	OCFS2_FILECHECK_ERR_SUCCESS = 0,	/* Success */
+	OCFS2_FILECHECK_ERR_FAILED = 1000,	/* Other failure */
+	OCFS2_FILECHECK_ERR_INPROGRESS,		/* In progress */
+	OCFS2_FILECHECK_ERR_READONLY,		/* Read only */
+	OCFS2_FILECHECK_ERR_INJBD,		/* Buffer in jbd */
+	OCFS2_FILECHECK_ERR_INVALIDINO,		/* Invalid ino */
+	OCFS2_FILECHECK_ERR_BLOCKECC,		/* Block ecc */
+	OCFS2_FILECHECK_ERR_BLOCKNO,		/* Block number */
+	OCFS2_FILECHECK_ERR_VALIDFLAG,		/* Inode valid flag */
+	OCFS2_FILECHECK_ERR_GENERATION,		/* Inode generation */
+	OCFS2_FILECHECK_ERR_UNSUPPORTED		/* Unsupported */
+};
+
+#define OCFS2_FILECHECK_ERR_START	OCFS2_FILECHECK_ERR_FAILED
+#define OCFS2_FILECHECK_ERR_END		OCFS2_FILECHECK_ERR_UNSUPPORTED
+
+int ocfs2_filecheck_create_sysfs(struct super_block *sb);
+int ocfs2_filecheck_remove_sysfs(struct super_block *sb);
+
+#endif  /* FILECHECK_H */
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 36294446d960..12f4a9e9800f 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -53,6 +53,7 @@
 #include "xattr.h"
 #include "refcounttree.h"
 #include "ocfs2_trace.h"
+#include "filecheck.h"
 
 #include "buffer_head_io.h"
 
@@ -74,6 +75,14 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
 				    struct inode *inode,
 				    struct buffer_head *fe_bh);
 
+static int ocfs2_filecheck_read_inode_block_full(struct inode *inode,
+						 struct buffer_head **bh,
+						 int flags, int type);
+static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
+						struct buffer_head *bh);
+static int ocfs2_filecheck_repair_inode_block(struct super_block *sb,
+					      struct buffer_head *bh);
+
 void ocfs2_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = OCFS2_I(inode)->ip_attr;
@@ -127,6 +136,7 @@ struct inode *ocfs2_ilookup(struct super_block *sb, u64 blkno)
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 			 int sysfile_type)
 {
+	int rc = 0;
 	struct inode *inode = NULL;
 	struct super_block *sb = osb->sb;
 	struct ocfs2_find_inode_args args;
@@ -161,12 +171,17 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 	}
 	trace_ocfs2_iget5_locked(inode->i_state);
 	if (inode->i_state & I_NEW) {
-		ocfs2_read_locked_inode(inode, &args);
+		rc = ocfs2_read_locked_inode(inode, &args);
 		unlock_new_inode(inode);
 	}
 	if (is_bad_inode(inode)) {
 		iput(inode);
-		inode = ERR_PTR(-ESTALE);
+		if ((flags & OCFS2_FI_FLAG_FILECHECK_CHK) ||
+		    (flags & OCFS2_FI_FLAG_FILECHECK_FIX))
+			/* Return OCFS2_FILECHECK_ERR_XXX related errno */
+			inode = ERR_PTR(rc);
+		else
+			inode = ERR_PTR(-ESTALE);
 		goto bail;
 	}
 
@@ -410,7 +425,7 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 	struct ocfs2_super *osb;
 	struct ocfs2_dinode *fe;
 	struct buffer_head *bh = NULL;
-	int status, can_lock;
+	int status, can_lock, lock_level = 0;
 	u32 generation = 0;
 
 	status = -EINVAL;
@@ -478,7 +493,7 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 			mlog_errno(status);
 			return status;
 		}
-		status = ocfs2_inode_lock(inode, NULL, 0);
+		status = ocfs2_inode_lock(inode, NULL, lock_level);
 		if (status) {
 			make_bad_inode(inode);
 			mlog_errno(status);
@@ -495,16 +510,32 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 	}
 
 	if (can_lock) {
-		status = ocfs2_read_inode_block_full(inode, &bh,
-						     OCFS2_BH_IGNORE_CACHE);
+		if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_CHK)
+			status = ocfs2_filecheck_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE, 0);
+		else if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_FIX)
+			status = ocfs2_filecheck_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE, 1);
+		else
+			status = ocfs2_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE);
 	} else {
 		status = ocfs2_read_blocks_sync(osb, args->fi_blkno, 1, &bh);
 		/*
 		 * If buffer is in jbd, then its checksum may not have been
 		 * computed as yet.
 		 */
-		if (!status && !buffer_jbd(bh))
-			status = ocfs2_validate_inode_block(osb->sb, bh);
+		if (!status && !buffer_jbd(bh)) {
+			if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_CHK)
+				status = ocfs2_filecheck_validate_inode_block(
+								osb->sb, bh);
+			else if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_FIX)
+				status = ocfs2_filecheck_repair_inode_block(
+								osb->sb, bh);
+			else
+				status = ocfs2_validate_inode_block(
+								osb->sb, bh);
+		}
 	}
 	if (status < 0) {
 		mlog_errno(status);
@@ -532,11 +563,24 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 
 	BUG_ON(args->fi_blkno != le64_to_cpu(fe->i_blkno));
 
+	if (buffer_dirty(bh) && !buffer_jbd(bh)) {
+		if (can_lock) {
+			ocfs2_inode_unlock(inode, lock_level);
+			lock_level = 1;
+			ocfs2_inode_lock(inode, NULL, lock_level);
+		}
+		status = ocfs2_write_block(osb, bh, INODE_CACHE(inode));
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
 	status = 0;
 
 bail:
 	if (can_lock)
-		ocfs2_inode_unlock(inode, 0);
+		ocfs2_inode_unlock(inode, lock_level);
 
 	if (status < 0)
 		make_bad_inode(inode);
@@ -1126,6 +1170,9 @@ static void ocfs2_clear_inode(struct inode *inode)
 	mlog_bug_on_msg(!list_empty(&oi->ip_io_markers),
 			"Clear inode of %llu, inode has io markers\n",
 			(unsigned long long)oi->ip_blkno);
+	mlog_bug_on_msg(!list_empty(&oi->ip_unwritten_list),
+			"Clear inode of %llu, inode has unwritten extents\n",
+			(unsigned long long)oi->ip_blkno);
 
 	ocfs2_extent_map_trunc(inode, 0);
 
@@ -1397,6 +1444,169 @@ bail:
 	return rc;
 }
 
+static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
+						struct buffer_head *bh)
+{
+	int rc = 0;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
+
+	trace_ocfs2_filecheck_validate_inode_block(
+		(unsigned long long)bh->b_blocknr);
+
+	BUG_ON(!buffer_uptodate(bh));
+
+	/*
+	 * Call ocfs2_validate_meta_ecc() first since it has ecc repair
+	 * function, but we should not return error immediately when ecc
+	 * validation fails, because the reason is quite likely the invalid
+	 * inode number inputed.
+	 */
+	rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check);
+	if (rc) {
+		mlog(ML_ERROR,
+		     "Filecheck: checksum failed for dinode %llu\n",
+		     (unsigned long long)bh->b_blocknr);
+		rc = -OCFS2_FILECHECK_ERR_BLOCKECC;
+	}
+
+	if (!OCFS2_IS_VALID_DINODE(di)) {
+		mlog(ML_ERROR,
+		     "Filecheck: invalid dinode #%llu: signature = %.*s\n",
+		     (unsigned long long)bh->b_blocknr, 7, di->i_signature);
+		rc = -OCFS2_FILECHECK_ERR_INVALIDINO;
+		goto bail;
+	} else if (rc)
+		goto bail;
+
+	if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
+		mlog(ML_ERROR,
+		     "Filecheck: invalid dinode #%llu: i_blkno is %llu\n",
+		     (unsigned long long)bh->b_blocknr,
+		     (unsigned long long)le64_to_cpu(di->i_blkno));
+		rc = -OCFS2_FILECHECK_ERR_BLOCKNO;
+		goto bail;
+	}
+
+	if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
+		mlog(ML_ERROR,
+		     "Filecheck: invalid dinode #%llu: OCFS2_VALID_FL "
+		     "not set\n",
+		     (unsigned long long)bh->b_blocknr);
+		rc = -OCFS2_FILECHECK_ERR_VALIDFLAG;
+		goto bail;
+	}
+
+	if (le32_to_cpu(di->i_fs_generation) !=
+	    OCFS2_SB(sb)->fs_generation) {
+		mlog(ML_ERROR,
+		     "Filecheck: invalid dinode #%llu: fs_generation is %u\n",
+		     (unsigned long long)bh->b_blocknr,
+		     le32_to_cpu(di->i_fs_generation));
+		rc = -OCFS2_FILECHECK_ERR_GENERATION;
+		goto bail;
+	}
+
+bail:
+	return rc;
+}
+
+static int ocfs2_filecheck_repair_inode_block(struct super_block *sb,
+					      struct buffer_head *bh)
+{
+	int changed = 0;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
+
+	if (!ocfs2_filecheck_validate_inode_block(sb, bh))
+		return 0;
+
+	trace_ocfs2_filecheck_repair_inode_block(
+		(unsigned long long)bh->b_blocknr);
+
+	if (ocfs2_is_hard_readonly(OCFS2_SB(sb)) ||
+	    ocfs2_is_soft_readonly(OCFS2_SB(sb))) {
+		mlog(ML_ERROR,
+		     "Filecheck: cannot repair dinode #%llu "
+		     "on readonly filesystem\n",
+		     (unsigned long long)bh->b_blocknr);
+		return -OCFS2_FILECHECK_ERR_READONLY;
+	}
+
+	if (buffer_jbd(bh)) {
+		mlog(ML_ERROR,
+		     "Filecheck: cannot repair dinode #%llu, "
+		     "its buffer is in jbd\n",
+		     (unsigned long long)bh->b_blocknr);
+		return -OCFS2_FILECHECK_ERR_INJBD;
+	}
+
+	if (!OCFS2_IS_VALID_DINODE(di)) {
+		/* Cannot fix invalid inode block */
+		return -OCFS2_FILECHECK_ERR_INVALIDINO;
+	}
+
+	if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
+		/* Cannot just add VALID_FL flag back as a fix,
+		 * need more things to check here.
+		 */
+		return -OCFS2_FILECHECK_ERR_VALIDFLAG;
+	}
+
+	if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
+		di->i_blkno = cpu_to_le64(bh->b_blocknr);
+		changed = 1;
+		mlog(ML_ERROR,
+		     "Filecheck: reset dinode #%llu: i_blkno to %llu\n",
+		     (unsigned long long)bh->b_blocknr,
+		     (unsigned long long)le64_to_cpu(di->i_blkno));
+	}
+
+	if (le32_to_cpu(di->i_fs_generation) !=
+	    OCFS2_SB(sb)->fs_generation) {
+		di->i_fs_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation);
+		changed = 1;
+		mlog(ML_ERROR,
+		     "Filecheck: reset dinode #%llu: fs_generation to %u\n",
+		     (unsigned long long)bh->b_blocknr,
+		     le32_to_cpu(di->i_fs_generation));
+	}
+
+	if (changed || ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check)) {
+		ocfs2_compute_meta_ecc(sb, bh->b_data, &di->i_check);
+		mark_buffer_dirty(bh);
+		mlog(ML_ERROR,
+		     "Filecheck: reset dinode #%llu: compute meta ecc\n",
+		     (unsigned long long)bh->b_blocknr);
+	}
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_read_inode_block_full(struct inode *inode,
+				      struct buffer_head **bh,
+				      int flags, int type)
+{
+	int rc;
+	struct buffer_head *tmp = *bh;
+
+	if (!type) /* Check inode block */
+		rc = ocfs2_read_blocks(INODE_CACHE(inode),
+				OCFS2_I(inode)->ip_blkno,
+				1, &tmp, flags,
+				ocfs2_filecheck_validate_inode_block);
+	else /* Repair inode block */
+		rc = ocfs2_read_blocks(INODE_CACHE(inode),
+				OCFS2_I(inode)->ip_blkno,
+				1, &tmp, flags,
+				ocfs2_filecheck_repair_inode_block);
+
+	/* If ocfs2_read_blocks() got us a new bh, pass it up. */
+	if (!rc && !*bh)
+		*bh = tmp;
+
+	return rc;
+}
+
 int ocfs2_read_inode_block_full(struct inode *inode, struct buffer_head **bh,
 				int flags)
 {
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index aac8b86f312e..d8f3fc8d2551 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -43,9 +43,6 @@ struct ocfs2_inode_info
 	/* protects extended attribute changes on this inode */
 	struct rw_semaphore		ip_xattr_sem;
 
-	/* Number of outstanding AIO's which are not page aligned */
-	struct mutex			ip_unaligned_aio;
-
 	/* These fields are protected by ip_lock */
 	spinlock_t			ip_lock;
 	u32				ip_open_count;
@@ -57,6 +54,9 @@ struct ocfs2_inode_info
 	u32				ip_flags; /* see below */
 	u32				ip_attr; /* inode attributes */
 
+	/* Record unwritten extents during direct io. */
+	struct list_head		ip_unwritten_list;
+
 	/* protected by recovery_lock. */
 	struct inode			*ip_next_orphan;
 
@@ -139,6 +139,9 @@ int ocfs2_drop_inode(struct inode *inode);
 /* Flags for ocfs2_iget() */
 #define OCFS2_FI_FLAG_SYSFILE		0x1
 #define OCFS2_FI_FLAG_ORPHAN_RECOVERY	0x2
+#define OCFS2_FI_FLAG_FILECHECK_CHK	0x4
+#define OCFS2_FI_FLAG_FILECHECK_FIX	0x8
+
 struct inode *ocfs2_ilookup(struct super_block *sb, u64 feoff);
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 feoff, unsigned flags,
 			 int sysfile_type);
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 61b833b721d8..e607419cdfa4 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -231,7 +231,7 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb)
 	/* At this point, we know that no more recovery threads can be
 	 * launched, so wait for any recovery completion work to
 	 * complete. */
-	flush_workqueue(ocfs2_wq);
+	flush_workqueue(osb->ocfs2_wq);
 
 	/*
 	 * Now that recovery is shut down, and the osb is about to be
@@ -1326,7 +1326,7 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 
 	spin_lock(&journal->j_lock);
 	list_add_tail(&item->lri_list, &journal->j_la_cleanups);
-	queue_work(ocfs2_wq, &journal->j_recovery_work);
+	queue_work(journal->j_osb->ocfs2_wq, &journal->j_recovery_work);
 	spin_unlock(&journal->j_lock);
 }
 
@@ -1968,7 +1968,7 @@ static void ocfs2_orphan_scan_work(struct work_struct *work)
 	mutex_lock(&os->os_lock);
 	ocfs2_queue_orphan_scan(osb);
 	if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE)
-		queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work,
+		queue_delayed_work(osb->ocfs2_wq, &os->os_orphan_scan_work,
 				      ocfs2_orphan_scan_timeout());
 	mutex_unlock(&os->os_lock);
 }
@@ -2008,7 +2008,7 @@ void ocfs2_orphan_scan_start(struct ocfs2_super *osb)
 		atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE);
 	else {
 		atomic_set(&os->os_state, ORPHAN_SCAN_ACTIVE);
-		queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work,
+		queue_delayed_work(osb->ocfs2_wq, &os->os_orphan_scan_work,
 				   ocfs2_orphan_scan_timeout());
 	}
 }
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 7d62c43a2c3e..fe0d1f9571bb 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -386,7 +386,7 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 	struct ocfs2_dinode *alloc = NULL;
 
 	cancel_delayed_work(&osb->la_enable_wq);
-	flush_workqueue(ocfs2_wq);
+	flush_workqueue(osb->ocfs2_wq);
 
 	if (osb->local_alloc_state == OCFS2_LA_UNUSED)
 		goto out;
@@ -1085,7 +1085,7 @@ static int ocfs2_recalc_la_window(struct ocfs2_super *osb,
 		} else {
 			osb->local_alloc_state = OCFS2_LA_DISABLED;
 		}
-		queue_delayed_work(ocfs2_wq, &osb->la_enable_wq,
+		queue_delayed_work(osb->ocfs2_wq, &osb->la_enable_wq,
 				   OCFS2_LA_ENABLE_INTERVAL);
 		goto out_unlock;
 	}
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 9581d190f6e1..9ea081f4e6e4 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -104,8 +104,8 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
 	if (page->index == last_index)
 		len = ((size - 1) & ~PAGE_CACHE_MASK) + 1;
 
-	ret = ocfs2_write_begin_nolock(file, mapping, pos, len, 0, &locked_page,
-				       &fsdata, di_bh, page);
+	ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP,
+				       &locked_page, &fsdata, di_bh, page);
 	if (ret) {
 		if (ret != -ENOSPC)
 			mlog_errno(ret);
@@ -147,6 +147,10 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	ret = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (ret < 0) {
 		mlog_errno(ret);
+		if (ret == -ENOMEM)
+			ret = VM_FAULT_OOM;
+		else
+			ret = VM_FAULT_SIGBUS;
 		goto out;
 	}
 
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7a0126267847..6cf6538a0651 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -464,6 +464,14 @@ struct ocfs2_super
 	struct ocfs2_refcount_tree *osb_ref_tree_lru;
 
 	struct mutex system_file_mutex;
+
+	/*
+	 * OCFS2 needs to schedule several different types of work which
+	 * require cluster locking, disk I/O, recovery waits, etc. Since these
+	 * types of work tend to be heavy we avoid using the kernel events
+	 * workqueue and schedule on our own.
+	 */
+	struct workqueue_struct *ocfs2_wq;
 };
 
 #define OCFS2_SB(sb)	    ((struct ocfs2_super *)(sb)->s_fs_info)
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 6cb019b7c6a8..f8f5fc5e6c05 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1450,28 +1450,20 @@ DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_remove_inode_range);
 
 TRACE_EVENT(ocfs2_prepare_inode_for_write,
 	TP_PROTO(unsigned long long ino, unsigned long long saved_pos,
-		 int appending, unsigned long count,
-		 int *direct_io, int *has_refcount),
-	TP_ARGS(ino, saved_pos, appending, count, direct_io, has_refcount),
+		 unsigned long count),
+	TP_ARGS(ino, saved_pos, count),
 	TP_STRUCT__entry(
 		__field(unsigned long long, ino)
 		__field(unsigned long long, saved_pos)
-		__field(int, appending)
 		__field(unsigned long, count)
-		__field(int, direct_io)
-		__field(int, has_refcount)
 	),
 	TP_fast_assign(
 		__entry->ino = ino;
 		__entry->saved_pos = saved_pos;
-		__entry->appending = appending;
 		__entry->count = count;
-		__entry->direct_io = direct_io ? *direct_io : -1;
-		__entry->has_refcount = has_refcount ? *has_refcount : -1;
 	),
-	TP_printk("%llu %llu %d %lu %d %d", __entry->ino,
-		  __entry->saved_pos, __entry->appending, __entry->count,
-		  __entry->direct_io, __entry->has_refcount)
+	TP_printk("%llu %llu %lu", __entry->ino,
+		  __entry->saved_pos, __entry->count)
 );
 
 DEFINE_OCFS2_INT_EVENT(generic_file_aio_read_ret);
@@ -1540,6 +1532,8 @@ DEFINE_OCFS2_ULL_INT_EVENT(ocfs2_read_locked_inode);
 DEFINE_OCFS2_INT_INT_EVENT(ocfs2_check_orphan_recovery_state);
 
 DEFINE_OCFS2_ULL_EVENT(ocfs2_validate_inode_block);
+DEFINE_OCFS2_ULL_EVENT(ocfs2_filecheck_validate_inode_block);
+DEFINE_OCFS2_ULL_EVENT(ocfs2_filecheck_repair_inode_block);
 
 TRACE_EVENT(ocfs2_inode_is_valid_to_delete,
 	TP_PROTO(void *task, void *dc_task, unsigned long long ino,
@@ -2035,6 +2029,8 @@ DEFINE_OCFS2_UINT_INT_EVENT(ocfs2_release_dquot);
 
 DEFINE_OCFS2_UINT_INT_EVENT(ocfs2_acquire_dquot);
 
+DEFINE_OCFS2_UINT_INT_EVENT(ocfs2_get_next_id);
+
 DEFINE_OCFS2_UINT_INT_EVENT(ocfs2_mark_dquot_dirty);
 
 /* End of trace events for fs/ocfs2/quota_global.c. */
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 9c9dd30bc945..3892f3c079ca 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -726,7 +726,7 @@ static int ocfs2_release_dquot(struct dquot *dquot)
 		dqgrab(dquot);
 		/* First entry on list -> queue work */
 		if (llist_add(&OCFS2_DQUOT(dquot)->list, &osb->dquot_drop_list))
-			queue_work(ocfs2_wq, &osb->dquot_drop_work);
+			queue_work(osb->ocfs2_wq, &osb->dquot_drop_work);
 		goto out;
 	}
 	status = ocfs2_lock_global_qf(oinfo, 1);
@@ -860,6 +860,30 @@ out:
 	return status;
 }
 
+static int ocfs2_get_next_id(struct super_block *sb, struct kqid *qid)
+{
+	int type = qid->type;
+	struct ocfs2_mem_dqinfo *info = sb_dqinfo(sb, type)->dqi_priv;
+	int status = 0;
+
+	trace_ocfs2_get_next_id(from_kqid(&init_user_ns, *qid), type);
+	status = ocfs2_lock_global_qf(info, 0);
+	if (status < 0)
+		goto out;
+	status = ocfs2_qinfo_lock(info, 0);
+	if (status < 0)
+		goto out_global;
+	status = qtree_get_next_id(&info->dqi_gi, qid);
+	ocfs2_qinfo_unlock(info, 0);
+out_global:
+	ocfs2_unlock_global_qf(info, 0);
+out:
+	/* Avoid logging ENOENT since it just means there isn't next ID */
+	if (status && status != -ENOENT)
+		mlog_errno(status);
+	return status;
+}
+
 static int ocfs2_mark_dquot_dirty(struct dquot *dquot)
 {
 	unsigned long mask = (1 << (DQ_LASTSET_B + QIF_ILIMITS_B)) |
@@ -968,4 +992,5 @@ const struct dquot_operations ocfs2_quota_operations = {
 	.write_info	= ocfs2_write_info,
 	.alloc_dquot	= ocfs2_alloc_dquot,
 	.destroy_dquot	= ocfs2_destroy_dquot,
+	.get_next_id	= ocfs2_get_next_id,
 };
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index 576b9a04873f..18451e0fab81 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -196,7 +196,7 @@ static int update_backups(struct inode * inode, u32 clusters, char *data)
 	for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) {
 		blkno = ocfs2_backup_super_blkno(inode->i_sb, i);
 		cluster = ocfs2_blocks_to_clusters(inode->i_sb, blkno);
-		if (cluster > clusters)
+		if (cluster >= clusters)
 			break;
 
 		ret = ocfs2_read_blocks_sync(osb, blkno, 1, &backup);
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 5d965e83bd43..13219ed73e1d 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -629,7 +629,8 @@ static struct attribute_group ocfs2_attr_group = {
 	.attrs = ocfs2_attrs,
 };
 
-static struct kset *ocfs2_kset;
+struct kset *ocfs2_kset;
+EXPORT_SYMBOL_GPL(ocfs2_kset);
 
 static void ocfs2_sysfs_exit(void)
 {
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index 66334a30cea8..f2dce10fae54 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -298,4 +298,6 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
 
+extern struct kset *ocfs2_kset;
+
 #endif  /* STACKGLUE_H */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index faa1365097bc..7db631e1c8b0 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -74,17 +74,12 @@
 #include "suballoc.h"
 
 #include "buffer_head_io.h"
+#include "filecheck.h"
 
 static struct kmem_cache *ocfs2_inode_cachep;
 struct kmem_cache *ocfs2_dquot_cachep;
 struct kmem_cache *ocfs2_qf_chunk_cachep;
 
-/* OCFS2 needs to schedule several different types of work which
- * require cluster locking, disk I/O, recovery waits, etc. Since these
- * types of work tend to be heavy we avoid using the kernel events
- * workqueue and schedule on our own. */
-struct workqueue_struct *ocfs2_wq = NULL;
-
 static struct dentry *ocfs2_debugfs_root;
 
 MODULE_AUTHOR("Oracle");
@@ -236,6 +231,7 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 	struct ocfs2_recovery_map *rm = osb->recovery_map;
 	struct ocfs2_orphan_scan *os = &osb->osb_orphan_scan;
 	int i, out = 0;
+	unsigned long flags;
 
 	out += snprintf(buf + out, len - out,
 			"%10s => Id: %-s  Uuid: %-s  Gen: 0x%X  Label: %-s\n",
@@ -271,14 +267,14 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 				cconn->cc_version.pv_minor);
 	}
 
-	spin_lock(&osb->dc_task_lock);
+	spin_lock_irqsave(&osb->dc_task_lock, flags);
 	out += snprintf(buf + out, len - out,
 			"%10s => Pid: %d  Count: %lu  WakeSeq: %lu  "
 			"WorkSeq: %lu\n", "DownCnvt",
 			(osb->dc_task ?  task_pid_nr(osb->dc_task) : -1),
 			osb->blocked_lock_count, osb->dc_wake_sequence,
 			osb->dc_work_sequence);
-	spin_unlock(&osb->dc_task_lock);
+	spin_unlock_irqrestore(&osb->dc_task_lock, flags);
 
 	spin_lock(&osb->osb_lock);
 	out += snprintf(buf + out, len - out, "%10s => Pid: %d  Nodes:",
@@ -1204,6 +1200,9 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	/* Start this when the mount is almost sure of being successful */
 	ocfs2_orphan_scan_start(osb);
 
+	/* Create filecheck sysfile /sys/fs/ocfs2/<devname>/filecheck */
+	ocfs2_filecheck_create_sysfs(sb);
+
 	return status;
 
 read_super_error:
@@ -1608,33 +1607,25 @@ static int __init ocfs2_init(void)
 	if (status < 0)
 		goto out2;
 
-	ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
-	if (!ocfs2_wq) {
-		status = -ENOMEM;
-		goto out3;
-	}
-
 	ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
 	if (!ocfs2_debugfs_root) {
 		status = -ENOMEM;
 		mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n");
-		goto out4;
+		goto out3;
 	}
 
 	ocfs2_set_locking_protocol();
 
 	status = register_quota_format(&ocfs2_quota_format);
 	if (status < 0)
-		goto out4;
+		goto out3;
 	status = register_filesystem(&ocfs2_fs_type);
 	if (!status)
 		return 0;
 
 	unregister_quota_format(&ocfs2_quota_format);
-out4:
-	destroy_workqueue(ocfs2_wq);
-	debugfs_remove(ocfs2_debugfs_root);
 out3:
+	debugfs_remove(ocfs2_debugfs_root);
 	ocfs2_free_mem_caches();
 out2:
 	exit_ocfs2_uptodate_cache();
@@ -1645,11 +1636,6 @@ out1:
 
 static void __exit ocfs2_exit(void)
 {
-	if (ocfs2_wq) {
-		flush_workqueue(ocfs2_wq);
-		destroy_workqueue(ocfs2_wq);
-	}
-
 	unregister_quota_format(&ocfs2_quota_format);
 
 	debugfs_remove(ocfs2_debugfs_root);
@@ -1667,6 +1653,7 @@ static void ocfs2_put_super(struct super_block *sb)
 
 	ocfs2_sync_blockdev(sb);
 	ocfs2_dismount_volume(sb, 0);
+	ocfs2_filecheck_remove_sysfs(sb);
 }
 
 static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -1739,8 +1726,8 @@ static void ocfs2_inode_init_once(void *data)
 	spin_lock_init(&oi->ip_lock);
 	ocfs2_extent_map_init(&oi->vfs_inode);
 	INIT_LIST_HEAD(&oi->ip_io_markers);
+	INIT_LIST_HEAD(&oi->ip_unwritten_list);
 	oi->ip_dir_start_lookup = 0;
-	mutex_init(&oi->ip_unaligned_aio);
 	init_rwsem(&oi->ip_alloc_sem);
 	init_rwsem(&oi->ip_xattr_sem);
 	mutex_init(&oi->ip_io_mutex);
@@ -2343,6 +2330,12 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	}
 	cleancache_init_shared_fs(sb);
 
+	osb->ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
+	if (!osb->ocfs2_wq) {
+		status = -ENOMEM;
+		mlog_errno(status);
+	}
+
 bail:
 	return status;
 }
@@ -2530,6 +2523,12 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
 {
 	/* This function assumes that the caller has the main osb resource */
 
+	/* ocfs2_initializer_super have already created this workqueue */
+	if (osb->ocfs2_wq) {
+		flush_workqueue(osb->ocfs2_wq);
+		destroy_workqueue(osb->ocfs2_wq);
+	}
+
 	ocfs2_free_slot_info(osb);
 
 	kfree(osb->osb_orphan_wipes);
diff --git a/fs/ocfs2/super.h b/fs/ocfs2/super.h
index b477d0b1c7b6..b023e4f3d740 100644
--- a/fs/ocfs2/super.h
+++ b/fs/ocfs2/super.h
@@ -26,8 +26,6 @@
 #ifndef OCFS2_SUPER_H
 #define OCFS2_SUPER_H
 
-extern struct workqueue_struct *ocfs2_wq;
-
 int ocfs2_publish_get_mount_state(struct ocfs2_super *osb,
 				  int node_num);
 
diff --git a/fs/open.c b/fs/open.c
index 55bdc75e2172..17cb6b1dab75 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -992,14 +992,12 @@ struct file *filp_open(const char *filename, int flags, umode_t mode)
 EXPORT_SYMBOL(filp_open);
 
 struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
-			    const char *filename, int flags)
+			    const char *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
-	int err = build_open_flags(flags, 0, &op);
+	int err = build_open_flags(flags, mode, &op);
 	if (err)
 		return ERR_PTR(err);
-	if (flags & O_CREAT)
-		return ERR_PTR(-EINVAL);
 	return do_file_open_root(dentry, mnt, filename, &op);
 }
 EXPORT_SYMBOL(file_open_root);
diff --git a/fs/orangefs/Kconfig b/fs/orangefs/Kconfig
new file mode 100644
index 000000000000..1554c02489de
--- /dev/null
+++ b/fs/orangefs/Kconfig
@@ -0,0 +1,6 @@
+config ORANGEFS_FS
+	tristate "ORANGEFS (Powered by PVFS) support"
+	select FS_POSIX_ACL
+	help
+	   Orange is a parallel file system designed for use on high end
+	   computing (HEC) systems.
diff --git a/fs/orangefs/Makefile b/fs/orangefs/Makefile
new file mode 100644
index 000000000000..a9d6a968fe6d
--- /dev/null
+++ b/fs/orangefs/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for the ORANGEFS filesystem.
+#
+
+obj-$(CONFIG_ORANGEFS_FS) += orangefs.o
+
+orangefs-objs := acl.o file.o orangefs-cache.o orangefs-utils.o xattr.o \
+		 dcache.o inode.o orangefs-sysfs.o orangefs-mod.o super.o \
+		 devorangefs-req.o namei.o symlink.o dir.o orangefs-bufmap.o \
+		 orangefs-debugfs.o waitqueue.o
diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c
new file mode 100644
index 000000000000..03f89dbb2512
--- /dev/null
+++ b/fs/orangefs/acl.c
@@ -0,0 +1,175 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+#include <linux/posix_acl_xattr.h>
+#include <linux/fs_struct.h>
+
+struct posix_acl *orangefs_get_acl(struct inode *inode, int type)
+{
+	struct posix_acl *acl;
+	int ret;
+	char *key = NULL, *value = NULL;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		key = ORANGEFS_XATTR_NAME_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		key = ORANGEFS_XATTR_NAME_ACL_DEFAULT;
+		break;
+	default:
+		gossip_err("orangefs_get_acl: bogus value of type %d\n", type);
+		return ERR_PTR(-EINVAL);
+	}
+	/*
+	 * Rather than incurring a network call just to determine the exact
+	 * length of the attribute, I just allocate a max length to save on
+	 * the network call. Conceivably, we could pass NULL to
+	 * orangefs_inode_getxattr() to probe the length of the value, but
+	 * I don't do that for now.
+	 */
+	value = kmalloc(ORANGEFS_MAX_XATTR_VALUELEN, GFP_KERNEL);
+	if (value == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	gossip_debug(GOSSIP_ACL_DEBUG,
+		     "inode %pU, key %s, type %d\n",
+		     get_khandle_from_ino(inode),
+		     key,
+		     type);
+	ret = orangefs_inode_getxattr(inode,
+				   "",
+				   key,
+				   value,
+				   ORANGEFS_MAX_XATTR_VALUELEN);
+	/* if the key exists, convert it to an in-memory rep */
+	if (ret > 0) {
+		acl = posix_acl_from_xattr(&init_user_ns, value, ret);
+	} else if (ret == -ENODATA || ret == -ENOSYS) {
+		acl = NULL;
+	} else {
+		gossip_err("inode %pU retrieving acl's failed with error %d\n",
+			   get_khandle_from_ino(inode),
+			   ret);
+		acl = ERR_PTR(ret);
+	}
+	/* kfree(NULL) is safe, so don't worry if value ever got used */
+	kfree(value);
+	return acl;
+}
+
+int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	int error = 0;
+	void *value = NULL;
+	size_t size = 0;
+	const char *name = NULL;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = ORANGEFS_XATTR_NAME_ACL_ACCESS;
+		if (acl) {
+			umode_t mode = inode->i_mode;
+			/*
+			 * can we represent this with the traditional file
+			 * mode permission bits?
+			 */
+			error = posix_acl_equiv_mode(acl, &mode);
+			if (error < 0) {
+				gossip_err("%s: posix_acl_equiv_mode err: %d\n",
+					   __func__,
+					   error);
+				return error;
+			}
+
+			if (inode->i_mode != mode)
+				SetModeFlag(orangefs_inode);
+			inode->i_mode = mode;
+			mark_inode_dirty_sync(inode);
+			if (error == 0)
+				acl = NULL;
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = ORANGEFS_XATTR_NAME_ACL_DEFAULT;
+		break;
+	default:
+		gossip_err("%s: invalid type %d!\n", __func__, type);
+		return -EINVAL;
+	}
+
+	gossip_debug(GOSSIP_ACL_DEBUG,
+		     "%s: inode %pU, key %s type %d\n",
+		     __func__, get_khandle_from_ino(inode),
+		     name,
+		     type);
+
+	if (acl) {
+		size = posix_acl_xattr_size(acl->a_count);
+		value = kmalloc(size, GFP_KERNEL);
+		if (!value)
+			return -ENOMEM;
+
+		error = posix_acl_to_xattr(&init_user_ns, acl, value, size);
+		if (error < 0)
+			goto out;
+	}
+
+	gossip_debug(GOSSIP_ACL_DEBUG,
+		     "%s: name %s, value %p, size %zd, acl %p\n",
+		     __func__, name, value, size, acl);
+	/*
+	 * Go ahead and set the extended attribute now. NOTE: Suppose acl
+	 * was NULL, then value will be NULL and size will be 0 and that
+	 * will xlate to a removexattr. However, we don't want removexattr
+	 * complain if attributes does not exist.
+	 */
+	error = orangefs_inode_setxattr(inode, "", name, value, size, 0);
+
+out:
+	kfree(value);
+	if (!error)
+		set_cached_acl(inode, type, acl);
+	return error;
+}
+
+int orangefs_init_acl(struct inode *inode, struct inode *dir)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct posix_acl *default_acl, *acl;
+	umode_t mode = inode->i_mode;
+	int error = 0;
+
+	ClearModeFlag(orangefs_inode);
+
+	error = posix_acl_create(dir, &mode, &default_acl, &acl);
+	if (error)
+		return error;
+
+	if (default_acl) {
+		error = orangefs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+		posix_acl_release(default_acl);
+	}
+
+	if (acl) {
+		if (!error)
+			error = orangefs_set_acl(inode, acl, ACL_TYPE_ACCESS);
+		posix_acl_release(acl);
+	}
+
+	/* If mode of the inode was changed, then do a forcible ->setattr */
+	if (mode != inode->i_mode) {
+		SetModeFlag(orangefs_inode);
+		inode->i_mode = mode;
+		orangefs_flush_inode(inode);
+	}
+
+	return error;
+}
diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c
new file mode 100644
index 000000000000..5dfc4f3cfe68
--- /dev/null
+++ b/fs/orangefs/dcache.c
@@ -0,0 +1,138 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Implementation of dentry (directory cache) functions.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+
+/* Returns 1 if dentry can still be trusted, else 0. */
+static int orangefs_revalidate_lookup(struct dentry *dentry)
+{
+	struct dentry *parent_dentry = dget_parent(dentry);
+	struct inode *parent_inode = parent_dentry->d_inode;
+	struct orangefs_inode_s *parent = ORANGEFS_I(parent_inode);
+	struct inode *inode = dentry->d_inode;
+	struct orangefs_kernel_op_s *new_op;
+	int ret = 0;
+	int err = 0;
+
+	gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: attempting lookup.\n", __func__);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_LOOKUP);
+	if (!new_op)
+		goto out_put_parent;
+
+	new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW;
+	new_op->upcall.req.lookup.parent_refn = parent->refn;
+	strncpy(new_op->upcall.req.lookup.d_name,
+		dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+
+	gossip_debug(GOSSIP_DCACHE_DEBUG,
+		     "%s:%s:%d interrupt flag [%d]\n",
+		     __FILE__,
+		     __func__,
+		     __LINE__,
+		     get_interruptible_flag(parent_inode));
+
+	err = service_operation(new_op, "orangefs_lookup",
+			get_interruptible_flag(parent_inode));
+
+	/* Positive dentry: reject if error or not the same inode. */
+	if (inode) {
+		if (err) {
+			gossip_debug(GOSSIP_DCACHE_DEBUG,
+			    "%s:%s:%d lookup failure.\n",
+			    __FILE__, __func__, __LINE__);
+			goto out_drop;
+		}
+		if (!match_handle(new_op->downcall.resp.lookup.refn.khandle,
+		    inode)) {
+			gossip_debug(GOSSIP_DCACHE_DEBUG,
+			    "%s:%s:%d no match.\n",
+			    __FILE__, __func__, __LINE__);
+			goto out_drop;
+		}
+
+	/* Negative dentry: reject if success or error other than ENOENT. */
+	} else {
+		gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: negative dentry.\n",
+		    __func__);
+		if (!err || err != -ENOENT) {
+			if (new_op->downcall.status != 0)
+				gossip_debug(GOSSIP_DCACHE_DEBUG,
+				    "%s:%s:%d lookup failure.\n",
+				    __FILE__, __func__, __LINE__);
+			goto out_drop;
+		}
+	}
+
+	ret = 1;
+out_release_op:
+	op_release(new_op);
+out_put_parent:
+	dput(parent_dentry);
+	return ret;
+out_drop:
+	gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d revalidate failed\n",
+	    __FILE__, __func__, __LINE__);
+	goto out_release_op;
+}
+
+/*
+ * Verify that dentry is valid.
+ *
+ * Should return 1 if dentry can still be trusted, else 0.
+ */
+static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	int ret;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: called on dentry %p.\n",
+		     __func__, dentry);
+
+	/* skip root handle lookups. */
+	if (dentry->d_inode && is_root_handle(dentry->d_inode))
+		return 1;
+
+	/*
+	 * If this passes, the positive dentry still exists or the negative
+	 * dentry still does not exist.
+	 */
+	if (!orangefs_revalidate_lookup(dentry))
+		return 0;
+
+	/* We do not need to continue with negative dentries. */
+	if (!dentry->d_inode)
+		goto out;
+
+	/* Now we must perform a getattr to validate the inode contents. */
+
+	ret = orangefs_inode_check_changed(dentry->d_inode);
+	if (ret < 0) {
+		gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d getattr failure.\n",
+		    __FILE__, __func__, __LINE__);
+		return 0;
+	}
+	if (ret == 0)
+		return 0;
+
+out:
+	gossip_debug(GOSSIP_DCACHE_DEBUG,
+	    "%s: negative dentry or positive dentry and inode valid.\n",
+	    __func__);
+	return 1;
+}
+
+const struct dentry_operations orangefs_dentry_operations = {
+	.d_revalidate = orangefs_d_revalidate,
+};
diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c
new file mode 100644
index 000000000000..db170beba797
--- /dev/null
+++ b/fs/orangefs/devorangefs-req.c
@@ -0,0 +1,943 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * Changes by Acxiom Corporation to add protocol version to kernel
+ * communication, Copyright Acxiom Corporation, 2005.
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-dev-proto.h"
+#include "orangefs-bufmap.h"
+
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+
+/* this file implements the /dev/pvfs2-req device node */
+
+static int open_access_count;
+
+#define DUMP_DEVICE_ERROR()                                                   \
+do {                                                                          \
+	gossip_err("*****************************************************\n");\
+	gossip_err("ORANGEFS Device Error:  You cannot open the device file ");  \
+	gossip_err("\n/dev/%s more than once.  Please make sure that\nthere " \
+		   "are no ", ORANGEFS_REQDEVICE_NAME);                          \
+	gossip_err("instances of a program using this device\ncurrently "     \
+		   "running. (You must verify this!)\n");                     \
+	gossip_err("For example, you can use the lsof program as follows:\n");\
+	gossip_err("'lsof | grep %s' (run this as root)\n",                   \
+		   ORANGEFS_REQDEVICE_NAME);                                     \
+	gossip_err("  open_access_count = %d\n", open_access_count);          \
+	gossip_err("*****************************************************\n");\
+} while (0)
+
+static int hash_func(__u64 tag, int table_size)
+{
+	return do_div(tag, (unsigned int)table_size);
+}
+
+static void orangefs_devreq_add_op(struct orangefs_kernel_op_s *op)
+{
+	int index = hash_func(op->tag, hash_table_size);
+
+	list_add_tail(&op->list, &htable_ops_in_progress[index]);
+}
+
+/*
+ * find the op with this tag and remove it from the in progress
+ * hash table.
+ */
+static struct orangefs_kernel_op_s *orangefs_devreq_remove_op(__u64 tag)
+{
+	struct orangefs_kernel_op_s *op, *next;
+	int index;
+
+	index = hash_func(tag, hash_table_size);
+
+	spin_lock(&htable_ops_in_progress_lock);
+	list_for_each_entry_safe(op,
+				 next,
+				 &htable_ops_in_progress[index],
+				 list) {
+		if (op->tag == tag && !op_state_purged(op) &&
+		    !op_state_given_up(op)) {
+			list_del_init(&op->list);
+			spin_unlock(&htable_ops_in_progress_lock);
+			return op;
+		}
+	}
+
+	spin_unlock(&htable_ops_in_progress_lock);
+	return NULL;
+}
+
+/* Returns whether any FS are still pending remounted */
+static int mark_all_pending_mounts(void)
+{
+	int unmounted = 1;
+	struct orangefs_sb_info_s *orangefs_sb = NULL;
+
+	spin_lock(&orangefs_superblocks_lock);
+	list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) {
+		/* All of these file system require a remount */
+		orangefs_sb->mount_pending = 1;
+		unmounted = 0;
+	}
+	spin_unlock(&orangefs_superblocks_lock);
+	return unmounted;
+}
+
+/*
+ * Determine if a given file system needs to be remounted or not
+ *  Returns -1 on error
+ *           0 if already mounted
+ *           1 if needs remount
+ */
+static int fs_mount_pending(__s32 fsid)
+{
+	int mount_pending = -1;
+	struct orangefs_sb_info_s *orangefs_sb = NULL;
+
+	spin_lock(&orangefs_superblocks_lock);
+	list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) {
+		if (orangefs_sb->fs_id == fsid) {
+			mount_pending = orangefs_sb->mount_pending;
+			break;
+		}
+	}
+	spin_unlock(&orangefs_superblocks_lock);
+	return mount_pending;
+}
+
+static int orangefs_devreq_open(struct inode *inode, struct file *file)
+{
+	int ret = -EINVAL;
+
+	if (!(file->f_flags & O_NONBLOCK)) {
+		gossip_err("%s: device cannot be opened in blocking mode\n",
+			   __func__);
+		goto out;
+	}
+	ret = -EACCES;
+	gossip_debug(GOSSIP_DEV_DEBUG, "client-core: opening device\n");
+	mutex_lock(&devreq_mutex);
+
+	if (open_access_count == 0) {
+		open_access_count = 1;
+		ret = 0;
+	} else {
+		DUMP_DEVICE_ERROR();
+	}
+	mutex_unlock(&devreq_mutex);
+
+out:
+
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "pvfs2-client-core: open device complete (ret = %d)\n",
+		     ret);
+	return ret;
+}
+
+/* Function for read() callers into the device */
+static ssize_t orangefs_devreq_read(struct file *file,
+				 char __user *buf,
+				 size_t count, loff_t *offset)
+{
+	struct orangefs_kernel_op_s *op, *temp;
+	__s32 proto_ver = ORANGEFS_KERNEL_PROTO_VERSION;
+	static __s32 magic = ORANGEFS_DEVREQ_MAGIC;
+	struct orangefs_kernel_op_s *cur_op = NULL;
+	unsigned long ret;
+
+	/* We do not support blocking IO. */
+	if (!(file->f_flags & O_NONBLOCK)) {
+		gossip_err("%s: blocking read from client-core.\n",
+			   __func__);
+		return -EINVAL;
+	}
+
+	/*
+	 * The client will do an ioctl to find MAX_DEV_REQ_UPSIZE, then
+	 * always read with that size buffer.
+	 */
+	if (count != MAX_DEV_REQ_UPSIZE) {
+		gossip_err("orangefs: client-core tried to read wrong size\n");
+		return -EINVAL;
+	}
+
+restart:
+	/* Get next op (if any) from top of list. */
+	spin_lock(&orangefs_request_list_lock);
+	list_for_each_entry_safe(op, temp, &orangefs_request_list, list) {
+		__s32 fsid;
+		/* This lock is held past the end of the loop when we break. */
+		spin_lock(&op->lock);
+		if (unlikely(op_state_purged(op) || op_state_given_up(op))) {
+			spin_unlock(&op->lock);
+			continue;
+		}
+
+		fsid = fsid_of_op(op);
+		if (fsid != ORANGEFS_FS_ID_NULL) {
+			int ret;
+			/* Skip ops whose filesystem needs to be mounted. */
+			ret = fs_mount_pending(fsid);
+			if (ret == 1) {
+				gossip_debug(GOSSIP_DEV_DEBUG,
+				    "%s: mount pending, skipping op tag "
+				    "%llu %s\n",
+				    __func__,
+				    llu(op->tag),
+				    get_opname_string(op));
+				spin_unlock(&op->lock);
+				continue;
+			/*
+			 * Skip ops whose filesystem we don't know about unless
+			 * it is being mounted.
+			 */
+			/* XXX: is there a better way to detect this? */
+			} else if (ret == -1 &&
+				   !(op->upcall.type ==
+					ORANGEFS_VFS_OP_FS_MOUNT ||
+				     op->upcall.type ==
+					ORANGEFS_VFS_OP_GETATTR)) {
+				gossip_debug(GOSSIP_DEV_DEBUG,
+				    "orangefs: skipping op tag %llu %s\n",
+				    llu(op->tag), get_opname_string(op));
+				gossip_err(
+				    "orangefs: ERROR: fs_mount_pending %d\n",
+				    fsid);
+				spin_unlock(&op->lock);
+				continue;
+			}
+		}
+		/*
+		 * Either this op does not pertain to a filesystem, is mounting
+		 * a filesystem, or pertains to a mounted filesystem. Let it
+		 * through.
+		 */
+		cur_op = op;
+		break;
+	}
+
+	/*
+	 * At this point we either have a valid op and can continue or have not
+	 * found an op and must ask the client to try again later.
+	 */
+	if (!cur_op) {
+		spin_unlock(&orangefs_request_list_lock);
+		return -EAGAIN;
+	}
+
+	gossip_debug(GOSSIP_DEV_DEBUG, "%s: reading op tag %llu %s\n",
+		     __func__,
+		     llu(cur_op->tag),
+		     get_opname_string(cur_op));
+
+	/*
+	 * Such an op should never be on the list in the first place. If so, we
+	 * will abort.
+	 */
+	if (op_state_in_progress(cur_op) || op_state_serviced(cur_op)) {
+		gossip_err("orangefs: ERROR: Current op already queued.\n");
+		list_del_init(&cur_op->list);
+		spin_unlock(&cur_op->lock);
+		spin_unlock(&orangefs_request_list_lock);
+		return -EAGAIN;
+	}
+
+	list_del_init(&cur_op->list);
+	spin_unlock(&orangefs_request_list_lock);
+
+	spin_unlock(&cur_op->lock);
+
+	/* Push the upcall out. */
+	ret = copy_to_user(buf, &proto_ver, sizeof(__s32));
+	if (ret != 0)
+		goto error;
+	ret = copy_to_user(buf+sizeof(__s32), &magic, sizeof(__s32));
+	if (ret != 0)
+		goto error;
+	ret = copy_to_user(buf+2 * sizeof(__s32), &cur_op->tag, sizeof(__u64));
+	if (ret != 0)
+		goto error;
+	ret = copy_to_user(buf+2*sizeof(__s32)+sizeof(__u64), &cur_op->upcall,
+			   sizeof(struct orangefs_upcall_s));
+	if (ret != 0)
+		goto error;
+
+	spin_lock(&htable_ops_in_progress_lock);
+	spin_lock(&cur_op->lock);
+	if (unlikely(op_state_given_up(cur_op))) {
+		spin_unlock(&cur_op->lock);
+		spin_unlock(&htable_ops_in_progress_lock);
+		complete(&cur_op->waitq);
+		goto restart;
+	}
+
+	/*
+	 * Set the operation to be in progress and move it between lists since
+	 * it has been sent to the client.
+	 */
+	set_op_state_inprogress(cur_op);
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "%s: 1 op:%s: op_state:%d: process:%s:\n",
+		     __func__,
+		     get_opname_string(cur_op),
+		     cur_op->op_state,
+		     current->comm);
+	orangefs_devreq_add_op(cur_op);
+	spin_unlock(&cur_op->lock);
+	spin_unlock(&htable_ops_in_progress_lock);
+
+	/* The client only asks to read one size buffer. */
+	return MAX_DEV_REQ_UPSIZE;
+error:
+	/*
+	 * We were unable to copy the op data to the client. Put the op back in
+	 * list. If client has crashed, the op will be purged later when the
+	 * device is released.
+	 */
+	gossip_err("orangefs: Failed to copy data to user space\n");
+	spin_lock(&orangefs_request_list_lock);
+	spin_lock(&cur_op->lock);
+	if (likely(!op_state_given_up(cur_op))) {
+		set_op_state_waiting(cur_op);
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: 2 op:%s: op_state:%d: process:%s:\n",
+			     __func__,
+			     get_opname_string(cur_op),
+			     cur_op->op_state,
+			     current->comm);
+		list_add(&cur_op->list, &orangefs_request_list);
+		spin_unlock(&cur_op->lock);
+	} else {
+		spin_unlock(&cur_op->lock);
+		complete(&cur_op->waitq);
+	}
+	spin_unlock(&orangefs_request_list_lock);
+	return -EFAULT;
+}
+
+/*
+ * Function for writev() callers into the device.
+ *
+ * Userspace should have written:
+ *  - __u32 version
+ *  - __u32 magic
+ *  - __u64 tag
+ *  - struct orangefs_downcall_s
+ *  - trailer buffer (in the case of READDIR operations)
+ */
+static ssize_t orangefs_devreq_write_iter(struct kiocb *iocb,
+				      struct iov_iter *iter)
+{
+	ssize_t ret;
+	struct orangefs_kernel_op_s *op = NULL;
+	struct {
+		__u32 version;
+		__u32 magic;
+		__u64 tag;
+	} head;
+	int total = ret = iov_iter_count(iter);
+	int n;
+	int downcall_size = sizeof(struct orangefs_downcall_s);
+	int head_size = sizeof(head);
+
+	gossip_debug(GOSSIP_DEV_DEBUG, "%s: total:%d: ret:%zd:\n",
+		     __func__,
+		     total,
+		     ret);
+
+        if (total < MAX_DEV_REQ_DOWNSIZE) {
+		gossip_err("%s: total:%d: must be at least:%u:\n",
+			   __func__,
+			   total,
+			   (unsigned int) MAX_DEV_REQ_DOWNSIZE);
+		return -EFAULT;
+	}
+     
+	n = copy_from_iter(&head, head_size, iter);
+	if (n < head_size) {
+		gossip_err("%s: failed to copy head.\n", __func__);
+		return -EFAULT;
+	}
+
+	if (head.version < ORANGEFS_MINIMUM_USERSPACE_VERSION) {
+		gossip_err("%s: userspace claims version"
+			   "%d, minimum version required: %d.\n",
+			   __func__,
+			   head.version,
+			   ORANGEFS_MINIMUM_USERSPACE_VERSION);
+		return -EPROTO;
+	}
+
+	if (head.magic != ORANGEFS_DEVREQ_MAGIC) {
+		gossip_err("Error: Device magic number does not match.\n");
+		return -EPROTO;
+	}
+
+	/* remove the op from the in progress hash table */
+	op = orangefs_devreq_remove_op(head.tag);
+	if (!op) {
+		gossip_err("WARNING: No one's waiting for tag %llu\n",
+			   llu(head.tag));
+		return ret;
+	}
+
+	n = copy_from_iter(&op->downcall, downcall_size, iter);
+	if (n != downcall_size) {
+		gossip_err("%s: failed to copy downcall.\n", __func__);
+		goto Efault;
+	}
+
+	if (op->downcall.status)
+		goto wakeup;
+
+	/*
+	 * We've successfully peeled off the head and the downcall. 
+	 * Something has gone awry if total doesn't equal the
+	 * sum of head_size, downcall_size and trailer_size.
+	 */
+	if ((head_size + downcall_size + op->downcall.trailer_size) != total) {
+		gossip_err("%s: funky write, head_size:%d"
+			   ": downcall_size:%d: trailer_size:%lld"
+			   ": total size:%d:\n",
+			   __func__,
+			   head_size,
+			   downcall_size,
+			   op->downcall.trailer_size,
+			   total);
+		goto Efault;
+	}
+
+	/* Only READDIR operations should have trailers. */
+	if ((op->downcall.type != ORANGEFS_VFS_OP_READDIR) &&
+	    (op->downcall.trailer_size != 0)) {
+		gossip_err("%s: %x operation with trailer.",
+			   __func__,
+			   op->downcall.type);
+		goto Efault;
+	}
+
+	/* READDIR operations should always have trailers. */
+	if ((op->downcall.type == ORANGEFS_VFS_OP_READDIR) &&
+	    (op->downcall.trailer_size == 0)) {
+		gossip_err("%s: %x operation with no trailer.",
+			   __func__,
+			   op->downcall.type);
+		goto Efault;
+	}
+
+	if (op->downcall.type != ORANGEFS_VFS_OP_READDIR)
+		goto wakeup;
+
+	op->downcall.trailer_buf =
+		vmalloc(op->downcall.trailer_size);
+	if (op->downcall.trailer_buf == NULL) {
+		gossip_err("%s: failed trailer vmalloc.\n",
+			   __func__);
+		goto Enomem;
+	}
+	memset(op->downcall.trailer_buf, 0, op->downcall.trailer_size);
+	n = copy_from_iter(op->downcall.trailer_buf,
+			   op->downcall.trailer_size,
+			   iter);
+	if (n != op->downcall.trailer_size) {
+		gossip_err("%s: failed to copy trailer.\n", __func__);
+		vfree(op->downcall.trailer_buf);
+		goto Efault;
+	}
+
+wakeup:
+	/*
+	 * Return to vfs waitqueue, and back to service_operation
+	 * through wait_for_matching_downcall. 
+	 */
+	spin_lock(&op->lock);
+	if (unlikely(op_is_cancel(op))) {
+		spin_unlock(&op->lock);
+		put_cancel(op);
+	} else if (unlikely(op_state_given_up(op))) {
+		spin_unlock(&op->lock);
+		complete(&op->waitq);
+	} else {
+		set_op_state_serviced(op);
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: op:%s: op_state:%d: process:%s:\n",
+			     __func__,
+			     get_opname_string(op),
+			     op->op_state,
+			     current->comm);
+		spin_unlock(&op->lock);
+	}
+	return ret;
+
+Efault:
+	op->downcall.status = -(ORANGEFS_ERROR_BIT | 9);
+	ret = -EFAULT;
+	goto wakeup;
+
+Enomem:
+	op->downcall.status = -(ORANGEFS_ERROR_BIT | 8);
+	ret = -ENOMEM;
+	goto wakeup;
+}
+
+/*
+ * NOTE: gets called when the last reference to this device is dropped.
+ * Using the open_access_count variable, we enforce a reference count
+ * on this file so that it can be opened by only one process at a time.
+ * the devreq_mutex is used to make sure all i/o has completed
+ * before we call orangefs_bufmap_finalize, and similar such tricky
+ * situations
+ */
+static int orangefs_devreq_release(struct inode *inode, struct file *file)
+{
+	int unmounted = 0;
+
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "%s:pvfs2-client-core: exiting, closing device\n",
+		     __func__);
+
+	mutex_lock(&devreq_mutex);
+	orangefs_bufmap_finalize();
+
+	open_access_count = -1;
+
+	unmounted = mark_all_pending_mounts();
+	gossip_debug(GOSSIP_DEV_DEBUG, "ORANGEFS Device Close: Filesystem(s) %s\n",
+		     (unmounted ? "UNMOUNTED" : "MOUNTED"));
+
+	purge_waiting_ops();
+	purge_inprogress_ops();
+
+	orangefs_bufmap_run_down();
+
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "pvfs2-client-core: device close complete\n");
+	open_access_count = 0;
+	mutex_unlock(&devreq_mutex);
+	return 0;
+}
+
+int is_daemon_in_service(void)
+{
+	int in_service;
+
+	/*
+	 * What this function does is checks if client-core is alive
+	 * based on the access count we maintain on the device.
+	 */
+	mutex_lock(&devreq_mutex);
+	in_service = open_access_count == 1 ? 0 : -EIO;
+	mutex_unlock(&devreq_mutex);
+	return in_service;
+}
+
+bool __is_daemon_in_service(void)
+{
+	return open_access_count == 1;
+}
+
+static inline long check_ioctl_command(unsigned int command)
+{
+	/* Check for valid ioctl codes */
+	if (_IOC_TYPE(command) != ORANGEFS_DEV_MAGIC) {
+		gossip_err("device ioctl magic numbers don't match! Did you rebuild pvfs2-client-core/libpvfs2? [cmd %x, magic %x != %x]\n",
+			command,
+			_IOC_TYPE(command),
+			ORANGEFS_DEV_MAGIC);
+		return -EINVAL;
+	}
+	/* and valid ioctl commands */
+	if (_IOC_NR(command) >= ORANGEFS_DEV_MAXNR || _IOC_NR(command) <= 0) {
+		gossip_err("Invalid ioctl command number [%d >= %d]\n",
+			   _IOC_NR(command), ORANGEFS_DEV_MAXNR);
+		return -ENOIOCTLCMD;
+	}
+	return 0;
+}
+
+static long dispatch_ioctl_command(unsigned int command, unsigned long arg)
+{
+	static __s32 magic = ORANGEFS_DEVREQ_MAGIC;
+	static __s32 max_up_size = MAX_DEV_REQ_UPSIZE;
+	static __s32 max_down_size = MAX_DEV_REQ_DOWNSIZE;
+	struct ORANGEFS_dev_map_desc user_desc;
+	int ret = 0;
+	struct dev_mask_info_s mask_info = { 0 };
+	struct dev_mask2_info_s mask2_info = { 0, 0 };
+	int upstream_kmod = 1;
+	struct orangefs_sb_info_s *orangefs_sb;
+
+	/* mtmoore: add locking here */
+
+	switch (command) {
+	case ORANGEFS_DEV_GET_MAGIC:
+		return ((put_user(magic, (__s32 __user *) arg) == -EFAULT) ?
+			-EIO :
+			0);
+	case ORANGEFS_DEV_GET_MAX_UPSIZE:
+		return ((put_user(max_up_size,
+				  (__s32 __user *) arg) == -EFAULT) ?
+					-EIO :
+					0);
+	case ORANGEFS_DEV_GET_MAX_DOWNSIZE:
+		return ((put_user(max_down_size,
+				  (__s32 __user *) arg) == -EFAULT) ?
+					-EIO :
+					0);
+	case ORANGEFS_DEV_MAP:
+		ret = copy_from_user(&user_desc,
+				     (struct ORANGEFS_dev_map_desc __user *)
+				     arg,
+				     sizeof(struct ORANGEFS_dev_map_desc));
+		/* WTF -EIO and not -EFAULT? */
+		return ret ? -EIO : orangefs_bufmap_initialize(&user_desc);
+	case ORANGEFS_DEV_REMOUNT_ALL:
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: got ORANGEFS_DEV_REMOUNT_ALL\n",
+			     __func__);
+
+		/*
+		 * remount all mounted orangefs volumes to regain the lost
+		 * dynamic mount tables (if any) -- NOTE: this is done
+		 * without keeping the superblock list locked due to the
+		 * upcall/downcall waiting.  also, the request mutex is
+		 * used to ensure that no operations will be serviced until
+		 * all of the remounts are serviced (to avoid ops between
+		 * mounts to fail)
+		 */
+		ret = mutex_lock_interruptible(&request_mutex);
+		if (ret < 0)
+			return ret;
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: priority remount in progress\n",
+			     __func__);
+		spin_lock(&orangefs_superblocks_lock);
+		list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) {
+			/*
+			 * We have to drop the spinlock, so entries can be
+			 * removed.  They can't be freed, though, so we just
+			 * keep the forward pointers and zero the back ones -
+			 * that way we can get to the rest of the list.
+			 */
+			if (!orangefs_sb->list.prev)
+				continue;
+			gossip_debug(GOSSIP_DEV_DEBUG,
+				     "%s: Remounting SB %p\n",
+				     __func__,
+				     orangefs_sb);
+
+			spin_unlock(&orangefs_superblocks_lock);
+			ret = orangefs_remount(orangefs_sb);
+			spin_lock(&orangefs_superblocks_lock);
+			if (ret) {
+				gossip_debug(GOSSIP_DEV_DEBUG,
+					     "SB %p remount failed\n",
+					     orangefs_sb);
+				break;
+			}
+		}
+		spin_unlock(&orangefs_superblocks_lock);
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: priority remount complete\n",
+			     __func__);
+		mutex_unlock(&request_mutex);
+		return ret;
+
+	case ORANGEFS_DEV_UPSTREAM:
+		ret = copy_to_user((void __user *)arg,
+				    &upstream_kmod,
+				    sizeof(upstream_kmod));
+
+		if (ret != 0)
+			return -EIO;
+		else
+			return ret;
+
+	case ORANGEFS_DEV_CLIENT_MASK:
+		ret = copy_from_user(&mask2_info,
+				     (void __user *)arg,
+				     sizeof(struct dev_mask2_info_s));
+
+		if (ret != 0)
+			return -EIO;
+
+		client_debug_mask.mask1 = mask2_info.mask1_value;
+		client_debug_mask.mask2 = mask2_info.mask2_value;
+
+		pr_info("%s: client debug mask has been been received "
+			":%llx: :%llx:\n",
+			__func__,
+			(unsigned long long)client_debug_mask.mask1,
+			(unsigned long long)client_debug_mask.mask2);
+
+		return ret;
+
+	case ORANGEFS_DEV_CLIENT_STRING:
+		ret = copy_from_user(&client_debug_array_string,
+				     (void __user *)arg,
+				     ORANGEFS_MAX_DEBUG_STRING_LEN);
+		/*
+		 * The real client-core makes an effort to ensure
+		 * that actual strings that aren't too long to fit in
+		 * this buffer is what we get here. We're going to use
+		 * string functions on the stuff we got, so we'll make
+		 * this extra effort to try and keep from
+		 * flowing out of this buffer when we use the string
+		 * functions, even if somehow the stuff we end up
+		 * with here is garbage.
+		 */
+		client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN - 1] =
+			'\0';
+		
+		if (ret != 0) {
+			pr_info("%s: CLIENT_STRING: copy_from_user failed\n",
+				__func__);
+			return -EIO;
+		}
+
+		pr_info("%s: client debug array string has been received.\n",
+			__func__);
+
+		if (!help_string_initialized) {
+
+			/* Free the "we don't know yet" default string... */
+			kfree(debug_help_string);
+
+			/* build a proper debug help string */
+			if (orangefs_prepare_debugfs_help_string(0)) {
+				gossip_err("%s: no debug help string \n",
+					   __func__);
+				return -EIO;
+			}
+
+			/* Replace the boilerplate boot-time debug-help file. */
+			debugfs_remove(help_file_dentry);
+
+			help_file_dentry =
+				debugfs_create_file(
+					ORANGEFS_KMOD_DEBUG_HELP_FILE,
+					0444,
+					debug_dir,
+					debug_help_string,
+					&debug_help_fops);
+
+			if (!help_file_dentry) {
+				gossip_err("%s: debugfs_create_file failed for"
+					   " :%s:!\n",
+					   __func__,
+					   ORANGEFS_KMOD_DEBUG_HELP_FILE);
+				return -EIO;
+			}
+		}
+
+		debug_mask_to_string(&client_debug_mask, 1);
+
+		debugfs_remove(client_debug_dentry);
+
+		orangefs_client_debug_init();
+
+		help_string_initialized++;
+
+		return ret;
+
+	case ORANGEFS_DEV_DEBUG:
+		ret = copy_from_user(&mask_info,
+				     (void __user *)arg,
+				     sizeof(mask_info));
+
+		if (ret != 0)
+			return -EIO;
+
+		if (mask_info.mask_type == KERNEL_MASK) {
+			if ((mask_info.mask_value == 0)
+			    && (kernel_mask_set_mod_init)) {
+				/*
+				 * the kernel debug mask was set when the
+				 * kernel module was loaded; don't override
+				 * it if the client-core was started without
+				 * a value for ORANGEFS_KMODMASK.
+				 */
+				return 0;
+			}
+			debug_mask_to_string(&mask_info.mask_value,
+					     mask_info.mask_type);
+			gossip_debug_mask = mask_info.mask_value;
+			pr_info("%s: kernel debug mask has been modified to "
+				":%s: :%llx:\n",
+				__func__,
+				kernel_debug_string,
+				(unsigned long long)gossip_debug_mask);
+		} else if (mask_info.mask_type == CLIENT_MASK) {
+			debug_mask_to_string(&mask_info.mask_value,
+					     mask_info.mask_type);
+			pr_info("%s: client debug mask has been modified to"
+				":%s: :%llx:\n",
+				__func__,
+				client_debug_string,
+				llu(mask_info.mask_value));
+		} else {
+			gossip_lerr("Invalid mask type....\n");
+			return -EINVAL;
+		}
+
+		return ret;
+
+	default:
+		return -ENOIOCTLCMD;
+	}
+	return -ENOIOCTLCMD;
+}
+
+static long orangefs_devreq_ioctl(struct file *file,
+			       unsigned int command, unsigned long arg)
+{
+	long ret;
+
+	/* Check for properly constructed commands */
+	ret = check_ioctl_command(command);
+	if (ret < 0)
+		return (int)ret;
+
+	return (int)dispatch_ioctl_command(command, arg);
+}
+
+#ifdef CONFIG_COMPAT		/* CONFIG_COMPAT is in .config */
+
+/*  Compat structure for the ORANGEFS_DEV_MAP ioctl */
+struct ORANGEFS_dev_map_desc32 {
+	compat_uptr_t ptr;
+	__s32 total_size;
+	__s32 size;
+	__s32 count;
+};
+
+static unsigned long translate_dev_map26(unsigned long args, long *error)
+{
+	struct ORANGEFS_dev_map_desc32 __user *p32 = (void __user *)args;
+	/*
+	 * Depending on the architecture, allocate some space on the
+	 * user-call-stack based on our expected layout.
+	 */
+	struct ORANGEFS_dev_map_desc __user *p =
+	    compat_alloc_user_space(sizeof(*p));
+	compat_uptr_t addr;
+
+	*error = 0;
+	/* get the ptr from the 32 bit user-space */
+	if (get_user(addr, &p32->ptr))
+		goto err;
+	/* try to put that into a 64-bit layout */
+	if (put_user(compat_ptr(addr), &p->ptr))
+		goto err;
+	/* copy the remaining fields */
+	if (copy_in_user(&p->total_size, &p32->total_size, sizeof(__s32)))
+		goto err;
+	if (copy_in_user(&p->size, &p32->size, sizeof(__s32)))
+		goto err;
+	if (copy_in_user(&p->count, &p32->count, sizeof(__s32)))
+		goto err;
+	return (unsigned long)p;
+err:
+	*error = -EFAULT;
+	return 0;
+}
+
+/*
+ * 32 bit user-space apps' ioctl handlers when kernel modules
+ * is compiled as a 64 bit one
+ */
+static long orangefs_devreq_compat_ioctl(struct file *filp, unsigned int cmd,
+				      unsigned long args)
+{
+	long ret;
+	unsigned long arg = args;
+
+	/* Check for properly constructed commands */
+	ret = check_ioctl_command(cmd);
+	if (ret < 0)
+		return ret;
+	if (cmd == ORANGEFS_DEV_MAP) {
+		/*
+		 * convert the arguments to what we expect internally
+		 * in kernel space
+		 */
+		arg = translate_dev_map26(args, &ret);
+		if (ret < 0) {
+			gossip_err("Could not translate dev map\n");
+			return ret;
+		}
+	}
+	/* no other ioctl requires translation */
+	return dispatch_ioctl_command(cmd, arg);
+}
+
+#endif /* CONFIG_COMPAT is in .config */
+
+/* the assigned character device major number */
+static int orangefs_dev_major;
+
+/*
+ * Initialize orangefs device specific state:
+ * Must be called at module load time only
+ */
+int orangefs_dev_init(void)
+{
+	/* register orangefs-req device  */
+	orangefs_dev_major = register_chrdev(0,
+					  ORANGEFS_REQDEVICE_NAME,
+					  &orangefs_devreq_file_operations);
+	if (orangefs_dev_major < 0) {
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "Failed to register /dev/%s (error %d)\n",
+			     ORANGEFS_REQDEVICE_NAME, orangefs_dev_major);
+		return orangefs_dev_major;
+	}
+
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "*** /dev/%s character device registered ***\n",
+		     ORANGEFS_REQDEVICE_NAME);
+	gossip_debug(GOSSIP_DEV_DEBUG, "'mknod /dev/%s c %d 0'.\n",
+		     ORANGEFS_REQDEVICE_NAME, orangefs_dev_major);
+	return 0;
+}
+
+void orangefs_dev_cleanup(void)
+{
+	unregister_chrdev(orangefs_dev_major, ORANGEFS_REQDEVICE_NAME);
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "*** /dev/%s character device unregistered ***\n",
+		     ORANGEFS_REQDEVICE_NAME);
+}
+
+static unsigned int orangefs_devreq_poll(struct file *file,
+				      struct poll_table_struct *poll_table)
+{
+	int poll_revent_mask = 0;
+
+	poll_wait(file, &orangefs_request_list_waitq, poll_table);
+
+	if (!list_empty(&orangefs_request_list))
+		poll_revent_mask |= POLL_IN;
+	return poll_revent_mask;
+}
+
+const struct file_operations orangefs_devreq_file_operations = {
+	.owner = THIS_MODULE,
+	.read = orangefs_devreq_read,
+	.write_iter = orangefs_devreq_write_iter,
+	.open = orangefs_devreq_open,
+	.release = orangefs_devreq_release,
+	.unlocked_ioctl = orangefs_devreq_ioctl,
+
+#ifdef CONFIG_COMPAT		/* CONFIG_COMPAT is in .config */
+	.compat_ioctl = orangefs_devreq_compat_ioctl,
+#endif
+	.poll = orangefs_devreq_poll
+};
diff --git a/fs/orangefs/dir.c b/fs/orangefs/dir.c
new file mode 100644
index 000000000000..f30b6ecacdd1
--- /dev/null
+++ b/fs/orangefs/dir.c
@@ -0,0 +1,400 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+/*
+ * decode routine used by kmod to deal with the blob sent from
+ * userspace for readdirs. The blob contains zero or more of these
+ * sub-blobs:
+ *   __u32 - represents length of the character string that follows.
+ *   string - between 1 and ORANGEFS_NAME_MAX bytes long.
+ *   padding - (if needed) to cause the __u32 plus the string to be
+ *             eight byte aligned.
+ *   khandle - sizeof(khandle) bytes.
+ */
+static long decode_dirents(char *ptr, size_t size,
+                           struct orangefs_readdir_response_s *readdir)
+{
+	int i;
+	struct orangefs_readdir_response_s *rd =
+		(struct orangefs_readdir_response_s *) ptr;
+	char *buf = ptr;
+	int khandle_size = sizeof(struct orangefs_khandle);
+	size_t offset = offsetof(struct orangefs_readdir_response_s,
+				dirent_array);
+	/* 8 reflects eight byte alignment */
+	int smallest_blob = khandle_size + 8;
+	__u32 len;
+	int aligned_len;
+	int sizeof_u32 = sizeof(__u32);
+	long ret;
+
+	gossip_debug(GOSSIP_DIR_DEBUG, "%s: size:%zu:\n", __func__, size);
+
+	/* size is = offset on empty dirs, > offset on non-empty dirs... */
+	if (size < offset) {
+		gossip_err("%s: size:%zu: offset:%zu:\n",
+			   __func__,
+			   size,
+			   offset);
+		ret = -EINVAL;
+		goto out;
+	}
+
+        if ((size == offset) && (readdir->orangefs_dirent_outcount != 0)) {
+		gossip_err("%s: size:%zu: dirent_outcount:%d:\n",
+			   __func__,
+			   size,
+			   readdir->orangefs_dirent_outcount);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	readdir->token = rd->token;
+	readdir->orangefs_dirent_outcount = rd->orangefs_dirent_outcount;
+	readdir->dirent_array = kcalloc(readdir->orangefs_dirent_outcount,
+					sizeof(*readdir->dirent_array),
+					GFP_KERNEL);
+	if (readdir->dirent_array == NULL) {
+		gossip_err("%s: kcalloc failed.\n", __func__);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	buf += offset;
+	size -= offset;
+
+	for (i = 0; i < readdir->orangefs_dirent_outcount; i++) {
+		if (size < smallest_blob) {
+			gossip_err("%s: size:%zu: smallest_blob:%d:\n",
+				   __func__,
+				   size,
+				   smallest_blob);
+			ret = -EINVAL;
+			goto free;
+		}
+
+		len = *(__u32 *)buf;
+		if ((len < 1) || (len > ORANGEFS_NAME_MAX)) {
+			gossip_err("%s: len:%d:\n", __func__, len);
+			ret = -EINVAL;
+			goto free;
+		}
+
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "%s: size:%zu: len:%d:\n",
+			     __func__,
+			     size,
+			     len);
+
+		readdir->dirent_array[i].d_name = buf + sizeof_u32;
+		readdir->dirent_array[i].d_length = len;
+
+		/*
+		 * Calculate "aligned" length of this string and its
+		 * associated __u32 descriptor.
+		 */
+		aligned_len = ((sizeof_u32 + len + 1) + 7) & ~7;
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "%s: aligned_len:%d:\n",
+			     __func__,
+			     aligned_len);
+
+		/*
+		 * The end of the blob should coincide with the end
+		 * of the last sub-blob.
+		 */
+		if (size < aligned_len + khandle_size) {
+			gossip_err("%s: ran off the end of the blob.\n",
+				   __func__);
+			ret = -EINVAL;
+			goto free;
+		}
+		size -= aligned_len + khandle_size;
+
+		buf += aligned_len;
+
+		readdir->dirent_array[i].khandle =
+			*(struct orangefs_khandle *) buf;
+		buf += khandle_size;
+	}
+	ret = buf - ptr;
+	gossip_debug(GOSSIP_DIR_DEBUG, "%s: returning:%ld:\n", __func__, ret);
+	goto out;
+
+free:
+	kfree(readdir->dirent_array);
+	readdir->dirent_array = NULL;
+
+out:
+	return ret;
+}
+
+/*
+ * Read directory entries from an instance of an open directory.
+ */
+static int orangefs_readdir(struct file *file, struct dir_context *ctx)
+{
+	int ret = 0;
+	int buffer_index;
+	/*
+	 * ptoken supports Orangefs' distributed directory logic, added
+	 * in 2.9.2.
+	 */
+	__u64 *ptoken = file->private_data;
+	__u64 pos = 0;
+	ino_t ino = 0;
+	struct dentry *dentry = file->f_path.dentry;
+	struct orangefs_kernel_op_s *new_op = NULL;
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(dentry->d_inode);
+	int buffer_full = 0;
+	struct orangefs_readdir_response_s readdir_response;
+	void *dents_buf;
+	int i = 0;
+	int len = 0;
+	ino_t current_ino = 0;
+	char *current_entry = NULL;
+	long bytes_decoded;
+
+	gossip_debug(GOSSIP_DIR_DEBUG,
+		     "%s: ctx->pos:%lld, ptoken = %llu\n",
+		     __func__,
+		     lld(ctx->pos),
+		     llu(*ptoken));
+
+	pos = (__u64) ctx->pos;
+
+	/* are we done? */
+	if (pos == ORANGEFS_READDIR_END) {
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "Skipping to termination path\n");
+		return 0;
+	}
+
+	gossip_debug(GOSSIP_DIR_DEBUG,
+		     "orangefs_readdir called on %s (pos=%llu)\n",
+		     dentry->d_name.name, llu(pos));
+
+	memset(&readdir_response, 0, sizeof(readdir_response));
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_READDIR);
+	if (!new_op)
+		return -ENOMEM;
+
+	/*
+	 * Only the indices are shared. No memory is actually shared, but the
+	 * mechanism is used.
+	 */
+	new_op->uses_shared_memory = 1;
+	new_op->upcall.req.readdir.refn = orangefs_inode->refn;
+	new_op->upcall.req.readdir.max_dirent_count =
+	    ORANGEFS_MAX_DIRENT_COUNT_READDIR;
+
+	gossip_debug(GOSSIP_DIR_DEBUG,
+		     "%s: upcall.req.readdir.refn.khandle: %pU\n",
+		     __func__,
+		     &new_op->upcall.req.readdir.refn.khandle);
+
+	new_op->upcall.req.readdir.token = *ptoken;
+
+get_new_buffer_index:
+	buffer_index = orangefs_readdir_index_get();
+	if (buffer_index < 0) {
+		ret = buffer_index;
+		gossip_lerr("orangefs_readdir: orangefs_readdir_index_get() failure (%d)\n",
+			    ret);
+		goto out_free_op;
+	}
+	new_op->upcall.req.readdir.buf_index = buffer_index;
+
+	ret = service_operation(new_op,
+				"orangefs_readdir",
+				get_interruptible_flag(dentry->d_inode));
+
+	gossip_debug(GOSSIP_DIR_DEBUG,
+		     "Readdir downcall status is %d.  ret:%d\n",
+		     new_op->downcall.status,
+		     ret);
+
+	orangefs_readdir_index_put(buffer_index);
+
+	if (ret == -EAGAIN && op_state_purged(new_op)) {
+		/* Client-core indices are invalid after it restarted. */
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			"%s: Getting new buffer_index for retry of readdir..\n",
+			 __func__);
+		goto get_new_buffer_index;
+	}
+
+	if (ret == -EIO && op_state_purged(new_op)) {
+		gossip_err("%s: Client is down. Aborting readdir call.\n",
+			__func__);
+		goto out_slot;
+	}
+
+	if (ret < 0 || new_op->downcall.status != 0) {
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "Readdir request failed.  Status:%d\n",
+			     new_op->downcall.status);
+		if (ret >= 0)
+			ret = new_op->downcall.status;
+		goto out_slot;
+	}
+
+	dents_buf = new_op->downcall.trailer_buf;
+	if (dents_buf == NULL) {
+		gossip_err("Invalid NULL buffer in readdir response\n");
+		ret = -ENOMEM;
+		goto out_slot;
+	}
+
+	bytes_decoded = decode_dirents(dents_buf, new_op->downcall.trailer_size,
+					&readdir_response);
+	if (bytes_decoded < 0) {
+		ret = bytes_decoded;
+		gossip_err("Could not decode readdir from buffer %d\n", ret);
+		goto out_vfree;
+	}
+
+	if (bytes_decoded != new_op->downcall.trailer_size) {
+		gossip_err("orangefs_readdir: # bytes decoded (%ld) "
+			   "!= trailer size (%ld)\n",
+			   bytes_decoded,
+			   (long)new_op->downcall.trailer_size);
+		ret = -EINVAL;
+		goto out_destroy_handle;
+	}
+
+	/*
+	 *  orangefs doesn't actually store dot and dot-dot, but
+	 *  we need to have them represented.
+	 */
+	if (pos == 0) {
+		ino = get_ino_from_khandle(dentry->d_inode);
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "%s: calling dir_emit of \".\" with pos = %llu\n",
+			     __func__,
+			     llu(pos));
+		ret = dir_emit(ctx, ".", 1, ino, DT_DIR);
+		pos += 1;
+	}
+
+	if (pos == 1) {
+		ino = get_parent_ino_from_dentry(dentry);
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "%s: calling dir_emit of \"..\" with pos = %llu\n",
+			     __func__,
+			     llu(pos));
+		ret = dir_emit(ctx, "..", 2, ino, DT_DIR);
+		pos += 1;
+	}
+
+	/*
+	 * we stored ORANGEFS_ITERATE_NEXT in ctx->pos last time around
+	 * to prevent "finding" dot and dot-dot on any iteration
+	 * other than the first.
+	 */
+	if (ctx->pos == ORANGEFS_ITERATE_NEXT)
+		ctx->pos = 0;
+
+	gossip_debug(GOSSIP_DIR_DEBUG,
+		     "%s: dirent_outcount:%d:\n",
+		     __func__,
+		     readdir_response.orangefs_dirent_outcount);
+	for (i = ctx->pos;
+	     i < readdir_response.orangefs_dirent_outcount;
+	     i++) {
+		len = readdir_response.dirent_array[i].d_length;
+		current_entry = readdir_response.dirent_array[i].d_name;
+		current_ino = orangefs_khandle_to_ino(
+			&readdir_response.dirent_array[i].khandle);
+
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "calling dir_emit for %s with len %d"
+			     ", ctx->pos %ld\n",
+			     current_entry,
+			     len,
+			     (unsigned long)ctx->pos);
+		/*
+		 * type is unknown. We don't return object type
+		 * in the dirent_array. This leaves getdents
+		 * clueless about type.
+		 */
+		ret =
+		    dir_emit(ctx, current_entry, len, current_ino, DT_UNKNOWN);
+		if (!ret)
+			break;
+		ctx->pos++;
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			      "%s: ctx->pos:%lld\n",
+			      __func__,
+			      lld(ctx->pos));
+
+	}
+
+	/*
+	 * we ran all the way through the last batch, set up for
+	 * getting another batch...
+	 */
+	if (ret) {
+		*ptoken = readdir_response.token;
+		ctx->pos = ORANGEFS_ITERATE_NEXT;
+	}
+
+	/*
+	 * Did we hit the end of the directory?
+	 */
+	if (readdir_response.token == ORANGEFS_READDIR_END &&
+	    !buffer_full) {
+		gossip_debug(GOSSIP_DIR_DEBUG,
+		"End of dir detected; setting ctx->pos to ORANGEFS_READDIR_END.\n");
+		ctx->pos = ORANGEFS_READDIR_END;
+	}
+
+out_destroy_handle:
+	/* kfree(NULL) is safe */
+	kfree(readdir_response.dirent_array);
+out_vfree:
+	gossip_debug(GOSSIP_DIR_DEBUG, "vfree %p\n", dents_buf);
+	vfree(dents_buf);
+out_slot:
+	orangefs_readdir_index_put(buffer_index);
+out_free_op:
+	op_release(new_op);
+	gossip_debug(GOSSIP_DIR_DEBUG, "orangefs_readdir returning %d\n", ret);
+	return ret;
+}
+
+static int orangefs_dir_open(struct inode *inode, struct file *file)
+{
+	__u64 *ptoken;
+
+	file->private_data = kmalloc(sizeof(__u64), GFP_KERNEL);
+	if (!file->private_data)
+		return -ENOMEM;
+
+	ptoken = file->private_data;
+	*ptoken = ORANGEFS_READDIR_START;
+	return 0;
+}
+
+static int orangefs_dir_release(struct inode *inode, struct file *file)
+{
+	orangefs_flush_inode(inode);
+	kfree(file->private_data);
+	return 0;
+}
+
+/** ORANGEFS implementation of VFS directory operations */
+const struct file_operations orangefs_dir_operations = {
+	.read = generic_read_dir,
+	.iterate = orangefs_readdir,
+	.open = orangefs_dir_open,
+	.release = orangefs_dir_release,
+};
diff --git a/fs/orangefs/downcall.h b/fs/orangefs/downcall.h
new file mode 100644
index 000000000000..66b99210f1f9
--- /dev/null
+++ b/fs/orangefs/downcall.h
@@ -0,0 +1,133 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Definitions of downcalls used in Linux kernel module.
+ */
+
+#ifndef __DOWNCALL_H
+#define __DOWNCALL_H
+
+/*
+ * Sanitized the device-client core interaction
+ * for clean 32-64 bit usage
+ */
+struct orangefs_io_response {
+	__s64 amt_complete;
+};
+
+struct orangefs_lookup_response {
+	struct orangefs_object_kref refn;
+};
+
+struct orangefs_create_response {
+	struct orangefs_object_kref refn;
+};
+
+struct orangefs_symlink_response {
+	struct orangefs_object_kref refn;
+};
+
+struct orangefs_getattr_response {
+	struct ORANGEFS_sys_attr_s attributes;
+	char link_target[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_mkdir_response {
+	struct orangefs_object_kref refn;
+};
+
+/*
+ * duplication of some system interface structures so that I don't have
+ * to allocate extra memory
+ */
+struct orangefs_dirent {
+	char *d_name;
+	int d_length;
+	struct orangefs_khandle khandle;
+};
+
+struct orangefs_statfs_response {
+	__s64 block_size;
+	__s64 blocks_total;
+	__s64 blocks_avail;
+	__s64 files_total;
+	__s64 files_avail;
+};
+
+struct orangefs_fs_mount_response {
+	__s32 fs_id;
+	__s32 id;
+	struct orangefs_khandle root_khandle;
+};
+
+/* the getxattr response is the attribute value */
+struct orangefs_getxattr_response {
+	__s32 val_sz;
+	__s32 __pad1;
+	char val[ORANGEFS_MAX_XATTR_VALUELEN];
+};
+
+/* the listxattr response is an array of attribute names */
+struct orangefs_listxattr_response {
+	__s32 returned_count;
+	__s32 __pad1;
+	__u64 token;
+	char key[ORANGEFS_MAX_XATTR_LISTLEN * ORANGEFS_MAX_XATTR_NAMELEN];
+	__s32 keylen;
+	__s32 __pad2;
+	__s32 lengths[ORANGEFS_MAX_XATTR_LISTLEN];
+};
+
+struct orangefs_param_response {
+	__s64 value;
+};
+
+#define PERF_COUNT_BUF_SIZE 4096
+struct orangefs_perf_count_response {
+	char buffer[PERF_COUNT_BUF_SIZE];
+};
+
+#define FS_KEY_BUF_SIZE 4096
+struct orangefs_fs_key_response {
+	__s32 fs_keylen;
+	__s32 __pad1;
+	char fs_key[FS_KEY_BUF_SIZE];
+};
+
+struct orangefs_downcall_s {
+	__s32 type;
+	__s32 status;
+	/* currently trailer is used only by readdir */
+	__s64 trailer_size;
+	char *trailer_buf;
+
+	union {
+		struct orangefs_io_response io;
+		struct orangefs_lookup_response lookup;
+		struct orangefs_create_response create;
+		struct orangefs_symlink_response sym;
+		struct orangefs_getattr_response getattr;
+		struct orangefs_mkdir_response mkdir;
+		struct orangefs_statfs_response statfs;
+		struct orangefs_fs_mount_response fs_mount;
+		struct orangefs_getxattr_response getxattr;
+		struct orangefs_listxattr_response listxattr;
+		struct orangefs_param_response param;
+		struct orangefs_perf_count_response perf_count;
+		struct orangefs_fs_key_response fs_key;
+	} resp;
+};
+
+struct orangefs_readdir_response_s {
+	__u64 token;
+	__u64 directory_version;
+	__u32 __pad2;
+	__u32 orangefs_dirent_outcount;
+	struct orangefs_dirent *dirent_array;
+};
+
+#endif /* __DOWNCALL_H */
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
new file mode 100644
index 000000000000..ae92795ed965
--- /dev/null
+++ b/fs/orangefs/file.c
@@ -0,0 +1,717 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Linux VFS file operations.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+
+/*
+ * Copy to client-core's address space from the buffers specified
+ * by the iovec upto total_size bytes.
+ * NOTE: the iovector can either contain addresses which
+ *       can futher be kernel-space or user-space addresses.
+ *       or it can pointers to struct page's
+ */
+static int precopy_buffers(int buffer_index,
+			   struct iov_iter *iter,
+			   size_t total_size)
+{
+	int ret = 0;
+	/*
+	 * copy data from application/kernel by pulling it out
+	 * of the iovec.
+	 */
+
+
+	if (total_size) {
+		ret = orangefs_bufmap_copy_from_iovec(iter,
+						      buffer_index,
+						      total_size);
+		if (ret < 0)
+		gossip_err("%s: Failed to copy-in buffers. Please make sure that the pvfs2-client is running. %ld\n",
+			   __func__,
+			   (long)ret);
+	}
+
+	if (ret < 0)
+		gossip_err("%s: Failed to copy-in buffers. Please make sure that the pvfs2-client is running. %ld\n",
+			__func__,
+			(long)ret);
+	return ret;
+}
+
+/*
+ * Copy from client-core's address space to the buffers specified
+ * by the iovec upto total_size bytes.
+ * NOTE: the iovector can either contain addresses which
+ *       can futher be kernel-space or user-space addresses.
+ *       or it can pointers to struct page's
+ */
+static int postcopy_buffers(int buffer_index,
+			    struct iov_iter *iter,
+			    size_t total_size)
+{
+	int ret = 0;
+	/*
+	 * copy data to application/kernel by pushing it out to
+	 * the iovec. NOTE; target buffers can be addresses or
+	 * struct page pointers.
+	 */
+	if (total_size) {
+		ret = orangefs_bufmap_copy_to_iovec(iter,
+						    buffer_index,
+						    total_size);
+		if (ret < 0)
+			gossip_err("%s: Failed to copy-out buffers. Please make sure that the pvfs2-client is running (%ld)\n",
+				__func__,
+				(long)ret);
+	}
+	return ret;
+}
+
+/*
+ * Post and wait for the I/O upcall to finish
+ */
+static ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inode,
+		loff_t *offset, struct iov_iter *iter,
+		size_t total_size, loff_t readahead_size)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
+	struct orangefs_kernel_op_s *new_op = NULL;
+	struct iov_iter saved = *iter;
+	int buffer_index = -1;
+	ssize_t ret;
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_FILE_IO);
+	if (!new_op)
+		return -ENOMEM;
+
+	/* synchronous I/O */
+	new_op->upcall.req.io.readahead_size = readahead_size;
+	new_op->upcall.req.io.io_type = type;
+	new_op->upcall.req.io.refn = orangefs_inode->refn;
+
+populate_shared_memory:
+	/* get a shared buffer index */
+	buffer_index = orangefs_bufmap_get();
+	if (buffer_index < 0) {
+		ret = buffer_index;
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s: orangefs_bufmap_get failure (%zd)\n",
+			     __func__, ret);
+		goto out;
+	}
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU): GET op %p -> buffer_index %d\n",
+		     __func__,
+		     handle,
+		     new_op,
+		     buffer_index);
+
+	new_op->uses_shared_memory = 1;
+	new_op->upcall.req.io.buf_index = buffer_index;
+	new_op->upcall.req.io.count = total_size;
+	new_op->upcall.req.io.offset = *offset;
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU): offset: %llu total_size: %zd\n",
+		     __func__,
+		     handle,
+		     llu(*offset),
+		     total_size);
+	/*
+	 * Stage 1: copy the buffers into client-core's address space
+	 * precopy_buffers only pertains to writes.
+	 */
+	if (type == ORANGEFS_IO_WRITE) {
+		ret = precopy_buffers(buffer_index,
+				      iter,
+				      total_size);
+		if (ret < 0)
+			goto out;
+	}
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU): Calling post_io_request with tag (%llu)\n",
+		     __func__,
+		     handle,
+		     llu(new_op->tag));
+
+	/* Stage 2: Service the I/O operation */
+	ret = service_operation(new_op,
+				type == ORANGEFS_IO_WRITE ?
+					"file_write" :
+					"file_read",
+				get_interruptible_flag(inode));
+
+	/*
+	 * If service_operation() returns -EAGAIN #and# the operation was
+	 * purged from orangefs_request_list or htable_ops_in_progress, then
+	 * we know that the client was restarted, causing the shared memory
+	 * area to be wiped clean.  To restart a  write operation in this
+	 * case, we must re-copy the data from the user's iovec to a NEW
+	 * shared memory location. To restart a read operation, we must get
+	 * a new shared memory location.
+	 */
+	if (ret == -EAGAIN && op_state_purged(new_op)) {
+		orangefs_bufmap_put(buffer_index);
+		buffer_index = -1;
+		if (type == ORANGEFS_IO_WRITE)
+			*iter = saved;
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s:going to repopulate_shared_memory.\n",
+			     __func__);
+		goto populate_shared_memory;
+	}
+
+	if (ret < 0) {
+		if (ret == -EINTR) {
+			/*
+			 * We can't return EINTR if any data was written,
+			 * it's not POSIX. It is minimally acceptable
+			 * to give a partial write, the way NFS does.
+			 *
+			 * It would be optimal to return all or nothing,
+			 * but if a userspace write is bigger than
+			 * an IO buffer, and the interrupt occurs
+			 * between buffer writes, that would not be
+			 * possible.
+			 */
+			switch (new_op->op_state - OP_VFS_STATE_GIVEN_UP) {
+			/*
+			 * If the op was waiting when the interrupt
+			 * occurred, then the client-core did not
+			 * trigger the write.
+			 */
+			case OP_VFS_STATE_WAITING:
+				if (*offset == 0)
+					ret = -EINTR;
+				else
+					ret = 0;
+				break;
+			/* 
+			 * If the op was in progress when the interrupt
+			 * occurred, then the client-core was able to
+			 * trigger the write.
+			 */
+			case OP_VFS_STATE_INPROGR:
+				ret = total_size;
+				break;
+			default:
+				gossip_err("%s: unexpected op state :%d:.\n",
+					   __func__,
+					   new_op->op_state);
+				ret = 0;
+				break;
+			}
+			gossip_debug(GOSSIP_FILE_DEBUG,
+				     "%s: got EINTR, state:%d: %p\n",
+				     __func__,
+				     new_op->op_state,
+				     new_op);
+		} else {
+			gossip_err("%s: error in %s handle %pU, returning %zd\n",
+				__func__,
+				type == ORANGEFS_IO_READ ?
+					"read from" : "write to",
+				handle, ret);
+		}
+		if (orangefs_cancel_op_in_progress(new_op))
+			return ret;
+
+		goto out;
+	}
+
+	/*
+	 * Stage 3: Post copy buffers from client-core's address space
+	 * postcopy_buffers only pertains to reads.
+	 */
+	if (type == ORANGEFS_IO_READ) {
+		ret = postcopy_buffers(buffer_index,
+				       iter,
+				       new_op->downcall.resp.io.amt_complete);
+		if (ret < 0)
+			goto out;
+	}
+	gossip_debug(GOSSIP_FILE_DEBUG,
+	    "%s(%pU): Amount %s, returned by the sys-io call:%d\n",
+	    __func__,
+	    handle,
+	    type == ORANGEFS_IO_READ ?  "read" : "written",
+	    (int)new_op->downcall.resp.io.amt_complete);
+
+	ret = new_op->downcall.resp.io.amt_complete;
+
+out:
+	if (buffer_index >= 0) {
+		orangefs_bufmap_put(buffer_index);
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): PUT buffer_index %d\n",
+			     __func__, handle, buffer_index);
+		buffer_index = -1;
+	}
+	op_release(new_op);
+	return ret;
+}
+
+/*
+ * Common entry point for read/write/readv/writev
+ * This function will dispatch it to either the direct I/O
+ * or buffered I/O path depending on the mount options and/or
+ * augmented/extended metadata attached to the file.
+ * Note: File extended attributes override any mount options.
+ */
+static ssize_t do_readv_writev(enum ORANGEFS_io_type type, struct file *file,
+		loff_t *offset, struct iov_iter *iter)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
+	size_t count = iov_iter_count(iter);
+	ssize_t total_count = 0;
+	ssize_t ret = -EINVAL;
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		"%s-BEGIN(%pU): count(%d) after estimate_max_iovecs.\n",
+		__func__,
+		handle,
+		(int)count);
+
+	if (type == ORANGEFS_IO_WRITE) {
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): proceeding with offset : %llu, "
+			     "size %d\n",
+			     __func__,
+			     handle,
+			     llu(*offset),
+			     (int)count);
+	}
+
+	if (count == 0) {
+		ret = 0;
+		goto out;
+	}
+
+	while (iov_iter_count(iter)) {
+		size_t each_count = iov_iter_count(iter);
+		size_t amt_complete;
+
+		/* how much to transfer in this loop iteration */
+		if (each_count > orangefs_bufmap_size_query())
+			each_count = orangefs_bufmap_size_query();
+
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): size of each_count(%d)\n",
+			     __func__,
+			     handle,
+			     (int)each_count);
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): BEFORE wait_for_io: offset is %d\n",
+			     __func__,
+			     handle,
+			     (int)*offset);
+
+		ret = wait_for_direct_io(type, inode, offset, iter,
+				each_count, 0);
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): return from wait_for_io:%d\n",
+			     __func__,
+			     handle,
+			     (int)ret);
+
+		if (ret < 0)
+			goto out;
+
+		*offset += ret;
+		total_count += ret;
+		amt_complete = ret;
+
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): AFTER wait_for_io: offset is %d\n",
+			     __func__,
+			     handle,
+			     (int)*offset);
+
+		/*
+		 * if we got a short I/O operations,
+		 * fall out and return what we got so far
+		 */
+		if (amt_complete < each_count)
+			break;
+	} /*end while */
+
+out:
+	if (total_count > 0)
+		ret = total_count;
+	if (ret > 0) {
+		if (type == ORANGEFS_IO_READ) {
+			file_accessed(file);
+		} else {
+			SetMtimeFlag(orangefs_inode);
+			inode->i_mtime = CURRENT_TIME;
+			mark_inode_dirty_sync(inode);
+		}
+	}
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU): Value(%d) returned.\n",
+		     __func__,
+		     handle,
+		     (int)ret);
+
+	return ret;
+}
+
+/*
+ * Read data from a specified offset in a file (referenced by inode).
+ * Data may be placed either in a user or kernel buffer.
+ */
+ssize_t orangefs_inode_read(struct inode *inode,
+			    struct iov_iter *iter,
+			    loff_t *offset,
+			    loff_t readahead_size)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	size_t count = iov_iter_count(iter);
+	size_t bufmap_size;
+	ssize_t ret = -EINVAL;
+
+	g_orangefs_stats.reads++;
+
+	bufmap_size = orangefs_bufmap_size_query();
+	if (count > bufmap_size) {
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s: count is too large (%zd/%zd)!\n",
+			     __func__, count, bufmap_size);
+		return -EINVAL;
+	}
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU) %zd@%llu\n",
+		     __func__,
+		     &orangefs_inode->refn.khandle,
+		     count,
+		     llu(*offset));
+
+	ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, offset, iter,
+			count, readahead_size);
+	if (ret > 0)
+		*offset += ret;
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU): Value(%zd) returned.\n",
+		     __func__,
+		     &orangefs_inode->refn.khandle,
+		     ret);
+
+	return ret;
+}
+
+static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	loff_t pos = *(&iocb->ki_pos);
+	ssize_t rc = 0;
+
+	BUG_ON(iocb->private);
+
+	gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_read_iter\n");
+
+	g_orangefs_stats.reads++;
+
+	rc = do_readv_writev(ORANGEFS_IO_READ, file, &pos, iter);
+	iocb->ki_pos = pos;
+
+	return rc;
+}
+
+static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	loff_t pos;
+	ssize_t rc;
+
+	BUG_ON(iocb->private);
+
+	gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n");
+
+	mutex_lock(&file->f_mapping->host->i_mutex);
+
+	/* Make sure generic_write_checks sees an up to date inode size. */
+	if (file->f_flags & O_APPEND) {
+		rc = orangefs_inode_getattr(file->f_mapping->host, 0, 1);
+		if (rc == -ESTALE)
+			rc = -EIO;
+		if (rc) {
+			gossip_err("%s: orangefs_inode_getattr failed, "
+			    "rc:%zd:.\n", __func__, rc);
+			goto out;
+		}
+	}
+
+	if (file->f_pos > i_size_read(file->f_mapping->host))
+		orangefs_i_size_write(file->f_mapping->host, file->f_pos);
+
+	rc = generic_write_checks(iocb, iter);
+
+	if (rc <= 0) {
+		gossip_err("%s: generic_write_checks failed, rc:%zd:.\n",
+			   __func__, rc);
+		goto out;
+	}
+
+	/*
+	 * if we are appending, generic_write_checks would have updated
+	 * pos to the end of the file, so we will wait till now to set
+	 * pos...
+	 */
+	pos = *(&iocb->ki_pos);
+
+	rc = do_readv_writev(ORANGEFS_IO_WRITE,
+			     file,
+			     &pos,
+			     iter);
+	if (rc < 0) {
+		gossip_err("%s: do_readv_writev failed, rc:%zd:.\n",
+			   __func__, rc);
+		goto out;
+	}
+
+	iocb->ki_pos = pos;
+	g_orangefs_stats.writes++;
+
+out:
+
+	mutex_unlock(&file->f_mapping->host->i_mutex);
+	return rc;
+}
+
+/*
+ * Perform a miscellaneous operation on a file.
+ */
+static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	int ret = -ENOTTY;
+	__u64 val = 0;
+	unsigned long uval;
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "orangefs_ioctl: called with cmd %d\n",
+		     cmd);
+
+	/*
+	 * we understand some general ioctls on files, such as the immutable
+	 * and append flags
+	 */
+	if (cmd == FS_IOC_GETFLAGS) {
+		val = 0;
+		ret = orangefs_inode_getxattr(file_inode(file),
+					      ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+					      "user.pvfs2.meta_hint",
+					      &val, sizeof(val));
+		if (ret < 0 && ret != -ENODATA)
+			return ret;
+		else if (ret == -ENODATA)
+			val = 0;
+		uval = val;
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "orangefs_ioctl: FS_IOC_GETFLAGS: %llu\n",
+			     (unsigned long long)uval);
+		return put_user(uval, (int __user *)arg);
+	} else if (cmd == FS_IOC_SETFLAGS) {
+		ret = 0;
+		if (get_user(uval, (int __user *)arg))
+			return -EFAULT;
+		/*
+		 * ORANGEFS_MIRROR_FL is set internally when the mirroring mode
+		 * is turned on for a file. The user is not allowed to turn
+		 * on this bit, but the bit is present if the user first gets
+		 * the flags and then updates the flags with some new
+		 * settings. So, we ignore it in the following edit. bligon.
+		 */
+		if ((uval & ~ORANGEFS_MIRROR_FL) &
+		    (~(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NOATIME_FL))) {
+			gossip_err("orangefs_ioctl: the FS_IOC_SETFLAGS only supports setting one of FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NOATIME_FL\n");
+			return -EINVAL;
+		}
+		val = uval;
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "orangefs_ioctl: FS_IOC_SETFLAGS: %llu\n",
+			     (unsigned long long)val);
+		ret = orangefs_inode_setxattr(file_inode(file),
+					      ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+					      "user.pvfs2.meta_hint",
+					      &val, sizeof(val), 0);
+	}
+
+	return ret;
+}
+
+/*
+ * Memory map a region of a file.
+ */
+static int orangefs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "orangefs_file_mmap: called on %s\n",
+		     (file ?
+			(char *)file->f_path.dentry->d_name.name :
+			(char *)"Unknown"));
+
+	/* set the sequential readahead hint */
+	vma->vm_flags |= VM_SEQ_READ;
+	vma->vm_flags &= ~VM_RAND_READ;
+
+	/* Use readonly mmap since we cannot support writable maps. */
+	return generic_file_readonly_mmap(file, vma);
+}
+
+#define mapping_nrpages(idata) ((idata)->nrpages)
+
+/*
+ * Called to notify the module that there are no more references to
+ * this file (i.e. no processes have it open).
+ *
+ * \note Not called when each file is closed.
+ */
+static int orangefs_file_release(struct inode *inode, struct file *file)
+{
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "orangefs_file_release: called on %s\n",
+		     file->f_path.dentry->d_name.name);
+
+	orangefs_flush_inode(inode);
+
+	/*
+	 * remove all associated inode pages from the page cache and mmap
+	 * readahead cache (if any); this forces an expensive refresh of
+	 * data for the next caller of mmap (or 'get_block' accesses)
+	 */
+	if (file->f_path.dentry->d_inode &&
+	    file->f_path.dentry->d_inode->i_mapping &&
+	    mapping_nrpages(&file->f_path.dentry->d_inode->i_data))
+		truncate_inode_pages(file->f_path.dentry->d_inode->i_mapping,
+				     0);
+	return 0;
+}
+
+/*
+ * Push all data for a specific file onto permanent storage.
+ */
+static int orangefs_fsync(struct file *file,
+		       loff_t start,
+		       loff_t end,
+		       int datasync)
+{
+	int ret = -EINVAL;
+	struct orangefs_inode_s *orangefs_inode =
+		ORANGEFS_I(file->f_path.dentry->d_inode);
+	struct orangefs_kernel_op_s *new_op = NULL;
+
+	/* required call */
+	filemap_write_and_wait_range(file->f_mapping, start, end);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_FSYNC);
+	if (!new_op)
+		return -ENOMEM;
+	new_op->upcall.req.fsync.refn = orangefs_inode->refn;
+
+	ret = service_operation(new_op,
+			"orangefs_fsync",
+			get_interruptible_flag(file->f_path.dentry->d_inode));
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "orangefs_fsync got return value of %d\n",
+		     ret);
+
+	op_release(new_op);
+
+	orangefs_flush_inode(file->f_path.dentry->d_inode);
+	return ret;
+}
+
+/*
+ * Change the file pointer position for an instance of an open file.
+ *
+ * \note If .llseek is overriden, we must acquire lock as described in
+ *       Documentation/filesystems/Locking.
+ *
+ * Future upgrade could support SEEK_DATA and SEEK_HOLE but would
+ * require much changes to the FS
+ */
+static loff_t orangefs_file_llseek(struct file *file, loff_t offset, int origin)
+{
+	int ret = -EINVAL;
+	struct inode *inode = file_inode(file);
+
+	if (origin == SEEK_END) {
+		/*
+		 * revalidate the inode's file size.
+		 * NOTE: We are only interested in file size here,
+		 * so we set mask accordingly.
+		 */
+		ret = orangefs_inode_getattr(file->f_mapping->host, 0, 1);
+		if (ret == -ESTALE)
+			ret = -EIO;
+		if (ret) {
+			gossip_debug(GOSSIP_FILE_DEBUG,
+				     "%s:%s:%d calling make bad inode\n",
+				     __FILE__,
+				     __func__,
+				     __LINE__);
+			return ret;
+		}
+	}
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "orangefs_file_llseek: offset is %ld | origin is %d"
+		     " | inode size is %lu\n",
+		     (long)offset,
+		     origin,
+		     (unsigned long)i_size_read(inode));
+
+	return generic_file_llseek(file, offset, origin);
+}
+
+/*
+ * Support local locks (locks that only this kernel knows about)
+ * if Orangefs was mounted -o local_lock.
+ */
+static int orangefs_lock(struct file *filp, int cmd, struct file_lock *fl)
+{
+	int rc = -EINVAL;
+
+	if (ORANGEFS_SB(filp->f_inode->i_sb)->flags & ORANGEFS_OPT_LOCAL_LOCK) {
+		if (cmd == F_GETLK) {
+			rc = 0;
+			posix_test_lock(filp, fl);
+		} else {
+			rc = posix_lock_file(filp, fl, NULL);
+		}
+	}
+
+	return rc;
+}
+
+/** ORANGEFS implementation of VFS file operations */
+const struct file_operations orangefs_file_operations = {
+	.llseek		= orangefs_file_llseek,
+	.read_iter	= orangefs_file_read_iter,
+	.write_iter	= orangefs_file_write_iter,
+	.lock		= orangefs_lock,
+	.unlocked_ioctl	= orangefs_ioctl,
+	.mmap		= orangefs_file_mmap,
+	.open		= generic_file_open,
+	.release	= orangefs_file_release,
+	.fsync		= orangefs_fsync,
+};
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
new file mode 100644
index 000000000000..2382e267b49e
--- /dev/null
+++ b/fs/orangefs/inode.c
@@ -0,0 +1,475 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Linux VFS inode operations.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+static int read_one_page(struct page *page)
+{
+	int ret;
+	int max_block;
+	ssize_t bytes_read = 0;
+	struct inode *inode = page->mapping->host;
+	const __u32 blocksize = PAGE_CACHE_SIZE;	/* inode->i_blksize */
+	const __u32 blockbits = PAGE_CACHE_SHIFT;	/* inode->i_blkbits */
+	struct iov_iter to;
+	struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE};
+
+	iov_iter_bvec(&to, ITER_BVEC | READ, &bv, 1, PAGE_SIZE);
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		    "orangefs_readpage called with page %p\n",
+		     page);
+
+	max_block = ((inode->i_size / blocksize) + 1);
+
+	if (page->index < max_block) {
+		loff_t blockptr_offset = (((loff_t) page->index) << blockbits);
+
+		bytes_read = orangefs_inode_read(inode,
+						 &to,
+						 &blockptr_offset,
+						 inode->i_size);
+	}
+	/* this will only zero remaining unread portions of the page data */
+	iov_iter_zero(~0U, &to);
+	/* takes care of potential aliasing */
+	flush_dcache_page(page);
+	if (bytes_read < 0) {
+		ret = bytes_read;
+		SetPageError(page);
+	} else {
+		SetPageUptodate(page);
+		if (PageError(page))
+			ClearPageError(page);
+		ret = 0;
+	}
+	/* unlock the page after the ->readpage() routine completes */
+	unlock_page(page);
+	return ret;
+}
+
+static int orangefs_readpage(struct file *file, struct page *page)
+{
+	return read_one_page(page);
+}
+
+static int orangefs_readpages(struct file *file,
+			   struct address_space *mapping,
+			   struct list_head *pages,
+			   unsigned nr_pages)
+{
+	int page_idx;
+	int ret;
+
+	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpages called\n");
+
+	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
+		struct page *page;
+
+		page = list_entry(pages->prev, struct page, lru);
+		list_del(&page->lru);
+		if (!add_to_page_cache(page,
+				       mapping,
+				       page->index,
+				       GFP_KERNEL)) {
+			ret = read_one_page(page);
+			gossip_debug(GOSSIP_INODE_DEBUG,
+				"failure adding page to cache, read_one_page returned: %d\n",
+				ret);
+	      } else {
+			page_cache_release(page);
+	      }
+	}
+	BUG_ON(!list_empty(pages));
+	return 0;
+}
+
+static void orangefs_invalidatepage(struct page *page,
+				 unsigned int offset,
+				 unsigned int length)
+{
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_invalidatepage called on page %p "
+		     "(offset is %u)\n",
+		     page,
+		     offset);
+
+	ClearPageUptodate(page);
+	ClearPageMappedToDisk(page);
+	return;
+
+}
+
+static int orangefs_releasepage(struct page *page, gfp_t foo)
+{
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_releasepage called on page %p\n",
+		     page);
+	return 0;
+}
+
+/*
+ * Having a direct_IO entry point in the address_space_operations
+ * struct causes the kernel to allows us to use O_DIRECT on
+ * open. Nothing will ever call this thing, but in the future we
+ * will need to be able to use O_DIRECT on open in order to support
+ * AIO. Modeled after NFS, they do this too.
+ */
+/*
+ * static ssize_t orangefs_direct_IO(int rw,
+ *			struct kiocb *iocb,
+ *			struct iov_iter *iter,
+ *			loff_t offset)
+ *{
+ *	gossip_debug(GOSSIP_INODE_DEBUG,
+ *		     "orangefs_direct_IO: %s\n",
+ *		     iocb->ki_filp->f_path.dentry->d_name.name);
+ *
+ *	return -EINVAL;
+ *}
+ */
+
+struct backing_dev_info orangefs_backing_dev_info = {
+	.name = "orangefs",
+	.ra_pages = 0,
+	.capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+};
+
+/** ORANGEFS2 implementation of address space operations */
+const struct address_space_operations orangefs_address_operations = {
+	.readpage = orangefs_readpage,
+	.readpages = orangefs_readpages,
+	.invalidatepage = orangefs_invalidatepage,
+	.releasepage = orangefs_releasepage,
+/*	.direct_IO = orangefs_direct_IO */
+};
+
+static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	loff_t orig_size;
+	int ret = -EINVAL;
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "%s: %pU: Handle is %pU | fs_id %d | size is %llu\n",
+		     __func__,
+		     get_khandle_from_ino(inode),
+		     &orangefs_inode->refn.khandle,
+		     orangefs_inode->refn.fs_id,
+		     iattr->ia_size);
+
+	/* Ensure that we have a up to date size, so we know if it changed. */
+	ret = orangefs_inode_getattr(inode, 0, 1);
+	if (ret == -ESTALE)
+		ret = -EIO;
+	if (ret) {
+		gossip_err("%s: orangefs_inode_getattr failed, ret:%d:.\n",
+		    __func__, ret);
+		return ret;
+	}
+	orig_size = i_size_read(inode);
+
+	truncate_setsize(inode, iattr->ia_size);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_TRUNCATE);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.truncate.refn = orangefs_inode->refn;
+	new_op->upcall.req.truncate.size = (__s64) iattr->ia_size;
+
+	ret = service_operation(new_op, __func__,
+				get_interruptible_flag(inode));
+
+	/*
+	 * the truncate has no downcall members to retrieve, but
+	 * the status value tells us if it went through ok or not
+	 */
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs: orangefs_truncate got return value of %d\n",
+		     ret);
+
+	op_release(new_op);
+
+	if (ret != 0)
+		return ret;
+
+	/*
+	 * Only change the c/mtime if we are changing the size or we are
+	 * explicitly asked to change it.  This handles the semantic difference
+	 * between truncate() and ftruncate() as implemented in the VFS.
+	 *
+	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
+	 * special case where we need to update the times despite not having
+	 * these flags set.  For all other operations the VFS set these flags
+	 * explicitly if it wants a timestamp update.
+	 */
+	if (orig_size != i_size_read(inode) &&
+	    !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
+		iattr->ia_ctime = iattr->ia_mtime =
+			current_fs_time(inode->i_sb);
+		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
+	}
+
+	return ret;
+}
+
+/*
+ * Change attributes of an object referenced by dentry.
+ */
+int orangefs_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+	int ret = -EINVAL;
+	struct inode *inode = dentry->d_inode;
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_setattr: called on %s\n",
+		     dentry->d_name.name);
+
+	ret = inode_change_ok(inode, iattr);
+	if (ret)
+		goto out;
+
+	if ((iattr->ia_valid & ATTR_SIZE) &&
+	    iattr->ia_size != i_size_read(inode)) {
+		ret = orangefs_setattr_size(inode, iattr);
+		if (ret)
+			goto out;
+	}
+
+	setattr_copy(inode, iattr);
+	mark_inode_dirty(inode);
+
+	ret = orangefs_inode_setattr(inode, iattr);
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_setattr: inode_setattr returned %d\n",
+		     ret);
+
+	if (!ret && (iattr->ia_valid & ATTR_MODE))
+		/* change mod on a file that has ACLs */
+		ret = posix_acl_chmod(inode, inode->i_mode);
+
+out:
+	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_setattr: returning %d\n", ret);
+	return ret;
+}
+
+/*
+ * Obtain attributes of an object given a dentry
+ */
+int orangefs_getattr(struct vfsmount *mnt,
+		  struct dentry *dentry,
+		  struct kstat *kstat)
+{
+	int ret = -ENOENT;
+	struct inode *inode = dentry->d_inode;
+	struct orangefs_inode_s *orangefs_inode = NULL;
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_getattr: called on %s\n",
+		     dentry->d_name.name);
+
+	ret = orangefs_inode_getattr(inode, 0, 1);
+	if (ret == 0) {
+		generic_fillattr(inode, kstat);
+
+		/* override block size reported to stat */
+		orangefs_inode = ORANGEFS_I(inode);
+		kstat->blksize = orangefs_inode->blksize;
+	}
+	return ret;
+}
+
+int orangefs_permission(struct inode *inode, int mask)
+{
+	int ret;
+
+	if (mask & MAY_NOT_BLOCK)
+		return -ECHILD;
+
+	gossip_debug(GOSSIP_INODE_DEBUG, "%s: refreshing\n", __func__);
+
+	/* Make sure the permission (and other common attrs) are up to date. */
+	ret = orangefs_inode_getattr(inode, 0, 0);
+	if (ret < 0)
+		return ret;
+
+	return generic_permission(inode, mask);
+}
+
+/* ORANGEDS2 implementation of VFS inode operations for files */
+struct inode_operations orangefs_file_inode_operations = {
+	.get_acl = orangefs_get_acl,
+	.set_acl = orangefs_set_acl,
+	.setattr = orangefs_setattr,
+	.getattr = orangefs_getattr,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
+	.listxattr = orangefs_listxattr,
+	.removexattr = generic_removexattr,
+	.permission = orangefs_permission,
+};
+
+static int orangefs_init_iops(struct inode *inode)
+{
+	inode->i_mapping->a_ops = &orangefs_address_operations;
+
+	switch (inode->i_mode & S_IFMT) {
+	case S_IFREG:
+		inode->i_op = &orangefs_file_inode_operations;
+		inode->i_fop = &orangefs_file_operations;
+		inode->i_blkbits = PAGE_CACHE_SHIFT;
+		break;
+	case S_IFLNK:
+		inode->i_op = &orangefs_symlink_inode_operations;
+		break;
+	case S_IFDIR:
+		inode->i_op = &orangefs_dir_inode_operations;
+		inode->i_fop = &orangefs_dir_operations;
+		break;
+	default:
+		gossip_debug(GOSSIP_INODE_DEBUG,
+			     "%s: unsupported mode\n",
+			     __func__);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Given a ORANGEFS object identifier (fsid, handle), convert it into a ino_t type
+ * that will be used as a hash-index from where the handle will
+ * be searched for in the VFS hash table of inodes.
+ */
+static inline ino_t orangefs_handle_hash(struct orangefs_object_kref *ref)
+{
+	if (!ref)
+		return 0;
+	return orangefs_khandle_to_ino(&(ref->khandle));
+}
+
+/*
+ * Called to set up an inode from iget5_locked.
+ */
+static int orangefs_set_inode(struct inode *inode, void *data)
+{
+	struct orangefs_object_kref *ref = (struct orangefs_object_kref *) data;
+	ORANGEFS_I(inode)->refn.fs_id = ref->fs_id;
+	ORANGEFS_I(inode)->refn.khandle = ref->khandle;
+	return 0;
+}
+
+/*
+ * Called to determine if handles match.
+ */
+static int orangefs_test_inode(struct inode *inode, void *data)
+{
+	struct orangefs_object_kref *ref = (struct orangefs_object_kref *) data;
+	struct orangefs_inode_s *orangefs_inode = NULL;
+
+	orangefs_inode = ORANGEFS_I(inode);
+	return (!ORANGEFS_khandle_cmp(&(orangefs_inode->refn.khandle), &(ref->khandle))
+		&& orangefs_inode->refn.fs_id == ref->fs_id);
+}
+
+/*
+ * Front-end to lookup the inode-cache maintained by the VFS using the ORANGEFS
+ * file handle.
+ *
+ * @sb: the file system super block instance.
+ * @ref: The ORANGEFS object for which we are trying to locate an inode structure.
+ */
+struct inode *orangefs_iget(struct super_block *sb, struct orangefs_object_kref *ref)
+{
+	struct inode *inode = NULL;
+	unsigned long hash;
+	int error;
+
+	hash = orangefs_handle_hash(ref);
+	inode = iget5_locked(sb, hash, orangefs_test_inode, orangefs_set_inode, ref);
+	if (!inode || !(inode->i_state & I_NEW))
+		return inode;
+
+	error = orangefs_inode_getattr(inode, 1, 0);
+	if (error) {
+		iget_failed(inode);
+		return ERR_PTR(error);
+	}
+
+	inode->i_ino = hash;	/* needed for stat etc */
+	orangefs_init_iops(inode);
+	unlock_new_inode(inode);
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "iget handle %pU, fsid %d hash %ld i_ino %lu\n",
+		     &ref->khandle,
+		     ref->fs_id,
+		     hash,
+		     inode->i_ino);
+
+	return inode;
+}
+
+/*
+ * Allocate an inode for a newly created file and insert it into the inode hash.
+ */
+struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir,
+		int mode, dev_t dev, struct orangefs_object_kref *ref)
+{
+	unsigned long hash = orangefs_handle_hash(ref);
+	struct inode *inode;
+	int error;
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "%s:(sb is %p | MAJOR(dev)=%u | MINOR(dev)=%u mode=%o)\n",
+		     __func__,
+		     sb,
+		     MAJOR(dev),
+		     MINOR(dev),
+		     mode);
+
+	inode = new_inode(sb);
+	if (!inode)
+		return NULL;
+
+	orangefs_set_inode(inode, ref);
+	inode->i_ino = hash;	/* needed for stat etc */
+
+	error = orangefs_inode_getattr(inode, 1, 0);
+	if (error)
+		goto out_iput;
+
+	orangefs_init_iops(inode);
+
+	inode->i_mode = mode;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_size = PAGE_CACHE_SIZE;
+	inode->i_rdev = dev;
+
+	error = insert_inode_locked4(inode, hash, orangefs_test_inode, ref);
+	if (error < 0)
+		goto out_iput;
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "Initializing ACL's for inode %pU\n",
+		     get_khandle_from_ino(inode));
+	orangefs_init_acl(inode, dir);
+	return inode;
+
+out_iput:
+	iput(inode);
+	return ERR_PTR(error);
+}
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
new file mode 100644
index 000000000000..5a60c508af4e
--- /dev/null
+++ b/fs/orangefs/namei.c
@@ -0,0 +1,462 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Linux VFS namei operations.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+
+/*
+ * Get a newly allocated inode to go with a negative dentry.
+ */
+static int orangefs_create(struct inode *dir,
+			struct dentry *dentry,
+			umode_t mode,
+			bool exclusive)
+{
+	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
+	struct orangefs_kernel_op_s *new_op;
+	struct inode *inode;
+	int ret;
+
+	gossip_debug(GOSSIP_NAME_DEBUG, "%s: %s\n",
+		     __func__,
+		     dentry->d_name.name);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_CREATE);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.create.parent_refn = parent->refn;
+
+	fill_default_sys_attrs(new_op->upcall.req.create.attributes,
+			       ORANGEFS_TYPE_METAFILE, mode);
+
+	strncpy(new_op->upcall.req.create.d_name,
+		dentry->d_name.name, ORANGEFS_NAME_MAX);
+
+	ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: %s: handle:%pU: fsid:%d: new_op:%p: ret:%d:\n",
+		     __func__,
+		     dentry->d_name.name,
+		     &new_op->downcall.resp.create.refn.khandle,
+		     new_op->downcall.resp.create.refn.fs_id,
+		     new_op,
+		     ret);
+
+	if (ret < 0)
+		goto out;
+
+	inode = orangefs_new_inode(dir->i_sb, dir, S_IFREG | mode, 0,
+				&new_op->downcall.resp.create.refn);
+	if (IS_ERR(inode)) {
+		gossip_err("%s: Failed to allocate inode for file :%s:\n",
+			   __func__,
+			   dentry->d_name.name);
+		ret = PTR_ERR(inode);
+		goto out;
+	}
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: Assigned inode :%pU: for file :%s:\n",
+		     __func__,
+		     get_khandle_from_ino(inode),
+		     dentry->d_name.name);
+
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: dentry instantiated for %s\n",
+		     __func__,
+		     dentry->d_name.name);
+
+	SetMtimeFlag(parent);
+	dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
+	mark_inode_dirty_sync(dir);
+	ret = 0;
+out:
+	op_release(new_op);
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: %s: returning %d\n",
+		     __func__,
+		     dentry->d_name.name,
+		     ret);
+	return ret;
+}
+
+/*
+ * Attempt to resolve an object name (dentry->d_name), parent handle, and
+ * fsid into a handle for the object.
+ */
+static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
+				   unsigned int flags)
+{
+	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
+	struct orangefs_kernel_op_s *new_op;
+	struct inode *inode;
+	struct dentry *res;
+	int ret = -EINVAL;
+
+	/*
+	 * in theory we could skip a lookup here (if the intent is to
+	 * create) in order to avoid a potentially failed lookup, but
+	 * leaving it in can skip a valid lookup and try to create a file
+	 * that already exists (e.g. the vfs already handles checking for
+	 * -EEXIST on O_EXCL opens, which is broken if we skip this lookup
+	 * in the create path)
+	 */
+	gossip_debug(GOSSIP_NAME_DEBUG, "%s called on %s\n",
+		     __func__, dentry->d_name.name);
+
+	if (dentry->d_name.len > (ORANGEFS_NAME_MAX - 1))
+		return ERR_PTR(-ENAMETOOLONG);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_LOOKUP);
+	if (!new_op)
+		return ERR_PTR(-ENOMEM);
+
+	new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW;
+
+	gossip_debug(GOSSIP_NAME_DEBUG, "%s:%s:%d using parent %pU\n",
+		     __FILE__,
+		     __func__,
+		     __LINE__,
+		     &parent->refn.khandle);
+	new_op->upcall.req.lookup.parent_refn = parent->refn;
+
+	strncpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: doing lookup on %s under %pU,%d\n",
+		     __func__,
+		     new_op->upcall.req.lookup.d_name,
+		     &new_op->upcall.req.lookup.parent_refn.khandle,
+		     new_op->upcall.req.lookup.parent_refn.fs_id);
+
+	ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Lookup Got %pU, fsid %d (ret=%d)\n",
+		     &new_op->downcall.resp.lookup.refn.khandle,
+		     new_op->downcall.resp.lookup.refn.fs_id,
+		     ret);
+
+	if (ret < 0) {
+		if (ret == -ENOENT) {
+			/*
+			 * if no inode was found, add a negative dentry to
+			 * dcache anyway; if we don't, we don't hold expected
+			 * lookup semantics and we most noticeably break
+			 * during directory renames.
+			 *
+			 * however, if the operation failed or exited, do not
+			 * add the dentry (e.g. in the case that a touch is
+			 * issued on a file that already exists that was
+			 * interrupted during this lookup -- no need to add
+			 * another negative dentry for an existing file)
+			 */
+
+			gossip_debug(GOSSIP_NAME_DEBUG,
+				     "orangefs_lookup: Adding *negative* dentry "
+				     "%p for %s\n",
+				     dentry,
+				     dentry->d_name.name);
+
+			d_add(dentry, NULL);
+			res = NULL;
+			goto out;
+		}
+
+		/* must be a non-recoverable error */
+		res = ERR_PTR(ret);
+		goto out;
+	}
+
+	inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
+	if (IS_ERR(inode)) {
+		gossip_debug(GOSSIP_NAME_DEBUG,
+			"error %ld from iget\n", PTR_ERR(inode));
+		res = ERR_CAST(inode);
+		goto out;
+	}
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s:%s:%d "
+		     "Found good inode [%lu] with count [%d]\n",
+		     __FILE__,
+		     __func__,
+		     __LINE__,
+		     inode->i_ino,
+		     (int)atomic_read(&inode->i_count));
+
+	/* update dentry/inode pair into dcache */
+	res = d_splice_alias(inode, dentry);
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Lookup success (inode ct = %d)\n",
+		     (int)atomic_read(&inode->i_count));
+out:
+	op_release(new_op);
+	return res;
+}
+
+/* return 0 on success; non-zero otherwise */
+static int orangefs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
+	struct orangefs_kernel_op_s *new_op;
+	int ret;
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: called on %s\n"
+		     "  (inode %pU): Parent is %pU | fs_id %d\n",
+		     __func__,
+		     dentry->d_name.name,
+		     get_khandle_from_ino(inode),
+		     &parent->refn.khandle,
+		     parent->refn.fs_id);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_REMOVE);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.remove.parent_refn = parent->refn;
+	strncpy(new_op->upcall.req.remove.d_name, dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+
+	ret = service_operation(new_op, "orangefs_unlink",
+				get_interruptible_flag(inode));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: service_operation returned:%d:\n",
+		     __func__,
+		     ret);
+
+	op_release(new_op);
+
+	if (!ret) {
+		drop_nlink(inode);
+
+		SetMtimeFlag(parent);
+		dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
+		mark_inode_dirty_sync(dir);
+	}
+	return ret;
+}
+
+static int orangefs_symlink(struct inode *dir,
+			 struct dentry *dentry,
+			 const char *symname)
+{
+	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
+	struct orangefs_kernel_op_s *new_op;
+	struct inode *inode;
+	int mode = 755;
+	int ret;
+
+	gossip_debug(GOSSIP_NAME_DEBUG, "%s: called\n", __func__);
+
+	if (!symname)
+		return -EINVAL;
+
+	if (strlen(symname)+1 > ORANGEFS_NAME_MAX)
+		return -ENAMETOOLONG;
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_SYMLINK);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.sym.parent_refn = parent->refn;
+
+	fill_default_sys_attrs(new_op->upcall.req.sym.attributes,
+			       ORANGEFS_TYPE_SYMLINK,
+			       mode);
+
+	strncpy(new_op->upcall.req.sym.entry_name,
+		dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+	strncpy(new_op->upcall.req.sym.target, symname, ORANGEFS_NAME_MAX);
+
+	ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Symlink Got ORANGEFS handle %pU on fsid %d (ret=%d)\n",
+		     &new_op->downcall.resp.sym.refn.khandle,
+		     new_op->downcall.resp.sym.refn.fs_id, ret);
+
+	if (ret < 0) {
+		gossip_debug(GOSSIP_NAME_DEBUG,
+			    "%s: failed with error code %d\n",
+			    __func__, ret);
+		goto out;
+	}
+
+	inode = orangefs_new_inode(dir->i_sb, dir, S_IFLNK | mode, 0,
+				&new_op->downcall.resp.sym.refn);
+	if (IS_ERR(inode)) {
+		gossip_err
+		    ("*** Failed to allocate orangefs symlink inode\n");
+		ret = PTR_ERR(inode);
+		goto out;
+	}
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Assigned symlink inode new number of %pU\n",
+		     get_khandle_from_ino(inode));
+
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Inode (Symlink) %pU -> %s\n",
+		     get_khandle_from_ino(inode),
+		     dentry->d_name.name);
+
+	SetMtimeFlag(parent);
+	dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
+	mark_inode_dirty_sync(dir);
+	ret = 0;
+out:
+	op_release(new_op);
+	return ret;
+}
+
+static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
+	struct orangefs_kernel_op_s *new_op;
+	struct inode *inode;
+	int ret;
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_MKDIR);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.mkdir.parent_refn = parent->refn;
+
+	fill_default_sys_attrs(new_op->upcall.req.mkdir.attributes,
+			      ORANGEFS_TYPE_DIRECTORY, mode);
+
+	strncpy(new_op->upcall.req.mkdir.d_name,
+		dentry->d_name.name, ORANGEFS_NAME_MAX);
+
+	ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Mkdir Got ORANGEFS handle %pU on fsid %d\n",
+		     &new_op->downcall.resp.mkdir.refn.khandle,
+		     new_op->downcall.resp.mkdir.refn.fs_id);
+
+	if (ret < 0) {
+		gossip_debug(GOSSIP_NAME_DEBUG,
+			     "%s: failed with error code %d\n",
+			     __func__, ret);
+		goto out;
+	}
+
+	inode = orangefs_new_inode(dir->i_sb, dir, S_IFDIR | mode, 0,
+				&new_op->downcall.resp.mkdir.refn);
+	if (IS_ERR(inode)) {
+		gossip_err("*** Failed to allocate orangefs dir inode\n");
+		ret = PTR_ERR(inode);
+		goto out;
+	}
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Assigned dir inode new number of %pU\n",
+		     get_khandle_from_ino(inode));
+
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Inode (Directory) %pU -> %s\n",
+		     get_khandle_from_ino(inode),
+		     dentry->d_name.name);
+
+	/*
+	 * NOTE: we have no good way to keep nlink consistent for directories
+	 * across clients; keep constant at 1.
+	 */
+	SetMtimeFlag(parent);
+	dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
+	mark_inode_dirty_sync(dir);
+out:
+	op_release(new_op);
+	return ret;
+}
+
+static int orangefs_rename(struct inode *old_dir,
+			struct dentry *old_dentry,
+			struct inode *new_dir,
+			struct dentry *new_dentry)
+{
+	struct orangefs_kernel_op_s *new_op;
+	int ret;
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "orangefs_rename: called (%s/%s => %s/%s) ct=%d\n",
+		     old_dentry->d_parent->d_name.name,
+		     old_dentry->d_name.name,
+		     new_dentry->d_parent->d_name.name,
+		     new_dentry->d_name.name,
+		     d_count(new_dentry));
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_RENAME);
+	if (!new_op)
+		return -EINVAL;
+
+	new_op->upcall.req.rename.old_parent_refn = ORANGEFS_I(old_dir)->refn;
+	new_op->upcall.req.rename.new_parent_refn = ORANGEFS_I(new_dir)->refn;
+
+	strncpy(new_op->upcall.req.rename.d_old_name,
+		old_dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+	strncpy(new_op->upcall.req.rename.d_new_name,
+		new_dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+
+	ret = service_operation(new_op,
+				"orangefs_rename",
+				get_interruptible_flag(old_dentry->d_inode));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "orangefs_rename: got downcall status %d\n",
+		     ret);
+
+	if (new_dentry->d_inode)
+		new_dentry->d_inode->i_ctime = CURRENT_TIME;
+
+	op_release(new_op);
+	return ret;
+}
+
+/* ORANGEFS implementation of VFS inode operations for directories */
+struct inode_operations orangefs_dir_inode_operations = {
+	.lookup = orangefs_lookup,
+	.get_acl = orangefs_get_acl,
+	.set_acl = orangefs_set_acl,
+	.create = orangefs_create,
+	.unlink = orangefs_unlink,
+	.symlink = orangefs_symlink,
+	.mkdir = orangefs_mkdir,
+	.rmdir = orangefs_unlink,
+	.rename = orangefs_rename,
+	.setattr = orangefs_setattr,
+	.getattr = orangefs_getattr,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
+	.removexattr = generic_removexattr,
+	.listxattr = orangefs_listxattr,
+	.permission = orangefs_permission,
+};
diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c
new file mode 100644
index 000000000000..1f8acc9f9a88
--- /dev/null
+++ b/fs/orangefs/orangefs-bufmap.c
@@ -0,0 +1,556 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+struct slot_map {
+	int c;
+	wait_queue_head_t q;
+	int count;
+	unsigned long *map;
+};
+
+static struct slot_map rw_map = {
+	.c = -1,
+	.q = __WAIT_QUEUE_HEAD_INITIALIZER(rw_map.q)
+};
+static struct slot_map readdir_map = {
+	.c = -1,
+	.q = __WAIT_QUEUE_HEAD_INITIALIZER(readdir_map.q)
+};
+
+
+static void install(struct slot_map *m, int count, unsigned long *map)
+{
+	spin_lock(&m->q.lock);
+	m->c = m->count = count;
+	m->map = map;
+	wake_up_all_locked(&m->q);
+	spin_unlock(&m->q.lock);
+}
+
+static void mark_killed(struct slot_map *m)
+{
+	spin_lock(&m->q.lock);
+	m->c -= m->count + 1;
+	spin_unlock(&m->q.lock);
+}
+
+static void run_down(struct slot_map *m)
+{
+	DEFINE_WAIT(wait);
+	spin_lock(&m->q.lock);
+	if (m->c != -1) {
+		for (;;) {
+			if (likely(list_empty(&wait.task_list)))
+				__add_wait_queue_tail(&m->q, &wait);
+			set_current_state(TASK_UNINTERRUPTIBLE);
+
+			if (m->c == -1)
+				break;
+
+			spin_unlock(&m->q.lock);
+			schedule();
+			spin_lock(&m->q.lock);
+		}
+		__remove_wait_queue(&m->q, &wait);
+		__set_current_state(TASK_RUNNING);
+	}
+	m->map = NULL;
+	spin_unlock(&m->q.lock);
+}
+
+static void put(struct slot_map *m, int slot)
+{
+	int v;
+	spin_lock(&m->q.lock);
+	__clear_bit(slot, m->map);
+	v = ++m->c;
+	if (unlikely(v == 1))	/* no free slots -> one free slot */
+		wake_up_locked(&m->q);
+	else if (unlikely(v == -1))	/* finished dying */
+		wake_up_all_locked(&m->q);
+	spin_unlock(&m->q.lock);
+}
+
+static int wait_for_free(struct slot_map *m)
+{
+	long left = slot_timeout_secs * HZ;
+	DEFINE_WAIT(wait);
+
+	do {
+		long n = left, t;
+		if (likely(list_empty(&wait.task_list)))
+			__add_wait_queue_tail_exclusive(&m->q, &wait);
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		if (m->c > 0)
+			break;
+
+		if (m->c < 0) {
+			/* we are waiting for map to be installed */
+			/* it would better be there soon, or we go away */
+			if (n > ORANGEFS_BUFMAP_WAIT_TIMEOUT_SECS * HZ)
+				n = ORANGEFS_BUFMAP_WAIT_TIMEOUT_SECS * HZ;
+		}
+		spin_unlock(&m->q.lock);
+		t = schedule_timeout(n);
+		spin_lock(&m->q.lock);
+		if (unlikely(!t) && n != left && m->c < 0)
+			left = t;
+		else
+			left = t + (left - n);
+		if (unlikely(signal_pending(current)))
+			left = -EINTR;
+	} while (left > 0);
+
+	if (!list_empty(&wait.task_list))
+		list_del(&wait.task_list);
+	else if (left <= 0 && waitqueue_active(&m->q))
+		__wake_up_locked_key(&m->q, TASK_INTERRUPTIBLE, NULL);
+	__set_current_state(TASK_RUNNING);
+
+	if (likely(left > 0))
+		return 0;
+
+	return left < 0 ? -EINTR : -ETIMEDOUT;
+}
+
+static int get(struct slot_map *m)
+{
+	int res = 0;
+	spin_lock(&m->q.lock);
+	if (unlikely(m->c <= 0))
+		res = wait_for_free(m);
+	if (likely(!res)) {
+		m->c--;
+		res = find_first_zero_bit(m->map, m->count);
+		__set_bit(res, m->map);
+	}
+	spin_unlock(&m->q.lock);
+	return res;
+}
+
+/* used to describe mapped buffers */
+struct orangefs_bufmap_desc {
+	void *uaddr;			/* user space address pointer */
+	struct page **page_array;	/* array of mapped pages */
+	int array_count;		/* size of above arrays */
+	struct list_head list_link;
+};
+
+static struct orangefs_bufmap {
+	int desc_size;
+	int desc_shift;
+	int desc_count;
+	int total_size;
+	int page_count;
+
+	struct page **page_array;
+	struct orangefs_bufmap_desc *desc_array;
+
+	/* array to track usage of buffer descriptors */
+	unsigned long *buffer_index_array;
+
+	/* array to track usage of buffer descriptors for readdir */
+#define N DIV_ROUND_UP(ORANGEFS_READDIR_DEFAULT_DESC_COUNT, BITS_PER_LONG)
+	unsigned long readdir_index_array[N];
+#undef N
+} *__orangefs_bufmap;
+
+static DEFINE_SPINLOCK(orangefs_bufmap_lock);
+
+static void
+orangefs_bufmap_unmap(struct orangefs_bufmap *bufmap)
+{
+	int i;
+
+	for (i = 0; i < bufmap->page_count; i++)
+		page_cache_release(bufmap->page_array[i]);
+}
+
+static void
+orangefs_bufmap_free(struct orangefs_bufmap *bufmap)
+{
+	kfree(bufmap->page_array);
+	kfree(bufmap->desc_array);
+	kfree(bufmap->buffer_index_array);
+	kfree(bufmap);
+}
+
+/*
+ * XXX: Can the size and shift change while the caller gives up the 
+ * XXX: lock between calling this and doing something useful?
+ */
+
+int orangefs_bufmap_size_query(void)
+{
+	struct orangefs_bufmap *bufmap;
+	int size = 0;
+	spin_lock(&orangefs_bufmap_lock);
+	bufmap = __orangefs_bufmap;
+	if (bufmap)
+		size = bufmap->desc_size;
+	spin_unlock(&orangefs_bufmap_lock);
+	return size;
+}
+
+int orangefs_bufmap_shift_query(void)
+{
+	struct orangefs_bufmap *bufmap;
+	int shift = 0;
+	spin_lock(&orangefs_bufmap_lock);
+	bufmap = __orangefs_bufmap;
+	if (bufmap)
+		shift = bufmap->desc_shift;
+	spin_unlock(&orangefs_bufmap_lock);
+	return shift;
+}
+
+static DECLARE_WAIT_QUEUE_HEAD(bufmap_waitq);
+static DECLARE_WAIT_QUEUE_HEAD(readdir_waitq);
+
+/*
+ * orangefs_get_bufmap_init
+ *
+ * If bufmap_init is 1, then the shared memory system, including the
+ * buffer_index_array, is available.  Otherwise, it is not.
+ *
+ * returns the value of bufmap_init
+ */
+int orangefs_get_bufmap_init(void)
+{
+	return __orangefs_bufmap ? 1 : 0;
+}
+
+
+static struct orangefs_bufmap *
+orangefs_bufmap_alloc(struct ORANGEFS_dev_map_desc *user_desc)
+{
+	struct orangefs_bufmap *bufmap;
+
+	bufmap = kzalloc(sizeof(*bufmap), GFP_KERNEL);
+	if (!bufmap)
+		goto out;
+
+	bufmap->total_size = user_desc->total_size;
+	bufmap->desc_count = user_desc->count;
+	bufmap->desc_size = user_desc->size;
+	bufmap->desc_shift = ilog2(bufmap->desc_size);
+
+	bufmap->buffer_index_array =
+		kzalloc(DIV_ROUND_UP(bufmap->desc_count, BITS_PER_LONG), GFP_KERNEL);
+	if (!bufmap->buffer_index_array) {
+		gossip_err("orangefs: could not allocate %d buffer indices\n",
+				bufmap->desc_count);
+		goto out_free_bufmap;
+	}
+
+	bufmap->desc_array =
+		kcalloc(bufmap->desc_count, sizeof(struct orangefs_bufmap_desc),
+			GFP_KERNEL);
+	if (!bufmap->desc_array) {
+		gossip_err("orangefs: could not allocate %d descriptors\n",
+				bufmap->desc_count);
+		goto out_free_index_array;
+	}
+
+	bufmap->page_count = bufmap->total_size / PAGE_SIZE;
+
+	/* allocate storage to track our page mappings */
+	bufmap->page_array =
+		kcalloc(bufmap->page_count, sizeof(struct page *), GFP_KERNEL);
+	if (!bufmap->page_array)
+		goto out_free_desc_array;
+
+	return bufmap;
+
+out_free_desc_array:
+	kfree(bufmap->desc_array);
+out_free_index_array:
+	kfree(bufmap->buffer_index_array);
+out_free_bufmap:
+	kfree(bufmap);
+out:
+	return NULL;
+}
+
+static int
+orangefs_bufmap_map(struct orangefs_bufmap *bufmap,
+		struct ORANGEFS_dev_map_desc *user_desc)
+{
+	int pages_per_desc = bufmap->desc_size / PAGE_SIZE;
+	int offset = 0, ret, i;
+
+	/* map the pages */
+	ret = get_user_pages_fast((unsigned long)user_desc->ptr,
+			     bufmap->page_count, 1, bufmap->page_array);
+
+	if (ret < 0)
+		return ret;
+
+	if (ret != bufmap->page_count) {
+		gossip_err("orangefs error: asked for %d pages, only got %d.\n",
+				bufmap->page_count, ret);
+
+		for (i = 0; i < ret; i++) {
+			SetPageError(bufmap->page_array[i]);
+			page_cache_release(bufmap->page_array[i]);
+		}
+		return -ENOMEM;
+	}
+
+	/*
+	 * ideally we want to get kernel space pointers for each page, but
+	 * we can't kmap that many pages at once if highmem is being used.
+	 * so instead, we just kmap/kunmap the page address each time the
+	 * kaddr is needed.
+	 */
+	for (i = 0; i < bufmap->page_count; i++)
+		flush_dcache_page(bufmap->page_array[i]);
+
+	/* build a list of available descriptors */
+	for (offset = 0, i = 0; i < bufmap->desc_count; i++) {
+		bufmap->desc_array[i].page_array = &bufmap->page_array[offset];
+		bufmap->desc_array[i].array_count = pages_per_desc;
+		bufmap->desc_array[i].uaddr =
+		    (user_desc->ptr + (i * pages_per_desc * PAGE_SIZE));
+		offset += pages_per_desc;
+	}
+
+	return 0;
+}
+
+/*
+ * orangefs_bufmap_initialize()
+ *
+ * initializes the mapped buffer interface
+ *
+ * returns 0 on success, -errno on failure
+ */
+int orangefs_bufmap_initialize(struct ORANGEFS_dev_map_desc *user_desc)
+{
+	struct orangefs_bufmap *bufmap;
+	int ret = -EINVAL;
+
+	gossip_debug(GOSSIP_BUFMAP_DEBUG,
+		     "orangefs_bufmap_initialize: called (ptr ("
+		     "%p) sz (%d) cnt(%d).\n",
+		     user_desc->ptr,
+		     user_desc->size,
+		     user_desc->count);
+
+	/*
+	 * sanity check alignment and size of buffer that caller wants to
+	 * work with
+	 */
+	if (PAGE_ALIGN((unsigned long)user_desc->ptr) !=
+	    (unsigned long)user_desc->ptr) {
+		gossip_err("orangefs error: memory alignment (front). %p\n",
+			   user_desc->ptr);
+		goto out;
+	}
+
+	if (PAGE_ALIGN(((unsigned long)user_desc->ptr + user_desc->total_size))
+	    != (unsigned long)(user_desc->ptr + user_desc->total_size)) {
+		gossip_err("orangefs error: memory alignment (back).(%p + %d)\n",
+			   user_desc->ptr,
+			   user_desc->total_size);
+		goto out;
+	}
+
+	if (user_desc->total_size != (user_desc->size * user_desc->count)) {
+		gossip_err("orangefs error: user provided an oddly sized buffer: (%d, %d, %d)\n",
+			   user_desc->total_size,
+			   user_desc->size,
+			   user_desc->count);
+		goto out;
+	}
+
+	if ((user_desc->size % PAGE_SIZE) != 0) {
+		gossip_err("orangefs error: bufmap size not page size divisible (%d).\n",
+			   user_desc->size);
+		goto out;
+	}
+
+	ret = -ENOMEM;
+	bufmap = orangefs_bufmap_alloc(user_desc);
+	if (!bufmap)
+		goto out;
+
+	ret = orangefs_bufmap_map(bufmap, user_desc);
+	if (ret)
+		goto out_free_bufmap;
+
+
+	spin_lock(&orangefs_bufmap_lock);
+	if (__orangefs_bufmap) {
+		spin_unlock(&orangefs_bufmap_lock);
+		gossip_err("orangefs: error: bufmap already initialized.\n");
+		ret = -EINVAL;
+		goto out_unmap_bufmap;
+	}
+	__orangefs_bufmap = bufmap;
+	install(&rw_map,
+		bufmap->desc_count,
+		bufmap->buffer_index_array);
+	install(&readdir_map,
+		ORANGEFS_READDIR_DEFAULT_DESC_COUNT,
+		bufmap->readdir_index_array);
+	spin_unlock(&orangefs_bufmap_lock);
+
+	gossip_debug(GOSSIP_BUFMAP_DEBUG,
+		     "orangefs_bufmap_initialize: exiting normally\n");
+	return 0;
+
+out_unmap_bufmap:
+	orangefs_bufmap_unmap(bufmap);
+out_free_bufmap:
+	orangefs_bufmap_free(bufmap);
+out:
+	return ret;
+}
+
+/*
+ * orangefs_bufmap_finalize()
+ *
+ * shuts down the mapped buffer interface and releases any resources
+ * associated with it
+ *
+ * no return value
+ */
+void orangefs_bufmap_finalize(void)
+{
+	struct orangefs_bufmap *bufmap = __orangefs_bufmap;
+	if (!bufmap)
+		return;
+	gossip_debug(GOSSIP_BUFMAP_DEBUG, "orangefs_bufmap_finalize: called\n");
+	mark_killed(&rw_map);
+	mark_killed(&readdir_map);
+	gossip_debug(GOSSIP_BUFMAP_DEBUG,
+		     "orangefs_bufmap_finalize: exiting normally\n");
+}
+
+void orangefs_bufmap_run_down(void)
+{
+	struct orangefs_bufmap *bufmap = __orangefs_bufmap;
+	if (!bufmap)
+		return;
+	run_down(&rw_map);
+	run_down(&readdir_map);
+	spin_lock(&orangefs_bufmap_lock);
+	__orangefs_bufmap = NULL;
+	spin_unlock(&orangefs_bufmap_lock);
+	orangefs_bufmap_unmap(bufmap);
+	orangefs_bufmap_free(bufmap);
+}
+
+/*
+ * orangefs_bufmap_get()
+ *
+ * gets a free mapped buffer descriptor, will sleep until one becomes
+ * available if necessary
+ *
+ * returns slot on success, -errno on failure
+ */
+int orangefs_bufmap_get(void)
+{
+	return get(&rw_map);
+}
+
+/*
+ * orangefs_bufmap_put()
+ *
+ * returns a mapped buffer descriptor to the collection
+ *
+ * no return value
+ */
+void orangefs_bufmap_put(int buffer_index)
+{
+	put(&rw_map, buffer_index);
+}
+
+/*
+ * orangefs_readdir_index_get()
+ *
+ * gets a free descriptor, will sleep until one becomes
+ * available if necessary.
+ * Although the readdir buffers are not mapped into kernel space
+ * we could do that at a later point of time. Regardless, these
+ * indices are used by the client-core.
+ *
+ * returns slot on success, -errno on failure
+ */
+int orangefs_readdir_index_get(void)
+{
+	return get(&readdir_map);
+}
+
+void orangefs_readdir_index_put(int buffer_index)
+{
+	put(&readdir_map, buffer_index);
+}
+
+/*
+ * we've been handed an iovec, we need to copy it to 
+ * the shared memory descriptor at "buffer_index".
+ */
+int orangefs_bufmap_copy_from_iovec(struct iov_iter *iter,
+				int buffer_index,
+				size_t size)
+{
+	struct orangefs_bufmap_desc *to;
+	int i;
+
+	gossip_debug(GOSSIP_BUFMAP_DEBUG,
+		     "%s: buffer_index:%d: size:%zu:\n",
+		     __func__, buffer_index, size);
+
+	to = &__orangefs_bufmap->desc_array[buffer_index];
+	for (i = 0; size; i++) {
+		struct page *page = to->page_array[i];
+		size_t n = size;
+		if (n > PAGE_SIZE)
+			n = PAGE_SIZE;
+		n = copy_page_from_iter(page, 0, n, iter);
+		if (!n)
+			return -EFAULT;
+		size -= n;
+	}
+	return 0;
+
+}
+
+/*
+ * we've been handed an iovec, we need to fill it from
+ * the shared memory descriptor at "buffer_index".
+ */
+int orangefs_bufmap_copy_to_iovec(struct iov_iter *iter,
+				    int buffer_index,
+				    size_t size)
+{
+	struct orangefs_bufmap_desc *from;
+	int i;
+
+	from = &__orangefs_bufmap->desc_array[buffer_index];
+	gossip_debug(GOSSIP_BUFMAP_DEBUG,
+		     "%s: buffer_index:%d: size:%zu:\n",
+		     __func__, buffer_index, size);
+
+
+	for (i = 0; size; i++) {
+		struct page *page = from->page_array[i];
+		size_t n = size;
+		if (n > PAGE_SIZE)
+			n = PAGE_SIZE;
+		n = copy_page_to_iter(page, 0, n, iter);
+		if (!n)
+			return -EFAULT;
+		size -= n;
+	}
+	return 0;
+}
diff --git a/fs/orangefs/orangefs-bufmap.h b/fs/orangefs/orangefs-bufmap.h
new file mode 100644
index 000000000000..71f64f4057b5
--- /dev/null
+++ b/fs/orangefs/orangefs-bufmap.h
@@ -0,0 +1,36 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#ifndef __ORANGEFS_BUFMAP_H
+#define __ORANGEFS_BUFMAP_H
+
+int orangefs_bufmap_size_query(void);
+
+int orangefs_bufmap_shift_query(void);
+
+int orangefs_bufmap_initialize(struct ORANGEFS_dev_map_desc *user_desc);
+
+void orangefs_bufmap_finalize(void);
+
+void orangefs_bufmap_run_down(void);
+
+int orangefs_bufmap_get(void);
+
+void orangefs_bufmap_put(int buffer_index);
+
+int orangefs_readdir_index_get(void);
+
+void orangefs_readdir_index_put(int buffer_index);
+
+int orangefs_bufmap_copy_from_iovec(struct iov_iter *iter,
+				int buffer_index,
+				size_t size);
+
+int orangefs_bufmap_copy_to_iovec(struct iov_iter *iter,
+			      int buffer_index,
+			      size_t size);
+
+#endif /* __ORANGEFS_BUFMAP_H */
diff --git a/fs/orangefs/orangefs-cache.c b/fs/orangefs/orangefs-cache.c
new file mode 100644
index 000000000000..900a2e38e11b
--- /dev/null
+++ b/fs/orangefs/orangefs-cache.c
@@ -0,0 +1,161 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+
+/* tags assigned to kernel upcall operations */
+static __u64 next_tag_value;
+static DEFINE_SPINLOCK(next_tag_value_lock);
+
+/* the orangefs memory caches */
+
+/* a cache for orangefs upcall/downcall operations */
+static struct kmem_cache *op_cache;
+
+int op_cache_initialize(void)
+{
+	op_cache = kmem_cache_create("orangefs_op_cache",
+				     sizeof(struct orangefs_kernel_op_s),
+				     0,
+				     ORANGEFS_CACHE_CREATE_FLAGS,
+				     NULL);
+
+	if (!op_cache) {
+		gossip_err("Cannot create orangefs_op_cache\n");
+		return -ENOMEM;
+	}
+
+	/* initialize our atomic tag counter */
+	spin_lock(&next_tag_value_lock);
+	next_tag_value = 100;
+	spin_unlock(&next_tag_value_lock);
+	return 0;
+}
+
+int op_cache_finalize(void)
+{
+	kmem_cache_destroy(op_cache);
+	return 0;
+}
+
+char *get_opname_string(struct orangefs_kernel_op_s *new_op)
+{
+	if (new_op) {
+		__s32 type = new_op->upcall.type;
+
+		if (type == ORANGEFS_VFS_OP_FILE_IO)
+			return "OP_FILE_IO";
+		else if (type == ORANGEFS_VFS_OP_LOOKUP)
+			return "OP_LOOKUP";
+		else if (type == ORANGEFS_VFS_OP_CREATE)
+			return "OP_CREATE";
+		else if (type == ORANGEFS_VFS_OP_GETATTR)
+			return "OP_GETATTR";
+		else if (type == ORANGEFS_VFS_OP_REMOVE)
+			return "OP_REMOVE";
+		else if (type == ORANGEFS_VFS_OP_MKDIR)
+			return "OP_MKDIR";
+		else if (type == ORANGEFS_VFS_OP_READDIR)
+			return "OP_READDIR";
+		else if (type == ORANGEFS_VFS_OP_READDIRPLUS)
+			return "OP_READDIRPLUS";
+		else if (type == ORANGEFS_VFS_OP_SETATTR)
+			return "OP_SETATTR";
+		else if (type == ORANGEFS_VFS_OP_SYMLINK)
+			return "OP_SYMLINK";
+		else if (type == ORANGEFS_VFS_OP_RENAME)
+			return "OP_RENAME";
+		else if (type == ORANGEFS_VFS_OP_STATFS)
+			return "OP_STATFS";
+		else if (type == ORANGEFS_VFS_OP_TRUNCATE)
+			return "OP_TRUNCATE";
+		else if (type == ORANGEFS_VFS_OP_MMAP_RA_FLUSH)
+			return "OP_MMAP_RA_FLUSH";
+		else if (type == ORANGEFS_VFS_OP_FS_MOUNT)
+			return "OP_FS_MOUNT";
+		else if (type == ORANGEFS_VFS_OP_FS_UMOUNT)
+			return "OP_FS_UMOUNT";
+		else if (type == ORANGEFS_VFS_OP_GETXATTR)
+			return "OP_GETXATTR";
+		else if (type == ORANGEFS_VFS_OP_SETXATTR)
+			return "OP_SETXATTR";
+		else if (type == ORANGEFS_VFS_OP_LISTXATTR)
+			return "OP_LISTXATTR";
+		else if (type == ORANGEFS_VFS_OP_REMOVEXATTR)
+			return "OP_REMOVEXATTR";
+		else if (type == ORANGEFS_VFS_OP_PARAM)
+			return "OP_PARAM";
+		else if (type == ORANGEFS_VFS_OP_PERF_COUNT)
+			return "OP_PERF_COUNT";
+		else if (type == ORANGEFS_VFS_OP_CANCEL)
+			return "OP_CANCEL";
+		else if (type == ORANGEFS_VFS_OP_FSYNC)
+			return "OP_FSYNC";
+		else if (type == ORANGEFS_VFS_OP_FSKEY)
+			return "OP_FSKEY";
+	}
+	return "OP_UNKNOWN?";
+}
+
+void orangefs_new_tag(struct orangefs_kernel_op_s *op)
+{
+	spin_lock(&next_tag_value_lock);
+	op->tag = next_tag_value++;
+	if (next_tag_value == 0)
+		next_tag_value = 100;
+	spin_unlock(&next_tag_value_lock);
+}
+
+struct orangefs_kernel_op_s *op_alloc(__s32 type)
+{
+	struct orangefs_kernel_op_s *new_op = NULL;
+
+	new_op = kmem_cache_zalloc(op_cache, GFP_KERNEL);
+	if (new_op) {
+		INIT_LIST_HEAD(&new_op->list);
+		spin_lock_init(&new_op->lock);
+		init_completion(&new_op->waitq);
+
+		new_op->upcall.type = ORANGEFS_VFS_OP_INVALID;
+		new_op->downcall.type = ORANGEFS_VFS_OP_INVALID;
+		new_op->downcall.status = -1;
+
+		new_op->op_state = OP_VFS_STATE_UNKNOWN;
+
+		/* initialize the op specific tag and upcall credentials */
+		orangefs_new_tag(new_op);
+		new_op->upcall.type = type;
+		new_op->attempts = 0;
+		gossip_debug(GOSSIP_CACHE_DEBUG,
+			     "Alloced OP (%p: %llu %s)\n",
+			     new_op,
+			     llu(new_op->tag),
+			     get_opname_string(new_op));
+
+		new_op->upcall.uid = from_kuid(current_user_ns(),
+					       current_fsuid());
+
+		new_op->upcall.gid = from_kgid(current_user_ns(),
+					       current_fsgid());
+	} else {
+		gossip_err("op_alloc: kmem_cache_zalloc failed!\n");
+	}
+	return new_op;
+}
+
+void op_release(struct orangefs_kernel_op_s *orangefs_op)
+{
+	if (orangefs_op) {
+		gossip_debug(GOSSIP_CACHE_DEBUG,
+			     "Releasing OP (%p: %llu)\n",
+			     orangefs_op,
+			     llu(orangefs_op->tag));
+		kmem_cache_free(op_cache, orangefs_op);
+	} else {
+		gossip_err("NULL pointer in op_release\n");
+	}
+}
diff --git a/fs/orangefs/orangefs-debug.h b/fs/orangefs/orangefs-debug.h
new file mode 100644
index 000000000000..387db17cde2b
--- /dev/null
+++ b/fs/orangefs/orangefs-debug.h
@@ -0,0 +1,92 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/* This file just defines debugging masks to be used with the gossip
+ * logging utility.  All debugging masks for ORANGEFS are kept here to make
+ * sure we don't have collisions.
+ */
+
+#ifndef __ORANGEFS_DEBUG_H
+#define __ORANGEFS_DEBUG_H
+
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <stdint.h>
+#endif
+
+#define	GOSSIP_NO_DEBUG			(__u64)0
+
+#define GOSSIP_SUPER_DEBUG		((__u64)1 << 0)
+#define GOSSIP_INODE_DEBUG		((__u64)1 << 1)
+#define GOSSIP_FILE_DEBUG		((__u64)1 << 2)
+#define GOSSIP_DIR_DEBUG		((__u64)1 << 3)
+#define GOSSIP_UTILS_DEBUG		((__u64)1 << 4)
+#define GOSSIP_WAIT_DEBUG		((__u64)1 << 5)
+#define GOSSIP_ACL_DEBUG		((__u64)1 << 6)
+#define GOSSIP_DCACHE_DEBUG		((__u64)1 << 7)
+#define GOSSIP_DEV_DEBUG		((__u64)1 << 8)
+#define GOSSIP_NAME_DEBUG		((__u64)1 << 9)
+#define GOSSIP_BUFMAP_DEBUG		((__u64)1 << 10)
+#define GOSSIP_CACHE_DEBUG		((__u64)1 << 11)
+#define GOSSIP_DEBUGFS_DEBUG		((__u64)1 << 12)
+#define GOSSIP_XATTR_DEBUG		((__u64)1 << 13)
+#define GOSSIP_INIT_DEBUG		((__u64)1 << 14)
+#define GOSSIP_SYSFS_DEBUG		((__u64)1 << 15)
+
+#define GOSSIP_MAX_NR                 16
+#define GOSSIP_MAX_DEBUG              (((__u64)1 << GOSSIP_MAX_NR) - 1)
+
+/*function prototypes*/
+__u64 ORANGEFS_kmod_eventlog_to_mask(const char *event_logging);
+__u64 ORANGEFS_debug_eventlog_to_mask(const char *event_logging);
+char *ORANGEFS_debug_mask_to_eventlog(__u64 mask);
+char *ORANGEFS_kmod_mask_to_eventlog(__u64 mask);
+
+/* a private internal type */
+struct __keyword_mask_s {
+	const char *keyword;
+	__u64 mask_val;
+};
+
+/*
+ * Map all kmod keywords to kmod debug masks here. Keep this
+ * structure "packed":
+ *
+ *   "all" is always last...
+ *
+ *   keyword     mask_val     index
+ *     foo          1           0
+ *     bar          2           1
+ *     baz          4           2
+ *     qux          8           3
+ *      .           .           .
+ */
+static struct __keyword_mask_s s_kmod_keyword_mask_map[] = {
+	{"super", GOSSIP_SUPER_DEBUG},
+	{"inode", GOSSIP_INODE_DEBUG},
+	{"file", GOSSIP_FILE_DEBUG},
+	{"dir", GOSSIP_DIR_DEBUG},
+	{"utils", GOSSIP_UTILS_DEBUG},
+	{"wait", GOSSIP_WAIT_DEBUG},
+	{"acl", GOSSIP_ACL_DEBUG},
+	{"dcache", GOSSIP_DCACHE_DEBUG},
+	{"dev", GOSSIP_DEV_DEBUG},
+	{"name", GOSSIP_NAME_DEBUG},
+	{"bufmap", GOSSIP_BUFMAP_DEBUG},
+	{"cache", GOSSIP_CACHE_DEBUG},
+	{"debugfs", GOSSIP_DEBUGFS_DEBUG},
+	{"xattr", GOSSIP_XATTR_DEBUG},
+	{"init", GOSSIP_INIT_DEBUG},
+	{"sysfs", GOSSIP_SYSFS_DEBUG},
+	{"none", GOSSIP_NO_DEBUG},
+	{"all", GOSSIP_MAX_DEBUG}
+};
+
+static const int num_kmod_keyword_mask_map = (int)
+	(sizeof(s_kmod_keyword_mask_map) / sizeof(struct __keyword_mask_s));
+
+#endif /* __ORANGEFS_DEBUG_H */
diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
new file mode 100644
index 000000000000..19670b8b4053
--- /dev/null
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -0,0 +1,455 @@
+/*
+ * What:		/sys/kernel/debug/orangefs/debug-help
+ * Date:		June 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			List of client and kernel debug keywords.
+ *
+ *
+ * What:		/sys/kernel/debug/orangefs/client-debug
+ * Date:		June 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Debug setting for "the client", the userspace
+ * 			helper for the kernel module.
+ *
+ *
+ * What:		/sys/kernel/debug/orangefs/kernel-debug
+ * Date:		June 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Debug setting for the orangefs kernel module.
+ *
+ * 			Any of the keywords, or comma-separated lists
+ * 			of keywords, from debug-help can be catted to
+ * 			client-debug or kernel-debug.
+ *
+ * 			"none", "all" and "verbose" are special keywords
+ * 			for client-debug. Setting client-debug to "all"
+ * 			is kind of like trying to drink water from a
+ * 			fire hose, "verbose" triggers most of the same
+ * 			output except for the constant flow of output
+ * 			from the main wait loop.
+ *
+ * 			"none" and "all" are similar settings for kernel-debug
+ * 			no need for a "verbose".
+ */
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+
+#include <linux/uaccess.h>
+
+#include "orangefs-debugfs.h"
+#include "protocol.h"
+#include "orangefs-kernel.h"
+
+static int orangefs_debug_disabled = 1;
+
+static int orangefs_debug_help_open(struct inode *, struct file *);
+
+const struct file_operations debug_help_fops = {
+	.open           = orangefs_debug_help_open,
+	.read           = seq_read,
+	.release        = seq_release,
+	.llseek         = seq_lseek,
+};
+
+static void *help_start(struct seq_file *, loff_t *);
+static void *help_next(struct seq_file *, void *, loff_t *);
+static void help_stop(struct seq_file *, void *);
+static int help_show(struct seq_file *, void *);
+
+static const struct seq_operations help_debug_ops = {
+	.start	= help_start,
+	.next	= help_next,
+	.stop	= help_stop,
+	.show	= help_show,
+};
+
+/*
+ * Used to protect data in ORANGEFS_KMOD_DEBUG_FILE and
+ * ORANGEFS_KMOD_DEBUG_FILE.
+ */
+static DEFINE_MUTEX(orangefs_debug_lock);
+
+int orangefs_debug_open(struct inode *, struct file *);
+
+static ssize_t orangefs_debug_read(struct file *,
+				 char __user *,
+				 size_t,
+				 loff_t *);
+
+static ssize_t orangefs_debug_write(struct file *,
+				  const char __user *,
+				  size_t,
+				  loff_t *);
+
+static const struct file_operations kernel_debug_fops = {
+	.open           = orangefs_debug_open,
+	.read           = orangefs_debug_read,
+	.write		= orangefs_debug_write,
+	.llseek         = generic_file_llseek,
+};
+
+/*
+ * initialize kmod debug operations, create orangefs debugfs dir and
+ * ORANGEFS_KMOD_DEBUG_HELP_FILE.
+ */
+int orangefs_debugfs_init(void)
+{
+
+	int rc = -ENOMEM;
+
+	debug_dir = debugfs_create_dir("orangefs", NULL);
+	if (!debug_dir) {
+		pr_info("%s: debugfs_create_dir failed.\n", __func__);
+		goto out;
+	}
+
+	help_file_dentry = debugfs_create_file(ORANGEFS_KMOD_DEBUG_HELP_FILE,
+				  0444,
+				  debug_dir,
+				  debug_help_string,
+				  &debug_help_fops);
+	if (!help_file_dentry) {
+		pr_info("%s: debugfs_create_file failed.\n", __func__);
+		goto out;
+	}
+
+	orangefs_debug_disabled = 0;
+	rc = 0;
+
+out:
+
+	return rc;
+}
+
+void orangefs_debugfs_cleanup(void)
+{
+	if (debug_dir)
+		debugfs_remove_recursive(debug_dir);
+}
+
+/* open ORANGEFS_KMOD_DEBUG_HELP_FILE */
+static int orangefs_debug_help_open(struct inode *inode, struct file *file)
+{
+	int rc = -ENODEV;
+	int ret;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "orangefs_debug_help_open: start\n");
+
+	if (orangefs_debug_disabled)
+		goto out;
+
+	ret = seq_open(file, &help_debug_ops);
+	if (ret)
+		goto out;
+
+	((struct seq_file *)(file->private_data))->private = inode->i_private;
+
+	rc = 0;
+
+out:
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "orangefs_debug_help_open: rc:%d:\n",
+		     rc);
+	return rc;
+}
+
+/*
+ * I think start always gets called again after stop. Start
+ * needs to return NULL when it is done. The whole "payload"
+ * in this case is a single (long) string, so by the second
+ * time we get to start (pos = 1), we're done.
+ */
+static void *help_start(struct seq_file *m, loff_t *pos)
+{
+	void *payload = NULL;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_start: start\n");
+
+	if (*pos == 0)
+		payload = m->private;
+
+	return payload;
+}
+
+static void *help_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_next: start\n");
+
+	return NULL;
+}
+
+static void help_stop(struct seq_file *m, void *p)
+{
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_stop: start\n");
+}
+
+static int help_show(struct seq_file *m, void *v)
+{
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_show: start\n");
+
+	seq_puts(m, v);
+
+	return 0;
+}
+
+/*
+ * initialize the kernel-debug file.
+ */
+int orangefs_kernel_debug_init(void)
+{
+	int rc = -ENOMEM;
+	struct dentry *ret;
+	char *k_buffer = NULL;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__);
+
+	k_buffer = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
+	if (!k_buffer)
+		goto out;
+
+	if (strlen(kernel_debug_string) + 1 < ORANGEFS_MAX_DEBUG_STRING_LEN) {
+		strcpy(k_buffer, kernel_debug_string);
+		strcat(k_buffer, "\n");
+	} else {
+		strcpy(k_buffer, "none\n");
+		pr_info("%s: overflow 1!\n", __func__);
+	}
+
+	ret = debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE,
+				  0444,
+				  debug_dir,
+				  k_buffer,
+				  &kernel_debug_fops);
+	if (!ret) {
+		pr_info("%s: failed to create %s.\n",
+			__func__,
+			ORANGEFS_KMOD_DEBUG_FILE);
+		goto out;
+	}
+
+	rc = 0;
+
+out:
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc);
+	return rc;
+}
+
+/*
+ * initialize the client-debug file.
+ */
+int orangefs_client_debug_init(void)
+{
+
+	int rc = -ENOMEM;
+	char *c_buffer = NULL;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__);
+
+	c_buffer = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
+	if (!c_buffer)
+		goto out;
+
+	if (strlen(client_debug_string) + 1 < ORANGEFS_MAX_DEBUG_STRING_LEN) {
+		strcpy(c_buffer, client_debug_string);
+		strcat(c_buffer, "\n");
+	} else {
+		strcpy(c_buffer, "none\n");
+		pr_info("%s: overflow! 2\n", __func__);
+	}
+
+	client_debug_dentry = debugfs_create_file(ORANGEFS_CLIENT_DEBUG_FILE,
+						  0444,
+						  debug_dir,
+						  c_buffer,
+						  &kernel_debug_fops);
+	if (!client_debug_dentry) {
+		pr_info("%s: failed to create updated %s.\n",
+			__func__,
+			ORANGEFS_CLIENT_DEBUG_FILE);
+		goto out;
+	}
+
+	rc = 0;
+
+out:
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc);
+	return rc;
+}
+
+/* open ORANGEFS_KMOD_DEBUG_FILE or ORANGEFS_CLIENT_DEBUG_FILE.*/
+int orangefs_debug_open(struct inode *inode, struct file *file)
+{
+	int rc = -ENODEV;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "%s: orangefs_debug_disabled: %d\n",
+		     __func__,
+		     orangefs_debug_disabled);
+
+	if (orangefs_debug_disabled)
+		goto out;
+
+	rc = 0;
+	mutex_lock(&orangefs_debug_lock);
+	file->private_data = inode->i_private;
+	mutex_unlock(&orangefs_debug_lock);
+
+out:
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "orangefs_debug_open: rc: %d\n",
+		     rc);
+	return rc;
+}
+
+static ssize_t orangefs_debug_read(struct file *file,
+				 char __user *ubuf,
+				 size_t count,
+				 loff_t *ppos)
+{
+	char *buf;
+	int sprintf_ret;
+	ssize_t read_ret = -ENOMEM;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "orangefs_debug_read: start\n");
+
+	buf = kmalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
+	if (!buf)
+		goto out;
+
+	mutex_lock(&orangefs_debug_lock);
+	sprintf_ret = sprintf(buf, "%s", (char *)file->private_data);
+	mutex_unlock(&orangefs_debug_lock);
+
+	read_ret = simple_read_from_buffer(ubuf, count, ppos, buf, sprintf_ret);
+
+	kfree(buf);
+
+out:
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "orangefs_debug_read: ret: %zu\n",
+		     read_ret);
+
+	return read_ret;
+}
+
+static ssize_t orangefs_debug_write(struct file *file,
+				  const char __user *ubuf,
+				  size_t count,
+				  loff_t *ppos)
+{
+	char *buf;
+	int rc = -EFAULT;
+	size_t silly = 0;
+	char *debug_string;
+	struct orangefs_kernel_op_s *new_op = NULL;
+	struct client_debug_mask c_mask = { NULL, 0, 0 };
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		"orangefs_debug_write: %s\n",
+		file->f_path.dentry->d_name.name);
+
+	/*
+	 * Thwart users who try to jamb a ridiculous number
+	 * of bytes into the debug file...
+	 */
+	if (count > ORANGEFS_MAX_DEBUG_STRING_LEN + 1) {
+		silly = count;
+		count = ORANGEFS_MAX_DEBUG_STRING_LEN + 1;
+	}
+
+	buf = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
+	if (!buf)
+		goto out;
+
+	if (copy_from_user(buf, ubuf, count - 1)) {
+		gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+			     "%s: copy_from_user failed!\n",
+			     __func__);
+		goto out;
+	}
+
+	/*
+	 * Map the keyword string from userspace into a valid debug mask.
+	 * The mapping process involves mapping the human-inputted string
+	 * into a valid mask, and then rebuilding the string from the
+	 * verified valid mask.
+	 *
+	 * A service operation is required to set a new client-side
+	 * debug mask.
+	 */
+	if (!strcmp(file->f_path.dentry->d_name.name,
+		    ORANGEFS_KMOD_DEBUG_FILE)) {
+		debug_string_to_mask(buf, &gossip_debug_mask, 0);
+		debug_mask_to_string(&gossip_debug_mask, 0);
+		debug_string = kernel_debug_string;
+		gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+			     "New kernel debug string is %s\n",
+			     kernel_debug_string);
+	} else {
+		/* Can't reset client debug mask if client is not running. */
+		if (is_daemon_in_service()) {
+			pr_info("%s: Client not running :%d:\n",
+				__func__,
+				is_daemon_in_service());
+			goto out;
+		}
+
+		debug_string_to_mask(buf, &c_mask, 1);
+		debug_mask_to_string(&c_mask, 1);
+		debug_string = client_debug_string;
+
+		new_op = op_alloc(ORANGEFS_VFS_OP_PARAM);
+		if (!new_op) {
+			pr_info("%s: op_alloc failed!\n", __func__);
+			goto out;
+		}
+
+		new_op->upcall.req.param.op =
+			ORANGEFS_PARAM_REQUEST_OP_TWO_MASK_VALUES;
+		new_op->upcall.req.param.type = ORANGEFS_PARAM_REQUEST_SET;
+		memset(new_op->upcall.req.param.s_value,
+		       0,
+		       ORANGEFS_MAX_DEBUG_STRING_LEN);
+		sprintf(new_op->upcall.req.param.s_value,
+			"%llx %llx\n",
+			c_mask.mask1,
+			c_mask.mask2);
+
+		/* service_operation returns 0 on success... */
+		rc = service_operation(new_op,
+				       "orangefs_param",
+					ORANGEFS_OP_INTERRUPTIBLE);
+
+		if (rc)
+			gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+				     "%s: service_operation failed! rc:%d:\n",
+				     __func__,
+				     rc);
+
+		op_release(new_op);
+	}
+
+	mutex_lock(&orangefs_debug_lock);
+	memset(file->f_inode->i_private, 0, ORANGEFS_MAX_DEBUG_STRING_LEN);
+	sprintf((char *)file->f_inode->i_private, "%s\n", debug_string);
+	mutex_unlock(&orangefs_debug_lock);
+
+	*ppos += count;
+	if (silly)
+		rc = silly;
+	else
+		rc = count;
+
+out:
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "orangefs_debug_write: rc: %d\n",
+		     rc);
+	kfree(buf);
+	return rc;
+}
diff --git a/fs/orangefs/orangefs-debugfs.h b/fs/orangefs/orangefs-debugfs.h
new file mode 100644
index 000000000000..e4828c0e3ef9
--- /dev/null
+++ b/fs/orangefs/orangefs-debugfs.h
@@ -0,0 +1,3 @@
+int orangefs_debugfs_init(void);
+int orangefs_kernel_debug_init(void);
+void orangefs_debugfs_cleanup(void);
diff --git a/fs/orangefs/orangefs-dev-proto.h b/fs/orangefs/orangefs-dev-proto.h
new file mode 100644
index 000000000000..9eac9d9a3f3a
--- /dev/null
+++ b/fs/orangefs/orangefs-dev-proto.h
@@ -0,0 +1,62 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#ifndef _ORANGEFS_DEV_PROTO_H
+#define _ORANGEFS_DEV_PROTO_H
+
+/*
+ * types and constants shared between user space and kernel space for
+ * device interaction using a common protocol
+ */
+
+/*
+ * valid orangefs kernel operation types
+ */
+#define ORANGEFS_VFS_OP_INVALID           0xFF000000
+#define ORANGEFS_VFS_OP_FILE_IO        0xFF000001
+#define ORANGEFS_VFS_OP_LOOKUP         0xFF000002
+#define ORANGEFS_VFS_OP_CREATE         0xFF000003
+#define ORANGEFS_VFS_OP_GETATTR        0xFF000004
+#define ORANGEFS_VFS_OP_REMOVE         0xFF000005
+#define ORANGEFS_VFS_OP_MKDIR          0xFF000006
+#define ORANGEFS_VFS_OP_READDIR        0xFF000007
+#define ORANGEFS_VFS_OP_SETATTR        0xFF000008
+#define ORANGEFS_VFS_OP_SYMLINK        0xFF000009
+#define ORANGEFS_VFS_OP_RENAME         0xFF00000A
+#define ORANGEFS_VFS_OP_STATFS         0xFF00000B
+#define ORANGEFS_VFS_OP_TRUNCATE       0xFF00000C
+#define ORANGEFS_VFS_OP_MMAP_RA_FLUSH  0xFF00000D
+#define ORANGEFS_VFS_OP_FS_MOUNT       0xFF00000E
+#define ORANGEFS_VFS_OP_FS_UMOUNT      0xFF00000F
+#define ORANGEFS_VFS_OP_GETXATTR       0xFF000010
+#define ORANGEFS_VFS_OP_SETXATTR          0xFF000011
+#define ORANGEFS_VFS_OP_LISTXATTR         0xFF000012
+#define ORANGEFS_VFS_OP_REMOVEXATTR       0xFF000013
+#define ORANGEFS_VFS_OP_PARAM          0xFF000014
+#define ORANGEFS_VFS_OP_PERF_COUNT     0xFF000015
+#define ORANGEFS_VFS_OP_CANCEL            0xFF00EE00
+#define ORANGEFS_VFS_OP_FSYNC          0xFF00EE01
+#define ORANGEFS_VFS_OP_FSKEY             0xFF00EE02
+#define ORANGEFS_VFS_OP_READDIRPLUS       0xFF00EE03
+
+/*
+ * Misc constants. Please retain them as multiples of 8!
+ * Otherwise 32-64 bit interactions will be messed up :)
+ */
+#define ORANGEFS_MAX_DEBUG_STRING_LEN	0x00000400
+#define ORANGEFS_MAX_DEBUG_ARRAY_LEN	0x00000800
+
+/*
+ * The maximum number of directory entries in a single request is 96.
+ * XXX: Why can this not be higher. The client-side code can handle up to 512.
+ * XXX: What happens if we expect more than the client can return?
+ */
+#define ORANGEFS_MAX_DIRENT_COUNT_READDIR 96
+
+#include "upcall.h"
+#include "downcall.h"
+
+#endif
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
new file mode 100644
index 000000000000..a9925e296ceb
--- /dev/null
+++ b/fs/orangefs/orangefs-kernel.h
@@ -0,0 +1,623 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  The ORANGEFS Linux kernel support allows ORANGEFS volumes to be mounted and
+ *  accessed through the Linux VFS (i.e. using standard I/O system calls).
+ *  This support is only needed on clients that wish to mount the file system.
+ *
+ */
+
+/*
+ *  Declarations and macros for the ORANGEFS Linux kernel support.
+ */
+
+#ifndef __ORANGEFSKERNEL_H
+#define __ORANGEFSKERNEL_H
+
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/statfs.h>
+#include <linux/backing-dev.h>
+#include <linux/device.h>
+#include <linux/mpage.h>
+#include <linux/namei.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/vmalloc.h>
+
+#include <linux/aio.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/compat.h>
+#include <linux/mount.h>
+#include <linux/uaccess.h>
+#include <linux/atomic.h>
+#include <linux/uio.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/wait.h>
+#include <linux/dcache.h>
+#include <linux/pagemap.h>
+#include <linux/poll.h>
+#include <linux/rwsem.h>
+#include <linux/xattr.h>
+#include <linux/exportfs.h>
+
+#include <asm/unaligned.h>
+
+#include "orangefs-dev-proto.h"
+
+#ifdef ORANGEFS_KERNEL_DEBUG
+#define ORANGEFS_DEFAULT_OP_TIMEOUT_SECS       10
+#else
+#define ORANGEFS_DEFAULT_OP_TIMEOUT_SECS       20
+#endif
+
+#define ORANGEFS_BUFMAP_WAIT_TIMEOUT_SECS   30
+
+#define ORANGEFS_DEFAULT_SLOT_TIMEOUT_SECS     900	/* 15 minutes */
+
+#define ORANGEFS_REQDEVICE_NAME          "pvfs2-req"
+
+#define ORANGEFS_DEVREQ_MAGIC             0x20030529
+#define ORANGEFS_LINK_MAX                 0x000000FF
+#define ORANGEFS_PURGE_RETRY_COUNT     0x00000005
+#define ORANGEFS_MAX_NUM_OPTIONS          0x00000004
+#define ORANGEFS_MAX_MOUNT_OPT_LEN        0x00000080
+#define ORANGEFS_MAX_FSKEY_LEN            64
+
+#define MAX_DEV_REQ_UPSIZE (2 * sizeof(__s32) +   \
+sizeof(__u64) + sizeof(struct orangefs_upcall_s))
+#define MAX_DEV_REQ_DOWNSIZE (2 * sizeof(__s32) + \
+sizeof(__u64) + sizeof(struct orangefs_downcall_s))
+
+/*
+ * valid orangefs kernel operation states
+ *
+ * unknown  - op was just initialized
+ * waiting  - op is on request_list (upward bound)
+ * inprogr  - op is in progress (waiting for downcall)
+ * serviced - op has matching downcall; ok
+ * purged   - op has to start a timer since client-core
+ *            exited uncleanly before servicing op
+ * given up - submitter has given up waiting for it
+ */
+enum orangefs_vfs_op_states {
+	OP_VFS_STATE_UNKNOWN = 0,
+	OP_VFS_STATE_WAITING = 1,
+	OP_VFS_STATE_INPROGR = 2,
+	OP_VFS_STATE_SERVICED = 4,
+	OP_VFS_STATE_PURGED = 8,
+	OP_VFS_STATE_GIVEN_UP = 16,
+};
+
+/*
+ * An array of client_debug_mask will be built to hold debug keyword/mask
+ * values fetched from userspace.
+ */
+struct client_debug_mask {
+	char *keyword;
+	__u64 mask1;
+	__u64 mask2;
+};
+
+/*
+ * orangefs kernel memory related flags
+ */
+
+#if ((defined ORANGEFS_KERNEL_DEBUG) && (defined CONFIG_DEBUG_SLAB))
+#define ORANGEFS_CACHE_CREATE_FLAGS SLAB_RED_ZONE
+#else
+#define ORANGEFS_CACHE_CREATE_FLAGS 0
+#endif /* ((defined ORANGEFS_KERNEL_DEBUG) && (defined CONFIG_DEBUG_SLAB)) */
+
+/* orangefs xattr and acl related defines */
+#define ORANGEFS_XATTR_INDEX_POSIX_ACL_ACCESS  1
+#define ORANGEFS_XATTR_INDEX_POSIX_ACL_DEFAULT 2
+#define ORANGEFS_XATTR_INDEX_TRUSTED           3
+#define ORANGEFS_XATTR_INDEX_DEFAULT           4
+
+#define ORANGEFS_XATTR_NAME_ACL_ACCESS XATTR_NAME_POSIX_ACL_ACCESS
+#define ORANGEFS_XATTR_NAME_ACL_DEFAULT XATTR_NAME_POSIX_ACL_DEFAULT
+#define ORANGEFS_XATTR_NAME_TRUSTED_PREFIX "trusted."
+#define ORANGEFS_XATTR_NAME_DEFAULT_PREFIX ""
+
+/* these functions are defined in orangefs-utils.c */
+int orangefs_prepare_cdm_array(char *debug_array_string);
+int orangefs_prepare_debugfs_help_string(int);
+
+/* defined in orangefs-debugfs.c */
+int orangefs_client_debug_init(void);
+
+void debug_string_to_mask(char *, void *, int);
+void do_c_mask(int, char *, struct client_debug_mask **);
+void do_k_mask(int, char *, __u64 **);
+
+void debug_mask_to_string(void *, int);
+void do_k_string(void *, int);
+void do_c_string(void *, int);
+int check_amalgam_keyword(void *, int);
+int keyword_is_amalgam(char *);
+
+/*these variables are defined in orangefs-mod.c */
+extern char kernel_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+extern char client_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+extern char client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+extern unsigned int kernel_mask_set_mod_init;
+
+extern int orangefs_init_acl(struct inode *inode, struct inode *dir);
+extern const struct xattr_handler *orangefs_xattr_handlers[];
+
+extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type);
+extern int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+
+/*
+ * Redefine xtvec structure so that we could move helper functions out of
+ * the define
+ */
+struct xtvec {
+	__kernel_off_t xtv_off;		/* must be off_t */
+	__kernel_size_t xtv_len;	/* must be size_t */
+};
+
+/*
+ * orangefs data structures
+ */
+struct orangefs_kernel_op_s {
+	enum orangefs_vfs_op_states op_state;
+	__u64 tag;
+
+	/*
+	 * Set uses_shared_memory to non zero if this operation uses
+	 * shared memory. If true, then a retry on the op must also
+	 * get a new shared memory buffer and re-populate it.
+	 * Cancels don't care - it only matters for service_operation()
+	 * retry logics and cancels don't go through it anymore. It
+	 * safely stays non-zero when we use it as slot_to_free.
+	 */
+	union {
+		int uses_shared_memory;
+		int slot_to_free;
+	};
+
+	struct orangefs_upcall_s upcall;
+	struct orangefs_downcall_s downcall;
+
+	struct completion waitq;
+	spinlock_t lock;
+
+	int attempts;
+
+	struct list_head list;
+};
+
+#define set_op_state_waiting(op)     ((op)->op_state = OP_VFS_STATE_WAITING)
+#define set_op_state_inprogress(op)  ((op)->op_state = OP_VFS_STATE_INPROGR)
+#define set_op_state_given_up(op)  ((op)->op_state = OP_VFS_STATE_GIVEN_UP)
+static inline void set_op_state_serviced(struct orangefs_kernel_op_s *op)
+{
+	op->op_state = OP_VFS_STATE_SERVICED;
+	complete(&op->waitq);
+}
+
+#define op_state_waiting(op)     ((op)->op_state & OP_VFS_STATE_WAITING)
+#define op_state_in_progress(op) ((op)->op_state & OP_VFS_STATE_INPROGR)
+#define op_state_serviced(op)    ((op)->op_state & OP_VFS_STATE_SERVICED)
+#define op_state_purged(op)      ((op)->op_state & OP_VFS_STATE_PURGED)
+#define op_state_given_up(op)    ((op)->op_state & OP_VFS_STATE_GIVEN_UP)
+#define op_is_cancel(op)         ((op)->upcall.type == ORANGEFS_VFS_OP_CANCEL)
+
+void op_release(struct orangefs_kernel_op_s *op);
+
+extern void orangefs_bufmap_put(int);
+static inline void put_cancel(struct orangefs_kernel_op_s *op)
+{
+	orangefs_bufmap_put(op->slot_to_free);
+	op_release(op);
+}
+
+static inline void set_op_state_purged(struct orangefs_kernel_op_s *op)
+{
+	spin_lock(&op->lock);
+	if (unlikely(op_is_cancel(op))) {
+		list_del_init(&op->list);
+		spin_unlock(&op->lock);
+		put_cancel(op);
+	} else {
+		op->op_state |= OP_VFS_STATE_PURGED;
+		complete(&op->waitq);
+		spin_unlock(&op->lock);
+	}
+}
+
+/* per inode private orangefs info */
+struct orangefs_inode_s {
+	struct orangefs_object_kref refn;
+	char link_target[ORANGEFS_NAME_MAX];
+	__s64 blksize;
+	/*
+	 * Reading/Writing Extended attributes need to acquire the appropriate
+	 * reader/writer semaphore on the orangefs_inode_s structure.
+	 */
+	struct rw_semaphore xattr_sem;
+
+	struct inode vfs_inode;
+	sector_t last_failed_block_index_read;
+
+	/*
+	 * State of in-memory attributes not yet flushed to disk associated
+	 * with this object
+	 */
+	unsigned long pinode_flags;
+};
+
+#define P_ATIME_FLAG 0
+#define P_MTIME_FLAG 1
+#define P_CTIME_FLAG 2
+#define P_MODE_FLAG  3
+
+#define ClearAtimeFlag(pinode) clear_bit(P_ATIME_FLAG, &(pinode)->pinode_flags)
+#define SetAtimeFlag(pinode)   set_bit(P_ATIME_FLAG, &(pinode)->pinode_flags)
+#define AtimeFlag(pinode)      test_bit(P_ATIME_FLAG, &(pinode)->pinode_flags)
+
+#define ClearMtimeFlag(pinode) clear_bit(P_MTIME_FLAG, &(pinode)->pinode_flags)
+#define SetMtimeFlag(pinode)   set_bit(P_MTIME_FLAG, &(pinode)->pinode_flags)
+#define MtimeFlag(pinode)      test_bit(P_MTIME_FLAG, &(pinode)->pinode_flags)
+
+#define ClearCtimeFlag(pinode) clear_bit(P_CTIME_FLAG, &(pinode)->pinode_flags)
+#define SetCtimeFlag(pinode)   set_bit(P_CTIME_FLAG, &(pinode)->pinode_flags)
+#define CtimeFlag(pinode)      test_bit(P_CTIME_FLAG, &(pinode)->pinode_flags)
+
+#define ClearModeFlag(pinode) clear_bit(P_MODE_FLAG, &(pinode)->pinode_flags)
+#define SetModeFlag(pinode)   set_bit(P_MODE_FLAG, &(pinode)->pinode_flags)
+#define ModeFlag(pinode)      test_bit(P_MODE_FLAG, &(pinode)->pinode_flags)
+
+/* per superblock private orangefs info */
+struct orangefs_sb_info_s {
+	struct orangefs_khandle root_khandle;
+	__s32 fs_id;
+	int id;
+	int flags;
+#define ORANGEFS_OPT_INTR	0x01
+#define ORANGEFS_OPT_LOCAL_LOCK	0x02
+	char devname[ORANGEFS_MAX_SERVER_ADDR_LEN];
+	struct super_block *sb;
+	int mount_pending;
+	struct list_head list;
+};
+
+/*
+ * structure that holds the state of any async I/O operation issued
+ * through the VFS. Needed especially to handle cancellation requests
+ * or even completion notification so that the VFS client-side daemon
+ * can free up its vfs_request slots.
+ */
+struct orangefs_kiocb_s {
+	/* the pointer to the task that initiated the AIO */
+	struct task_struct *tsk;
+
+	/* pointer to the kiocb that kicked this operation */
+	struct kiocb *kiocb;
+
+	/* buffer index that was used for the I/O */
+	struct orangefs_bufmap *bufmap;
+	int buffer_index;
+
+	/* orangefs kernel operation type */
+	struct orangefs_kernel_op_s *op;
+
+	/* The user space buffers from/to which I/O is being staged */
+	struct iovec *iov;
+
+	/* number of elements in the iovector */
+	unsigned long nr_segs;
+
+	/* set to indicate the type of the operation */
+	int rw;
+
+	/* file offset */
+	loff_t offset;
+
+	/* and the count in bytes */
+	size_t bytes_to_be_copied;
+
+	ssize_t bytes_copied;
+	int needs_cleanup;
+};
+
+struct orangefs_stats {
+	unsigned long cache_hits;
+	unsigned long cache_misses;
+	unsigned long reads;
+	unsigned long writes;
+};
+
+extern struct orangefs_stats g_orangefs_stats;
+
+/*
+ * NOTE: See Documentation/filesystems/porting for information
+ * on implementing FOO_I and properly accessing fs private data
+ */
+static inline struct orangefs_inode_s *ORANGEFS_I(struct inode *inode)
+{
+	return container_of(inode, struct orangefs_inode_s, vfs_inode);
+}
+
+static inline struct orangefs_sb_info_s *ORANGEFS_SB(struct super_block *sb)
+{
+	return (struct orangefs_sb_info_s *) sb->s_fs_info;
+}
+
+/* ino_t descends from "unsigned long", 8 bytes, 64 bits. */
+static inline ino_t orangefs_khandle_to_ino(struct orangefs_khandle *khandle)
+{
+	union {
+		unsigned char u[8];
+		__u64 ino;
+	} ihandle;
+
+	ihandle.u[0] = khandle->u[0] ^ khandle->u[4];
+	ihandle.u[1] = khandle->u[1] ^ khandle->u[5];
+	ihandle.u[2] = khandle->u[2] ^ khandle->u[6];
+	ihandle.u[3] = khandle->u[3] ^ khandle->u[7];
+	ihandle.u[4] = khandle->u[12] ^ khandle->u[8];
+	ihandle.u[5] = khandle->u[13] ^ khandle->u[9];
+	ihandle.u[6] = khandle->u[14] ^ khandle->u[10];
+	ihandle.u[7] = khandle->u[15] ^ khandle->u[11];
+
+	return ihandle.ino;
+}
+
+static inline struct orangefs_khandle *get_khandle_from_ino(struct inode *inode)
+{
+	return &(ORANGEFS_I(inode)->refn.khandle);
+}
+
+static inline __s32 get_fsid_from_ino(struct inode *inode)
+{
+	return ORANGEFS_I(inode)->refn.fs_id;
+}
+
+static inline ino_t get_ino_from_khandle(struct inode *inode)
+{
+	struct orangefs_khandle *khandle;
+	ino_t ino;
+
+	khandle = get_khandle_from_ino(inode);
+	ino = orangefs_khandle_to_ino(khandle);
+	return ino;
+}
+
+static inline ino_t get_parent_ino_from_dentry(struct dentry *dentry)
+{
+	return get_ino_from_khandle(dentry->d_parent->d_inode);
+}
+
+static inline int is_root_handle(struct inode *inode)
+{
+	gossip_debug(GOSSIP_DCACHE_DEBUG,
+		     "%s: root handle: %pU, this handle: %pU:\n",
+		     __func__,
+		     &ORANGEFS_SB(inode->i_sb)->root_khandle,
+		     get_khandle_from_ino(inode));
+
+	if (ORANGEFS_khandle_cmp(&(ORANGEFS_SB(inode->i_sb)->root_khandle),
+			     get_khandle_from_ino(inode)))
+		return 0;
+	else
+		return 1;
+}
+
+static inline int match_handle(struct orangefs_khandle resp_handle,
+			       struct inode *inode)
+{
+	gossip_debug(GOSSIP_DCACHE_DEBUG,
+		     "%s: one handle: %pU, another handle:%pU:\n",
+		     __func__,
+		     &resp_handle,
+		     get_khandle_from_ino(inode));
+
+	if (ORANGEFS_khandle_cmp(&resp_handle, get_khandle_from_ino(inode)))
+		return 0;
+	else
+		return 1;
+}
+
+/*
+ * defined in orangefs-cache.c
+ */
+int op_cache_initialize(void);
+int op_cache_finalize(void);
+struct orangefs_kernel_op_s *op_alloc(__s32 type);
+void orangefs_new_tag(struct orangefs_kernel_op_s *op);
+char *get_opname_string(struct orangefs_kernel_op_s *new_op);
+
+int orangefs_inode_cache_initialize(void);
+int orangefs_inode_cache_finalize(void);
+
+/*
+ * defined in orangefs-mod.c
+ */
+void purge_inprogress_ops(void);
+
+/*
+ * defined in waitqueue.c
+ */
+void purge_waiting_ops(void);
+
+/*
+ * defined in super.c
+ */
+struct dentry *orangefs_mount(struct file_system_type *fst,
+			   int flags,
+			   const char *devname,
+			   void *data);
+
+void orangefs_kill_sb(struct super_block *sb);
+int orangefs_remount(struct orangefs_sb_info_s *);
+
+int fsid_key_table_initialize(void);
+void fsid_key_table_finalize(void);
+
+/*
+ * defined in inode.c
+ */
+__u32 convert_to_orangefs_mask(unsigned long lite_mask);
+struct inode *orangefs_new_inode(struct super_block *sb,
+			      struct inode *dir,
+			      int mode,
+			      dev_t dev,
+			      struct orangefs_object_kref *ref);
+
+int orangefs_setattr(struct dentry *dentry, struct iattr *iattr);
+
+int orangefs_getattr(struct vfsmount *mnt,
+		  struct dentry *dentry,
+		  struct kstat *kstat);
+
+int orangefs_permission(struct inode *inode, int mask);
+
+/*
+ * defined in xattr.c
+ */
+int orangefs_setxattr(struct dentry *dentry,
+		   const char *name,
+		   const void *value,
+		   size_t size,
+		   int flags);
+
+ssize_t orangefs_getxattr(struct dentry *dentry,
+		       const char *name,
+		       void *buffer,
+		       size_t size);
+
+ssize_t orangefs_listxattr(struct dentry *dentry, char *buffer, size_t size);
+
+/*
+ * defined in namei.c
+ */
+struct inode *orangefs_iget(struct super_block *sb,
+			 struct orangefs_object_kref *ref);
+
+ssize_t orangefs_inode_read(struct inode *inode,
+			    struct iov_iter *iter,
+			    loff_t *offset,
+			    loff_t readahead_size);
+
+/*
+ * defined in devorangefs-req.c
+ */
+int orangefs_dev_init(void);
+void orangefs_dev_cleanup(void);
+int is_daemon_in_service(void);
+bool __is_daemon_in_service(void);
+
+/*
+ * defined in orangefs-utils.c
+ */
+__s32 fsid_of_op(struct orangefs_kernel_op_s *op);
+
+int orangefs_flush_inode(struct inode *inode);
+
+ssize_t orangefs_inode_getxattr(struct inode *inode,
+			     const char *prefix,
+			     const char *name,
+			     void *buffer,
+			     size_t size);
+
+int orangefs_inode_setxattr(struct inode *inode,
+			 const char *prefix,
+			 const char *name,
+			 const void *value,
+			 size_t size,
+			 int flags);
+
+int orangefs_inode_getattr(struct inode *inode, int new, int size);
+
+int orangefs_inode_check_changed(struct inode *inode);
+
+int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr);
+
+void orangefs_make_bad_inode(struct inode *inode);
+
+int orangefs_unmount_sb(struct super_block *sb);
+
+bool orangefs_cancel_op_in_progress(struct orangefs_kernel_op_s *op);
+
+int orangefs_normalize_to_errno(__s32 error_code);
+
+extern struct mutex devreq_mutex;
+extern struct mutex request_mutex;
+extern int debug;
+extern int op_timeout_secs;
+extern int slot_timeout_secs;
+extern struct list_head orangefs_superblocks;
+extern spinlock_t orangefs_superblocks_lock;
+extern struct list_head orangefs_request_list;
+extern spinlock_t orangefs_request_list_lock;
+extern wait_queue_head_t orangefs_request_list_waitq;
+extern struct list_head *htable_ops_in_progress;
+extern spinlock_t htable_ops_in_progress_lock;
+extern int hash_table_size;
+
+extern const struct address_space_operations orangefs_address_operations;
+extern struct backing_dev_info orangefs_backing_dev_info;
+extern struct inode_operations orangefs_file_inode_operations;
+extern const struct file_operations orangefs_file_operations;
+extern struct inode_operations orangefs_symlink_inode_operations;
+extern struct inode_operations orangefs_dir_inode_operations;
+extern const struct file_operations orangefs_dir_operations;
+extern const struct dentry_operations orangefs_dentry_operations;
+extern const struct file_operations orangefs_devreq_file_operations;
+
+extern wait_queue_head_t orangefs_bufmap_init_waitq;
+
+/*
+ * misc convenience macros
+ */
+
+#define ORANGEFS_OP_INTERRUPTIBLE 1   /* service_operation() is interruptible */
+#define ORANGEFS_OP_PRIORITY      2   /* service_operation() is high priority */
+#define ORANGEFS_OP_CANCELLATION  4   /* this is a cancellation */
+#define ORANGEFS_OP_NO_MUTEX      8   /* don't acquire request_mutex */
+#define ORANGEFS_OP_ASYNC         16  /* Queue it, but don't wait */
+
+int service_operation(struct orangefs_kernel_op_s *op,
+		      const char *op_name,
+		      int flags);
+
+#define get_interruptible_flag(inode) \
+	((ORANGEFS_SB(inode->i_sb)->flags & ORANGEFS_OPT_INTR) ? \
+		ORANGEFS_OP_INTERRUPTIBLE : 0)
+
+#define fill_default_sys_attrs(sys_attr, type, mode)			\
+do {									\
+	sys_attr.owner = from_kuid(current_user_ns(), current_fsuid()); \
+	sys_attr.group = from_kgid(current_user_ns(), current_fsgid()); \
+	sys_attr.perms = ORANGEFS_util_translate_mode(mode);		\
+	sys_attr.mtime = 0;						\
+	sys_attr.atime = 0;						\
+	sys_attr.ctime = 0;						\
+	sys_attr.mask = ORANGEFS_ATTR_SYS_ALL_SETABLE;			\
+} while (0)
+
+static inline void orangefs_i_size_write(struct inode *inode, loff_t i_size)
+{
+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
+	mutex_lock(&inode->i_mutex);
+#endif
+	i_size_write(inode, i_size);
+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
+	mutex_unlock(&inode->i_mutex);
+#endif
+}
+
+#endif /* __ORANGEFSKERNEL_H */
diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c
new file mode 100644
index 000000000000..6f072a8c0de1
--- /dev/null
+++ b/fs/orangefs/orangefs-mod.c
@@ -0,0 +1,293 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * Changes by Acxiom Corporation to add proc file handler for pvfs2 client
+ * parameters, Copyright Acxiom Corporation, 2005.
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-debugfs.h"
+#include "orangefs-sysfs.h"
+
+/* ORANGEFS_VERSION is a ./configure define */
+#ifndef ORANGEFS_VERSION
+#define ORANGEFS_VERSION "upstream"
+#endif
+
+/*
+ * global variables declared here
+ */
+
+/* array of client debug keyword/mask values */
+struct client_debug_mask *cdm_array;
+int cdm_element_count;
+
+char kernel_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN] = "none";
+char client_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+char client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+
+char *debug_help_string;
+int help_string_initialized;
+struct dentry *help_file_dentry;
+struct dentry *client_debug_dentry;
+struct dentry *debug_dir;
+int client_verbose_index;
+int client_all_index;
+struct orangefs_stats g_orangefs_stats;
+
+/* the size of the hash tables for ops in progress */
+int hash_table_size = 509;
+
+static ulong module_parm_debug_mask;
+__u64 gossip_debug_mask;
+struct client_debug_mask client_debug_mask = { NULL, 0, 0 };
+unsigned int kernel_mask_set_mod_init; /* implicitly false */
+int op_timeout_secs = ORANGEFS_DEFAULT_OP_TIMEOUT_SECS;
+int slot_timeout_secs = ORANGEFS_DEFAULT_SLOT_TIMEOUT_SECS;
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("ORANGEFS Development Team");
+MODULE_DESCRIPTION("The Linux Kernel VFS interface to ORANGEFS");
+MODULE_PARM_DESC(module_parm_debug_mask, "debugging level (see orangefs-debug.h for values)");
+MODULE_PARM_DESC(op_timeout_secs, "Operation timeout in seconds");
+MODULE_PARM_DESC(slot_timeout_secs, "Slot timeout in seconds");
+MODULE_PARM_DESC(hash_table_size,
+		 "size of hash table for operations in progress");
+
+static struct file_system_type orangefs_fs_type = {
+	.name = "pvfs2",
+	.mount = orangefs_mount,
+	.kill_sb = orangefs_kill_sb,
+	.owner = THIS_MODULE,
+};
+
+module_param(hash_table_size, int, 0);
+module_param(module_parm_debug_mask, ulong, 0644);
+module_param(op_timeout_secs, int, 0);
+module_param(slot_timeout_secs, int, 0);
+
+/* synchronizes the request device file */
+DEFINE_MUTEX(devreq_mutex);
+
+/*
+ * Blocks non-priority requests from being queued for servicing.  This
+ * could be used for protecting the request list data structure, but
+ * for now it's only being used to stall the op addition to the request
+ * list
+ */
+DEFINE_MUTEX(request_mutex);
+
+/* hash table for storing operations waiting for matching downcall */
+struct list_head *htable_ops_in_progress;
+DEFINE_SPINLOCK(htable_ops_in_progress_lock);
+
+/* list for queueing upcall operations */
+LIST_HEAD(orangefs_request_list);
+
+/* used to protect the above orangefs_request_list */
+DEFINE_SPINLOCK(orangefs_request_list_lock);
+
+/* used for incoming request notification */
+DECLARE_WAIT_QUEUE_HEAD(orangefs_request_list_waitq);
+
+static int __init orangefs_init(void)
+{
+	int ret = -1;
+	__u32 i = 0;
+
+	/* convert input debug mask to a 64-bit unsigned integer */
+	gossip_debug_mask = (unsigned long long) module_parm_debug_mask;
+
+	/*
+	 * set the kernel's gossip debug string; invalid mask values will
+	 * be ignored.
+	 */
+	debug_mask_to_string(&gossip_debug_mask, 0);
+
+	/* remove any invalid values from the mask */
+	debug_string_to_mask(kernel_debug_string, &gossip_debug_mask, 0);
+
+	/*
+	 * if the mask has a non-zero value, then indicate that the mask
+	 * was set when the kernel module was loaded.  The orangefs dev ioctl
+	 * command will look at this boolean to determine if the kernel's
+	 * debug mask should be overwritten when the client-core is started.
+	 */
+	if (gossip_debug_mask != 0)
+		kernel_mask_set_mod_init = true;
+
+	pr_info("%s: called with debug mask: :%s: :%llx:\n",
+		__func__,
+		kernel_debug_string,
+		(unsigned long long)gossip_debug_mask);
+
+	ret = bdi_init(&orangefs_backing_dev_info);
+
+	if (ret)
+		return ret;
+
+	if (op_timeout_secs < 0)
+		op_timeout_secs = 0;
+
+	if (slot_timeout_secs < 0)
+		slot_timeout_secs = 0;
+
+	/* initialize global book keeping data structures */
+	ret = op_cache_initialize();
+	if (ret < 0)
+		goto err;
+
+	ret = orangefs_inode_cache_initialize();
+	if (ret < 0)
+		goto cleanup_op;
+
+	htable_ops_in_progress =
+	    kcalloc(hash_table_size, sizeof(struct list_head), GFP_KERNEL);
+	if (!htable_ops_in_progress) {
+		gossip_err("Failed to initialize op hashtable");
+		ret = -ENOMEM;
+		goto cleanup_inode;
+	}
+
+	/* initialize a doubly linked at each hash table index */
+	for (i = 0; i < hash_table_size; i++)
+		INIT_LIST_HEAD(&htable_ops_in_progress[i]);
+
+	ret = fsid_key_table_initialize();
+	if (ret < 0)
+		goto cleanup_progress_table;
+
+	/*
+	 * Build the contents of /sys/kernel/debug/orangefs/debug-help
+	 * from the keywords in the kernel keyword/mask array.
+	 *
+	 * The keywords in the client keyword/mask array are
+	 * unknown at boot time.
+	 *
+	 * orangefs_prepare_debugfs_help_string will be used again
+	 * later to rebuild the debug-help file after the client starts
+	 * and passes along the needed info. The argument signifies
+	 * which time orangefs_prepare_debugfs_help_string is being
+	 * called.
+	 */
+	ret = orangefs_prepare_debugfs_help_string(1);
+	if (ret)
+		goto cleanup_key_table;
+
+	ret = orangefs_debugfs_init();
+	if (ret)
+		goto debugfs_init_failed;
+
+	ret = orangefs_kernel_debug_init();
+	if (ret)
+		goto kernel_debug_init_failed;
+
+	ret = orangefs_sysfs_init();
+	if (ret)
+		goto sysfs_init_failed;
+
+	/* Initialize the orangefsdev subsystem. */
+	ret = orangefs_dev_init();
+	if (ret < 0) {
+		gossip_err("%s: could not initialize device subsystem %d!\n",
+			   __func__,
+			   ret);
+		goto cleanup_device;
+	}
+
+	ret = register_filesystem(&orangefs_fs_type);
+	if (ret == 0) {
+		pr_info("orangefs: module version %s loaded\n", ORANGEFS_VERSION);
+		ret = 0;
+		goto out;
+	}
+
+	orangefs_sysfs_exit();
+
+cleanup_device:
+	orangefs_dev_cleanup();
+
+sysfs_init_failed:
+
+kernel_debug_init_failed:
+
+debugfs_init_failed:
+	orangefs_debugfs_cleanup();
+
+cleanup_key_table:
+	fsid_key_table_finalize();
+
+cleanup_progress_table:
+	kfree(htable_ops_in_progress);
+
+cleanup_inode:
+	orangefs_inode_cache_finalize();
+
+cleanup_op:
+	op_cache_finalize();
+
+err:
+	bdi_destroy(&orangefs_backing_dev_info);
+
+out:
+	return ret;
+}
+
+static void __exit orangefs_exit(void)
+{
+	int i = 0;
+	gossip_debug(GOSSIP_INIT_DEBUG, "orangefs: orangefs_exit called\n");
+
+	unregister_filesystem(&orangefs_fs_type);
+	orangefs_debugfs_cleanup();
+	orangefs_sysfs_exit();
+	fsid_key_table_finalize();
+	orangefs_dev_cleanup();
+	BUG_ON(!list_empty(&orangefs_request_list));
+	for (i = 0; i < hash_table_size; i++)
+		BUG_ON(!list_empty(&htable_ops_in_progress[i]));
+
+	orangefs_inode_cache_finalize();
+	op_cache_finalize();
+
+	kfree(htable_ops_in_progress);
+
+	bdi_destroy(&orangefs_backing_dev_info);
+
+	pr_info("orangefs: module version %s unloaded\n", ORANGEFS_VERSION);
+}
+
+/*
+ * What we do in this function is to walk the list of operations
+ * that are in progress in the hash table and mark them as purged as well.
+ */
+void purge_inprogress_ops(void)
+{
+	int i;
+
+	for (i = 0; i < hash_table_size; i++) {
+		struct orangefs_kernel_op_s *op;
+		struct orangefs_kernel_op_s *next;
+
+		spin_lock(&htable_ops_in_progress_lock);
+		list_for_each_entry_safe(op,
+					 next,
+					 &htable_ops_in_progress[i],
+					 list) {
+			set_op_state_purged(op);
+			gossip_debug(GOSSIP_DEV_DEBUG,
+				     "%s: op:%s: op_state:%d: process:%s:\n",
+				     __func__,
+				     get_opname_string(op),
+				     op->op_state,
+				     current->comm);
+		}
+		spin_unlock(&htable_ops_in_progress_lock);
+	}
+}
+
+module_init(orangefs_init);
+module_exit(orangefs_exit);
diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c
new file mode 100644
index 000000000000..5c03113e3ad2
--- /dev/null
+++ b/fs/orangefs/orangefs-sysfs.c
@@ -0,0 +1,1772 @@
+/*
+ * Documentation/ABI/stable/orangefs-sysfs:
+ *
+ * What:		/sys/fs/orangefs/perf_counter_reset
+ * Date:		June 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			echo a 0 or a 1 into perf_counter_reset to
+ * 			reset all the counters in
+ * 			/sys/fs/orangefs/perf_counters
+ * 			except ones with PINT_PERF_PRESERVE set.
+ *
+ *
+ * What:		/sys/fs/orangefs/perf_counters/...
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Counters and settings for various caches.
+ * 			Read only.
+ *
+ *
+ * What:		/sys/fs/orangefs/perf_time_interval_secs
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ *			Length of perf counter intervals in
+ *			seconds.
+ *
+ *
+ * What:		/sys/fs/orangefs/perf_history_size
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			The perf_counters cache statistics have N, or
+ * 			perf_history_size, samples. The default is
+ * 			one.
+ *
+ *			Every perf_time_interval_secs the (first)
+ *			samples are reset.
+ *
+ *			If N is greater than one, the "current" set
+ *			of samples is reset, and the samples from the
+ *			other N-1 intervals remain available.
+ *
+ *
+ * What:		/sys/fs/orangefs/op_timeout_secs
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ *			Service operation timeout in seconds.
+ *
+ *
+ * What:		/sys/fs/orangefs/slot_timeout_secs
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ *			"Slot" timeout in seconds. A "slot"
+ *			is an indexed buffer in the shared
+ *			memory segment used for communication
+ *			between the kernel module and userspace.
+ *			Slots are requested and waited for,
+ *			the wait times out after slot_timeout_secs.
+ *
+ *
+ * What:		/sys/fs/orangefs/acache/...
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Attribute cache configurable settings.
+ *
+ *
+ * What:		/sys/fs/orangefs/ncache/...
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Name cache configurable settings.
+ *
+ *
+ * What:		/sys/fs/orangefs/capcache/...
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Capability cache configurable settings.
+ *
+ *
+ * What:		/sys/fs/orangefs/ccache/...
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Credential cache configurable settings.
+ *
+ */
+
+#include <linux/fs.h>
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-sysfs.h"
+
+#define ORANGEFS_KOBJ_ID "orangefs"
+#define ACACHE_KOBJ_ID "acache"
+#define CAPCACHE_KOBJ_ID "capcache"
+#define CCACHE_KOBJ_ID "ccache"
+#define NCACHE_KOBJ_ID "ncache"
+#define PC_KOBJ_ID "pc"
+#define STATS_KOBJ_ID "stats"
+
+struct orangefs_obj {
+	struct kobject kobj;
+	int op_timeout_secs;
+	int perf_counter_reset;
+	int perf_history_size;
+	int perf_time_interval_secs;
+	int slot_timeout_secs;
+};
+
+struct acache_orangefs_obj {
+	struct kobject kobj;
+	int hard_limit;
+	int reclaim_percentage;
+	int soft_limit;
+	int timeout_msecs;
+};
+
+struct capcache_orangefs_obj {
+	struct kobject kobj;
+	int hard_limit;
+	int reclaim_percentage;
+	int soft_limit;
+	int timeout_secs;
+};
+
+struct ccache_orangefs_obj {
+	struct kobject kobj;
+	int hard_limit;
+	int reclaim_percentage;
+	int soft_limit;
+	int timeout_secs;
+};
+
+struct ncache_orangefs_obj {
+	struct kobject kobj;
+	int hard_limit;
+	int reclaim_percentage;
+	int soft_limit;
+	int timeout_msecs;
+};
+
+struct pc_orangefs_obj {
+	struct kobject kobj;
+	char *acache;
+	char *capcache;
+	char *ncache;
+};
+
+struct stats_orangefs_obj {
+	struct kobject kobj;
+	int reads;
+	int writes;
+};
+
+struct orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct orangefs_obj *orangefs_obj,
+			struct orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct orangefs_obj *orangefs_obj,
+			 struct orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct acache_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct acache_orangefs_obj *acache_orangefs_obj,
+			struct acache_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct acache_orangefs_obj *acache_orangefs_obj,
+			 struct acache_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct capcache_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct capcache_orangefs_obj *capcache_orangefs_obj,
+			struct capcache_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct capcache_orangefs_obj *capcache_orangefs_obj,
+			 struct capcache_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct ccache_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct ccache_orangefs_obj *ccache_orangefs_obj,
+			struct ccache_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct ccache_orangefs_obj *ccache_orangefs_obj,
+			 struct ccache_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct ncache_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct ncache_orangefs_obj *ncache_orangefs_obj,
+			struct ncache_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct ncache_orangefs_obj *ncache_orangefs_obj,
+			 struct ncache_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct pc_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct pc_orangefs_obj *pc_orangefs_obj,
+			struct pc_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct pc_orangefs_obj *pc_orangefs_obj,
+			 struct pc_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct stats_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct stats_orangefs_obj *stats_orangefs_obj,
+			struct stats_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct stats_orangefs_obj *stats_orangefs_obj,
+			 struct stats_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+static ssize_t orangefs_attr_show(struct kobject *kobj,
+				  struct attribute *attr,
+				  char *buf)
+{
+	struct orangefs_attribute *attribute;
+	struct orangefs_obj *orangefs_obj;
+	int rc;
+
+	attribute = container_of(attr, struct orangefs_attribute, attr);
+	orangefs_obj = container_of(kobj, struct orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static ssize_t orangefs_attr_store(struct kobject *kobj,
+				   struct attribute *attr,
+				   const char *buf,
+				   size_t len)
+{
+	struct orangefs_attribute *attribute;
+	struct orangefs_obj *orangefs_obj;
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "orangefs_attr_store: start\n");
+
+	attribute = container_of(attr, struct orangefs_attribute, attr);
+	orangefs_obj = container_of(kobj, struct orangefs_obj, kobj);
+
+	if (!attribute->store) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->store(orangefs_obj, attribute, buf, len);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops orangefs_sysfs_ops = {
+	.show = orangefs_attr_show,
+	.store = orangefs_attr_store,
+};
+
+static ssize_t acache_orangefs_attr_show(struct kobject *kobj,
+					 struct attribute *attr,
+					 char *buf)
+{
+	struct acache_orangefs_attribute *attribute;
+	struct acache_orangefs_obj *acache_orangefs_obj;
+	int rc;
+
+	attribute = container_of(attr, struct acache_orangefs_attribute, attr);
+	acache_orangefs_obj =
+		container_of(kobj, struct acache_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(acache_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static ssize_t acache_orangefs_attr_store(struct kobject *kobj,
+					  struct attribute *attr,
+					  const char *buf,
+					  size_t len)
+{
+	struct acache_orangefs_attribute *attribute;
+	struct acache_orangefs_obj *acache_orangefs_obj;
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "acache_orangefs_attr_store: start\n");
+
+	attribute = container_of(attr, struct acache_orangefs_attribute, attr);
+	acache_orangefs_obj =
+		container_of(kobj, struct acache_orangefs_obj, kobj);
+
+	if (!attribute->store) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->store(acache_orangefs_obj, attribute, buf, len);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops acache_orangefs_sysfs_ops = {
+	.show = acache_orangefs_attr_show,
+	.store = acache_orangefs_attr_store,
+};
+
+static ssize_t capcache_orangefs_attr_show(struct kobject *kobj,
+					   struct attribute *attr,
+					   char *buf)
+{
+	struct capcache_orangefs_attribute *attribute;
+	struct capcache_orangefs_obj *capcache_orangefs_obj;
+	int rc;
+
+	attribute =
+		container_of(attr, struct capcache_orangefs_attribute, attr);
+	capcache_orangefs_obj =
+		container_of(kobj, struct capcache_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(capcache_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static ssize_t capcache_orangefs_attr_store(struct kobject *kobj,
+					    struct attribute *attr,
+					    const char *buf,
+					    size_t len)
+{
+	struct capcache_orangefs_attribute *attribute;
+	struct capcache_orangefs_obj *capcache_orangefs_obj;
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "capcache_orangefs_attr_store: start\n");
+
+	attribute =
+		container_of(attr, struct capcache_orangefs_attribute, attr);
+	capcache_orangefs_obj =
+		container_of(kobj, struct capcache_orangefs_obj, kobj);
+
+	if (!attribute->store) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->store(capcache_orangefs_obj, attribute, buf, len);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops capcache_orangefs_sysfs_ops = {
+	.show = capcache_orangefs_attr_show,
+	.store = capcache_orangefs_attr_store,
+};
+
+static ssize_t ccache_orangefs_attr_show(struct kobject *kobj,
+					 struct attribute *attr,
+					 char *buf)
+{
+	struct ccache_orangefs_attribute *attribute;
+	struct ccache_orangefs_obj *ccache_orangefs_obj;
+	int rc;
+
+	attribute =
+		container_of(attr, struct ccache_orangefs_attribute, attr);
+	ccache_orangefs_obj =
+		container_of(kobj, struct ccache_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(ccache_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static ssize_t ccache_orangefs_attr_store(struct kobject *kobj,
+					  struct attribute *attr,
+					  const char *buf,
+					  size_t len)
+{
+	struct ccache_orangefs_attribute *attribute;
+	struct ccache_orangefs_obj *ccache_orangefs_obj;
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "ccache_orangefs_attr_store: start\n");
+
+	attribute =
+		container_of(attr, struct ccache_orangefs_attribute, attr);
+	ccache_orangefs_obj =
+		container_of(kobj, struct ccache_orangefs_obj, kobj);
+
+	if (!attribute->store) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->store(ccache_orangefs_obj, attribute, buf, len);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops ccache_orangefs_sysfs_ops = {
+	.show = ccache_orangefs_attr_show,
+	.store = ccache_orangefs_attr_store,
+};
+
+static ssize_t ncache_orangefs_attr_show(struct kobject *kobj,
+					 struct attribute *attr,
+					 char *buf)
+{
+	struct ncache_orangefs_attribute *attribute;
+	struct ncache_orangefs_obj *ncache_orangefs_obj;
+	int rc;
+
+	attribute = container_of(attr, struct ncache_orangefs_attribute, attr);
+	ncache_orangefs_obj =
+		container_of(kobj, struct ncache_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(ncache_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static ssize_t ncache_orangefs_attr_store(struct kobject *kobj,
+					  struct attribute *attr,
+					  const char *buf,
+					  size_t len)
+{
+	struct ncache_orangefs_attribute *attribute;
+	struct ncache_orangefs_obj *ncache_orangefs_obj;
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "ncache_orangefs_attr_store: start\n");
+
+	attribute = container_of(attr, struct ncache_orangefs_attribute, attr);
+	ncache_orangefs_obj =
+		container_of(kobj, struct ncache_orangefs_obj, kobj);
+
+	if (!attribute->store) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->store(ncache_orangefs_obj, attribute, buf, len);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops ncache_orangefs_sysfs_ops = {
+	.show = ncache_orangefs_attr_show,
+	.store = ncache_orangefs_attr_store,
+};
+
+static ssize_t pc_orangefs_attr_show(struct kobject *kobj,
+				     struct attribute *attr,
+				     char *buf)
+{
+	struct pc_orangefs_attribute *attribute;
+	struct pc_orangefs_obj *pc_orangefs_obj;
+	int rc;
+
+	attribute = container_of(attr, struct pc_orangefs_attribute, attr);
+	pc_orangefs_obj =
+		container_of(kobj, struct pc_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(pc_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops pc_orangefs_sysfs_ops = {
+	.show = pc_orangefs_attr_show,
+};
+
+static ssize_t stats_orangefs_attr_show(struct kobject *kobj,
+					struct attribute *attr,
+					char *buf)
+{
+	struct stats_orangefs_attribute *attribute;
+	struct stats_orangefs_obj *stats_orangefs_obj;
+	int rc;
+
+	attribute = container_of(attr, struct stats_orangefs_attribute, attr);
+	stats_orangefs_obj =
+		container_of(kobj, struct stats_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(stats_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops stats_orangefs_sysfs_ops = {
+	.show = stats_orangefs_attr_show,
+};
+
+static void orangefs_release(struct kobject *kobj)
+{
+	struct orangefs_obj *orangefs_obj;
+
+	orangefs_obj = container_of(kobj, struct orangefs_obj, kobj);
+	kfree(orangefs_obj);
+}
+
+static void acache_orangefs_release(struct kobject *kobj)
+{
+	struct acache_orangefs_obj *acache_orangefs_obj;
+
+	acache_orangefs_obj =
+		container_of(kobj, struct acache_orangefs_obj, kobj);
+	kfree(acache_orangefs_obj);
+}
+
+static void capcache_orangefs_release(struct kobject *kobj)
+{
+	struct capcache_orangefs_obj *capcache_orangefs_obj;
+
+	capcache_orangefs_obj =
+		container_of(kobj, struct capcache_orangefs_obj, kobj);
+	kfree(capcache_orangefs_obj);
+}
+
+static void ccache_orangefs_release(struct kobject *kobj)
+{
+	struct ccache_orangefs_obj *ccache_orangefs_obj;
+
+	ccache_orangefs_obj =
+		container_of(kobj, struct ccache_orangefs_obj, kobj);
+	kfree(ccache_orangefs_obj);
+}
+
+static void ncache_orangefs_release(struct kobject *kobj)
+{
+	struct ncache_orangefs_obj *ncache_orangefs_obj;
+
+	ncache_orangefs_obj =
+		container_of(kobj, struct ncache_orangefs_obj, kobj);
+	kfree(ncache_orangefs_obj);
+}
+
+static void pc_orangefs_release(struct kobject *kobj)
+{
+	struct pc_orangefs_obj *pc_orangefs_obj;
+
+	pc_orangefs_obj =
+		container_of(kobj, struct pc_orangefs_obj, kobj);
+	kfree(pc_orangefs_obj);
+}
+
+static void stats_orangefs_release(struct kobject *kobj)
+{
+	struct stats_orangefs_obj *stats_orangefs_obj;
+
+	stats_orangefs_obj =
+		container_of(kobj, struct stats_orangefs_obj, kobj);
+	kfree(stats_orangefs_obj);
+}
+
+static ssize_t sysfs_int_show(char *kobj_id, char *buf, void *attr)
+{
+	int rc = -EIO;
+	struct orangefs_attribute *orangefs_attr;
+	struct stats_orangefs_attribute *stats_orangefs_attr;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG, "sysfs_int_show: id:%s:\n", kobj_id);
+
+	if (!strcmp(kobj_id, ORANGEFS_KOBJ_ID)) {
+		orangefs_attr = (struct orangefs_attribute *)attr;
+
+		if (!strcmp(orangefs_attr->attr.name, "op_timeout_secs")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%d\n",
+				       op_timeout_secs);
+			goto out;
+		} else if (!strcmp(orangefs_attr->attr.name,
+				   "slot_timeout_secs")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%d\n",
+				       slot_timeout_secs);
+			goto out;
+		} else {
+			goto out;
+		}
+
+	} else if (!strcmp(kobj_id, STATS_KOBJ_ID)) {
+		stats_orangefs_attr = (struct stats_orangefs_attribute *)attr;
+
+		if (!strcmp(stats_orangefs_attr->attr.name, "reads")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%lu\n",
+				       g_orangefs_stats.reads);
+			goto out;
+		} else if (!strcmp(stats_orangefs_attr->attr.name, "writes")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%lu\n",
+				       g_orangefs_stats.writes);
+			goto out;
+		} else {
+			goto out;
+		}
+	}
+
+out:
+
+	return rc;
+}
+
+static ssize_t int_orangefs_show(struct orangefs_obj *orangefs_obj,
+				 struct orangefs_attribute *attr,
+				 char *buf)
+{
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "int_orangefs_show:start attr->attr.name:%s:\n",
+		     attr->attr.name);
+
+	rc = sysfs_int_show(ORANGEFS_KOBJ_ID, buf, (void *) attr);
+
+	return rc;
+}
+
+static ssize_t int_stats_show(struct stats_orangefs_obj *stats_orangefs_obj,
+			struct stats_orangefs_attribute *attr,
+			char *buf)
+{
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "int_stats_show:start attr->attr.name:%s:\n",
+		     attr->attr.name);
+
+	rc = sysfs_int_show(STATS_KOBJ_ID, buf, (void *) attr);
+
+	return rc;
+}
+
+static ssize_t int_store(struct orangefs_obj *orangefs_obj,
+			 struct orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count)
+{
+	int rc = 0;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "int_store: start attr->attr.name:%s: buf:%s:\n",
+		     attr->attr.name, buf);
+
+	if (!strcmp(attr->attr.name, "op_timeout_secs")) {
+		rc = kstrtoint(buf, 0, &op_timeout_secs);
+		goto out;
+	} else if (!strcmp(attr->attr.name, "slot_timeout_secs")) {
+		rc = kstrtoint(buf, 0, &slot_timeout_secs);
+		goto out;
+	} else {
+		goto out;
+	}
+
+out:
+	if (rc)
+		rc = -EINVAL;
+	else
+		rc = count;
+
+	return rc;
+}
+
+/*
+ * obtain attribute values from userspace with a service operation.
+ */
+static int sysfs_service_op_show(char *kobj_id, char *buf, void *attr)
+{
+	struct orangefs_kernel_op_s *new_op = NULL;
+	int rc = 0;
+	char *ser_op_type = NULL;
+	struct orangefs_attribute *orangefs_attr;
+	struct acache_orangefs_attribute *acache_attr;
+	struct capcache_orangefs_attribute *capcache_attr;
+	struct ccache_orangefs_attribute *ccache_attr;
+	struct ncache_orangefs_attribute *ncache_attr;
+	struct pc_orangefs_attribute *pc_attr;
+	__u32 op_alloc_type;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "sysfs_service_op_show: id:%s:\n",
+		     kobj_id);
+
+	if (strcmp(kobj_id, PC_KOBJ_ID))
+		op_alloc_type = ORANGEFS_VFS_OP_PARAM;
+	else
+		op_alloc_type = ORANGEFS_VFS_OP_PERF_COUNT;
+
+	new_op = op_alloc(op_alloc_type);
+	if (!new_op)
+		return -ENOMEM;
+
+	/* Can't do a service_operation if the client is not running... */
+	rc = is_daemon_in_service();
+	if (rc) {
+		pr_info("%s: Client not running :%d:\n",
+			__func__,
+			is_daemon_in_service());
+		goto out;
+	}
+
+	if (strcmp(kobj_id, PC_KOBJ_ID))
+		new_op->upcall.req.param.type = ORANGEFS_PARAM_REQUEST_GET;
+
+	if (!strcmp(kobj_id, ORANGEFS_KOBJ_ID)) {
+		orangefs_attr = (struct orangefs_attribute *)attr;
+
+		if (!strcmp(orangefs_attr->attr.name, "perf_history_size"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_PERF_HISTORY_SIZE;
+		else if (!strcmp(orangefs_attr->attr.name,
+				 "perf_time_interval_secs"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_PERF_TIME_INTERVAL_SECS;
+		else if (!strcmp(orangefs_attr->attr.name,
+				 "perf_counter_reset"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_PERF_RESET;
+
+	} else if (!strcmp(kobj_id, ACACHE_KOBJ_ID)) {
+		acache_attr = (struct acache_orangefs_attribute *)attr;
+
+		if (!strcmp(acache_attr->attr.name, "timeout_msecs"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_ACACHE_TIMEOUT_MSECS;
+
+		if (!strcmp(acache_attr->attr.name, "hard_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_ACACHE_HARD_LIMIT;
+
+		if (!strcmp(acache_attr->attr.name, "soft_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_ACACHE_SOFT_LIMIT;
+
+		if (!strcmp(acache_attr->attr.name, "reclaim_percentage"))
+			new_op->upcall.req.param.op =
+			  ORANGEFS_PARAM_REQUEST_OP_ACACHE_RECLAIM_PERCENTAGE;
+
+	} else if (!strcmp(kobj_id, CAPCACHE_KOBJ_ID)) {
+		capcache_attr = (struct capcache_orangefs_attribute *)attr;
+
+		if (!strcmp(capcache_attr->attr.name, "timeout_secs"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_TIMEOUT_SECS;
+
+		if (!strcmp(capcache_attr->attr.name, "hard_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_HARD_LIMIT;
+
+		if (!strcmp(capcache_attr->attr.name, "soft_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_SOFT_LIMIT;
+
+		if (!strcmp(capcache_attr->attr.name, "reclaim_percentage"))
+			new_op->upcall.req.param.op =
+			  ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_RECLAIM_PERCENTAGE;
+
+	} else if (!strcmp(kobj_id, CCACHE_KOBJ_ID)) {
+		ccache_attr = (struct ccache_orangefs_attribute *)attr;
+
+		if (!strcmp(ccache_attr->attr.name, "timeout_secs"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CCACHE_TIMEOUT_SECS;
+
+		if (!strcmp(ccache_attr->attr.name, "hard_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CCACHE_HARD_LIMIT;
+
+		if (!strcmp(ccache_attr->attr.name, "soft_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CCACHE_SOFT_LIMIT;
+
+		if (!strcmp(ccache_attr->attr.name, "reclaim_percentage"))
+			new_op->upcall.req.param.op =
+			  ORANGEFS_PARAM_REQUEST_OP_CCACHE_RECLAIM_PERCENTAGE;
+
+	} else if (!strcmp(kobj_id, NCACHE_KOBJ_ID)) {
+		ncache_attr = (struct ncache_orangefs_attribute *)attr;
+
+		if (!strcmp(ncache_attr->attr.name, "timeout_msecs"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_NCACHE_TIMEOUT_MSECS;
+
+		if (!strcmp(ncache_attr->attr.name, "hard_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_NCACHE_HARD_LIMIT;
+
+		if (!strcmp(ncache_attr->attr.name, "soft_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_NCACHE_SOFT_LIMIT;
+
+		if (!strcmp(ncache_attr->attr.name, "reclaim_percentage"))
+			new_op->upcall.req.param.op =
+			  ORANGEFS_PARAM_REQUEST_OP_NCACHE_RECLAIM_PERCENTAGE;
+
+	} else if (!strcmp(kobj_id, PC_KOBJ_ID)) {
+		pc_attr = (struct pc_orangefs_attribute *)attr;
+
+		if (!strcmp(pc_attr->attr.name, ACACHE_KOBJ_ID))
+			new_op->upcall.req.perf_count.type =
+				ORANGEFS_PERF_COUNT_REQUEST_ACACHE;
+
+		if (!strcmp(pc_attr->attr.name, CAPCACHE_KOBJ_ID))
+			new_op->upcall.req.perf_count.type =
+				ORANGEFS_PERF_COUNT_REQUEST_CAPCACHE;
+
+		if (!strcmp(pc_attr->attr.name, NCACHE_KOBJ_ID))
+			new_op->upcall.req.perf_count.type =
+				ORANGEFS_PERF_COUNT_REQUEST_NCACHE;
+
+	} else {
+		gossip_err("sysfs_service_op_show: unknown kobj_id:%s:\n",
+			   kobj_id);
+		rc = -EINVAL;
+		goto out;
+	}
+
+
+	if (strcmp(kobj_id, PC_KOBJ_ID))
+		ser_op_type = "orangefs_param";
+	else
+		ser_op_type = "orangefs_perf_count";
+
+	/*
+	 * The service_operation will return an errno return code on
+	 * error, and zero on success.
+	 */
+	rc = service_operation(new_op, ser_op_type, ORANGEFS_OP_INTERRUPTIBLE);
+
+out:
+	if (!rc) {
+		if (strcmp(kobj_id, PC_KOBJ_ID)) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%d\n",
+				       (int)new_op->downcall.resp.param.value);
+		} else {
+			rc = scnprintf(
+				buf,
+				PAGE_SIZE,
+				"%s",
+				new_op->downcall.resp.perf_count.buffer);
+		}
+	}
+
+	op_release(new_op);
+
+	return rc;
+
+}
+
+static ssize_t service_orangefs_show(struct orangefs_obj *orangefs_obj,
+				     struct orangefs_attribute *attr,
+				     char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(ORANGEFS_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+static ssize_t
+	service_acache_show(struct acache_orangefs_obj *acache_orangefs_obj,
+			    struct acache_orangefs_attribute *attr,
+			    char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(ACACHE_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+static ssize_t service_capcache_show(struct capcache_orangefs_obj
+					*capcache_orangefs_obj,
+				     struct capcache_orangefs_attribute *attr,
+				     char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(CAPCACHE_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+static ssize_t service_ccache_show(struct ccache_orangefs_obj
+					*ccache_orangefs_obj,
+				   struct ccache_orangefs_attribute *attr,
+				   char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(CCACHE_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+static ssize_t
+	service_ncache_show(struct ncache_orangefs_obj *ncache_orangefs_obj,
+			    struct ncache_orangefs_attribute *attr,
+			    char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(NCACHE_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+static ssize_t
+	service_pc_show(struct pc_orangefs_obj *pc_orangefs_obj,
+			    struct pc_orangefs_attribute *attr,
+			    char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(PC_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+/*
+ * pass attribute values back to userspace with a service operation.
+ *
+ * We have to do a memory allocation, an sscanf and a service operation.
+ * And we have to evaluate what the user entered, to make sure the
+ * value is within the range supported by the attribute. So, there's
+ * a lot of return code checking and mapping going on here.
+ *
+ * We want to return 1 if we think everything went OK, and
+ * EINVAL if not.
+ */
+static int sysfs_service_op_store(char *kobj_id, const char *buf, void *attr)
+{
+	struct orangefs_kernel_op_s *new_op = NULL;
+	int val = 0;
+	int rc = 0;
+	struct orangefs_attribute *orangefs_attr;
+	struct acache_orangefs_attribute *acache_attr;
+	struct capcache_orangefs_attribute *capcache_attr;
+	struct ccache_orangefs_attribute *ccache_attr;
+	struct ncache_orangefs_attribute *ncache_attr;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "sysfs_service_op_store: id:%s:\n",
+		     kobj_id);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_PARAM);
+	if (!new_op)
+		return -EINVAL; /* sic */
+
+	/* Can't do a service_operation if the client is not running... */
+	rc = is_daemon_in_service();
+	if (rc) {
+		pr_info("%s: Client not running :%d:\n",
+			__func__,
+			is_daemon_in_service());
+		goto out;
+	}
+
+	/*
+	 * The value we want to send back to userspace is in buf.
+	 */
+	rc = kstrtoint(buf, 0, &val);
+	if (rc)
+		goto out;
+
+	if (!strcmp(kobj_id, ORANGEFS_KOBJ_ID)) {
+		orangefs_attr = (struct orangefs_attribute *)attr;
+
+		if (!strcmp(orangefs_attr->attr.name, "perf_history_size")) {
+			if (val > 0) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_PERF_HISTORY_SIZE;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(orangefs_attr->attr.name,
+				   "perf_time_interval_secs")) {
+			if (val > 0) {
+				new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_PERF_TIME_INTERVAL_SECS;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(orangefs_attr->attr.name,
+				   "perf_counter_reset")) {
+			if ((val == 0) || (val == 1)) {
+				new_op->upcall.req.param.op =
+					ORANGEFS_PARAM_REQUEST_OP_PERF_RESET;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		}
+
+	} else if (!strcmp(kobj_id, ACACHE_KOBJ_ID)) {
+		acache_attr = (struct acache_orangefs_attribute *)attr;
+
+		if (!strcmp(acache_attr->attr.name, "hard_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_ACACHE_HARD_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(acache_attr->attr.name, "soft_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_ACACHE_SOFT_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(acache_attr->attr.name,
+				   "reclaim_percentage")) {
+			if ((val > -1) && (val < 101)) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_ACACHE_RECLAIM_PERCENTAGE;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(acache_attr->attr.name, "timeout_msecs")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_ACACHE_TIMEOUT_MSECS;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		}
+
+	} else if (!strcmp(kobj_id, CAPCACHE_KOBJ_ID)) {
+		capcache_attr = (struct capcache_orangefs_attribute *)attr;
+
+		if (!strcmp(capcache_attr->attr.name, "hard_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_HARD_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(capcache_attr->attr.name, "soft_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_SOFT_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(capcache_attr->attr.name,
+				   "reclaim_percentage")) {
+			if ((val > -1) && (val < 101)) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_RECLAIM_PERCENTAGE;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(capcache_attr->attr.name, "timeout_secs")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_TIMEOUT_SECS;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		}
+
+	} else if (!strcmp(kobj_id, CCACHE_KOBJ_ID)) {
+		ccache_attr = (struct ccache_orangefs_attribute *)attr;
+
+		if (!strcmp(ccache_attr->attr.name, "hard_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CCACHE_HARD_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ccache_attr->attr.name, "soft_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CCACHE_SOFT_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ccache_attr->attr.name,
+				   "reclaim_percentage")) {
+			if ((val > -1) && (val < 101)) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CCACHE_RECLAIM_PERCENTAGE;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ccache_attr->attr.name, "timeout_secs")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CCACHE_TIMEOUT_SECS;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		}
+
+	} else if (!strcmp(kobj_id, NCACHE_KOBJ_ID)) {
+		ncache_attr = (struct ncache_orangefs_attribute *)attr;
+
+		if (!strcmp(ncache_attr->attr.name, "hard_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_NCACHE_HARD_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ncache_attr->attr.name, "soft_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_NCACHE_SOFT_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ncache_attr->attr.name,
+				   "reclaim_percentage")) {
+			if ((val > -1) && (val < 101)) {
+				new_op->upcall.req.param.op =
+					ORANGEFS_PARAM_REQUEST_OP_NCACHE_RECLAIM_PERCENTAGE;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ncache_attr->attr.name, "timeout_msecs")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_NCACHE_TIMEOUT_MSECS;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		}
+
+	} else {
+		gossip_err("sysfs_service_op_store: unknown kobj_id:%s:\n",
+			   kobj_id);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	new_op->upcall.req.param.type = ORANGEFS_PARAM_REQUEST_SET;
+
+	new_op->upcall.req.param.value = val;
+
+	/*
+	 * The service_operation will return a errno return code on
+	 * error, and zero on success.
+	 */
+	rc = service_operation(new_op, "orangefs_param", ORANGEFS_OP_INTERRUPTIBLE);
+
+	if (rc < 0) {
+		gossip_err("sysfs_service_op_store: service op returned:%d:\n",
+			rc);
+		rc = 0;
+	} else {
+		rc = 1;
+	}
+
+out:
+	op_release(new_op);
+
+	if (rc == -ENOMEM || rc == 0)
+		rc = -EINVAL;
+
+	return rc;
+}
+
+static ssize_t
+	service_orangefs_store(struct orangefs_obj *orangefs_obj,
+			       struct orangefs_attribute *attr,
+			       const char *buf,
+			       size_t count)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_store(ORANGEFS_KOBJ_ID, buf, (void *) attr);
+
+	/* rc should have an errno value if the service_op went bad. */
+	if (rc == 1)
+		rc = count;
+
+	return rc;
+}
+
+static ssize_t
+	service_acache_store(struct acache_orangefs_obj *acache_orangefs_obj,
+			     struct acache_orangefs_attribute *attr,
+			     const char *buf,
+			     size_t count)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_store(ACACHE_KOBJ_ID, buf, (void *) attr);
+
+	/* rc should have an errno value if the service_op went bad. */
+	if (rc == 1)
+		rc = count;
+
+	return rc;
+}
+
+static ssize_t
+	service_capcache_store(struct capcache_orangefs_obj
+				*capcache_orangefs_obj,
+			       struct capcache_orangefs_attribute *attr,
+			       const char *buf,
+			       size_t count)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_store(CAPCACHE_KOBJ_ID, buf, (void *) attr);
+
+	/* rc should have an errno value if the service_op went bad. */
+	if (rc == 1)
+		rc = count;
+
+	return rc;
+}
+
+static ssize_t service_ccache_store(struct ccache_orangefs_obj
+					*ccache_orangefs_obj,
+				    struct ccache_orangefs_attribute *attr,
+				    const char *buf,
+				    size_t count)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_store(CCACHE_KOBJ_ID, buf, (void *) attr);
+
+	/* rc should have an errno value if the service_op went bad. */
+	if (rc == 1)
+		rc = count;
+
+	return rc;
+}
+
+static ssize_t
+	service_ncache_store(struct ncache_orangefs_obj *ncache_orangefs_obj,
+			     struct ncache_orangefs_attribute *attr,
+			     const char *buf,
+			     size_t count)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_store(NCACHE_KOBJ_ID, buf, (void *) attr);
+
+	/* rc should have an errno value if the service_op went bad. */
+	if (rc == 1)
+		rc = count;
+
+	return rc;
+}
+
+static struct orangefs_attribute op_timeout_secs_attribute =
+	__ATTR(op_timeout_secs, 0664, int_orangefs_show, int_store);
+
+static struct orangefs_attribute slot_timeout_secs_attribute =
+	__ATTR(slot_timeout_secs, 0664, int_orangefs_show, int_store);
+
+static struct orangefs_attribute perf_counter_reset_attribute =
+	__ATTR(perf_counter_reset,
+	       0664,
+	       service_orangefs_show,
+	       service_orangefs_store);
+
+static struct orangefs_attribute perf_history_size_attribute =
+	__ATTR(perf_history_size,
+	       0664,
+	       service_orangefs_show,
+	       service_orangefs_store);
+
+static struct orangefs_attribute perf_time_interval_secs_attribute =
+	__ATTR(perf_time_interval_secs,
+	       0664,
+	       service_orangefs_show,
+	       service_orangefs_store);
+
+static struct attribute *orangefs_default_attrs[] = {
+	&op_timeout_secs_attribute.attr,
+	&slot_timeout_secs_attribute.attr,
+	&perf_counter_reset_attribute.attr,
+	&perf_history_size_attribute.attr,
+	&perf_time_interval_secs_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type orangefs_ktype = {
+	.sysfs_ops = &orangefs_sysfs_ops,
+	.release = orangefs_release,
+	.default_attrs = orangefs_default_attrs,
+};
+
+static struct acache_orangefs_attribute acache_hard_limit_attribute =
+	__ATTR(hard_limit,
+	       0664,
+	       service_acache_show,
+	       service_acache_store);
+
+static struct acache_orangefs_attribute acache_reclaim_percent_attribute =
+	__ATTR(reclaim_percentage,
+	       0664,
+	       service_acache_show,
+	       service_acache_store);
+
+static struct acache_orangefs_attribute acache_soft_limit_attribute =
+	__ATTR(soft_limit,
+	       0664,
+	       service_acache_show,
+	       service_acache_store);
+
+static struct acache_orangefs_attribute acache_timeout_msecs_attribute =
+	__ATTR(timeout_msecs,
+	       0664,
+	       service_acache_show,
+	       service_acache_store);
+
+static struct attribute *acache_orangefs_default_attrs[] = {
+	&acache_hard_limit_attribute.attr,
+	&acache_reclaim_percent_attribute.attr,
+	&acache_soft_limit_attribute.attr,
+	&acache_timeout_msecs_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type acache_orangefs_ktype = {
+	.sysfs_ops = &acache_orangefs_sysfs_ops,
+	.release = acache_orangefs_release,
+	.default_attrs = acache_orangefs_default_attrs,
+};
+
+static struct capcache_orangefs_attribute capcache_hard_limit_attribute =
+	__ATTR(hard_limit,
+	       0664,
+	       service_capcache_show,
+	       service_capcache_store);
+
+static struct capcache_orangefs_attribute capcache_reclaim_percent_attribute =
+	__ATTR(reclaim_percentage,
+	       0664,
+	       service_capcache_show,
+	       service_capcache_store);
+
+static struct capcache_orangefs_attribute capcache_soft_limit_attribute =
+	__ATTR(soft_limit,
+	       0664,
+	       service_capcache_show,
+	       service_capcache_store);
+
+static struct capcache_orangefs_attribute capcache_timeout_secs_attribute =
+	__ATTR(timeout_secs,
+	       0664,
+	       service_capcache_show,
+	       service_capcache_store);
+
+static struct attribute *capcache_orangefs_default_attrs[] = {
+	&capcache_hard_limit_attribute.attr,
+	&capcache_reclaim_percent_attribute.attr,
+	&capcache_soft_limit_attribute.attr,
+	&capcache_timeout_secs_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type capcache_orangefs_ktype = {
+	.sysfs_ops = &capcache_orangefs_sysfs_ops,
+	.release = capcache_orangefs_release,
+	.default_attrs = capcache_orangefs_default_attrs,
+};
+
+static struct ccache_orangefs_attribute ccache_hard_limit_attribute =
+	__ATTR(hard_limit,
+	       0664,
+	       service_ccache_show,
+	       service_ccache_store);
+
+static struct ccache_orangefs_attribute ccache_reclaim_percent_attribute =
+	__ATTR(reclaim_percentage,
+	       0664,
+	       service_ccache_show,
+	       service_ccache_store);
+
+static struct ccache_orangefs_attribute ccache_soft_limit_attribute =
+	__ATTR(soft_limit,
+	       0664,
+	       service_ccache_show,
+	       service_ccache_store);
+
+static struct ccache_orangefs_attribute ccache_timeout_secs_attribute =
+	__ATTR(timeout_secs,
+	       0664,
+	       service_ccache_show,
+	       service_ccache_store);
+
+static struct attribute *ccache_orangefs_default_attrs[] = {
+	&ccache_hard_limit_attribute.attr,
+	&ccache_reclaim_percent_attribute.attr,
+	&ccache_soft_limit_attribute.attr,
+	&ccache_timeout_secs_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type ccache_orangefs_ktype = {
+	.sysfs_ops = &ccache_orangefs_sysfs_ops,
+	.release = ccache_orangefs_release,
+	.default_attrs = ccache_orangefs_default_attrs,
+};
+
+static struct ncache_orangefs_attribute ncache_hard_limit_attribute =
+	__ATTR(hard_limit,
+	       0664,
+	       service_ncache_show,
+	       service_ncache_store);
+
+static struct ncache_orangefs_attribute ncache_reclaim_percent_attribute =
+	__ATTR(reclaim_percentage,
+	       0664,
+	       service_ncache_show,
+	       service_ncache_store);
+
+static struct ncache_orangefs_attribute ncache_soft_limit_attribute =
+	__ATTR(soft_limit,
+	       0664,
+	       service_ncache_show,
+	       service_ncache_store);
+
+static struct ncache_orangefs_attribute ncache_timeout_msecs_attribute =
+	__ATTR(timeout_msecs,
+	       0664,
+	       service_ncache_show,
+	       service_ncache_store);
+
+static struct attribute *ncache_orangefs_default_attrs[] = {
+	&ncache_hard_limit_attribute.attr,
+	&ncache_reclaim_percent_attribute.attr,
+	&ncache_soft_limit_attribute.attr,
+	&ncache_timeout_msecs_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type ncache_orangefs_ktype = {
+	.sysfs_ops = &ncache_orangefs_sysfs_ops,
+	.release = ncache_orangefs_release,
+	.default_attrs = ncache_orangefs_default_attrs,
+};
+
+static struct pc_orangefs_attribute pc_acache_attribute =
+	__ATTR(acache,
+	       0664,
+	       service_pc_show,
+	       NULL);
+
+static struct pc_orangefs_attribute pc_capcache_attribute =
+	__ATTR(capcache,
+	       0664,
+	       service_pc_show,
+	       NULL);
+
+static struct pc_orangefs_attribute pc_ncache_attribute =
+	__ATTR(ncache,
+	       0664,
+	       service_pc_show,
+	       NULL);
+
+static struct attribute *pc_orangefs_default_attrs[] = {
+	&pc_acache_attribute.attr,
+	&pc_capcache_attribute.attr,
+	&pc_ncache_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type pc_orangefs_ktype = {
+	.sysfs_ops = &pc_orangefs_sysfs_ops,
+	.release = pc_orangefs_release,
+	.default_attrs = pc_orangefs_default_attrs,
+};
+
+static struct stats_orangefs_attribute stats_reads_attribute =
+	__ATTR(reads,
+	       0664,
+	       int_stats_show,
+	       NULL);
+
+static struct stats_orangefs_attribute stats_writes_attribute =
+	__ATTR(writes,
+	       0664,
+	       int_stats_show,
+	       NULL);
+
+static struct attribute *stats_orangefs_default_attrs[] = {
+	&stats_reads_attribute.attr,
+	&stats_writes_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type stats_orangefs_ktype = {
+	.sysfs_ops = &stats_orangefs_sysfs_ops,
+	.release = stats_orangefs_release,
+	.default_attrs = stats_orangefs_default_attrs,
+};
+
+static struct orangefs_obj *orangefs_obj;
+static struct acache_orangefs_obj *acache_orangefs_obj;
+static struct capcache_orangefs_obj *capcache_orangefs_obj;
+static struct ccache_orangefs_obj *ccache_orangefs_obj;
+static struct ncache_orangefs_obj *ncache_orangefs_obj;
+static struct pc_orangefs_obj *pc_orangefs_obj;
+static struct stats_orangefs_obj *stats_orangefs_obj;
+
+int orangefs_sysfs_init(void)
+{
+	int rc = -EINVAL;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG, "orangefs_sysfs_init: start\n");
+
+	/* create /sys/fs/orangefs. */
+	orangefs_obj = kzalloc(sizeof(*orangefs_obj), GFP_KERNEL);
+	if (!orangefs_obj)
+		goto out;
+
+	rc = kobject_init_and_add(&orangefs_obj->kobj,
+				  &orangefs_ktype,
+				  fs_kobj,
+				  ORANGEFS_KOBJ_ID);
+
+	if (rc)
+		goto ofs_obj_bail;
+
+	kobject_uevent(&orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/acache. */
+	acache_orangefs_obj = kzalloc(sizeof(*acache_orangefs_obj), GFP_KERNEL);
+	if (!acache_orangefs_obj) {
+		rc = -EINVAL;
+		goto ofs_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&acache_orangefs_obj->kobj,
+				  &acache_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  ACACHE_KOBJ_ID);
+
+	if (rc)
+		goto acache_obj_bail;
+
+	kobject_uevent(&acache_orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/capcache. */
+	capcache_orangefs_obj =
+		kzalloc(sizeof(*capcache_orangefs_obj), GFP_KERNEL);
+	if (!capcache_orangefs_obj) {
+		rc = -EINVAL;
+		goto acache_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&capcache_orangefs_obj->kobj,
+				  &capcache_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  CAPCACHE_KOBJ_ID);
+	if (rc)
+		goto capcache_obj_bail;
+
+	kobject_uevent(&capcache_orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/ccache. */
+	ccache_orangefs_obj =
+		kzalloc(sizeof(*ccache_orangefs_obj), GFP_KERNEL);
+	if (!ccache_orangefs_obj) {
+		rc = -EINVAL;
+		goto capcache_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&ccache_orangefs_obj->kobj,
+				  &ccache_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  CCACHE_KOBJ_ID);
+	if (rc)
+		goto ccache_obj_bail;
+
+	kobject_uevent(&ccache_orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/ncache. */
+	ncache_orangefs_obj = kzalloc(sizeof(*ncache_orangefs_obj), GFP_KERNEL);
+	if (!ncache_orangefs_obj) {
+		rc = -EINVAL;
+		goto ccache_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&ncache_orangefs_obj->kobj,
+				  &ncache_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  NCACHE_KOBJ_ID);
+
+	if (rc)
+		goto ncache_obj_bail;
+
+	kobject_uevent(&ncache_orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/perf_counters. */
+	pc_orangefs_obj = kzalloc(sizeof(*pc_orangefs_obj), GFP_KERNEL);
+	if (!pc_orangefs_obj) {
+		rc = -EINVAL;
+		goto ncache_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&pc_orangefs_obj->kobj,
+				  &pc_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  "perf_counters");
+
+	if (rc)
+		goto pc_obj_bail;
+
+	kobject_uevent(&pc_orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/stats. */
+	stats_orangefs_obj = kzalloc(sizeof(*stats_orangefs_obj), GFP_KERNEL);
+	if (!stats_orangefs_obj) {
+		rc = -EINVAL;
+		goto pc_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&stats_orangefs_obj->kobj,
+				  &stats_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  STATS_KOBJ_ID);
+
+	if (rc)
+		goto stats_obj_bail;
+
+	kobject_uevent(&stats_orangefs_obj->kobj, KOBJ_ADD);
+	goto out;
+
+stats_obj_bail:
+		kobject_put(&stats_orangefs_obj->kobj);
+
+pc_obj_bail:
+		kobject_put(&pc_orangefs_obj->kobj);
+
+ncache_obj_bail:
+		kobject_put(&ncache_orangefs_obj->kobj);
+
+ccache_obj_bail:
+		kobject_put(&ccache_orangefs_obj->kobj);
+
+capcache_obj_bail:
+		kobject_put(&capcache_orangefs_obj->kobj);
+
+acache_obj_bail:
+		kobject_put(&acache_orangefs_obj->kobj);
+
+ofs_obj_bail:
+		kobject_put(&orangefs_obj->kobj);
+out:
+	return rc;
+}
+
+void orangefs_sysfs_exit(void)
+{
+	gossip_debug(GOSSIP_SYSFS_DEBUG, "orangefs_sysfs_exit: start\n");
+
+	kobject_put(&acache_orangefs_obj->kobj);
+	kobject_put(&capcache_orangefs_obj->kobj);
+	kobject_put(&ccache_orangefs_obj->kobj);
+	kobject_put(&ncache_orangefs_obj->kobj);
+	kobject_put(&pc_orangefs_obj->kobj);
+	kobject_put(&stats_orangefs_obj->kobj);
+
+	kobject_put(&orangefs_obj->kobj);
+}
diff --git a/fs/orangefs/orangefs-sysfs.h b/fs/orangefs/orangefs-sysfs.h
new file mode 100644
index 000000000000..f0b76382db02
--- /dev/null
+++ b/fs/orangefs/orangefs-sysfs.h
@@ -0,0 +1,2 @@
+extern int orangefs_sysfs_init(void);
+extern void orangefs_sysfs_exit(void);
diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c
new file mode 100644
index 000000000000..40f5163b56aa
--- /dev/null
+++ b/fs/orangefs/orangefs-utils.c
@@ -0,0 +1,1048 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-dev-proto.h"
+#include "orangefs-bufmap.h"
+
+__s32 fsid_of_op(struct orangefs_kernel_op_s *op)
+{
+	__s32 fsid = ORANGEFS_FS_ID_NULL;
+
+	if (op) {
+		switch (op->upcall.type) {
+		case ORANGEFS_VFS_OP_FILE_IO:
+			fsid = op->upcall.req.io.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_LOOKUP:
+			fsid = op->upcall.req.lookup.parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_CREATE:
+			fsid = op->upcall.req.create.parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_GETATTR:
+			fsid = op->upcall.req.getattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_REMOVE:
+			fsid = op->upcall.req.remove.parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_MKDIR:
+			fsid = op->upcall.req.mkdir.parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_READDIR:
+			fsid = op->upcall.req.readdir.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_SETATTR:
+			fsid = op->upcall.req.setattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_SYMLINK:
+			fsid = op->upcall.req.sym.parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_RENAME:
+			fsid = op->upcall.req.rename.old_parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_STATFS:
+			fsid = op->upcall.req.statfs.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_TRUNCATE:
+			fsid = op->upcall.req.truncate.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_MMAP_RA_FLUSH:
+			fsid = op->upcall.req.ra_cache_flush.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_FS_UMOUNT:
+			fsid = op->upcall.req.fs_umount.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_GETXATTR:
+			fsid = op->upcall.req.getxattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_SETXATTR:
+			fsid = op->upcall.req.setxattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_LISTXATTR:
+			fsid = op->upcall.req.listxattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_REMOVEXATTR:
+			fsid = op->upcall.req.removexattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_FSYNC:
+			fsid = op->upcall.req.fsync.refn.fs_id;
+			break;
+		default:
+			break;
+		}
+	}
+	return fsid;
+}
+
+static int orangefs_inode_flags(struct ORANGEFS_sys_attr_s *attrs)
+{
+	int flags = 0;
+	if (attrs->flags & ORANGEFS_IMMUTABLE_FL)
+		flags |= S_IMMUTABLE;
+	else
+		flags &= ~S_IMMUTABLE;
+	if (attrs->flags & ORANGEFS_APPEND_FL)
+		flags |= S_APPEND;
+	else
+		flags &= ~S_APPEND;
+	if (attrs->flags & ORANGEFS_NOATIME_FL)
+		flags |= S_NOATIME;
+	else
+		flags &= ~S_NOATIME;
+	return flags;
+}
+
+static int orangefs_inode_perms(struct ORANGEFS_sys_attr_s *attrs)
+{
+	int perm_mode = 0;
+
+	if (attrs->perms & ORANGEFS_O_EXECUTE)
+		perm_mode |= S_IXOTH;
+	if (attrs->perms & ORANGEFS_O_WRITE)
+		perm_mode |= S_IWOTH;
+	if (attrs->perms & ORANGEFS_O_READ)
+		perm_mode |= S_IROTH;
+
+	if (attrs->perms & ORANGEFS_G_EXECUTE)
+		perm_mode |= S_IXGRP;
+	if (attrs->perms & ORANGEFS_G_WRITE)
+		perm_mode |= S_IWGRP;
+	if (attrs->perms & ORANGEFS_G_READ)
+		perm_mode |= S_IRGRP;
+
+	if (attrs->perms & ORANGEFS_U_EXECUTE)
+		perm_mode |= S_IXUSR;
+	if (attrs->perms & ORANGEFS_U_WRITE)
+		perm_mode |= S_IWUSR;
+	if (attrs->perms & ORANGEFS_U_READ)
+		perm_mode |= S_IRUSR;
+
+	if (attrs->perms & ORANGEFS_G_SGID)
+		perm_mode |= S_ISGID;
+	if (attrs->perms & ORANGEFS_U_SUID)
+		perm_mode |= S_ISUID;
+
+	return perm_mode;
+}
+
+/*
+ * NOTE: in kernel land, we never use the sys_attr->link_target for
+ * anything, so don't bother copying it into the sys_attr object here.
+ */
+static inline int copy_attributes_from_inode(struct inode *inode,
+					     struct ORANGEFS_sys_attr_s *attrs,
+					     struct iattr *iattr)
+{
+	umode_t tmp_mode;
+
+	if (!iattr || !inode || !attrs) {
+		gossip_err("NULL iattr (%p), inode (%p), attrs (%p) "
+			   "in copy_attributes_from_inode!\n",
+			   iattr,
+			   inode,
+			   attrs);
+		return -EINVAL;
+	}
+	/*
+	 * We need to be careful to only copy the attributes out of the
+	 * iattr object that we know are valid.
+	 */
+	attrs->mask = 0;
+	if (iattr->ia_valid & ATTR_UID) {
+		attrs->owner = from_kuid(current_user_ns(), iattr->ia_uid);
+		attrs->mask |= ORANGEFS_ATTR_SYS_UID;
+		gossip_debug(GOSSIP_UTILS_DEBUG, "(UID) %d\n", attrs->owner);
+	}
+	if (iattr->ia_valid & ATTR_GID) {
+		attrs->group = from_kgid(current_user_ns(), iattr->ia_gid);
+		attrs->mask |= ORANGEFS_ATTR_SYS_GID;
+		gossip_debug(GOSSIP_UTILS_DEBUG, "(GID) %d\n", attrs->group);
+	}
+
+	if (iattr->ia_valid & ATTR_ATIME) {
+		attrs->mask |= ORANGEFS_ATTR_SYS_ATIME;
+		if (iattr->ia_valid & ATTR_ATIME_SET) {
+			attrs->atime = (time64_t)iattr->ia_atime.tv_sec;
+			attrs->mask |= ORANGEFS_ATTR_SYS_ATIME_SET;
+		}
+	}
+	if (iattr->ia_valid & ATTR_MTIME) {
+		attrs->mask |= ORANGEFS_ATTR_SYS_MTIME;
+		if (iattr->ia_valid & ATTR_MTIME_SET) {
+			attrs->mtime = (time64_t)iattr->ia_mtime.tv_sec;
+			attrs->mask |= ORANGEFS_ATTR_SYS_MTIME_SET;
+		}
+	}
+	if (iattr->ia_valid & ATTR_CTIME)
+		attrs->mask |= ORANGEFS_ATTR_SYS_CTIME;
+
+	/*
+	 * ORANGEFS cannot set size with a setattr operation.  Probably not likely
+	 * to be requested through the VFS, but just in case, don't worry about
+	 * ATTR_SIZE
+	 */
+
+	if (iattr->ia_valid & ATTR_MODE) {
+		tmp_mode = iattr->ia_mode;
+		if (tmp_mode & (S_ISVTX)) {
+			if (is_root_handle(inode)) {
+				/*
+				 * allow sticky bit to be set on root (since
+				 * it shows up that way by default anyhow),
+				 * but don't show it to the server
+				 */
+				tmp_mode -= S_ISVTX;
+			} else {
+				gossip_debug(GOSSIP_UTILS_DEBUG,
+					     "User attempted to set sticky bit on non-root directory; returning EINVAL.\n");
+				return -EINVAL;
+			}
+		}
+
+		if (tmp_mode & (S_ISUID)) {
+			gossip_debug(GOSSIP_UTILS_DEBUG,
+				     "Attempting to set setuid bit (not supported); returning EINVAL.\n");
+			return -EINVAL;
+		}
+
+		attrs->perms = ORANGEFS_util_translate_mode(tmp_mode);
+		attrs->mask |= ORANGEFS_ATTR_SYS_PERM;
+	}
+
+	return 0;
+}
+
+static int orangefs_inode_type(enum orangefs_ds_type objtype)
+{
+	if (objtype == ORANGEFS_TYPE_METAFILE)
+		return S_IFREG;
+	else if (objtype == ORANGEFS_TYPE_DIRECTORY)
+		return S_IFDIR;
+	else if (objtype == ORANGEFS_TYPE_SYMLINK)
+		return S_IFLNK;
+	else
+		return -1;
+}
+
+static int orangefs_inode_is_stale(struct inode *inode, int new,
+    struct ORANGEFS_sys_attr_s *attrs, char *link_target)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	int type = orangefs_inode_type(attrs->objtype);
+	if (!new) {
+		/*
+		 * If the inode type or symlink target have changed then this
+		 * inode is stale.
+		 */
+		if (type == -1 || !(inode->i_mode & type)) {
+			orangefs_make_bad_inode(inode);
+			return 1;
+		}
+		if (type == S_IFLNK && strncmp(orangefs_inode->link_target,
+		    link_target, ORANGEFS_NAME_MAX)) {
+			orangefs_make_bad_inode(inode);
+			return 1;
+		}
+	}
+	return 0;
+}
+
+int orangefs_inode_getattr(struct inode *inode, int new, int size)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	loff_t inode_size, rounded_up_size;
+	int ret, type;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: called on inode %pU\n", __func__,
+	    get_khandle_from_ino(inode));
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_GETATTR);
+	if (!new_op)
+		return -ENOMEM;
+	new_op->upcall.req.getattr.refn = orangefs_inode->refn;
+	new_op->upcall.req.getattr.mask = size ?
+	    ORANGEFS_ATTR_SYS_ALL_NOHINT : ORANGEFS_ATTR_SYS_ALL_NOHINT_NOSIZE;
+
+	ret = service_operation(new_op, __func__,
+	    get_interruptible_flag(inode));
+	if (ret != 0)
+		goto out;
+
+	type = orangefs_inode_type(new_op->
+	    downcall.resp.getattr.attributes.objtype);
+	ret = orangefs_inode_is_stale(inode, new,
+	    &new_op->downcall.resp.getattr.attributes,
+	    new_op->downcall.resp.getattr.link_target);
+	if (ret) {
+		ret = -ESTALE;
+		goto out;
+	}
+
+	switch (type) {
+	case S_IFREG:
+		inode->i_flags = orangefs_inode_flags(&new_op->
+		    downcall.resp.getattr.attributes);
+		if (size) {
+			inode_size = (loff_t)new_op->
+			    downcall.resp.getattr.attributes.size;
+			rounded_up_size =
+			    (inode_size + (4096 - (inode_size % 4096)));
+			inode->i_size = inode_size;
+			orangefs_inode->blksize =
+			    new_op->downcall.resp.getattr.attributes.blksize;
+			spin_lock(&inode->i_lock);
+			inode->i_bytes = inode_size;
+			inode->i_blocks =
+			    (unsigned long)(rounded_up_size / 512);
+			spin_unlock(&inode->i_lock);
+		}
+		break;
+	case S_IFDIR:
+		inode->i_size = PAGE_CACHE_SIZE;
+		orangefs_inode->blksize = (1 << inode->i_blkbits);
+		spin_lock(&inode->i_lock);
+		inode_set_bytes(inode, inode->i_size);
+		spin_unlock(&inode->i_lock);
+		set_nlink(inode, 1);
+		break;
+	case S_IFLNK:
+		if (new) {
+			inode->i_size = (loff_t)strlen(new_op->
+			    downcall.resp.getattr.link_target);
+			orangefs_inode->blksize = (1 << inode->i_blkbits);
+			strlcpy(orangefs_inode->link_target,
+			    new_op->downcall.resp.getattr.link_target,
+			    ORANGEFS_NAME_MAX);
+			inode->i_link = orangefs_inode->link_target;
+		}
+		break;
+	}
+
+	inode->i_uid = make_kuid(&init_user_ns, new_op->
+	    downcall.resp.getattr.attributes.owner);
+	inode->i_gid = make_kgid(&init_user_ns, new_op->
+	    downcall.resp.getattr.attributes.group);
+	inode->i_atime.tv_sec = (time64_t)new_op->
+	    downcall.resp.getattr.attributes.atime;
+	inode->i_mtime.tv_sec = (time64_t)new_op->
+	    downcall.resp.getattr.attributes.mtime;
+	inode->i_ctime.tv_sec = (time64_t)new_op->
+	    downcall.resp.getattr.attributes.ctime;
+	inode->i_atime.tv_nsec = 0;
+	inode->i_mtime.tv_nsec = 0;
+	inode->i_ctime.tv_nsec = 0;
+
+	/* special case: mark the root inode as sticky */
+	inode->i_mode = type | (is_root_handle(inode) ? S_ISVTX : 0) |
+	    orangefs_inode_perms(&new_op->downcall.resp.getattr.attributes);
+
+	ret = 0;
+out:
+	op_release(new_op);
+	return ret;
+}
+
+int orangefs_inode_check_changed(struct inode *inode)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	int ret;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: called on inode %pU\n", __func__,
+	    get_khandle_from_ino(inode));
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_GETATTR);
+	if (!new_op)
+		return -ENOMEM;
+	new_op->upcall.req.getattr.refn = orangefs_inode->refn;
+	new_op->upcall.req.getattr.mask = ORANGEFS_ATTR_SYS_TYPE |
+	    ORANGEFS_ATTR_SYS_LNK_TARGET;
+
+	ret = service_operation(new_op, __func__,
+	    get_interruptible_flag(inode));
+	if (ret != 0)
+		goto out;
+
+	ret = orangefs_inode_is_stale(inode, 0,
+	    &new_op->downcall.resp.getattr.attributes,
+	    new_op->downcall.resp.getattr.link_target);
+out:
+	op_release(new_op);
+	return ret;
+}
+
+/*
+ * issues a orangefs setattr request to make sure the new attribute values
+ * take effect if successful.  returns 0 on success; -errno otherwise
+ */
+int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	int ret;
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_SETATTR);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.setattr.refn = orangefs_inode->refn;
+	ret = copy_attributes_from_inode(inode,
+		       &new_op->upcall.req.setattr.attributes,
+		       iattr);
+	if (ret >= 0) {
+		ret = service_operation(new_op, __func__,
+				get_interruptible_flag(inode));
+
+		gossip_debug(GOSSIP_UTILS_DEBUG,
+			     "orangefs_inode_setattr: returning %d\n",
+			     ret);
+	}
+
+	op_release(new_op);
+
+	/*
+	 * successful setattr should clear the atime, mtime and
+	 * ctime flags.
+	 */
+	if (ret == 0) {
+		ClearAtimeFlag(orangefs_inode);
+		ClearMtimeFlag(orangefs_inode);
+		ClearCtimeFlag(orangefs_inode);
+		ClearModeFlag(orangefs_inode);
+	}
+
+	return ret;
+}
+
+int orangefs_flush_inode(struct inode *inode)
+{
+	/*
+	 * If it is a dirty inode, this function gets called.
+	 * Gather all the information that needs to be setattr'ed
+	 * Right now, this will only be used for mode, atime, mtime
+	 * and/or ctime.
+	 */
+	struct iattr wbattr;
+	int ret;
+	int mtime_flag;
+	int ctime_flag;
+	int atime_flag;
+	int mode_flag;
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+
+	memset(&wbattr, 0, sizeof(wbattr));
+
+	/*
+	 * check inode flags up front, and clear them if they are set.  This
+	 * will prevent multiple processes from all trying to flush the same
+	 * inode if they call close() simultaneously
+	 */
+	mtime_flag = MtimeFlag(orangefs_inode);
+	ClearMtimeFlag(orangefs_inode);
+	ctime_flag = CtimeFlag(orangefs_inode);
+	ClearCtimeFlag(orangefs_inode);
+	atime_flag = AtimeFlag(orangefs_inode);
+	ClearAtimeFlag(orangefs_inode);
+	mode_flag = ModeFlag(orangefs_inode);
+	ClearModeFlag(orangefs_inode);
+
+	/*  -- Lazy atime,mtime and ctime update --
+	 * Note: all times are dictated by server in the new scheme
+	 * and not by the clients
+	 *
+	 * Also mode updates are being handled now..
+	 */
+
+	if (mtime_flag)
+		wbattr.ia_valid |= ATTR_MTIME;
+	if (ctime_flag)
+		wbattr.ia_valid |= ATTR_CTIME;
+	if (atime_flag)
+		wbattr.ia_valid |= ATTR_ATIME;
+
+	if (mode_flag) {
+		wbattr.ia_mode = inode->i_mode;
+		wbattr.ia_valid |= ATTR_MODE;
+	}
+
+	gossip_debug(GOSSIP_UTILS_DEBUG,
+		     "*********** orangefs_flush_inode: %pU "
+		     "(ia_valid %d)\n",
+		     get_khandle_from_ino(inode),
+		     wbattr.ia_valid);
+	if (wbattr.ia_valid == 0) {
+		gossip_debug(GOSSIP_UTILS_DEBUG,
+			     "orangefs_flush_inode skipping setattr()\n");
+		return 0;
+	}
+
+	gossip_debug(GOSSIP_UTILS_DEBUG,
+		     "orangefs_flush_inode (%pU) writing mode %o\n",
+		     get_khandle_from_ino(inode),
+		     inode->i_mode);
+
+	ret = orangefs_inode_setattr(inode, &wbattr);
+
+	return ret;
+}
+
+int orangefs_unmount_sb(struct super_block *sb)
+{
+	int ret = -EINVAL;
+	struct orangefs_kernel_op_s *new_op = NULL;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG,
+		     "orangefs_unmount_sb called on sb %p\n",
+		     sb);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_FS_UMOUNT);
+	if (!new_op)
+		return -ENOMEM;
+	new_op->upcall.req.fs_umount.id = ORANGEFS_SB(sb)->id;
+	new_op->upcall.req.fs_umount.fs_id = ORANGEFS_SB(sb)->fs_id;
+	strncpy(new_op->upcall.req.fs_umount.orangefs_config_server,
+		ORANGEFS_SB(sb)->devname,
+		ORANGEFS_MAX_SERVER_ADDR_LEN);
+
+	gossip_debug(GOSSIP_UTILS_DEBUG,
+		     "Attempting ORANGEFS Unmount via host %s\n",
+		     new_op->upcall.req.fs_umount.orangefs_config_server);
+
+	ret = service_operation(new_op, "orangefs_fs_umount", 0);
+
+	gossip_debug(GOSSIP_UTILS_DEBUG,
+		     "orangefs_unmount: got return value of %d\n", ret);
+	if (ret)
+		sb = ERR_PTR(ret);
+	else
+		ORANGEFS_SB(sb)->mount_pending = 1;
+
+	op_release(new_op);
+	return ret;
+}
+
+void orangefs_make_bad_inode(struct inode *inode)
+{
+	if (is_root_handle(inode)) {
+		/*
+		 * if this occurs, the pvfs2-client-core was killed but we
+		 * can't afford to lose the inode operations and such
+		 * associated with the root handle in any case.
+		 */
+		gossip_debug(GOSSIP_UTILS_DEBUG,
+			     "*** NOT making bad root inode %pU\n",
+			     get_khandle_from_ino(inode));
+	} else {
+		gossip_debug(GOSSIP_UTILS_DEBUG,
+			     "*** making bad inode %pU\n",
+			     get_khandle_from_ino(inode));
+		make_bad_inode(inode);
+	}
+}
+
+/*
+ * The following is a very dirty hack that is now a permanent part of the
+ * ORANGEFS protocol. See protocol.h for more error definitions.
+ */
+
+/* The order matches include/orangefs-types.h in the OrangeFS source. */
+static int PINT_errno_mapping[] = {
+	0, EPERM, ENOENT, EINTR, EIO, ENXIO, EBADF, EAGAIN, ENOMEM,
+	EFAULT, EBUSY, EEXIST, ENODEV, ENOTDIR, EISDIR, EINVAL, EMFILE,
+	EFBIG, ENOSPC, EROFS, EMLINK, EPIPE, EDEADLK, ENAMETOOLONG,
+	ENOLCK, ENOSYS, ENOTEMPTY, ELOOP, EWOULDBLOCK, ENOMSG, EUNATCH,
+	EBADR, EDEADLOCK, ENODATA, ETIME, ENONET, EREMOTE, ECOMM,
+	EPROTO, EBADMSG, EOVERFLOW, ERESTART, EMSGSIZE, EPROTOTYPE,
+	ENOPROTOOPT, EPROTONOSUPPORT, EOPNOTSUPP, EADDRINUSE,
+	EADDRNOTAVAIL, ENETDOWN, ENETUNREACH, ENETRESET, ENOBUFS,
+	ETIMEDOUT, ECONNREFUSED, EHOSTDOWN, EHOSTUNREACH, EALREADY,
+	EACCES, ECONNRESET, ERANGE
+};
+
+int orangefs_normalize_to_errno(__s32 error_code)
+{
+	__u32 i;
+
+	/* Success */
+	if (error_code == 0) {
+		return 0;
+	/*
+	 * This shouldn't ever happen. If it does it should be fixed on the
+	 * server.
+	 */
+	} else if (error_code > 0) {
+		gossip_err("orangefs: error status receieved.\n");
+		gossip_err("orangefs: assuming error code is inverted.\n");
+		error_code = -error_code;
+	}
+
+	/*
+	 * XXX: This is very bad since error codes from ORANGEFS may not be
+	 * suitable for return into userspace.
+	 */
+
+	/*
+	 * Convert ORANGEFS error values into errno values suitable for return
+	 * from the kernel.
+	 */
+	if ((-error_code) & ORANGEFS_NON_ERRNO_ERROR_BIT) {
+		if (((-error_code) &
+		    (ORANGEFS_ERROR_NUMBER_BITS|ORANGEFS_NON_ERRNO_ERROR_BIT|
+		    ORANGEFS_ERROR_BIT)) == ORANGEFS_ECANCEL) {
+			/*
+			 * cancellation error codes generally correspond to
+			 * a timeout from the client's perspective
+			 */
+			error_code = -ETIMEDOUT;
+		} else {
+			/* assume a default error code */
+			gossip_err("orangefs: warning: got error code without errno equivalent: %d.\n", error_code);
+			error_code = -EINVAL;
+		}
+
+	/* Convert ORANGEFS encoded errno values into regular errno values. */
+	} else if ((-error_code) & ORANGEFS_ERROR_BIT) {
+		i = (-error_code) & ~(ORANGEFS_ERROR_BIT|ORANGEFS_ERROR_CLASS_BITS);
+		if (i < sizeof(PINT_errno_mapping)/sizeof(*PINT_errno_mapping))
+			error_code = -PINT_errno_mapping[i];
+		else
+			error_code = -EINVAL;
+
+	/*
+	 * Only ORANGEFS protocol error codes should ever come here. Otherwise
+	 * there is a bug somewhere.
+	 */
+	} else {
+		gossip_err("orangefs: orangefs_normalize_to_errno: got error code which is not from ORANGEFS.\n");
+	}
+	return error_code;
+}
+
+#define NUM_MODES 11
+__s32 ORANGEFS_util_translate_mode(int mode)
+{
+	int ret = 0;
+	int i = 0;
+	static int modes[NUM_MODES] = {
+		S_IXOTH, S_IWOTH, S_IROTH,
+		S_IXGRP, S_IWGRP, S_IRGRP,
+		S_IXUSR, S_IWUSR, S_IRUSR,
+		S_ISGID, S_ISUID
+	};
+	static int orangefs_modes[NUM_MODES] = {
+		ORANGEFS_O_EXECUTE, ORANGEFS_O_WRITE, ORANGEFS_O_READ,
+		ORANGEFS_G_EXECUTE, ORANGEFS_G_WRITE, ORANGEFS_G_READ,
+		ORANGEFS_U_EXECUTE, ORANGEFS_U_WRITE, ORANGEFS_U_READ,
+		ORANGEFS_G_SGID, ORANGEFS_U_SUID
+	};
+
+	for (i = 0; i < NUM_MODES; i++)
+		if (mode & modes[i])
+			ret |= orangefs_modes[i];
+
+	return ret;
+}
+#undef NUM_MODES
+
+/*
+ * After obtaining a string representation of the client's debug
+ * keywords and their associated masks, this function is called to build an
+ * array of these values.
+ */
+int orangefs_prepare_cdm_array(char *debug_array_string)
+{
+	int i;
+	int rc = -EINVAL;
+	char *cds_head = NULL;
+	char *cds_delimiter = NULL;
+	int keyword_len = 0;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+	/*
+	 * figure out how many elements the cdm_array needs.
+	 */
+	for (i = 0; i < strlen(debug_array_string); i++)
+		if (debug_array_string[i] == '\n')
+			cdm_element_count++;
+
+	if (!cdm_element_count) {
+		pr_info("No elements in client debug array string!\n");
+		goto out;
+	}
+
+	cdm_array =
+		kzalloc(cdm_element_count * sizeof(struct client_debug_mask),
+			GFP_KERNEL);
+	if (!cdm_array) {
+		pr_info("malloc failed for cdm_array!\n");
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	cds_head = debug_array_string;
+
+	for (i = 0; i < cdm_element_count; i++) {
+		cds_delimiter = strchr(cds_head, '\n');
+		*cds_delimiter = '\0';
+
+		keyword_len = strcspn(cds_head, " ");
+
+		cdm_array[i].keyword = kzalloc(keyword_len + 1, GFP_KERNEL);
+		if (!cdm_array[i].keyword) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		sscanf(cds_head,
+		       "%s %llx %llx",
+		       cdm_array[i].keyword,
+		       (unsigned long long *)&(cdm_array[i].mask1),
+		       (unsigned long long *)&(cdm_array[i].mask2));
+
+		if (!strcmp(cdm_array[i].keyword, ORANGEFS_VERBOSE))
+			client_verbose_index = i;
+
+		if (!strcmp(cdm_array[i].keyword, ORANGEFS_ALL))
+			client_all_index = i;
+
+		cds_head = cds_delimiter + 1;
+	}
+
+	rc = cdm_element_count;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: rc:%d:\n", __func__, rc);
+
+out:
+
+	return rc;
+
+}
+
+/*
+ * /sys/kernel/debug/orangefs/debug-help can be catted to
+ * see all the available kernel and client debug keywords.
+ *
+ * When the kernel boots, we have no idea what keywords the
+ * client supports, nor their associated masks.
+ *
+ * We pass through this function once at boot and stamp a
+ * boilerplate "we don't know" message for the client in the
+ * debug-help file. We pass through here again when the client
+ * starts and then we can fill out the debug-help file fully.
+ *
+ * The client might be restarted any number of times between
+ * reboots, we only build the debug-help file the first time.
+ */
+int orangefs_prepare_debugfs_help_string(int at_boot)
+{
+	int rc = -EINVAL;
+	int i;
+	int byte_count = 0;
+	char *client_title = "Client Debug Keywords:\n";
+	char *kernel_title = "Kernel Debug Keywords:\n";
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+	if (at_boot) {
+		byte_count += strlen(HELP_STRING_UNINITIALIZED);
+		client_title = HELP_STRING_UNINITIALIZED;
+	} else {
+		/*
+		 * fill the client keyword/mask array and remember
+		 * how many elements there were.
+		 */
+		cdm_element_count =
+			orangefs_prepare_cdm_array(client_debug_array_string);
+		if (cdm_element_count <= 0)
+			goto out;
+
+		/* Count the bytes destined for debug_help_string. */
+		byte_count += strlen(client_title);
+
+		for (i = 0; i < cdm_element_count; i++) {
+			byte_count += strlen(cdm_array[i].keyword + 2);
+			if (byte_count >= DEBUG_HELP_STRING_SIZE) {
+				pr_info("%s: overflow 1!\n", __func__);
+				goto out;
+			}
+		}
+
+		gossip_debug(GOSSIP_UTILS_DEBUG,
+			     "%s: cdm_element_count:%d:\n",
+			     __func__,
+			     cdm_element_count);
+	}
+
+	byte_count += strlen(kernel_title);
+	for (i = 0; i < num_kmod_keyword_mask_map; i++) {
+		byte_count +=
+			strlen(s_kmod_keyword_mask_map[i].keyword + 2);
+		if (byte_count >= DEBUG_HELP_STRING_SIZE) {
+			pr_info("%s: overflow 2!\n", __func__);
+			goto out;
+		}
+	}
+
+	/* build debug_help_string. */
+	debug_help_string = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL);
+	if (!debug_help_string) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	strcat(debug_help_string, client_title);
+
+	if (!at_boot) {
+		for (i = 0; i < cdm_element_count; i++) {
+			strcat(debug_help_string, "\t");
+			strcat(debug_help_string, cdm_array[i].keyword);
+			strcat(debug_help_string, "\n");
+		}
+	}
+
+	strcat(debug_help_string, "\n");
+	strcat(debug_help_string, kernel_title);
+
+	for (i = 0; i < num_kmod_keyword_mask_map; i++) {
+		strcat(debug_help_string, "\t");
+		strcat(debug_help_string, s_kmod_keyword_mask_map[i].keyword);
+		strcat(debug_help_string, "\n");
+	}
+
+	rc = 0;
+
+out:
+
+	return rc;
+
+}
+
+/*
+ * kernel = type 0
+ * client = type 1
+ */
+void debug_mask_to_string(void *mask, int type)
+{
+	int i;
+	int len = 0;
+	char *debug_string;
+	int element_count = 0;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+	if (type) {
+		debug_string = client_debug_string;
+		element_count = cdm_element_count;
+	} else {
+		debug_string = kernel_debug_string;
+		element_count = num_kmod_keyword_mask_map;
+	}
+
+	memset(debug_string, 0, ORANGEFS_MAX_DEBUG_STRING_LEN);
+
+	/*
+	 * Some keywords, like "all" or "verbose", are amalgams of
+	 * numerous other keywords. Make a special check for those
+	 * before grinding through the whole mask only to find out
+	 * later...
+	 */
+	if (check_amalgam_keyword(mask, type))
+		goto out;
+
+	/* Build the debug string. */
+	for (i = 0; i < element_count; i++)
+		if (type)
+			do_c_string(mask, i);
+		else
+			do_k_string(mask, i);
+
+	len = strlen(debug_string);
+
+	if ((len) && (type))
+		client_debug_string[len - 1] = '\0';
+	else if (len)
+		kernel_debug_string[len - 1] = '\0';
+	else if (type)
+		strcpy(client_debug_string, "none");
+	else
+		strcpy(kernel_debug_string, "none");
+
+out:
+gossip_debug(GOSSIP_UTILS_DEBUG, "%s: string:%s:\n", __func__, debug_string);
+
+	return;
+
+}
+
+void do_k_string(void *k_mask, int index)
+{
+	__u64 *mask = (__u64 *) k_mask;
+
+	if (keyword_is_amalgam((char *) s_kmod_keyword_mask_map[index].keyword))
+		goto out;
+
+	if (*mask & s_kmod_keyword_mask_map[index].mask_val) {
+		if ((strlen(kernel_debug_string) +
+		     strlen(s_kmod_keyword_mask_map[index].keyword))
+			< ORANGEFS_MAX_DEBUG_STRING_LEN - 1) {
+				strcat(kernel_debug_string,
+				       s_kmod_keyword_mask_map[index].keyword);
+				strcat(kernel_debug_string, ",");
+			} else {
+				gossip_err("%s: overflow!\n", __func__);
+				strcpy(kernel_debug_string, ORANGEFS_ALL);
+				goto out;
+			}
+	}
+
+out:
+
+	return;
+}
+
+void do_c_string(void *c_mask, int index)
+{
+	struct client_debug_mask *mask = (struct client_debug_mask *) c_mask;
+
+	if (keyword_is_amalgam(cdm_array[index].keyword))
+		goto out;
+
+	if ((mask->mask1 & cdm_array[index].mask1) ||
+	    (mask->mask2 & cdm_array[index].mask2)) {
+		if ((strlen(client_debug_string) +
+		     strlen(cdm_array[index].keyword) + 1)
+			< ORANGEFS_MAX_DEBUG_STRING_LEN - 2) {
+				strcat(client_debug_string,
+				       cdm_array[index].keyword);
+				strcat(client_debug_string, ",");
+			} else {
+				gossip_err("%s: overflow!\n", __func__);
+				strcpy(client_debug_string, ORANGEFS_ALL);
+				goto out;
+			}
+	}
+out:
+	return;
+}
+
+int keyword_is_amalgam(char *keyword)
+{
+	int rc = 0;
+
+	if ((!strcmp(keyword, ORANGEFS_ALL)) || (!strcmp(keyword, ORANGEFS_VERBOSE)))
+		rc = 1;
+
+	return rc;
+}
+
+/*
+ * kernel = type 0
+ * client = type 1
+ *
+ * return 1 if we found an amalgam.
+ */
+int check_amalgam_keyword(void *mask, int type)
+{
+	__u64 *k_mask;
+	struct client_debug_mask *c_mask;
+	int k_all_index = num_kmod_keyword_mask_map - 1;
+	int rc = 0;
+
+	if (type) {
+		c_mask = (struct client_debug_mask *) mask;
+
+		if ((c_mask->mask1 == cdm_array[client_all_index].mask1) &&
+		    (c_mask->mask2 == cdm_array[client_all_index].mask2)) {
+			strcpy(client_debug_string, ORANGEFS_ALL);
+			rc = 1;
+			goto out;
+		}
+
+		if ((c_mask->mask1 == cdm_array[client_verbose_index].mask1) &&
+		    (c_mask->mask2 == cdm_array[client_verbose_index].mask2)) {
+			strcpy(client_debug_string, ORANGEFS_VERBOSE);
+			rc = 1;
+			goto out;
+		}
+
+	} else {
+		k_mask = (__u64 *) mask;
+
+		if (*k_mask >= s_kmod_keyword_mask_map[k_all_index].mask_val) {
+			strcpy(kernel_debug_string, ORANGEFS_ALL);
+			rc = 1;
+			goto out;
+		}
+	}
+
+out:
+
+	return rc;
+}
+
+/*
+ * kernel = type 0
+ * client = type 1
+ */
+void debug_string_to_mask(char *debug_string, void *mask, int type)
+{
+	char *unchecked_keyword;
+	int i;
+	char *strsep_fodder = kstrdup(debug_string, GFP_KERNEL);
+	char *original_pointer;
+	int element_count = 0;
+	struct client_debug_mask *c_mask;
+	__u64 *k_mask;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+	if (type) {
+		c_mask = (struct client_debug_mask *)mask;
+		element_count = cdm_element_count;
+	} else {
+		k_mask = (__u64 *)mask;
+		*k_mask = 0;
+		element_count = num_kmod_keyword_mask_map;
+	}
+
+	original_pointer = strsep_fodder;
+	while ((unchecked_keyword = strsep(&strsep_fodder, ",")))
+		if (strlen(unchecked_keyword)) {
+			for (i = 0; i < element_count; i++)
+				if (type)
+					do_c_mask(i,
+						  unchecked_keyword,
+						  &c_mask);
+				else
+					do_k_mask(i,
+						  unchecked_keyword,
+						  &k_mask);
+		}
+
+	kfree(original_pointer);
+}
+
+void do_c_mask(int i,
+	       char *unchecked_keyword,
+	       struct client_debug_mask **sane_mask)
+{
+
+	if (!strcmp(cdm_array[i].keyword, unchecked_keyword)) {
+		(**sane_mask).mask1 = (**sane_mask).mask1 | cdm_array[i].mask1;
+		(**sane_mask).mask2 = (**sane_mask).mask2 | cdm_array[i].mask2;
+	}
+}
+
+void do_k_mask(int i, char *unchecked_keyword, __u64 **sane_mask)
+{
+
+	if (!strcmp(s_kmod_keyword_mask_map[i].keyword, unchecked_keyword))
+		**sane_mask = (**sane_mask) |
+				s_kmod_keyword_mask_map[i].mask_val;
+}
diff --git a/fs/orangefs/protocol.h b/fs/orangefs/protocol.h
new file mode 100644
index 000000000000..45ce4ff4cbc7
--- /dev/null
+++ b/fs/orangefs/protocol.h
@@ -0,0 +1,452 @@
+#include <linux/types.h>
+#include <linux/spinlock_types.h>
+#include <linux/slab.h>
+#include <linux/ioctl.h>
+
+extern struct client_debug_mask *cdm_array;
+extern char *debug_help_string;
+extern int help_string_initialized;
+extern struct dentry *debug_dir;
+extern struct dentry *help_file_dentry;
+extern struct dentry *client_debug_dentry;
+extern const struct file_operations debug_help_fops;
+extern int client_all_index;
+extern int client_verbose_index;
+extern int cdm_element_count;
+#define DEBUG_HELP_STRING_SIZE 4096
+#define HELP_STRING_UNINITIALIZED \
+	"Client Debug Keywords are unknown until the first time\n" \
+	"the client is started after boot.\n"
+#define ORANGEFS_KMOD_DEBUG_HELP_FILE "debug-help"
+#define ORANGEFS_KMOD_DEBUG_FILE "kernel-debug"
+#define ORANGEFS_CLIENT_DEBUG_FILE "client-debug"
+#define ORANGEFS_VERBOSE "verbose"
+#define ORANGEFS_ALL "all"
+
+/* pvfs2-config.h ***********************************************************/
+#define ORANGEFS_VERSION_MAJOR 2
+#define ORANGEFS_VERSION_MINOR 9
+#define ORANGEFS_VERSION_SUB 0
+
+/* khandle stuff  ***********************************************************/
+
+/*
+ * The 2.9 core will put 64 bit handles in here like this:
+ *    1234 0000 0000 5678
+ * The 3.0 and beyond cores will put 128 bit handles in here like this:
+ *    1234 5678 90AB CDEF
+ * The kernel module will always use the first four bytes and
+ * the last four bytes as an inum.
+ */
+struct orangefs_khandle {
+	unsigned char u[16];
+}  __aligned(8);
+
+/*
+ * kernel version of an object ref.
+ */
+struct orangefs_object_kref {
+	struct orangefs_khandle khandle;
+	__s32 fs_id;
+	__s32 __pad1;
+};
+
+/*
+ * compare 2 khandles assumes little endian thus from large address to
+ * small address
+ */
+static inline int ORANGEFS_khandle_cmp(const struct orangefs_khandle *kh1,
+				   const struct orangefs_khandle *kh2)
+{
+	int i;
+
+	for (i = 15; i >= 0; i--) {
+		if (kh1->u[i] > kh2->u[i])
+			return 1;
+		if (kh1->u[i] < kh2->u[i])
+			return -1;
+	}
+
+	return 0;
+}
+
+static inline void ORANGEFS_khandle_to(const struct orangefs_khandle *kh,
+				   void *p, int size)
+{
+
+	memset(p, 0, size);
+	memcpy(p, kh->u, 16);
+
+}
+
+static inline void ORANGEFS_khandle_from(struct orangefs_khandle *kh,
+				     void *p, int size)
+{
+	memset(kh, 0, 16);
+	memcpy(kh->u, p, 16);
+
+}
+
+/* pvfs2-types.h ************************************************************/
+typedef __u32 ORANGEFS_uid;
+typedef __u32 ORANGEFS_gid;
+typedef __s32 ORANGEFS_fs_id;
+typedef __u32 ORANGEFS_permissions;
+typedef __u64 ORANGEFS_time;
+typedef __s64 ORANGEFS_size;
+typedef __u64 ORANGEFS_flags;
+typedef __u64 ORANGEFS_ds_position;
+typedef __s32 ORANGEFS_error;
+typedef __s64 ORANGEFS_offset;
+
+#define ORANGEFS_SUPER_MAGIC 0x20030528
+
+/*
+ * ORANGEFS error codes are a signed 32-bit integer. Error codes are negative, but
+ * the sign is stripped before decoding.
+ */
+
+/* Bit 31 is not used since it is the sign. */
+
+/*
+ * Bit 30 specifies that this is a ORANGEFS error. A ORANGEFS error is either an
+ * encoded errno value or a ORANGEFS protocol error.
+ */
+#define ORANGEFS_ERROR_BIT (1 << 30)
+
+/*
+ * Bit 29 specifies that this is a ORANGEFS protocol error and not an encoded
+ * errno value.
+ */
+#define ORANGEFS_NON_ERRNO_ERROR_BIT (1 << 29)
+
+/*
+ * Bits 9, 8, and 7 specify the error class, which encodes the section of
+ * server code the error originated in for logging purposes. It is not used
+ * in the kernel except to be masked out.
+ */
+#define ORANGEFS_ERROR_CLASS_BITS 0x380
+
+/* Bits 6 - 0 are reserved for the actual error code. */
+#define ORANGEFS_ERROR_NUMBER_BITS 0x7f
+
+/* Encoded errno values decoded by PINT_errno_mapping in orangefs-utils.c. */
+
+/* Our own ORANGEFS protocol error codes. */
+#define ORANGEFS_ECANCEL    (1|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_EDEVINIT   (2|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_EDETAIL    (3|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_EHOSTNTFD  (4|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_EADDRNTFD  (5|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_ENORECVR   (6|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_ETRYAGAIN  (7|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_ENOTPVFS   (8|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_ESECURITY  (9|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+
+/* permission bits */
+#define ORANGEFS_O_EXECUTE (1 << 0)
+#define ORANGEFS_O_WRITE   (1 << 1)
+#define ORANGEFS_O_READ    (1 << 2)
+#define ORANGEFS_G_EXECUTE (1 << 3)
+#define ORANGEFS_G_WRITE   (1 << 4)
+#define ORANGEFS_G_READ    (1 << 5)
+#define ORANGEFS_U_EXECUTE (1 << 6)
+#define ORANGEFS_U_WRITE   (1 << 7)
+#define ORANGEFS_U_READ    (1 << 8)
+/* no ORANGEFS_U_VTX (sticky bit) */
+#define ORANGEFS_G_SGID    (1 << 10)
+#define ORANGEFS_U_SUID    (1 << 11)
+
+/* definition taken from stdint.h */
+#define INT32_MAX (2147483647)
+#define ORANGEFS_ITERATE_START    (INT32_MAX - 1)
+#define ORANGEFS_ITERATE_END      (INT32_MAX - 2)
+#define ORANGEFS_ITERATE_NEXT     (INT32_MAX - 3)
+#define ORANGEFS_READDIR_START ORANGEFS_ITERATE_START
+#define ORANGEFS_READDIR_END   ORANGEFS_ITERATE_END
+#define ORANGEFS_IMMUTABLE_FL FS_IMMUTABLE_FL
+#define ORANGEFS_APPEND_FL    FS_APPEND_FL
+#define ORANGEFS_NOATIME_FL   FS_NOATIME_FL
+#define ORANGEFS_MIRROR_FL    0x01000000ULL
+#define ORANGEFS_O_EXECUTE (1 << 0)
+#define ORANGEFS_FS_ID_NULL       ((__s32)0)
+#define ORANGEFS_ATTR_SYS_UID                   (1 << 0)
+#define ORANGEFS_ATTR_SYS_GID                   (1 << 1)
+#define ORANGEFS_ATTR_SYS_PERM                  (1 << 2)
+#define ORANGEFS_ATTR_SYS_ATIME                 (1 << 3)
+#define ORANGEFS_ATTR_SYS_CTIME                 (1 << 4)
+#define ORANGEFS_ATTR_SYS_MTIME                 (1 << 5)
+#define ORANGEFS_ATTR_SYS_TYPE                  (1 << 6)
+#define ORANGEFS_ATTR_SYS_ATIME_SET             (1 << 7)
+#define ORANGEFS_ATTR_SYS_MTIME_SET             (1 << 8)
+#define ORANGEFS_ATTR_SYS_SIZE                  (1 << 20)
+#define ORANGEFS_ATTR_SYS_LNK_TARGET            (1 << 24)
+#define ORANGEFS_ATTR_SYS_DFILE_COUNT           (1 << 25)
+#define ORANGEFS_ATTR_SYS_DIRENT_COUNT          (1 << 26)
+#define ORANGEFS_ATTR_SYS_BLKSIZE               (1 << 28)
+#define ORANGEFS_ATTR_SYS_MIRROR_COPIES_COUNT   (1 << 29)
+#define ORANGEFS_ATTR_SYS_COMMON_ALL	\
+	(ORANGEFS_ATTR_SYS_UID	|	\
+	 ORANGEFS_ATTR_SYS_GID	|	\
+	 ORANGEFS_ATTR_SYS_PERM	|	\
+	 ORANGEFS_ATTR_SYS_ATIME	|	\
+	 ORANGEFS_ATTR_SYS_CTIME	|	\
+	 ORANGEFS_ATTR_SYS_MTIME	|	\
+	 ORANGEFS_ATTR_SYS_TYPE)
+
+#define ORANGEFS_ATTR_SYS_ALL_SETABLE		\
+(ORANGEFS_ATTR_SYS_COMMON_ALL-ORANGEFS_ATTR_SYS_TYPE)
+
+#define ORANGEFS_ATTR_SYS_ALL_NOHINT			\
+	(ORANGEFS_ATTR_SYS_COMMON_ALL		|	\
+	 ORANGEFS_ATTR_SYS_SIZE			|	\
+	 ORANGEFS_ATTR_SYS_LNK_TARGET		|	\
+	 ORANGEFS_ATTR_SYS_DFILE_COUNT		|	\
+	 ORANGEFS_ATTR_SYS_MIRROR_COPIES_COUNT	|	\
+	 ORANGEFS_ATTR_SYS_DIRENT_COUNT		|	\
+	 ORANGEFS_ATTR_SYS_BLKSIZE)
+
+#define ORANGEFS_ATTR_SYS_ALL_NOHINT_NOSIZE		\
+	(ORANGEFS_ATTR_SYS_COMMON_ALL		|	\
+	 ORANGEFS_ATTR_SYS_LNK_TARGET		|	\
+	 ORANGEFS_ATTR_SYS_DFILE_COUNT		|	\
+	 ORANGEFS_ATTR_SYS_MIRROR_COPIES_COUNT	|	\
+	 ORANGEFS_ATTR_SYS_DIRENT_COUNT		|	\
+	 ORANGEFS_ATTR_SYS_BLKSIZE)
+
+#define ORANGEFS_XATTR_REPLACE 0x2
+#define ORANGEFS_XATTR_CREATE  0x1
+#define ORANGEFS_MAX_SERVER_ADDR_LEN 256
+#define ORANGEFS_NAME_MAX                256
+/*
+ * max extended attribute name len as imposed by the VFS and exploited for the
+ * upcall request types.
+ * NOTE: Please retain them as multiples of 8 even if you wish to change them
+ * This is *NECESSARY* for supporting 32 bit user-space binaries on a 64-bit
+ * kernel. Due to implementation within DBPF, this really needs to be
+ * ORANGEFS_NAME_MAX, which it was the same value as, but no reason to let it
+ * break if that changes in the future.
+ */
+#define ORANGEFS_MAX_XATTR_NAMELEN   ORANGEFS_NAME_MAX	/* Not the same as
+						 * XATTR_NAME_MAX defined
+						 * by <linux/xattr.h>
+						 */
+#define ORANGEFS_MAX_XATTR_VALUELEN  8192	/* Not the same as XATTR_SIZE_MAX
+					 * defined by <linux/xattr.h>
+					 */
+#define ORANGEFS_MAX_XATTR_LISTLEN   16	/* Not the same as XATTR_LIST_MAX
+					 * defined by <linux/xattr.h>
+					 */
+/*
+ * ORANGEFS I/O operation types, used in both system and server interfaces.
+ */
+enum ORANGEFS_io_type {
+	ORANGEFS_IO_READ = 1,
+	ORANGEFS_IO_WRITE = 2
+};
+
+/*
+ * If this enum is modified the server parameters related to the precreate pool
+ * batch and low threshold sizes may need to be modified  to reflect this
+ * change.
+ */
+enum orangefs_ds_type {
+	ORANGEFS_TYPE_NONE = 0,
+	ORANGEFS_TYPE_METAFILE = (1 << 0),
+	ORANGEFS_TYPE_DATAFILE = (1 << 1),
+	ORANGEFS_TYPE_DIRECTORY = (1 << 2),
+	ORANGEFS_TYPE_SYMLINK = (1 << 3),
+	ORANGEFS_TYPE_DIRDATA = (1 << 4),
+	ORANGEFS_TYPE_INTERNAL = (1 << 5)	/* for the server's private use */
+};
+
+/*
+ * ORANGEFS_certificate simply stores a buffer with the buffer size.
+ * The buffer can be converted to an OpenSSL X509 struct for use.
+ */
+struct ORANGEFS_certificate {
+	__u32 buf_size;
+	unsigned char *buf;
+};
+
+/*
+ * A credential identifies a user and is signed by the client/user
+ * private key.
+ */
+struct ORANGEFS_credential {
+	__u32 userid;	/* user id */
+	__u32 num_groups;	/* length of group_array */
+	__u32 *group_array;	/* groups for which the user is a member */
+	char *issuer;		/* alias of the issuing server */
+	__u64 timeout;	/* seconds after epoch to time out */
+	__u32 sig_size;	/* length of the signature in bytes */
+	unsigned char *signature;	/* digital signature */
+	struct ORANGEFS_certificate certificate;	/* user certificate buffer */
+};
+#define extra_size_ORANGEFS_credential (ORANGEFS_REQ_LIMIT_GROUPS	*	\
+				    sizeof(__u32)		+	\
+				    ORANGEFS_REQ_LIMIT_ISSUER	+	\
+				    ORANGEFS_REQ_LIMIT_SIGNATURE	+	\
+				    extra_size_ORANGEFS_certificate)
+
+/* This structure is used by the VFS-client interaction alone */
+struct ORANGEFS_keyval_pair {
+	char key[ORANGEFS_MAX_XATTR_NAMELEN];
+	__s32 key_sz;	/* __s32 for portable, fixed-size structures */
+	__s32 val_sz;
+	char val[ORANGEFS_MAX_XATTR_VALUELEN];
+};
+
+/* pvfs2-sysint.h ***********************************************************/
+/* Describes attributes for a file, directory, or symlink. */
+struct ORANGEFS_sys_attr_s {
+	__u32 owner;
+	__u32 group;
+	__u32 perms;
+	__u64 atime;
+	__u64 mtime;
+	__u64 ctime;
+	__s64 size;
+
+	/* NOTE: caller must free if valid */
+	char *link_target;
+
+	/* Changed to __s32 so that size of structure does not change */
+	__s32 dfile_count;
+
+	/* Changed to __s32 so that size of structure does not change */
+	__s32 distr_dir_servers_initial;
+
+	/* Changed to __s32 so that size of structure does not change */
+	__s32 distr_dir_servers_max;
+
+	/* Changed to __s32 so that size of structure does not change */
+	__s32 distr_dir_split_size;
+
+	__u32 mirror_copies_count;
+
+	/* NOTE: caller must free if valid */
+	char *dist_name;
+
+	/* NOTE: caller must free if valid */
+	char *dist_params;
+
+	__s64 dirent_count;
+	enum orangefs_ds_type objtype;
+	__u64 flags;
+	__u32 mask;
+	__s64 blksize;
+};
+
+#define ORANGEFS_LOOKUP_LINK_NO_FOLLOW 0
+
+/* pint-dev.h ***************************************************************/
+
+/* parameter structure used in ORANGEFS_DEV_DEBUG ioctl command */
+struct dev_mask_info_s {
+	enum {
+		KERNEL_MASK,
+		CLIENT_MASK,
+	} mask_type;
+	__u64 mask_value;
+};
+
+struct dev_mask2_info_s {
+	__u64 mask1_value;
+	__u64 mask2_value;
+};
+
+/* pvfs2-util.h *************************************************************/
+__s32 ORANGEFS_util_translate_mode(int mode);
+
+/* pvfs2-debug.h ************************************************************/
+#include "orangefs-debug.h"
+
+/* pvfs2-internal.h *********************************************************/
+#define llu(x) (unsigned long long)(x)
+#define lld(x) (long long)(x)
+
+/* pint-dev-shared.h ********************************************************/
+#define ORANGEFS_DEV_MAGIC 'k'
+
+#define ORANGEFS_READDIR_DEFAULT_DESC_COUNT  5
+
+#define DEV_GET_MAGIC           0x1
+#define DEV_GET_MAX_UPSIZE      0x2
+#define DEV_GET_MAX_DOWNSIZE    0x3
+#define DEV_MAP                 0x4
+#define DEV_REMOUNT_ALL         0x5
+#define DEV_DEBUG               0x6
+#define DEV_UPSTREAM            0x7
+#define DEV_CLIENT_MASK         0x8
+#define DEV_CLIENT_STRING       0x9
+#define DEV_MAX_NR              0xa
+
+/* supported ioctls, codes are with respect to user-space */
+enum {
+	ORANGEFS_DEV_GET_MAGIC = _IOW(ORANGEFS_DEV_MAGIC, DEV_GET_MAGIC, __s32),
+	ORANGEFS_DEV_GET_MAX_UPSIZE =
+	    _IOW(ORANGEFS_DEV_MAGIC, DEV_GET_MAX_UPSIZE, __s32),
+	ORANGEFS_DEV_GET_MAX_DOWNSIZE =
+	    _IOW(ORANGEFS_DEV_MAGIC, DEV_GET_MAX_DOWNSIZE, __s32),
+	ORANGEFS_DEV_MAP = _IO(ORANGEFS_DEV_MAGIC, DEV_MAP),
+	ORANGEFS_DEV_REMOUNT_ALL = _IO(ORANGEFS_DEV_MAGIC, DEV_REMOUNT_ALL),
+	ORANGEFS_DEV_DEBUG = _IOR(ORANGEFS_DEV_MAGIC, DEV_DEBUG, __s32),
+	ORANGEFS_DEV_UPSTREAM = _IOW(ORANGEFS_DEV_MAGIC, DEV_UPSTREAM, int),
+	ORANGEFS_DEV_CLIENT_MASK = _IOW(ORANGEFS_DEV_MAGIC,
+				    DEV_CLIENT_MASK,
+				    struct dev_mask2_info_s),
+	ORANGEFS_DEV_CLIENT_STRING = _IOW(ORANGEFS_DEV_MAGIC,
+				      DEV_CLIENT_STRING,
+				      char *),
+	ORANGEFS_DEV_MAXNR = DEV_MAX_NR,
+};
+
+/*
+ * version number for use in communicating between kernel space and user
+ * space. Zero signifies the upstream version of the kernel module.
+ */
+#define ORANGEFS_KERNEL_PROTO_VERSION 0
+#define ORANGEFS_MINIMUM_USERSPACE_VERSION 20904
+
+/*
+ * describes memory regions to map in the ORANGEFS_DEV_MAP ioctl.
+ * NOTE: See devorangefs-req.c for 32 bit compat structure.
+ * Since this structure has a variable-sized layout that is different
+ * on 32 and 64 bit platforms, we need to normalize to a 64 bit layout
+ * on such systems before servicing ioctl calls from user-space binaries
+ * that may be 32 bit!
+ */
+struct ORANGEFS_dev_map_desc {
+	void *ptr;
+	__s32 total_size;
+	__s32 size;
+	__s32 count;
+};
+
+/* gossip.h *****************************************************************/
+
+#ifdef GOSSIP_DISABLE_DEBUG
+#define gossip_debug(mask, format, f...) do {} while (0)
+#else
+extern __u64 gossip_debug_mask;
+extern struct client_debug_mask client_debug_mask;
+
+/* try to avoid function call overhead by checking masks in macro */
+#define gossip_debug(mask, format, f...)			\
+do {								\
+	if (gossip_debug_mask & mask)				\
+		printk(format, ##f);				\
+} while (0)
+#endif /* GOSSIP_DISABLE_DEBUG */
+
+/* do file and line number printouts w/ the GNU preprocessor */
+#define gossip_ldebug(mask, format, f...)				\
+		gossip_debug(mask, "%s: " format, __func__, ##f)
+
+#define gossip_err printk
+#define gossip_lerr(format, f...)					\
+		gossip_err("%s line %d: " format,			\
+			   __FILE__,					\
+			   __LINE__,					\
+			   ##f)
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
new file mode 100644
index 000000000000..b9da9a0281c9
--- /dev/null
+++ b/fs/orangefs/super.c
@@ -0,0 +1,559 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+#include <linux/parser.h>
+
+/* a cache for orangefs-inode objects (i.e. orangefs inode private data) */
+static struct kmem_cache *orangefs_inode_cache;
+
+/* list for storing orangefs specific superblocks in use */
+LIST_HEAD(orangefs_superblocks);
+
+DEFINE_SPINLOCK(orangefs_superblocks_lock);
+
+enum {
+	Opt_intr,
+	Opt_acl,
+	Opt_local_lock,
+
+	Opt_err
+};
+
+static const match_table_t tokens = {
+	{ Opt_acl,		"acl" },
+	{ Opt_intr,		"intr" },
+	{ Opt_local_lock,	"local_lock" },
+	{ Opt_err,	NULL }
+};
+
+
+static int parse_mount_options(struct super_block *sb, char *options,
+		int silent)
+{
+	struct orangefs_sb_info_s *orangefs_sb = ORANGEFS_SB(sb);
+	substring_t args[MAX_OPT_ARGS];
+	char *p;
+
+	/*
+	 * Force any potential flags that might be set from the mount
+	 * to zero, ie, initialize to unset.
+	 */
+	sb->s_flags &= ~MS_POSIXACL;
+	orangefs_sb->flags &= ~ORANGEFS_OPT_INTR;
+	orangefs_sb->flags &= ~ORANGEFS_OPT_LOCAL_LOCK;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+
+		if (!*p)
+			continue;
+
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_acl:
+			sb->s_flags |= MS_POSIXACL;
+			break;
+		case Opt_intr:
+			orangefs_sb->flags |= ORANGEFS_OPT_INTR;
+			break;
+		case Opt_local_lock:
+			orangefs_sb->flags |= ORANGEFS_OPT_LOCAL_LOCK;
+			break;
+		default:
+			goto fail;
+		}
+	}
+
+	return 0;
+fail:
+	if (!silent)
+		gossip_err("Error: mount option [%s] is not supported.\n", p);
+	return -EINVAL;
+}
+
+static void orangefs_inode_cache_ctor(void *req)
+{
+	struct orangefs_inode_s *orangefs_inode = req;
+
+	inode_init_once(&orangefs_inode->vfs_inode);
+	init_rwsem(&orangefs_inode->xattr_sem);
+
+	orangefs_inode->vfs_inode.i_version = 1;
+}
+
+static struct inode *orangefs_alloc_inode(struct super_block *sb)
+{
+	struct orangefs_inode_s *orangefs_inode;
+
+	orangefs_inode = kmem_cache_alloc(orangefs_inode_cache, GFP_KERNEL);
+	if (orangefs_inode == NULL) {
+		gossip_err("Failed to allocate orangefs_inode\n");
+		return NULL;
+	}
+
+	/*
+	 * We want to clear everything except for rw_semaphore and the
+	 * vfs_inode.
+	 */
+	memset(&orangefs_inode->refn.khandle, 0, 16);
+	orangefs_inode->refn.fs_id = ORANGEFS_FS_ID_NULL;
+	orangefs_inode->last_failed_block_index_read = 0;
+	memset(orangefs_inode->link_target, 0, sizeof(orangefs_inode->link_target));
+	orangefs_inode->pinode_flags = 0;
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_alloc_inode: allocated %p\n",
+		     &orangefs_inode->vfs_inode);
+	return &orangefs_inode->vfs_inode;
+}
+
+static void orangefs_destroy_inode(struct inode *inode)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+			"%s: deallocated %p destroying inode %pU\n",
+			__func__, orangefs_inode, get_khandle_from_ino(inode));
+
+	kmem_cache_free(orangefs_inode_cache, orangefs_inode);
+}
+
+/*
+ * NOTE: information filled in here is typically reflected in the
+ * output of the system command 'df'
+*/
+static int orangefs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	int ret = -ENOMEM;
+	struct orangefs_kernel_op_s *new_op = NULL;
+	int flags = 0;
+	struct super_block *sb = NULL;
+
+	sb = dentry->d_sb;
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_statfs: called on sb %p (fs_id is %d)\n",
+		     sb,
+		     (int)(ORANGEFS_SB(sb)->fs_id));
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_STATFS);
+	if (!new_op)
+		return ret;
+	new_op->upcall.req.statfs.fs_id = ORANGEFS_SB(sb)->fs_id;
+
+	if (ORANGEFS_SB(sb)->flags & ORANGEFS_OPT_INTR)
+		flags = ORANGEFS_OP_INTERRUPTIBLE;
+
+	ret = service_operation(new_op, "orangefs_statfs", flags);
+
+	if (new_op->downcall.status < 0)
+		goto out_op_release;
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "%s: got %ld blocks available | "
+		     "%ld blocks total | %ld block size | "
+		     "%ld files total | %ld files avail\n",
+		     __func__,
+		     (long)new_op->downcall.resp.statfs.blocks_avail,
+		     (long)new_op->downcall.resp.statfs.blocks_total,
+		     (long)new_op->downcall.resp.statfs.block_size,
+		     (long)new_op->downcall.resp.statfs.files_total,
+		     (long)new_op->downcall.resp.statfs.files_avail);
+
+	buf->f_type = sb->s_magic;
+	memcpy(&buf->f_fsid, &ORANGEFS_SB(sb)->fs_id, sizeof(buf->f_fsid));
+	buf->f_bsize = new_op->downcall.resp.statfs.block_size;
+	buf->f_namelen = ORANGEFS_NAME_MAX;
+
+	buf->f_blocks = (sector_t) new_op->downcall.resp.statfs.blocks_total;
+	buf->f_bfree = (sector_t) new_op->downcall.resp.statfs.blocks_avail;
+	buf->f_bavail = (sector_t) new_op->downcall.resp.statfs.blocks_avail;
+	buf->f_files = (sector_t) new_op->downcall.resp.statfs.files_total;
+	buf->f_ffree = (sector_t) new_op->downcall.resp.statfs.files_avail;
+	buf->f_frsize = sb->s_blocksize;
+
+out_op_release:
+	op_release(new_op);
+	gossip_debug(GOSSIP_SUPER_DEBUG, "orangefs_statfs: returning %d\n", ret);
+	return ret;
+}
+
+/*
+ * Remount as initiated by VFS layer.  We just need to reparse the mount
+ * options, no need to signal pvfs2-client-core about it.
+ */
+static int orangefs_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	gossip_debug(GOSSIP_SUPER_DEBUG, "orangefs_remount_fs: called\n");
+	return parse_mount_options(sb, data, 1);
+}
+
+/*
+ * Remount as initiated by pvfs2-client-core on restart.  This is used to
+ * repopulate mount information left from previous pvfs2-client-core.
+ *
+ * the idea here is that given a valid superblock, we're
+ * re-initializing the user space client with the initial mount
+ * information specified when the super block was first initialized.
+ * this is very different than the first initialization/creation of a
+ * superblock.  we use the special service_priority_operation to make
+ * sure that the mount gets ahead of any other pending operation that
+ * is waiting for servicing.  this means that the pvfs2-client won't
+ * fail to start several times for all other pending operations before
+ * the client regains all of the mount information from us.
+ * NOTE: this function assumes that the request_mutex is already acquired!
+ */
+int orangefs_remount(struct orangefs_sb_info_s *orangefs_sb)
+{
+	struct orangefs_kernel_op_s *new_op;
+	int ret = -EINVAL;
+
+	gossip_debug(GOSSIP_SUPER_DEBUG, "orangefs_remount: called\n");
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_FS_MOUNT);
+	if (!new_op)
+		return -ENOMEM;
+	strncpy(new_op->upcall.req.fs_mount.orangefs_config_server,
+		orangefs_sb->devname,
+		ORANGEFS_MAX_SERVER_ADDR_LEN);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "Attempting ORANGEFS Remount via host %s\n",
+		     new_op->upcall.req.fs_mount.orangefs_config_server);
+
+	/*
+	 * we assume that the calling function has already acquired the
+	 * request_mutex to prevent other operations from bypassing
+	 * this one
+	 */
+	ret = service_operation(new_op, "orangefs_remount",
+		ORANGEFS_OP_PRIORITY | ORANGEFS_OP_NO_MUTEX);
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_remount: mount got return value of %d\n",
+		     ret);
+	if (ret == 0) {
+		/*
+		 * store the id assigned to this sb -- it's just a
+		 * short-lived mapping that the system interface uses
+		 * to map this superblock to a particular mount entry
+		 */
+		orangefs_sb->id = new_op->downcall.resp.fs_mount.id;
+		orangefs_sb->mount_pending = 0;
+	}
+
+	op_release(new_op);
+	return ret;
+}
+
+int fsid_key_table_initialize(void)
+{
+	return 0;
+}
+
+void fsid_key_table_finalize(void)
+{
+}
+
+/* Called whenever the VFS dirties the inode in response to atime updates */
+static void orangefs_dirty_inode(struct inode *inode, int flags)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_dirty_inode: %pU\n",
+		     get_khandle_from_ino(inode));
+	SetAtimeFlag(orangefs_inode);
+}
+
+static const struct super_operations orangefs_s_ops = {
+	.alloc_inode = orangefs_alloc_inode,
+	.destroy_inode = orangefs_destroy_inode,
+	.dirty_inode = orangefs_dirty_inode,
+	.drop_inode = generic_delete_inode,
+	.statfs = orangefs_statfs,
+	.remount_fs = orangefs_remount_fs,
+	.show_options = generic_show_options,
+};
+
+static struct dentry *orangefs_fh_to_dentry(struct super_block *sb,
+				  struct fid *fid,
+				  int fh_len,
+				  int fh_type)
+{
+	struct orangefs_object_kref refn;
+
+	if (fh_len < 5 || fh_type > 2)
+		return NULL;
+
+	ORANGEFS_khandle_from(&(refn.khandle), fid->raw, 16);
+	refn.fs_id = (u32) fid->raw[4];
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "fh_to_dentry: handle %pU, fs_id %d\n",
+		     &refn.khandle,
+		     refn.fs_id);
+
+	return d_obtain_alias(orangefs_iget(sb, &refn));
+}
+
+static int orangefs_encode_fh(struct inode *inode,
+		    __u32 *fh,
+		    int *max_len,
+		    struct inode *parent)
+{
+	int len = parent ? 10 : 5;
+	int type = 1;
+	struct orangefs_object_kref refn;
+
+	if (*max_len < len) {
+		gossip_lerr("fh buffer is too small for encoding\n");
+		*max_len = len;
+		type = 255;
+		goto out;
+	}
+
+	refn = ORANGEFS_I(inode)->refn;
+	ORANGEFS_khandle_to(&refn.khandle, fh, 16);
+	fh[4] = refn.fs_id;
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "Encoding fh: handle %pU, fsid %u\n",
+		     &refn.khandle,
+		     refn.fs_id);
+
+
+	if (parent) {
+		refn = ORANGEFS_I(parent)->refn;
+		ORANGEFS_khandle_to(&refn.khandle, (char *) fh + 20, 16);
+		fh[9] = refn.fs_id;
+
+		type = 2;
+		gossip_debug(GOSSIP_SUPER_DEBUG,
+			     "Encoding parent: handle %pU, fsid %u\n",
+			     &refn.khandle,
+			     refn.fs_id);
+	}
+	*max_len = len;
+
+out:
+	return type;
+}
+
+static const struct export_operations orangefs_export_ops = {
+	.encode_fh = orangefs_encode_fh,
+	.fh_to_dentry = orangefs_fh_to_dentry,
+};
+
+static int orangefs_fill_sb(struct super_block *sb,
+		struct orangefs_fs_mount_response *fs_mount,
+		void *data, int silent)
+{
+	int ret = -EINVAL;
+	struct inode *root = NULL;
+	struct dentry *root_dentry = NULL;
+	struct orangefs_object_kref root_object;
+
+	/* alloc and init our private orangefs sb info */
+	sb->s_fs_info = kzalloc(sizeof(struct orangefs_sb_info_s), GFP_KERNEL);
+	if (!ORANGEFS_SB(sb))
+		return -ENOMEM;
+	ORANGEFS_SB(sb)->sb = sb;
+
+	ORANGEFS_SB(sb)->root_khandle = fs_mount->root_khandle;
+	ORANGEFS_SB(sb)->fs_id = fs_mount->fs_id;
+	ORANGEFS_SB(sb)->id = fs_mount->id;
+
+	if (data) {
+		ret = parse_mount_options(sb, data, silent);
+		if (ret)
+			return ret;
+	}
+
+	/* Hang the xattr handlers off the superblock */
+	sb->s_xattr = orangefs_xattr_handlers;
+	sb->s_magic = ORANGEFS_SUPER_MAGIC;
+	sb->s_op = &orangefs_s_ops;
+	sb->s_d_op = &orangefs_dentry_operations;
+
+	sb->s_blocksize = orangefs_bufmap_size_query();
+	sb->s_blocksize_bits = orangefs_bufmap_shift_query();
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+
+	root_object.khandle = ORANGEFS_SB(sb)->root_khandle;
+	root_object.fs_id = ORANGEFS_SB(sb)->fs_id;
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "get inode %pU, fsid %d\n",
+		     &root_object.khandle,
+		     root_object.fs_id);
+
+	root = orangefs_iget(sb, &root_object);
+	if (IS_ERR(root))
+		return PTR_ERR(root);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "Allocated root inode [%p] with mode %x\n",
+		     root,
+		     root->i_mode);
+
+	/* allocates and places root dentry in dcache */
+	root_dentry = d_make_root(root);
+	if (!root_dentry)
+		return -ENOMEM;
+
+	sb->s_export_op = &orangefs_export_ops;
+	sb->s_root = root_dentry;
+	return 0;
+}
+
+struct dentry *orangefs_mount(struct file_system_type *fst,
+			   int flags,
+			   const char *devname,
+			   void *data)
+{
+	int ret = -EINVAL;
+	struct super_block *sb = ERR_PTR(-EINVAL);
+	struct orangefs_kernel_op_s *new_op;
+	struct dentry *d = ERR_PTR(-EINVAL);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_mount: called with devname %s\n",
+		     devname);
+
+	if (!devname) {
+		gossip_err("ERROR: device name not specified.\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_FS_MOUNT);
+	if (!new_op)
+		return ERR_PTR(-ENOMEM);
+
+	strncpy(new_op->upcall.req.fs_mount.orangefs_config_server,
+		devname,
+		ORANGEFS_MAX_SERVER_ADDR_LEN);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "Attempting ORANGEFS Mount via host %s\n",
+		     new_op->upcall.req.fs_mount.orangefs_config_server);
+
+	ret = service_operation(new_op, "orangefs_mount", 0);
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_mount: mount got return value of %d\n", ret);
+	if (ret)
+		goto free_op;
+
+	if (new_op->downcall.resp.fs_mount.fs_id == ORANGEFS_FS_ID_NULL) {
+		gossip_err("ERROR: Retrieved null fs_id\n");
+		ret = -EINVAL;
+		goto free_op;
+	}
+
+	sb = sget(fst, NULL, set_anon_super, flags, NULL);
+
+	if (IS_ERR(sb)) {
+		d = ERR_CAST(sb);
+		goto free_op;
+	}
+
+	ret = orangefs_fill_sb(sb,
+	      &new_op->downcall.resp.fs_mount, data,
+	      flags & MS_SILENT ? 1 : 0);
+
+	if (ret) {
+		d = ERR_PTR(ret);
+		goto free_op;
+	}
+
+	/*
+	 * on successful mount, store the devname and data
+	 * used
+	 */
+	strncpy(ORANGEFS_SB(sb)->devname,
+		devname,
+		ORANGEFS_MAX_SERVER_ADDR_LEN);
+
+	/* mount_pending must be cleared */
+	ORANGEFS_SB(sb)->mount_pending = 0;
+
+	/*
+	 * finally, add this sb to our list of known orangefs
+	 * sb's
+	 */
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "Adding SB %p to orangefs superblocks\n",
+		     ORANGEFS_SB(sb));
+	spin_lock(&orangefs_superblocks_lock);
+	list_add_tail(&ORANGEFS_SB(sb)->list, &orangefs_superblocks);
+	spin_unlock(&orangefs_superblocks_lock);
+	op_release(new_op);
+	return dget(sb->s_root);
+
+free_op:
+	gossip_err("orangefs_mount: mount request failed with %d\n", ret);
+	if (ret == -EINVAL) {
+		gossip_err("Ensure that all orangefs-servers have the same FS configuration files\n");
+		gossip_err("Look at pvfs2-client-core log file (typically /tmp/pvfs2-client.log) for more details\n");
+	}
+
+	op_release(new_op);
+
+	return d;
+}
+
+void orangefs_kill_sb(struct super_block *sb)
+{
+	gossip_debug(GOSSIP_SUPER_DEBUG, "orangefs_kill_sb: called\n");
+
+	/* provided sb cleanup */
+	kill_anon_super(sb);
+
+	/*
+	 * issue the unmount to userspace to tell it to remove the
+	 * dynamic mount info it has for this superblock
+	 */
+	 orangefs_unmount_sb(sb);
+
+	/* remove the sb from our list of orangefs specific sb's */
+
+	spin_lock(&orangefs_superblocks_lock);
+	__list_del_entry(&ORANGEFS_SB(sb)->list);	/* not list_del_init */
+	ORANGEFS_SB(sb)->list.prev = NULL;
+	spin_unlock(&orangefs_superblocks_lock);
+
+	/*
+	 * make sure that ORANGEFS_DEV_REMOUNT_ALL loop that might've seen us
+	 * gets completed before we free the dang thing.
+	 */
+	mutex_lock(&request_mutex);
+	mutex_unlock(&request_mutex);
+
+	/* free the orangefs superblock private data */
+	kfree(ORANGEFS_SB(sb));
+}
+
+int orangefs_inode_cache_initialize(void)
+{
+	orangefs_inode_cache = kmem_cache_create("orangefs_inode_cache",
+					      sizeof(struct orangefs_inode_s),
+					      0,
+					      ORANGEFS_CACHE_CREATE_FLAGS,
+					      orangefs_inode_cache_ctor);
+
+	if (!orangefs_inode_cache) {
+		gossip_err("Cannot create orangefs_inode_cache\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+int orangefs_inode_cache_finalize(void)
+{
+	kmem_cache_destroy(orangefs_inode_cache);
+	return 0;
+}
diff --git a/fs/orangefs/symlink.c b/fs/orangefs/symlink.c
new file mode 100644
index 000000000000..6418dd638680
--- /dev/null
+++ b/fs/orangefs/symlink.c
@@ -0,0 +1,19 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+struct inode_operations orangefs_symlink_inode_operations = {
+	.readlink = generic_readlink,
+	.get_link = simple_get_link,
+	.setattr = orangefs_setattr,
+	.getattr = orangefs_getattr,
+	.listxattr = orangefs_listxattr,
+	.setxattr = generic_setxattr,
+	.permission = orangefs_permission,
+};
diff --git a/fs/orangefs/upcall.h b/fs/orangefs/upcall.h
new file mode 100644
index 000000000000..001b20239407
--- /dev/null
+++ b/fs/orangefs/upcall.h
@@ -0,0 +1,246 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#ifndef __UPCALL_H
+#define __UPCALL_H
+
+/*
+ * Sanitized this header file to fix
+ * 32-64 bit interaction issues between
+ * client-core and device
+ */
+struct orangefs_io_request_s {
+	__s32 __pad1;
+	__s32 buf_index;
+	__s32 count;
+	__s32 __pad2;
+	__s64 offset;
+	struct orangefs_object_kref refn;
+	enum ORANGEFS_io_type io_type;
+	__s32 readahead_size;
+};
+
+struct orangefs_lookup_request_s {
+	__s32 sym_follow;
+	__s32 __pad1;
+	struct orangefs_object_kref parent_refn;
+	char d_name[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_create_request_s {
+	struct orangefs_object_kref parent_refn;
+	struct ORANGEFS_sys_attr_s attributes;
+	char d_name[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_symlink_request_s {
+	struct orangefs_object_kref parent_refn;
+	struct ORANGEFS_sys_attr_s attributes;
+	char entry_name[ORANGEFS_NAME_MAX];
+	char target[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_getattr_request_s {
+	struct orangefs_object_kref refn;
+	__u32 mask;
+	__u32 __pad1;
+};
+
+struct orangefs_setattr_request_s {
+	struct orangefs_object_kref refn;
+	struct ORANGEFS_sys_attr_s attributes;
+};
+
+struct orangefs_remove_request_s {
+	struct orangefs_object_kref parent_refn;
+	char d_name[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_mkdir_request_s {
+	struct orangefs_object_kref parent_refn;
+	struct ORANGEFS_sys_attr_s attributes;
+	char d_name[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_readdir_request_s {
+	struct orangefs_object_kref refn;
+	__u64 token;
+	__s32 max_dirent_count;
+	__s32 buf_index;
+};
+
+struct orangefs_readdirplus_request_s {
+	struct orangefs_object_kref refn;
+	__u64 token;
+	__s32 max_dirent_count;
+	__u32 mask;
+	__s32 buf_index;
+	__s32 __pad1;
+};
+
+struct orangefs_rename_request_s {
+	struct orangefs_object_kref old_parent_refn;
+	struct orangefs_object_kref new_parent_refn;
+	char d_old_name[ORANGEFS_NAME_MAX];
+	char d_new_name[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_statfs_request_s {
+	__s32 fs_id;
+	__s32 __pad1;
+};
+
+struct orangefs_truncate_request_s {
+	struct orangefs_object_kref refn;
+	__s64 size;
+};
+
+struct orangefs_mmap_ra_cache_flush_request_s {
+	struct orangefs_object_kref refn;
+};
+
+struct orangefs_fs_mount_request_s {
+	char orangefs_config_server[ORANGEFS_MAX_SERVER_ADDR_LEN];
+};
+
+struct orangefs_fs_umount_request_s {
+	__s32 id;
+	__s32 fs_id;
+	char orangefs_config_server[ORANGEFS_MAX_SERVER_ADDR_LEN];
+};
+
+struct orangefs_getxattr_request_s {
+	struct orangefs_object_kref refn;
+	__s32 key_sz;
+	__s32 __pad1;
+	char key[ORANGEFS_MAX_XATTR_NAMELEN];
+};
+
+struct orangefs_setxattr_request_s {
+	struct orangefs_object_kref refn;
+	struct ORANGEFS_keyval_pair keyval;
+	__s32 flags;
+	__s32 __pad1;
+};
+
+struct orangefs_listxattr_request_s {
+	struct orangefs_object_kref refn;
+	__s32 requested_count;
+	__s32 __pad1;
+	__u64 token;
+};
+
+struct orangefs_removexattr_request_s {
+	struct orangefs_object_kref refn;
+	__s32 key_sz;
+	__s32 __pad1;
+	char key[ORANGEFS_MAX_XATTR_NAMELEN];
+};
+
+struct orangefs_op_cancel_s {
+	__u64 op_tag;
+};
+
+struct orangefs_fsync_request_s {
+	struct orangefs_object_kref refn;
+};
+
+enum orangefs_param_request_type {
+	ORANGEFS_PARAM_REQUEST_SET = 1,
+	ORANGEFS_PARAM_REQUEST_GET = 2
+};
+
+enum orangefs_param_request_op {
+	ORANGEFS_PARAM_REQUEST_OP_ACACHE_TIMEOUT_MSECS = 1,
+	ORANGEFS_PARAM_REQUEST_OP_ACACHE_HARD_LIMIT = 2,
+	ORANGEFS_PARAM_REQUEST_OP_ACACHE_SOFT_LIMIT = 3,
+	ORANGEFS_PARAM_REQUEST_OP_ACACHE_RECLAIM_PERCENTAGE = 4,
+	ORANGEFS_PARAM_REQUEST_OP_PERF_TIME_INTERVAL_SECS = 5,
+	ORANGEFS_PARAM_REQUEST_OP_PERF_HISTORY_SIZE = 6,
+	ORANGEFS_PARAM_REQUEST_OP_PERF_RESET = 7,
+	ORANGEFS_PARAM_REQUEST_OP_NCACHE_TIMEOUT_MSECS = 8,
+	ORANGEFS_PARAM_REQUEST_OP_NCACHE_HARD_LIMIT = 9,
+	ORANGEFS_PARAM_REQUEST_OP_NCACHE_SOFT_LIMIT = 10,
+	ORANGEFS_PARAM_REQUEST_OP_NCACHE_RECLAIM_PERCENTAGE = 11,
+	ORANGEFS_PARAM_REQUEST_OP_STATIC_ACACHE_TIMEOUT_MSECS = 12,
+	ORANGEFS_PARAM_REQUEST_OP_STATIC_ACACHE_HARD_LIMIT = 13,
+	ORANGEFS_PARAM_REQUEST_OP_STATIC_ACACHE_SOFT_LIMIT = 14,
+	ORANGEFS_PARAM_REQUEST_OP_STATIC_ACACHE_RECLAIM_PERCENTAGE = 15,
+	ORANGEFS_PARAM_REQUEST_OP_CLIENT_DEBUG = 16,
+	ORANGEFS_PARAM_REQUEST_OP_CCACHE_TIMEOUT_SECS = 17,
+	ORANGEFS_PARAM_REQUEST_OP_CCACHE_HARD_LIMIT = 18,
+	ORANGEFS_PARAM_REQUEST_OP_CCACHE_SOFT_LIMIT = 19,
+	ORANGEFS_PARAM_REQUEST_OP_CCACHE_RECLAIM_PERCENTAGE = 20,
+	ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_TIMEOUT_SECS = 21,
+	ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_HARD_LIMIT = 22,
+	ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_SOFT_LIMIT = 23,
+	ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_RECLAIM_PERCENTAGE = 24,
+	ORANGEFS_PARAM_REQUEST_OP_TWO_MASK_VALUES = 25,
+};
+
+struct orangefs_param_request_s {
+	enum orangefs_param_request_type type;
+	enum orangefs_param_request_op op;
+	__s64 value;
+	char s_value[ORANGEFS_MAX_DEBUG_STRING_LEN];
+};
+
+enum orangefs_perf_count_request_type {
+	ORANGEFS_PERF_COUNT_REQUEST_ACACHE = 1,
+	ORANGEFS_PERF_COUNT_REQUEST_NCACHE = 2,
+	ORANGEFS_PERF_COUNT_REQUEST_CAPCACHE = 3,
+};
+
+struct orangefs_perf_count_request_s {
+	enum orangefs_perf_count_request_type type;
+	__s32 __pad1;
+};
+
+struct orangefs_fs_key_request_s {
+	__s32 fsid;
+	__s32 __pad1;
+};
+
+struct orangefs_upcall_s {
+	__s32 type;
+	__u32 uid;
+	__u32 gid;
+	int pid;
+	int tgid;
+	/* Trailers unused but must be retained for protocol compatibility. */
+	__s64 trailer_size;
+	char *trailer_buf;
+
+	union {
+		struct orangefs_io_request_s io;
+		struct orangefs_lookup_request_s lookup;
+		struct orangefs_create_request_s create;
+		struct orangefs_symlink_request_s sym;
+		struct orangefs_getattr_request_s getattr;
+		struct orangefs_setattr_request_s setattr;
+		struct orangefs_remove_request_s remove;
+		struct orangefs_mkdir_request_s mkdir;
+		struct orangefs_readdir_request_s readdir;
+		struct orangefs_readdirplus_request_s readdirplus;
+		struct orangefs_rename_request_s rename;
+		struct orangefs_statfs_request_s statfs;
+		struct orangefs_truncate_request_s truncate;
+		struct orangefs_mmap_ra_cache_flush_request_s ra_cache_flush;
+		struct orangefs_fs_mount_request_s fs_mount;
+		struct orangefs_fs_umount_request_s fs_umount;
+		struct orangefs_getxattr_request_s getxattr;
+		struct orangefs_setxattr_request_s setxattr;
+		struct orangefs_listxattr_request_s listxattr;
+		struct orangefs_removexattr_request_s removexattr;
+		struct orangefs_op_cancel_s cancel;
+		struct orangefs_fsync_request_s fsync;
+		struct orangefs_param_request_s param;
+		struct orangefs_perf_count_request_s perf_count;
+		struct orangefs_fs_key_request_s fs_key;
+	} req;
+};
+
+#endif /* __UPCALL_H */
diff --git a/fs/orangefs/waitqueue.c b/fs/orangefs/waitqueue.c
new file mode 100644
index 000000000000..31635bc303fe
--- /dev/null
+++ b/fs/orangefs/waitqueue.c
@@ -0,0 +1,357 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ * (C) 2011 Omnibond Systems
+ *
+ * Changes by Acxiom Corporation to implement generic service_operation()
+ * function, Copyright Acxiom Corporation, 2005.
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  In-kernel waitqueue operations.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+static int wait_for_matching_downcall(struct orangefs_kernel_op_s *, long, bool);
+static void orangefs_clean_up_interrupted_operation(struct orangefs_kernel_op_s *);
+
+/*
+ * What we do in this function is to walk the list of operations that are
+ * present in the request queue and mark them as purged.
+ * NOTE: This is called from the device close after client-core has
+ * guaranteed that no new operations could appear on the list since the
+ * client-core is anyway going to exit.
+ */
+void purge_waiting_ops(void)
+{
+	struct orangefs_kernel_op_s *op;
+
+	spin_lock(&orangefs_request_list_lock);
+	list_for_each_entry(op, &orangefs_request_list, list) {
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "pvfs2-client-core: purging op tag %llu %s\n",
+			     llu(op->tag),
+			     get_opname_string(op));
+		set_op_state_purged(op);
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: op:%s: op_state:%d: process:%s:\n",
+			     __func__,
+			     get_opname_string(op),
+			     op->op_state,
+			     current->comm);
+	}
+	spin_unlock(&orangefs_request_list_lock);
+}
+
+/*
+ * submits a ORANGEFS operation and waits for it to complete
+ *
+ * Note op->downcall.status will contain the status of the operation (in
+ * errno format), whether provided by pvfs2-client or a result of failure to
+ * service the operation.  If the caller wishes to distinguish, then
+ * op->state can be checked to see if it was serviced or not.
+ *
+ * Returns contents of op->downcall.status for convenience
+ */
+int service_operation(struct orangefs_kernel_op_s *op,
+		      const char *op_name,
+		      int flags)
+{
+	long timeout = MAX_SCHEDULE_TIMEOUT;
+	int ret = 0;
+
+	DEFINE_WAIT(wait_entry);
+
+	op->upcall.tgid = current->tgid;
+	op->upcall.pid = current->pid;
+
+retry_servicing:
+	op->downcall.status = 0;
+	gossip_debug(GOSSIP_WAIT_DEBUG,
+		     "%s: %s op:%p: process:%s: pid:%d:\n",
+		     __func__,
+		     op_name,
+		     op,
+		     current->comm,
+		     current->pid);
+
+	/*
+	 * If ORANGEFS_OP_NO_MUTEX was set in flags, we need to avoid
+	 * acquiring the request_mutex because we're servicing a
+	 * high priority remount operation and the request_mutex is
+	 * already taken.
+	 */
+	if (!(flags & ORANGEFS_OP_NO_MUTEX)) {
+		if (flags & ORANGEFS_OP_INTERRUPTIBLE)
+			ret = mutex_lock_interruptible(&request_mutex);
+		else
+			ret = mutex_lock_killable(&request_mutex);
+		/*
+		 * check to see if we were interrupted while waiting for
+		 * mutex
+		 */
+		if (ret < 0) {
+			op->downcall.status = ret;
+			gossip_debug(GOSSIP_WAIT_DEBUG,
+				     "%s: service_operation interrupted.\n",
+				     __func__);
+			return ret;
+		}
+	}
+
+	/* queue up the operation */
+	spin_lock(&orangefs_request_list_lock);
+	spin_lock(&op->lock);
+	set_op_state_waiting(op);
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "%s: op:%s: op_state:%d: process:%s:\n",
+		     __func__,
+		     get_opname_string(op),
+		     op->op_state,
+		     current->comm);
+	/* add high priority remount op to the front of the line. */
+	if (flags & ORANGEFS_OP_PRIORITY)
+		list_add(&op->list, &orangefs_request_list);
+	else
+		list_add_tail(&op->list, &orangefs_request_list);
+	spin_unlock(&op->lock);
+	wake_up_interruptible(&orangefs_request_list_waitq);
+	if (!__is_daemon_in_service()) {
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "%s:client core is NOT in service.\n",
+			     __func__);
+		timeout = op_timeout_secs * HZ;
+	}
+	spin_unlock(&orangefs_request_list_lock);
+
+	if (!(flags & ORANGEFS_OP_NO_MUTEX))
+		mutex_unlock(&request_mutex);
+
+	ret = wait_for_matching_downcall(op, timeout,
+					 flags & ORANGEFS_OP_INTERRUPTIBLE);
+
+	gossip_debug(GOSSIP_WAIT_DEBUG,
+		     "%s: wait_for_matching_downcall returned %d for %p\n",
+		     __func__,
+		     ret,
+		     op);
+
+	/* got matching downcall; make sure status is in errno format */
+	if (!ret) {
+		spin_unlock(&op->lock);
+		op->downcall.status =
+		    orangefs_normalize_to_errno(op->downcall.status);
+		ret = op->downcall.status;
+		goto out;
+	}
+
+	/* failed to get matching downcall */
+	if (ret == -ETIMEDOUT) {
+		gossip_err("%s: %s -- wait timed out; aborting attempt.\n",
+			   __func__,
+			   op_name);
+	}
+
+	/*
+	 * remove a waiting op from the request list or
+	 * remove an in-progress op from the in-progress list.
+	 */
+	orangefs_clean_up_interrupted_operation(op);
+
+	op->downcall.status = ret;
+	/* retry if operation has not been serviced and if requested */
+	if (ret == -EAGAIN) {
+		op->attempts++;
+		timeout = op_timeout_secs * HZ;
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "orangefs: tag %llu (%s)"
+			     " -- operation to be retried (%d attempt)\n",
+			     llu(op->tag),
+			     op_name,
+			     op->attempts);
+
+		/*
+		 * io ops (ops that use the shared memory buffer) have
+		 * to be returned to their caller for a retry. Other ops
+		 * can just be recycled here.
+		 */
+		if (!op->uses_shared_memory)
+			goto retry_servicing;
+	}
+
+out:
+	gossip_debug(GOSSIP_WAIT_DEBUG,
+		     "%s: %s returning: %d for %p.\n",
+		     __func__,
+		     op_name,
+		     ret,
+		     op);
+	return ret;
+}
+
+/* This can get called on an I/O op if it had a bad service_operation. */
+bool orangefs_cancel_op_in_progress(struct orangefs_kernel_op_s *op)
+{
+	u64 tag = op->tag;
+	if (!op_state_in_progress(op))
+		return false;
+
+	op->slot_to_free = op->upcall.req.io.buf_index;
+	memset(&op->upcall, 0, sizeof(op->upcall));
+	memset(&op->downcall, 0, sizeof(op->downcall));
+	op->upcall.type = ORANGEFS_VFS_OP_CANCEL;
+	op->upcall.req.cancel.op_tag = tag;
+	op->downcall.type = ORANGEFS_VFS_OP_INVALID;
+	op->downcall.status = -1;
+	orangefs_new_tag(op);
+
+	spin_lock(&orangefs_request_list_lock);
+	/* orangefs_request_list_lock is enough of a barrier here */
+	if (!__is_daemon_in_service()) {
+		spin_unlock(&orangefs_request_list_lock);
+		return false;
+	}
+	spin_lock(&op->lock);
+	set_op_state_waiting(op);
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "%s: op:%s: op_state:%d: process:%s:\n",
+		     __func__,
+		     get_opname_string(op),
+		     op->op_state,
+		     current->comm);
+	list_add(&op->list, &orangefs_request_list);
+	spin_unlock(&op->lock);
+	spin_unlock(&orangefs_request_list_lock);
+
+	gossip_debug(GOSSIP_WAIT_DEBUG,
+		     "Attempting ORANGEFS operation cancellation of tag %llu\n",
+		     llu(tag));
+	return true;
+}
+
+/*
+ * Change an op to the "given up" state and remove it from its list.
+ */
+static void
+	orangefs_clean_up_interrupted_operation(struct orangefs_kernel_op_s *op)
+{
+	/*
+	 * handle interrupted cases depending on what state we were in when
+	 * the interruption is detected.
+	 *
+	 * Called with op->lock held.
+	 */
+
+	/*
+	 * List manipulation code elsewhere will ignore ops that
+	 * have been given up upon.
+	 */
+	op->op_state |= OP_VFS_STATE_GIVEN_UP;
+
+	if (list_empty(&op->list)) {
+		/* caught copying to/from daemon */
+		BUG_ON(op_state_serviced(op));
+		spin_unlock(&op->lock);
+		wait_for_completion(&op->waitq);
+	} else if (op_state_waiting(op)) {
+		/*
+		 * upcall hasn't been read; remove op from upcall request
+		 * list.
+		 */
+		spin_unlock(&op->lock);
+		spin_lock(&orangefs_request_list_lock);
+		list_del_init(&op->list);
+		spin_unlock(&orangefs_request_list_lock);
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "Interrupted: Removed op %p from request_list\n",
+			     op);
+	} else if (op_state_in_progress(op)) {
+		/* op must be removed from the in progress htable */
+		spin_unlock(&op->lock);
+		spin_lock(&htable_ops_in_progress_lock);
+		list_del_init(&op->list);
+		spin_unlock(&htable_ops_in_progress_lock);
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "Interrupted: Removed op %p"
+			     " from htable_ops_in_progress\n",
+			     op);
+	} else {
+		spin_unlock(&op->lock);
+		gossip_err("interrupted operation is in a weird state 0x%x\n",
+			   op->op_state);
+	}
+	reinit_completion(&op->waitq);
+}
+
+/*
+ * Sleeps on waitqueue waiting for matching downcall.
+ * If client-core finishes servicing, then we are good to go.
+ * else if client-core exits, we get woken up here, and retry with a timeout
+ *
+ * When this call returns to the caller, the specified op will no
+ * longer be in either the in_progress hash table or on the request list.
+ *
+ * Returns 0 on success and -errno on failure
+ * Errors are:
+ * EAGAIN in case we want the caller to requeue and try again..
+ * EINTR/EIO/ETIMEDOUT indicating we are done trying to service this
+ * operation since client-core seems to be exiting too often
+ * or if we were interrupted.
+ *
+ * Returns with op->lock taken.
+ */
+static int wait_for_matching_downcall(struct orangefs_kernel_op_s *op,
+				      long timeout,
+				      bool interruptible)
+{
+	long n;
+
+	/*
+	 * There's a "schedule_timeout" inside of these wait
+	 * primitives, during which the op is out of the hands of the
+	 * user process that needs something done and is being
+	 * manipulated by the client-core process.
+	 */
+	if (interruptible)
+		n = wait_for_completion_interruptible_timeout(&op->waitq,
+							      timeout);
+	else
+		n = wait_for_completion_killable_timeout(&op->waitq, timeout);
+
+	spin_lock(&op->lock);
+
+	if (op_state_serviced(op))
+		return 0;
+
+	if (unlikely(n < 0)) {
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "%s: operation interrupted, tag %llu, %p\n",
+			     __func__,
+			     llu(op->tag),
+			     op);
+		return -EINTR;
+	}
+	if (op_state_purged(op)) {
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "%s: operation purged, tag %llu, %p, %d\n",
+			     __func__,
+			     llu(op->tag),
+			     op,
+			     op->attempts);
+		return (op->attempts < ORANGEFS_PURGE_RETRY_COUNT) ?
+			 -EAGAIN :
+			 -EIO;
+	}
+	/* must have timed out, then... */
+	gossip_debug(GOSSIP_WAIT_DEBUG,
+		     "%s: operation timed out, tag %llu, %p, %d)\n",
+		     __func__,
+		     llu(op->tag),
+		     op,
+		     op->attempts);
+	return -ETIMEDOUT;
+}
diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c
new file mode 100644
index 000000000000..ef5da7538cd5
--- /dev/null
+++ b/fs/orangefs/xattr.c
@@ -0,0 +1,545 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Linux VFS extended attribute operations.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+#include <linux/posix_acl_xattr.h>
+#include <linux/xattr.h>
+
+
+#define SYSTEM_ORANGEFS_KEY "system.pvfs2."
+#define SYSTEM_ORANGEFS_KEY_LEN 13
+
+/*
+ * this function returns
+ *   0 if the key corresponding to name is not meant to be printed as part
+ *     of a listxattr.
+ *   1 if the key corresponding to name is meant to be returned as part of
+ *     a listxattr.
+ * The ones that start SYSTEM_ORANGEFS_KEY are the ones to avoid printing.
+ */
+static int is_reserved_key(const char *key, size_t size)
+{
+
+	if (size < SYSTEM_ORANGEFS_KEY_LEN)
+		return 1;
+
+	return strncmp(key, SYSTEM_ORANGEFS_KEY, SYSTEM_ORANGEFS_KEY_LEN) ?  1 : 0;
+}
+
+static inline int convert_to_internal_xattr_flags(int setxattr_flags)
+{
+	int internal_flag = 0;
+
+	if (setxattr_flags & XATTR_REPLACE) {
+		/* Attribute must exist! */
+		internal_flag = ORANGEFS_XATTR_REPLACE;
+	} else if (setxattr_flags & XATTR_CREATE) {
+		/* Attribute must not exist */
+		internal_flag = ORANGEFS_XATTR_CREATE;
+	}
+	return internal_flag;
+}
+
+
+/*
+ * Tries to get a specified key's attributes of a given
+ * file into a user-specified buffer. Note that the getxattr
+ * interface allows for the users to probe the size of an
+ * extended attribute by passing in a value of 0 to size.
+ * Thus our return value is always the size of the attribute
+ * unless the key does not exist for the file and/or if
+ * there were errors in fetching the attribute value.
+ */
+ssize_t orangefs_inode_getxattr(struct inode *inode, const char *prefix,
+		const char *name, void *buffer, size_t size)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op = NULL;
+	ssize_t ret = -ENOMEM;
+	ssize_t length = 0;
+	int fsuid;
+	int fsgid;
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "%s: prefix %s name %s, buffer_size %zd\n",
+		     __func__, prefix, name, size);
+
+	if (name == NULL || (size > 0 && buffer == NULL)) {
+		gossip_err("orangefs_inode_getxattr: bogus NULL pointers\n");
+		return -EINVAL;
+	}
+	if ((strlen(name) + strlen(prefix)) >= ORANGEFS_MAX_XATTR_NAMELEN) {
+		gossip_err("Invalid key length (%d)\n",
+			   (int)(strlen(name) + strlen(prefix)));
+		return -EINVAL;
+	}
+
+	fsuid = from_kuid(current_user_ns(), current_fsuid());
+	fsgid = from_kgid(current_user_ns(), current_fsgid());
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "getxattr on inode %pU, name %s "
+		     "(uid %o, gid %o)\n",
+		     get_khandle_from_ino(inode),
+		     name,
+		     fsuid,
+		     fsgid);
+
+	down_read(&orangefs_inode->xattr_sem);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_GETXATTR);
+	if (!new_op)
+		goto out_unlock;
+
+	new_op->upcall.req.getxattr.refn = orangefs_inode->refn;
+	ret = snprintf((char *)new_op->upcall.req.getxattr.key,
+		       ORANGEFS_MAX_XATTR_NAMELEN, "%s%s", prefix, name);
+
+	/*
+	 * NOTE: Although keys are meant to be NULL terminated textual
+	 * strings, I am going to explicitly pass the length just in case
+	 * we change this later on...
+	 */
+	new_op->upcall.req.getxattr.key_sz = ret + 1;
+
+	ret = service_operation(new_op, "orangefs_inode_getxattr",
+				get_interruptible_flag(inode));
+	if (ret != 0) {
+		if (ret == -ENOENT) {
+			ret = -ENODATA;
+			gossip_debug(GOSSIP_XATTR_DEBUG,
+				     "orangefs_inode_getxattr: inode %pU key %s"
+				     " does not exist!\n",
+				     get_khandle_from_ino(inode),
+				     (char *)new_op->upcall.req.getxattr.key);
+		}
+		goto out_release_op;
+	}
+
+	/*
+	 * Length returned includes null terminator.
+	 */
+	length = new_op->downcall.resp.getxattr.val_sz;
+
+	/*
+	 * Just return the length of the queried attribute.
+	 */
+	if (size == 0) {
+		ret = length;
+		goto out_release_op;
+	}
+
+	/*
+	 * Check to see if key length is > provided buffer size.
+	 */
+	if (length > size) {
+		ret = -ERANGE;
+		goto out_release_op;
+	}
+
+	memset(buffer, 0, size);
+	memcpy(buffer, new_op->downcall.resp.getxattr.val, length);
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+	     "orangefs_inode_getxattr: inode %pU "
+	     "key %s key_sz %d, val_len %d\n",
+	     get_khandle_from_ino(inode),
+	     (char *)new_op->
+		upcall.req.getxattr.key,
+		     (int)new_op->
+		upcall.req.getxattr.key_sz,
+	     (int)ret);
+
+	ret = length;
+
+out_release_op:
+	op_release(new_op);
+out_unlock:
+	up_read(&orangefs_inode->xattr_sem);
+	return ret;
+}
+
+static int orangefs_inode_removexattr(struct inode *inode,
+			    const char *prefix,
+			    const char *name,
+			    int flags)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op = NULL;
+	int ret = -ENOMEM;
+
+	down_write(&orangefs_inode->xattr_sem);
+	new_op = op_alloc(ORANGEFS_VFS_OP_REMOVEXATTR);
+	if (!new_op)
+		goto out_unlock;
+
+	new_op->upcall.req.removexattr.refn = orangefs_inode->refn;
+	/*
+	 * NOTE: Although keys are meant to be NULL terminated
+	 * textual strings, I am going to explicitly pass the
+	 * length just in case we change this later on...
+	 */
+	ret = snprintf((char *)new_op->upcall.req.removexattr.key,
+		       ORANGEFS_MAX_XATTR_NAMELEN,
+		       "%s%s",
+		       (prefix ? prefix : ""),
+		       name);
+	new_op->upcall.req.removexattr.key_sz = ret + 1;
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "orangefs_inode_removexattr: key %s, key_sz %d\n",
+		     (char *)new_op->upcall.req.removexattr.key,
+		     (int)new_op->upcall.req.removexattr.key_sz);
+
+	ret = service_operation(new_op,
+				"orangefs_inode_removexattr",
+				get_interruptible_flag(inode));
+	if (ret == -ENOENT) {
+		/*
+		 * Request to replace a non-existent attribute is an error.
+		 */
+		if (flags & XATTR_REPLACE)
+			ret = -ENODATA;
+		else
+			ret = 0;
+	}
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "orangefs_inode_removexattr: returning %d\n", ret);
+
+	op_release(new_op);
+out_unlock:
+	up_write(&orangefs_inode->xattr_sem);
+	return ret;
+}
+
+/*
+ * Tries to set an attribute for a given key on a file.
+ *
+ * Returns a -ve number on error and 0 on success.  Key is text, but value
+ * can be binary!
+ */
+int orangefs_inode_setxattr(struct inode *inode, const char *prefix,
+		const char *name, const void *value, size_t size, int flags)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	int internal_flag = 0;
+	int ret = -ENOMEM;
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "%s: prefix %s, name %s, buffer_size %zd\n",
+		     __func__, prefix, name, size);
+
+	if (size < 0 ||
+	    size >= ORANGEFS_MAX_XATTR_VALUELEN ||
+	    flags < 0) {
+		gossip_err("orangefs_inode_setxattr: bogus values of size(%d), flags(%d)\n",
+			   (int)size,
+			   flags);
+		return -EINVAL;
+	}
+
+	if (name == NULL ||
+	    (size > 0 && value == NULL)) {
+		gossip_err("orangefs_inode_setxattr: bogus NULL pointers!\n");
+		return -EINVAL;
+	}
+
+	internal_flag = convert_to_internal_xattr_flags(flags);
+
+	if (prefix) {
+		if (strlen(name) + strlen(prefix) >= ORANGEFS_MAX_XATTR_NAMELEN) {
+			gossip_err
+			    ("orangefs_inode_setxattr: bogus key size (%d)\n",
+			     (int)(strlen(name) + strlen(prefix)));
+			return -EINVAL;
+		}
+	} else {
+		if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) {
+			gossip_err
+			    ("orangefs_inode_setxattr: bogus key size (%d)\n",
+			     (int)(strlen(name)));
+			return -EINVAL;
+		}
+	}
+
+	/* This is equivalent to a removexattr */
+	if (size == 0 && value == NULL) {
+		gossip_debug(GOSSIP_XATTR_DEBUG,
+			     "removing xattr (%s%s)\n",
+			     prefix,
+			     name);
+		return orangefs_inode_removexattr(inode, prefix, name, flags);
+	}
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "setxattr on inode %pU, name %s\n",
+		     get_khandle_from_ino(inode),
+		     name);
+
+	down_write(&orangefs_inode->xattr_sem);
+	new_op = op_alloc(ORANGEFS_VFS_OP_SETXATTR);
+	if (!new_op)
+		goto out_unlock;
+
+
+	new_op->upcall.req.setxattr.refn = orangefs_inode->refn;
+	new_op->upcall.req.setxattr.flags = internal_flag;
+	/*
+	 * NOTE: Although keys are meant to be NULL terminated textual
+	 * strings, I am going to explicitly pass the length just in
+	 * case we change this later on...
+	 */
+	ret = snprintf((char *)new_op->upcall.req.setxattr.keyval.key,
+		       ORANGEFS_MAX_XATTR_NAMELEN,
+		       "%s%s",
+		       prefix, name);
+	new_op->upcall.req.setxattr.keyval.key_sz = ret + 1;
+	memcpy(new_op->upcall.req.setxattr.keyval.val, value, size);
+	new_op->upcall.req.setxattr.keyval.val_sz = size;
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "orangefs_inode_setxattr: key %s, key_sz %d "
+		     " value size %zd\n",
+		     (char *)new_op->upcall.req.setxattr.keyval.key,
+		     (int)new_op->upcall.req.setxattr.keyval.key_sz,
+		     size);
+
+	ret = service_operation(new_op,
+				"orangefs_inode_setxattr",
+				get_interruptible_flag(inode));
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "orangefs_inode_setxattr: returning %d\n",
+		     ret);
+
+	/* when request is serviced properly, free req op struct */
+	op_release(new_op);
+out_unlock:
+	up_write(&orangefs_inode->xattr_sem);
+	return ret;
+}
+
+/*
+ * Tries to get a specified object's keys into a user-specified buffer of a
+ * given size.  Note that like the previous instances of xattr routines, this
+ * also allows you to pass in a NULL pointer and 0 size to probe the size for
+ * subsequent memory allocations. Thus our return value is always the size of
+ * all the keys unless there were errors in fetching the keys!
+ */
+ssize_t orangefs_listxattr(struct dentry *dentry, char *buffer, size_t size)
+{
+	struct inode *inode = dentry->d_inode;
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	__u64 token = ORANGEFS_ITERATE_START;
+	ssize_t ret = -ENOMEM;
+	ssize_t total = 0;
+	int count_keys = 0;
+	int key_size;
+	int i = 0;
+	int returned_count = 0;
+
+	if (size > 0 && buffer == NULL) {
+		gossip_err("%s: bogus NULL pointers\n", __func__);
+		return -EINVAL;
+	}
+	if (size < 0) {
+		gossip_err("Invalid size (%d)\n", (int)size);
+		return -EINVAL;
+	}
+
+	down_read(&orangefs_inode->xattr_sem);
+	new_op = op_alloc(ORANGEFS_VFS_OP_LISTXATTR);
+	if (!new_op)
+		goto out_unlock;
+
+	if (buffer && size > 0)
+		memset(buffer, 0, size);
+
+try_again:
+	key_size = 0;
+	new_op->upcall.req.listxattr.refn = orangefs_inode->refn;
+	new_op->upcall.req.listxattr.token = token;
+	new_op->upcall.req.listxattr.requested_count =
+	    (size == 0) ? 0 : ORANGEFS_MAX_XATTR_LISTLEN;
+	ret = service_operation(new_op, __func__,
+				get_interruptible_flag(inode));
+	if (ret != 0)
+		goto done;
+
+	if (size == 0) {
+		/*
+		 * This is a bit of a big upper limit, but I did not want to
+		 * spend too much time getting this correct, since users end
+		 * up allocating memory rather than us...
+		 */
+		total = new_op->downcall.resp.listxattr.returned_count *
+			ORANGEFS_MAX_XATTR_NAMELEN;
+		goto done;
+	}
+
+	returned_count = new_op->downcall.resp.listxattr.returned_count;
+	if (returned_count < 0 ||
+	    returned_count >= ORANGEFS_MAX_XATTR_LISTLEN) {
+		gossip_err("%s: impossible value for returned_count:%d:\n",
+		__func__,
+		returned_count);
+		ret = -EIO;
+		goto done;
+	}
+
+	/*
+	 * Check to see how much can be fit in the buffer. Fit only whole keys.
+	 */
+	for (i = 0; i < returned_count; i++) {
+		if (new_op->downcall.resp.listxattr.lengths[i] < 0 ||
+		    new_op->downcall.resp.listxattr.lengths[i] >
+		    ORANGEFS_MAX_XATTR_NAMELEN) {
+			gossip_err("%s: impossible value for lengths[%d]\n",
+			    __func__,
+			    new_op->downcall.resp.listxattr.lengths[i]);
+			ret = -EIO;
+			goto done;
+		}
+		if (total + new_op->downcall.resp.listxattr.lengths[i] > size)
+			goto done;
+
+		/*
+		 * Since many dumb programs try to setxattr() on our reserved
+		 * xattrs this is a feeble attempt at defeating those by not
+		 * listing them in the output of listxattr.. sigh
+		 */
+		if (is_reserved_key(new_op->downcall.resp.listxattr.key +
+				    key_size,
+				    new_op->downcall.resp.
+					listxattr.lengths[i])) {
+			gossip_debug(GOSSIP_XATTR_DEBUG, "Copying key %d -> %s\n",
+					i, new_op->downcall.resp.listxattr.key +
+						key_size);
+			memcpy(buffer + total,
+				new_op->downcall.resp.listxattr.key + key_size,
+				new_op->downcall.resp.listxattr.lengths[i]);
+			total += new_op->downcall.resp.listxattr.lengths[i];
+			count_keys++;
+		} else {
+			gossip_debug(GOSSIP_XATTR_DEBUG, "[RESERVED] key %d -> %s\n",
+					i, new_op->downcall.resp.listxattr.key +
+						key_size);
+		}
+		key_size += new_op->downcall.resp.listxattr.lengths[i];
+	}
+
+	/*
+	 * Since the buffer was large enough, we might have to continue
+	 * fetching more keys!
+	 */
+	token = new_op->downcall.resp.listxattr.token;
+	if (token != ORANGEFS_ITERATE_END)
+		goto try_again;
+
+done:
+	gossip_debug(GOSSIP_XATTR_DEBUG, "%s: returning %d"
+		     " [size of buffer %ld] (filled in %d keys)\n",
+		     __func__,
+		     ret ? (int)ret : (int)total,
+		     (long)size,
+		     count_keys);
+	op_release(new_op);
+	if (ret == 0)
+		ret = total;
+out_unlock:
+	up_read(&orangefs_inode->xattr_sem);
+	return ret;
+}
+
+static int orangefs_xattr_set_default(const struct xattr_handler *handler,
+				      struct dentry *dentry,
+				      const char *name,
+				      const void *buffer,
+				      size_t size,
+				      int flags)
+{
+	return orangefs_inode_setxattr(dentry->d_inode,
+				    ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+				    name,
+				    buffer,
+				    size,
+				    flags);
+}
+
+static int orangefs_xattr_get_default(const struct xattr_handler *handler,
+				      struct dentry *dentry,
+				      const char *name,
+				      void *buffer,
+				      size_t size)
+{
+	return orangefs_inode_getxattr(dentry->d_inode,
+				    ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+				    name,
+				    buffer,
+				    size);
+
+}
+
+static int orangefs_xattr_set_trusted(const struct xattr_handler *handler,
+				     struct dentry *dentry,
+				     const char *name,
+				     const void *buffer,
+				     size_t size,
+				     int flags)
+{
+	return orangefs_inode_setxattr(dentry->d_inode,
+				    ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
+				    name,
+				    buffer,
+				    size,
+				    flags);
+}
+
+static int orangefs_xattr_get_trusted(const struct xattr_handler *handler,
+				      struct dentry *dentry,
+				      const char *name,
+				      void *buffer,
+				      size_t size)
+{
+	return orangefs_inode_getxattr(dentry->d_inode,
+				    ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
+				    name,
+				    buffer,
+				    size);
+}
+
+static struct xattr_handler orangefs_xattr_trusted_handler = {
+	.prefix = ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
+	.get = orangefs_xattr_get_trusted,
+	.set = orangefs_xattr_set_trusted,
+};
+
+static struct xattr_handler orangefs_xattr_default_handler = {
+	/*
+	 * NOTE: this is set to be the empty string.
+	 * so that all un-prefixed xattrs keys get caught
+	 * here!
+	 */
+	.prefix = ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+	.get = orangefs_xattr_get_default,
+	.set = orangefs_xattr_set_default,
+};
+
+const struct xattr_handler *orangefs_xattr_handlers[] = {
+	&posix_acl_access_xattr_handler,
+	&posix_acl_default_xattr_handler,
+	&orangefs_xattr_trusted_handler,
+	&orangefs_xattr_default_handler,
+	NULL
+};
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index d894e7cd9a86..cc514da6f3e7 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -7,6 +7,7 @@
  * the Free Software Foundation.
  */
 
+#include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/file.h>
@@ -16,10 +17,41 @@
 #include <linux/uaccess.h>
 #include <linux/sched.h>
 #include <linux/namei.h>
+#include <linux/fdtable.h>
+#include <linux/ratelimit.h>
 #include "overlayfs.h"
 
 #define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
 
+static bool __read_mostly ovl_check_copy_up;
+module_param_named(check_copy_up, ovl_check_copy_up, bool,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(ovl_check_copy_up,
+		 "Warn on copy-up when causing process also has a R/O fd open");
+
+static int ovl_check_fd(const void *data, struct file *f, unsigned int fd)
+{
+	const struct dentry *dentry = data;
+
+	if (f->f_inode == d_inode(dentry))
+		pr_warn_ratelimited("overlayfs: Warning: Copying up %pD, but open R/O on fd %u which will cease to be coherent [pid=%d %s]\n",
+				    f, fd, current->pid, current->comm);
+	return 0;
+}
+
+/*
+ * Check the fds open by this process and warn if something like the following
+ * scenario is about to occur:
+ *
+ *	fd1 = open("foo", O_RDONLY);
+ *	fd2 = open("foo", O_RDWR);
+ */
+static void ovl_do_check_copy_up(struct dentry *dentry)
+{
+	if (ovl_check_copy_up)
+		iterate_fd(current->files, 0, ovl_check_fd, dentry);
+}
+
 int ovl_copy_xattr(struct dentry *old, struct dentry *new)
 {
 	ssize_t list_size, size, value_size = 0;
@@ -235,6 +267,7 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 
 	if (S_ISREG(stat->mode)) {
 		struct path upperpath;
+
 		ovl_path_upper(dentry, &upperpath);
 		BUG_ON(upperpath.dentry != NULL);
 		upperpath.dentry = newdentry;
@@ -309,6 +342,8 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	if (WARN_ON(!workdir))
 		return -EROFS;
 
+	ovl_do_check_copy_up(lowerpath->dentry);
+
 	ovl_path_upper(parent, &parentpath);
 	upperdir = parentpath.dentry;
 
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index ed95272d57a6..b3fc0a35bf62 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -596,21 +596,25 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 {
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
 	struct inode *dir = upperdir->d_inode;
-	struct dentry *upper = ovl_dentry_upper(dentry);
+	struct dentry *upper;
 	int err;
 
 	inode_lock_nested(dir, I_MUTEX_PARENT);
+	upper = lookup_one_len(dentry->d_name.name, upperdir,
+			       dentry->d_name.len);
+	err = PTR_ERR(upper);
+	if (IS_ERR(upper))
+		goto out_unlock;
+
 	err = -ESTALE;
-	if (upper->d_parent == upperdir) {
-		/* Don't let d_delete() think it can reset d_inode */
-		dget(upper);
+	if (upper == ovl_dentry_upper(dentry)) {
 		if (is_dir)
 			err = vfs_rmdir(dir, upper);
 		else
 			err = vfs_unlink(dir, upper, NULL);
-		dput(upper);
 		ovl_dentry_version_inc(dentry->d_parent);
 	}
+	dput(upper);
 
 	/*
 	 * Keeping this dentry hashed would mean having to release
@@ -618,7 +622,9 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	 * sole user of this dentry.  Too tricky...  Just unhash for
 	 * now.
 	 */
-	d_drop(dentry);
+	if (!err)
+		d_drop(dentry);
+out_unlock:
 	inode_unlock(dir);
 
 	return err;
@@ -713,7 +719,6 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	struct dentry *trap;
 	bool old_opaque;
 	bool new_opaque;
-	bool new_create = false;
 	bool cleanup_whiteout = false;
 	bool overwrite = !(flags & RENAME_EXCHANGE);
 	bool is_dir = d_is_dir(old);
@@ -839,29 +844,38 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 
 	trap = lock_rename(new_upperdir, old_upperdir);
 
-	olddentry = ovl_dentry_upper(old);
-	newdentry = ovl_dentry_upper(new);
-	if (newdentry) {
+
+	olddentry = lookup_one_len(old->d_name.name, old_upperdir,
+				   old->d_name.len);
+	err = PTR_ERR(olddentry);
+	if (IS_ERR(olddentry))
+		goto out_unlock;
+
+	err = -ESTALE;
+	if (olddentry != ovl_dentry_upper(old))
+		goto out_dput_old;
+
+	newdentry = lookup_one_len(new->d_name.name, new_upperdir,
+				   new->d_name.len);
+	err = PTR_ERR(newdentry);
+	if (IS_ERR(newdentry))
+		goto out_dput_old;
+
+	err = -ESTALE;
+	if (ovl_dentry_upper(new)) {
 		if (opaquedir) {
-			newdentry = opaquedir;
-			opaquedir = NULL;
+			if (newdentry != opaquedir)
+				goto out_dput;
 		} else {
-			dget(newdentry);
+			if (newdentry != ovl_dentry_upper(new))
+				goto out_dput;
 		}
 	} else {
-		new_create = true;
-		newdentry = lookup_one_len(new->d_name.name, new_upperdir,
-					   new->d_name.len);
-		err = PTR_ERR(newdentry);
-		if (IS_ERR(newdentry))
-			goto out_unlock;
+		if (!d_is_negative(newdentry) &&
+		    (!new_opaque || !ovl_is_whiteout(newdentry)))
+			goto out_dput;
 	}
 
-	err = -ESTALE;
-	if (olddentry->d_parent != old_upperdir)
-		goto out_dput;
-	if (newdentry->d_parent != new_upperdir)
-		goto out_dput;
 	if (olddentry == trap)
 		goto out_dput;
 	if (newdentry == trap)
@@ -903,6 +917,13 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	if (!overwrite && new_is_dir && !old_opaque && new_opaque)
 		ovl_remove_opaque(newdentry);
 
+	/*
+	 * Old dentry now lives in different location. Dentries in
+	 * lowerstack are stale. We cannot drop them here because
+	 * access to them is lockless. This could be only pure upper
+	 * or opaque directory - numlower is zero. Or upper non-dir
+	 * entry - its pureness is tracked by flag opaque.
+	 */
 	if (old_opaque != new_opaque) {
 		ovl_dentry_set_opaque(old, new_opaque);
 		if (!overwrite)
@@ -917,6 +938,8 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 
 out_dput:
 	dput(newdentry);
+out_dput_old:
+	dput(olddentry);
 out_unlock:
 	unlock_rename(new_upperdir, old_upperdir);
 out_revert_creds:
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 49e204560655..a4ff5d0d7db9 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -65,6 +65,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 
 		inode_lock(upperdentry->d_inode);
 		err = notify_change(upperdentry, attr, NULL);
+		if (!err)
+			ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
 		inode_unlock(upperdentry->d_inode);
 	}
 	ovl_drop_write(dentry);
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 99b4168c36ff..6a7090f4a441 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -166,6 +166,7 @@ extern const struct file_operations ovl_dir_operations;
 int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list);
 void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list);
 void ovl_cache_free(struct list_head *list);
+int ovl_check_d_type_supported(struct path *realpath);
 
 /* inode.c */
 int ovl_setattr(struct dentry *dentry, struct iattr *attr);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index fdaf28f75e12..6ec1e43a9a54 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -36,13 +36,14 @@ struct ovl_dir_cache {
 
 struct ovl_readdir_data {
 	struct dir_context ctx;
-	bool is_merge;
+	bool is_lowest;
 	struct rb_root root;
 	struct list_head *list;
 	struct list_head middle;
 	struct ovl_cache_entry *first_maybe_whiteout;
 	int count;
 	int err;
+	bool d_type_supported;
 };
 
 struct ovl_dir_file {
@@ -139,9 +140,9 @@ static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd,
 	return 0;
 }
 
-static int ovl_fill_lower(struct ovl_readdir_data *rdd,
-			  const char *name, int namelen,
-			  loff_t offset, u64 ino, unsigned int d_type)
+static int ovl_fill_lowest(struct ovl_readdir_data *rdd,
+			   const char *name, int namelen,
+			   loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct ovl_cache_entry *p;
 
@@ -193,10 +194,10 @@ static int ovl_fill_merge(struct dir_context *ctx, const char *name,
 		container_of(ctx, struct ovl_readdir_data, ctx);
 
 	rdd->count++;
-	if (!rdd->is_merge)
+	if (!rdd->is_lowest)
 		return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type);
 	else
-		return ovl_fill_lower(rdd, name, namelen, offset, ino, d_type);
+		return ovl_fill_lowest(rdd, name, namelen, offset, ino, d_type);
 }
 
 static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
@@ -289,7 +290,7 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
 		.ctx.actor = ovl_fill_merge,
 		.list = list,
 		.root = RB_ROOT,
-		.is_merge = false,
+		.is_lowest = false,
 	};
 	int idx, next;
 
@@ -306,7 +307,7 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
 			 * allows offsets to be reasonably constant
 			 */
 			list_add(&rdd.middle, rdd.list);
-			rdd.is_merge = true;
+			rdd.is_lowest = true;
 			err = ovl_dir_read(&realpath, &rdd);
 			list_del(&rdd.middle);
 		}
@@ -577,3 +578,39 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
 	}
 	inode_unlock(upper->d_inode);
 }
+
+static int ovl_check_d_type(struct dir_context *ctx, const char *name,
+			  int namelen, loff_t offset, u64 ino,
+			  unsigned int d_type)
+{
+	struct ovl_readdir_data *rdd =
+		container_of(ctx, struct ovl_readdir_data, ctx);
+
+	/* Even if d_type is not supported, DT_DIR is returned for . and .. */
+	if (!strncmp(name, ".", namelen) || !strncmp(name, "..", namelen))
+		return 0;
+
+	if (d_type != DT_UNKNOWN)
+		rdd->d_type_supported = true;
+
+	return 0;
+}
+
+/*
+ * Returns 1 if d_type is supported, 0 not supported/unknown. Negative values
+ * if error is encountered.
+ */
+int ovl_check_d_type_supported(struct path *realpath)
+{
+	int err;
+	struct ovl_readdir_data rdd = {
+		.ctx.actor = ovl_check_d_type,
+		.d_type_supported = false,
+	};
+
+	err = ovl_dir_read(realpath, &rdd);
+	if (err)
+		return err;
+
+	return rdd.d_type_supported;
+}
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 8d826bd56b26..ef64984c9bbc 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -76,12 +76,14 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry)
 	if (oe->__upperdentry) {
 		type = __OVL_PATH_UPPER;
 
-		if (oe->numlower) {
-			if (S_ISDIR(dentry->d_inode->i_mode))
-				type |= __OVL_PATH_MERGE;
-		} else if (!oe->opaque) {
+		/*
+		 * Non-dir dentry can hold lower dentry from previous
+		 * location. Its purity depends only on opaque flag.
+		 */
+		if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode))
+			type |= __OVL_PATH_MERGE;
+		else if (!oe->opaque)
 			type |= __OVL_PATH_PURE;
-		}
 	} else {
 		if (oe->numlower > 1)
 			type |= __OVL_PATH_MERGE;
@@ -341,6 +343,7 @@ static const struct dentry_operations ovl_dentry_operations = {
 
 static const struct dentry_operations ovl_reval_dentry_operations = {
 	.d_release = ovl_dentry_release,
+	.d_select_inode = ovl_d_select_inode,
 	.d_revalidate = ovl_dentry_revalidate,
 	.d_weak_revalidate = ovl_dentry_weak_revalidate,
 };
@@ -933,7 +936,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 
 	err = -EINVAL;
 	if (!ufs->config.lowerdir) {
-		pr_err("overlayfs: missing 'lowerdir'\n");
+		if (!silent)
+			pr_err("overlayfs: missing 'lowerdir'\n");
 		goto out_free_config;
 	}
 
@@ -1025,6 +1029,21 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			sb->s_flags |= MS_RDONLY;
 			ufs->workdir = NULL;
 		}
+
+		/*
+		 * Upper should support d_type, else whiteouts are visible.
+		 * Given workdir and upper are on same fs, we can do
+		 * iterate_dir() on workdir.
+		 */
+		err = ovl_check_d_type_supported(&workpath);
+		if (err < 0)
+			goto out_put_workdir;
+
+		if (!err) {
+			pr_err("overlayfs: upper fs needs to support d_type.\n");
+			err = -EINVAL;
+			goto out_put_workdir;
+		}
 	}
 
 	err = -ENOMEM;
diff --git a/fs/pnode.c b/fs/pnode.c
index 6367e1e435c6..c524fdddc7fb 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -202,6 +202,11 @@ static struct mount *last_dest, *last_source, *dest_master;
 static struct mountpoint *mp;
 static struct hlist_head *list;
 
+static inline bool peers(struct mount *m1, struct mount *m2)
+{
+	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
+}
+
 static int propagate_one(struct mount *m)
 {
 	struct mount *child;
@@ -212,7 +217,7 @@ static int propagate_one(struct mount *m)
 	/* skip if mountpoint isn't covered by it */
 	if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
 		return 0;
-	if (m->mnt_group_id == last_dest->mnt_group_id) {
+	if (peers(m, last_dest)) {
 		type = CL_MAKE_SHARED;
 	} else {
 		struct mount *n, *p;
@@ -223,7 +228,7 @@ static int propagate_one(struct mount *m)
 					last_source = last_source->mnt_master;
 					last_dest = last_source->mnt_parent;
 				}
-				if (n->mnt_group_id != last_dest->mnt_group_id) {
+				if (!peers(n, last_dest)) {
 					last_source = last_source->mnt_master;
 					last_dest = last_source->mnt_parent;
 				}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4f764c2ac1a5..b1755b23893e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -434,7 +434,7 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
 			&& !lookup_symbol_name(wchan, symname))
 		seq_printf(m, "%s", symname);
 	else
-		seq_putc(m, '0');
+		seq_puts(m, "0\n");
 
 	return 0;
 }
@@ -2158,6 +2158,7 @@ static const struct file_operations proc_map_files_operations = {
 	.llseek		= default_llseek,
 };
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
 struct timers_private {
 	struct pid *pid;
 	struct task_struct *task;
@@ -2256,6 +2257,73 @@ static const struct file_operations proc_timers_operations = {
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
 };
+#endif
+
+static ssize_t timerslack_ns_write(struct file *file, const char __user *buf,
+					size_t count, loff_t *offset)
+{
+	struct inode *inode = file_inode(file);
+	struct task_struct *p;
+	u64 slack_ns;
+	int err;
+
+	err = kstrtoull_from_user(buf, count, 10, &slack_ns);
+	if (err < 0)
+		return err;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) {
+		task_lock(p);
+		if (slack_ns == 0)
+			p->timer_slack_ns = p->default_timer_slack_ns;
+		else
+			p->timer_slack_ns = slack_ns;
+		task_unlock(p);
+	} else
+		count = -EPERM;
+
+	put_task_struct(p);
+
+	return count;
+}
+
+static int timerslack_ns_show(struct seq_file *m, void *v)
+{
+	struct inode *inode = m->private;
+	struct task_struct *p;
+	int err =  0;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) {
+		task_lock(p);
+		seq_printf(m, "%llu\n", p->timer_slack_ns);
+		task_unlock(p);
+	} else
+		err = -EPERM;
+
+	put_task_struct(p);
+
+	return err;
+}
+
+static int timerslack_ns_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, timerslack_ns_show, inode);
+}
+
+static const struct file_operations proc_pid_set_timerslack_ns_operations = {
+	.open		= timerslack_ns_open,
+	.read		= seq_read,
+	.write		= timerslack_ns_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
 
 static int proc_pident_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
@@ -2831,6 +2899,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	REG("timers",	  S_IRUGO, proc_timers_operations),
 #endif
+	REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations),
 };
 
 static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index df4661abadc4..83720460c5bc 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -29,10 +29,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	unsigned long committed;
 	long cached;
 	long available;
-	unsigned long pagecache;
-	unsigned long wmark_low = 0;
 	unsigned long pages[NR_LRU_LISTS];
-	struct zone *zone;
 	int lru;
 
 /*
@@ -51,33 +48,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
 		pages[lru] = global_page_state(NR_LRU_BASE + lru);
 
-	for_each_zone(zone)
-		wmark_low += zone->watermark[WMARK_LOW];
-
-	/*
-	 * Estimate the amount of memory available for userspace allocations,
-	 * without causing swapping.
-	 */
-	available = i.freeram - totalreserve_pages;
-
-	/*
-	 * Not all the page cache can be freed, otherwise the system will
-	 * start swapping. Assume at least half of the page cache, or the
-	 * low watermark worth of cache, needs to stay.
-	 */
-	pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
-	pagecache -= min(pagecache / 2, wmark_low);
-	available += pagecache;
-
-	/*
-	 * Part of the reclaimable slab consists of items that are in use,
-	 * and cannot be freed. Cap this estimate at the low watermark.
-	 */
-	available += global_page_state(NR_SLAB_RECLAIMABLE) -
-		     min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
-
-	if (available < 0)
-		available = 0;
+	available = si_mem_available();
 
 	/*
 	 * Tagged format, for easy grepping and expansion.
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 276f12431dbf..72cb26f85d58 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -28,6 +28,9 @@ static const struct proc_ns_operations *ns_entries[] = {
 	&userns_operations,
 #endif
 	&mntns_operations,
+#ifdef CONFIG_CGROUPS
+	&cgroupns_operations,
+#endif
 };
 
 static const char *proc_ns_get_link(struct dentry *dentry,
diff --git a/fs/proc/page.c b/fs/proc/page.c
index b2855eea5405..712f1b9992cc 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -103,9 +103,9 @@ u64 stable_page_flags(struct page *page)
 	 * pseudo flags for the well known (anonymous) memory mapped pages
 	 *
 	 * Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the
-	 * simple test in page_mapcount() is not enough.
+	 * simple test in page_mapped() is not enough.
 	 */
-	if (!PageSlab(page) && page_mapcount(page))
+	if (!PageSlab(page) && page_mapped(page))
 		u |= 1 << KPF_MMAP;
 	if (PageAnon(page))
 		u |= 1 << KPF_ANON;
@@ -148,6 +148,8 @@ u64 stable_page_flags(struct page *page)
 	 */
 	if (PageBuddy(page))
 		u |= 1 << KPF_BUDDY;
+	else if (page_count(page) == 0 && is_free_buddy_page(page))
+		u |= 1 << KPF_BUDDY;
 
 	if (PageBalloon(page))
 		u |= 1 << KPF_BALLOON;
@@ -158,6 +160,8 @@ u64 stable_page_flags(struct page *page)
 	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
 
 	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
+	if (PageTail(page) && PageSlab(compound_head(page)))
+		u |= 1 << KPF_SLAB;
 
 	u |= kpf_copy_bit(k, KPF_ERROR,		PG_error);
 	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 85d16c67c33e..9df431642042 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -259,23 +259,29 @@ static int do_maps_open(struct inode *inode, struct file *file,
 				sizeof(struct proc_maps_private));
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+/*
+ * Indicate if the VMA is a stack for the given task; for
+ * /proc/PID/maps that is the stack of the main task.
+ */
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
-	struct inode *inode = priv->inode;
-	struct task_struct *task;
-	pid_t ret = 0;
+	int stack = 0;
 
-	rcu_read_lock();
-	task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
+	if (is_pid) {
+		stack = vma->vm_start <= vma->vm_mm->start_stack &&
+			vma->vm_end >= vma->vm_mm->start_stack;
+	} else {
+		struct inode *inode = priv->inode;
+		struct task_struct *task;
+
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_PID);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+			stack = vma_is_stack_for_task(vma, task);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
-
-	return ret;
+	return stack;
 }
 
 static void
@@ -335,8 +341,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 	name = arch_vma_name(vma);
 	if (!name) {
-		pid_t tid;
-
 		if (!mm) {
 			name = "[vdso]";
 			goto done;
@@ -348,21 +352,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			goto done;
 		}
 
-		tid = pid_of_stack(priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack)) {
-				name = "[stack]";
-			} else {
-				/* Thread stack in /proc/PID/maps */
-				seq_pad(m, ' ');
-				seq_printf(m, "[stack:%d]", tid);
-			}
-		}
+		if (is_stack(priv, vma, is_pid))
+			name = "[stack]";
 	}
 
 done:
@@ -669,11 +660,20 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_MERGEABLE)]	= "mg",
 		[ilog2(VM_UFFD_MISSING)]= "um",
 		[ilog2(VM_UFFD_WP)]	= "uw",
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+		/* These come out via ProtectionKey: */
+		[ilog2(VM_PKEY_BIT0)]	= "",
+		[ilog2(VM_PKEY_BIT1)]	= "",
+		[ilog2(VM_PKEY_BIT2)]	= "",
+		[ilog2(VM_PKEY_BIT3)]	= "",
+#endif
 	};
 	size_t i;
 
 	seq_puts(m, "VmFlags: ");
 	for (i = 0; i < BITS_PER_LONG; i++) {
+		if (!mnemonics[i][0])
+			continue;
 		if (vma->vm_flags & (1UL << i)) {
 			seq_printf(m, "%c%c ",
 				   mnemonics[i][0], mnemonics[i][1]);
@@ -711,6 +711,10 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 }
 #endif /* HUGETLB_PAGE */
 
+void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma)
+{
+}
+
 static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
 	struct vm_area_struct *vma = v;
@@ -792,6 +796,7 @@ 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);
 
+	arch_show_smap(m, vma);
 	show_smap_vma_flags(m, vma);
 	m_cache_vma(m, vma);
 	return 0;
@@ -1552,18 +1557,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
 		unsigned long addr, unsigned long end, struct mm_walk *walk)
 {
+	pte_t huge_pte = huge_ptep_get(pte);
 	struct numa_maps *md;
 	struct page *page;
 
-	if (!pte_present(*pte))
+	if (!pte_present(huge_pte))
 		return 0;
 
-	page = pte_page(*pte);
+	page = pte_page(huge_pte);
 	if (!page)
 		return 0;
 
 	md = walk->private;
-	gather_stats(page, md, pte_dirty(*pte), 1);
+	gather_stats(page, md, pte_dirty(huge_pte), 1);
 	return 0;
 }
 
@@ -1617,19 +1623,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 		seq_file_path(m, file, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
-	} else {
-		pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
-				seq_puts(m, " stack");
-			else
-				seq_printf(m, " stack:%d", tid);
-		}
+	} else if (is_stack(proc_priv, vma, is_pid)) {
+		seq_puts(m, " stack");
 	}
 
 	if (is_vm_hugetlb_page(vma))
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index e0d64c92e4f6..faacb0c0d857 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -123,23 +123,26 @@ unsigned long task_statm(struct mm_struct *mm,
 	return size;
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
-	struct inode *inode = priv->inode;
-	struct task_struct *task;
-	pid_t ret = 0;
-
-	rcu_read_lock();
-	task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
+	struct mm_struct *mm = vma->vm_mm;
+	int stack = 0;
+
+	if (is_pid) {
+		stack = vma->vm_start <= mm->start_stack &&
+			vma->vm_end >= mm->start_stack;
+	} else {
+		struct inode *inode = priv->inode;
+		struct task_struct *task;
+
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_PID);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+			stack = vma_is_stack_for_task(vma, task);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
-
-	return ret;
+	return stack;
 }
 
 /*
@@ -181,21 +184,9 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
 	if (file) {
 		seq_pad(m, ' ');
 		seq_file_path(m, file, "");
-	} else if (mm) {
-		pid_t tid = pid_of_stack(priv, vma, is_pid);
-
-		if (tid != 0) {
-			seq_pad(m, ' ');
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
-				seq_printf(m, "[stack]");
-			else
-				seq_printf(m, "[stack:%d]", tid);
-		}
+	} else if (mm && is_stack(priv, vma, is_pid)) {
+		seq_pad(m, ' ');
+		seq_printf(m, "[stack]");
 	}
 
 	seq_putc(m, '\n');
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 4e61388ec03d..55bb57e6a30d 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -231,7 +231,9 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
 
 	list_for_each_entry(m, &vmcore_list, list) {
 		if (*fpos < m->offset + m->size) {
-			tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
+			tsz = (size_t)min_t(unsigned long long,
+					    m->offset + m->size - *fpos,
+					    buflen);
 			start = m->paddr + *fpos - m->offset;
 			tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
 			if (tmp < 0)
@@ -461,7 +463,8 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 		if (start < m->offset + m->size) {
 			u64 paddr = 0;
 
-			tsz = min_t(size_t, m->offset + m->size - start, size);
+			tsz = (size_t)min_t(unsigned long long,
+					    m->offset + m->size - start, size);
 			paddr = m->paddr + start - m->offset;
 			if (vmcore_remap_oldmem_pfn(vma, vma->vm_start + len,
 						    paddr >> PAGE_SHIFT, tsz,
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 2256e7e23e67..3f1190d18991 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -199,6 +199,8 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
 	if (sb->s_op->show_devname) {
 		seq_puts(m, "device ");
 		err = sb->s_op->show_devname(m, mnt_path.dentry);
+		if (err)
+			goto out;
 	} else {
 		if (r->mnt_devname) {
 			seq_puts(m, "device ");
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 319c3a60cfa5..bd9812e83461 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -55,8 +55,8 @@ 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);
+static unsigned long long mem_address;
+module_param(mem_address, ullong, 0400);
 MODULE_PARM_DESC(mem_address,
 		"start of reserved RAM used to store oops/panic logs");
 
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 3c3b81bb6dfe..ba827daea5a0 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -411,6 +411,8 @@ int dquot_acquire(struct dquot *dquot)
 		ret = dqopt->ops[dquot->dq_id.type]->read_dqblk(dquot);
 	if (ret < 0)
 		goto out_iolock;
+	/* Make sure flags update is visible after dquot has been filled */
+	smp_mb__before_atomic();
 	set_bit(DQ_READ_B, &dquot->dq_flags);
 	/* Instantiate dquot if needed */
 	if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && !dquot->dq_off) {
@@ -427,6 +429,11 @@ int dquot_acquire(struct dquot *dquot)
 			goto out_iolock;
 		}
 	}
+	/*
+	 * Make sure flags update is visible after on-disk struct has been
+	 * allocated. Paired with smp_rmb() in dqget().
+	 */
+	smp_mb__before_atomic();
 	set_bit(DQ_ACTIVE_B, &dquot->dq_flags);
 out_iolock:
 	mutex_unlock(&dqopt->dqio_mutex);
@@ -887,6 +894,11 @@ we_slept:
 			goto out;
 		}
 	}
+	/*
+	 * Make sure following reads see filled structure - paired with
+	 * smp_mb__before_atomic() in dquot_acquire().
+	 */
+	smp_rmb();
 #ifdef CONFIG_QUOTA_DEBUG
 	BUG_ON(!dquot->dq_sb);	/* Has somebody invalidated entry under us? */
 #endif
@@ -1398,7 +1410,7 @@ static int dquot_active(const struct inode *inode)
 static int __dquot_initialize(struct inode *inode, int type)
 {
 	int cnt, init_needed = 0;
-	struct dquot **dquots, *got[MAXQUOTAS];
+	struct dquot **dquots, *got[MAXQUOTAS] = {};
 	struct super_block *sb = inode->i_sb;
 	qsize_t rsv;
 	int ret = 0;
@@ -1415,7 +1427,6 @@ static int __dquot_initialize(struct inode *inode, int type)
 		int rc;
 		struct dquot *dquot;
 
-		got[cnt] = NULL;
 		if (type != -1 && cnt != type)
 			continue;
 		/*
@@ -2031,6 +2042,21 @@ int dquot_commit_info(struct super_block *sb, int type)
 }
 EXPORT_SYMBOL(dquot_commit_info);
 
+int dquot_get_next_id(struct super_block *sb, struct kqid *qid)
+{
+	struct quota_info *dqopt = sb_dqopt(sb);
+	int err;
+
+	if (!dqopt->ops[qid->type]->get_next_id)
+		return -ENOSYS;
+	mutex_lock(&dqopt->dqio_mutex);
+	err = dqopt->ops[qid->type]->get_next_id(sb, qid);
+	mutex_unlock(&dqopt->dqio_mutex);
+
+	return err;
+}
+EXPORT_SYMBOL(dquot_get_next_id);
+
 /*
  * Definitions of diskquota operations.
  */
@@ -2042,6 +2068,7 @@ const struct dquot_operations dquot_operations = {
 	.write_info	= dquot_commit_info,
 	.alloc_dquot	= dquot_alloc,
 	.destroy_dquot	= dquot_destroy,
+	.get_next_id	= dquot_get_next_id,
 };
 EXPORT_SYMBOL(dquot_operations);
 
@@ -2430,9 +2457,7 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name,
 	struct dentry *dentry;
 	int error;
 
-	inode_lock(d_inode(sb->s_root));
-	dentry = lookup_one_len(qf_name, sb->s_root, strlen(qf_name));
-	inode_unlock(d_inode(sb->s_root));
+	dentry = lookup_one_len_unlocked(qf_name, sb->s_root, strlen(qf_name));
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
@@ -2565,6 +2590,27 @@ int dquot_get_dqblk(struct super_block *sb, struct kqid qid,
 }
 EXPORT_SYMBOL(dquot_get_dqblk);
 
+int dquot_get_next_dqblk(struct super_block *sb, struct kqid *qid,
+			 struct qc_dqblk *di)
+{
+	struct dquot *dquot;
+	int err;
+
+	if (!sb->dq_op->get_next_id)
+		return -ENOSYS;
+	err = sb->dq_op->get_next_id(sb, qid);
+	if (err < 0)
+		return err;
+	dquot = dqget(sb, *qid);
+	if (IS_ERR(dquot))
+		return PTR_ERR(dquot);
+	do_get_dqblk(dquot, di);
+	dqput(dquot);
+
+	return 0;
+}
+EXPORT_SYMBOL(dquot_get_next_dqblk);
+
 #define VFS_QC_MASK \
 	(QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \
 	 QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \
@@ -2765,6 +2811,7 @@ const struct quotactl_ops dquot_quotactl_ops = {
 	.get_state	= dquot_get_state,
 	.set_info	= dquot_set_dqinfo,
 	.get_dqblk	= dquot_get_dqblk,
+	.get_nextdqblk	= dquot_get_next_dqblk,
 	.set_dqblk	= dquot_set_dqblk
 };
 EXPORT_SYMBOL(dquot_quotactl_ops);
@@ -2776,6 +2823,7 @@ const struct quotactl_ops dquot_quotactl_sysfile_ops = {
 	.get_state	= dquot_get_state,
 	.set_info	= dquot_set_dqinfo,
 	.get_dqblk	= dquot_get_dqblk,
+	.get_nextdqblk	= dquot_get_next_dqblk,
 	.set_dqblk	= dquot_set_dqblk
 };
 EXPORT_SYMBOL(dquot_quotactl_sysfile_ops);
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 3746367098fd..0f10ee9892ce 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -79,7 +79,7 @@ unsigned int qtype_enforce_flag(int type)
 	return 0;
 }
 
-static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id,
+static int quota_quotaon(struct super_block *sb, int type, qid_t id,
 		         struct path *path)
 {
 	if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable)
@@ -222,6 +222,34 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id,
 	return 0;
 }
 
+/*
+ * Return quota for next active quota >= this id, if any exists,
+ * otherwise return -ENOENT via ->get_nextdqblk
+ */
+static int quota_getnextquota(struct super_block *sb, int type, qid_t id,
+			  void __user *addr)
+{
+	struct kqid qid;
+	struct qc_dqblk fdq;
+	struct if_nextdqblk idq;
+	int ret;
+
+	if (!sb->s_qcop->get_nextdqblk)
+		return -ENOSYS;
+	qid = make_kqid(current_user_ns(), type, id);
+	if (!qid_valid(qid))
+		return -EINVAL;
+	ret = sb->s_qcop->get_nextdqblk(sb, &qid, &fdq);
+	if (ret)
+		return ret;
+	/* struct if_nextdqblk is a superset of struct if_dqblk */
+	copy_to_if_dqblk((struct if_dqblk *)&idq, &fdq);
+	idq.dqb_id = from_kqid(current_user_ns(), qid);
+	if (copy_to_user(addr, &idq, sizeof(idq)))
+		return -EFAULT;
+	return 0;
+}
+
 static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src)
 {
 	dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit);
@@ -625,6 +653,34 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id,
 	return ret;
 }
 
+/*
+ * Return quota for next active quota >= this id, if any exists,
+ * otherwise return -ENOENT via ->get_nextdqblk.
+ */
+static int quota_getnextxquota(struct super_block *sb, int type, qid_t id,
+			    void __user *addr)
+{
+	struct fs_disk_quota fdq;
+	struct qc_dqblk qdq;
+	struct kqid qid;
+	qid_t id_out;
+	int ret;
+
+	if (!sb->s_qcop->get_nextdqblk)
+		return -ENOSYS;
+	qid = make_kqid(current_user_ns(), type, id);
+	if (!qid_valid(qid))
+		return -EINVAL;
+	ret = sb->s_qcop->get_nextdqblk(sb, &qid, &qdq);
+	if (ret)
+		return ret;
+	id_out = from_kqid(current_user_ns(), qid);
+	copy_to_xfs_dqblk(&fdq, &qdq, type, id_out);
+	if (copy_to_user(addr, &fdq, sizeof(fdq)))
+		return -EFAULT;
+	return ret;
+}
+
 static int quota_rmxquota(struct super_block *sb, void __user *addr)
 {
 	__u32 flags;
@@ -659,7 +715,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 
 	switch (cmd) {
 	case Q_QUOTAON:
-		return quota_quotaon(sb, type, cmd, id, path);
+		return quota_quotaon(sb, type, id, path);
 	case Q_QUOTAOFF:
 		return quota_quotaoff(sb, type);
 	case Q_GETFMT:
@@ -670,6 +726,8 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 		return quota_setinfo(sb, type, addr);
 	case Q_GETQUOTA:
 		return quota_getquota(sb, type, id, addr);
+	case Q_GETNEXTQUOTA:
+		return quota_getnextquota(sb, type, id, addr);
 	case Q_SETQUOTA:
 		return quota_setquota(sb, type, id, addr);
 	case Q_SYNC:
@@ -690,6 +748,8 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 		return quota_setxquota(sb, type, id, addr);
 	case Q_XGETQUOTA:
 		return quota_getxquota(sb, type, id, addr);
+	case Q_XGETNEXTQUOTA:
+		return quota_getnextxquota(sb, type, id, addr);
 	case Q_XQUOTASYNC:
 		if (sb->s_flags & MS_RDONLY)
 			return -EROFS;
@@ -705,6 +765,11 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 /* Return 1 if 'cmd' will block on frozen filesystem */
 static int quotactl_cmd_write(int cmd)
 {
+	/*
+	 * We cannot allow Q_GETQUOTA and Q_GETNEXTQUOTA without write access
+	 * as dquot_acquire() may allocate space for new structure and OCFS2
+	 * needs to increment on-disk use count.
+	 */
 	switch (cmd) {
 	case Q_GETFMT:
 	case Q_GETINFO:
@@ -712,6 +777,7 @@ static int quotactl_cmd_write(int cmd)
 	case Q_XGETQSTAT:
 	case Q_XGETQSTATV:
 	case Q_XGETQUOTA:
+	case Q_XGETNEXTQUOTA:
 	case Q_XQUOTASYNC:
 		return 0;
 	}
diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c
index 58efb83dec1c..0738972e8d3f 100644
--- a/fs/quota/quota_tree.c
+++ b/fs/quota/quota_tree.c
@@ -22,10 +22,9 @@ MODULE_LICENSE("GPL");
 
 #define __QUOTA_QT_PARANOIA
 
-static int get_index(struct qtree_mem_dqinfo *info, struct kqid qid, int depth)
+static int __get_index(struct qtree_mem_dqinfo *info, qid_t id, int depth)
 {
 	unsigned int epb = info->dqi_usable_bs >> 2;
-	qid_t id = from_kqid(&init_user_ns, qid);
 
 	depth = info->dqi_qtree_depth - depth - 1;
 	while (depth--)
@@ -33,6 +32,13 @@ static int get_index(struct qtree_mem_dqinfo *info, struct kqid qid, int depth)
 	return id % epb;
 }
 
+static int get_index(struct qtree_mem_dqinfo *info, struct kqid qid, int depth)
+{
+	qid_t id = from_kqid(&init_user_ns, qid);
+
+	return __get_index(info, id, depth);
+}
+
 /* Number of entries in one blocks */
 static int qtree_dqstr_in_blk(struct qtree_mem_dqinfo *info)
 {
@@ -668,3 +674,60 @@ int qtree_release_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
 	return 0;
 }
 EXPORT_SYMBOL(qtree_release_dquot);
+
+static int find_next_id(struct qtree_mem_dqinfo *info, qid_t *id,
+			unsigned int blk, int depth)
+{
+	char *buf = getdqbuf(info->dqi_usable_bs);
+	__le32 *ref = (__le32 *)buf;
+	ssize_t ret;
+	unsigned int epb = info->dqi_usable_bs >> 2;
+	unsigned int level_inc = 1;
+	int i;
+
+	if (!buf)
+		return -ENOMEM;
+
+	for (i = depth; i < info->dqi_qtree_depth - 1; i++)
+		level_inc *= epb;
+
+	ret = read_blk(info, blk, buf);
+	if (ret < 0) {
+		quota_error(info->dqi_sb,
+			    "Can't read quota tree block %u", blk);
+		goto out_buf;
+	}
+	for (i = __get_index(info, *id, depth); i < epb; i++) {
+		if (ref[i] == cpu_to_le32(0)) {
+			*id += level_inc;
+			continue;
+		}
+		if (depth == info->dqi_qtree_depth - 1) {
+			ret = 0;
+			goto out_buf;
+		}
+		ret = find_next_id(info, id, le32_to_cpu(ref[i]), depth + 1);
+		if (ret != -ENOENT)
+			break;
+	}
+	if (i == epb) {
+		ret = -ENOENT;
+		goto out_buf;
+	}
+out_buf:
+	kfree(buf);
+	return ret;
+}
+
+int qtree_get_next_id(struct qtree_mem_dqinfo *info, struct kqid *qid)
+{
+	qid_t id = from_kqid(&init_user_ns, *qid);
+	int ret;
+
+	ret = find_next_id(info, &id, QT_TREEOFF, 0);
+	if (ret < 0)
+		return ret;
+	*qid = make_kqid(&init_user_ns, qid->type, id);
+	return 0;
+}
+EXPORT_SYMBOL(qtree_get_next_id);
diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c
index ed85d4f35c04..ca71bf881ad1 100644
--- a/fs/quota/quota_v2.c
+++ b/fs/quota/quota_v2.c
@@ -304,6 +304,11 @@ static int v2_free_file_info(struct super_block *sb, int type)
 	return 0;
 }
 
+static int v2_get_next_id(struct super_block *sb, struct kqid *qid)
+{
+	return qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid);
+}
+
 static const struct quota_format_ops v2_format_ops = {
 	.check_quota_file	= v2_check_quota_file,
 	.read_file_info		= v2_read_file_info,
@@ -312,6 +317,7 @@ static const struct quota_format_ops v2_format_ops = {
 	.read_dqblk		= v2_read_dquot,
 	.commit_dqblk		= v2_write_dquot,
 	.release_dqblk		= v2_release_dquot,
+	.get_next_id		= v2_get_next_id,
 };
 
 static struct quota_format_type v2r0_quota_format = {
diff --git a/fs/read_write.c b/fs/read_write.c
index 324ec271cc4e..cf377cf9dfe3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -17,6 +17,7 @@
 #include <linux/splice.h>
 #include <linux/compat.h>
 #include <linux/mount.h>
+#include <linux/fs.h>
 #include "internal.h"
 
 #include <asm/uaccess.h>
@@ -183,7 +184,7 @@ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence)
 	switch (whence) {
 	case SEEK_SET: case SEEK_CUR:
 		return generic_file_llseek_size(file, offset, whence,
-						~0ULL, 0);
+						OFFSET_MAX, 0);
 	default:
 		return -EINVAL;
 	}
@@ -692,12 +693,17 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
 EXPORT_SYMBOL(iov_shorten);
 
 static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, iter_fn_t fn)
+		loff_t *ppos, iter_fn_t fn, int flags)
 {
 	struct kiocb kiocb;
 	ssize_t ret;
 
+	if (flags & ~RWF_HIPRI)
+		return -EOPNOTSUPP;
+
 	init_sync_kiocb(&kiocb, filp);
+	if (flags & RWF_HIPRI)
+		kiocb.ki_flags |= IOCB_HIPRI;
 	kiocb.ki_pos = *ppos;
 
 	ret = fn(&kiocb, iter);
@@ -708,10 +714,13 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 
 /* Do it by hand, with file-ops */
 static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, io_fn_t fn)
+		loff_t *ppos, io_fn_t fn, int flags)
 {
 	ssize_t ret = 0;
 
+	if (flags & ~RWF_HIPRI)
+		return -EOPNOTSUPP;
+
 	while (iov_iter_count(iter)) {
 		struct iovec iovec = iov_iter_iovec(iter);
 		ssize_t nr;
@@ -812,7 +821,8 @@ out:
 
 static ssize_t do_readv_writev(int type, struct file *file,
 			       const struct iovec __user * uvector,
-			       unsigned long nr_segs, loff_t *pos)
+			       unsigned long nr_segs, loff_t *pos,
+			       int flags)
 {
 	size_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
@@ -844,9 +854,9 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	}
 
 	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
+		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
 	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn);
+		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
 
 	if (type != READ)
 		file_end_write(file);
@@ -863,40 +873,40 @@ out:
 }
 
 ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
-		  unsigned long vlen, loff_t *pos)
+		  unsigned long vlen, loff_t *pos, int flags)
 {
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_READ))
 		return -EINVAL;
 
-	return do_readv_writev(READ, file, vec, vlen, pos);
+	return do_readv_writev(READ, file, vec, vlen, pos, flags);
 }
 
 EXPORT_SYMBOL(vfs_readv);
 
 ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
-		   unsigned long vlen, loff_t *pos)
+		   unsigned long vlen, loff_t *pos, int flags)
 {
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 
-	return do_readv_writev(WRITE, file, vec, vlen, pos);
+	return do_readv_writev(WRITE, file, vec, vlen, pos, flags);
 }
 
 EXPORT_SYMBOL(vfs_writev);
 
-SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
-		unsigned long, vlen)
+static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
+			unsigned long vlen, int flags)
 {
 	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
 		loff_t pos = file_pos_read(f.file);
-		ret = vfs_readv(f.file, vec, vlen, &pos);
+		ret = vfs_readv(f.file, vec, vlen, &pos, flags);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
 		fdput_pos(f);
@@ -908,15 +918,15 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 	return ret;
 }
 
-SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
-		unsigned long, vlen)
+static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec,
+			 unsigned long vlen, int flags)
 {
 	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
 		loff_t pos = file_pos_read(f.file);
-		ret = vfs_writev(f.file, vec, vlen, &pos);
+		ret = vfs_writev(f.file, vec, vlen, &pos, flags);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
 		fdput_pos(f);
@@ -934,10 +944,9 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
 	return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low;
 }
 
-SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
-		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec,
+			 unsigned long vlen, loff_t pos, int flags)
 {
-	loff_t pos = pos_from_hilo(pos_h, pos_l);
 	struct fd f;
 	ssize_t ret = -EBADF;
 
@@ -948,7 +957,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
 	if (f.file) {
 		ret = -ESPIPE;
 		if (f.file->f_mode & FMODE_PREAD)
-			ret = vfs_readv(f.file, vec, vlen, &pos);
+			ret = vfs_readv(f.file, vec, vlen, &pos, flags);
 		fdput(f);
 	}
 
@@ -958,10 +967,9 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
 	return ret;
 }
 
-SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
-		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec,
+			  unsigned long vlen, loff_t pos, int flags)
 {
-	loff_t pos = pos_from_hilo(pos_h, pos_l);
 	struct fd f;
 	ssize_t ret = -EBADF;
 
@@ -972,7 +980,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
 	if (f.file) {
 		ret = -ESPIPE;
 		if (f.file->f_mode & FMODE_PWRITE)
-			ret = vfs_writev(f.file, vec, vlen, &pos);
+			ret = vfs_writev(f.file, vec, vlen, &pos, flags);
 		fdput(f);
 	}
 
@@ -982,11 +990,64 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
 	return ret;
 }
 
+SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen)
+{
+	return do_readv(fd, vec, vlen, 0);
+}
+
+SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen)
+{
+	return do_writev(fd, vec, vlen, 0);
+}
+
+SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	return do_preadv(fd, vec, vlen, pos, 0);
+}
+
+SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
+		int, flags)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	if (pos == -1)
+		return do_readv(fd, vec, vlen, flags);
+
+	return do_preadv(fd, vec, vlen, pos, flags);
+}
+
+SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	return do_pwritev(fd, vec, vlen, pos, 0);
+}
+
+SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
+		int, flags)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	if (pos == -1)
+		return do_writev(fd, vec, vlen, flags);
+
+	return do_pwritev(fd, vec, vlen, pos, flags);
+}
+
 #ifdef CONFIG_COMPAT
 
 static ssize_t compat_do_readv_writev(int type, struct file *file,
 			       const struct compat_iovec __user *uvector,
-			       unsigned long nr_segs, loff_t *pos)
+			       unsigned long nr_segs, loff_t *pos,
+			       int flags)
 {
 	compat_ssize_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
@@ -1018,9 +1079,9 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	}
 
 	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
+		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
 	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn);
+		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
 
 	if (type != READ)
 		file_end_write(file);
@@ -1038,7 +1099,7 @@ out:
 
 static size_t compat_readv(struct file *file,
 			   const struct compat_iovec __user *vec,
-			   unsigned long vlen, loff_t *pos)
+			   unsigned long vlen, loff_t *pos, int flags)
 {
 	ssize_t ret = -EBADF;
 
@@ -1049,7 +1110,7 @@ static size_t compat_readv(struct file *file,
 	if (!(file->f_mode & FMODE_CAN_READ))
 		goto out;
 
-	ret = compat_do_readv_writev(READ, file, vec, vlen, pos);
+	ret = compat_do_readv_writev(READ, file, vec, vlen, pos, flags);
 
 out:
 	if (ret > 0)
@@ -1058,9 +1119,9 @@ out:
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
-		compat_ulong_t, vlen)
+static size_t do_compat_readv(compat_ulong_t fd,
+				 const struct compat_iovec __user *vec,
+				 compat_ulong_t vlen, int flags)
 {
 	struct fd f = fdget_pos(fd);
 	ssize_t ret;
@@ -1069,16 +1130,24 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
 	if (!f.file)
 		return -EBADF;
 	pos = f.file->f_pos;
-	ret = compat_readv(f.file, vec, vlen, &pos);
+	ret = compat_readv(f.file, vec, vlen, &pos, flags);
 	if (ret >= 0)
 		f.file->f_pos = pos;
 	fdput_pos(f);
 	return ret;
+
 }
 
-static long __compat_sys_preadv64(unsigned long fd,
+COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen)
+{
+	return do_compat_readv(fd, vec, vlen, 0);
+}
+
+static long do_compat_preadv64(unsigned long fd,
 				  const struct compat_iovec __user *vec,
-				  unsigned long vlen, loff_t pos)
+				  unsigned long vlen, loff_t pos, int flags)
 {
 	struct fd f;
 	ssize_t ret;
@@ -1090,7 +1159,7 @@ static long __compat_sys_preadv64(unsigned long fd,
 		return -EBADF;
 	ret = -ESPIPE;
 	if (f.file->f_mode & FMODE_PREAD)
-		ret = compat_readv(f.file, vec, vlen, &pos);
+		ret = compat_readv(f.file, vec, vlen, &pos, flags);
 	fdput(f);
 	return ret;
 }
@@ -1100,7 +1169,7 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
 		const struct compat_iovec __user *,vec,
 		unsigned long, vlen, loff_t, pos)
 {
-	return __compat_sys_preadv64(fd, vec, vlen, pos);
+	return do_compat_preadv64(fd, vec, vlen, pos, 0);
 }
 #endif
 
@@ -1110,12 +1179,25 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
-	return __compat_sys_preadv64(fd, vec, vlen, pos);
+	return do_compat_preadv64(fd, vec, vlen, pos, 0);
+}
+
+COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
+		int, flags)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+	if (pos == -1)
+		return do_compat_readv(fd, vec, vlen, flags);
+
+	return do_compat_preadv64(fd, vec, vlen, pos, flags);
 }
 
 static size_t compat_writev(struct file *file,
 			    const struct compat_iovec __user *vec,
-			    unsigned long vlen, loff_t *pos)
+			    unsigned long vlen, loff_t *pos, int flags)
 {
 	ssize_t ret = -EBADF;
 
@@ -1126,7 +1208,7 @@ static size_t compat_writev(struct file *file,
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		goto out;
 
-	ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);
+	ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, 0);
 
 out:
 	if (ret > 0)
@@ -1135,9 +1217,9 @@ out:
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
-		const struct compat_iovec __user *, vec,
-		compat_ulong_t, vlen)
+static size_t do_compat_writev(compat_ulong_t fd,
+				  const struct compat_iovec __user* vec,
+				  compat_ulong_t vlen, int flags)
 {
 	struct fd f = fdget_pos(fd);
 	ssize_t ret;
@@ -1146,16 +1228,23 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
 	if (!f.file)
 		return -EBADF;
 	pos = f.file->f_pos;
-	ret = compat_writev(f.file, vec, vlen, &pos);
+	ret = compat_writev(f.file, vec, vlen, &pos, flags);
 	if (ret >= 0)
 		f.file->f_pos = pos;
 	fdput_pos(f);
 	return ret;
 }
 
-static long __compat_sys_pwritev64(unsigned long fd,
+COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
+		const struct compat_iovec __user *, vec,
+		compat_ulong_t, vlen)
+{
+	return do_compat_writev(fd, vec, vlen, 0);
+}
+
+static long do_compat_pwritev64(unsigned long fd,
 				   const struct compat_iovec __user *vec,
-				   unsigned long vlen, loff_t pos)
+				   unsigned long vlen, loff_t pos, int flags)
 {
 	struct fd f;
 	ssize_t ret;
@@ -1167,7 +1256,7 @@ static long __compat_sys_pwritev64(unsigned long fd,
 		return -EBADF;
 	ret = -ESPIPE;
 	if (f.file->f_mode & FMODE_PWRITE)
-		ret = compat_writev(f.file, vec, vlen, &pos);
+		ret = compat_writev(f.file, vec, vlen, &pos, flags);
 	fdput(f);
 	return ret;
 }
@@ -1177,7 +1266,7 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
 		const struct compat_iovec __user *,vec,
 		unsigned long, vlen, loff_t, pos)
 {
-	return __compat_sys_pwritev64(fd, vec, vlen, pos);
+	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
 }
 #endif
 
@@ -1187,8 +1276,21 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
-	return __compat_sys_pwritev64(fd, vec, vlen, pos);
+	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
 }
+
+COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+	if (pos == -1)
+		return do_compat_writev(fd, vec, vlen, flags);
+
+	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
+}
+
 #endif
 
 static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
@@ -1532,10 +1634,12 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 
 	if (!(file_in->f_mode & FMODE_READ) ||
 	    !(file_out->f_mode & FMODE_WRITE) ||
-	    (file_out->f_flags & O_APPEND) ||
-	    !file_in->f_op->clone_file_range)
+	    (file_out->f_flags & O_APPEND))
 		return -EBADF;
 
+	if (!file_in->f_op->clone_file_range)
+		return -EOPNOTSUPP;
+
 	ret = clone_verify_area(file_in, pos_in, len, false);
 	if (ret)
 		return ret;
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index c0306ec8ed7b..b8f2d1e8c645 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -802,6 +802,7 @@ static const struct dquot_operations reiserfs_quota_operations = {
 	.write_info = reiserfs_write_info,
 	.alloc_dquot	= dquot_alloc,
 	.destroy_dquot	= dquot_destroy,
+	.get_next_id	= dquot_get_next_id,
 };
 
 static const struct quotactl_ops reiserfs_qctl_operations = {
diff --git a/fs/select.c b/fs/select.c
index 79d0d4953cad..869293988c2a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -70,9 +70,9 @@ static long __estimate_accuracy(struct timespec *tv)
 	return slack;
 }
 
-long select_estimate_accuracy(struct timespec *tv)
+u64 select_estimate_accuracy(struct timespec *tv)
 {
-	unsigned long ret;
+	u64 ret;
 	struct timespec now;
 
 	/*
@@ -402,7 +402,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
 	struct poll_wqueues table;
 	poll_table *wait;
 	int retval, i, timed_out = 0;
-	unsigned long slack = 0;
+	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
 	unsigned long busy_end = 0;
 
@@ -784,7 +784,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 	poll_table* pt = &wait->pt;
 	ktime_t expire, *to = NULL;
 	int timed_out = 0, count = 0;
-	unsigned long slack = 0;
+	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
 	unsigned long busy_end = 0;
 
diff --git a/fs/splice.c b/fs/splice.c
index 82bc0d64fc38..9947b5c69664 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -185,6 +185,9 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 	unsigned int spd_pages = spd->nr_pages;
 	int ret, do_wakeup, page_nr;
 
+	if (!spd_pages)
+		return 0;
+
 	ret = 0;
 	do_wakeup = 0;
 	page_nr = 0;
@@ -577,7 +580,7 @@ static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
 	old_fs = get_fs();
 	set_fs(get_ds());
 	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos);
+	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
 	set_fs(old_fs);
 
 	return res;
diff --git a/fs/super.c b/fs/super.c
index 1182af8fd5ff..74914b1bae70 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -415,6 +415,7 @@ void generic_shutdown_super(struct super_block *sb)
 		sb->s_flags &= ~MS_ACTIVE;
 
 		fsnotify_unmount_inodes(sb);
+		cgroup_writeback_umount();
 
 		evict_inodes(sb);
 
diff --git a/fs/timerfd.c b/fs/timerfd.c
index b94fa6c3c6eb..053818dd6c18 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -153,7 +153,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
 	if (isalarm(ctx))
 		remaining = alarm_expires_remaining(&ctx->t.alarm);
 	else
-		remaining = hrtimer_expires_remaining(&ctx->t.tmr);
+		remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr);
 
 	return remaining.tv64 < 0 ? ktime_set(0, 0): remaining;
 }
diff --git a/fs/ubifs/Makefile b/fs/ubifs/Makefile
index 2c6f0cb816b4..c54a24360f85 100644
--- a/fs/ubifs/Makefile
+++ b/fs/ubifs/Makefile
@@ -4,3 +4,4 @@ ubifs-y += shrinker.o journal.o file.o dir.o super.o sb.o io.o
 ubifs-y += tnc.o master.o scan.o replay.o log.o commit.o gc.o orphan.o
 ubifs-y += budget.o find.o tnc_commit.o compress.o lpt.o lprops.o
 ubifs-y += recovery.o ioctl.o lpt_commit.o tnc_misc.o xattr.o debug.o
+ubifs-y += misc.o
diff --git a/fs/ubifs/misc.c b/fs/ubifs/misc.c
new file mode 100644
index 000000000000..486a2844949f
--- /dev/null
+++ b/fs/ubifs/misc.c
@@ -0,0 +1,57 @@
+#include <linux/kernel.h>
+#include "ubifs.h"
+
+/* Normal UBIFS messages */
+void ubifs_msg(const struct ubifs_info *c, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	pr_notice("UBIFS (ubi%d:%d): %pV\n",
+		  c->vi.ubi_num, c->vi.vol_id, &vaf);
+
+	va_end(args);
+}								    \
+
+/* UBIFS error messages */
+void ubifs_err(const struct ubifs_info *c, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	pr_err("UBIFS error (ubi%d:%d pid %d): %ps: %pV\n",
+	       c->vi.ubi_num, c->vi.vol_id, current->pid,
+	       __builtin_return_address(0),
+	       &vaf);
+
+	va_end(args);
+}								    \
+
+/* UBIFS warning messages */
+void ubifs_warn(const struct ubifs_info *c, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	pr_warn("UBIFS warning (ubi%d:%d pid %d): %ps: %pV\n",
+		c->vi.ubi_num, c->vi.vol_id, current->pid,
+		__builtin_return_address(0),
+		&vaf);
+
+	va_end(args);
+}
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index a5697de763f5..c2a57e193a81 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -42,30 +42,6 @@
 /* Version of this UBIFS implementation */
 #define UBIFS_VERSION 1
 
-/* Normal UBIFS messages */
-#define ubifs_msg(c, fmt, ...)                                      \
-	pr_notice("UBIFS (ubi%d:%d): " fmt "\n",                    \
-		  (c)->vi.ubi_num, (c)->vi.vol_id, ##__VA_ARGS__)
-/* UBIFS error messages */
-#define ubifs_err(c, fmt, ...)                                      \
-	pr_err("UBIFS error (ubi%d:%d pid %d): %s: " fmt "\n",      \
-	       (c)->vi.ubi_num, (c)->vi.vol_id, current->pid,       \
-	       __func__, ##__VA_ARGS__)
-/* UBIFS warning messages */
-#define ubifs_warn(c, fmt, ...)                                     \
-	pr_warn("UBIFS warning (ubi%d:%d pid %d): %s: " fmt "\n",   \
-		(c)->vi.ubi_num, (c)->vi.vol_id, current->pid,      \
-		__func__, ##__VA_ARGS__)
-/*
- * A variant of 'ubifs_err()' which takes the UBIFS file-sytem description
- * object as an argument.
- */
-#define ubifs_errc(c, fmt, ...)                                     \
-	do {                                                        \
-		if (!(c)->probing)                                  \
-			ubifs_err(c, fmt, ##__VA_ARGS__);           \
-	} while (0)
-
 /* UBIFS file system VFS magic number */
 #define UBIFS_SUPER_MAGIC 0x24051905
 
@@ -1802,4 +1778,21 @@ int ubifs_decompress(const struct ubifs_info *c, const void *buf, int len,
 #include "misc.h"
 #include "key.h"
 
+/* Normal UBIFS messages */
+__printf(2, 3)
+void ubifs_msg(const struct ubifs_info *c, const char *fmt, ...);
+__printf(2, 3)
+void ubifs_err(const struct ubifs_info *c, const char *fmt, ...);
+__printf(2, 3)
+void ubifs_warn(const struct ubifs_info *c, const char *fmt, ...);
+/*
+ * A variant of 'ubifs_err()' which takes the UBIFS file-sytem description
+ * object as an argument.
+ */
+#define ubifs_errc(c, fmt, ...)						\
+do {									\
+	if (!(c)->probing)						\
+		ubifs_err(c, fmt, ##__VA_ARGS__);			\
+} while (0)
+
 #endif /* !__UBIFS_H__ */
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index c7f4d434d098..b043e044121d 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -59,7 +59,6 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/xattr.h>
-#include <linux/posix_acl_xattr.h>
 
 /*
  * Limit the number of extended attributes per inode so that the total size
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index 541d9c65014d..b51b371b874a 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -45,7 +45,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 	int block, iblock;
 	loff_t nf_pos;
 	int flen;
-	unsigned char *fname = NULL;
+	unsigned char *fname = NULL, *copy_name = NULL;
 	unsigned char *nameptr;
 	uint16_t liu;
 	uint8_t lfi;
@@ -143,7 +143,15 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 			if (poffset >= lfi) {
 				nameptr = (char *)(fibh.ebh->b_data + poffset - lfi);
 			} else {
-				nameptr = fname;
+				if (!copy_name) {
+					copy_name = kmalloc(UDF_NAME_LEN,
+							    GFP_NOFS);
+					if (!copy_name) {
+						ret = -ENOMEM;
+						goto out;
+					}
+				}
+				nameptr = copy_name;
 				memcpy(nameptr, fi->fileIdent + liu,
 				       lfi - poffset);
 				memcpy(nameptr + lfi - poffset,
@@ -185,6 +193,7 @@ out:
 	brelse(fibh.sbh);
 	brelse(epos.bh);
 	kfree(fname);
+	kfree(copy_name);
 
 	return ret;
 }
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 42eafb91f7ff..a2ba11eca995 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -165,7 +165,7 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir,
 	struct fileIdentDesc *fi = NULL;
 	loff_t f_pos;
 	int block, flen;
-	unsigned char *fname = NULL;
+	unsigned char *fname = NULL, *copy_name = NULL;
 	unsigned char *nameptr;
 	uint8_t lfi;
 	uint16_t liu;
@@ -236,7 +236,15 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir,
 				nameptr = (uint8_t *)(fibh->ebh->b_data +
 						      poffset - lfi);
 			else {
-				nameptr = fname;
+				if (!copy_name) {
+					copy_name = kmalloc(UDF_NAME_LEN,
+							    GFP_NOFS);
+					if (!copy_name) {
+						fi = ERR_PTR(-ENOMEM);
+						goto out_err;
+					}
+				}
+				nameptr = copy_name;
 				memcpy(nameptr, fi->fileIdent + liu,
 					lfi - poffset);
 				memcpy(nameptr + lfi - poffset,
@@ -279,6 +287,7 @@ out_err:
 out_ok:
 	brelse(epos.bh);
 	kfree(fname);
+	kfree(copy_name);
 
 	return fi;
 }
@@ -291,7 +300,7 @@ static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry,
 	struct udf_fileident_bh fibh;
 	struct fileIdentDesc *fi;
 
-	if (dentry->d_name.len > UDF_NAME_LEN - 2)
+	if (dentry->d_name.len > UDF_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
 #ifdef UDF_RECOVERY
@@ -351,7 +360,7 @@ static struct fileIdentDesc *udf_add_entry(struct inode *dir,
 	struct udf_inode_info *dinfo;
 
 	fibh->sbh = fibh->ebh = NULL;
-	name = kmalloc(UDF_NAME_LEN, GFP_NOFS);
+	name = kmalloc(UDF_NAME_LEN_CS0, GFP_NOFS);
 	if (!name) {
 		*err = -ENOMEM;
 		goto out_err;
@@ -362,8 +371,9 @@ static struct fileIdentDesc *udf_add_entry(struct inode *dir,
 			*err = -EINVAL;
 			goto out_err;
 		}
-		namelen = udf_put_filename(sb, dentry->d_name.name, name,
-						 dentry->d_name.len);
+		namelen = udf_put_filename(sb, dentry->d_name.name,
+					   dentry->d_name.len,
+					   name, UDF_NAME_LEN_CS0);
 		if (!namelen) {
 			*err = -ENAMETOOLONG;
 			goto out_err;
@@ -914,7 +924,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 
 	iinfo = UDF_I(inode);
 	down_write(&iinfo->i_data_sem);
-	name = kmalloc(UDF_NAME_LEN, GFP_NOFS);
+	name = kmalloc(UDF_NAME_LEN_CS0, GFP_NOFS);
 	if (!name) {
 		err = -ENOMEM;
 		goto out_no_entry;
@@ -997,8 +1007,9 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 		}
 
 		if (pc->componentType == 5) {
-			namelen = udf_put_filename(sb, compstart, name,
-						   symname - compstart);
+			namelen = udf_put_filename(sb, compstart,
+						   symname - compstart,
+						   name, UDF_NAME_LEN_CS0);
 			if (!namelen)
 				goto out_no_entry;
 
diff --git a/fs/udf/super.c b/fs/udf/super.c
index a522c15a0bfd..fa92fe839fda 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -887,18 +887,14 @@ static int udf_find_fileset(struct super_block *sb,
 static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
 {
 	struct primaryVolDesc *pvoldesc;
-	struct ustr *instr, *outstr;
+	uint8_t *outstr;
 	struct buffer_head *bh;
 	uint16_t ident;
 	int ret = -ENOMEM;
 
-	instr = kmalloc(sizeof(struct ustr), GFP_NOFS);
-	if (!instr)
-		return -ENOMEM;
-
-	outstr = kmalloc(sizeof(struct ustr), GFP_NOFS);
+	outstr = kmalloc(128, GFP_NOFS);
 	if (!outstr)
-		goto out1;
+		return -ENOMEM;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
 	if (!bh) {
@@ -923,31 +919,25 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
 #endif
 	}
 
-	if (!udf_build_ustr(instr, pvoldesc->volIdent, 32)) {
-		ret = udf_CS0toUTF8(outstr, instr);
-		if (ret < 0)
-			goto out_bh;
+	ret = udf_CS0toUTF8(outstr, 31, pvoldesc->volIdent, 32);
+	if (ret < 0)
+		goto out_bh;
 
-		strncpy(UDF_SB(sb)->s_volume_ident, outstr->u_name,
-			outstr->u_len > 31 ? 31 : outstr->u_len);
-		udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident);
-	}
+	strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret);
+	udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident);
 
-	if (!udf_build_ustr(instr, pvoldesc->volSetIdent, 128)) {
-		ret = udf_CS0toUTF8(outstr, instr);
-		if (ret < 0)
-			goto out_bh;
+	ret = udf_CS0toUTF8(outstr, 127, pvoldesc->volSetIdent, 128);
+	if (ret < 0)
+		goto out_bh;
 
-		udf_debug("volSetIdent[] = '%s'\n", outstr->u_name);
-	}
+	outstr[ret] = 0;
+	udf_debug("volSetIdent[] = '%s'\n", outstr);
 
 	ret = 0;
 out_bh:
 	brelse(bh);
 out2:
 	kfree(outstr);
-out1:
-	kfree(instr);
 	return ret;
 }
 
@@ -2358,7 +2348,7 @@ static int udf_statfs(struct dentry *dentry, struct kstatfs *buf)
 					  le32_to_cpu(lvidiu->numDirs)) : 0)
 			+ buf->f_bfree;
 	buf->f_ffree = buf->f_bfree;
-	buf->f_namelen = UDF_NAME_LEN - 2;
+	buf->f_namelen = UDF_NAME_LEN;
 	buf->f_fsid.val[0] = (u32)id;
 	buf->f_fsid.val[1] = (u32)(id >> 32);
 
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index fa0044b6b81d..972b70625614 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -49,8 +49,8 @@ extern __printf(3, 4) void _udf_warn(struct super_block *sb,
 #define UDF_EXTENT_FLAG_MASK	0xC0000000
 
 #define UDF_NAME_PAD		4
-#define UDF_NAME_LEN		256
-#define UDF_PATH_LEN		1023
+#define UDF_NAME_LEN		254
+#define UDF_NAME_LEN_CS0	255
 
 static inline size_t udf_file_entry_alloc_offset(struct inode *inode)
 {
@@ -106,12 +106,6 @@ struct generic_desc {
 	__le32		volDescSeqNum;
 };
 
-struct ustr {
-	uint8_t u_cmpID;
-	uint8_t u_name[UDF_NAME_LEN - 2];
-	uint8_t u_len;
-};
-
 
 /* super.c */
 
@@ -214,12 +208,11 @@ udf_get_lb_pblock(struct super_block *sb, struct kernel_lb_addr *loc,
 }
 
 /* unicode.c */
-extern int udf_get_filename(struct super_block *, uint8_t *, int, uint8_t *,
-			    int);
-extern int udf_put_filename(struct super_block *, const uint8_t *, uint8_t *,
-			    int);
-extern int udf_build_ustr(struct ustr *, dstring *, int);
-extern int udf_CS0toUTF8(struct ustr *, const struct ustr *);
+extern int udf_get_filename(struct super_block *, const uint8_t *, int,
+			    uint8_t *, int);
+extern int udf_put_filename(struct super_block *, const uint8_t *, int,
+			    uint8_t *, int);
+extern int udf_CS0toUTF8(uint8_t *, int, const uint8_t *, int);
 
 /* ialloc.c */
 extern void udf_free_inode(struct inode *);
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index e788a05aab83..3ff42f4437f3 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -28,199 +28,72 @@
 
 #include "udf_sb.h"
 
-static int udf_translate_to_linux(uint8_t *, int, uint8_t *, int, uint8_t *,
-				  int);
-
-static int udf_char_to_ustr(struct ustr *dest, const uint8_t *src, int strlen)
-{
-	if ((!dest) || (!src) || (!strlen) || (strlen > UDF_NAME_LEN - 2))
-		return 0;
-
-	memset(dest, 0, sizeof(struct ustr));
-	memcpy(dest->u_name, src, strlen);
-	dest->u_cmpID = 0x08;
-	dest->u_len = strlen;
-
-	return strlen;
-}
-
-/*
- * udf_build_ustr
- */
-int udf_build_ustr(struct ustr *dest, dstring *ptr, int size)
-{
-	int usesize;
-
-	if (!dest || !ptr || !size)
-		return -1;
-	BUG_ON(size < 2);
-
-	usesize = min_t(size_t, ptr[size - 1], sizeof(dest->u_name));
-	usesize = min(usesize, size - 2);
-	dest->u_cmpID = ptr[0];
-	dest->u_len = usesize;
-	memcpy(dest->u_name, ptr + 1, usesize);
-	memset(dest->u_name + usesize, 0, sizeof(dest->u_name) - usesize);
-
-	return 0;
-}
-
-/*
- * udf_build_ustr_exact
- */
-static void udf_build_ustr_exact(struct ustr *dest, dstring *ptr, int exactsize)
-{
-	memset(dest, 0, sizeof(struct ustr));
-	dest->u_cmpID = ptr[0];
-	dest->u_len = exactsize - 1;
-	memcpy(dest->u_name, ptr + 1, exactsize - 1);
-}
-
-/*
- * udf_CS0toUTF8
- *
- * PURPOSE
- *	Convert OSTA Compressed Unicode to the UTF-8 equivalent.
- *
- * PRE-CONDITIONS
- *	utf			Pointer to UTF-8 output buffer.
- *	ocu			Pointer to OSTA Compressed Unicode input buffer
- *				of size UDF_NAME_LEN bytes.
- * 				both of type "struct ustr *"
- *
- * POST-CONDITIONS
- *	<return>		>= 0 on success.
- *
- * HISTORY
- *	November 12, 1997 - Andrew E. Mileski
- *	Written, tested, and released.
- */
-int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i)
+static int udf_uni2char_utf8(wchar_t uni,
+			     unsigned char *out,
+			     int boundlen)
 {
-	const uint8_t *ocu;
-	uint8_t cmp_id, ocu_len;
-	int i;
-
-	ocu_len = ocu_i->u_len;
-	if (ocu_len == 0) {
-		memset(utf_o, 0, sizeof(struct ustr));
-		return 0;
-	}
-
-	cmp_id = ocu_i->u_cmpID;
-	if (cmp_id != 8 && cmp_id != 16) {
-		memset(utf_o, 0, sizeof(struct ustr));
-		pr_err("unknown compression code (%d) stri=%s\n",
-		       cmp_id, ocu_i->u_name);
-		return -EINVAL;
-	}
-
-	ocu = ocu_i->u_name;
-	utf_o->u_len = 0;
-	for (i = 0; (i < ocu_len) && (utf_o->u_len <= (UDF_NAME_LEN - 3));) {
-
-		/* Expand OSTA compressed Unicode to Unicode */
-		uint32_t c = ocu[i++];
-		if (cmp_id == 16)
-			c = (c << 8) | ocu[i++];
-
-		/* Compress Unicode to UTF-8 */
-		if (c < 0x80U)
-			utf_o->u_name[utf_o->u_len++] = (uint8_t)c;
-		else if (c < 0x800U) {
-			if (utf_o->u_len > (UDF_NAME_LEN - 4))
-				break;
-			utf_o->u_name[utf_o->u_len++] =
-						(uint8_t)(0xc0 | (c >> 6));
-			utf_o->u_name[utf_o->u_len++] =
-						(uint8_t)(0x80 | (c & 0x3f));
-		} else {
-			if (utf_o->u_len > (UDF_NAME_LEN - 5))
-				break;
-			utf_o->u_name[utf_o->u_len++] =
-						(uint8_t)(0xe0 | (c >> 12));
-			utf_o->u_name[utf_o->u_len++] =
-						(uint8_t)(0x80 |
-							  ((c >> 6) & 0x3f));
-			utf_o->u_name[utf_o->u_len++] =
-						(uint8_t)(0x80 | (c & 0x3f));
-		}
+	int u_len = 0;
+
+	if (boundlen <= 0)
+		return -ENAMETOOLONG;
+
+	if (uni < 0x80) {
+		out[u_len++] = (unsigned char)uni;
+	} else if (uni < 0x800) {
+		if (boundlen < 2)
+			return -ENAMETOOLONG;
+		out[u_len++] = (unsigned char)(0xc0 | (uni >> 6));
+		out[u_len++] = (unsigned char)(0x80 | (uni & 0x3f));
+	} else {
+		if (boundlen < 3)
+			return -ENAMETOOLONG;
+		out[u_len++] = (unsigned char)(0xe0 | (uni >> 12));
+		out[u_len++] = (unsigned char)(0x80 | ((uni >> 6) & 0x3f));
+		out[u_len++] = (unsigned char)(0x80 | (uni & 0x3f));
 	}
-	utf_o->u_cmpID = 8;
-
-	return utf_o->u_len;
+	return u_len;
 }
 
-/*
- *
- * udf_UTF8toCS0
- *
- * PURPOSE
- *	Convert UTF-8 to the OSTA Compressed Unicode equivalent.
- *
- * DESCRIPTION
- *	This routine is only called by udf_lookup().
- *
- * PRE-CONDITIONS
- *	ocu			Pointer to OSTA Compressed Unicode output
- *				buffer of size UDF_NAME_LEN bytes.
- *	utf			Pointer to UTF-8 input buffer.
- *	utf_len			Length of UTF-8 input buffer in bytes.
- *
- * POST-CONDITIONS
- *	<return>		Zero on success.
- *
- * HISTORY
- *	November 12, 1997 - Andrew E. Mileski
- *	Written, tested, and released.
- */
-static int udf_UTF8toCS0(dstring *ocu, struct ustr *utf, int length)
+static int udf_char2uni_utf8(const unsigned char *in,
+			     int boundlen,
+			     wchar_t *uni)
 {
-	unsigned c, i, max_val, utf_char;
-	int utf_cnt, u_len, u_ch;
-
-	memset(ocu, 0, sizeof(dstring) * length);
-	ocu[0] = 8;
-	max_val = 0xffU;
-	u_ch = 1;
+	unsigned int utf_char;
+	unsigned char c;
+	int utf_cnt, u_len;
 
-try_again:
-	u_len = 0U;
-	utf_char = 0U;
-	utf_cnt = 0U;
-	for (i = 0U; i < utf->u_len; i++) {
-		/* Name didn't fit? */
-		if (u_len + 1 + u_ch >= length)
-			return 0;
-
-		c = (uint8_t)utf->u_name[i];
+	utf_char = 0;
+	utf_cnt = 0;
+	for (u_len = 0; u_len < boundlen;) {
+		c = in[u_len++];
 
 		/* Complete a multi-byte UTF-8 character */
 		if (utf_cnt) {
-			utf_char = (utf_char << 6) | (c & 0x3fU);
+			utf_char = (utf_char << 6) | (c & 0x3f);
 			if (--utf_cnt)
 				continue;
 		} else {
 			/* Check for a multi-byte UTF-8 character */
-			if (c & 0x80U) {
+			if (c & 0x80) {
 				/* Start a multi-byte UTF-8 character */
-				if ((c & 0xe0U) == 0xc0U) {
-					utf_char = c & 0x1fU;
+				if ((c & 0xe0) == 0xc0) {
+					utf_char = c & 0x1f;
 					utf_cnt = 1;
-				} else if ((c & 0xf0U) == 0xe0U) {
-					utf_char = c & 0x0fU;
+				} else if ((c & 0xf0) == 0xe0) {
+					utf_char = c & 0x0f;
 					utf_cnt = 2;
-				} else if ((c & 0xf8U) == 0xf0U) {
-					utf_char = c & 0x07U;
+				} else if ((c & 0xf8) == 0xf0) {
+					utf_char = c & 0x07;
 					utf_cnt = 3;
-				} else if ((c & 0xfcU) == 0xf8U) {
-					utf_char = c & 0x03U;
+				} else if ((c & 0xfc) == 0xf8) {
+					utf_char = c & 0x03;
 					utf_cnt = 4;
-				} else if ((c & 0xfeU) == 0xfcU) {
-					utf_char = c & 0x01U;
+				} else if ((c & 0xfe) == 0xfc) {
+					utf_char = c & 0x01;
 					utf_cnt = 5;
 				} else {
-					goto error_out;
+					utf_cnt = -1;
+					break;
 				}
 				continue;
 			} else {
@@ -228,97 +101,216 @@ try_again:
 				utf_char = c;
 			}
 		}
-
-		/* Choose no compression if necessary */
-		if (utf_char > max_val) {
-			if (max_val == 0xffU) {
-				max_val = 0xffffU;
-				ocu[0] = (uint8_t)0x10U;
-				u_ch = 2;
-				goto try_again;
-			}
-			goto error_out;
-		}
-
-		if (max_val == 0xffffU)
-			ocu[++u_len] = (uint8_t)(utf_char >> 8);
-		ocu[++u_len] = (uint8_t)(utf_char & 0xffU);
+		*uni = utf_char;
+		break;
 	}
-
 	if (utf_cnt) {
-error_out:
-		ocu[++u_len] = '?';
-		printk(KERN_DEBUG pr_fmt("bad UTF-8 character\n"));
+		*uni = '?';
+		return -EINVAL;
 	}
+	return u_len;
+}
 
-	ocu[length - 1] = (uint8_t)u_len + 1;
+#define ILLEGAL_CHAR_MARK	'_'
+#define EXT_MARK		'.'
+#define CRC_MARK		'#'
+#define EXT_SIZE		5
+/* Number of chars we need to store generated CRC to make filename unique */
+#define CRC_LEN			5
+
+static int udf_name_conv_char(uint8_t *str_o, int str_o_max_len,
+			      int *str_o_idx,
+			      const uint8_t *str_i, int str_i_max_len,
+			      int *str_i_idx,
+			      int u_ch, int *needsCRC,
+			      int (*conv_f)(wchar_t, unsigned char *, int),
+			      int translate)
+{
+	uint32_t c;
+	int illChar = 0;
+	int len, gotch = 0;
+
+	for (; (!gotch) && (*str_i_idx < str_i_max_len); *str_i_idx += u_ch) {
+		if (*str_o_idx >= str_o_max_len) {
+			*needsCRC = 1;
+			return gotch;
+		}
 
-	return u_len + 1;
+		/* Expand OSTA compressed Unicode to Unicode */
+		c = str_i[*str_i_idx];
+		if (u_ch > 1)
+			c = (c << 8) | str_i[*str_i_idx + 1];
+
+		if (translate && (c == '/' || c == 0))
+			illChar = 1;
+		else if (illChar)
+			break;
+		else
+			gotch = 1;
+	}
+	if (illChar) {
+		*needsCRC = 1;
+		c = ILLEGAL_CHAR_MARK;
+		gotch = 1;
+	}
+	if (gotch) {
+		len = conv_f(c, &str_o[*str_o_idx], str_o_max_len - *str_o_idx);
+		/* Valid character? */
+		if (len >= 0)
+			*str_o_idx += len;
+		else if (len == -ENAMETOOLONG) {
+			*needsCRC = 1;
+			gotch = 0;
+		} else {
+			str_o[(*str_o_idx)++] = '?';
+			*needsCRC = 1;
+		}
+	}
+	return gotch;
 }
 
-static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o,
-			const struct ustr *ocu_i)
+static int udf_name_from_CS0(uint8_t *str_o, int str_max_len,
+			     const uint8_t *ocu, int ocu_len,
+			     int (*conv_f)(wchar_t, unsigned char *, int),
+			     int translate)
 {
-	const uint8_t *ocu;
-	uint8_t cmp_id, ocu_len;
-	int i, len;
+	uint32_t c;
+	uint8_t cmp_id;
+	int idx, len;
+	int u_ch;
+	int needsCRC = 0;
+	int ext_i_len, ext_max_len;
+	int str_o_len = 0;	/* Length of resulting output */
+	int ext_o_len = 0;	/* Extension output length */
+	int ext_crc_len = 0;	/* Extension output length if used with CRC */
+	int i_ext = -1;		/* Extension position in input buffer */
+	int o_crc = 0;		/* Rightmost possible output pos for CRC+ext */
+	unsigned short valueCRC;
+	uint8_t ext[EXT_SIZE * NLS_MAX_CHARSET_SIZE + 1];
+	uint8_t crc[CRC_LEN];
 
+	if (str_max_len <= 0)
+		return 0;
 
-	ocu_len = ocu_i->u_len;
 	if (ocu_len == 0) {
-		memset(utf_o, 0, sizeof(struct ustr));
+		memset(str_o, 0, str_max_len);
 		return 0;
 	}
 
-	cmp_id = ocu_i->u_cmpID;
+	cmp_id = ocu[0];
 	if (cmp_id != 8 && cmp_id != 16) {
-		memset(utf_o, 0, sizeof(struct ustr));
-		pr_err("unknown compression code (%d) stri=%s\n",
-		       cmp_id, ocu_i->u_name);
+		memset(str_o, 0, str_max_len);
+		pr_err("unknown compression code (%d)\n", cmp_id);
 		return -EINVAL;
 	}
+	u_ch = cmp_id >> 3;
 
-	ocu = ocu_i->u_name;
-	utf_o->u_len = 0;
-	for (i = 0; (i < ocu_len) && (utf_o->u_len <= (UDF_NAME_LEN - 3));) {
-		/* Expand OSTA compressed Unicode to Unicode */
-		uint32_t c = ocu[i++];
-		if (cmp_id == 16)
-			c = (c << 8) | ocu[i++];
+	ocu++;
+	ocu_len--;
 
-		len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len],
-				    UDF_NAME_LEN - 2 - utf_o->u_len);
-		/* Valid character? */
-		if (len >= 0)
-			utf_o->u_len += len;
-		else
-			utf_o->u_name[utf_o->u_len++] = '?';
+	if (ocu_len % u_ch) {
+		pr_err("incorrect filename length (%d)\n", ocu_len + 1);
+		return -EINVAL;
+	}
+
+	if (translate) {
+		/* Look for extension */
+		for (idx = ocu_len - u_ch, ext_i_len = 0;
+		     (idx >= 0) && (ext_i_len < EXT_SIZE);
+		     idx -= u_ch, ext_i_len++) {
+			c = ocu[idx];
+			if (u_ch > 1)
+				c = (c << 8) | ocu[idx + 1];
+
+			if (c == EXT_MARK) {
+				if (ext_i_len)
+					i_ext = idx;
+				break;
+			}
+		}
+		if (i_ext >= 0) {
+			/* Convert extension */
+			ext_max_len = min_t(int, sizeof(ext), str_max_len);
+			ext[ext_o_len++] = EXT_MARK;
+			idx = i_ext + u_ch;
+			while (udf_name_conv_char(ext, ext_max_len, &ext_o_len,
+						  ocu, ocu_len, &idx,
+						  u_ch, &needsCRC,
+						  conv_f, translate)) {
+				if ((ext_o_len + CRC_LEN) < str_max_len)
+					ext_crc_len = ext_o_len;
+			}
+		}
 	}
-	utf_o->u_cmpID = 8;
 
-	return utf_o->u_len;
+	idx = 0;
+	while (1) {
+		if (translate && (idx == i_ext)) {
+			if (str_o_len > (str_max_len - ext_o_len))
+				needsCRC = 1;
+			break;
+		}
+
+		if (!udf_name_conv_char(str_o, str_max_len, &str_o_len,
+					ocu, ocu_len, &idx,
+					u_ch, &needsCRC, conv_f, translate))
+			break;
+
+		if (translate &&
+		    (str_o_len <= (str_max_len - ext_o_len - CRC_LEN)))
+			o_crc = str_o_len;
+	}
+
+	if (translate) {
+		if (str_o_len <= 2 && str_o[0] == '.' &&
+		    (str_o_len == 1 || str_o[1] == '.'))
+			needsCRC = 1;
+		if (needsCRC) {
+			str_o_len = o_crc;
+			valueCRC = crc_itu_t(0, ocu, ocu_len);
+			crc[0] = CRC_MARK;
+			crc[1] = hex_asc_upper_hi(valueCRC >> 8);
+			crc[2] = hex_asc_upper_lo(valueCRC >> 8);
+			crc[3] = hex_asc_upper_hi(valueCRC);
+			crc[4] = hex_asc_upper_lo(valueCRC);
+			len = min_t(int, CRC_LEN, str_max_len - str_o_len);
+			memcpy(&str_o[str_o_len], crc, len);
+			str_o_len += len;
+			ext_o_len = ext_crc_len;
+		}
+		if (ext_o_len > 0) {
+			memcpy(&str_o[str_o_len], ext, ext_o_len);
+			str_o_len += ext_o_len;
+		}
+	}
+
+	return str_o_len;
 }
 
-static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni,
-			int length)
+static int udf_name_to_CS0(uint8_t *ocu, int ocu_max_len,
+			   const uint8_t *str_i, int str_len,
+			   int (*conv_f)(const unsigned char *, int, wchar_t *))
 {
-	int len;
-	unsigned i, max_val;
-	uint16_t uni_char;
+	int i, len;
+	unsigned int max_val;
+	wchar_t uni_char;
 	int u_len, u_ch;
 
-	memset(ocu, 0, sizeof(dstring) * length);
+	if (ocu_max_len <= 0)
+		return 0;
+
+	memset(ocu, 0, ocu_max_len);
 	ocu[0] = 8;
-	max_val = 0xffU;
+	max_val = 0xff;
 	u_ch = 1;
 
 try_again:
-	u_len = 0U;
-	for (i = 0U; i < uni->u_len; i++) {
+	u_len = 1;
+	for (i = 0; i < str_len; i++) {
 		/* Name didn't fit? */
-		if (u_len + 1 + u_ch >= length)
+		if (u_len + u_ch > ocu_max_len)
 			return 0;
-		len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char);
+		len = conv_f(&str_i[i], str_len - i, &uni_char);
 		if (!len)
 			continue;
 		/* Invalid character, deal with it */
@@ -328,187 +320,65 @@ try_again:
 		}
 
 		if (uni_char > max_val) {
-			max_val = 0xffffU;
-			ocu[0] = (uint8_t)0x10U;
+			max_val = 0xffff;
+			ocu[0] = 0x10;
 			u_ch = 2;
 			goto try_again;
 		}
 
-		if (max_val == 0xffffU)
-			ocu[++u_len] = (uint8_t)(uni_char >> 8);
-		ocu[++u_len] = (uint8_t)(uni_char & 0xffU);
+		if (max_val == 0xffff)
+			ocu[u_len++] = (uint8_t)(uni_char >> 8);
+		ocu[u_len++] = (uint8_t)(uni_char & 0xff);
 		i += len - 1;
 	}
 
-	ocu[length - 1] = (uint8_t)u_len + 1;
-	return u_len + 1;
+	return u_len;
 }
 
-int udf_get_filename(struct super_block *sb, uint8_t *sname, int slen,
+int udf_CS0toUTF8(uint8_t *utf_o, int o_len, const uint8_t *ocu_i, int i_len)
+{
+	return udf_name_from_CS0(utf_o, o_len, ocu_i, i_len,
+				 udf_uni2char_utf8, 0);
+}
+
+int udf_get_filename(struct super_block *sb, const uint8_t *sname, int slen,
 		     uint8_t *dname, int dlen)
 {
-	struct ustr *filename, *unifilename;
+	int (*conv_f)(wchar_t, unsigned char *, int);
 	int ret;
 
 	if (!slen)
 		return -EIO;
 
-	filename = kmalloc(sizeof(struct ustr), GFP_NOFS);
-	if (!filename)
-		return -ENOMEM;
-
-	unifilename = kmalloc(sizeof(struct ustr), GFP_NOFS);
-	if (!unifilename) {
-		ret = -ENOMEM;
-		goto out1;
-	}
+	if (dlen <= 0)
+		return 0;
 
-	udf_build_ustr_exact(unifilename, sname, slen);
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) {
-		ret = udf_CS0toUTF8(filename, unifilename);
-		if (ret < 0) {
-			udf_debug("Failed in udf_get_filename: sname = %s\n",
-				  sname);
-			goto out2;
-		}
+		conv_f = udf_uni2char_utf8;
 	} else if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) {
-		ret = udf_CS0toNLS(UDF_SB(sb)->s_nls_map, filename,
-				   unifilename);
-		if (ret < 0) {
-			udf_debug("Failed in udf_get_filename: sname = %s\n",
-				  sname);
-			goto out2;
-		}
+		conv_f = UDF_SB(sb)->s_nls_map->uni2char;
 	} else
 		BUG();
 
-	ret = udf_translate_to_linux(dname, dlen,
-				     filename->u_name, filename->u_len,
-				     unifilename->u_name, unifilename->u_len);
+	ret = udf_name_from_CS0(dname, dlen, sname, slen, conv_f, 1);
 	/* Zero length filename isn't valid... */
 	if (ret == 0)
 		ret = -EINVAL;
-out2:
-	kfree(unifilename);
-out1:
-	kfree(filename);
 	return ret;
 }
 
-int udf_put_filename(struct super_block *sb, const uint8_t *sname,
-		     uint8_t *dname, int flen)
+int udf_put_filename(struct super_block *sb, const uint8_t *sname, int slen,
+		     uint8_t *dname, int dlen)
 {
-	struct ustr unifilename;
-	int namelen;
-
-	if (!udf_char_to_ustr(&unifilename, sname, flen))
-		return 0;
+	int (*conv_f)(const unsigned char *, int, wchar_t *);
 
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) {
-		namelen = udf_UTF8toCS0(dname, &unifilename, UDF_NAME_LEN);
-		if (!namelen)
-			return 0;
+		conv_f = udf_char2uni_utf8;
 	} else if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) {
-		namelen = udf_NLStoCS0(UDF_SB(sb)->s_nls_map, dname,
-					&unifilename, UDF_NAME_LEN);
-		if (!namelen)
-			return 0;
+		conv_f = UDF_SB(sb)->s_nls_map->char2uni;
 	} else
-		return 0;
+		BUG();
 
-	return namelen;
+	return udf_name_to_CS0(dname, dlen, sname, slen, conv_f);
 }
 
-#define ILLEGAL_CHAR_MARK	'_'
-#define EXT_MARK		'.'
-#define CRC_MARK		'#'
-#define EXT_SIZE 		5
-/* Number of chars we need to store generated CRC to make filename unique */
-#define CRC_LEN			5
-
-static int udf_translate_to_linux(uint8_t *newName, int newLen,
-				  uint8_t *udfName, int udfLen,
-				  uint8_t *fidName, int fidNameLen)
-{
-	int index, newIndex = 0, needsCRC = 0;
-	int extIndex = 0, newExtIndex = 0, hasExt = 0;
-	unsigned short valueCRC;
-	uint8_t curr;
-
-	if (udfName[0] == '.' &&
-	    (udfLen == 1 || (udfLen == 2 && udfName[1] == '.'))) {
-		needsCRC = 1;
-		newIndex = udfLen;
-		memcpy(newName, udfName, udfLen);
-	} else {
-		for (index = 0; index < udfLen; index++) {
-			curr = udfName[index];
-			if (curr == '/' || curr == 0) {
-				needsCRC = 1;
-				curr = ILLEGAL_CHAR_MARK;
-				while (index + 1 < udfLen &&
-						(udfName[index + 1] == '/' ||
-						 udfName[index + 1] == 0))
-					index++;
-			}
-			if (curr == EXT_MARK &&
-					(udfLen - index - 1) <= EXT_SIZE) {
-				if (udfLen == index + 1)
-					hasExt = 0;
-				else {
-					hasExt = 1;
-					extIndex = index;
-					newExtIndex = newIndex;
-				}
-			}
-			if (newIndex < newLen)
-				newName[newIndex++] = curr;
-			else
-				needsCRC = 1;
-		}
-	}
-	if (needsCRC) {
-		uint8_t ext[EXT_SIZE];
-		int localExtIndex = 0;
-
-		if (hasExt) {
-			int maxFilenameLen;
-			for (index = 0;
-			     index < EXT_SIZE && extIndex + index + 1 < udfLen;
-			     index++) {
-				curr = udfName[extIndex + index + 1];
-
-				if (curr == '/' || curr == 0) {
-					needsCRC = 1;
-					curr = ILLEGAL_CHAR_MARK;
-					while (extIndex + index + 2 < udfLen &&
-					      (index + 1 < EXT_SIZE &&
-						(udfName[extIndex + index + 2] == '/' ||
-						 udfName[extIndex + index + 2] == 0)))
-						index++;
-				}
-				ext[localExtIndex++] = curr;
-			}
-			maxFilenameLen = newLen - CRC_LEN - localExtIndex;
-			if (newIndex > maxFilenameLen)
-				newIndex = maxFilenameLen;
-			else
-				newIndex = newExtIndex;
-		} else if (newIndex > newLen - CRC_LEN)
-			newIndex = newLen - CRC_LEN;
-		newName[newIndex++] = CRC_MARK;
-		valueCRC = crc_itu_t(0, fidName, fidNameLen);
-		newName[newIndex++] = hex_asc_upper_hi(valueCRC >> 8);
-		newName[newIndex++] = hex_asc_upper_lo(valueCRC >> 8);
-		newName[newIndex++] = hex_asc_upper_hi(valueCRC);
-		newName[newIndex++] = hex_asc_upper_lo(valueCRC);
-
-		if (hasExt) {
-			newName[newIndex++] = EXT_MARK;
-			for (index = 0; index < localExtIndex; index++)
-				newName[newIndex++] = ext[index];
-		}
-	}
-
-	return newIndex;
-}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 50311703135b..66cdb44616d5 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -287,6 +287,12 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 		goto out;
 
 	/*
+	 * We don't do userfault handling for the final child pid update.
+	 */
+	if (current->flags & PF_EXITING)
+		goto out;
+
+	/*
 	 * Check that we can return VM_FAULT_RETRY.
 	 *
 	 * NOTE: it should become possible to return VM_FAULT_RETRY
diff --git a/fs/xattr.c b/fs/xattr.c
index 07d0e47f6a7f..4861322e28e8 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -940,7 +940,7 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 	bool trusted = capable(CAP_SYS_ADMIN);
 	struct simple_xattr *xattr;
 	ssize_t remaining_size = size;
-	int err;
+	int err = 0;
 
 #ifdef CONFIG_FS_POSIX_ACL
 	if (inode->i_acl) {
@@ -965,11 +965,11 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 
 		err = xattr_list_one(&buffer, &remaining_size, xattr->name);
 		if (err)
-			return err;
+			break;
 	}
 	spin_unlock(&xattrs->lock);
 
-	return size - remaining_size;
+	return err ? err : size - remaining_size;
 }
 
 /*
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index f64639176670..3542d94fddce 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -121,4 +121,5 @@ xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o
 xfs-$(CONFIG_XFS_POSIX_ACL)	+= xfs_acl.o
 xfs-$(CONFIG_SYSCTL)		+= xfs_sysctl.o
 xfs-$(CONFIG_COMPAT)		+= xfs_ioctl32.o
-xfs-$(CONFIG_NFSD_PNFS)		+= xfs_pnfs.o
+xfs-$(CONFIG_NFSD_BLOCKLAYOUT)	+= xfs_pnfs.o
+xfs-$(CONFIG_NFSD_SCSILAYOUT)	+= xfs_pnfs.o
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 444626ddbd1b..d9b42425291e 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -118,8 +118,6 @@ xfs_allocbt_free_block(
 	xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
 			      XFS_EXTENT_BUSY_SKIP_DISCARD);
 	xfs_trans_agbtree_delta(cur->bc_tp, -1);
-
-	xfs_trans_binval(cur->bc_tp, bp);
 	return 0;
 }
 
diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h
index 919756e3ba53..90928bbe693c 100644
--- a/fs/xfs/libxfs/xfs_attr_sf.h
+++ b/fs/xfs/libxfs/xfs_attr_sf.h
@@ -24,22 +24,6 @@
  * Small attribute lists are packed as tightly as possible so as
  * to fit into the literal area of the inode.
  */
-
-/*
- * Entries are packed toward the top as tight as possible.
- */
-typedef struct xfs_attr_shortform {
-	struct xfs_attr_sf_hdr {	/* constant-structure header block */
-		__be16	totsize;	/* total bytes in shortform list */
-		__u8	count;	/* count of active entries */
-	} hdr;
-	struct xfs_attr_sf_entry {
-		__uint8_t namelen;	/* actual length of name (no NULL) */
-		__uint8_t valuelen;	/* actual length of value (no NULL) */
-		__uint8_t flags;	/* flags bits (see xfs_attr_leaf.h) */
-		__uint8_t nameval[1];	/* name & value bytes concatenated */
-	} list[1];			/* variable sized array */
-} xfs_attr_shortform_t;
 typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t;
 typedef struct xfs_attr_sf_entry xfs_attr_sf_entry_t;
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index ef00156f4f96..041b6948aecc 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -477,10 +477,7 @@ xfs_bmap_check_leaf_extents(
 		}
 		block = XFS_BUF_TO_BLOCK(bp);
 	}
-	if (bp_release) {
-		bp_release = 0;
-		xfs_trans_brelse(NULL, bp);
-	}
+
 	return;
 
 error0:
@@ -912,7 +909,7 @@ xfs_bmap_local_to_extents(
 	 * We don't want to deal with the case of keeping inode data inline yet.
 	 * So sending the data fork of a regular inode is invalid.
 	 */
-	ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK));
+	ASSERT(!(S_ISREG(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK));
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
 
@@ -1079,7 +1076,7 @@ xfs_bmap_add_attrfork_local(
 	if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
 		return 0;
 
-	if (S_ISDIR(ip->i_d.di_mode)) {
+	if (S_ISDIR(VFS_I(ip)->i_mode)) {
 		memset(&dargs, 0, sizeof(dargs));
 		dargs.geo = ip->i_mount->m_dir_geo;
 		dargs.dp = ip;
@@ -1091,7 +1088,7 @@ xfs_bmap_add_attrfork_local(
 		return xfs_dir2_sf_to_block(&dargs);
 	}
 
-	if (S_ISLNK(ip->i_d.di_mode))
+	if (S_ISLNK(VFS_I(ip)->i_mode))
 		return xfs_bmap_local_to_extents(tp, ip, firstblock, 1,
 						 flags, XFS_DATA_FORK,
 						 xfs_symlink_local_to_remote);
@@ -4721,6 +4718,66 @@ error0:
 }
 
 /*
+ * When a delalloc extent is split (e.g., due to a hole punch), the original
+ * indlen reservation must be shared across the two new extents that are left
+ * behind.
+ *
+ * Given the original reservation and the worst case indlen for the two new
+ * extents (as calculated by xfs_bmap_worst_indlen()), split the original
+ * reservation fairly across the two new extents. If necessary, steal available
+ * blocks from a deleted extent to make up a reservation deficiency (e.g., if
+ * ores == 1). The number of stolen blocks is returned. The availability and
+ * subsequent accounting of stolen blocks is the responsibility of the caller.
+ */
+static xfs_filblks_t
+xfs_bmap_split_indlen(
+	xfs_filblks_t			ores,		/* original res. */
+	xfs_filblks_t			*indlen1,	/* ext1 worst indlen */
+	xfs_filblks_t			*indlen2,	/* ext2 worst indlen */
+	xfs_filblks_t			avail)		/* stealable blocks */
+{
+	xfs_filblks_t			len1 = *indlen1;
+	xfs_filblks_t			len2 = *indlen2;
+	xfs_filblks_t			nres = len1 + len2; /* new total res. */
+	xfs_filblks_t			stolen = 0;
+
+	/*
+	 * Steal as many blocks as we can to try and satisfy the worst case
+	 * indlen for both new extents.
+	 */
+	while (nres > ores && avail) {
+		nres--;
+		avail--;
+		stolen++;
+	}
+
+	/*
+	 * The only blocks available are those reserved for the original
+	 * extent and what we can steal from the extent being removed.
+	 * If this still isn't enough to satisfy the combined
+	 * requirements for the two new extents, skim blocks off of each
+	 * of the new reservations until they match what is available.
+	 */
+	while (nres > ores) {
+		if (len1) {
+			len1--;
+			nres--;
+		}
+		if (nres == ores)
+			break;
+		if (len2) {
+			len2--;
+			nres--;
+		}
+	}
+
+	*indlen1 = len1;
+	*indlen2 = len2;
+
+	return stolen;
+}
+
+/*
  * Called by xfs_bmapi to update file extent records and the btree
  * after removing space (or undoing a delayed allocation).
  */
@@ -4984,28 +5041,29 @@ xfs_bmap_del_extent(
 			XFS_IFORK_NEXT_SET(ip, whichfork,
 				XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
 		} else {
+			xfs_filblks_t	stolen;
 			ASSERT(whichfork == XFS_DATA_FORK);
-			temp = xfs_bmap_worst_indlen(ip, temp);
+
+			/*
+			 * Distribute the original indlen reservation across the
+			 * two new extents. Steal blocks from the deleted extent
+			 * if necessary. Stealing blocks simply fudges the
+			 * fdblocks accounting in xfs_bunmapi().
+			 */
+			temp = xfs_bmap_worst_indlen(ip, got.br_blockcount);
+			temp2 = xfs_bmap_worst_indlen(ip, new.br_blockcount);
+			stolen = xfs_bmap_split_indlen(da_old, &temp, &temp2,
+						       del->br_blockcount);
+			da_new = temp + temp2 - stolen;
+			del->br_blockcount -= stolen;
+
+			/*
+			 * Set the reservation for each extent. Warn if either
+			 * is zero as this can lead to delalloc problems.
+			 */
+			WARN_ON_ONCE(!temp || !temp2);
 			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			temp2 = xfs_bmap_worst_indlen(ip, temp2);
 			new.br_startblock = nullstartblock((int)temp2);
-			da_new = temp + temp2;
-			while (da_new > da_old) {
-				if (temp) {
-					temp--;
-					da_new--;
-					xfs_bmbt_set_startblock(ep,
-						nullstartblock((int)temp));
-				}
-				if (da_new == da_old)
-					break;
-				if (temp2) {
-					temp2--;
-					da_new--;
-					new.br_startblock =
-						nullstartblock((int)temp2);
-				}
-			}
 		}
 		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 		xfs_iext_insert(ip, *idx + 1, 1, &new, state);
@@ -5210,7 +5268,7 @@ xfs_bunmapi(
 			 * This is better than zeroing it.
 			 */
 			ASSERT(del.br_state == XFS_EXT_NORM);
-			ASSERT(xfs_trans_get_block_res(tp) > 0);
+			ASSERT(tp->t_blk_res > 0);
 			/*
 			 * If this spans a realtime extent boundary,
 			 * chop it back to the start of the one we end at.
@@ -5241,7 +5299,7 @@ xfs_bunmapi(
 				del.br_startblock += mod;
 			} else if ((del.br_startoff == start &&
 				    (del.br_state == XFS_EXT_UNWRITTEN ||
-				     xfs_trans_get_block_res(tp) == 0)) ||
+				     tp->t_blk_res == 0)) ||
 				   !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
 				/*
 				 * Can't make it unwritten.  There isn't
@@ -5296,9 +5354,37 @@ xfs_bunmapi(
 				goto nodelete;
 			}
 		}
+
+		/*
+		 * If it's the case where the directory code is running
+		 * with no block reservation, and the deleted block is in
+		 * the middle of its extent, and the resulting insert
+		 * of an extent would cause transformation to btree format,
+		 * then reject it.  The calling code will then swap
+		 * blocks around instead.
+		 * We have to do this now, rather than waiting for the
+		 * conversion to btree format, since the transaction
+		 * will be dirty.
+		 */
+		if (!wasdel && tp->t_blk_res == 0 &&
+		    XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
+		    XFS_IFORK_NEXTENTS(ip, whichfork) >= /* Note the >= */
+			XFS_IFORK_MAXEXT(ip, whichfork) &&
+		    del.br_startoff > got.br_startoff &&
+		    del.br_startoff + del.br_blockcount <
+		    got.br_startoff + got.br_blockcount) {
+			error = -ENOSPC;
+			goto error0;
+		}
+
+		/*
+		 * Unreserve quota and update realtime free space, if
+		 * appropriate. If delayed allocation, update the inode delalloc
+		 * counter now and wait to update the sb counters as
+		 * xfs_bmap_del_extent() might need to borrow some blocks.
+		 */
 		if (wasdel) {
 			ASSERT(startblockval(del.br_startblock) > 0);
-			/* Update realtime/data freespace, unreserve quota */
 			if (isrt) {
 				xfs_filblks_t rtexts;
 
@@ -5309,8 +5395,6 @@ xfs_bunmapi(
 					ip, -((long)del.br_blockcount), 0,
 					XFS_QMOPT_RES_RTBLKS);
 			} else {
-				xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount,
-						 false);
 				(void)xfs_trans_reserve_quota_nblks(NULL,
 					ip, -((long)del.br_blockcount), 0,
 					XFS_QMOPT_RES_REGBLKS);
@@ -5321,32 +5405,16 @@ xfs_bunmapi(
 					XFS_BTCUR_BPRV_WASDEL;
 		} else if (cur)
 			cur->bc_private.b.flags &= ~XFS_BTCUR_BPRV_WASDEL;
-		/*
-		 * If it's the case where the directory code is running
-		 * with no block reservation, and the deleted block is in
-		 * the middle of its extent, and the resulting insert
-		 * of an extent would cause transformation to btree format,
-		 * then reject it.  The calling code will then swap
-		 * blocks around instead.
-		 * We have to do this now, rather than waiting for the
-		 * conversion to btree format, since the transaction
-		 * will be dirty.
-		 */
-		if (!wasdel && xfs_trans_get_block_res(tp) == 0 &&
-		    XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
-		    XFS_IFORK_NEXTENTS(ip, whichfork) >= /* Note the >= */
-			XFS_IFORK_MAXEXT(ip, whichfork) &&
-		    del.br_startoff > got.br_startoff &&
-		    del.br_startoff + del.br_blockcount <
-		    got.br_startoff + got.br_blockcount) {
-			error = -ENOSPC;
-			goto error0;
-		}
+
 		error = xfs_bmap_del_extent(ip, tp, &lastx, flist, cur, &del,
 				&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 		if (error)
 			goto error0;
+
+		if (!isrt && wasdel)
+			xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false);
+
 		bno = del.br_startoff - 1;
 nodelete:
 		/*
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 1637c37bfbaa..6282f6e708af 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -461,7 +461,7 @@ xfs_bmbt_alloc_block(
 		 * reservation amount is insufficient then we may fail a
 		 * block allocation here and corrupt the filesystem.
 		 */
-		args.minleft = xfs_trans_get_block_res(args.tp);
+		args.minleft = args.tp->t_blk_res;
 	} else if (cur->bc_private.b.flist->xbf_low) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
@@ -470,7 +470,7 @@ xfs_bmbt_alloc_block(
 
 	args.minlen = args.maxlen = args.prod = 1;
 	args.wasdel = cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL;
-	if (!args.wasdel && xfs_trans_get_block_res(args.tp) == 0) {
+	if (!args.wasdel && args.tp->t_blk_res == 0) {
 		error = -ENOSPC;
 		goto error0;
 	}
@@ -531,7 +531,6 @@ xfs_bmbt_free_block(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
-	xfs_trans_binval(tp, bp);
 	return 0;
 }
 
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index a0eb18ce3ad3..1f88e1ce770f 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -294,6 +294,21 @@ xfs_btree_sblock_verify_crc(
 	return true;
 }
 
+static int
+xfs_btree_free_block(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	int			error;
+
+	error = cur->bc_ops->free_block(cur, bp);
+	if (!error) {
+		xfs_trans_binval(cur->bc_tp, bp);
+		XFS_BTREE_STATS_INC(cur, free);
+	}
+	return error;
+}
+
 /*
  * Delete the btree cursor.
  */
@@ -3209,6 +3224,7 @@ xfs_btree_kill_iroot(
 	int			level;
 	int			index;
 	int			numrecs;
+	int			error;
 #ifdef DEBUG
 	union xfs_btree_ptr	ptr;
 	int			i;
@@ -3272,8 +3288,6 @@ xfs_btree_kill_iroot(
 	cpp = xfs_btree_ptr_addr(cur, 1, cblock);
 #ifdef DEBUG
 	for (i = 0; i < numrecs; i++) {
-		int		error;
-
 		error = xfs_btree_check_ptr(cur, cpp, i, level - 1);
 		if (error) {
 			XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
@@ -3283,8 +3297,11 @@ xfs_btree_kill_iroot(
 #endif
 	xfs_btree_copy_ptrs(cur, pp, cpp, numrecs);
 
-	cur->bc_ops->free_block(cur, cbp);
-	XFS_BTREE_STATS_INC(cur, free);
+	error = xfs_btree_free_block(cur, cbp);
+	if (error) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+		return error;
+	}
 
 	cur->bc_bufs[level - 1] = NULL;
 	be16_add_cpu(&block->bb_level, -1);
@@ -3317,14 +3334,12 @@ xfs_btree_kill_root(
 	 */
 	cur->bc_ops->set_root(cur, newroot, -1);
 
-	error = cur->bc_ops->free_block(cur, bp);
+	error = xfs_btree_free_block(cur, bp);
 	if (error) {
 		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
 		return error;
 	}
 
-	XFS_BTREE_STATS_INC(cur, free);
-
 	cur->bc_bufs[level] = NULL;
 	cur->bc_ra[level] = 0;
 	cur->bc_nlevels--;
@@ -3830,10 +3845,9 @@ xfs_btree_delrec(
 	}
 
 	/* Free the deleted block. */
-	error = cur->bc_ops->free_block(cur, rbp);
+	error = xfs_btree_free_block(cur, rbp);
 	if (error)
 		goto error0;
-	XFS_BTREE_STATS_INC(cur, free);
 
 	/*
 	 * If we joined with the left neighbor, set the buffer in the
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index b14bbd6bb05f..8d4d8bce41bf 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -641,6 +641,22 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
  */
 #define XFS_ATTR_LEAF_MAPSIZE	3	/* how many freespace slots */
 
+/*
+ * Entries are packed toward the top as tight as possible.
+ */
+typedef struct xfs_attr_shortform {
+	struct xfs_attr_sf_hdr {	/* constant-structure header block */
+		__be16	totsize;	/* total bytes in shortform list */
+		__u8	count;	/* count of active entries */
+	} hdr;
+	struct xfs_attr_sf_entry {
+		__uint8_t namelen;	/* actual length of name (no NULL) */
+		__uint8_t valuelen;	/* actual length of value (no NULL) */
+		__uint8_t flags;	/* flags bits (see xfs_attr_leaf.h) */
+		__uint8_t nameval[1];	/* name & value bytes concatenated */
+	} list[1];			/* variable sized array */
+} xfs_attr_shortform_t;
+
 typedef struct xfs_attr_leaf_map {	/* RLE map of free bytes */
 	__be16	base;			  /* base of free region */
 	__be16	size;			  /* length of free region */
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 2fb53a5c0a74..af0f9d171f8a 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -176,7 +176,7 @@ xfs_dir_isempty(
 {
 	xfs_dir2_sf_hdr_t	*sfp;
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	if (dp->i_d.di_size == 0)	/* might happen during shutdown. */
 		return 1;
 	if (dp->i_d.di_size > XFS_IFORK_DSIZE(dp))
@@ -231,7 +231,7 @@ xfs_dir_init(
 	struct xfs_da_args *args;
 	int		error;
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	error = xfs_dir_ino_validate(tp->t_mountp, pdp->i_ino);
 	if (error)
 		return error;
@@ -266,7 +266,7 @@ xfs_dir_createname(
 	int			rval;
 	int			v;		/* type-checking value */
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	if (inum) {
 		rval = xfs_dir_ino_validate(tp->t_mountp, inum);
 		if (rval)
@@ -364,7 +364,7 @@ xfs_dir_lookup(
 	int		v;		/* type-checking value */
 	int		lock_mode;
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	XFS_STATS_INC(dp->i_mount, xs_dir_lookup);
 
 	/*
@@ -443,7 +443,7 @@ xfs_dir_removename(
 	int		rval;
 	int		v;		/* type-checking value */
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	XFS_STATS_INC(dp->i_mount, xs_dir_remove);
 
 	args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
@@ -505,7 +505,7 @@ xfs_dir_replace(
 	int		rval;
 	int		v;		/* type-checking value */
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 
 	rval = xfs_dir_ino_validate(tp->t_mountp, inum);
 	if (rval)
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 63ee03db796c..75a557432d0f 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -2235,6 +2235,9 @@ xfs_dir2_node_trim_free(
 
 	dp = args->dp;
 	tp = args->trans;
+
+	*rvalp = 0;
+
 	/*
 	 * Read the freespace block.
 	 */
@@ -2255,7 +2258,6 @@ xfs_dir2_node_trim_free(
 	 */
 	if (freehdr.nused > 0) {
 		xfs_trans_brelse(tp, bp);
-		*rvalp = 0;
 		return 0;
 	}
 	/*
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 66d702e6b9ff..22297f9b0fd5 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2403,8 +2403,8 @@ xfs_ialloc_compute_maxlevels(
 
 	maxleafents = (1LL << XFS_INO_AGINO_BITS(mp)) >>
 		XFS_INODES_PER_CHUNK_LOG;
-	minleafrecs = mp->m_alloc_mnr[0];
-	minnoderecs = mp->m_alloc_mnr[1];
+	minleafrecs = mp->m_inobt_mnr[0];
+	minnoderecs = mp->m_inobt_mnr[1];
 	maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
 	for (level = 1; maxblocks > 1; level++)
 		maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index c679f3c05b63..89c21d771e35 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -125,16 +125,8 @@ xfs_inobt_free_block(
 	struct xfs_btree_cur	*cur,
 	struct xfs_buf		*bp)
 {
-	xfs_fsblock_t		fsbno;
-	int			error;
-
-	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp));
-	error = xfs_free_extent(cur->bc_tp, fsbno, 1);
-	if (error)
-		return error;
-
-	xfs_trans_binval(cur->bc_tp, bp);
-	return error;
+	return xfs_free_extent(cur->bc_tp,
+			XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1);
 }
 
 STATIC int
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 1aabfda669b0..9d9559eb2835 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -195,28 +195,50 @@ xfs_imap_to_bp(
 }
 
 void
-xfs_dinode_from_disk(
-	xfs_icdinode_t		*to,
-	xfs_dinode_t		*from)
+xfs_inode_from_disk(
+	struct xfs_inode	*ip,
+	struct xfs_dinode	*from)
 {
-	to->di_magic = be16_to_cpu(from->di_magic);
-	to->di_mode = be16_to_cpu(from->di_mode);
-	to->di_version = from ->di_version;
+	struct xfs_icdinode	*to = &ip->i_d;
+	struct inode		*inode = VFS_I(ip);
+
+
+	/*
+	 * Convert v1 inodes immediately to v2 inode format as this is the
+	 * minimum inode version format we support in the rest of the code.
+	 */
+	to->di_version = from->di_version;
+	if (to->di_version == 1) {
+		set_nlink(inode, be16_to_cpu(from->di_onlink));
+		to->di_projid_lo = 0;
+		to->di_projid_hi = 0;
+		to->di_version = 2;
+	} else {
+		set_nlink(inode, be32_to_cpu(from->di_nlink));
+		to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
+		to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
+	}
+
 	to->di_format = from->di_format;
-	to->di_onlink = be16_to_cpu(from->di_onlink);
 	to->di_uid = be32_to_cpu(from->di_uid);
 	to->di_gid = be32_to_cpu(from->di_gid);
-	to->di_nlink = be32_to_cpu(from->di_nlink);
-	to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
-	to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
-	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
 	to->di_flushiter = be16_to_cpu(from->di_flushiter);
-	to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec);
-	to->di_atime.t_nsec = be32_to_cpu(from->di_atime.t_nsec);
-	to->di_mtime.t_sec = be32_to_cpu(from->di_mtime.t_sec);
-	to->di_mtime.t_nsec = be32_to_cpu(from->di_mtime.t_nsec);
-	to->di_ctime.t_sec = be32_to_cpu(from->di_ctime.t_sec);
-	to->di_ctime.t_nsec = be32_to_cpu(from->di_ctime.t_nsec);
+
+	/*
+	 * Time is signed, so need to convert to signed 32 bit before
+	 * storing in inode timestamp which may be 64 bit. Otherwise
+	 * a time before epoch is converted to a time long after epoch
+	 * on 64 bit systems.
+	 */
+	inode->i_atime.tv_sec = (int)be32_to_cpu(from->di_atime.t_sec);
+	inode->i_atime.tv_nsec = (int)be32_to_cpu(from->di_atime.t_nsec);
+	inode->i_mtime.tv_sec = (int)be32_to_cpu(from->di_mtime.t_sec);
+	inode->i_mtime.tv_nsec = (int)be32_to_cpu(from->di_mtime.t_nsec);
+	inode->i_ctime.tv_sec = (int)be32_to_cpu(from->di_ctime.t_sec);
+	inode->i_ctime.tv_nsec = (int)be32_to_cpu(from->di_ctime.t_nsec);
+	inode->i_generation = be32_to_cpu(from->di_gen);
+	inode->i_mode = be16_to_cpu(from->di_mode);
+
 	to->di_size = be64_to_cpu(from->di_size);
 	to->di_nblocks = be64_to_cpu(from->di_nblocks);
 	to->di_extsize = be32_to_cpu(from->di_extsize);
@@ -227,42 +249,96 @@ xfs_dinode_from_disk(
 	to->di_dmevmask	= be32_to_cpu(from->di_dmevmask);
 	to->di_dmstate	= be16_to_cpu(from->di_dmstate);
 	to->di_flags	= be16_to_cpu(from->di_flags);
-	to->di_gen	= be32_to_cpu(from->di_gen);
 
 	if (to->di_version == 3) {
-		to->di_changecount = be64_to_cpu(from->di_changecount);
+		inode->i_version = be64_to_cpu(from->di_changecount);
 		to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
 		to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
 		to->di_flags2 = be64_to_cpu(from->di_flags2);
-		to->di_ino = be64_to_cpu(from->di_ino);
-		to->di_lsn = be64_to_cpu(from->di_lsn);
-		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
-		uuid_copy(&to->di_uuid, &from->di_uuid);
 	}
 }
 
 void
-xfs_dinode_to_disk(
-	xfs_dinode_t		*to,
-	xfs_icdinode_t		*from)
+xfs_inode_to_disk(
+	struct xfs_inode	*ip,
+	struct xfs_dinode	*to,
+	xfs_lsn_t		lsn)
+{
+	struct xfs_icdinode	*from = &ip->i_d;
+	struct inode		*inode = VFS_I(ip);
+
+	to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+	to->di_onlink = 0;
+
+	to->di_version = from->di_version;
+	to->di_format = from->di_format;
+	to->di_uid = cpu_to_be32(from->di_uid);
+	to->di_gid = cpu_to_be32(from->di_gid);
+	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
+	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
+
+	memset(to->di_pad, 0, sizeof(to->di_pad));
+	to->di_atime.t_sec = cpu_to_be32(inode->i_atime.tv_sec);
+	to->di_atime.t_nsec = cpu_to_be32(inode->i_atime.tv_nsec);
+	to->di_mtime.t_sec = cpu_to_be32(inode->i_mtime.tv_sec);
+	to->di_mtime.t_nsec = cpu_to_be32(inode->i_mtime.tv_nsec);
+	to->di_ctime.t_sec = cpu_to_be32(inode->i_ctime.tv_sec);
+	to->di_ctime.t_nsec = cpu_to_be32(inode->i_ctime.tv_nsec);
+	to->di_nlink = cpu_to_be32(inode->i_nlink);
+	to->di_gen = cpu_to_be32(inode->i_generation);
+	to->di_mode = cpu_to_be16(inode->i_mode);
+
+	to->di_size = cpu_to_be64(from->di_size);
+	to->di_nblocks = cpu_to_be64(from->di_nblocks);
+	to->di_extsize = cpu_to_be32(from->di_extsize);
+	to->di_nextents = cpu_to_be32(from->di_nextents);
+	to->di_anextents = cpu_to_be16(from->di_anextents);
+	to->di_forkoff = from->di_forkoff;
+	to->di_aformat = from->di_aformat;
+	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
+	to->di_dmstate = cpu_to_be16(from->di_dmstate);
+	to->di_flags = cpu_to_be16(from->di_flags);
+
+	if (from->di_version == 3) {
+		to->di_changecount = cpu_to_be64(inode->i_version);
+		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
+		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
+		to->di_flags2 = cpu_to_be64(from->di_flags2);
+
+		to->di_ino = cpu_to_be64(ip->i_ino);
+		to->di_lsn = cpu_to_be64(lsn);
+		memset(to->di_pad2, 0, sizeof(to->di_pad2));
+		uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
+		to->di_flushiter = 0;
+	} else {
+		to->di_flushiter = cpu_to_be16(from->di_flushiter);
+	}
+}
+
+void
+xfs_log_dinode_to_disk(
+	struct xfs_log_dinode	*from,
+	struct xfs_dinode	*to)
 {
 	to->di_magic = cpu_to_be16(from->di_magic);
 	to->di_mode = cpu_to_be16(from->di_mode);
-	to->di_version = from ->di_version;
+	to->di_version = from->di_version;
 	to->di_format = from->di_format;
-	to->di_onlink = cpu_to_be16(from->di_onlink);
+	to->di_onlink = 0;
 	to->di_uid = cpu_to_be32(from->di_uid);
 	to->di_gid = cpu_to_be32(from->di_gid);
 	to->di_nlink = cpu_to_be32(from->di_nlink);
 	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
 	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
 	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
+
 	to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
 	to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
 	to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
 	to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec);
 	to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec);
 	to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec);
+
 	to->di_size = cpu_to_be64(from->di_size);
 	to->di_nblocks = cpu_to_be64(from->di_nblocks);
 	to->di_extsize = cpu_to_be32(from->di_extsize);
@@ -367,13 +443,10 @@ xfs_iread(
 	    !(mp->m_flags & XFS_MOUNT_IKEEP)) {
 		/* initialise the on-disk inode core */
 		memset(&ip->i_d, 0, sizeof(ip->i_d));
-		ip->i_d.di_magic = XFS_DINODE_MAGIC;
-		ip->i_d.di_gen = prandom_u32();
-		if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		VFS_I(ip)->i_generation = prandom_u32();
+		if (xfs_sb_version_hascrc(&mp->m_sb))
 			ip->i_d.di_version = 3;
-			ip->i_d.di_ino = ip->i_ino;
-			uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_meta_uuid);
-		} else
+		else
 			ip->i_d.di_version = 2;
 		return 0;
 	}
@@ -403,7 +476,7 @@ xfs_iread(
 	 * Otherwise, just get the truly permanent information.
 	 */
 	if (dip->di_mode) {
-		xfs_dinode_from_disk(&ip->i_d, dip);
+		xfs_inode_from_disk(ip, dip);
 		error = xfs_iformat_fork(ip, dip);
 		if (error)  {
 #ifdef DEBUG
@@ -417,16 +490,10 @@ xfs_iread(
 		 * Partial initialisation of the in-core inode. Just the bits
 		 * that xfs_ialloc won't overwrite or relies on being correct.
 		 */
-		ip->i_d.di_magic = be16_to_cpu(dip->di_magic);
 		ip->i_d.di_version = dip->di_version;
-		ip->i_d.di_gen = be32_to_cpu(dip->di_gen);
+		VFS_I(ip)->i_generation = be32_to_cpu(dip->di_gen);
 		ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);
 
-		if (dip->di_version == 3) {
-			ip->i_d.di_ino = be64_to_cpu(dip->di_ino);
-			uuid_copy(&ip->i_d.di_uuid, &dip->di_uuid);
-		}
-
 		/*
 		 * Make sure to pull in the mode here as well in
 		 * case the inode is released without being used.
@@ -434,25 +501,10 @@ xfs_iread(
 		 * the inode is already free and not try to mess
 		 * with the uninitialized part of it.
 		 */
-		ip->i_d.di_mode = 0;
-	}
-
-	/*
-	 * Automatically convert version 1 inode formats in memory to version 2
-	 * inode format. If the inode is modified, it will get logged and
-	 * rewritten as a version 2 inode. We can do this because we set the
-	 * superblock feature bit for v2 inodes unconditionally during mount
-	 * and it means the reast of the code can assume the inode version is 2
-	 * or higher.
-	 */
-	if (ip->i_d.di_version == 1) {
-		ip->i_d.di_version = 2;
-		memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
-		ip->i_d.di_nlink = ip->i_d.di_onlink;
-		ip->i_d.di_onlink = 0;
-		xfs_set_projid(ip, 0);
+		VFS_I(ip)->i_mode = 0;
 	}
 
+	ASSERT(ip->i_d.di_version >= 2);
 	ip->i_delayed_blks = 0;
 
 	/*
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 9308c47f2a52..7c4dd321b215 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -20,7 +20,36 @@
 
 struct xfs_inode;
 struct xfs_dinode;
-struct xfs_icdinode;
+
+/*
+ * In memory representation of the XFS inode. This is held in the in-core struct
+ * xfs_inode and represents the current on disk values but the structure is not
+ * in on-disk format.  That is, this structure is always translated to on-disk
+ * format specific structures at the appropriate time.
+ */
+struct xfs_icdinode {
+	__int8_t	di_version;	/* inode version */
+	__int8_t	di_format;	/* format of di_c data */
+	__uint16_t	di_flushiter;	/* incremented on flush */
+	__uint32_t	di_uid;		/* owner's user id */
+	__uint32_t	di_gid;		/* owner's group id */
+	__uint16_t	di_projid_lo;	/* lower part of owner's project id */
+	__uint16_t	di_projid_hi;	/* higher part of owner's project id */
+	xfs_fsize_t	di_size;	/* number of bytes in file */
+	xfs_rfsblock_t	di_nblocks;	/* # of direct & btree blocks used */
+	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
+	xfs_extnum_t	di_nextents;	/* number of extents in data fork */
+	xfs_aextnum_t	di_anextents;	/* number of extents in attribute fork*/
+	__uint8_t	di_forkoff;	/* attr fork offs, <<3 for 64b align */
+	__int8_t	di_aformat;	/* format of attr fork's data */
+	__uint32_t	di_dmevmask;	/* DMIG event mask */
+	__uint16_t	di_dmstate;	/* DMIG state info */
+	__uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
+
+	__uint64_t	di_flags2;	/* more random flags */
+
+	xfs_ictimestamp_t di_crtime;	/* time created */
+};
 
 /*
  * Inode location information.  Stored in the inode and passed to
@@ -38,8 +67,11 @@ int	xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
 int	xfs_iread(struct xfs_mount *, struct xfs_trans *,
 		  struct xfs_inode *, uint);
 void	xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
-void	xfs_dinode_to_disk(struct xfs_dinode *to, struct xfs_icdinode *from);
-void	xfs_dinode_from_disk(struct xfs_icdinode *to, struct xfs_dinode *from);
+void	xfs_inode_to_disk(struct xfs_inode *ip, struct xfs_dinode *to,
+			  xfs_lsn_t lsn);
+void	xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
+void	xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
+			       struct xfs_dinode *to);
 
 #if defined(DEBUG)
 void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 0defbd02f62d..11faf7df14c8 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -31,6 +31,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_attr_sf.h"
+#include "xfs_da_format.h"
 
 kmem_zone_t *xfs_ifork_zone;
 
@@ -120,7 +121,7 @@ xfs_iformat_fork(
 		return -EFSCORRUPTED;
 	}
 
-	switch (ip->i_d.di_mode & S_IFMT) {
+	switch (VFS_I(ip)->i_mode & S_IFMT) {
 	case S_IFIFO:
 	case S_IFCHR:
 	case S_IFBLK:
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 265314690415..d54a8018b079 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -290,6 +290,7 @@ typedef struct xfs_inode_log_format_64 {
 	__int32_t		ilf_boffset;	/* off of inode in buffer */
 } xfs_inode_log_format_64_t;
 
+
 /*
  * Flags for xfs_trans_log_inode flags field.
  */
@@ -360,15 +361,15 @@ typedef struct xfs_ictimestamp {
 } xfs_ictimestamp_t;
 
 /*
- * NOTE:  This structure must be kept identical to struct xfs_dinode
- *	  except for the endianness annotations.
+ * Define the format of the inode core that is logged. This structure must be
+ * kept identical to struct xfs_dinode except for the endianness annotations.
  */
-typedef struct xfs_icdinode {
+struct xfs_log_dinode {
 	__uint16_t	di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
 	__uint16_t	di_mode;	/* mode and type of file */
 	__int8_t	di_version;	/* inode version */
 	__int8_t	di_format;	/* format of di_c data */
-	__uint16_t	di_onlink;	/* old number of links to file */
+	__uint8_t	di_pad3[2];	/* unused in v2/3 inodes */
 	__uint32_t	di_uid;		/* owner's user id */
 	__uint32_t	di_gid;		/* owner's group id */
 	__uint32_t	di_nlink;	/* number of links to file */
@@ -407,13 +408,13 @@ typedef struct xfs_icdinode {
 	uuid_t		di_uuid;	/* UUID of the filesystem */
 
 	/* structure must be padded to 64 bit alignment */
-} xfs_icdinode_t;
+};
 
-static inline uint xfs_icdinode_size(int version)
+static inline uint xfs_log_dinode_size(int version)
 {
 	if (version == 3)
-		return sizeof(struct xfs_icdinode);
-	return offsetof(struct xfs_icdinode, di_next_unlinked);
+		return sizeof(struct xfs_log_dinode);
+	return offsetof(struct xfs_log_dinode, di_next_unlinked);
 }
 
 /*
@@ -495,6 +496,8 @@ enum xfs_blft {
 	XFS_BLFT_ATTR_LEAF_BUF,
 	XFS_BLFT_ATTR_RMT_BUF,
 	XFS_BLFT_SB_BUF,
+	XFS_BLFT_RTBITMAP_BUF,
+	XFS_BLFT_RTSUMMARY_BUF,
 	XFS_BLFT_MAX_BUF = (1 << XFS_BLFT_BITS),
 };
 
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index f51078f1e92a..8eed51275bb3 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -37,7 +37,7 @@ typedef __uint16_t	xfs_qwarncnt_t;
 #define XFS_DQ_PROJ		0x0002		/* project quota */
 #define XFS_DQ_GROUP		0x0004		/* a group quota */
 #define XFS_DQ_DIRTY		0x0008		/* dquot is dirty */
-#define XFS_DQ_FREEING		0x0010		/* dquot is beeing torn down */
+#define XFS_DQ_FREEING		0x0010		/* dquot is being torn down */
 
 #define XFS_DQ_ALLTYPES		(XFS_DQ_USER|XFS_DQ_PROJ|XFS_DQ_GROUP)
 
@@ -116,6 +116,7 @@ typedef __uint16_t	xfs_qwarncnt_t;
 #define XFS_QMOPT_DQREPAIR	0x0001000 /* repair dquot if damaged */
 #define XFS_QMOPT_GQUOTA	0x0002000 /* group dquot requested */
 #define XFS_QMOPT_ENOSPC	0x0004000 /* enospc instead of edquot (prj) */
+#define XFS_QMOPT_DQNEXT	0x0008000 /* return next dquot >= this ID */
 
 /*
  * flags to xfs_trans_mod_dquot to indicate which field needs to be
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 9b59ffa1fc19..951c044e24e4 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -42,6 +42,31 @@
  */
 
 /*
+ * Real time buffers need verifiers to avoid runtime warnings during IO.
+ * We don't have anything to verify, however, so these are just dummy
+ * operations.
+ */
+static void
+xfs_rtbuf_verify_read(
+	struct xfs_buf	*bp)
+{
+	return;
+}
+
+static void
+xfs_rtbuf_verify_write(
+	struct xfs_buf	*bp)
+{
+	return;
+}
+
+const struct xfs_buf_ops xfs_rtbuf_ops = {
+	.name = "rtbuf",
+	.verify_read = xfs_rtbuf_verify_read,
+	.verify_write = xfs_rtbuf_verify_write,
+};
+
+/*
  * Get a buffer for the bitmap or summary file block specified.
  * The buffer is returned read and locked.
  */
@@ -68,9 +93,12 @@ xfs_rtbuf_get(
 	ASSERT(map.br_startblock != NULLFSBLOCK);
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 				   XFS_FSB_TO_DADDR(mp, map.br_startblock),
-				   mp->m_bsize, 0, &bp, NULL);
+				   mp->m_bsize, 0, &bp, &xfs_rtbuf_ops);
 	if (error)
 		return error;
+
+	xfs_trans_buf_set_type(tp, bp, issum ? XFS_BLFT_RTSUMMARY_BUF
+					     : XFS_BLFT_RTBITMAP_BUF);
 	*bpp = bp;
 	return 0;
 }
@@ -983,7 +1011,7 @@ xfs_rtfree_extent(
 	    mp->m_sb.sb_rextents) {
 		if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
 			mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
-		*(__uint64_t *)&mp->m_rbmip->i_d.di_atime = 0;
+		*(__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0;
 		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
 	}
 	return 0;
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index b25bb9a343f3..961e6475a309 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -27,7 +27,6 @@ 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 *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);
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 15c3ceb845b9..81ac870834da 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -53,6 +53,7 @@ extern const struct xfs_buf_ops xfs_dquot_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_sb_buf_ops;
 extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
 extern const struct xfs_buf_ops xfs_symlink_buf_ops;
+extern const struct xfs_buf_ops xfs_rtbuf_ops;
 
 /*
  * Transaction types.  Used to distinguish types of buffers. These never reach
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 379c089fb051..d445a64b979e 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -36,6 +36,21 @@
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
 
+/* flags for direct write completions */
+#define XFS_DIO_FLAG_UNWRITTEN	(1 << 0)
+#define XFS_DIO_FLAG_APPEND	(1 << 1)
+
+/*
+ * structure owned by writepages passed to individual writepage calls
+ */
+struct xfs_writepage_ctx {
+	struct xfs_bmbt_irec    imap;
+	bool			imap_valid;
+	unsigned int		io_type;
+	struct xfs_ioend	*ioend;
+	sector_t		last_block;
+};
+
 void
 xfs_count_page_state(
 	struct page		*page,
@@ -55,7 +70,7 @@ xfs_count_page_state(
 	} while ((bh = bh->b_this_page) != head);
 }
 
-STATIC struct block_device *
+struct block_device *
 xfs_find_bdev_for_inode(
 	struct inode		*inode)
 {
@@ -214,10 +229,12 @@ xfs_end_io(
 	struct xfs_inode *ip = XFS_I(ioend->io_inode);
 	int		error = 0;
 
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+	/*
+	 * Set an error if the mount has shut down and proceed with end I/O
+	 * processing so it can perform whatever cleanups are necessary.
+	 */
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		ioend->io_error = -EIO;
-		goto done;
-	}
 
 	/*
 	 * For unwritten extents we need to issue transactions to convert a
@@ -265,7 +282,7 @@ xfs_alloc_ioend(
 	 */
 	atomic_set(&ioend->io_remaining, 1);
 	ioend->io_error = 0;
-	ioend->io_list = NULL;
+	INIT_LIST_HEAD(&ioend->io_list);
 	ioend->io_type = type;
 	ioend->io_inode = inode;
 	ioend->io_buffer_head = NULL;
@@ -283,8 +300,7 @@ xfs_map_blocks(
 	struct inode		*inode,
 	loff_t			offset,
 	struct xfs_bmbt_irec	*imap,
-	int			type,
-	int			nonblocking)
+	int			type)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -300,12 +316,7 @@ xfs_map_blocks(
 	if (type == XFS_IO_UNWRITTEN)
 		bmapi_flags |= XFS_BMAPI_IGSTATE;
 
-	if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
-		if (nonblocking)
-			return -EAGAIN;
-		xfs_ilock(ip, XFS_ILOCK_SHARED);
-	}
-
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
 	ASSERT(offset <= mp->m_super->s_maxbytes);
@@ -341,7 +352,7 @@ xfs_map_blocks(
 	return 0;
 }
 
-STATIC int
+STATIC bool
 xfs_imap_valid(
 	struct inode		*inode,
 	struct xfs_bmbt_irec	*imap,
@@ -414,8 +425,7 @@ xfs_start_buffer_writeback(
 STATIC void
 xfs_start_page_writeback(
 	struct page		*page,
-	int			clear_dirty,
-	int			buffers)
+	int			clear_dirty)
 {
 	ASSERT(PageLocked(page));
 	ASSERT(!PageWriteback(page));
@@ -434,10 +444,6 @@ xfs_start_page_writeback(
 		set_page_writeback_keepwrite(page);
 
 	unlock_page(page);
-
-	/* If no buffers on the page are to be written, finish it here */
-	if (!buffers)
-		end_page_writeback(page);
 }
 
 static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
@@ -446,153 +452,101 @@ static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
 }
 
 /*
- * Submit all of the bios for all of the ioends we have saved up, covering the
- * initial writepage page and also any probed pages.
- *
- * Because we may have multiple ioends spanning a page, we need to start
- * writeback on all the buffers before we submit them for I/O. If we mark the
- * buffers as we got, then we can end up with a page that only has buffers
- * marked async write and I/O complete on can occur before we mark the other
- * buffers async write.
- *
- * The end result of this is that we trip a bug in end_page_writeback() because
- * we call it twice for the one page as the code in end_buffer_async_write()
- * assumes that all buffers on the page are started at the same time.
- *
- * The fix is two passes across the ioend list - one to start writeback on the
- * buffer_heads, and then submit them for I/O on the second pass.
+ * Submit all of the bios for an ioend. We are only passed a single ioend at a
+ * time; the caller is responsible for chaining prior to submission.
  *
  * If @fail is non-zero, it means that we have a situation where some part of
  * the submission process has failed after we have marked paged for writeback
  * and unlocked them. In this situation, we need to fail the ioend chain rather
  * than submit it to IO. This typically only happens on a filesystem shutdown.
  */
-STATIC void
+STATIC int
 xfs_submit_ioend(
 	struct writeback_control *wbc,
 	xfs_ioend_t		*ioend,
-	int			fail)
+	int			status)
 {
-	xfs_ioend_t		*head = ioend;
-	xfs_ioend_t		*next;
 	struct buffer_head	*bh;
 	struct bio		*bio;
 	sector_t		lastblock = 0;
 
-	/* Pass 1 - start writeback */
-	do {
-		next = ioend->io_list;
-		for (bh = ioend->io_buffer_head; bh; bh = bh->b_private)
-			xfs_start_buffer_writeback(bh);
-	} while ((ioend = next) != NULL);
+	/* Reserve log space if we might write beyond the on-disk inode size. */
+	if (!status &&
+	     ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend))
+		status = xfs_setfilesize_trans_alloc(ioend);
+	/*
+	 * If we are failing the IO now, just mark the ioend with an
+	 * error and finish it. This will run IO completion immediately
+	 * as there is only one reference to the ioend at this point in
+	 * time.
+	 */
+	if (status) {
+		ioend->io_error = status;
+		xfs_finish_ioend(ioend);
+		return status;
+	}
 
-	/* Pass 2 - submit I/O */
-	ioend = head;
-	do {
-		next = ioend->io_list;
-		bio = NULL;
+	bio = NULL;
+	for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) {
 
-		/*
-		 * If we are failing the IO now, just mark the ioend with an
-		 * error and finish it. This will run IO completion immediately
-		 * as there is only one reference to the ioend at this point in
-		 * time.
-		 */
-		if (fail) {
-			ioend->io_error = fail;
-			xfs_finish_ioend(ioend);
-			continue;
+		if (!bio) {
+retry:
+			bio = xfs_alloc_ioend_bio(bh);
+		} else if (bh->b_blocknr != lastblock + 1) {
+			xfs_submit_ioend_bio(wbc, ioend, bio);
+			goto retry;
 		}
 
-		for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) {
-
-			if (!bio) {
- retry:
-				bio = xfs_alloc_ioend_bio(bh);
-			} else if (bh->b_blocknr != lastblock + 1) {
-				xfs_submit_ioend_bio(wbc, ioend, bio);
-				goto retry;
-			}
-
-			if (xfs_bio_add_buffer(bio, bh) != bh->b_size) {
-				xfs_submit_ioend_bio(wbc, ioend, bio);
-				goto retry;
-			}
-
-			lastblock = bh->b_blocknr;
-		}
-		if (bio)
+		if (xfs_bio_add_buffer(bio, bh) != bh->b_size) {
 			xfs_submit_ioend_bio(wbc, ioend, bio);
-		xfs_finish_ioend(ioend);
-	} while ((ioend = next) != NULL);
-}
-
-/*
- * Cancel submission of all buffer_heads so far in this endio.
- * Toss the endio too.  Only ever called for the initial page
- * in a writepage request, so only ever one page.
- */
-STATIC void
-xfs_cancel_ioend(
-	xfs_ioend_t		*ioend)
-{
-	xfs_ioend_t		*next;
-	struct buffer_head	*bh, *next_bh;
-
-	do {
-		next = ioend->io_list;
-		bh = ioend->io_buffer_head;
-		do {
-			next_bh = bh->b_private;
-			clear_buffer_async_write(bh);
-			/*
-			 * The unwritten flag is cleared when added to the
-			 * ioend. We're not submitting for I/O so mark the
-			 * buffer unwritten again for next time around.
-			 */
-			if (ioend->io_type == XFS_IO_UNWRITTEN)
-				set_buffer_unwritten(bh);
-			unlock_buffer(bh);
-		} while ((bh = next_bh) != NULL);
+			goto retry;
+		}
 
-		mempool_free(ioend, xfs_ioend_pool);
-	} while ((ioend = next) != NULL);
+		lastblock = bh->b_blocknr;
+	}
+	if (bio)
+		xfs_submit_ioend_bio(wbc, ioend, bio);
+	xfs_finish_ioend(ioend);
+	return 0;
 }
 
 /*
  * Test to see if we've been building up a completion structure for
  * earlier buffers -- if so, we try to append to this ioend if we
  * can, otherwise we finish off any current ioend and start another.
- * Return true if we've finished the given ioend.
+ * Return the ioend we finished off so that the caller can submit it
+ * once it has finished processing the dirty page.
  */
 STATIC void
 xfs_add_to_ioend(
 	struct inode		*inode,
 	struct buffer_head	*bh,
 	xfs_off_t		offset,
-	unsigned int		type,
-	xfs_ioend_t		**result,
-	int			need_ioend)
+	struct xfs_writepage_ctx *wpc,
+	struct list_head	*iolist)
 {
-	xfs_ioend_t		*ioend = *result;
-
-	if (!ioend || need_ioend || type != ioend->io_type) {
-		xfs_ioend_t	*previous = *result;
-
-		ioend = xfs_alloc_ioend(inode, type);
-		ioend->io_offset = offset;
-		ioend->io_buffer_head = bh;
-		ioend->io_buffer_tail = bh;
-		if (previous)
-			previous->io_list = ioend;
-		*result = ioend;
+	if (!wpc->ioend || wpc->io_type != wpc->ioend->io_type ||
+	    bh->b_blocknr != wpc->last_block + 1 ||
+	    offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
+		struct xfs_ioend	*new;
+
+		if (wpc->ioend)
+			list_add(&wpc->ioend->io_list, iolist);
+
+		new = xfs_alloc_ioend(inode, wpc->io_type);
+		new->io_offset = offset;
+		new->io_buffer_head = bh;
+		new->io_buffer_tail = bh;
+		wpc->ioend = new;
 	} else {
-		ioend->io_buffer_tail->b_private = bh;
-		ioend->io_buffer_tail = bh;
+		wpc->ioend->io_buffer_tail->b_private = bh;
+		wpc->ioend->io_buffer_tail = bh;
 	}
 
 	bh->b_private = NULL;
-	ioend->io_size += bh->b_size;
+	wpc->ioend->io_size += bh->b_size;
+	wpc->last_block = bh->b_blocknr;
+	xfs_start_buffer_writeback(bh);
 }
 
 STATIC void
@@ -678,183 +632,6 @@ xfs_check_page_type(
 	return false;
 }
 
-/*
- * Allocate & map buffers for page given the extent map. Write it out.
- * except for the original page of a writepage, this is called on
- * delalloc/unwritten pages only, for the original page it is possible
- * that the page has no mapping at all.
- */
-STATIC int
-xfs_convert_page(
-	struct inode		*inode,
-	struct page		*page,
-	loff_t			tindex,
-	struct xfs_bmbt_irec	*imap,
-	xfs_ioend_t		**ioendp,
-	struct writeback_control *wbc)
-{
-	struct buffer_head	*bh, *head;
-	xfs_off_t		end_offset;
-	unsigned long		p_offset;
-	unsigned int		type;
-	int			len, page_dirty;
-	int			count = 0, done = 0, uptodate = 1;
- 	xfs_off_t		offset = page_offset(page);
-
-	if (page->index != tindex)
-		goto fail;
-	if (!trylock_page(page))
-		goto fail;
-	if (PageWriteback(page))
-		goto fail_unlock_page;
-	if (page->mapping != inode->i_mapping)
-		goto fail_unlock_page;
-	if (!xfs_check_page_type(page, (*ioendp)->io_type, false))
-		goto fail_unlock_page;
-
-	/*
-	 * page_dirty is initially a count of buffers on the page before
-	 * EOF and is decremented as we move each into a cleanable state.
-	 *
-	 * Derivation:
-	 *
-	 * End offset is the highest offset that this page should represent.
-	 * If we are on the last page, (end_offset & (PAGE_CACHE_SIZE - 1))
-	 * will evaluate non-zero and be less than PAGE_CACHE_SIZE and
-	 * hence give us the correct page_dirty count. On any other page,
-	 * it will be zero and in that case we need page_dirty to be the
-	 * count of buffers on the page.
-	 */
-	end_offset = min_t(unsigned long long,
-			(xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
-			i_size_read(inode));
-
-	/*
-	 * If the current map does not span the entire page we are about to try
-	 * to write, then give up. The only way we can write a page that spans
-	 * multiple mappings in a single writeback iteration is via the
-	 * xfs_vm_writepage() function. Data integrity writeback requires the
-	 * entire page to be written in a single attempt, otherwise the part of
-	 * the page we don't write here doesn't get written as part of the data
-	 * integrity sync.
-	 *
-	 * For normal writeback, we also don't attempt to write partial pages
-	 * here as it simply means that write_cache_pages() will see it under
-	 * writeback and ignore the page until some point in the future, at
-	 * which time this will be the only page in the file that needs
-	 * writeback.  Hence for more optimal IO patterns, we should always
-	 * avoid partial page writeback due to multiple mappings on a page here.
-	 */
-	if (!xfs_imap_valid(inode, imap, end_offset))
-		goto fail_unlock_page;
-
-	len = 1 << inode->i_blkbits;
-	p_offset = min_t(unsigned long, end_offset & (PAGE_CACHE_SIZE - 1),
-					PAGE_CACHE_SIZE);
-	p_offset = p_offset ? roundup(p_offset, len) : PAGE_CACHE_SIZE;
-	page_dirty = p_offset / len;
-
-	/*
-	 * The moment we find a buffer that doesn't match our current type
-	 * specification or can't be written, abort the loop and start
-	 * writeback. As per the above xfs_imap_valid() check, only
-	 * xfs_vm_writepage() can handle partial page writeback fully - we are
-	 * limited here to the buffers that are contiguous with the current
-	 * ioend, and hence a buffer we can't write breaks that contiguity and
-	 * we have to defer the rest of the IO to xfs_vm_writepage().
-	 */
-	bh = head = page_buffers(page);
-	do {
-		if (offset >= end_offset)
-			break;
-		if (!buffer_uptodate(bh))
-			uptodate = 0;
-		if (!(PageUptodate(page) || buffer_uptodate(bh))) {
-			done = 1;
-			break;
-		}
-
-		if (buffer_unwritten(bh) || buffer_delay(bh) ||
-		    buffer_mapped(bh)) {
-			if (buffer_unwritten(bh))
-				type = XFS_IO_UNWRITTEN;
-			else if (buffer_delay(bh))
-				type = XFS_IO_DELALLOC;
-			else
-				type = XFS_IO_OVERWRITE;
-
-			/*
-			 * imap should always be valid because of the above
-			 * partial page end_offset check on the imap.
-			 */
-			ASSERT(xfs_imap_valid(inode, imap, offset));
-
-			lock_buffer(bh);
-			if (type != XFS_IO_OVERWRITE)
-				xfs_map_at_offset(inode, bh, imap, offset);
-			xfs_add_to_ioend(inode, bh, offset, type,
-					 ioendp, done);
-
-			page_dirty--;
-			count++;
-		} else {
-			done = 1;
-			break;
-		}
-	} while (offset += len, (bh = bh->b_this_page) != head);
-
-	if (uptodate && bh == head)
-		SetPageUptodate(page);
-
-	if (count) {
-		if (--wbc->nr_to_write <= 0 &&
-		    wbc->sync_mode == WB_SYNC_NONE)
-			done = 1;
-	}
-	xfs_start_page_writeback(page, !page_dirty, count);
-
-	return done;
- fail_unlock_page:
-	unlock_page(page);
- fail:
-	return 1;
-}
-
-/*
- * Convert & write out a cluster of pages in the same extent as defined
- * by mp and following the start page.
- */
-STATIC void
-xfs_cluster_write(
-	struct inode		*inode,
-	pgoff_t			tindex,
-	struct xfs_bmbt_irec	*imap,
-	xfs_ioend_t		**ioendp,
-	struct writeback_control *wbc,
-	pgoff_t			tlast)
-{
-	struct pagevec		pvec;
-	int			done = 0, i;
-
-	pagevec_init(&pvec, 0);
-	while (!done && tindex <= tlast) {
-		unsigned len = min_t(pgoff_t, PAGEVEC_SIZE, tlast - tindex + 1);
-
-		if (!pagevec_lookup(&pvec, inode->i_mapping, tindex, len))
-			break;
-
-		for (i = 0; i < pagevec_count(&pvec); i++) {
-			done = xfs_convert_page(inode, pvec.pages[i], tindex++,
-					imap, ioendp, wbc);
-			if (done)
-				break;
-		}
-
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-}
-
 STATIC void
 xfs_vm_invalidatepage(
 	struct page		*page,
@@ -932,6 +709,164 @@ out_invalidate:
 }
 
 /*
+ * We implement an immediate ioend submission policy here to avoid needing to
+ * chain multiple ioends and hence nest mempool allocations which can violate
+ * forward progress guarantees we need to provide. The current ioend we are
+ * adding buffers to is cached on the writepage context, and if the new buffer
+ * does not append to the cached ioend it will create a new ioend and cache that
+ * instead.
+ *
+ * If a new ioend is created and cached, the old ioend is returned and queued
+ * locally for submission once the entire page is processed or an error has been
+ * detected.  While ioends are submitted immediately after they are completed,
+ * batching optimisations are provided by higher level block plugging.
+ *
+ * At the end of a writeback pass, there will be a cached ioend remaining on the
+ * writepage context that the caller will need to submit.
+ */
+static int
+xfs_writepage_map(
+	struct xfs_writepage_ctx *wpc,
+	struct writeback_control *wbc,
+	struct inode		*inode,
+	struct page		*page,
+	loff_t			offset,
+	__uint64_t              end_offset)
+{
+	LIST_HEAD(submit_list);
+	struct xfs_ioend	*ioend, *next;
+	struct buffer_head	*bh, *head;
+	ssize_t			len = 1 << inode->i_blkbits;
+	int			error = 0;
+	int			count = 0;
+	int			uptodate = 1;
+
+	bh = head = page_buffers(page);
+	offset = page_offset(page);
+	do {
+		if (offset >= end_offset)
+			break;
+		if (!buffer_uptodate(bh))
+			uptodate = 0;
+
+		/*
+		 * set_page_dirty dirties all buffers in a page, independent
+		 * of their state.  The dirty state however is entirely
+		 * meaningless for holes (!mapped && uptodate), so skip
+		 * buffers covering holes here.
+		 */
+		if (!buffer_mapped(bh) && buffer_uptodate(bh)) {
+			wpc->imap_valid = false;
+			continue;
+		}
+
+		if (buffer_unwritten(bh)) {
+			if (wpc->io_type != XFS_IO_UNWRITTEN) {
+				wpc->io_type = XFS_IO_UNWRITTEN;
+				wpc->imap_valid = false;
+			}
+		} else if (buffer_delay(bh)) {
+			if (wpc->io_type != XFS_IO_DELALLOC) {
+				wpc->io_type = XFS_IO_DELALLOC;
+				wpc->imap_valid = false;
+			}
+		} else if (buffer_uptodate(bh)) {
+			if (wpc->io_type != XFS_IO_OVERWRITE) {
+				wpc->io_type = XFS_IO_OVERWRITE;
+				wpc->imap_valid = false;
+			}
+		} else {
+			if (PageUptodate(page))
+				ASSERT(buffer_mapped(bh));
+			/*
+			 * This buffer is not uptodate and will not be
+			 * written to disk.  Ensure that we will put any
+			 * subsequent writeable buffers into a new
+			 * ioend.
+			 */
+			wpc->imap_valid = false;
+			continue;
+		}
+
+		if (wpc->imap_valid)
+			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
+							 offset);
+		if (!wpc->imap_valid) {
+			error = xfs_map_blocks(inode, offset, &wpc->imap,
+					     wpc->io_type);
+			if (error)
+				goto out;
+			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
+							 offset);
+		}
+		if (wpc->imap_valid) {
+			lock_buffer(bh);
+			if (wpc->io_type != XFS_IO_OVERWRITE)
+				xfs_map_at_offset(inode, bh, &wpc->imap, offset);
+			xfs_add_to_ioend(inode, bh, offset, wpc, &submit_list);
+			count++;
+		}
+
+	} while (offset += len, ((bh = bh->b_this_page) != head));
+
+	if (uptodate && bh == head)
+		SetPageUptodate(page);
+
+	ASSERT(wpc->ioend || list_empty(&submit_list));
+
+out:
+	/*
+	 * On error, we have to fail the ioend here because we have locked
+	 * buffers in the ioend. If we don't do this, we'll deadlock
+	 * invalidating the page as that tries to lock the buffers on the page.
+	 * Also, because we may have set pages under writeback, we have to make
+	 * sure we run IO completion to mark the error state of the IO
+	 * appropriately, so we can't cancel the ioend directly here. That means
+	 * we have to mark this page as under writeback if we included any
+	 * buffers from it in the ioend chain so that completion treats it
+	 * correctly.
+	 *
+	 * If we didn't include the page in the ioend, the on error we can
+	 * simply discard and unlock it as there are no other users of the page
+	 * or it's buffers right now. The caller will still need to trigger
+	 * submission of outstanding ioends on the writepage context so they are
+	 * treated correctly on error.
+	 */
+	if (count) {
+		xfs_start_page_writeback(page, !error);
+
+		/*
+		 * Preserve the original error if there was one, otherwise catch
+		 * submission errors here and propagate into subsequent ioend
+		 * submissions.
+		 */
+		list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
+			int error2;
+
+			list_del_init(&ioend->io_list);
+			error2 = xfs_submit_ioend(wbc, ioend, error);
+			if (error2 && !error)
+				error = error2;
+		}
+	} else if (error) {
+		xfs_aops_discard_page(page);
+		ClearPageUptodate(page);
+		unlock_page(page);
+	} else {
+		/*
+		 * We can end up here with no error and nothing to write if we
+		 * race with a partial page truncate on a sub-page block sized
+		 * filesystem. In that case we need to mark the page clean.
+		 */
+		xfs_start_page_writeback(page, 1);
+		end_page_writeback(page);
+	}
+
+	mapping_set_error(page->mapping, error);
+	return error;
+}
+
+/*
  * Write out a dirty page.
  *
  * For delalloc space on the page we need to allocate space and flush it.
@@ -940,22 +875,16 @@ out_invalidate:
  * For any other dirty buffer heads on the page we should flush them.
  */
 STATIC int
-xfs_vm_writepage(
+xfs_do_writepage(
 	struct page		*page,
-	struct writeback_control *wbc)
+	struct writeback_control *wbc,
+	void			*data)
 {
+	struct xfs_writepage_ctx *wpc = data;
 	struct inode		*inode = page->mapping->host;
-	struct buffer_head	*bh, *head;
-	struct xfs_bmbt_irec	imap;
-	xfs_ioend_t		*ioend = NULL, *iohead = NULL;
 	loff_t			offset;
-	unsigned int		type;
 	__uint64_t              end_offset;
-	pgoff_t                 end_index, last_index;
-	ssize_t			len;
-	int			err, imap_valid = 0, uptodate = 1;
-	int			count = 0;
-	int			nonblocking = 0;
+	pgoff_t                 end_index;
 
 	trace_xfs_writepage(inode, page, 0, 0);
 
@@ -982,12 +911,9 @@ xfs_vm_writepage(
 	if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
 		goto redirty;
 
-	/* Is this page beyond the end of the file? */
-	offset = i_size_read(inode);
-	end_index = offset >> PAGE_CACHE_SHIFT;
-	last_index = (offset - 1) >> PAGE_CACHE_SHIFT;
-
 	/*
+	 * Is this page beyond the end of the file?
+	 *
 	 * The page index is less than the end_index, adjust the end_offset
 	 * to the highest offset that this page should represent.
 	 * -----------------------------------------------------
@@ -998,6 +924,8 @@ xfs_vm_writepage(
 	 * |     desired writeback range    |      see else    |
 	 * ---------------------------------^------------------|
 	 */
+	offset = i_size_read(inode);
+	end_index = offset >> PAGE_CACHE_SHIFT;
 	if (page->index < end_index)
 		end_offset = (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT;
 	else {
@@ -1049,152 +977,7 @@ xfs_vm_writepage(
 		end_offset = offset;
 	}
 
-	len = 1 << inode->i_blkbits;
-
-	bh = head = page_buffers(page);
-	offset = page_offset(page);
-	type = XFS_IO_OVERWRITE;
-
-	if (wbc->sync_mode == WB_SYNC_NONE)
-		nonblocking = 1;
-
-	do {
-		int new_ioend = 0;
-
-		if (offset >= end_offset)
-			break;
-		if (!buffer_uptodate(bh))
-			uptodate = 0;
-
-		/*
-		 * set_page_dirty dirties all buffers in a page, independent
-		 * of their state.  The dirty state however is entirely
-		 * meaningless for holes (!mapped && uptodate), so skip
-		 * buffers covering holes here.
-		 */
-		if (!buffer_mapped(bh) && buffer_uptodate(bh)) {
-			imap_valid = 0;
-			continue;
-		}
-
-		if (buffer_unwritten(bh)) {
-			if (type != XFS_IO_UNWRITTEN) {
-				type = XFS_IO_UNWRITTEN;
-				imap_valid = 0;
-			}
-		} else if (buffer_delay(bh)) {
-			if (type != XFS_IO_DELALLOC) {
-				type = XFS_IO_DELALLOC;
-				imap_valid = 0;
-			}
-		} else if (buffer_uptodate(bh)) {
-			if (type != XFS_IO_OVERWRITE) {
-				type = XFS_IO_OVERWRITE;
-				imap_valid = 0;
-			}
-		} else {
-			if (PageUptodate(page))
-				ASSERT(buffer_mapped(bh));
-			/*
-			 * This buffer is not uptodate and will not be
-			 * written to disk.  Ensure that we will put any
-			 * subsequent writeable buffers into a new
-			 * ioend.
-			 */
-			imap_valid = 0;
-			continue;
-		}
-
-		if (imap_valid)
-			imap_valid = xfs_imap_valid(inode, &imap, offset);
-		if (!imap_valid) {
-			/*
-			 * If we didn't have a valid mapping then we need to
-			 * put the new mapping into a separate ioend structure.
-			 * This ensures non-contiguous extents always have
-			 * separate ioends, which is particularly important
-			 * for unwritten extent conversion at I/O completion
-			 * time.
-			 */
-			new_ioend = 1;
-			err = xfs_map_blocks(inode, offset, &imap, type,
-					     nonblocking);
-			if (err)
-				goto error;
-			imap_valid = xfs_imap_valid(inode, &imap, offset);
-		}
-		if (imap_valid) {
-			lock_buffer(bh);
-			if (type != XFS_IO_OVERWRITE)
-				xfs_map_at_offset(inode, bh, &imap, offset);
-			xfs_add_to_ioend(inode, bh, offset, type, &ioend,
-					 new_ioend);
-			count++;
-		}
-
-		if (!iohead)
-			iohead = ioend;
-
-	} while (offset += len, ((bh = bh->b_this_page) != head));
-
-	if (uptodate && bh == head)
-		SetPageUptodate(page);
-
-	xfs_start_page_writeback(page, 1, count);
-
-	/* if there is no IO to be submitted for this page, we are done */
-	if (!ioend)
-		return 0;
-
-	ASSERT(iohead);
-
-	/*
-	 * Any errors from this point onwards need tobe reported through the IO
-	 * completion path as we have marked the initial page as under writeback
-	 * and unlocked it.
-	 */
-	if (imap_valid) {
-		xfs_off_t		end_index;
-
-		end_index = imap.br_startoff + imap.br_blockcount;
-
-		/* to bytes */
-		end_index <<= inode->i_blkbits;
-
-		/* to pages */
-		end_index = (end_index - 1) >> PAGE_CACHE_SHIFT;
-
-		/* check against file size */
-		if (end_index > last_index)
-			end_index = last_index;
-
-		xfs_cluster_write(inode, page->index + 1, &imap, &ioend,
-				  wbc, end_index);
-	}
-
-
-	/*
-	 * Reserve log space if we might write beyond the on-disk inode size.
-	 */
-	err = 0;
-	if (ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend))
-		err = xfs_setfilesize_trans_alloc(ioend);
-
-	xfs_submit_ioend(wbc, iohead, err);
-
-	return 0;
-
-error:
-	if (iohead)
-		xfs_cancel_ioend(iohead);
-
-	if (err == -EAGAIN)
-		goto redirty;
-
-	xfs_aops_discard_page(page);
-	ClearPageUptodate(page);
-	unlock_page(page);
-	return err;
+	return xfs_writepage_map(wpc, wbc, inode, page, offset, end_offset);
 
 redirty:
 	redirty_page_for_writepage(wbc, page);
@@ -1203,12 +986,40 @@ redirty:
 }
 
 STATIC int
+xfs_vm_writepage(
+	struct page		*page,
+	struct writeback_control *wbc)
+{
+	struct xfs_writepage_ctx wpc = {
+		.io_type = XFS_IO_INVALID,
+	};
+	int			ret;
+
+	ret = xfs_do_writepage(page, wbc, &wpc);
+	if (wpc.ioend)
+		ret = xfs_submit_ioend(wbc, wpc.ioend, ret);
+	return ret;
+}
+
+STATIC int
 xfs_vm_writepages(
 	struct address_space	*mapping,
 	struct writeback_control *wbc)
 {
+	struct xfs_writepage_ctx wpc = {
+		.io_type = XFS_IO_INVALID,
+	};
+	int			ret;
+
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
-	return generic_writepages(mapping, wbc);
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping,
+				xfs_find_bdev_for_inode(mapping->host), wbc);
+
+	ret = write_cache_pages(mapping, wbc, xfs_do_writepage, &wpc);
+	if (wpc.ioend)
+		ret = xfs_submit_ioend(wbc, wpc.ioend, ret);
+	return ret;
 }
 
 /*
@@ -1238,27 +1049,8 @@ xfs_vm_releasepage(
 }
 
 /*
- * When we map a DIO buffer, we may need to attach an ioend that describes the
- * type of write IO we are doing. This passes to the completion function the
- * operations it needs to perform. If the mapping is for an overwrite wholly
- * within the EOF then we don't need an ioend and so we don't allocate one.
- * This avoids the unnecessary overhead of allocating and freeing ioends for
- * workloads that don't require transactions on IO completion.
- *
- * If we get multiple mappings in a single IO, we might be mapping different
- * types. But because the direct IO can only have a single private pointer, we
- * need to ensure that:
- *
- * a) i) the ioend spans the entire region of unwritten mappings; or
- *    ii) the ioend spans all the mappings that cross or are beyond EOF; and
- * b) if it contains unwritten extents, it is *permanently* marked as such
- *
- * We could do this by chaining ioends like buffered IO does, but we only
- * actually get one IO completion callback from the direct IO, and that spans
- * the entire IO regardless of how many mappings and IOs are needed to complete
- * the DIO. There is only going to be one reference to the ioend and its life
- * cycle is constrained by the DIO completion code. hence we don't need
- * reference counting here.
+ * When we map a DIO buffer, we may need to pass flags to
+ * xfs_end_io_direct_write to tell it what kind of write IO we are doing.
  *
  * Note that for DIO, an IO to the highest supported file block offset (i.e.
  * 2^63 - 1FSB bytes) will result in the offset + count overflowing a signed 64
@@ -1266,68 +1058,26 @@ xfs_vm_releasepage(
  * extending the file size. We won't know for sure until IO completion is run
  * and the actual max write offset is communicated to the IO completion
  * routine.
- *
- * For DAX page faults, we are preparing to never see unwritten extents here,
- * nor should we ever extend the inode size. Hence we will soon have nothing to
- * do here for this case, ensuring we don't have to provide an IO completion
- * callback to free an ioend that we don't actually need for a fault into the
- * page at offset (2^63 - 1FSB) bytes.
  */
-
 static void
 xfs_map_direct(
 	struct inode		*inode,
 	struct buffer_head	*bh_result,
 	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset,
-	bool			dax_fault)
+	xfs_off_t		offset)
 {
-	struct xfs_ioend	*ioend;
+	uintptr_t		*flags = (uintptr_t *)&bh_result->b_private;
 	xfs_off_t		size = bh_result->b_size;
-	int			type;
-
-	if (ISUNWRITTEN(imap))
-		type = XFS_IO_UNWRITTEN;
-	else
-		type = XFS_IO_OVERWRITE;
 
-	trace_xfs_gbmap_direct(XFS_I(inode), offset, size, type, imap);
-
-	if (dax_fault) {
-		ASSERT(type == XFS_IO_OVERWRITE);
-		trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type,
-					    imap);
-		return;
-	}
+	trace_xfs_get_blocks_map_direct(XFS_I(inode), offset, size,
+		ISUNWRITTEN(imap) ? XFS_IO_UNWRITTEN : XFS_IO_OVERWRITE, imap);
 
-	if (bh_result->b_private) {
-		ioend = bh_result->b_private;
-		ASSERT(ioend->io_size > 0);
-		ASSERT(offset >= ioend->io_offset);
-		if (offset + size > ioend->io_offset + ioend->io_size)
-			ioend->io_size = offset - ioend->io_offset + size;
-
-		if (type == XFS_IO_UNWRITTEN && type != ioend->io_type)
-			ioend->io_type = XFS_IO_UNWRITTEN;
-
-		trace_xfs_gbmap_direct_update(XFS_I(inode), ioend->io_offset,
-					      ioend->io_size, ioend->io_type,
-					      imap);
-	} else if (type == XFS_IO_UNWRITTEN ||
-		   offset + size > i_size_read(inode) ||
-		   offset + size < 0) {
-		ioend = xfs_alloc_ioend(inode, type);
-		ioend->io_offset = offset;
-		ioend->io_size = size;
-
-		bh_result->b_private = ioend;
+	if (ISUNWRITTEN(imap)) {
+		*flags |= XFS_DIO_FLAG_UNWRITTEN;
+		set_buffer_defer_completion(bh_result);
+	} else if (offset + size > i_size_read(inode) || offset + size < 0) {
+		*flags |= XFS_DIO_FLAG_APPEND;
 		set_buffer_defer_completion(bh_result);
-
-		trace_xfs_gbmap_direct_new(XFS_I(inode), offset, size, type,
-					   imap);
-	} else {
-		trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type,
-					    imap);
 	}
 }
 
@@ -1498,9 +1248,12 @@ __xfs_get_blocks(
 		if (ISUNWRITTEN(&imap))
 			set_buffer_unwritten(bh_result);
 		/* direct IO needs special help */
-		if (create && direct)
-			xfs_map_direct(inode, bh_result, &imap, offset,
-				       dax_fault);
+		if (create && direct) {
+			if (dax_fault)
+				ASSERT(!ISUNWRITTEN(&imap));
+			else
+				xfs_map_direct(inode, bh_result, &imap, offset);
+		}
 	}
 
 	/*
@@ -1570,42 +1323,50 @@ xfs_get_blocks_dax_fault(
 	return __xfs_get_blocks(inode, iblock, bh_result, create, true, true);
 }
 
-static void
-__xfs_end_io_direct_write(
-	struct inode		*inode,
-	struct xfs_ioend	*ioend,
+/*
+ * Complete a direct I/O write request.
+ *
+ * xfs_map_direct passes us some flags in the private data to tell us what to
+ * do.  If no flags are set, then the write IO is an overwrite wholly within
+ * the existing allocated file size and so there is nothing for us to do.
+ *
+ * Note that in this case the completion can be called in interrupt context,
+ * whereas if we have flags set we will always be called in task context
+ * (i.e. from a workqueue).
+ */
+STATIC int
+xfs_end_io_direct_write(
+	struct kiocb		*iocb,
 	loff_t			offset,
-	ssize_t			size)
+	ssize_t			size,
+	void			*private)
 {
-	struct xfs_mount	*mp = XFS_I(inode)->i_mount;
+	struct inode		*inode = file_inode(iocb->ki_filp);
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	uintptr_t		flags = (uintptr_t)private;
+	int			error = 0;
 
-	if (XFS_FORCED_SHUTDOWN(mp) || ioend->io_error)
-		goto out_end_io;
+	trace_xfs_end_io_direct_write(ip, offset, size);
 
-	/*
-	 * dio completion end_io functions are only called on writes if more
-	 * than 0 bytes was written.
-	 */
-	ASSERT(size > 0);
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
 
-	/*
-	 * The ioend only maps whole blocks, while the IO may be sector aligned.
-	 * Hence the ioend offset/size may not match the IO offset/size exactly.
-	 * Because we don't map overwrites within EOF into the ioend, the offset
-	 * may not match, but only if the endio spans EOF.  Either way, write
-	 * the IO sizes into the ioend so that completion processing does the
-	 * right thing.
-	 */
-	ASSERT(offset + size <= ioend->io_offset + ioend->io_size);
-	ioend->io_size = size;
-	ioend->io_offset = offset;
+	if (size <= 0)
+		return size;
 
 	/*
-	 * The ioend tells us whether we are doing unwritten extent conversion
+	 * The flags tell us whether we are doing unwritten extent conversions
 	 * or an append transaction that updates the on-disk file size. These
 	 * cases are the only cases where we should *potentially* be needing
 	 * to update the VFS inode size.
-	 *
+	 */
+	if (flags == 0) {
+		ASSERT(offset + size <= i_size_read(inode));
+		return 0;
+	}
+
+	/*
 	 * We need to update the in-core inode size here so that we don't end up
 	 * with the on-disk inode size being outside the in-core inode size. We
 	 * have no other method of updating EOF for AIO, so always do it here
@@ -1616,91 +1377,56 @@ __xfs_end_io_direct_write(
 	 * here can result in EOF moving backwards and Bad Things Happen when
 	 * that occurs.
 	 */
-	spin_lock(&XFS_I(inode)->i_flags_lock);
+	spin_lock(&ip->i_flags_lock);
 	if (offset + size > i_size_read(inode))
 		i_size_write(inode, offset + size);
-	spin_unlock(&XFS_I(inode)->i_flags_lock);
+	spin_unlock(&ip->i_flags_lock);
 
-	/*
-	 * If we are doing an append IO that needs to update the EOF on disk,
-	 * do the transaction reserve now so we can use common end io
-	 * processing. Stashing the error (if there is one) in the ioend will
-	 * result in the ioend processing passing on the error if it is
-	 * possible as we can't return it from here.
-	 */
-	if (ioend->io_type == XFS_IO_OVERWRITE)
-		ioend->io_error = xfs_setfilesize_trans_alloc(ioend);
+	if (flags & XFS_DIO_FLAG_UNWRITTEN) {
+		trace_xfs_end_io_direct_write_unwritten(ip, offset, size);
 
-out_end_io:
-	xfs_end_io(&ioend->io_work);
-	return;
-}
+		error = xfs_iomap_write_unwritten(ip, offset, size);
+	} else if (flags & XFS_DIO_FLAG_APPEND) {
+		struct xfs_trans *tp;
 
-/*
- * Complete a direct I/O write request.
- *
- * The ioend structure is passed from __xfs_get_blocks() to tell us what to do.
- * If no ioend exists (i.e. @private == NULL) then the write IO is an overwrite
- * wholly within the EOF and so there is nothing for us to do. Note that in this
- * case the completion can be called in interrupt context, whereas if we have an
- * ioend we will always be called in task context (i.e. from a workqueue).
- */
-STATIC void
-xfs_end_io_direct_write(
-	struct kiocb		*iocb,
-	loff_t			offset,
-	ssize_t			size,
-	void			*private)
-{
-	struct inode		*inode = file_inode(iocb->ki_filp);
-	struct xfs_ioend	*ioend = private;
-
-	trace_xfs_gbmap_direct_endio(XFS_I(inode), offset, size,
-				     ioend ? ioend->io_type : 0, NULL);
+		trace_xfs_end_io_direct_write_append(ip, offset, size);
 
-	if (!ioend) {
-		ASSERT(offset + size <= i_size_read(inode));
-		return;
+		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);
+			return error;
+		}
+		error = xfs_setfilesize(ip, tp, offset, size);
 	}
 
-	__xfs_end_io_direct_write(inode, ioend, offset, size);
+	return error;
 }
 
-static inline ssize_t
-xfs_vm_do_dio(
-	struct inode		*inode,
+STATIC ssize_t
+xfs_vm_direct_IO(
 	struct kiocb		*iocb,
 	struct iov_iter		*iter,
-	loff_t			offset,
-	void			(*endio)(struct kiocb	*iocb,
-					 loff_t		offset,
-					 ssize_t	size,
-					 void		*private),
-	int			flags)
+	loff_t			offset)
 {
+	struct inode		*inode = iocb->ki_filp->f_mapping->host;
+	dio_iodone_t		*endio = NULL;
+	int			flags = 0;
 	struct block_device	*bdev;
 
-	if (IS_DAX(inode))
+	if (iov_iter_rw(iter) == WRITE) {
+		endio = xfs_end_io_direct_write;
+		flags = DIO_ASYNC_EXTEND;
+	}
+
+	if (IS_DAX(inode)) {
 		return dax_do_io(iocb, inode, iter, offset,
 				 xfs_get_blocks_direct, endio, 0);
+	}
 
 	bdev = xfs_find_bdev_for_inode(inode);
 	return  __blockdev_direct_IO(iocb, inode, bdev, iter, offset,
-				     xfs_get_blocks_direct, endio, NULL, flags);
-}
-
-STATIC ssize_t
-xfs_vm_direct_IO(
-	struct kiocb		*iocb,
-	struct iov_iter		*iter,
-	loff_t			offset)
-{
-	struct inode		*inode = iocb->ki_filp->f_mapping->host;
-
-	if (iov_iter_rw(iter) == WRITE)
-		return xfs_vm_do_dio(inode, iocb, iter, offset,
-				     xfs_end_io_direct_write, DIO_ASYNC_EXTEND);
-	return xfs_vm_do_dio(inode, iocb, iter, offset, NULL, 0);
+			xfs_get_blocks_direct, endio, NULL, flags);
 }
 
 /*
@@ -1752,6 +1478,7 @@ xfs_vm_write_failed(
 	loff_t			from = pos & (PAGE_CACHE_SIZE - 1);
 	loff_t			to = from + len;
 	struct buffer_head	*bh, *head;
+	struct xfs_mount	*mp = XFS_I(inode)->i_mount;
 
 	/*
 	 * The request pos offset might be 32 or 64 bit, this is all fine
@@ -1783,14 +1510,23 @@ xfs_vm_write_failed(
 		if (block_start >= to)
 			break;
 
-		if (!buffer_delay(bh))
+		/*
+		 * Process delalloc and unwritten buffers beyond EOF. We can
+		 * encounter unwritten buffers in the event that a file has
+		 * post-EOF unwritten extents and an extending write happens to
+		 * fail (e.g., an unaligned write that also involves a delalloc
+		 * to the same page).
+		 */
+		if (!buffer_delay(bh) && !buffer_unwritten(bh))
 			continue;
 
-		if (!buffer_new(bh) && block_offset < i_size_read(inode))
+		if (!xfs_mp_fail_writes(mp) && !buffer_new(bh) &&
+		    block_offset < i_size_read(inode))
 			continue;
 
-		xfs_vm_kill_delalloc_range(inode, block_offset,
-					   block_offset + bh->b_size);
+		if (buffer_delay(bh))
+			xfs_vm_kill_delalloc_range(inode, block_offset,
+						   block_offset + bh->b_size);
 
 		/*
 		 * This buffer does not contain data anymore. make sure anyone
@@ -1801,6 +1537,7 @@ xfs_vm_write_failed(
 		clear_buffer_mapped(bh);
 		clear_buffer_new(bh);
 		clear_buffer_dirty(bh);
+		clear_buffer_unwritten(bh);
 	}
 
 }
@@ -1824,6 +1561,7 @@ xfs_vm_write_begin(
 	pgoff_t			index = pos >> PAGE_CACHE_SHIFT;
 	struct page		*page;
 	int			status;
+	struct xfs_mount	*mp = XFS_I(mapping->host)->i_mount;
 
 	ASSERT(len <= PAGE_CACHE_SIZE);
 
@@ -1832,6 +1570,8 @@ xfs_vm_write_begin(
 		return -ENOMEM;
 
 	status = __block_write_begin(page, pos, len, xfs_get_blocks);
+	if (xfs_mp_fail_writes(mp))
+		status = -EIO;
 	if (unlikely(status)) {
 		struct inode	*inode = mapping->host;
 		size_t		isize = i_size_read(inode);
@@ -1844,6 +1584,8 @@ xfs_vm_write_begin(
 		 * allocated in this write, not blocks that were previously
 		 * written successfully.
 		 */
+		if (xfs_mp_fail_writes(mp))
+			isize = 0;
 		if (pos + len > isize) {
 			ssize_t start = max_t(ssize_t, pos, isize);
 
@@ -1953,7 +1695,6 @@ xfs_vm_set_page_dirty(
 	loff_t			end_offset;
 	loff_t			offset;
 	int			newly_dirty;
-	struct mem_cgroup	*memcg;
 
 	if (unlikely(!mapping))
 		return !TestSetPageDirty(page);
@@ -1974,10 +1715,10 @@ xfs_vm_set_page_dirty(
 		} while (bh != head);
 	}
 	/*
-	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
-	 * per-memcg dirty page counters.
+	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * synchronized with per-memcg dirty page counters.
 	 */
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 
@@ -1988,13 +1729,13 @@ xfs_vm_set_page_dirty(
 		spin_lock_irqsave(&mapping->tree_lock, flags);
 		if (page->mapping) {	/* Race with truncate? */
 			WARN_ON_ONCE(!PageUptodate(page));
-			account_page_dirtied(page, mapping, memcg);
+			account_page_dirtied(page, mapping);
 			radix_tree_tag_set(&mapping->page_tree,
 					page_index(page), PAGECACHE_TAG_DIRTY);
 		}
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	}
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 	if (newly_dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	return newly_dirty;
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index f6ffc9ae5ceb..b4421177b68d 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -24,12 +24,14 @@ extern mempool_t *xfs_ioend_pool;
  * Types of I/O for bmap clustering and I/O completion tracking.
  */
 enum {
+	XFS_IO_INVALID,		/* initial state */
 	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 \
+	{ XFS_IO_INVALID,		"invalid" }, \
 	{ XFS_IO_DELALLOC,		"delalloc" }, \
 	{ XFS_IO_UNWRITTEN,		"unwritten" }, \
 	{ XFS_IO_OVERWRITE,		"overwrite" }
@@ -39,7 +41,7 @@ enum {
  * It can manage several multi-page bio's at once.
  */
 typedef struct xfs_ioend {
-	struct xfs_ioend	*io_list;	/* next ioend in chain */
+	struct list_head	io_list;	/* next ioend in chain */
 	unsigned int		io_type;	/* delalloc / unwritten */
 	int			io_error;	/* I/O error code */
 	atomic_t		io_remaining;	/* hold count */
@@ -62,5 +64,6 @@ int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
 			         struct buffer_head *map_bh, int create);
 
 extern void xfs_count_page_state(struct page *, int *, int *);
+extern struct block_device *xfs_find_bdev_for_inode(struct inode *);
 
 #endif /* __XFS_AOPS_H__ */
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 0ef7c2ed3f8a..4fa14820e2e2 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -202,8 +202,10 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
 					sbp->namelen,
 					sbp->valuelen,
 					&sbp->name[sbp->namelen]);
-		if (error)
+		if (error) {
+			kmem_free(sbuf);
 			return error;
+		}
 		if (context->seen_enough)
 			break;
 		cursor->offset++;
@@ -454,14 +456,13 @@ xfs_attr3_leaf_list_int(
 				args.rmtblkcnt = xfs_attr3_rmt_blocks(
 							args.dp->i_mount, valuelen);
 				retval = xfs_attr_rmtval_get(&args);
-				if (retval)
-					return retval;
-				retval = context->put_listent(context,
-						entry->flags,
-						name_rmt->name,
-						(int)name_rmt->namelen,
-						valuelen,
-						args.value);
+				if (!retval)
+					retval = context->put_listent(context,
+							entry->flags,
+							name_rmt->name,
+							(int)name_rmt->namelen,
+							valuelen,
+							args.value);
 				kmem_free(args.value);
 			} else {
 				retval = context->put_listent(context,
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 45ec9e40150c..a32c1dcae2ff 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -75,7 +75,8 @@ xfs_zero_extent(
 	ssize_t		size = XFS_FSB_TO_B(mp, count_fsb);
 
 	if (IS_DAX(VFS_I(ip)))
-		return dax_clear_blocks(VFS_I(ip), block, size);
+		return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)),
+				sector, size);
 
 	/*
 	 * let the block layer decide on the fastest method of
@@ -202,10 +203,12 @@ xfs_bmap_rtalloc(
 		ralen = MAXEXTLEN / mp->m_sb.sb_rextsize;
 
 	/*
-	 * Lock out other modifications to the RT bitmap inode.
+	 * Lock out modifications to both the RT bitmap and summary inodes
 	 */
 	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+	xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL);
 
 	/*
 	 * If it's an allocation to an empty file at offset 0,
@@ -821,7 +824,7 @@ bool
 xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
 {
 	/* prealloc/delalloc exists only on regular files */
-	if (!S_ISREG(ip->i_d.di_mode))
+	if (!S_ISREG(VFS_I(ip)->i_mode))
 		return false;
 
 	/*
@@ -1726,7 +1729,7 @@ xfs_swap_extents(
 	xfs_lock_two_inodes(ip, tip, XFS_MMAPLOCK_EXCL);
 
 	/* Verify that both files have the same format */
-	if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
+	if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) {
 		error = -EINVAL;
 		goto out_unlock;
 	}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 435c7de42e5f..9a2191b91137 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -650,7 +650,7 @@ xfs_buf_read_map(
 	if (bp) {
 		trace_xfs_buf_read(bp, flags, _RET_IP_);
 
-		if (!XFS_BUF_ISDONE(bp)) {
+		if (!(bp->b_flags & XBF_DONE)) {
 			XFS_STATS_INC(target->bt_mount, xb_get_read);
 			bp->b_ops = ops;
 			_xfs_buf_read(bp, flags);
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index c75721acd867..4eb89bd4ee73 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -302,6 +302,7 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 
 /* Buffer Utility Routines */
 extern void *xfs_buf_offset(struct xfs_buf *, size_t);
+extern void xfs_buf_stale(struct xfs_buf *bp);
 
 /* Delayed Write Buffer Routines */
 extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
@@ -312,31 +313,6 @@ extern int xfs_buf_delwri_submit_nowait(struct list_head *);
 extern int xfs_buf_init(void);
 extern void xfs_buf_terminate(void);
 
-#define XFS_BUF_ZEROFLAGS(bp) \
-	((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
-			    XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \
-			    XBF_WRITE_FAIL))
-
-void xfs_buf_stale(struct xfs_buf *bp);
-#define XFS_BUF_UNSTALE(bp)	((bp)->b_flags &= ~XBF_STALE)
-#define XFS_BUF_ISSTALE(bp)	((bp)->b_flags & XBF_STALE)
-
-#define XFS_BUF_DONE(bp)	((bp)->b_flags |= XBF_DONE)
-#define XFS_BUF_UNDONE(bp)	((bp)->b_flags &= ~XBF_DONE)
-#define XFS_BUF_ISDONE(bp)	((bp)->b_flags & XBF_DONE)
-
-#define XFS_BUF_ASYNC(bp)	((bp)->b_flags |= XBF_ASYNC)
-#define XFS_BUF_UNASYNC(bp)	((bp)->b_flags &= ~XBF_ASYNC)
-#define XFS_BUF_ISASYNC(bp)	((bp)->b_flags & XBF_ASYNC)
-
-#define XFS_BUF_READ(bp)	((bp)->b_flags |= XBF_READ)
-#define XFS_BUF_UNREAD(bp)	((bp)->b_flags &= ~XBF_READ)
-#define XFS_BUF_ISREAD(bp)	((bp)->b_flags & XBF_READ)
-
-#define XFS_BUF_WRITE(bp)	((bp)->b_flags |= XBF_WRITE)
-#define XFS_BUF_UNWRITE(bp)	((bp)->b_flags &= ~XBF_WRITE)
-#define XFS_BUF_ISWRITE(bp)	((bp)->b_flags & XBF_WRITE)
-
 /*
  * These macros use the IO block map rather than b_bn. b_bn is now really
  * just for the buffer cache index for cached buffers. As IO does not use b_bn
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 7e986da34f6c..99e91a0e554e 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -431,7 +431,7 @@ xfs_buf_item_unpin(
 	if (freed && stale) {
 		ASSERT(bip->bli_flags & XFS_BLI_STALE);
 		ASSERT(xfs_buf_islocked(bp));
-		ASSERT(XFS_BUF_ISSTALE(bp));
+		ASSERT(bp->b_flags & XBF_STALE);
 		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 
 		trace_xfs_buf_item_unpin_stale(bip);
@@ -493,7 +493,7 @@ xfs_buf_item_unpin(
 		xfs_buf_hold(bp);
 		bp->b_flags |= XBF_ASYNC;
 		xfs_buf_ioerror(bp, -EIO);
-		XFS_BUF_UNDONE(bp);
+		bp->b_flags &= ~XBF_DONE;
 		xfs_buf_stale(bp);
 		xfs_buf_ioend(bp);
 	}
@@ -1067,7 +1067,7 @@ xfs_buf_iodone_callbacks(
 	 */
 	if (XFS_FORCED_SHUTDOWN(mp)) {
 		xfs_buf_stale(bp);
-		XFS_BUF_DONE(bp);
+		bp->b_flags |= XBF_DONE;
 		trace_xfs_buf_item_iodone(bp, _RET_IP_);
 		goto do_callbacks;
 	}
@@ -1090,7 +1090,7 @@ xfs_buf_iodone_callbacks(
 	 * errors tend to affect the whole device and a failing log write
 	 * will make us give up.  But we really ought to do better here.
 	 */
-	if (XFS_BUF_ISASYNC(bp)) {
+	if (bp->b_flags & XBF_ASYNC) {
 		ASSERT(bp->b_iodone != NULL);
 
 		trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
@@ -1113,7 +1113,7 @@ xfs_buf_iodone_callbacks(
 	 * sure to return the error to the caller of xfs_bwrite().
 	 */
 	xfs_buf_stale(bp);
-	XFS_BUF_DONE(bp);
+	bp->b_flags |= XBF_DONE;
 
 	trace_xfs_buf_error_relse(bp, _RET_IP_);
 
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 642d55d10075..93b3ab0c5435 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -665,7 +665,7 @@ xfs_readdir(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	XFS_STATS_INC(dp->i_mount, xs_dir_getdents);
 
 	args.dp = dp;
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index e85a9519a5ae..272c3f8b6f7d 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -227,7 +227,7 @@ xfs_discard_extents(
 				GFP_NOFS, 0);
 		if (error && error != -EOPNOTSUPP) {
 			xfs_info(mp,
-	 "discard failed for extent [0x%llu,%u], error %d",
+	 "discard failed for extent [0x%llx,%u], error %d",
 				 (unsigned long long)busyp->bno,
 				 busyp->length,
 				 error);
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 9c44d38dcd1f..316b2a1bdba5 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -92,26 +92,28 @@ xfs_qm_adjust_dqlimits(
 {
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
 	struct xfs_disk_dquot	*d = &dq->q_core;
+	struct xfs_def_quota	*defq;
 	int			prealloc = 0;
 
 	ASSERT(d->d_id);
+	defq = xfs_get_defquota(dq, q);
 
-	if (q->qi_bsoftlimit && !d->d_blk_softlimit) {
-		d->d_blk_softlimit = cpu_to_be64(q->qi_bsoftlimit);
+	if (defq->bsoftlimit && !d->d_blk_softlimit) {
+		d->d_blk_softlimit = cpu_to_be64(defq->bsoftlimit);
 		prealloc = 1;
 	}
-	if (q->qi_bhardlimit && !d->d_blk_hardlimit) {
-		d->d_blk_hardlimit = cpu_to_be64(q->qi_bhardlimit);
+	if (defq->bhardlimit && !d->d_blk_hardlimit) {
+		d->d_blk_hardlimit = cpu_to_be64(defq->bhardlimit);
 		prealloc = 1;
 	}
-	if (q->qi_isoftlimit && !d->d_ino_softlimit)
-		d->d_ino_softlimit = cpu_to_be64(q->qi_isoftlimit);
-	if (q->qi_ihardlimit && !d->d_ino_hardlimit)
-		d->d_ino_hardlimit = cpu_to_be64(q->qi_ihardlimit);
-	if (q->qi_rtbsoftlimit && !d->d_rtb_softlimit)
-		d->d_rtb_softlimit = cpu_to_be64(q->qi_rtbsoftlimit);
-	if (q->qi_rtbhardlimit && !d->d_rtb_hardlimit)
-		d->d_rtb_hardlimit = cpu_to_be64(q->qi_rtbhardlimit);
+	if (defq->isoftlimit && !d->d_ino_softlimit)
+		d->d_ino_softlimit = cpu_to_be64(defq->isoftlimit);
+	if (defq->ihardlimit && !d->d_ino_hardlimit)
+		d->d_ino_hardlimit = cpu_to_be64(defq->ihardlimit);
+	if (defq->rtbsoftlimit && !d->d_rtb_softlimit)
+		d->d_rtb_softlimit = cpu_to_be64(defq->rtbsoftlimit);
+	if (defq->rtbhardlimit && !d->d_rtb_hardlimit)
+		d->d_rtb_hardlimit = cpu_to_be64(defq->rtbhardlimit);
 
 	if (prealloc)
 		xfs_dquot_set_prealloc_limits(dq);
@@ -232,7 +234,8 @@ xfs_qm_init_dquot_blk(
 {
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
 	xfs_dqblk_t	*d;
-	int		curid, i;
+	xfs_dqid_t	curid;
+	int		i;
 
 	ASSERT(tp);
 	ASSERT(xfs_buf_islocked(bp));
@@ -243,7 +246,6 @@ xfs_qm_init_dquot_blk(
 	 * ID of the first dquot in the block - id's are zero based.
 	 */
 	curid = id - (id % q->qi_dqperchunk);
-	ASSERT(curid >= 0);
 	memset(d, 0, BBTOB(q->qi_dqchunklen));
 	for (i = 0; i < q->qi_dqperchunk; i++, d++, curid++) {
 		d->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
@@ -464,12 +466,13 @@ xfs_qm_dqtobp(
 	struct xfs_bmbt_irec	map;
 	int			nmaps = 1, error;
 	struct xfs_buf		*bp;
-	struct xfs_inode	*quotip = xfs_dq_to_quota_inode(dqp);
+	struct xfs_inode	*quotip;
 	struct xfs_mount	*mp = dqp->q_mount;
 	xfs_dqid_t		id = be32_to_cpu(dqp->q_core.d_id);
 	struct xfs_trans	*tp = (tpp ? *tpp : NULL);
 	uint			lock_mode;
 
+	quotip = xfs_quota_inode(dqp->q_mount, dqp->dq_flags);
 	dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk;
 
 	lock_mode = xfs_ilock_data_map_shared(quotip);
@@ -685,6 +688,56 @@ error0:
 }
 
 /*
+ * Advance to the next id in the current chunk, or if at the
+ * end of the chunk, skip ahead to first id in next allocated chunk
+ * using the SEEK_DATA interface.
+ */
+int
+xfs_dq_get_next_id(
+	xfs_mount_t		*mp,
+	uint			type,
+	xfs_dqid_t		*id,
+	loff_t			eof)
+{
+	struct xfs_inode	*quotip;
+	xfs_fsblock_t		start;
+	loff_t			offset;
+	uint			lock;
+	xfs_dqid_t		next_id;
+	int			error = 0;
+
+	/* Simple advance */
+	next_id = *id + 1;
+
+	/* If new ID is within the current chunk, advancing it sufficed */
+	if (next_id % mp->m_quotainfo->qi_dqperchunk) {
+		*id = next_id;
+		return 0;
+	}
+
+	/* Nope, next_id is now past the current chunk, so find the next one */
+	start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk;
+
+	quotip = xfs_quota_inode(mp, type);
+	lock = xfs_ilock_data_map_shared(quotip);
+
+	offset = __xfs_seek_hole_data(VFS_I(quotip), XFS_FSB_TO_B(mp, start),
+				      eof, SEEK_DATA);
+	if (offset < 0)
+		error = offset;
+
+	xfs_iunlock(quotip, lock);
+
+	/* -ENXIO is essentially "no more data" */
+	if (error)
+		return (error == -ENXIO ? -ENOENT: error);
+
+	/* Convert next data offset back to a quota id */
+	*id = XFS_B_TO_FSB(mp, offset) * mp->m_quotainfo->qi_dqperchunk;
+	return 0;
+}
+
+/*
  * Given the file system, inode OR id, and type (UDQUOT/GDQUOT), return a
  * a locked dquot, doing an allocation (if requested) as needed.
  * When both an inode and an id are given, the inode's id takes precedence.
@@ -704,6 +757,7 @@ xfs_qm_dqget(
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
 	struct radix_tree_root *tree = xfs_dquot_tree(qi, type);
 	struct xfs_dquot	*dqp;
+	loff_t			eof = 0;
 	int			error;
 
 	ASSERT(XFS_IS_QUOTA_RUNNING(mp));
@@ -731,6 +785,21 @@ xfs_qm_dqget(
 	}
 #endif
 
+	/* Get the end of the quota file if we need it */
+	if (flags & XFS_QMOPT_DQNEXT) {
+		struct xfs_inode	*quotip;
+		xfs_fileoff_t		last;
+		uint			lock_mode;
+
+		quotip = xfs_quota_inode(mp, type);
+		lock_mode = xfs_ilock_data_map_shared(quotip);
+		error = xfs_bmap_last_offset(quotip, &last, XFS_DATA_FORK);
+		xfs_iunlock(quotip, lock_mode);
+		if (error)
+			return error;
+		eof = XFS_FSB_TO_B(mp, last);
+	}
+
 restart:
 	mutex_lock(&qi->qi_tree_lock);
 	dqp = radix_tree_lookup(tree, id);
@@ -744,6 +813,18 @@ restart:
 			goto restart;
 		}
 
+		/* uninit / unused quota found in radix tree, keep looking  */
+		if (flags & XFS_QMOPT_DQNEXT) {
+			if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
+				xfs_dqunlock(dqp);
+				mutex_unlock(&qi->qi_tree_lock);
+				error = xfs_dq_get_next_id(mp, type, &id, eof);
+				if (error)
+					return error;
+				goto restart;
+			}
+		}
+
 		dqp->q_nrefs++;
 		mutex_unlock(&qi->qi_tree_lock);
 
@@ -770,6 +851,13 @@ restart:
 	if (ip)
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 
+	/* If we are asked to find next active id, keep looking */
+	if (error == -ENOENT && (flags & XFS_QMOPT_DQNEXT)) {
+		error = xfs_dq_get_next_id(mp, type, &id, eof);
+		if (!error)
+			goto restart;
+	}
+
 	if (error)
 		return error;
 
@@ -820,6 +908,17 @@ restart:
 	qi->qi_dquots++;
 	mutex_unlock(&qi->qi_tree_lock);
 
+	/* If we are asked to find next active id, keep looking */
+	if (flags & XFS_QMOPT_DQNEXT) {
+		if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
+			xfs_qm_dqput(dqp);
+			error = xfs_dq_get_next_id(mp, type, &id, eof);
+			if (error)
+				return error;
+			goto restart;
+		}
+	}
+
  dqret:
 	ASSERT((ip == NULL) || xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	trace_xfs_dqget_miss(dqp);
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 652cd3c5b58c..a1b2dd828b9d 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -152,7 +152,7 @@ xfs_nfs_get_inode(
 		return ERR_PTR(error);
 	}
 
-	if (ip->i_d.di_gen != generation) {
+	if (VFS_I(ip)->i_generation != generation) {
 		IRELE(ip);
 		return ERR_PTR(-ESTALE);
 	}
@@ -246,7 +246,7 @@ 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
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
 	.get_uuid		= xfs_fs_get_uuid,
 	.map_blocks		= xfs_fs_map_blocks,
 	.commit_blocks		= xfs_fs_commit_blocks,
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 52883ac3cf84..ac0fd32de31e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -156,9 +156,9 @@ xfs_update_prealloc_flags(
 	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;
+		VFS_I(ip)->i_mode &= ~S_ISUID;
+		if (VFS_I(ip)->i_mode & S_IXGRP)
+			VFS_I(ip)->i_mode &= ~S_ISGID;
 		xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	}
 
@@ -1337,31 +1337,31 @@ out:
 	return found;
 }
 
-STATIC loff_t
-xfs_seek_hole_data(
-	struct file		*file,
+/*
+ * caller must lock inode with xfs_ilock_data_map_shared,
+ * can we craft an appropriate ASSERT?
+ *
+ * end is because the VFS-level lseek interface is defined such that any
+ * offset past i_size shall return -ENXIO, but we use this for quota code
+ * which does not maintain i_size, and we want to SEEK_DATA past i_size.
+ */
+loff_t
+__xfs_seek_hole_data(
+	struct inode		*inode,
 	loff_t			start,
+	loff_t			end,
 	int			whence)
 {
-	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	loff_t			uninitialized_var(offset);
-	xfs_fsize_t		isize;
 	xfs_fileoff_t		fsbno;
-	xfs_filblks_t		end;
-	uint			lock;
+	xfs_filblks_t		lastbno;
 	int			error;
 
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	lock = xfs_ilock_data_map_shared(ip);
-
-	isize = i_size_read(inode);
-	if (start >= isize) {
+	if (start >= end) {
 		error = -ENXIO;
-		goto out_unlock;
+		goto out_error;
 	}
 
 	/*
@@ -1369,22 +1369,22 @@ xfs_seek_hole_data(
 	 * by fsbno to the end block of the file.
 	 */
 	fsbno = XFS_B_TO_FSBT(mp, start);
-	end = XFS_B_TO_FSB(mp, isize);
+	lastbno = XFS_B_TO_FSB(mp, end);
 
 	for (;;) {
 		struct xfs_bmbt_irec	map[2];
 		int			nmap = 2;
 		unsigned int		i;
 
-		error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
+		error = xfs_bmapi_read(ip, fsbno, lastbno - fsbno, map, &nmap,
 				       XFS_BMAPI_ENTIRE);
 		if (error)
-			goto out_unlock;
+			goto out_error;
 
 		/* No extents at given offset, must be beyond EOF */
 		if (nmap == 0) {
 			error = -ENXIO;
-			goto out_unlock;
+			goto out_error;
 		}
 
 		for (i = 0; i < nmap; i++) {
@@ -1426,7 +1426,7 @@ xfs_seek_hole_data(
 			 * hole at the end of any file).
 		 	 */
 			if (whence == SEEK_HOLE) {
-				offset = isize;
+				offset = end;
 				break;
 			}
 			/*
@@ -1434,7 +1434,7 @@ xfs_seek_hole_data(
 			 */
 			ASSERT(whence == SEEK_DATA);
 			error = -ENXIO;
-			goto out_unlock;
+			goto out_error;
 		}
 
 		ASSERT(i > 1);
@@ -1445,14 +1445,14 @@ xfs_seek_hole_data(
 		 */
 		fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
 		start = XFS_FSB_TO_B(mp, fsbno);
-		if (start >= isize) {
+		if (start >= end) {
 			if (whence == SEEK_HOLE) {
-				offset = isize;
+				offset = end;
 				break;
 			}
 			ASSERT(whence == SEEK_DATA);
 			error = -ENXIO;
-			goto out_unlock;
+			goto out_error;
 		}
 	}
 
@@ -1464,7 +1464,39 @@ out:
 	 * situation in particular.
 	 */
 	if (whence == SEEK_HOLE)
-		offset = min_t(loff_t, offset, isize);
+		offset = min_t(loff_t, offset, end);
+
+	return offset;
+
+out_error:
+	return error;
+}
+
+STATIC loff_t
+xfs_seek_hole_data(
+	struct file		*file,
+	loff_t			start,
+	int			whence)
+{
+	struct inode		*inode = file->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	uint			lock;
+	loff_t			offset, end;
+	int			error = 0;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
+	lock = xfs_ilock_data_map_shared(ip);
+
+	end = i_size_read(inode);
+	offset = __xfs_seek_hole_data(inode, start, end, whence);
+	if (offset < 0) {
+		error = offset;
+		goto out_unlock;
+	}
+
 	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 
 out_unlock:
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index c4c130f9bfb6..a51353a1f87f 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -151,7 +151,7 @@ xfs_filestream_pick_ag(
 	xfs_agnumber_t		ag, max_ag = NULLAGNUMBER;
 	int			err, trylock, nscan;
 
-	ASSERT(S_ISDIR(ip->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(ip)->i_mode));
 
 	/* 2% of an AG's blocks must be free for it to be chosen. */
 	minfree = mp->m_sb.sb_agblocks / 50;
@@ -319,7 +319,7 @@ xfs_filestream_lookup_ag(
 	xfs_agnumber_t		startag, ag = NULLAGNUMBER;
 	struct xfs_mru_cache_elem *mru;
 
-	ASSERT(S_ISREG(ip->i_d.di_mode));
+	ASSERT(S_ISREG(VFS_I(ip)->i_mode));
 
 	pip = xfs_filestream_get_parent(ip);
 	if (!pip)
diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h
index 1b6a98b66886..f32713f14f9a 100644
--- a/fs/xfs/xfs_fsops.h
+++ b/fs/xfs/xfs_fsops.h
@@ -25,6 +25,5 @@ extern int xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt);
 extern int xfs_reserve_blocks(xfs_mount_t *mp, __uint64_t *inval,
 				xfs_fsop_resblks_t *outval);
 extern int xfs_fs_goingdown(xfs_mount_t *mp, __uint32_t inflags);
-extern int xfs_fs_log_dummy(struct xfs_mount *mp);
 
 #endif	/* __XFS_FSOPS_H__ */
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index d7a490f24ead..bf2d60749278 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -63,6 +63,9 @@ xfs_inode_alloc(
 		return NULL;
 	}
 
+	/* VFS doesn't initialise i_mode! */
+	VFS_I(ip)->i_mode = 0;
+
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!spin_is_locked(&ip->i_flags_lock));
@@ -79,7 +82,7 @@ xfs_inode_alloc(
 	memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
 	ip->i_flags = 0;
 	ip->i_delayed_blks = 0;
-	memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
+	memset(&ip->i_d, 0, sizeof(ip->i_d));
 
 	return ip;
 }
@@ -98,7 +101,7 @@ void
 xfs_inode_free(
 	struct xfs_inode	*ip)
 {
-	switch (ip->i_d.di_mode & S_IFMT) {
+	switch (VFS_I(ip)->i_mode & S_IFMT) {
 	case S_IFREG:
 	case S_IFDIR:
 	case S_IFLNK:
@@ -135,6 +138,34 @@ xfs_inode_free(
 }
 
 /*
+ * When we recycle a reclaimable inode, we need to re-initialise the VFS inode
+ * part of the structure. This is made more complex by the fact we store
+ * information about the on-disk values in the VFS inode and so we can't just
+ * overwrite the values unconditionally. Hence we save the parameters we
+ * need to retain across reinitialisation, and rewrite them into the VFS inode
+ * after reinitialisation even if it fails.
+ */
+static int
+xfs_reinit_inode(
+	struct xfs_mount	*mp,
+	struct inode		*inode)
+{
+	int		error;
+	uint32_t	nlink = inode->i_nlink;
+	uint32_t	generation = inode->i_generation;
+	uint64_t	version = inode->i_version;
+	umode_t		mode = inode->i_mode;
+
+	error = inode_init_always(mp->m_super, inode);
+
+	set_nlink(inode, nlink);
+	inode->i_generation = generation;
+	inode->i_version = version;
+	inode->i_mode = mode;
+	return error;
+}
+
+/*
  * Check the validity of the inode we just found it the cache
  */
 static int
@@ -185,7 +216,7 @@ xfs_iget_cache_hit(
 	/*
 	 * If lookup is racing with unlink return an error immediately.
 	 */
-	if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
+	if (VFS_I(ip)->i_mode == 0 && !(flags & XFS_IGET_CREATE)) {
 		error = -ENOENT;
 		goto out_error;
 	}
@@ -208,7 +239,7 @@ xfs_iget_cache_hit(
 		spin_unlock(&ip->i_flags_lock);
 		rcu_read_unlock();
 
-		error = inode_init_always(mp->m_super, inode);
+		error = xfs_reinit_inode(mp, inode);
 		if (error) {
 			/*
 			 * Re-initializing the inode failed, and we are in deep
@@ -295,7 +326,7 @@ xfs_iget_cache_miss(
 
 	trace_xfs_iget_miss(ip);
 
-	if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
+	if ((VFS_I(ip)->i_mode == 0) && !(flags & XFS_IGET_CREATE)) {
 		error = -ENOENT;
 		goto out_destroy;
 	}
@@ -444,7 +475,7 @@ again:
 	 * If we have a real type for an on-disk inode, we can setup the inode
 	 * now.	 If it's a new inode being created, xfs_ialloc will handle it.
 	 */
-	if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0)
+	if (xfs_iflags_test(ip, XFS_INEW) && VFS_I(ip)->i_mode != 0)
 		xfs_setup_existing_inode(ip);
 	return 0;
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ceba1a83cacc..96f606deee31 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -57,9 +57,9 @@ kmem_zone_t *xfs_inode_zone;
  */
 #define	XFS_ITRUNC_MAX_EXTENTS	2
 
-STATIC int xfs_iflush_int(xfs_inode_t *, xfs_buf_t *);
-
-STATIC int xfs_iunlink_remove(xfs_trans_t *, xfs_inode_t *);
+STATIC int xfs_iflush_int(struct xfs_inode *, struct xfs_buf *);
+STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
+STATIC int xfs_iunlink_remove(struct xfs_trans *, struct xfs_inode *);
 
 /*
  * helper function to extract extent size hint from inode
@@ -766,6 +766,7 @@ xfs_ialloc(
 	uint		flags;
 	int		error;
 	struct timespec	tv;
+	struct inode	*inode;
 
 	/*
 	 * Call the space management code to pick
@@ -791,6 +792,7 @@ xfs_ialloc(
 	if (error)
 		return error;
 	ASSERT(ip != NULL);
+	inode = VFS_I(ip);
 
 	/*
 	 * We always convert v1 inodes to v2 now - we only support filesystems
@@ -800,20 +802,16 @@ xfs_ialloc(
 	if (ip->i_d.di_version == 1)
 		ip->i_d.di_version = 2;
 
-	ip->i_d.di_mode = mode;
-	ip->i_d.di_onlink = 0;
-	ip->i_d.di_nlink = nlink;
-	ASSERT(ip->i_d.di_nlink == nlink);
+	inode->i_mode = mode;
+	set_nlink(inode, nlink);
 	ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid());
 	ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid());
 	xfs_set_projid(ip, prid);
-	memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
 
 	if (pip && XFS_INHERIT_GID(pip)) {
 		ip->i_d.di_gid = pip->i_d.di_gid;
-		if ((pip->i_d.di_mode & S_ISGID) && S_ISDIR(mode)) {
-			ip->i_d.di_mode |= S_ISGID;
-		}
+		if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode))
+			inode->i_mode |= S_ISGID;
 	}
 
 	/*
@@ -822,38 +820,29 @@ xfs_ialloc(
 	 * (and only if the irix_sgid_inherit compatibility variable is set).
 	 */
 	if ((irix_sgid_inherit) &&
-	    (ip->i_d.di_mode & S_ISGID) &&
-	    (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid)))) {
-		ip->i_d.di_mode &= ~S_ISGID;
-	}
+	    (inode->i_mode & S_ISGID) &&
+	    (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid))))
+		inode->i_mode &= ~S_ISGID;
 
 	ip->i_d.di_size = 0;
 	ip->i_d.di_nextents = 0;
 	ASSERT(ip->i_d.di_nblocks == 0);
 
 	tv = current_fs_time(mp->m_super);
-	ip->i_d.di_mtime.t_sec = (__int32_t)tv.tv_sec;
-	ip->i_d.di_mtime.t_nsec = (__int32_t)tv.tv_nsec;
-	ip->i_d.di_atime = ip->i_d.di_mtime;
-	ip->i_d.di_ctime = ip->i_d.di_mtime;
+	inode->i_mtime = tv;
+	inode->i_atime = tv;
+	inode->i_ctime = tv;
 
-	/*
-	 * di_gen will have been taken care of in xfs_iread.
-	 */
 	ip->i_d.di_extsize = 0;
 	ip->i_d.di_dmevmask = 0;
 	ip->i_d.di_dmstate = 0;
 	ip->i_d.di_flags = 0;
 
 	if (ip->i_d.di_version == 3) {
-		ASSERT(ip->i_d.di_ino == ino);
-		ASSERT(uuid_equal(&ip->i_d.di_uuid, &mp->m_sb.sb_meta_uuid));
-		ip->i_d.di_crc = 0;
-		ip->i_d.di_changecount = 1;
-		ip->i_d.di_lsn = 0;
+		inode->i_version = 1;
 		ip->i_d.di_flags2 = 0;
-		memset(&(ip->i_d.di_pad2[0]), 0, sizeof(ip->i_d.di_pad2));
-		ip->i_d.di_crtime = ip->i_d.di_mtime;
+		ip->i_d.di_crtime.t_sec = (__int32_t)tv.tv_sec;
+		ip->i_d.di_crtime.t_nsec = (__int32_t)tv.tv_nsec;
 	}
 
 
@@ -1092,35 +1081,24 @@ xfs_dir_ialloc(
 }
 
 /*
- * Decrement the link count on an inode & log the change.
- * If this causes the link count to go to zero, initiate the
- * logging activity required to truncate a file.
+ * Decrement the link count on an inode & log the change.  If this causes the
+ * link count to go to zero, move the inode to AGI unlinked list so that it can
+ * be freed when the last active reference goes away via xfs_inactive().
  */
 int				/* error */
 xfs_droplink(
 	xfs_trans_t *tp,
 	xfs_inode_t *ip)
 {
-	int	error;
-
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
-	ASSERT (ip->i_d.di_nlink > 0);
-	ip->i_d.di_nlink--;
 	drop_nlink(VFS_I(ip));
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	error = 0;
-	if (ip->i_d.di_nlink == 0) {
-		/*
-		 * We're dropping the last link to this file.
-		 * Move the on-disk inode to the AGI unlinked list.
-		 * From xfs_inactive() we will pull the inode from
-		 * the list and free it.
-		 */
-		error = xfs_iunlink(tp, ip);
-	}
-	return error;
+	if (VFS_I(ip)->i_nlink)
+		return 0;
+
+	return xfs_iunlink(tp, ip);
 }
 
 /*
@@ -1134,8 +1112,6 @@ xfs_bumplink(
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
 	ASSERT(ip->i_d.di_version > 1);
-	ASSERT(ip->i_d.di_nlink > 0 || (VFS_I(ip)->i_state & I_LINKABLE));
-	ip->i_d.di_nlink++;
 	inc_nlink(VFS_I(ip));
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	return 0;
@@ -1393,7 +1369,6 @@ xfs_create_tmpfile(
 	 */
 	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
 
-	ip->i_d.di_nlink--;
 	error = xfs_iunlink(tp, ip);
 	if (error)
 		goto out_trans_cancel;
@@ -1444,7 +1419,7 @@ xfs_link(
 
 	trace_xfs_link(tdp, target_name);
 
-	ASSERT(!S_ISDIR(sip->i_d.di_mode));
+	ASSERT(!S_ISDIR(VFS_I(sip)->i_mode));
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
@@ -1492,7 +1467,10 @@ xfs_link(
 
 	xfs_bmap_init(&free_list, &first_block);
 
-	if (sip->i_d.di_nlink == 0) {
+	/*
+	 * Handle initial link state of O_TMPFILE inode
+	 */
+	if (VFS_I(sip)->i_nlink == 0) {
 		error = xfs_iunlink_remove(tp, sip);
 		if (error)
 			goto error_return;
@@ -1648,7 +1626,7 @@ xfs_release(
 	xfs_mount_t	*mp = ip->i_mount;
 	int		error;
 
-	if (!S_ISREG(ip->i_d.di_mode) || (ip->i_d.di_mode == 0))
+	if (!S_ISREG(VFS_I(ip)->i_mode) || (VFS_I(ip)->i_mode == 0))
 		return 0;
 
 	/* If this is a read-only mount, don't do this (would generate I/O) */
@@ -1679,7 +1657,7 @@ xfs_release(
 		}
 	}
 
-	if (ip->i_d.di_nlink == 0)
+	if (VFS_I(ip)->i_nlink == 0)
 		return 0;
 
 	if (xfs_can_free_eofblocks(ip, false)) {
@@ -1883,7 +1861,7 @@ xfs_inactive(
 	 * If the inode is already free, then there can be nothing
 	 * to clean up here.
 	 */
-	if (ip->i_d.di_mode == 0) {
+	if (VFS_I(ip)->i_mode == 0) {
 		ASSERT(ip->i_df.if_real_bytes == 0);
 		ASSERT(ip->i_df.if_broot_bytes == 0);
 		return;
@@ -1895,7 +1873,7 @@ xfs_inactive(
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
 		return;
 
-	if (ip->i_d.di_nlink != 0) {
+	if (VFS_I(ip)->i_nlink != 0) {
 		/*
 		 * force is true because we are evicting an inode from the
 		 * cache. Post-eof blocks must be freed, lest we end up with
@@ -1907,7 +1885,7 @@ xfs_inactive(
 		return;
 	}
 
-	if (S_ISREG(ip->i_d.di_mode) &&
+	if (S_ISREG(VFS_I(ip)->i_mode) &&
 	    (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
 	     ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
 		truncate = 1;
@@ -1916,7 +1894,7 @@ xfs_inactive(
 	if (error)
 		return;
 
-	if (S_ISLNK(ip->i_d.di_mode))
+	if (S_ISLNK(VFS_I(ip)->i_mode))
 		error = xfs_inactive_symlink(ip);
 	else if (truncate)
 		error = xfs_inactive_truncate(ip);
@@ -1952,16 +1930,21 @@ xfs_inactive(
 }
 
 /*
- * This is called when the inode's link count goes to 0.
- * We place the on-disk inode on a list in the AGI.  It
- * will be pulled from this list when the inode is freed.
+ * This is called when the inode's link count goes to 0 or we are creating a
+ * tmpfile via O_TMPFILE. In the case of a tmpfile, @ignore_linkcount will be
+ * set to true as the link count is dropped to zero by the VFS after we've
+ * created the file successfully, so we have to add it to the unlinked list
+ * while the link count is non-zero.
+ *
+ * We place the on-disk inode on a list in the AGI.  It will be pulled from this
+ * list when the inode is freed.
  */
-int
+STATIC int
 xfs_iunlink(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*ip)
+	struct xfs_trans *tp,
+	struct xfs_inode *ip)
 {
-	xfs_mount_t	*mp;
+	xfs_mount_t	*mp = tp->t_mountp;
 	xfs_agi_t	*agi;
 	xfs_dinode_t	*dip;
 	xfs_buf_t	*agibp;
@@ -1971,10 +1954,7 @@ xfs_iunlink(
 	int		offset;
 	int		error;
 
-	ASSERT(ip->i_d.di_nlink == 0);
-	ASSERT(ip->i_d.di_mode != 0);
-
-	mp = tp->t_mountp;
+	ASSERT(VFS_I(ip)->i_mode != 0);
 
 	/*
 	 * Get the agi buffer first.  It ensures lock ordering
@@ -2412,10 +2392,10 @@ xfs_ifree(
 	struct xfs_icluster	xic = { 0 };
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	ASSERT(ip->i_d.di_nlink == 0);
+	ASSERT(VFS_I(ip)->i_nlink == 0);
 	ASSERT(ip->i_d.di_nextents == 0);
 	ASSERT(ip->i_d.di_anextents == 0);
-	ASSERT(ip->i_d.di_size == 0 || !S_ISREG(ip->i_d.di_mode));
+	ASSERT(ip->i_d.di_size == 0 || !S_ISREG(VFS_I(ip)->i_mode));
 	ASSERT(ip->i_d.di_nblocks == 0);
 
 	/*
@@ -2429,7 +2409,7 @@ xfs_ifree(
 	if (error)
 		return error;
 
-	ip->i_d.di_mode = 0;		/* mark incore inode as free */
+	VFS_I(ip)->i_mode = 0;		/* mark incore inode as free */
 	ip->i_d.di_flags = 0;
 	ip->i_d.di_dmevmask = 0;
 	ip->i_d.di_forkoff = 0;		/* mark the attr fork not in use */
@@ -2439,7 +2419,7 @@ xfs_ifree(
 	 * Bump the generation count so no one will be confused
 	 * by reincarnations of this inode.
 	 */
-	ip->i_d.di_gen++;
+	VFS_I(ip)->i_generation++;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	if (xic.deleted)
@@ -2526,7 +2506,7 @@ xfs_remove(
 {
 	xfs_mount_t		*mp = dp->i_mount;
 	xfs_trans_t             *tp = NULL;
-	int			is_dir = S_ISDIR(ip->i_d.di_mode);
+	int			is_dir = S_ISDIR(VFS_I(ip)->i_mode);
 	int                     error = 0;
 	xfs_bmap_free_t         free_list;
 	xfs_fsblock_t           first_block;
@@ -2580,8 +2560,8 @@ xfs_remove(
 	 * If we're removing a directory perform some additional validation.
 	 */
 	if (is_dir) {
-		ASSERT(ip->i_d.di_nlink >= 2);
-		if (ip->i_d.di_nlink != 2) {
+		ASSERT(VFS_I(ip)->i_nlink >= 2);
+		if (VFS_I(ip)->i_nlink != 2) {
 			error = -ENOTEMPTY;
 			goto out_trans_cancel;
 		}
@@ -2771,7 +2751,7 @@ xfs_cross_rename(
 	if (dp1 != dp2) {
 		dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
 
-		if (S_ISDIR(ip2->i_d.di_mode)) {
+		if (S_ISDIR(VFS_I(ip2)->i_mode)) {
 			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
 						dp1->i_ino, first_block,
 						free_list, spaceres);
@@ -2779,7 +2759,7 @@ xfs_cross_rename(
 				goto out_trans_abort;
 
 			/* transfer ip2 ".." reference to dp1 */
-			if (!S_ISDIR(ip1->i_d.di_mode)) {
+			if (!S_ISDIR(VFS_I(ip1)->i_mode)) {
 				error = xfs_droplink(tp, dp2);
 				if (error)
 					goto out_trans_abort;
@@ -2798,7 +2778,7 @@ xfs_cross_rename(
 			ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
 		}
 
-		if (S_ISDIR(ip1->i_d.di_mode)) {
+		if (S_ISDIR(VFS_I(ip1)->i_mode)) {
 			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
 						dp2->i_ino, first_block,
 						free_list, spaceres);
@@ -2806,7 +2786,7 @@ xfs_cross_rename(
 				goto out_trans_abort;
 
 			/* transfer ip1 ".." reference to dp2 */
-			if (!S_ISDIR(ip2->i_d.di_mode)) {
+			if (!S_ISDIR(VFS_I(ip2)->i_mode)) {
 				error = xfs_droplink(tp, dp1);
 				if (error)
 					goto out_trans_abort;
@@ -2903,7 +2883,7 @@ xfs_rename(
 	struct xfs_inode	*inodes[__XFS_SORT_INODES];
 	int			num_inodes = __XFS_SORT_INODES;
 	bool			new_parent = (src_dp != target_dp);
-	bool			src_is_directory = S_ISDIR(src_ip->i_d.di_mode);
+	bool			src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
 	int			spaceres;
 	int			error;
 
@@ -3032,12 +3012,12 @@ xfs_rename(
 		 * target and source are directories and that target can be
 		 * destroyed, or that neither is a directory.
 		 */
-		if (S_ISDIR(target_ip->i_d.di_mode)) {
+		if (S_ISDIR(VFS_I(target_ip)->i_mode)) {
 			/*
 			 * Make sure target dir is empty.
 			 */
 			if (!(xfs_dir_isempty(target_ip)) ||
-			    (target_ip->i_d.di_nlink > 2)) {
+			    (VFS_I(target_ip)->i_nlink > 2)) {
 				error = -EEXIST;
 				goto out_trans_cancel;
 			}
@@ -3144,7 +3124,7 @@ xfs_rename(
 	 * intermediate state on disk.
 	 */
 	if (wip) {
-		ASSERT(VFS_I(wip)->i_nlink == 0 && wip->i_d.di_nlink == 0);
+		ASSERT(VFS_I(wip)->i_nlink == 0);
 		error = xfs_bumplink(tp, wip);
 		if (error)
 			goto out_bmap_cancel;
@@ -3313,7 +3293,7 @@ cluster_corrupt_out:
 		 * mark it as stale and brelse.
 		 */
 		if (bp->b_iodone) {
-			XFS_BUF_UNDONE(bp);
+			bp->b_flags &= ~XBF_DONE;
 			xfs_buf_stale(bp);
 			xfs_buf_ioerror(bp, -EIO);
 			xfs_buf_ioend(bp);
@@ -3462,14 +3442,7 @@ xfs_iflush_int(
 			__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
 		goto corrupt_out;
 	}
-	if (XFS_TEST_ERROR(ip->i_d.di_magic != XFS_DINODE_MAGIC,
-				mp, XFS_ERRTAG_IFLUSH_2, XFS_RANDOM_IFLUSH_2)) {
-		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
-			"%s: Bad inode %Lu, ptr 0x%p, magic number 0x%x",
-			__func__, ip->i_ino, ip, ip->i_d.di_magic);
-		goto corrupt_out;
-	}
-	if (S_ISREG(ip->i_d.di_mode)) {
+	if (S_ISREG(VFS_I(ip)->i_mode)) {
 		if (XFS_TEST_ERROR(
 		    (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
 		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE),
@@ -3479,7 +3452,7 @@ xfs_iflush_int(
 				__func__, ip->i_ino, ip);
 			goto corrupt_out;
 		}
-	} else if (S_ISDIR(ip->i_d.di_mode)) {
+	} else if (S_ISDIR(VFS_I(ip)->i_mode)) {
 		if (XFS_TEST_ERROR(
 		    (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
 		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
@@ -3523,12 +3496,11 @@ xfs_iflush_int(
 		ip->i_d.di_flushiter++;
 
 	/*
-	 * Copy the dirty parts of the inode into the on-disk
-	 * inode.  We always copy out the core of the inode,
-	 * because if the inode is dirty at all the core must
-	 * be.
+	 * Copy the dirty parts of the inode into the on-disk inode.  We always
+	 * copy out the core of the inode, because if the inode is dirty at all
+	 * the core must be.
 	 */
-	xfs_dinode_to_disk(dip, &ip->i_d);
+	xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn);
 
 	/* Wrap, we never let the log put out DI_MAX_FLUSH */
 	if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
@@ -3580,10 +3552,6 @@ xfs_iflush_int(
 	 */
 	xfs_buf_attach_iodone(bp, xfs_iflush_done, &iip->ili_item);
 
-	/* update the lsn in the on disk inode if required */
-	if (ip->i_d.di_version == 3)
-		dip->di_lsn = cpu_to_be64(iip->ili_item.li_lsn);
-
 	/* generate the checksum. */
 	xfs_dinode_calc_crc(mp, dip);
 
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index ca9e11989cbd..43e1d51b15eb 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -63,7 +63,7 @@ typedef struct xfs_inode {
 	unsigned long		i_flags;	/* see defined flags below */
 	unsigned int		i_delayed_blks;	/* count of delay alloc blks */
 
-	xfs_icdinode_t		i_d;		/* most of ondisk inode */
+	struct xfs_icdinode	i_d;		/* most of ondisk inode */
 
 	/* VFS inode */
 	struct inode		i_vnode;	/* embedded VFS inode */
@@ -88,7 +88,7 @@ static inline struct inode *VFS_I(struct xfs_inode *ip)
  */
 static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip)
 {
-	if (S_ISREG(ip->i_d.di_mode))
+	if (S_ISREG(VFS_I(ip)->i_mode))
 		return i_size_read(VFS_I(ip));
 	return ip->i_d.di_size;
 }
@@ -369,7 +369,7 @@ static inline int xfs_isiflocked(struct xfs_inode *ip)
  */
 #define XFS_INHERIT_GID(pip)	\
 	(((pip)->i_mount->m_flags & XFS_MOUNT_GRPID) || \
-	 ((pip)->i_d.di_mode & S_ISGID))
+	 (VFS_I(pip)->i_mode & S_ISGID))
 
 int		xfs_release(struct xfs_inode *ip);
 void		xfs_inactive(struct xfs_inode *ip);
@@ -405,8 +405,6 @@ int		xfs_ifree(struct xfs_trans *, xfs_inode_t *,
 			   struct xfs_bmap_free *);
 int		xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *,
 				      int, xfs_fsize_t);
-int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
-
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
 
 void		xfs_iunpin_wait(xfs_inode_t *);
@@ -437,6 +435,8 @@ int	xfs_update_prealloc_flags(struct xfs_inode *ip,
 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);
+loff_t	__xfs_seek_hole_data(struct inode *inode, loff_t start,
+			     loff_t eof, int whence);
 
 
 /* from xfs_iops.c */
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index d14b12b8cfef..c48b5b18d771 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -135,7 +135,7 @@ xfs_inode_item_size(
 
 	*nvecs += 2;
 	*nbytes += sizeof(struct xfs_inode_log_format) +
-		   xfs_icdinode_size(ip->i_d.di_version);
+		   xfs_log_dinode_size(ip->i_d.di_version);
 
 	xfs_inode_item_data_fork_size(iip, nvecs, nbytes);
 	if (XFS_IFORK_Q(ip))
@@ -322,6 +322,81 @@ xfs_inode_item_format_attr_fork(
 	}
 }
 
+static void
+xfs_inode_to_log_dinode(
+	struct xfs_inode	*ip,
+	struct xfs_log_dinode	*to,
+	xfs_lsn_t		lsn)
+{
+	struct xfs_icdinode	*from = &ip->i_d;
+	struct inode		*inode = VFS_I(ip);
+
+	to->di_magic = XFS_DINODE_MAGIC;
+
+	to->di_version = from->di_version;
+	to->di_format = from->di_format;
+	to->di_uid = from->di_uid;
+	to->di_gid = from->di_gid;
+	to->di_projid_lo = from->di_projid_lo;
+	to->di_projid_hi = from->di_projid_hi;
+
+	memset(to->di_pad, 0, sizeof(to->di_pad));
+	memset(to->di_pad3, 0, sizeof(to->di_pad3));
+	to->di_atime.t_sec = inode->i_atime.tv_sec;
+	to->di_atime.t_nsec = inode->i_atime.tv_nsec;
+	to->di_mtime.t_sec = inode->i_mtime.tv_sec;
+	to->di_mtime.t_nsec = inode->i_mtime.tv_nsec;
+	to->di_ctime.t_sec = inode->i_ctime.tv_sec;
+	to->di_ctime.t_nsec = inode->i_ctime.tv_nsec;
+	to->di_nlink = inode->i_nlink;
+	to->di_gen = inode->i_generation;
+	to->di_mode = inode->i_mode;
+
+	to->di_size = from->di_size;
+	to->di_nblocks = from->di_nblocks;
+	to->di_extsize = from->di_extsize;
+	to->di_nextents = from->di_nextents;
+	to->di_anextents = from->di_anextents;
+	to->di_forkoff = from->di_forkoff;
+	to->di_aformat = from->di_aformat;
+	to->di_dmevmask = from->di_dmevmask;
+	to->di_dmstate = from->di_dmstate;
+	to->di_flags = from->di_flags;
+
+	if (from->di_version == 3) {
+		to->di_changecount = inode->i_version;
+		to->di_crtime.t_sec = from->di_crtime.t_sec;
+		to->di_crtime.t_nsec = from->di_crtime.t_nsec;
+		to->di_flags2 = from->di_flags2;
+
+		to->di_ino = ip->i_ino;
+		to->di_lsn = lsn;
+		memset(to->di_pad2, 0, sizeof(to->di_pad2));
+		uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
+		to->di_flushiter = 0;
+	} else {
+		to->di_flushiter = from->di_flushiter;
+	}
+}
+
+/*
+ * Format the inode core. Current timestamp data is only in the VFS inode
+ * fields, so we need to grab them from there. Hence rather than just copying
+ * the XFS inode core structure, format the fields directly into the iovec.
+ */
+static void
+xfs_inode_item_format_core(
+	struct xfs_inode	*ip,
+	struct xfs_log_vec	*lv,
+	struct xfs_log_iovec	**vecp)
+{
+	struct xfs_log_dinode	*dic;
+
+	dic = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_ICORE);
+	xfs_inode_to_log_dinode(ip, dic, ip->i_itemp->ili_item.li_lsn);
+	xlog_finish_iovec(lv, *vecp, xfs_log_dinode_size(ip->i_d.di_version));
+}
+
 /*
  * This is called to fill in the vector of log iovecs for the given inode
  * log item.  It fills the first item with an inode log format structure,
@@ -351,10 +426,7 @@ xfs_inode_item_format(
 	ilf->ilf_size = 2; /* format + core */
 	xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format));
 
-	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ICORE,
-			&ip->i_d,
-			xfs_icdinode_size(ip->i_d.di_version));
-
+	xfs_inode_item_format_core(ip, lv, &vecp);
 	xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp);
 	if (XFS_IFORK_Q(ip)) {
 		xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 478d04e07f95..bcb6c19ce3ea 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -114,7 +114,7 @@ xfs_find_handle(
 		handle.ha_fid.fid_len = sizeof(xfs_fid_t) -
 					sizeof(handle.ha_fid.fid_len);
 		handle.ha_fid.fid_pad = 0;
-		handle.ha_fid.fid_gen = ip->i_d.di_gen;
+		handle.ha_fid.fid_gen = inode->i_generation;
 		handle.ha_fid.fid_ino = ip->i_ino;
 
 		hsize = XFS_HSIZE(handle);
@@ -963,7 +963,7 @@ xfs_set_diflags(
 		di_flags |= XFS_DIFLAG_NODEFRAG;
 	if (xflags & FS_XFLAG_FILESTREAM)
 		di_flags |= XFS_DIFLAG_FILESTREAM;
-	if (S_ISDIR(ip->i_d.di_mode)) {
+	if (S_ISDIR(VFS_I(ip)->i_mode)) {
 		if (xflags & FS_XFLAG_RTINHERIT)
 			di_flags |= XFS_DIFLAG_RTINHERIT;
 		if (xflags & FS_XFLAG_NOSYMLINKS)
@@ -972,7 +972,7 @@ xfs_set_diflags(
 			di_flags |= XFS_DIFLAG_EXTSZINHERIT;
 		if (xflags & FS_XFLAG_PROJINHERIT)
 			di_flags |= XFS_DIFLAG_PROJINHERIT;
-	} else if (S_ISREG(ip->i_d.di_mode)) {
+	} else if (S_ISREG(VFS_I(ip)->i_mode)) {
 		if (xflags & FS_XFLAG_REALTIME)
 			di_flags |= XFS_DIFLAG_REALTIME;
 		if (xflags & FS_XFLAG_EXTSIZE)
@@ -1060,23 +1060,86 @@ xfs_ioctl_setattr_xflags(
 }
 
 /*
+ * If we are changing DAX flags, we have to ensure the file is clean and any
+ * cached objects in the address space are invalidated and removed. This
+ * requires us to lock out other IO and page faults similar to a truncate
+ * operation. The locks need to be held until the transaction has been committed
+ * so that the cache invalidation is atomic with respect to the DAX flag
+ * manipulation.
+ */
+static int
+xfs_ioctl_setattr_dax_invalidate(
+	struct xfs_inode	*ip,
+	struct fsxattr		*fa,
+	int			*join_flags)
+{
+	struct inode		*inode = VFS_I(ip);
+	int			error;
+
+	*join_flags = 0;
+
+	/*
+	 * It is only valid to set the DAX flag on regular files and
+	 * directories on filesystems where the block size is equal to the page
+	 * size. On directories it serves as an inherit hint.
+	 */
+	if (fa->fsx_xflags & FS_XFLAG_DAX) {
+		if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
+			return -EINVAL;
+		if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE)
+			return -EINVAL;
+	}
+
+	/* If the DAX state is not changing, we have nothing to do here. */
+	if ((fa->fsx_xflags & FS_XFLAG_DAX) && IS_DAX(inode))
+		return 0;
+	if (!(fa->fsx_xflags & FS_XFLAG_DAX) && !IS_DAX(inode))
+		return 0;
+
+	/* lock, flush and invalidate mapping in preparation for flag change */
+	xfs_ilock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
+	error = filemap_write_and_wait(inode->i_mapping);
+	if (error)
+		goto out_unlock;
+	error = invalidate_inode_pages2(inode->i_mapping);
+	if (error)
+		goto out_unlock;
+
+	*join_flags = XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL;
+	return 0;
+
+out_unlock:
+	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
+	return error;
+
+}
+
+/*
  * 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.
+ *
+ * The inode might already be IO locked on call. If this is the case, it is
+ * indicated in @join_flags and we take full responsibility for ensuring they
+ * are unlocked from now on. Hence if we have an error here, we still have to
+ * unlock them. Otherwise, once they are joined to the transaction, they will
+ * be unlocked on commit/cancel.
  */
 static struct xfs_trans *
 xfs_ioctl_setattr_get_trans(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	int			join_flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
-	int			error;
+	int			error = -EROFS;
 
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
-		return ERR_PTR(-EROFS);
+		goto out_unlock;
+	error = -EIO;
 	if (XFS_FORCED_SHUTDOWN(mp))
-		return ERR_PTR(-EIO);
+		goto out_unlock;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
@@ -1084,7 +1147,8 @@ xfs_ioctl_setattr_get_trans(
 		goto out_cancel;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags);
+	join_flags = 0;
 
 	/*
 	 * CAP_FOWNER overrides the following restrictions:
@@ -1104,6 +1168,9 @@ xfs_ioctl_setattr_get_trans(
 
 out_cancel:
 	xfs_trans_cancel(tp);
+out_unlock:
+	if (join_flags)
+		xfs_iunlock(ip, join_flags);
 	return ERR_PTR(error);
 }
 
@@ -1128,14 +1195,14 @@ xfs_ioctl_setattr_check_extsize(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
-	if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode))
+	if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(VFS_I(ip)->i_mode))
 		return -EINVAL;
 
 	if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) &&
-	    !S_ISDIR(ip->i_d.di_mode))
+	    !S_ISDIR(VFS_I(ip)->i_mode))
 		return -EINVAL;
 
-	if (S_ISREG(ip->i_d.di_mode) && ip->i_d.di_nextents &&
+	if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_d.di_nextents &&
 	    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
 		return -EINVAL;
 
@@ -1202,6 +1269,7 @@ xfs_ioctl_setattr(
 	struct xfs_dquot	*pdqp = NULL;
 	struct xfs_dquot	*olddquot = NULL;
 	int			code;
+	int			join_flags = 0;
 
 	trace_xfs_ioctl_setattr(ip);
 
@@ -1225,7 +1293,18 @@ xfs_ioctl_setattr(
 			return code;
 	}
 
-	tp = xfs_ioctl_setattr_get_trans(ip);
+	/*
+	 * Changing DAX config may require inode locking for mapping
+	 * invalidation. These need to be held all the way to transaction commit
+	 * or cancel time, so need to be passed through to
+	 * xfs_ioctl_setattr_get_trans() so it can apply them to the join call
+	 * appropriately.
+	 */
+	code = xfs_ioctl_setattr_dax_invalidate(ip, fa, &join_flags);
+	if (code)
+		goto error_free_dquots;
+
+	tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
 	if (IS_ERR(tp)) {
 		code = PTR_ERR(tp);
 		goto error_free_dquots;
@@ -1256,9 +1335,9 @@ xfs_ioctl_setattr(
 	 * successful return from chown()
 	 */
 
-	if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
+	if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) &&
 	    !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
-		ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
+		VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);
 
 	/* Change the ownerships and register project quota modifications */
 	if (xfs_get_projid(ip) != fa->fsx_projid) {
@@ -1341,6 +1420,7 @@ xfs_ioc_setxflags(
 	struct xfs_trans	*tp;
 	struct fsxattr		fa;
 	unsigned int		flags;
+	int			join_flags = 0;
 	int			error;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
@@ -1357,7 +1437,18 @@ xfs_ioc_setxflags(
 	if (error)
 		return error;
 
-	tp = xfs_ioctl_setattr_get_trans(ip);
+	/*
+	 * Changing DAX config may require inode locking for mapping
+	 * invalidation. These need to be held all the way to transaction commit
+	 * or cancel time, so need to be passed through to
+	 * xfs_ioctl_setattr_get_trans() so it can apply them to the join call
+	 * appropriately.
+	 */
+	error = xfs_ioctl_setattr_dax_invalidate(ip, &fa, &join_flags);
+	if (error)
+		goto out_drop_write;
+
+	tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
 	if (IS_ERR(tp)) {
 		error = PTR_ERR(tp);
 		goto out_drop_write;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 76b71a1c6c32..fb7dc61f4a29 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -459,8 +459,8 @@ xfs_vn_getattr(
 
 	stat->size = XFS_ISIZE(ip);
 	stat->dev = inode->i_sb->s_dev;
-	stat->mode = ip->i_d.di_mode;
-	stat->nlink = ip->i_d.di_nlink;
+	stat->mode = inode->i_mode;
+	stat->nlink = inode->i_nlink;
 	stat->uid = inode->i_uid;
 	stat->gid = inode->i_gid;
 	stat->ino = ip->i_ino;
@@ -506,9 +506,6 @@ xfs_setattr_mode(
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
-	ip->i_d.di_mode &= S_IFMT;
-	ip->i_d.di_mode |= mode & ~S_IFMT;
-
 	inode->i_mode &= S_IFMT;
 	inode->i_mode |= mode & ~S_IFMT;
 }
@@ -522,21 +519,12 @@ xfs_setattr_time(
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
-	if (iattr->ia_valid & ATTR_ATIME) {
+	if (iattr->ia_valid & ATTR_ATIME)
 		inode->i_atime = iattr->ia_atime;
-		ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
-		ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
-	}
-	if (iattr->ia_valid & ATTR_CTIME) {
+	if (iattr->ia_valid & ATTR_CTIME)
 		inode->i_ctime = iattr->ia_ctime;
-		ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
-		ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
-	}
-	if (iattr->ia_valid & ATTR_MTIME) {
+	if (iattr->ia_valid & ATTR_MTIME)
 		inode->i_mtime = iattr->ia_mtime;
-		ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
-		ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
-	}
 }
 
 int
@@ -661,9 +649,9 @@ xfs_setattr_nonsize(
 		 * 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)) &&
+		if ((inode->i_mode & (S_ISUID|S_ISGID)) &&
 		    !capable(CAP_FSETID))
-			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
+			inode->i_mode &= ~(S_ISUID|S_ISGID);
 
 		/*
 		 * Change the ownerships and register quota modifications
@@ -773,7 +761,7 @@ xfs_setattr_size(
 
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
-	ASSERT(S_ISREG(ip->i_d.di_mode));
+	ASSERT(S_ISREG(inode->i_mode));
 	ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
 		ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
 
@@ -991,21 +979,13 @@ xfs_vn_update_time(
 	}
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if (flags & S_CTIME) {
+	if (flags & S_CTIME)
 		inode->i_ctime = *now;
-		ip->i_d.di_ctime.t_sec = (__int32_t)now->tv_sec;
-		ip->i_d.di_ctime.t_nsec = (__int32_t)now->tv_nsec;
-	}
-	if (flags & S_MTIME) {
+	if (flags & S_MTIME)
 		inode->i_mtime = *now;
-		ip->i_d.di_mtime.t_sec = (__int32_t)now->tv_sec;
-		ip->i_d.di_mtime.t_nsec = (__int32_t)now->tv_nsec;
-	}
-	if (flags & S_ATIME) {
+	if (flags & S_ATIME)
 		inode->i_atime = *now;
-		ip->i_d.di_atime.t_sec = (__int32_t)now->tv_sec;
-		ip->i_d.di_atime.t_nsec = (__int32_t)now->tv_nsec;
-	}
+
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
 	return xfs_trans_commit(tp);
@@ -1205,8 +1185,10 @@ xfs_diflags_to_iflags(
 		inode->i_flags |= S_SYNC;
 	if (flags & XFS_DIFLAG_NOATIME)
 		inode->i_flags |= S_NOATIME;
-	if (ip->i_mount->m_flags & XFS_MOUNT_DAX ||
-	    ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+	if (S_ISREG(inode->i_mode) &&
+	    ip->i_mount->m_sb.sb_blocksize == PAGE_SIZE &&
+	    (ip->i_mount->m_flags & XFS_MOUNT_DAX ||
+	     ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))
 		inode->i_flags |= S_DAX;
 }
 
@@ -1232,8 +1214,6 @@ xfs_setup_inode(
 	/* make the inode look hashed for the writeback code */
 	hlist_add_fake(&inode->i_hash);
 
-	inode->i_mode	= ip->i_d.di_mode;
-	set_nlink(inode, ip->i_d.di_nlink);
 	inode->i_uid    = xfs_uid_to_kuid(ip->i_d.di_uid);
 	inode->i_gid    = xfs_gid_to_kgid(ip->i_d.di_gid);
 
@@ -1249,14 +1229,7 @@ xfs_setup_inode(
 		break;
 	}
 
-	inode->i_generation = ip->i_d.di_gen;
 	i_size_write(inode, ip->i_d.di_size);
-	inode->i_atime.tv_sec	= ip->i_d.di_atime.t_sec;
-	inode->i_atime.tv_nsec	= ip->i_d.di_atime.t_nsec;
-	inode->i_mtime.tv_sec	= ip->i_d.di_mtime.t_sec;
-	inode->i_mtime.tv_nsec	= ip->i_d.di_mtime.t_nsec;
-	inode->i_ctime.tv_sec	= ip->i_d.di_ctime.t_sec;
-	inode->i_ctime.tv_nsec	= ip->i_d.di_ctime.t_nsec;
 	xfs_diflags_to_iflags(inode, ip);
 
 	ip->d_ops = ip->i_mount->m_nondir_inode_ops;
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 930ebd86beba..ce73eb34620d 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -57,6 +57,7 @@ xfs_bulkstat_one_int(
 {
 	struct xfs_icdinode	*dic;		/* dinode core info pointer */
 	struct xfs_inode	*ip;		/* incore inode pointer */
+	struct inode		*inode;
 	struct xfs_bstat	*buf;		/* return buffer */
 	int			error = 0;	/* error value */
 
@@ -77,30 +78,33 @@ xfs_bulkstat_one_int(
 
 	ASSERT(ip != NULL);
 	ASSERT(ip->i_imap.im_blkno != 0);
+	inode = VFS_I(ip);
 
 	dic = &ip->i_d;
 
 	/* xfs_iget returns the following without needing
 	 * further change.
 	 */
-	buf->bs_nlink = dic->di_nlink;
 	buf->bs_projid_lo = dic->di_projid_lo;
 	buf->bs_projid_hi = dic->di_projid_hi;
 	buf->bs_ino = ino;
-	buf->bs_mode = dic->di_mode;
 	buf->bs_uid = dic->di_uid;
 	buf->bs_gid = dic->di_gid;
 	buf->bs_size = dic->di_size;
-	buf->bs_atime.tv_sec = dic->di_atime.t_sec;
-	buf->bs_atime.tv_nsec = dic->di_atime.t_nsec;
-	buf->bs_mtime.tv_sec = dic->di_mtime.t_sec;
-	buf->bs_mtime.tv_nsec = dic->di_mtime.t_nsec;
-	buf->bs_ctime.tv_sec = dic->di_ctime.t_sec;
-	buf->bs_ctime.tv_nsec = dic->di_ctime.t_nsec;
+
+	buf->bs_nlink = inode->i_nlink;
+	buf->bs_atime.tv_sec = inode->i_atime.tv_sec;
+	buf->bs_atime.tv_nsec = inode->i_atime.tv_nsec;
+	buf->bs_mtime.tv_sec = inode->i_mtime.tv_sec;
+	buf->bs_mtime.tv_nsec = inode->i_mtime.tv_nsec;
+	buf->bs_ctime.tv_sec = inode->i_ctime.tv_sec;
+	buf->bs_ctime.tv_nsec = inode->i_ctime.tv_nsec;
+	buf->bs_gen = inode->i_generation;
+	buf->bs_mode = inode->i_mode;
+
 	buf->bs_xflags = xfs_ip2xflags(ip);
 	buf->bs_extsize = dic->di_extsize << mp->m_sb.sb_blocklog;
 	buf->bs_extents = dic->di_nextents;
-	buf->bs_gen = dic->di_gen;
 	memset(buf->bs_pad, 0, sizeof(buf->bs_pad));
 	buf->bs_dmevmask = dic->di_dmevmask;
 	buf->bs_dmstate = dic->di_dmstate;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 9c9a1c9bcc7f..b49ccf5c1d75 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1212,7 +1212,7 @@ xlog_iodone(xfs_buf_t *bp)
 	}
 
 	/* log I/O is always issued ASYNC */
-	ASSERT(XFS_BUF_ISASYNC(bp));
+	ASSERT(bp->b_flags & XBF_ASYNC);
 	xlog_state_done_syncing(iclog, aborted);
 
 	/*
@@ -1864,9 +1864,8 @@ xlog_sync(
 
 	bp->b_io_length = BTOBB(count);
 	bp->b_fspriv = iclog;
-	XFS_BUF_ZEROFLAGS(bp);
-	XFS_BUF_ASYNC(bp);
-	bp->b_flags |= XBF_SYNCIO;
+	bp->b_flags &= ~(XBF_FUA | XBF_FLUSH);
+	bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE);
 
 	if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) {
 		bp->b_flags |= XBF_FUA;
@@ -1893,12 +1892,11 @@ xlog_sync(
 
 	/* account for log which doesn't start at block #0 */
 	XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart);
+
 	/*
 	 * Don't call xfs_bwrite here. We do log-syncs even when the filesystem
 	 * is shutting down.
 	 */
-	XFS_BUF_WRITE(bp);
-
 	error = xlog_bdstrat(bp);
 	if (error) {
 		xfs_buf_ioerror_alert(bp, "xlog_sync");
@@ -1910,9 +1908,8 @@ xlog_sync(
 		xfs_buf_associate_memory(bp,
 				(char *)&iclog->ic_header + count, split);
 		bp->b_fspriv = iclog;
-		XFS_BUF_ZEROFLAGS(bp);
-		XFS_BUF_ASYNC(bp);
-		bp->b_flags |= XBF_SYNCIO;
+		bp->b_flags &= ~(XBF_FUA | XBF_FLUSH);
+		bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE);
 		if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
 			bp->b_flags |= XBF_FUA;
 
@@ -1921,7 +1918,6 @@ xlog_sync(
 
 		/* account for internal log which doesn't start at block #0 */
 		XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart);
-		XFS_BUF_WRITE(bp);
 		error = xlog_bdstrat(bp);
 		if (error) {
 			xfs_buf_ioerror_alert(bp, "xlog_sync (split)");
@@ -2012,77 +2008,81 @@ xlog_print_tic_res(
 	uint ophdr_spc = ticket->t_res_num_ophdrs * (uint)sizeof(xlog_op_header_t);
 
 	/* match with XLOG_REG_TYPE_* in xfs_log.h */
-	static char *res_type_str[XLOG_REG_TYPE_MAX] = {
-	    "bformat",
-	    "bchunk",
-	    "efi_format",
-	    "efd_format",
-	    "iformat",
-	    "icore",
-	    "iext",
-	    "ibroot",
-	    "ilocal",
-	    "iattr_ext",
-	    "iattr_broot",
-	    "iattr_local",
-	    "qformat",
-	    "dquot",
-	    "quotaoff",
-	    "LR header",
-	    "unmount",
-	    "commit",
-	    "trans header"
+#define REG_TYPE_STR(type, str)	[XLOG_REG_TYPE_##type] = str
+	static char *res_type_str[XLOG_REG_TYPE_MAX + 1] = {
+	    REG_TYPE_STR(BFORMAT, "bformat"),
+	    REG_TYPE_STR(BCHUNK, "bchunk"),
+	    REG_TYPE_STR(EFI_FORMAT, "efi_format"),
+	    REG_TYPE_STR(EFD_FORMAT, "efd_format"),
+	    REG_TYPE_STR(IFORMAT, "iformat"),
+	    REG_TYPE_STR(ICORE, "icore"),
+	    REG_TYPE_STR(IEXT, "iext"),
+	    REG_TYPE_STR(IBROOT, "ibroot"),
+	    REG_TYPE_STR(ILOCAL, "ilocal"),
+	    REG_TYPE_STR(IATTR_EXT, "iattr_ext"),
+	    REG_TYPE_STR(IATTR_BROOT, "iattr_broot"),
+	    REG_TYPE_STR(IATTR_LOCAL, "iattr_local"),
+	    REG_TYPE_STR(QFORMAT, "qformat"),
+	    REG_TYPE_STR(DQUOT, "dquot"),
+	    REG_TYPE_STR(QUOTAOFF, "quotaoff"),
+	    REG_TYPE_STR(LRHEADER, "LR header"),
+	    REG_TYPE_STR(UNMOUNT, "unmount"),
+	    REG_TYPE_STR(COMMIT, "commit"),
+	    REG_TYPE_STR(TRANSHDR, "trans header"),
+	    REG_TYPE_STR(ICREATE, "inode create")
 	};
+#undef REG_TYPE_STR
+#define TRANS_TYPE_STR(type)	[XFS_TRANS_##type] = #type
 	static char *trans_type_str[XFS_TRANS_TYPE_MAX] = {
-	    "SETATTR_NOT_SIZE",
-	    "SETATTR_SIZE",
-	    "INACTIVE",
-	    "CREATE",
-	    "CREATE_TRUNC",
-	    "TRUNCATE_FILE",
-	    "REMOVE",
-	    "LINK",
-	    "RENAME",
-	    "MKDIR",
-	    "RMDIR",
-	    "SYMLINK",
-	    "SET_DMATTRS",
-	    "GROWFS",
-	    "STRAT_WRITE",
-	    "DIOSTRAT",
-	    "WRITE_SYNC",
-	    "WRITEID",
-	    "ADDAFORK",
-	    "ATTRINVAL",
-	    "ATRUNCATE",
-	    "ATTR_SET",
-	    "ATTR_RM",
-	    "ATTR_FLAG",
-	    "CLEAR_AGI_BUCKET",
-	    "QM_SBCHANGE",
-	    "DUMMY1",
-	    "DUMMY2",
-	    "QM_QUOTAOFF",
-	    "QM_DQALLOC",
-	    "QM_SETQLIM",
-	    "QM_DQCLUSTER",
-	    "QM_QINOCREATE",
-	    "QM_QUOTAOFF_END",
-	    "FSYNC_TS",
-	    "GROWFSRT_ALLOC",
-	    "GROWFSRT_ZERO",
-	    "GROWFSRT_FREE",
-	    "SWAPEXT",
-	    "CHECKPOINT",
-	    "ICREATE",
-	    "CREATE_TMPFILE"
+	    TRANS_TYPE_STR(SETATTR_NOT_SIZE),
+	    TRANS_TYPE_STR(SETATTR_SIZE),
+	    TRANS_TYPE_STR(INACTIVE),
+	    TRANS_TYPE_STR(CREATE),
+	    TRANS_TYPE_STR(CREATE_TRUNC),
+	    TRANS_TYPE_STR(TRUNCATE_FILE),
+	    TRANS_TYPE_STR(REMOVE),
+	    TRANS_TYPE_STR(LINK),
+	    TRANS_TYPE_STR(RENAME),
+	    TRANS_TYPE_STR(MKDIR),
+	    TRANS_TYPE_STR(RMDIR),
+	    TRANS_TYPE_STR(SYMLINK),
+	    TRANS_TYPE_STR(SET_DMATTRS),
+	    TRANS_TYPE_STR(GROWFS),
+	    TRANS_TYPE_STR(STRAT_WRITE),
+	    TRANS_TYPE_STR(DIOSTRAT),
+	    TRANS_TYPE_STR(WRITEID),
+	    TRANS_TYPE_STR(ADDAFORK),
+	    TRANS_TYPE_STR(ATTRINVAL),
+	    TRANS_TYPE_STR(ATRUNCATE),
+	    TRANS_TYPE_STR(ATTR_SET),
+	    TRANS_TYPE_STR(ATTR_RM),
+	    TRANS_TYPE_STR(ATTR_FLAG),
+	    TRANS_TYPE_STR(CLEAR_AGI_BUCKET),
+	    TRANS_TYPE_STR(SB_CHANGE),
+	    TRANS_TYPE_STR(DUMMY1),
+	    TRANS_TYPE_STR(DUMMY2),
+	    TRANS_TYPE_STR(QM_QUOTAOFF),
+	    TRANS_TYPE_STR(QM_DQALLOC),
+	    TRANS_TYPE_STR(QM_SETQLIM),
+	    TRANS_TYPE_STR(QM_DQCLUSTER),
+	    TRANS_TYPE_STR(QM_QINOCREATE),
+	    TRANS_TYPE_STR(QM_QUOTAOFF_END),
+	    TRANS_TYPE_STR(FSYNC_TS),
+	    TRANS_TYPE_STR(GROWFSRT_ALLOC),
+	    TRANS_TYPE_STR(GROWFSRT_ZERO),
+	    TRANS_TYPE_STR(GROWFSRT_FREE),
+	    TRANS_TYPE_STR(SWAPEXT),
+	    TRANS_TYPE_STR(CHECKPOINT),
+	    TRANS_TYPE_STR(ICREATE),
+	    TRANS_TYPE_STR(CREATE_TMPFILE)
 	};
+#undef TRANS_TYPE_STR
 
 	xfs_warn(mp, "xlog_write: reservation summary:");
 	xfs_warn(mp, "  trans type  = %s (%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]),
+		  "bad-trans-type" : trans_type_str[ticket->t_trans_type]),
 		 ticket->t_trans_type);
 	xfs_warn(mp, "  unit res    = %d bytes",
 		 ticket->t_unit_res);
@@ -2101,7 +2101,7 @@ xlog_print_tic_res(
 		uint r_type = ticket->t_res_arr[i].r_type;
 		xfs_warn(mp, "region[%u]: %s - %u bytes", i,
 			    ((r_type <= 0 || r_type > XLOG_REG_TYPE_MAX) ?
-			    "bad-rtype" : res_type_str[r_type-1]),
+			    "bad-rtype" : res_type_str[r_type]),
 			    ticket->t_res_arr[i].r_len);
 	}
 
@@ -3979,7 +3979,7 @@ xfs_log_force_umount(
 	    log->l_flags & XLOG_ACTIVE_RECOVERY) {
 		mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN;
 		if (mp->m_sb_bp)
-			XFS_BUF_DONE(mp->m_sb_bp);
+			mp->m_sb_bp->b_flags |= XBF_DONE;
 		return 0;
 	}
 
@@ -4009,7 +4009,7 @@ xfs_log_force_umount(
 	spin_lock(&log->l_icloglock);
 	mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN;
 	if (mp->m_sb_bp)
-		XFS_BUF_DONE(mp->m_sb_bp);
+		mp->m_sb_bp->b_flags |= XBF_DONE;
 
 	/*
 	 * Mark the log and the iclogs with IO error flags to prevent any
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index da37beb76f6e..396565f43247 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -190,7 +190,7 @@ xlog_bread_noalign(
 	ASSERT(nbblks <= bp->b_length);
 
 	XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
-	XFS_BUF_READ(bp);
+	bp->b_flags |= XBF_READ;
 	bp->b_io_length = nbblks;
 	bp->b_error = 0;
 
@@ -275,7 +275,6 @@ xlog_bwrite(
 	ASSERT(nbblks <= bp->b_length);
 
 	XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
-	XFS_BUF_ZEROFLAGS(bp);
 	xfs_buf_hold(bp);
 	xfs_buf_lock(bp);
 	bp->b_io_length = nbblks;
@@ -1109,27 +1108,10 @@ xlog_verify_head(
 	bool			tmp_wrapped;
 
 	/*
-	 * Search backwards through the log looking for the log record header
-	 * block. This wraps all the way back around to the head so something is
-	 * seriously wrong if we can't find it.
-	 */
-	found = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp, rhead_blk,
-				      rhead, wrapped);
-	if (found < 0)
-		return found;
-	if (!found) {
-		xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__);
-		return -EIO;
-	}
-
-	*tail_blk = BLOCK_LSN(be64_to_cpu((*rhead)->h_tail_lsn));
-
-	/*
-	 * Now that we have a tail block, check the head of the log for torn
-	 * writes. Search again until we hit the tail or the maximum number of
-	 * log record I/Os that could have been in flight at one time. Use a
-	 * temporary buffer so we don't trash the rhead/bp pointer from the
-	 * call above.
+	 * Check the head of the log for torn writes. Search backwards from the
+	 * head until we hit the tail or the maximum number of log record I/Os
+	 * that could have been in flight at one time. Use a temporary buffer so
+	 * we don't trash the rhead/bp pointers from the caller.
 	 */
 	tmp_bp = xlog_get_bp(log, 1);
 	if (!tmp_bp)
@@ -1216,6 +1198,115 @@ xlog_verify_head(
 }
 
 /*
+ * Check whether the head of the log points to an unmount record. In other
+ * words, determine whether the log is clean. If so, update the in-core state
+ * appropriately.
+ */
+static int
+xlog_check_unmount_rec(
+	struct xlog		*log,
+	xfs_daddr_t		*head_blk,
+	xfs_daddr_t		*tail_blk,
+	struct xlog_rec_header	*rhead,
+	xfs_daddr_t		rhead_blk,
+	struct xfs_buf		*bp,
+	bool			*clean)
+{
+	struct xlog_op_header	*op_head;
+	xfs_daddr_t		umount_data_blk;
+	xfs_daddr_t		after_umount_blk;
+	int			hblks;
+	int			error;
+	char			*offset;
+
+	*clean = false;
+
+	/*
+	 * Look for unmount record. If we find it, then we know there was a
+	 * clean unmount. Since 'i' could be the last block in the physical
+	 * log, we convert to a log block before comparing to the head_blk.
+	 *
+	 * Save the current tail lsn to use to pass to xlog_clear_stale_blocks()
+	 * below. We won't want to clear the unmount record if there is one, so
+	 * we pass the lsn of the unmount record rather than the block after it.
+	 */
+	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
+		int	h_size = be32_to_cpu(rhead->h_size);
+		int	h_version = be32_to_cpu(rhead->h_version);
+
+		if ((h_version & XLOG_VERSION_2) &&
+		    (h_size > XLOG_HEADER_CYCLE_SIZE)) {
+			hblks = h_size / XLOG_HEADER_CYCLE_SIZE;
+			if (h_size % XLOG_HEADER_CYCLE_SIZE)
+				hblks++;
+		} else {
+			hblks = 1;
+		}
+	} else {
+		hblks = 1;
+	}
+	after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len));
+	after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize);
+	if (*head_blk == after_umount_blk &&
+	    be32_to_cpu(rhead->h_num_logops) == 1) {
+		umount_data_blk = rhead_blk + hblks;
+		umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize);
+		error = xlog_bread(log, umount_data_blk, 1, bp, &offset);
+		if (error)
+			return error;
+
+		op_head = (struct xlog_op_header *)offset;
+		if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) {
+			/*
+			 * Set tail and last sync so that newly written log
+			 * records will point recovery to after the current
+			 * unmount record.
+			 */
+			xlog_assign_atomic_lsn(&log->l_tail_lsn,
+					log->l_curr_cycle, after_umount_blk);
+			xlog_assign_atomic_lsn(&log->l_last_sync_lsn,
+					log->l_curr_cycle, after_umount_blk);
+			*tail_blk = after_umount_blk;
+
+			*clean = true;
+		}
+	}
+
+	return 0;
+}
+
+static void
+xlog_set_state(
+	struct xlog		*log,
+	xfs_daddr_t		head_blk,
+	struct xlog_rec_header	*rhead,
+	xfs_daddr_t		rhead_blk,
+	bool			bump_cycle)
+{
+	/*
+	 * Reset log values according to the state of the log when we
+	 * crashed.  In the case where head_blk == 0, we bump curr_cycle
+	 * one because the next write starts a new cycle rather than
+	 * continuing the cycle of the last good log record.  At this
+	 * point we have guaranteed that all partial log records have been
+	 * accounted for.  Therefore, we know that the last good log record
+	 * written was complete and ended exactly on the end boundary
+	 * of the physical log.
+	 */
+	log->l_prev_block = rhead_blk;
+	log->l_curr_block = (int)head_blk;
+	log->l_curr_cycle = be32_to_cpu(rhead->h_cycle);
+	if (bump_cycle)
+		log->l_curr_cycle++;
+	atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn));
+	atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn));
+	xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle,
+					BBTOB(log->l_curr_block));
+	xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle,
+					BBTOB(log->l_curr_block));
+}
+
+/*
  * Find the sync block number or the tail of the log.
  *
  * This will be the block number of the last record to have its
@@ -1238,22 +1329,20 @@ xlog_find_tail(
 	xfs_daddr_t		*tail_blk)
 {
 	xlog_rec_header_t	*rhead;
-	xlog_op_header_t	*op_head;
 	char			*offset = NULL;
 	xfs_buf_t		*bp;
 	int			error;
-	xfs_daddr_t		umount_data_blk;
-	xfs_daddr_t		after_umount_blk;
 	xfs_daddr_t		rhead_blk;
 	xfs_lsn_t		tail_lsn;
-	int			hblks;
 	bool			wrapped = false;
+	bool			clean = false;
 
 	/*
 	 * Find previous log record
 	 */
 	if ((error = xlog_find_head(log, head_blk)))
 		return error;
+	ASSERT(*head_blk < INT_MAX);
 
 	bp = xlog_get_bp(log, 1);
 	if (!bp)
@@ -1271,100 +1360,75 @@ xlog_find_tail(
 	}
 
 	/*
-	 * Trim the head block back to skip over torn records. We can have
-	 * multiple log I/Os in flight at any time, so we assume CRC failures
-	 * back through the previous several records are torn writes and skip
-	 * them.
+	 * Search backwards through the log looking for the log record header
+	 * block. This wraps all the way back around to the head so something is
+	 * seriously wrong if we can't find it.
 	 */
-	ASSERT(*head_blk < INT_MAX);
-	error = xlog_verify_head(log, head_blk, tail_blk, bp, &rhead_blk,
-				 &rhead, &wrapped);
-	if (error)
-		goto done;
+	error = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp,
+				      &rhead_blk, &rhead, &wrapped);
+	if (error < 0)
+		return error;
+	if (!error) {
+		xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__);
+		return -EIO;
+	}
+	*tail_blk = BLOCK_LSN(be64_to_cpu(rhead->h_tail_lsn));
 
 	/*
-	 * Reset log values according to the state of the log when we
-	 * crashed.  In the case where head_blk == 0, we bump curr_cycle
-	 * one because the next write starts a new cycle rather than
-	 * continuing the cycle of the last good log record.  At this
-	 * point we have guaranteed that all partial log records have been
-	 * accounted for.  Therefore, we know that the last good log record
-	 * written was complete and ended exactly on the end boundary
-	 * of the physical log.
+	 * Set the log state based on the current head record.
 	 */
-	log->l_prev_block = rhead_blk;
-	log->l_curr_block = (int)*head_blk;
-	log->l_curr_cycle = be32_to_cpu(rhead->h_cycle);
-	if (wrapped)
-		log->l_curr_cycle++;
-	atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn));
-	atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn));
-	xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle,
-					BBTOB(log->l_curr_block));
-	xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle,
-					BBTOB(log->l_curr_block));
+	xlog_set_state(log, *head_blk, rhead, rhead_blk, wrapped);
+	tail_lsn = atomic64_read(&log->l_tail_lsn);
 
 	/*
-	 * Look for unmount record.  If we find it, then we know there
-	 * was a clean unmount.  Since 'i' could be the last block in
-	 * the physical log, we convert to a log block before comparing
-	 * to the head_blk.
+	 * Look for an unmount record at the head of the log. This sets the log
+	 * state to determine whether recovery is necessary.
+	 */
+	error = xlog_check_unmount_rec(log, head_blk, tail_blk, rhead,
+				       rhead_blk, bp, &clean);
+	if (error)
+		goto done;
+
+	/*
+	 * Verify the log head if the log is not clean (e.g., we have anything
+	 * but an unmount record at the head). This uses CRC verification to
+	 * detect and trim torn writes. If discovered, CRC failures are
+	 * considered torn writes and the log head is trimmed accordingly.
 	 *
-	 * Save the current tail lsn to use to pass to
-	 * xlog_clear_stale_blocks() below.  We won't want to clear the
-	 * unmount record if there is one, so we pass the lsn of the
-	 * unmount record rather than the block after it.
+	 * Note that we can only run CRC verification when the log is dirty
+	 * because there's no guarantee that the log data behind an unmount
+	 * record is compatible with the current architecture.
 	 */
-	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
-		int	h_size = be32_to_cpu(rhead->h_size);
-		int	h_version = be32_to_cpu(rhead->h_version);
+	if (!clean) {
+		xfs_daddr_t	orig_head = *head_blk;
 
-		if ((h_version & XLOG_VERSION_2) &&
-		    (h_size > XLOG_HEADER_CYCLE_SIZE)) {
-			hblks = h_size / XLOG_HEADER_CYCLE_SIZE;
-			if (h_size % XLOG_HEADER_CYCLE_SIZE)
-				hblks++;
-		} else {
-			hblks = 1;
-		}
-	} else {
-		hblks = 1;
-	}
-	after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len));
-	after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize);
-	tail_lsn = atomic64_read(&log->l_tail_lsn);
-	if (*head_blk == after_umount_blk &&
-	    be32_to_cpu(rhead->h_num_logops) == 1) {
-		umount_data_blk = rhead_blk + hblks;
-		umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize);
-		error = xlog_bread(log, umount_data_blk, 1, bp, &offset);
+		error = xlog_verify_head(log, head_blk, tail_blk, bp,
+					 &rhead_blk, &rhead, &wrapped);
 		if (error)
 			goto done;
 
-		op_head = (xlog_op_header_t *)offset;
-		if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) {
-			/*
-			 * Set tail and last sync so that newly written
-			 * log records will point recovery to after the
-			 * current unmount record.
-			 */
-			xlog_assign_atomic_lsn(&log->l_tail_lsn,
-					log->l_curr_cycle, after_umount_blk);
-			xlog_assign_atomic_lsn(&log->l_last_sync_lsn,
-					log->l_curr_cycle, after_umount_blk);
-			*tail_blk = after_umount_blk;
-
-			/*
-			 * Note that the unmount was clean. If the unmount
-			 * was not clean, we need to know this to rebuild the
-			 * superblock counters from the perag headers if we
-			 * have a filesystem using non-persistent counters.
-			 */
-			log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN;
+		/* update in-core state again if the head changed */
+		if (*head_blk != orig_head) {
+			xlog_set_state(log, *head_blk, rhead, rhead_blk,
+				       wrapped);
+			tail_lsn = atomic64_read(&log->l_tail_lsn);
+			error = xlog_check_unmount_rec(log, head_blk, tail_blk,
+						       rhead, rhead_blk, bp,
+						       &clean);
+			if (error)
+				goto done;
 		}
 	}
 
 	/*
+	 * Note that the unmount was clean. If the unmount was not clean, we
+	 * need to know this to rebuild the superblock counters from the perag
+	 * headers if we have a filesystem using non-persistent counters.
+	 */
+	if (clean)
+		log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN;
+
+	/*
 	 * Make sure that there are no blocks in front of the head
 	 * with the same cycle number as the head.  This can happen
 	 * because we allow multiple outstanding log writes concurrently,
@@ -2473,6 +2537,13 @@ xlog_recover_validate_buf_type(
 		}
 		bp->b_ops = &xfs_sb_buf_ops;
 		break;
+#ifdef CONFIG_XFS_RT
+	case XFS_BLFT_RTBITMAP_BUF:
+	case XFS_BLFT_RTSUMMARY_BUF:
+		/* no magic numbers for verification of RT buffers */
+		bp->b_ops = &xfs_rtbuf_ops;
+		break;
+#endif /* CONFIG_XFS_RT */
 	default:
 		xfs_warn(mp, "Unknown buffer type %d!",
 			 xfs_blft_from_flags(buf_f));
@@ -2793,7 +2864,7 @@ xfs_recover_inode_owner_change(
 		return -ENOMEM;
 
 	/* instantiate the inode */
-	xfs_dinode_from_disk(&ip->i_d, dip);
+	xfs_inode_from_disk(ip, dip);
 	ASSERT(ip->i_d.di_version >= 3);
 
 	error = xfs_iformat_fork(ip, dip);
@@ -2839,7 +2910,7 @@ xlog_recover_inode_pass2(
 	int			error;
 	int			attr_index;
 	uint			fields;
-	xfs_icdinode_t		*dicp;
+	struct xfs_log_dinode	*ldip;
 	uint			isize;
 	int			need_free = 0;
 
@@ -2892,8 +2963,8 @@ xlog_recover_inode_pass2(
 		error = -EFSCORRUPTED;
 		goto out_release;
 	}
-	dicp = item->ri_buf[1].i_addr;
-	if (unlikely(dicp->di_magic != XFS_DINODE_MAGIC)) {
+	ldip = item->ri_buf[1].i_addr;
+	if (unlikely(ldip->di_magic != XFS_DINODE_MAGIC)) {
 		xfs_alert(mp,
 			"%s: Bad inode log record, rec ptr 0x%p, ino %Ld",
 			__func__, item, in_f->ilf_ino);
@@ -2929,13 +3000,13 @@ xlog_recover_inode_pass2(
 	 * to skip replay when the on disk inode is newer than the log one
 	 */
 	if (!xfs_sb_version_hascrc(&mp->m_sb) &&
-	    dicp->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
+	    ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
 		/*
 		 * Deal with the wrap case, DI_MAX_FLUSH is less
 		 * than smaller numbers
 		 */
 		if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
-		    dicp->di_flushiter < (DI_MAX_FLUSH >> 1)) {
+		    ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
 			/* do nothing */
 		} else {
 			trace_xfs_log_recover_inode_skip(log, in_f);
@@ -2945,13 +3016,13 @@ xlog_recover_inode_pass2(
 	}
 
 	/* Take the opportunity to reset the flush iteration count */
-	dicp->di_flushiter = 0;
+	ldip->di_flushiter = 0;
 
-	if (unlikely(S_ISREG(dicp->di_mode))) {
-		if ((dicp->di_format != XFS_DINODE_FMT_EXTENTS) &&
-		    (dicp->di_format != XFS_DINODE_FMT_BTREE)) {
+	if (unlikely(S_ISREG(ldip->di_mode))) {
+		if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
+		    (ldip->di_format != XFS_DINODE_FMT_BTREE)) {
 			XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(3)",
-					 XFS_ERRLEVEL_LOW, mp, dicp);
+					 XFS_ERRLEVEL_LOW, mp, ldip);
 			xfs_alert(mp,
 		"%s: Bad regular inode log record, rec ptr 0x%p, "
 		"ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
@@ -2959,12 +3030,12 @@ xlog_recover_inode_pass2(
 			error = -EFSCORRUPTED;
 			goto out_release;
 		}
-	} else if (unlikely(S_ISDIR(dicp->di_mode))) {
-		if ((dicp->di_format != XFS_DINODE_FMT_EXTENTS) &&
-		    (dicp->di_format != XFS_DINODE_FMT_BTREE) &&
-		    (dicp->di_format != XFS_DINODE_FMT_LOCAL)) {
+	} else if (unlikely(S_ISDIR(ldip->di_mode))) {
+		if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
+		    (ldip->di_format != XFS_DINODE_FMT_BTREE) &&
+		    (ldip->di_format != XFS_DINODE_FMT_LOCAL)) {
 			XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(4)",
-					     XFS_ERRLEVEL_LOW, mp, dicp);
+					     XFS_ERRLEVEL_LOW, mp, ldip);
 			xfs_alert(mp,
 		"%s: Bad dir inode log record, rec ptr 0x%p, "
 		"ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
@@ -2973,32 +3044,32 @@ xlog_recover_inode_pass2(
 			goto out_release;
 		}
 	}
-	if (unlikely(dicp->di_nextents + dicp->di_anextents > dicp->di_nblocks)){
+	if (unlikely(ldip->di_nextents + ldip->di_anextents > ldip->di_nblocks)){
 		XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(5)",
-				     XFS_ERRLEVEL_LOW, mp, dicp);
+				     XFS_ERRLEVEL_LOW, mp, ldip);
 		xfs_alert(mp,
 	"%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, "
 	"dino bp 0x%p, ino %Ld, total extents = %d, nblocks = %Ld",
 			__func__, item, dip, bp, in_f->ilf_ino,
-			dicp->di_nextents + dicp->di_anextents,
-			dicp->di_nblocks);
+			ldip->di_nextents + ldip->di_anextents,
+			ldip->di_nblocks);
 		error = -EFSCORRUPTED;
 		goto out_release;
 	}
-	if (unlikely(dicp->di_forkoff > mp->m_sb.sb_inodesize)) {
+	if (unlikely(ldip->di_forkoff > mp->m_sb.sb_inodesize)) {
 		XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(6)",
-				     XFS_ERRLEVEL_LOW, mp, dicp);
+				     XFS_ERRLEVEL_LOW, mp, ldip);
 		xfs_alert(mp,
 	"%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, "
 	"dino bp 0x%p, ino %Ld, forkoff 0x%x", __func__,
-			item, dip, bp, in_f->ilf_ino, dicp->di_forkoff);
+			item, dip, bp, in_f->ilf_ino, ldip->di_forkoff);
 		error = -EFSCORRUPTED;
 		goto out_release;
 	}
-	isize = xfs_icdinode_size(dicp->di_version);
+	isize = xfs_log_dinode_size(ldip->di_version);
 	if (unlikely(item->ri_buf[1].i_len > isize)) {
 		XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(7)",
-				     XFS_ERRLEVEL_LOW, mp, dicp);
+				     XFS_ERRLEVEL_LOW, mp, ldip);
 		xfs_alert(mp,
 			"%s: Bad inode log record length %d, rec ptr 0x%p",
 			__func__, item->ri_buf[1].i_len, item);
@@ -3006,8 +3077,8 @@ xlog_recover_inode_pass2(
 		goto out_release;
 	}
 
-	/* The core is in in-core format */
-	xfs_dinode_to_disk(dip, dicp);
+	/* recover the log dinode inode into the on disk inode */
+	xfs_log_dinode_to_disk(ldip, dip);
 
 	/* the rest is in on-disk format */
 	if (item->ri_buf[1].i_len > isize) {
@@ -4337,8 +4408,8 @@ xlog_recover_process_one_iunlink(
 	if (error)
 		goto fail_iput;
 
-	ASSERT(ip->i_d.di_nlink == 0);
-	ASSERT(ip->i_d.di_mode != 0);
+	ASSERT(VFS_I(ip)->i_nlink == 0);
+	ASSERT(VFS_I(ip)->i_mode != 0);
 
 	/* setup for the next pass */
 	agino = be32_to_cpu(dip->di_next_unlinked);
@@ -4491,7 +4562,7 @@ xlog_recover_process(
 	 * know precisely what failed.
 	 */
 	if (pass == XLOG_RECOVER_CRCPASS) {
-		if (rhead->h_crc && crc != le32_to_cpu(rhead->h_crc))
+		if (rhead->h_crc && crc != rhead->h_crc)
 			return -EFSBADCRC;
 		return 0;
 	}
@@ -4502,7 +4573,7 @@ xlog_recover_process(
 	 * zero CRC check prevents warnings from being emitted when upgrading
 	 * the kernel from one that does not add CRCs by default.
 	 */
-	if (crc != le32_to_cpu(rhead->h_crc)) {
+	if (crc != rhead->h_crc) {
 		if (rhead->h_crc || xfs_sb_version_hascrc(&log->l_mp->m_sb)) {
 			xfs_alert(log->l_mp,
 		"log record CRC mismatch: found 0x%x, expected 0x%x.",
@@ -4892,6 +4963,7 @@ xlog_do_recover(
 	xfs_daddr_t	head_blk,
 	xfs_daddr_t	tail_blk)
 {
+	struct xfs_mount *mp = log->l_mp;
 	int		error;
 	xfs_buf_t	*bp;
 	xfs_sb_t	*sbp;
@@ -4906,7 +4978,7 @@ xlog_do_recover(
 	/*
 	 * If IO errors happened during recovery, bail out.
 	 */
-	if (XFS_FORCED_SHUTDOWN(log->l_mp)) {
+	if (XFS_FORCED_SHUTDOWN(mp)) {
 		return -EIO;
 	}
 
@@ -4919,22 +4991,21 @@ xlog_do_recover(
 	 * or iunlinks they will have some entries in the AIL; so we look at
 	 * the AIL to determine how to set the tail_lsn.
 	 */
-	xlog_assign_tail_lsn(log->l_mp);
+	xlog_assign_tail_lsn(mp);
 
 	/*
 	 * Now that we've finished replaying all buffer and inode
 	 * updates, re-read in the superblock and reverify it.
 	 */
-	bp = xfs_getsb(log->l_mp, 0);
-	XFS_BUF_UNDONE(bp);
-	ASSERT(!(XFS_BUF_ISWRITE(bp)));
-	XFS_BUF_READ(bp);
-	XFS_BUF_UNASYNC(bp);
+	bp = xfs_getsb(mp, 0);
+	bp->b_flags &= ~(XBF_DONE | XBF_ASYNC);
+	ASSERT(!(bp->b_flags & XBF_WRITE));
+	bp->b_flags |= XBF_READ;
 	bp->b_ops = &xfs_sb_buf_ops;
 
 	error = xfs_buf_submit_wait(bp);
 	if (error) {
-		if (!XFS_FORCED_SHUTDOWN(log->l_mp)) {
+		if (!XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_buf_ioerror_alert(bp, __func__);
 			ASSERT(0);
 		}
@@ -4943,14 +5014,17 @@ xlog_do_recover(
 	}
 
 	/* Convert superblock from on-disk format */
-	sbp = &log->l_mp->m_sb;
+	sbp = &mp->m_sb;
 	xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp));
-	ASSERT(sbp->sb_magicnum == XFS_SB_MAGIC);
-	ASSERT(xfs_sb_good_version(sbp));
-	xfs_reinit_percpu_counters(log->l_mp);
-
 	xfs_buf_relse(bp);
 
+	/* re-initialise in-core superblock and geometry structures */
+	xfs_reinit_percpu_counters(mp);
+	error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi);
+	if (error) {
+		xfs_warn(mp, "Failed post-recovery per-ag init: %d", error);
+		return error;
+	}
 
 	xlog_recover_check_summary(log);
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index bb753b359bee..536a0ee9cd5a 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -185,9 +185,6 @@ xfs_initialize_perag(
 	xfs_agnumber_t	index;
 	xfs_agnumber_t	first_initialised = 0;
 	xfs_perag_t	*pag;
-	xfs_agino_t	agino;
-	xfs_ino_t	ino;
-	xfs_sb_t	*sbp = &mp->m_sb;
 	int		error = -ENOMEM;
 
 	/*
@@ -230,22 +227,7 @@ xfs_initialize_perag(
 		radix_tree_preload_end();
 	}
 
-	/*
-	 * If we mount with the inode64 option, or no inode overflows
-	 * the legacy 32-bit address space clear the inode32 option.
-	 */
-	agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
-	ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
-
-	if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) && ino > XFS_MAXINUMBER_32)
-		mp->m_flags |= XFS_MOUNT_32BITINODES;
-	else
-		mp->m_flags &= ~XFS_MOUNT_32BITINODES;
-
-	if (mp->m_flags & XFS_MOUNT_32BITINODES)
-		index = xfs_set_inode32(mp, agcount);
-	else
-		index = xfs_set_inode64(mp, agcount);
+	index = xfs_set_inode_alloc(mp, agcount);
 
 	if (maxagi)
 		*maxagi = index;
@@ -865,7 +847,7 @@ xfs_mountfs(
 
 	ASSERT(rip != NULL);
 
-	if (unlikely(!S_ISDIR(rip->i_d.di_mode))) {
+	if (unlikely(!S_ISDIR(VFS_I(rip)->i_mode))) {
 		xfs_warn(mp, "corrupted root inode %llu: not a directory",
 			(unsigned long long)rip->i_ino);
 		xfs_iunlock(rip, XFS_ILOCK_EXCL);
@@ -1284,7 +1266,7 @@ xfs_getsb(
 	}
 
 	xfs_buf_hold(bp);
-	ASSERT(XFS_BUF_ISDONE(bp));
+	ASSERT(bp->b_flags & XBF_DONE);
 	return bp;
 }
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index b57098481c10..bac6b3435591 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -147,6 +147,17 @@ typedef struct xfs_mount {
 	 * to various other kinds of pain inflicted on the pNFS server.
 	 */
 	__uint32_t		m_generation;
+
+#ifdef DEBUG
+	/*
+	 * DEBUG mode instrumentation to test and/or trigger delayed allocation
+	 * block killing in the event of failed writes. When enabled, all
+	 * buffered writes are forced to fail. All delalloc blocks in the range
+	 * of the write (including pre-existing delalloc blocks!) are tossed as
+	 * part of the write failure error handling sequence.
+	 */
+	bool			m_fail_writes;
+#endif
 } xfs_mount_t;
 
 /*
@@ -166,9 +177,8 @@ typedef struct xfs_mount {
 #define XFS_MOUNT_GRPID		(1ULL << 9)	/* group-ID assigned from directory */
 #define XFS_MOUNT_NORECOVERY	(1ULL << 10)	/* no recovery - dirty fs */
 #define XFS_MOUNT_DFLT_IOSIZE	(1ULL << 12)	/* set default i/o size */
-#define XFS_MOUNT_32BITINODES	(1ULL << 14)	/* do not create inodes above
-						 * 32 bits in size */
-#define XFS_MOUNT_SMALL_INUMS	(1ULL << 15)	/* users wants 32bit inodes */
+#define XFS_MOUNT_SMALL_INUMS	(1ULL << 14)	/* user wants 32bit inodes */
+#define XFS_MOUNT_32BITINODES	(1ULL << 15)	/* inode32 allocator active */
 #define XFS_MOUNT_NOUUID	(1ULL << 16)	/* ignore uuid during mount */
 #define XFS_MOUNT_BARRIER	(1ULL << 17)
 #define XFS_MOUNT_IKEEP		(1ULL << 18)	/* keep empty inode clusters*/
@@ -264,6 +274,20 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d)
 	return (xfs_agblock_t) do_div(ld, mp->m_sb.sb_agblocks);
 }
 
+#ifdef DEBUG
+static inline bool
+xfs_mp_fail_writes(struct xfs_mount *mp)
+{
+	return mp->m_fail_writes;
+}
+#else
+static inline bool
+xfs_mp_fail_writes(struct xfs_mount *mp)
+{
+	return 0;
+}
+#endif
+
 /*
  * Per-ag incore structure, copies of information in agf and agi, to improve the
  * performance of allocation group selection.
@@ -327,7 +351,6 @@ extern int	xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta,
 				 bool reserved);
 extern int	xfs_mod_frextents(struct xfs_mount *mp, int64_t delta);
 
-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_ondisk.h b/fs/xfs/xfs_ondisk.h
new file mode 100644
index 000000000000..184c44effdd5
--- /dev/null
+++ b/fs/xfs/xfs_ondisk.h
@@ -0,0 +1,117 @@
+/*
+ * Copyright (c) 2016 Oracle.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would 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 the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#ifndef __XFS_ONDISK_H
+#define __XFS_ONDISK_H
+
+#define XFS_CHECK_STRUCT_SIZE(structname, size) \
+	BUILD_BUG_ON_MSG(sizeof(structname) != (size), "XFS: sizeof(" \
+		#structname ") is wrong, expected " #size)
+
+static inline void __init
+xfs_check_ondisk_structs(void)
+{
+	/* ag/file structures */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_acl,			4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_acl_entry,		12);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agf,			224);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agfl,			36);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agi,			336);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_key,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_rec,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bmdr_block,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block,		72);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dinode,		176);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot,		104);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk,			136);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			264);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr,		56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_key,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_rec,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_timestamp,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_alloc_key_t,			8);
+	XFS_CHECK_STRUCT_SIZE(xfs_alloc_ptr_t,			4);
+	XFS_CHECK_STRUCT_SIZE(xfs_alloc_rec_t,			8);
+	XFS_CHECK_STRUCT_SIZE(xfs_inobt_ptr_t,			4);
+
+	/* dir/attr trees */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leaf_hdr,	80);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leafblock,	88);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_rmt_hdr,		56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da3_blkinfo,		56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da3_intnode,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da3_node_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_blk_hdr,		48);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_data_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_entry_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_hdr_t,		32);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_map_t,		4);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_local_t,	4);
+
+	/*
+	 * m68k has problems with xfs_attr_leaf_name_remote_t, but we pad it to
+	 * 4 bytes anyway so it's not obviously a problem.  Hence for the moment
+	 * we don't check this structure. This can be re-instated when the attr
+	 * definitions are updated to use c99 VLA definitions.
+	 *
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_remote_t,	12);
+	 */
+
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t,		40);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_shortform_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_blkinfo_t,			12);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_intnode_t,			16);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_node_entry_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_node_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_free_t,		4);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_unused_t,		6);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_t,			16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_ino4_t,			4);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_ino8_t,			8);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_inou_t,			8);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_entry_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_t,			16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_tail_t,		4);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_entry_t,		3);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_hdr_t,		10);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_off_t,		2);
+
+	/* log structures */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat,		24);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32,	28);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64,	32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32,	28);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64,	32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_32,		12);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode,		176);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log,		28);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_ictimestamp,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32,	52);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_64,	56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat,	20);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header,		16);
+}
+
+#endif /* __XFS_ONDISK_H */
diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h
index 8147ac108820..93f74853961b 100644
--- a/fs/xfs/xfs_pnfs.h
+++ b/fs/xfs/xfs_pnfs.h
@@ -1,7 +1,7 @@
 #ifndef _XFS_PNFS_H
 #define _XFS_PNFS_H 1
 
-#ifdef CONFIG_NFSD_PNFS
+#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT)
 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);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 532ab79d38fe..be125e1758c1 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -560,6 +560,37 @@ xfs_qm_shrink_count(
 	return list_lru_shrink_count(&qi->qi_lru, sc);
 }
 
+STATIC void
+xfs_qm_set_defquota(
+	xfs_mount_t	*mp,
+	uint		type,
+	xfs_quotainfo_t	*qinf)
+{
+	xfs_dquot_t		*dqp;
+	struct xfs_def_quota    *defq;
+	int			error;
+
+	error = xfs_qm_dqread(mp, 0, type, XFS_QMOPT_DOWARN, &dqp);
+
+	if (!error) {
+		xfs_disk_dquot_t        *ddqp = &dqp->q_core;
+
+		defq = xfs_get_defquota(dqp, qinf);
+
+		/*
+		 * Timers and warnings have been already set, let's just set the
+		 * default limits for this quota type
+		 */
+		defq->bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
+		defq->bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
+		defq->ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
+		defq->isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
+		defq->rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
+		defq->rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
+		xfs_qm_dqdestroy(dqp);
+	}
+}
+
 /*
  * This initializes all the quota information that's kept in the
  * mount structure
@@ -606,19 +637,19 @@ xfs_qm_init_quotainfo(
 	 * We try to get the limits from the superuser's limits fields.
 	 * This is quite hacky, but it is standard quota practice.
 	 *
-	 * We look at the USR dquot with id == 0 first, but if user quotas
-	 * are not enabled we goto the GRP dquot with id == 0.
-	 * We don't really care to keep separate default limits for user
-	 * and group quotas, at least not at this point.
-	 *
 	 * Since we may not have done a quotacheck by this point, just read
 	 * the dquot without attaching it to any hashtables or lists.
+	 *
+	 * Timers and warnings are globally set by the first timer found in
+	 * user/group/proj quota types, otherwise a default value is used.
+	 * This should be split into different fields per quota type.
 	 */
 	error = xfs_qm_dqread(mp, 0,
 			XFS_IS_UQUOTA_RUNNING(mp) ? XFS_DQ_USER :
 			 (XFS_IS_GQUOTA_RUNNING(mp) ? XFS_DQ_GROUP :
 			  XFS_DQ_PROJ),
 			XFS_QMOPT_DOWARN, &dqp);
+
 	if (!error) {
 		xfs_disk_dquot_t	*ddqp = &dqp->q_core;
 
@@ -639,13 +670,6 @@ xfs_qm_init_quotainfo(
 			be16_to_cpu(ddqp->d_iwarns) : XFS_QM_IWARNLIMIT;
 		qinf->qi_rtbwarnlimit = ddqp->d_rtbwarns ?
 			be16_to_cpu(ddqp->d_rtbwarns) : XFS_QM_RTBWARNLIMIT;
-		qinf->qi_bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
-		qinf->qi_bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
-		qinf->qi_ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
-		qinf->qi_isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
-		qinf->qi_rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
-		qinf->qi_rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
-
 		xfs_qm_dqdestroy(dqp);
 	} else {
 		qinf->qi_btimelimit = XFS_QM_BTIMELIMIT;
@@ -656,6 +680,13 @@ xfs_qm_init_quotainfo(
 		qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
 	}
 
+	if (XFS_IS_UQUOTA_RUNNING(mp))
+		xfs_qm_set_defquota(mp, XFS_DQ_USER, qinf);
+	if (XFS_IS_GQUOTA_RUNNING(mp))
+		xfs_qm_set_defquota(mp, XFS_DQ_GROUP, qinf);
+	if (XFS_IS_PQUOTA_RUNNING(mp))
+		xfs_qm_set_defquota(mp, XFS_DQ_PROJ, qinf);
+
 	qinf->qi_shrinker.count_objects = xfs_qm_shrink_count;
 	qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan;
 	qinf->qi_shrinker.seeks = DEFAULT_SEEKS;
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 996a04064894..2975a822e9f0 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -53,6 +53,15 @@ extern struct kmem_zone	*xfs_qm_dqtrxzone;
  */
 #define XFS_DQUOT_CLUSTER_SIZE_FSB	(xfs_filblks_t)1
 
+struct xfs_def_quota {
+	xfs_qcnt_t       bhardlimit;     /* default data blk hard limit */
+	xfs_qcnt_t       bsoftlimit;	 /* default data blk soft limit */
+	xfs_qcnt_t       ihardlimit;	 /* default inode count hard limit */
+	xfs_qcnt_t       isoftlimit;	 /* default inode count soft limit */
+	xfs_qcnt_t	 rtbhardlimit;   /* default realtime blk hard limit */
+	xfs_qcnt_t	 rtbsoftlimit;   /* default realtime blk soft limit */
+};
+
 /*
  * Various quota information for individual filesystems.
  * The mount structure keeps a pointer to this.
@@ -76,12 +85,9 @@ typedef struct xfs_quotainfo {
 	struct mutex	 qi_quotaofflock;/* to serialize quotaoff */
 	xfs_filblks_t	 qi_dqchunklen;	 /* # BBs in a chunk of dqs */
 	uint		 qi_dqperchunk;	 /* # ondisk dqs in above chunk */
-	xfs_qcnt_t	 qi_bhardlimit;	 /* default data blk hard limit */
-	xfs_qcnt_t	 qi_bsoftlimit;	 /* default data blk soft limit */
-	xfs_qcnt_t	 qi_ihardlimit;	 /* default inode count hard limit */
-	xfs_qcnt_t	 qi_isoftlimit;	 /* default inode count soft limit */
-	xfs_qcnt_t	 qi_rtbhardlimit;/* default realtime blk hard limit */
-	xfs_qcnt_t	 qi_rtbsoftlimit;/* default realtime blk soft limit */
+	struct xfs_def_quota	qi_usr_default;
+	struct xfs_def_quota	qi_grp_default;
+	struct xfs_def_quota	qi_prj_default;
 	struct shrinker  qi_shrinker;
 } xfs_quotainfo_t;
 
@@ -104,15 +110,15 @@ xfs_dquot_tree(
 }
 
 static inline struct xfs_inode *
-xfs_dq_to_quota_inode(struct xfs_dquot *dqp)
+xfs_quota_inode(xfs_mount_t *mp, uint dq_flags)
 {
-	switch (dqp->dq_flags & XFS_DQ_ALLTYPES) {
+	switch (dq_flags & XFS_DQ_ALLTYPES) {
 	case XFS_DQ_USER:
-		return dqp->q_mount->m_quotainfo->qi_uquotaip;
+		return mp->m_quotainfo->qi_uquotaip;
 	case XFS_DQ_GROUP:
-		return dqp->q_mount->m_quotainfo->qi_gquotaip;
+		return mp->m_quotainfo->qi_gquotaip;
 	case XFS_DQ_PROJ:
-		return dqp->q_mount->m_quotainfo->qi_pquotaip;
+		return mp->m_quotainfo->qi_pquotaip;
 	default:
 		ASSERT(0);
 	}
@@ -164,11 +170,27 @@ extern void		xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint);
 
 /* quota ops */
 extern int		xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint);
-extern int		xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t,
-					uint, struct qc_dqblk *);
+extern int		xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t *,
+					uint, struct qc_dqblk *, uint);
 extern int		xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint,
 					struct qc_dqblk *);
 extern int		xfs_qm_scall_quotaon(struct xfs_mount *, uint);
 extern int		xfs_qm_scall_quotaoff(struct xfs_mount *, uint);
 
+static inline struct xfs_def_quota *
+xfs_get_defquota(struct xfs_dquot *dqp, struct xfs_quotainfo *qi)
+{
+	struct xfs_def_quota *defq;
+
+	if (XFS_QM_ISUDQ(dqp))
+		defq = &qi->qi_usr_default;
+	else if (XFS_QM_ISGDQ(dqp))
+		defq = &qi->qi_grp_default;
+	else {
+		ASSERT(XFS_QM_ISPDQ(dqp));
+		defq = &qi->qi_prj_default;
+	}
+	return defq;
+}
+
 #endif /* __XFS_QM_H__ */
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 3640c6e896af..f4d0e0a8f517 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -404,6 +404,7 @@ xfs_qm_scall_setqlim(
 	struct xfs_disk_dquot	*ddq;
 	struct xfs_dquot	*dqp;
 	struct xfs_trans	*tp;
+	struct xfs_def_quota	*defq;
 	int			error;
 	xfs_qcnt_t		hard, soft;
 
@@ -431,6 +432,8 @@ xfs_qm_scall_setqlim(
 		ASSERT(error != -ENOENT);
 		goto out_unlock;
 	}
+
+	defq = xfs_get_defquota(dqp, q);
 	xfs_dqunlock(dqp);
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM);
@@ -458,8 +461,8 @@ xfs_qm_scall_setqlim(
 		ddq->d_blk_softlimit = cpu_to_be64(soft);
 		xfs_dquot_set_prealloc_limits(dqp);
 		if (id == 0) {
-			q->qi_bhardlimit = hard;
-			q->qi_bsoftlimit = soft;
+			defq->bhardlimit = hard;
+			defq->bsoftlimit = soft;
 		}
 	} else {
 		xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft);
@@ -474,8 +477,8 @@ xfs_qm_scall_setqlim(
 		ddq->d_rtb_hardlimit = cpu_to_be64(hard);
 		ddq->d_rtb_softlimit = cpu_to_be64(soft);
 		if (id == 0) {
-			q->qi_rtbhardlimit = hard;
-			q->qi_rtbsoftlimit = soft;
+			defq->rtbhardlimit = hard;
+			defq->rtbsoftlimit = soft;
 		}
 	} else {
 		xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft);
@@ -491,8 +494,8 @@ xfs_qm_scall_setqlim(
 		ddq->d_ino_hardlimit = cpu_to_be64(hard);
 		ddq->d_ino_softlimit = cpu_to_be64(soft);
 		if (id == 0) {
-			q->qi_ihardlimit = hard;
-			q->qi_isoftlimit = soft;
+			defq->ihardlimit = hard;
+			defq->isoftlimit = soft;
 		}
 	} else {
 		xfs_debug(mp, "ihard %Ld < isoft %Ld", hard, soft);
@@ -635,9 +638,10 @@ out:
 int
 xfs_qm_scall_getquota(
 	struct xfs_mount	*mp,
-	xfs_dqid_t		id,
+	xfs_dqid_t		*id,
 	uint			type,
-	struct qc_dqblk		*dst)
+	struct qc_dqblk		*dst,
+	uint			dqget_flags)
 {
 	struct xfs_dquot	*dqp;
 	int			error;
@@ -647,7 +651,7 @@ xfs_qm_scall_getquota(
 	 * we aren't passing the XFS_QMOPT_DOALLOC flag. If it doesn't
 	 * exist, we'll get ENOENT back.
 	 */
-	error = xfs_qm_dqget(mp, NULL, id, type, 0, &dqp);
+	error = xfs_qm_dqget(mp, NULL, *id, type, dqget_flags, &dqp);
 	if (error)
 		return error;
 
@@ -660,6 +664,9 @@ xfs_qm_scall_getquota(
 		goto out_put;
 	}
 
+	/* Fill in the ID we actually read from disk */
+	*id = be32_to_cpu(dqp->q_core.d_id);
+
 	memset(dst, 0, sizeof(*dst));
 	dst->d_spc_hardlimit =
 		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
@@ -701,7 +708,7 @@ xfs_qm_scall_getquota(
 	if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) ||
 	     (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) ||
 	     (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) &&
-	    id != 0) {
+	    *id != 0) {
 		if ((dst->d_space > dst->d_spc_softlimit) &&
 		    (dst->d_spc_softlimit > 0)) {
 			ASSERT(dst->d_spc_timer != 0);
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index 7795e0d01382..f82d79a8c694 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -231,14 +231,45 @@ xfs_fs_get_dqblk(
 	struct qc_dqblk		*qdq)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
+	xfs_dqid_t		id;
 
 	if (!XFS_IS_QUOTA_RUNNING(mp))
 		return -ENOSYS;
 	if (!XFS_IS_QUOTA_ON(mp))
 		return -ESRCH;
 
-	return xfs_qm_scall_getquota(mp, from_kqid(&init_user_ns, qid),
-				      xfs_quota_type(qid.type), qdq);
+	id = from_kqid(&init_user_ns, qid);
+	return xfs_qm_scall_getquota(mp, &id,
+				      xfs_quota_type(qid.type), qdq, 0);
+}
+
+/* Return quota info for active quota >= this qid */
+STATIC int
+xfs_fs_get_nextdqblk(
+	struct super_block	*sb,
+	struct kqid		*qid,
+	struct qc_dqblk		*qdq)
+{
+	int			ret;
+	struct xfs_mount	*mp = XFS_M(sb);
+	xfs_dqid_t		id;
+
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -ESRCH;
+
+	id = from_kqid(&init_user_ns, *qid);
+	ret = xfs_qm_scall_getquota(mp, &id,
+				    xfs_quota_type(qid->type), qdq,
+				    XFS_QMOPT_DQNEXT);
+	if (ret)
+		return ret;
+
+	/* ID may be different, so convert back what we got */
+	*qid = make_kqid(current_user_ns(), qid->type, id);
+	return 0;
+	
 }
 
 STATIC int
@@ -267,5 +298,6 @@ const struct quotactl_ops xfs_quotactl_operations = {
 	.quota_disable		= xfs_quota_disable,
 	.rm_xquota		= xfs_fs_rm_xquota,
 	.get_dqblk		= xfs_fs_get_dqblk,
+	.get_nextdqblk		= xfs_fs_get_nextdqblk,
 	.set_dqblk		= xfs_fs_set_dqblk,
 };
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index be02a68b2fe2..abf44435d04a 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1272,7 +1272,7 @@ xfs_rtpick_extent(
 
 	ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
 
-	seqp = (__uint64_t *)&mp->m_rbmip->i_d.di_atime;
+	seqp = (__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime;
 	if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) {
 		mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
 		*seqp = 0;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 59c9b7bd958d..d760934109b5 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -45,6 +45,7 @@
 #include "xfs_filestream.h"
 #include "xfs_quota.h"
 #include "xfs_sysfs.h"
+#include "xfs_ondisk.h"
 
 #include <linux/namei.h>
 #include <linux/init.h>
@@ -65,83 +66,85 @@ static struct kset *xfs_kset;		/* top-level xfs sysfs dir */
 static struct xfs_kobj xfs_dbg_kobj;	/* global debug sysfs attrs */
 #endif
 
-#define MNTOPT_LOGBUFS	"logbufs"	/* number of XFS log buffers */
-#define MNTOPT_LOGBSIZE	"logbsize"	/* size of XFS log buffers */
-#define MNTOPT_LOGDEV	"logdev"	/* log device */
-#define MNTOPT_RTDEV	"rtdev"		/* realtime I/O device */
-#define MNTOPT_BIOSIZE	"biosize"	/* log2 of preferred buffered io size */
-#define MNTOPT_WSYNC	"wsync"		/* safe-mode nfs compatible mount */
-#define MNTOPT_NOALIGN	"noalign"	/* turn off stripe alignment */
-#define MNTOPT_SWALLOC	"swalloc"	/* turn on stripe width allocation */
-#define MNTOPT_SUNIT	"sunit"		/* data volume stripe unit */
-#define MNTOPT_SWIDTH	"swidth"	/* data volume stripe width */
-#define MNTOPT_NOUUID	"nouuid"	/* ignore filesystem UUID */
-#define MNTOPT_MTPT	"mtpt"		/* filesystem mount point */
-#define MNTOPT_GRPID	"grpid"		/* group-ID from parent directory */
-#define MNTOPT_NOGRPID	"nogrpid"	/* group-ID from current process */
-#define MNTOPT_BSDGROUPS    "bsdgroups"    /* group-ID from parent directory */
-#define MNTOPT_SYSVGROUPS   "sysvgroups"   /* group-ID from current process */
-#define MNTOPT_ALLOCSIZE    "allocsize"    /* preferred allocation size */
-#define MNTOPT_NORECOVERY   "norecovery"   /* don't run XFS recovery */
-#define MNTOPT_BARRIER	"barrier"	/* use writer barriers for log write and
-					 * unwritten extent conversion */
-#define MNTOPT_NOBARRIER "nobarrier"	/* .. disable */
-#define MNTOPT_64BITINODE   "inode64"	/* inodes can be allocated anywhere */
-#define MNTOPT_32BITINODE   "inode32"	/* inode allocation limited to
-					 * XFS_MAXINUMBER_32 */
-#define MNTOPT_IKEEP	"ikeep"		/* do not free empty inode clusters */
-#define MNTOPT_NOIKEEP	"noikeep"	/* free empty inode clusters */
-#define MNTOPT_LARGEIO	   "largeio"	/* report large I/O sizes in stat() */
-#define MNTOPT_NOLARGEIO   "nolargeio"	/* do not report large I/O sizes
-					 * in stat(). */
-#define MNTOPT_ATTR2	"attr2"		/* do use attr2 attribute format */
-#define MNTOPT_NOATTR2	"noattr2"	/* do not use attr2 attribute format */
-#define MNTOPT_FILESTREAM  "filestreams" /* use filestreams allocator */
-#define MNTOPT_QUOTA	"quota"		/* disk quotas (user) */
-#define MNTOPT_NOQUOTA	"noquota"	/* no quotas */
-#define MNTOPT_USRQUOTA	"usrquota"	/* user quota enabled */
-#define MNTOPT_GRPQUOTA	"grpquota"	/* group quota enabled */
-#define MNTOPT_PRJQUOTA	"prjquota"	/* project quota enabled */
-#define MNTOPT_UQUOTA	"uquota"	/* user quota (IRIX variant) */
-#define MNTOPT_GQUOTA	"gquota"	/* group quota (IRIX variant) */
-#define MNTOPT_PQUOTA	"pquota"	/* project quota (IRIX variant) */
-#define MNTOPT_UQUOTANOENF "uqnoenforce"/* user quota limit enforcement */
-#define MNTOPT_GQUOTANOENF "gqnoenforce"/* group quota limit enforcement */
-#define MNTOPT_PQUOTANOENF "pqnoenforce"/* project quota limit enforcement */
-#define MNTOPT_QUOTANOENF  "qnoenforce"	/* same as uqnoenforce */
-#define MNTOPT_DISCARD	   "discard"	/* Discard unused blocks */
-#define MNTOPT_NODISCARD   "nodiscard"	/* Do not discard unused blocks */
-
-#define MNTOPT_DAX	"dax"		/* Enable direct access to bdev pages */
-
 /*
  * Table driven mount option parser.
- *
- * Currently only used for remount, but it will be used for mount
- * in the future, too.
  */
 enum {
-	Opt_barrier,
-	Opt_nobarrier,
-	Opt_inode64,
-	Opt_inode32,
-	Opt_err
+	Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_biosize,
+	Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid,
+	Opt_mtpt, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups,
+	Opt_allocsize, Opt_norecovery, Opt_barrier, Opt_nobarrier,
+	Opt_inode64, Opt_inode32, Opt_ikeep, Opt_noikeep,
+	Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2, Opt_filestreams,
+	Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota,
+	Opt_uquota, Opt_gquota, Opt_pquota,
+	Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
+	Opt_discard, Opt_nodiscard, Opt_dax, Opt_err,
 };
 
 static const match_table_t tokens = {
-	{Opt_barrier, "barrier"},
-	{Opt_nobarrier, "nobarrier"},
-	{Opt_inode64, "inode64"},
-	{Opt_inode32, "inode32"},
-	{Opt_err, NULL}
+	{Opt_logbufs,	"logbufs=%u"},	/* number of XFS log buffers */
+	{Opt_logbsize,	"logbsize=%s"},	/* size of XFS log buffers */
+	{Opt_logdev,	"logdev=%s"},	/* log device */
+	{Opt_rtdev,	"rtdev=%s"},	/* realtime I/O device */
+	{Opt_biosize,	"biosize=%u"},	/* log2 of preferred buffered io size */
+	{Opt_wsync,	"wsync"},	/* safe-mode nfs compatible mount */
+	{Opt_noalign,	"noalign"},	/* turn off stripe alignment */
+	{Opt_swalloc,	"swalloc"},	/* turn on stripe width allocation */
+	{Opt_sunit,	"sunit=%u"},	/* data volume stripe unit */
+	{Opt_swidth,	"swidth=%u"},	/* data volume stripe width */
+	{Opt_nouuid,	"nouuid"},	/* ignore filesystem UUID */
+	{Opt_mtpt,	"mtpt"},	/* filesystem mount point */
+	{Opt_grpid,	"grpid"},	/* group-ID from parent directory */
+	{Opt_nogrpid,	"nogrpid"},	/* group-ID from current process */
+	{Opt_bsdgroups,	"bsdgroups"},	/* group-ID from parent directory */
+	{Opt_sysvgroups,"sysvgroups"},	/* group-ID from current process */
+	{Opt_allocsize,	"allocsize=%s"},/* preferred allocation size */
+	{Opt_norecovery,"norecovery"},	/* don't run XFS recovery */
+	{Opt_barrier,	"barrier"},	/* use writer barriers for log write and
+					 * unwritten extent conversion */
+	{Opt_nobarrier,	"nobarrier"},	/* .. disable */
+	{Opt_inode64,	"inode64"},	/* inodes can be allocated anywhere */
+	{Opt_inode32,   "inode32"},	/* inode allocation limited to
+					 * XFS_MAXINUMBER_32 */
+	{Opt_ikeep,	"ikeep"},	/* do not free empty inode clusters */
+	{Opt_noikeep,	"noikeep"},	/* free empty inode clusters */
+	{Opt_largeio,	"largeio"},	/* report large I/O sizes in stat() */
+	{Opt_nolargeio,	"nolargeio"},	/* do not report large I/O sizes
+					 * in stat(). */
+	{Opt_attr2,	"attr2"},	/* do use attr2 attribute format */
+	{Opt_noattr2,	"noattr2"},	/* do not use attr2 attribute format */
+	{Opt_filestreams,"filestreams"},/* use filestreams allocator */
+	{Opt_quota,	"quota"},	/* disk quotas (user) */
+	{Opt_noquota,	"noquota"},	/* no quotas */
+	{Opt_usrquota,	"usrquota"},	/* user quota enabled */
+	{Opt_grpquota,	"grpquota"},	/* group quota enabled */
+	{Opt_prjquota,	"prjquota"},	/* project quota enabled */
+	{Opt_uquota,	"uquota"},	/* user quota (IRIX variant) */
+	{Opt_gquota,	"gquota"},	/* group quota (IRIX variant) */
+	{Opt_pquota,	"pquota"},	/* project quota (IRIX variant) */
+	{Opt_uqnoenforce,"uqnoenforce"},/* user quota limit enforcement */
+	{Opt_gqnoenforce,"gqnoenforce"},/* group quota limit enforcement */
+	{Opt_pqnoenforce,"pqnoenforce"},/* project quota limit enforcement */
+	{Opt_qnoenforce, "qnoenforce"},	/* same as uqnoenforce */
+	{Opt_discard,	"discard"},	/* Discard unused blocks */
+	{Opt_nodiscard,	"nodiscard"},	/* Do not discard unused blocks */
+
+	{Opt_dax,	"dax"},		/* Enable direct access to bdev pages */
+	{Opt_err,	NULL},
 };
 
 
 STATIC int
-suffix_kstrtoint(char *s, unsigned int base, int *res)
+suffix_kstrtoint(const substring_t *s, unsigned int base, int *res)
 {
 	int	last, shift_left_factor = 0, _res;
-	char	*value = s;
+	char	*value;
+	int	ret = 0;
+
+	value = match_strdup(s);
+	if (!value)
+		return -ENOMEM;
 
 	last = strlen(value) - 1;
 	if (value[last] == 'K' || value[last] == 'k') {
@@ -157,10 +160,11 @@ suffix_kstrtoint(char *s, unsigned int base, int *res)
 		value[last] = '\0';
 	}
 
-	if (kstrtoint(s, base, &_res))
-		return -EINVAL;
+	if (kstrtoint(value, base, &_res))
+		ret = -EINVAL;
+	kfree(value);
 	*res = _res << shift_left_factor;
-	return 0;
+	return ret;
 }
 
 /*
@@ -169,14 +173,19 @@ suffix_kstrtoint(char *s, unsigned int base, int *res)
  *
  * Note that this function leaks the various device name allocations on
  * failure.  The caller takes care of them.
+ *
+ * *sb is const because this is also used to test options on the remount
+ * path, and we don't want this to have any side effects at remount time.
+ * Today this function does not change *sb, but just to future-proof...
  */
 STATIC int
 xfs_parseargs(
 	struct xfs_mount	*mp,
 	char			*options)
 {
-	struct super_block	*sb = mp->m_super;
-	char			*this_char, *value;
+	const struct super_block *sb = mp->m_super;
+	char			*p;
+	substring_t		args[MAX_OPT_ARGS];
 	int			dsunit = 0;
 	int			dswidth = 0;
 	int			iosize = 0;
@@ -217,152 +226,152 @@ xfs_parseargs(
 	if (!options)
 		goto done;
 
-	while ((this_char = strsep(&options, ",")) != NULL) {
-		if (!*this_char)
+	while ((p = strsep(&options, ",")) != NULL) {
+		int		token;
+
+		if (!*p)
 			continue;
-		if ((value = strchr(this_char, '=')) != NULL)
-			*value++ = 0;
 
-		if (!strcmp(this_char, MNTOPT_LOGBUFS)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
-				return -EINVAL;
-			}
-			if (kstrtoint(value, 10, &mp->m_logbufs))
-				return -EINVAL;
-		} else if (!strcmp(this_char, MNTOPT_LOGBSIZE)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
-				return -EINVAL;
-			}
-			if (suffix_kstrtoint(value, 10, &mp->m_logbsize))
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_logbufs:
+			if (match_int(args, &mp->m_logbufs))
 				return -EINVAL;
-		} else if (!strcmp(this_char, MNTOPT_LOGDEV)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
+			break;
+		case Opt_logbsize:
+			if (suffix_kstrtoint(args, 10, &mp->m_logbsize))
 				return -EINVAL;
-			}
-			mp->m_logname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
+			break;
+		case Opt_logdev:
+			mp->m_logname = match_strdup(args);
 			if (!mp->m_logname)
 				return -ENOMEM;
-		} else if (!strcmp(this_char, MNTOPT_MTPT)) {
-			xfs_warn(mp, "%s option not allowed on this system",
-				this_char);
+			break;
+		case Opt_mtpt:
+			xfs_warn(mp, "%s option not allowed on this system", p);
 			return -EINVAL;
-		} else if (!strcmp(this_char, MNTOPT_RTDEV)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
-				return -EINVAL;
-			}
-			mp->m_rtname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
+		case Opt_rtdev:
+			mp->m_rtname = match_strdup(args);
 			if (!mp->m_rtname)
 				return -ENOMEM;
-		} else if (!strcmp(this_char, MNTOPT_ALLOCSIZE) ||
-			   !strcmp(this_char, MNTOPT_BIOSIZE)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
-				return -EINVAL;
-			}
-			if (suffix_kstrtoint(value, 10, &iosize))
+			break;
+		case Opt_allocsize:
+		case Opt_biosize:
+			if (suffix_kstrtoint(args, 10, &iosize))
 				return -EINVAL;
 			iosizelog = ffs(iosize) - 1;
-		} else if (!strcmp(this_char, MNTOPT_GRPID) ||
-			   !strcmp(this_char, MNTOPT_BSDGROUPS)) {
+			break;
+		case Opt_grpid:
+		case Opt_bsdgroups:
 			mp->m_flags |= XFS_MOUNT_GRPID;
-		} else if (!strcmp(this_char, MNTOPT_NOGRPID) ||
-			   !strcmp(this_char, MNTOPT_SYSVGROUPS)) {
+			break;
+		case Opt_nogrpid:
+		case Opt_sysvgroups:
 			mp->m_flags &= ~XFS_MOUNT_GRPID;
-		} else if (!strcmp(this_char, MNTOPT_WSYNC)) {
+			break;
+		case Opt_wsync:
 			mp->m_flags |= XFS_MOUNT_WSYNC;
-		} else if (!strcmp(this_char, MNTOPT_NORECOVERY)) {
+			break;
+		case Opt_norecovery:
 			mp->m_flags |= XFS_MOUNT_NORECOVERY;
-		} else if (!strcmp(this_char, MNTOPT_NOALIGN)) {
+			break;
+		case Opt_noalign:
 			mp->m_flags |= XFS_MOUNT_NOALIGN;
-		} else if (!strcmp(this_char, MNTOPT_SWALLOC)) {
+			break;
+		case Opt_swalloc:
 			mp->m_flags |= XFS_MOUNT_SWALLOC;
-		} else if (!strcmp(this_char, MNTOPT_SUNIT)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
-				return -EINVAL;
-			}
-			if (kstrtoint(value, 10, &dsunit))
-				return -EINVAL;
-		} else if (!strcmp(this_char, MNTOPT_SWIDTH)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
+			break;
+		case Opt_sunit:
+			if (match_int(args, &dsunit))
 				return -EINVAL;
-			}
-			if (kstrtoint(value, 10, &dswidth))
+			break;
+		case Opt_swidth:
+			if (match_int(args, &dswidth))
 				return -EINVAL;
-		} else if (!strcmp(this_char, MNTOPT_32BITINODE)) {
+			break;
+		case Opt_inode32:
 			mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
-		} else if (!strcmp(this_char, MNTOPT_64BITINODE)) {
+			break;
+		case Opt_inode64:
 			mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
-		} else if (!strcmp(this_char, MNTOPT_NOUUID)) {
+			break;
+		case Opt_nouuid:
 			mp->m_flags |= XFS_MOUNT_NOUUID;
-		} else if (!strcmp(this_char, MNTOPT_BARRIER)) {
+			break;
+		case Opt_barrier:
 			mp->m_flags |= XFS_MOUNT_BARRIER;
-		} else if (!strcmp(this_char, MNTOPT_NOBARRIER)) {
+			break;
+		case Opt_nobarrier:
 			mp->m_flags &= ~XFS_MOUNT_BARRIER;
-		} else if (!strcmp(this_char, MNTOPT_IKEEP)) {
+			break;
+		case Opt_ikeep:
 			mp->m_flags |= XFS_MOUNT_IKEEP;
-		} else if (!strcmp(this_char, MNTOPT_NOIKEEP)) {
+			break;
+		case Opt_noikeep:
 			mp->m_flags &= ~XFS_MOUNT_IKEEP;
-		} else if (!strcmp(this_char, MNTOPT_LARGEIO)) {
+			break;
+		case Opt_largeio:
 			mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
-		} else if (!strcmp(this_char, MNTOPT_NOLARGEIO)) {
+			break;
+		case Opt_nolargeio:
 			mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
-		} else if (!strcmp(this_char, MNTOPT_ATTR2)) {
+			break;
+		case Opt_attr2:
 			mp->m_flags |= XFS_MOUNT_ATTR2;
-		} else if (!strcmp(this_char, MNTOPT_NOATTR2)) {
+			break;
+		case Opt_noattr2:
 			mp->m_flags &= ~XFS_MOUNT_ATTR2;
 			mp->m_flags |= XFS_MOUNT_NOATTR2;
-		} else if (!strcmp(this_char, MNTOPT_FILESTREAM)) {
+			break;
+		case Opt_filestreams:
 			mp->m_flags |= XFS_MOUNT_FILESTREAMS;
-		} else if (!strcmp(this_char, MNTOPT_NOQUOTA)) {
+			break;
+		case Opt_noquota:
 			mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
 			mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
 			mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
-		} else if (!strcmp(this_char, MNTOPT_QUOTA) ||
-			   !strcmp(this_char, MNTOPT_UQUOTA) ||
-			   !strcmp(this_char, MNTOPT_USRQUOTA)) {
+			break;
+		case Opt_quota:
+		case Opt_uquota:
+		case Opt_usrquota:
 			mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
 					 XFS_UQUOTA_ENFD);
-		} else if (!strcmp(this_char, MNTOPT_QUOTANOENF) ||
-			   !strcmp(this_char, MNTOPT_UQUOTANOENF)) {
+			break;
+		case Opt_qnoenforce:
+		case Opt_uqnoenforce:
 			mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
 			mp->m_qflags &= ~XFS_UQUOTA_ENFD;
-		} else if (!strcmp(this_char, MNTOPT_PQUOTA) ||
-			   !strcmp(this_char, MNTOPT_PRJQUOTA)) {
+			break;
+		case Opt_pquota:
+		case Opt_prjquota:
 			mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
 					 XFS_PQUOTA_ENFD);
-		} else if (!strcmp(this_char, MNTOPT_PQUOTANOENF)) {
+			break;
+		case Opt_pqnoenforce:
 			mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
 			mp->m_qflags &= ~XFS_PQUOTA_ENFD;
-		} else if (!strcmp(this_char, MNTOPT_GQUOTA) ||
-			   !strcmp(this_char, MNTOPT_GRPQUOTA)) {
+		case Opt_gquota:
+		case Opt_grpquota:
 			mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
 					 XFS_GQUOTA_ENFD);
-		} else if (!strcmp(this_char, MNTOPT_GQUOTANOENF)) {
+			break;
+		case Opt_gqnoenforce:
 			mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
 			mp->m_qflags &= ~XFS_GQUOTA_ENFD;
-		} else if (!strcmp(this_char, MNTOPT_DISCARD)) {
+			break;
+		case Opt_discard:
 			mp->m_flags |= XFS_MOUNT_DISCARD;
-		} else if (!strcmp(this_char, MNTOPT_NODISCARD)) {
+			break;
+		case Opt_nodiscard:
 			mp->m_flags &= ~XFS_MOUNT_DISCARD;
+			break;
 #ifdef CONFIG_FS_DAX
-		} else if (!strcmp(this_char, MNTOPT_DAX)) {
+		case Opt_dax:
 			mp->m_flags |= XFS_MOUNT_DAX;
+			break;
 #endif
-		} else {
-			xfs_warn(mp, "unknown mount option [%s].", this_char);
+		default:
+			xfs_warn(mp, "unknown mount option [%s].", p);
 			return -EINVAL;
 		}
 	}
@@ -461,25 +470,25 @@ xfs_showargs(
 {
 	static struct proc_xfs_info xfs_info_set[] = {
 		/* the few simple ones we can get from the mount struct */
-		{ XFS_MOUNT_IKEEP,		"," MNTOPT_IKEEP },
-		{ XFS_MOUNT_WSYNC,		"," MNTOPT_WSYNC },
-		{ XFS_MOUNT_NOALIGN,		"," MNTOPT_NOALIGN },
-		{ XFS_MOUNT_SWALLOC,		"," MNTOPT_SWALLOC },
-		{ XFS_MOUNT_NOUUID,		"," MNTOPT_NOUUID },
-		{ XFS_MOUNT_NORECOVERY,		"," MNTOPT_NORECOVERY },
-		{ XFS_MOUNT_ATTR2,		"," MNTOPT_ATTR2 },
-		{ XFS_MOUNT_FILESTREAMS,	"," MNTOPT_FILESTREAM },
-		{ XFS_MOUNT_GRPID,		"," MNTOPT_GRPID },
-		{ XFS_MOUNT_DISCARD,		"," MNTOPT_DISCARD },
-		{ XFS_MOUNT_SMALL_INUMS,	"," MNTOPT_32BITINODE },
-		{ XFS_MOUNT_DAX,		"," MNTOPT_DAX },
+		{ XFS_MOUNT_IKEEP,		",ikeep" },
+		{ XFS_MOUNT_WSYNC,		",wsync" },
+		{ XFS_MOUNT_NOALIGN,		",noalign" },
+		{ XFS_MOUNT_SWALLOC,		",swalloc" },
+		{ XFS_MOUNT_NOUUID,		",nouuid" },
+		{ XFS_MOUNT_NORECOVERY,		",norecovery" },
+		{ XFS_MOUNT_ATTR2,		",attr2" },
+		{ XFS_MOUNT_FILESTREAMS,	",filestreams" },
+		{ XFS_MOUNT_GRPID,		",grpid" },
+		{ XFS_MOUNT_DISCARD,		",discard" },
+		{ XFS_MOUNT_SMALL_INUMS,	",inode32" },
+		{ XFS_MOUNT_DAX,		",dax" },
 		{ 0, NULL }
 	};
 	static struct proc_xfs_info xfs_info_unset[] = {
 		/* the few simple ones we can get from the mount struct */
-		{ XFS_MOUNT_COMPAT_IOSIZE,	"," MNTOPT_LARGEIO },
-		{ XFS_MOUNT_BARRIER,		"," MNTOPT_NOBARRIER },
-		{ XFS_MOUNT_SMALL_INUMS,	"," MNTOPT_64BITINODE },
+		{ XFS_MOUNT_COMPAT_IOSIZE,	",largeio" },
+		{ XFS_MOUNT_BARRIER,		",nobarrier" },
+		{ XFS_MOUNT_SMALL_INUMS,	",inode64" },
 		{ 0, NULL }
 	};
 	struct proc_xfs_info	*xfs_infop;
@@ -494,46 +503,46 @@ xfs_showargs(
 	}
 
 	if (mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)
-		seq_printf(m, "," MNTOPT_ALLOCSIZE "=%dk",
+		seq_printf(m, ",allocsize=%dk",
 				(int)(1 << mp->m_writeio_log) >> 10);
 
 	if (mp->m_logbufs > 0)
-		seq_printf(m, "," MNTOPT_LOGBUFS "=%d", mp->m_logbufs);
+		seq_printf(m, ",logbufs=%d", mp->m_logbufs);
 	if (mp->m_logbsize > 0)
-		seq_printf(m, "," MNTOPT_LOGBSIZE "=%dk", mp->m_logbsize >> 10);
+		seq_printf(m, ",logbsize=%dk", mp->m_logbsize >> 10);
 
 	if (mp->m_logname)
-		seq_show_option(m, MNTOPT_LOGDEV, mp->m_logname);
+		seq_show_option(m, "logdev", mp->m_logname);
 	if (mp->m_rtname)
-		seq_show_option(m, MNTOPT_RTDEV, mp->m_rtname);
+		seq_show_option(m, "rtdev", mp->m_rtname);
 
 	if (mp->m_dalign > 0)
-		seq_printf(m, "," MNTOPT_SUNIT "=%d",
+		seq_printf(m, ",sunit=%d",
 				(int)XFS_FSB_TO_BB(mp, mp->m_dalign));
 	if (mp->m_swidth > 0)
-		seq_printf(m, "," MNTOPT_SWIDTH "=%d",
+		seq_printf(m, ",swidth=%d",
 				(int)XFS_FSB_TO_BB(mp, mp->m_swidth));
 
 	if (mp->m_qflags & (XFS_UQUOTA_ACCT|XFS_UQUOTA_ENFD))
-		seq_puts(m, "," MNTOPT_USRQUOTA);
+		seq_puts(m, ",usrquota");
 	else if (mp->m_qflags & XFS_UQUOTA_ACCT)
-		seq_puts(m, "," MNTOPT_UQUOTANOENF);
+		seq_puts(m, ",uqnoenforce");
 
 	if (mp->m_qflags & XFS_PQUOTA_ACCT) {
 		if (mp->m_qflags & XFS_PQUOTA_ENFD)
-			seq_puts(m, "," MNTOPT_PRJQUOTA);
+			seq_puts(m, ",prjquota");
 		else
-			seq_puts(m, "," MNTOPT_PQUOTANOENF);
+			seq_puts(m, ",pqnoenforce");
 	}
 	if (mp->m_qflags & XFS_GQUOTA_ACCT) {
 		if (mp->m_qflags & XFS_GQUOTA_ENFD)
-			seq_puts(m, "," MNTOPT_GRPQUOTA);
+			seq_puts(m, ",grpquota");
 		else
-			seq_puts(m, "," MNTOPT_GQUOTANOENF);
+			seq_puts(m, ",gqnoenforce");
 	}
 
 	if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT))
-		seq_puts(m, "," MNTOPT_NOQUOTA);
+		seq_puts(m, ",noquota");
 
 	return 0;
 }
@@ -572,23 +581,35 @@ xfs_max_file_offset(
 }
 
 /*
- * xfs_set_inode32() and xfs_set_inode64() are passed an agcount
- * because in the growfs case, mp->m_sb.sb_agcount is not updated
- * yet to the potentially higher ag count.
+ * Set parameters for inode allocation heuristics, taking into account
+ * filesystem size and inode32/inode64 mount options; i.e. specifically
+ * whether or not XFS_MOUNT_SMALL_INUMS is set.
+ *
+ * Inode allocation patterns are altered only if inode32 is requested
+ * (XFS_MOUNT_SMALL_INUMS), and the filesystem is sufficiently large.
+ * If altered, XFS_MOUNT_32BITINODES is set as well.
+ *
+ * An agcount independent of that in the mount structure is provided
+ * because in the growfs case, mp->m_sb.sb_agcount is not yet updated
+ * to the potentially higher ag count.
+ *
+ * Returns the maximum AG index which may contain inodes.
  */
 xfs_agnumber_t
-xfs_set_inode32(struct xfs_mount *mp, xfs_agnumber_t agcount)
+xfs_set_inode_alloc(
+	struct xfs_mount *mp,
+	xfs_agnumber_t	agcount)
 {
-	xfs_agnumber_t	index = 0;
+	xfs_agnumber_t	index;
 	xfs_agnumber_t	maxagi = 0;
 	xfs_sb_t	*sbp = &mp->m_sb;
 	xfs_agnumber_t	max_metadata;
 	xfs_agino_t	agino;
 	xfs_ino_t	ino;
-	xfs_perag_t	*pag;
 
-	/* Calculate how much should be reserved for inodes to meet
-	 * the max inode percentage.
+	/*
+	 * Calculate how much should be reserved for inodes to meet
+	 * the max inode percentage.  Used only for inode32.
 	 */
 	if (mp->m_maxicount) {
 		__uint64_t	icount;
@@ -602,54 +623,48 @@ xfs_set_inode32(struct xfs_mount *mp, xfs_agnumber_t agcount)
 		max_metadata = agcount;
 	}
 
+	/* Get the last possible inode in the filesystem */
 	agino =	XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
+	ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
+
+	/*
+	 * If user asked for no more than 32-bit inodes, and the fs is
+	 * sufficiently large, set XFS_MOUNT_32BITINODES if we must alter
+	 * the allocator to accommodate the request.
+	 */
+	if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) && ino > XFS_MAXINUMBER_32)
+		mp->m_flags |= XFS_MOUNT_32BITINODES;
+	else
+		mp->m_flags &= ~XFS_MOUNT_32BITINODES;
 
 	for (index = 0; index < agcount; index++) {
-		ino = XFS_AGINO_TO_INO(mp, index, agino);
+		struct xfs_perag	*pag;
 
-		if (ino > XFS_MAXINUMBER_32) {
-			pag = xfs_perag_get(mp, index);
-			pag->pagi_inodeok = 0;
-			pag->pagf_metadata = 0;
-			xfs_perag_put(pag);
-			continue;
-		}
+		ino = XFS_AGINO_TO_INO(mp, index, agino);
 
 		pag = xfs_perag_get(mp, index);
-		pag->pagi_inodeok = 1;
-		maxagi++;
-		if (index < max_metadata)
-			pag->pagf_metadata = 1;
-		xfs_perag_put(pag);
-	}
-	mp->m_flags |= (XFS_MOUNT_32BITINODES |
-			XFS_MOUNT_SMALL_INUMS);
 
-	return maxagi;
-}
-
-xfs_agnumber_t
-xfs_set_inode64(struct xfs_mount *mp, xfs_agnumber_t agcount)
-{
-	xfs_agnumber_t index = 0;
-
-	for (index = 0; index < agcount; index++) {
-		struct xfs_perag	*pag;
+		if (mp->m_flags & XFS_MOUNT_32BITINODES) {
+			if (ino > XFS_MAXINUMBER_32) {
+				pag->pagi_inodeok = 0;
+				pag->pagf_metadata = 0;
+			} else {
+				pag->pagi_inodeok = 1;
+				maxagi++;
+				if (index < max_metadata)
+					pag->pagf_metadata = 1;
+				else
+					pag->pagf_metadata = 0;
+			}
+		} else {
+			pag->pagi_inodeok = 1;
+			pag->pagf_metadata = 0;
+		}
 
-		pag = xfs_perag_get(mp, index);
-		pag->pagi_inodeok = 1;
-		pag->pagf_metadata = 0;
 		xfs_perag_put(pag);
 	}
 
-	/* There is no need for lock protection on m_flags,
-	 * the rw_semaphore of the VFS superblock is locked
-	 * during mount/umount/remount operations, so this is
-	 * enough to avoid concurency on the m_flags field
-	 */
-	mp->m_flags &= ~(XFS_MOUNT_32BITINODES |
-			 XFS_MOUNT_SMALL_INUMS);
-	return index;
+	return (mp->m_flags & XFS_MOUNT_32BITINODES) ? maxagi : agcount;
 }
 
 STATIC int
@@ -1166,6 +1181,27 @@ xfs_quiesce_attr(
 }
 
 STATIC int
+xfs_test_remount_options(
+	struct super_block	*sb,
+	struct xfs_mount	*mp,
+	char			*options)
+{
+	int			error = 0;
+	struct xfs_mount	*tmp_mp;
+
+	tmp_mp = kmem_zalloc(sizeof(*tmp_mp), KM_MAYFAIL);
+	if (!tmp_mp)
+		return -ENOMEM;
+
+	tmp_mp->m_super = sb;
+	error = xfs_parseargs(tmp_mp, options);
+	xfs_free_fsname(tmp_mp);
+	kfree(tmp_mp);
+
+	return error;
+}
+
+STATIC int
 xfs_fs_remount(
 	struct super_block	*sb,
 	int			*flags,
@@ -1177,6 +1213,11 @@ xfs_fs_remount(
 	char			*p;
 	int			error;
 
+	/* First, check for complete junk; i.e. invalid options */
+	error = xfs_test_remount_options(sb, mp, options);
+	if (error)
+		return error;
+
 	sync_filesystem(sb);
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
@@ -1193,10 +1234,12 @@ xfs_fs_remount(
 			mp->m_flags &= ~XFS_MOUNT_BARRIER;
 			break;
 		case Opt_inode64:
-			mp->m_maxagi = xfs_set_inode64(mp, sbp->sb_agcount);
+			mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
+			mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
 			break;
 		case Opt_inode32:
-			mp->m_maxagi = xfs_set_inode32(mp, sbp->sb_agcount);
+			mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
+			mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
 			break;
 		default:
 			/*
@@ -1344,9 +1387,8 @@ xfs_finish_flags(
 	 */
 	if (xfs_sb_version_hascrc(&mp->m_sb) &&
 	    (mp->m_flags & XFS_MOUNT_NOATTR2)) {
-		xfs_warn(mp,
-"Cannot mount a V5 filesystem as %s. %s is always enabled for V5 filesystems.",
-			MNTOPT_NOATTR2, MNTOPT_ATTR2);
+		xfs_warn(mp, "Cannot mount a V5 filesystem as noattr2. "
+			     "attr2 is always enabled for V5 filesystems.");
 		return -EINVAL;
 	}
 
@@ -1817,6 +1859,8 @@ init_xfs_fs(void)
 {
 	int			error;
 
+	xfs_check_ondisk_structs();
+
 	printk(KERN_INFO XFS_VERSION_STRING " with "
 			 XFS_BUILD_OPTIONS " enabled\n");
 
diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h
index 499058fea303..2dfb1ce4585f 100644
--- a/fs/xfs/xfs_super.h
+++ b/fs/xfs/xfs_super.h
@@ -65,8 +65,8 @@ extern __uint64_t xfs_max_file_offset(unsigned int);
 
 extern void xfs_flush_inodes(struct xfs_mount *mp);
 extern void xfs_blkdev_issue_flush(struct xfs_buftarg *);
-extern xfs_agnumber_t xfs_set_inode32(struct xfs_mount *, xfs_agnumber_t agcount);
-extern xfs_agnumber_t xfs_set_inode64(struct xfs_mount *, xfs_agnumber_t agcount);
+extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *,
+					   xfs_agnumber_t agcount);
 
 extern const struct export_operations xfs_export_operations;
 extern const struct xattr_handler *xfs_xattr_handlers[];
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 641d625eb334..6ced4f143494 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -18,10 +18,13 @@
 
 #include "xfs.h"
 #include "xfs_sysfs.h"
+#include "xfs_format.h"
 #include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_log.h"
 #include "xfs_log_priv.h"
 #include "xfs_stats.h"
+#include "xfs_mount.h"
 
 struct xfs_sysfs_attr {
 	struct attribute attr;
@@ -45,16 +48,6 @@ to_attr(struct attribute *attr)
 
 #define ATTR_LIST(name) &xfs_sysfs_attr_##name.attr
 
-/*
- * xfs_mount kobject. This currently has no attributes and thus no need for show
- * and store helpers. The mp kobject serves as the per-mount parent object that
- * is identified by the fsname under sysfs.
- */
-
-struct kobj_type xfs_mp_ktype = {
-	.release = xfs_sysfs_release,
-};
-
 STATIC ssize_t
 xfs_sysfs_object_show(
 	struct kobject		*kobject,
@@ -83,6 +76,71 @@ static const struct sysfs_ops xfs_sysfs_ops = {
 	.store = xfs_sysfs_object_store,
 };
 
+/*
+ * xfs_mount kobject. The mp kobject also serves as the per-mount parent object
+ * that is identified by the fsname under sysfs.
+ */
+
+static inline struct xfs_mount *
+to_mp(struct kobject *kobject)
+{
+	struct xfs_kobj *kobj = to_kobj(kobject);
+
+	return container_of(kobj, struct xfs_mount, m_kobj);
+}
+
+#ifdef DEBUG
+
+STATIC ssize_t
+fail_writes_store(
+	struct kobject		*kobject,
+	const char		*buf,
+	size_t			count)
+{
+	struct xfs_mount	*mp = to_mp(kobject);
+	int			ret;
+	int			val;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val == 1)
+		mp->m_fail_writes = true;
+	else if (val == 0)
+		mp->m_fail_writes = false;
+	else
+		return -EINVAL;
+
+	return count;
+}
+
+STATIC ssize_t
+fail_writes_show(
+	struct kobject		*kobject,
+	char			*buf)
+{
+	struct xfs_mount	*mp = to_mp(kobject);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_fail_writes ? 1 : 0);
+}
+XFS_SYSFS_ATTR_RW(fail_writes);
+
+#endif /* DEBUG */
+
+static struct attribute *xfs_mp_attrs[] = {
+#ifdef DEBUG
+	ATTR_LIST(fail_writes),
+#endif
+	NULL,
+};
+
+struct kobj_type xfs_mp_ktype = {
+	.release = xfs_sysfs_release,
+	.sysfs_ops = &xfs_sysfs_ops,
+	.default_attrs = xfs_mp_attrs,
+};
+
 #ifdef DEBUG
 /* debug */
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 391d797cb53f..c8d58426008e 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1296,11 +1296,7 @@ DEFINE_IOMAP_EVENT(xfs_map_blocks_found);
 DEFINE_IOMAP_EVENT(xfs_map_blocks_alloc);
 DEFINE_IOMAP_EVENT(xfs_get_blocks_found);
 DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_new);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_update);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_none);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_endio);
+DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct);
 
 DECLARE_EVENT_CLASS(xfs_simple_io_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),
@@ -1340,6 +1336,9 @@ DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert);
 DEFINE_SIMPLE_IO_EVENT(xfs_get_blocks_notfound);
 DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize);
 DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof);
+DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
+DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_unwritten);
+DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_append);
 
 DECLARE_EVENT_CLASS(xfs_itrunc_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size),
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 748b16aff45a..20c53666cb4b 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1028,6 +1028,8 @@ __xfs_trans_roll(
 	struct xfs_trans_res	tres;
 	int			error;
 
+	*committed = 0;
+
 	/*
 	 * Ensure that the inode is always logged.
 	 */
@@ -1082,6 +1084,6 @@ xfs_trans_roll(
 	struct xfs_trans	**tpp,
 	struct xfs_inode	*dp)
 {
-	int			committed = 0;
+	int			committed;
 	return __xfs_trans_roll(tpp, dp, &committed);
 }
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 4643070d7cae..e7c49cf43fbc 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -133,7 +133,6 @@ typedef struct xfs_trans {
  * XFS transaction mechanism exported interfaces that are
  * actually macros.
  */
-#define	xfs_trans_get_block_res(tp)	((tp)->t_blk_res)
 #define	xfs_trans_set_sync(tp)		((tp)->t_flags |= XFS_TRANS_SYNC)
 
 #if defined(DEBUG) || defined(XFS_WARN)
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 4f18fd92ca13..d6c9c3e9e02b 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -497,6 +497,7 @@ xfsaild(
 	long		tout = 0;	/* milliseconds */
 
 	current->flags |= PF_MEMALLOC;
+	set_freezable();
 
 	while (!kthread_should_stop()) {
 		if (tout && tout <= 20)
@@ -519,14 +520,14 @@ xfsaild(
 		if (!xfs_ail_min(ailp) &&
 		    ailp->xa_target == ailp->xa_target_prev) {
 			spin_unlock(&ailp->xa_lock);
-			schedule();
+			freezable_schedule();
 			tout = 0;
 			continue;
 		}
 		spin_unlock(&ailp->xa_lock);
 
 		if (tout)
-			schedule_timeout(msecs_to_jiffies(tout));
+			freezable_schedule_timeout(msecs_to_jiffies(tout));
 
 		__set_current_state(TASK_RUNNING);
 
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 75798412859a..8ee29ca132dc 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -155,7 +155,7 @@ xfs_trans_get_buf_map(
 		ASSERT(xfs_buf_islocked(bp));
 		if (XFS_FORCED_SHUTDOWN(tp->t_mountp)) {
 			xfs_buf_stale(bp);
-			XFS_BUF_DONE(bp);
+			bp->b_flags |= XBF_DONE;
 		}
 
 		ASSERT(bp->b_transp == tp);
@@ -518,7 +518,7 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 	 * inside the b_bdstrat callback so that this won't get written to
 	 * disk.
 	 */
-	XFS_BUF_DONE(bp);
+	bp->b_flags |= XBF_DONE;
 
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 	bp->b_iodone = xfs_buf_iodone_callbacks;
@@ -534,8 +534,8 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 	 */
 	if (bip->bli_flags & XFS_BLI_STALE) {
 		bip->bli_flags &= ~XFS_BLI_STALE;
-		ASSERT(XFS_BUF_ISSTALE(bp));
-		XFS_BUF_UNSTALE(bp);
+		ASSERT(bp->b_flags & XBF_STALE);
+		bp->b_flags &= ~XBF_STALE;
 		bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL;
 	}
 
@@ -600,7 +600,7 @@ xfs_trans_binval(
 		 * If the buffer is already invalidated, then
 		 * just return.
 		 */
-		ASSERT(XFS_BUF_ISSTALE(bp));
+		ASSERT(bp->b_flags & XBF_STALE);
 		ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY)));
 		ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_INODE_BUF));
 		ASSERT(!(bip->__bli_format.blf_flags & XFS_BLFT_MASK));
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 995170194df0..c3d547211d16 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -609,17 +609,20 @@ xfs_trans_dqresv(
 	xfs_qcnt_t	total_count;
 	xfs_qcnt_t	*resbcountp;
 	xfs_quotainfo_t	*q = mp->m_quotainfo;
+	struct xfs_def_quota	*defq;
 
 
 	xfs_dqlock(dqp);
 
+	defq = xfs_get_defquota(dqp, q);
+
 	if (flags & XFS_TRANS_DQ_RES_BLKS) {
 		hardlimit = be64_to_cpu(dqp->q_core.d_blk_hardlimit);
 		if (!hardlimit)
-			hardlimit = q->qi_bhardlimit;
+			hardlimit = defq->bhardlimit;
 		softlimit = be64_to_cpu(dqp->q_core.d_blk_softlimit);
 		if (!softlimit)
-			softlimit = q->qi_bsoftlimit;
+			softlimit = defq->bsoftlimit;
 		timer = be32_to_cpu(dqp->q_core.d_btimer);
 		warns = be16_to_cpu(dqp->q_core.d_bwarns);
 		warnlimit = dqp->q_mount->m_quotainfo->qi_bwarnlimit;
@@ -628,10 +631,10 @@ xfs_trans_dqresv(
 		ASSERT(flags & XFS_TRANS_DQ_RES_RTBLKS);
 		hardlimit = be64_to_cpu(dqp->q_core.d_rtb_hardlimit);
 		if (!hardlimit)
-			hardlimit = q->qi_rtbhardlimit;
+			hardlimit = defq->rtbhardlimit;
 		softlimit = be64_to_cpu(dqp->q_core.d_rtb_softlimit);
 		if (!softlimit)
-			softlimit = q->qi_rtbsoftlimit;
+			softlimit = defq->rtbsoftlimit;
 		timer = be32_to_cpu(dqp->q_core.d_rtbtimer);
 		warns = be16_to_cpu(dqp->q_core.d_rtbwarns);
 		warnlimit = dqp->q_mount->m_quotainfo->qi_rtbwarnlimit;
@@ -672,10 +675,10 @@ xfs_trans_dqresv(
 			warnlimit = dqp->q_mount->m_quotainfo->qi_iwarnlimit;
 			hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit);
 			if (!hardlimit)
-				hardlimit = q->qi_ihardlimit;
+				hardlimit = defq->ihardlimit;
 			softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit);
 			if (!softlimit)
-				softlimit = q->qi_isoftlimit;
+				softlimit = defq->isoftlimit;
 
 			if (hardlimit && total_count > hardlimit) {
 				xfs_quota_warn(mp, dqp, QUOTA_NL_IHARDWARN);
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index b97f1df910ab..11a3af08b5c7 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -75,18 +75,10 @@ xfs_trans_ichgtime(
 
 	tv = current_fs_time(inode->i_sb);
 
-	if ((flags & XFS_ICHGTIME_MOD) &&
-	    !timespec_equal(&inode->i_mtime, &tv)) {
+	if (flags & XFS_ICHGTIME_MOD)
 		inode->i_mtime = tv;
-		ip->i_d.di_mtime.t_sec = tv.tv_sec;
-		ip->i_d.di_mtime.t_nsec = tv.tv_nsec;
-	}
-	if ((flags & XFS_ICHGTIME_CHG) &&
-	    !timespec_equal(&inode->i_ctime, &tv)) {
+	if (flags & XFS_ICHGTIME_CHG)
 		inode->i_ctime = tv;
-		ip->i_d.di_ctime.t_sec = tv.tv_sec;
-		ip->i_d.di_ctime.t_nsec = tv.tv_nsec;
-	}
 }
 
 /*
@@ -125,7 +117,7 @@ xfs_trans_log_inode(
 	 */
 	if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
 	    IS_I_VERSION(VFS_I(ip))) {
-		ip->i_d.di_changecount = ++VFS_I(ip)->i_version;
+		VFS_I(ip)->i_version++;
 		flags |= XFS_ILOG_CORE;
 	}
author	Tony Lindgren <tony@atomide.com>	2016-03-30 10:36:06 -0700
committer	Tony Lindgren <tony@atomide.com>	2016-03-30 10:36:06 -0700
commit	1809de7e7d37c585e01a1bcc583ea92b78fc759d (patch)
tree	76c5b35c2b04eafce86a1a729c02ab705eba44bc /fs
parent	ARM: OMAP2+: Use srst_udelay for USB on dm814x (diff)
parent	ARM: OMAP2+: hwmod: Fix updating of sysconfig register (diff)
download	wireguard-linux-1809de7e7d37c585e01a1bcc583ea92b78fc759d.tar.xz wireguard-linux-1809de7e7d37c585e01a1bcc583ea92b78fc759d.zip