Merge remote-tracking branch 'common/android-3.0' into android-samsung-30-wip-mergedown

* common/android-3.0: (1178 commits)
  cpufreq: interactive: remove unused target_validate_time_in_idle
  cpufreq: interactive: Boost frequency on touchscreen input
  cpufreq: Separate speed target revalidate time and initial set time
  cpufreq: interactive: based hispeed bump on target freq, not actual
  cpufreq: interactive: adjust code and documentation to match
  cpufreq: interactive: configurable delay before raising above hispeed
  sync: add poll support
  sw_sync: add fill_driver_data support
  sync: add ioctl to get fence data
  sw_sync: add debug support
  sync: add debugfs support
  sync: add timestamps to sync_pts
  sw_sync: add cpu based sync driver
  sync: Add synchronization framework
  Linux 3.0.28
  Bluetooth: Fix l2cap conn failures for ssp devices
  TOMOYO: Fix mount flags checking order.
  iommu/amd: Make sure IOMMU interrupts are re-enabled on resume
  cred: copy_process() should clear child->replacement_session_keyring
  ASoC: ak4642: fixup: mute needs +1 step
  ...

Conflicts:
	mm/compaction.c

Change-Id: I3dc59225d2435eddbed0c639155179e580891ac8
Signed-off-by: JP Abgrall <jpa@google.com>

106 files changed, 1471 insertions, 780 deletions

diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 5a9b684..1f3624d 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -109,7 +109,7 @@ struct afs_call {
 	unsigned		reply_size;	/* current size of reply */
 	unsigned		first_offset;	/* offset into mapping[first] */
 	unsigned		last_to;	/* amount of mapping[last] */
-	unsigned short		offset;		/* offset into received data store */
+	unsigned		offset;		/* offset into received data store */
 	unsigned char		unmarshall;	/* unmarshalling phase */
 	bool			incoming;	/* T if incoming call */
 	bool			send_pages;	/* T if data from mapping should be sent */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index e45a323..8ad8c2a 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -314,6 +314,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 	struct msghdr msg;
 	struct kvec iov[1];
 	int ret;
+	struct sk_buff *skb;
 
 	_enter("%x,{%d},", addr->s_addr, ntohs(call->port));
 
@@ -380,6 +381,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 
 error_do_abort:
 	rxrpc_kernel_abort_call(rxcall, RX_USER_ABORT);
+	while ((skb = skb_dequeue(&call->rx_queue)))
+		afs_free_skb(skb);
 	rxrpc_kernel_end_call(rxcall);
 	call->rxcall = NULL;
 error_kill_call:
diff --git a/fs/aio.c b/fs/aio.c
index e29ec48..b4a88cc 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -228,12 +228,6 @@ static void __put_ioctx(struct kioctx *ctx)
 	call_rcu(&ctx->rcu_head, ctx_rcu_free);
 }
 
-static inline void get_ioctx(struct kioctx *kioctx)
-{
-	BUG_ON(atomic_read(&kioctx->users) <= 0);
-	atomic_inc(&kioctx->users);
-}
-
 static inline int try_get_ioctx(struct kioctx *kioctx)
 {
 	return atomic_inc_not_zero(&kioctx->users);
@@ -273,7 +267,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	mm = ctx->mm = current->mm;
 	atomic_inc(&mm->mm_count);
 
-	atomic_set(&ctx->users, 1);
+	atomic_set(&ctx->users, 2);
 	spin_lock_init(&ctx->ctx_lock);
 	spin_lock_init(&ctx->ring_info.ring_lock);
 	init_waitqueue_head(&ctx->wait);
@@ -527,11 +521,16 @@ static void aio_fput_routine(struct work_struct *data)
 			fput(req->ki_filp);
 
 		/* Link the iocb into the context's free list */
+		rcu_read_lock();
 		spin_lock_irq(&ctx->ctx_lock);
 		really_put_req(ctx, req);
+		/*
+		 * at that point ctx might've been killed, but actual
+		 * freeing is RCU'd
+		 */
 		spin_unlock_irq(&ctx->ctx_lock);
+		rcu_read_unlock();
 
-		put_ioctx(ctx);
 		spin_lock_irq(&fput_lock);
 	}
 	spin_unlock_irq(&fput_lock);
@@ -562,7 +561,6 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 	 * this function will be executed w/out any aio kthread wakeup.
 	 */
 	if (unlikely(!fput_atomic(req->ki_filp))) {
-		get_ioctx(ctx);
 		spin_lock(&fput_lock);
 		list_add(&req->ki_list, &fput_head);
 		spin_unlock(&fput_lock);
@@ -1256,10 +1254,10 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 	ret = PTR_ERR(ioctx);
 	if (!IS_ERR(ioctx)) {
 		ret = put_user(ioctx->user_id, ctxp);
-		if (!ret)
+		if (!ret) {
+			put_ioctx(ioctx);
 			return 0;
-
-		get_ioctx(ioctx); /* io_destroy() expects us to hold a ref */
+		}
 		io_destroy(ioctx);
 	}
 
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 475f9c5..10cc45a 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -120,6 +120,7 @@ struct autofs_sb_info {
 	int sub_version;
 	int min_proto;
 	int max_proto;
+	int compat_daemon;
 	unsigned long exp_timeout;
 	unsigned int type;
 	int reghost_enabled;
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 509fe1e..56bac70 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -385,6 +385,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,
 		sbi->pipefd = pipefd;
 		sbi->pipe = pipe;
 		sbi->catatonic = 0;
+		sbi->compat_daemon = is_compat_task();
 	}
 out:
 	mutex_unlock(&sbi->wq_mutex);
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 180fa24..eb1e45c 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -19,6 +19,7 @@
 #include <linux/parser.h>
 #include <linux/bitops.h>
 #include <linux/magic.h>
+#include <linux/compat.h>
 #include "autofs_i.h"
 #include <linux/module.h>
 
@@ -224,6 +225,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	set_autofs_type_indirect(&sbi->type);
 	sbi->min_proto = 0;
 	sbi->max_proto = 0;
+	sbi->compat_daemon = is_compat_task();
 	mutex_init(&sbi->wq_mutex);
 	spin_lock_init(&sbi->fs_lock);
 	sbi->queues = NULL;
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 2543598..fbbb749 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -90,7 +90,24 @@ static int autofs4_write(struct file *file, const void *addr, int bytes)
 
 	return (bytes > 0);
 }
-	
+
+/*
+ * The autofs_v5 packet was misdesigned.
+ *
+ * The packets are identical on x86-32 and x86-64, but have different
+ * alignment. Which means that 'sizeof()' will give different results.
+ * Fix it up for the case of running 32-bit user mode on a 64-bit kernel.
+ */
+static noinline size_t autofs_v5_packet_size(struct autofs_sb_info *sbi)
+{
+	size_t pktsz = sizeof(struct autofs_v5_packet);
+#if defined(CONFIG_X86_64) && defined(CONFIG_COMPAT)
+	if (sbi->compat_daemon > 0)
+		pktsz -= 4;
+#endif
+	return pktsz;
+}
+
 static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 				 struct autofs_wait_queue *wq,
 				 int type)
@@ -147,8 +164,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 	{
 		struct autofs_v5_packet *packet = &pkt.v5_pkt.v5_packet;
 
-		pktsz = sizeof(*packet);
-
+		pktsz = autofs_v5_packet_size(sbi);
 		packet->wait_queue_token = wq->wait_queue_token;
 		packet->len = wq->name.len;
 		memcpy(packet->name, wq->name.name, wq->name.len);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 303983f..618493e 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -796,7 +796,16 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 			 * might try to exec.  This is because the brk will
 			 * follow the loader, and is not movable.  */
 #if defined(CONFIG_X86) || defined(CONFIG_ARM)
-			load_bias = 0;
+			/* Memory randomization might have been switched off
+			 * in runtime via sysctl.
+			 * If that is the case, retain the original non-zero
+			 * load_bias value in order to establish proper
+			 * non-randomized mappings.
+			 */
+			if (current->flags & PF_RANDOMIZE)
+				load_bias = 0;
+			else
+				load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
 #else
 			load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
 #endif
@@ -1413,7 +1422,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 	for (i = 1; i < view->n; ++i) {
 		const struct user_regset *regset = &view->regsets[i];
 		do_thread_regset_writeback(t->task, regset);
-		if (regset->core_note_type &&
+		if (regset->core_note_type && regset->get &&
 		    (!regset->active || regset->active(t->task, regset))) {
 			int ret;
 			size_t size = regset->n * regset->size;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 194cf66..74fc5ed 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1075,6 +1075,7 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 {
 	struct gendisk *disk;
+	struct module *owner;
 	int ret;
 	int partno;
 	int perm = 0;
@@ -1100,6 +1101,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	disk = get_gendisk(bdev->bd_dev, &partno);
 	if (!disk)
 		goto out;
+	owner = disk->fops->owner;
 
 	disk_block_events(disk);
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
@@ -1127,8 +1129,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 					bdev->bd_disk = NULL;
 					mutex_unlock(&bdev->bd_mutex);
 					disk_unblock_events(disk);
-					module_put(disk->fops->owner);
 					put_disk(disk);
+					module_put(owner);
 					goto restart;
 				}
 			}
@@ -1147,8 +1149,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			 * The latter is necessary to prevent ghost
 			 * partitions on a removed medium.
 			 */
-			if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM))
-				rescan_partitions(disk, bdev);
+			if (bdev->bd_invalidated) {
+				if (!ret)
+					rescan_partitions(disk, bdev);
+				else if (ret == -ENOMEDIUM)
+					invalidate_partitions(disk, bdev);
+			}
 			if (ret)
 				goto out_clear;
 		} else {
@@ -1178,14 +1184,18 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
-			if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM))
-				rescan_partitions(bdev->bd_disk, bdev);
+			if (bdev->bd_invalidated) {
+				if (!ret)
+					rescan_partitions(bdev->bd_disk, bdev);
+				else if (ret == -ENOMEDIUM)
+					invalidate_partitions(bdev->bd_disk, bdev);
+			}
 			if (ret)
 				goto out_unlock_bdev;
 		}
 		/* only one opener holds refs to the module and disk */
-		module_put(disk->fops->owner);
 		put_disk(disk);
+		module_put(owner);
 	}
 	bdev->bd_openers++;
 	if (for_part)
@@ -1205,8 +1215,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
  out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
 	disk_unblock_events(disk);
-	module_put(disk->fops->owner);
 	put_disk(disk);
+	module_put(owner);
  out:
 	bdput(bdev);
 
@@ -1432,14 +1442,15 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 	if (!bdev->bd_openers) {
 		struct module *owner = disk->fops->owner;
 
-		put_disk(disk);
-		module_put(owner);
 		disk_put_part(bdev->bd_part);
 		bdev->bd_part = NULL;
 		bdev->bd_disk = NULL;
 		if (bdev != bdev->bd_contains)
 			victim = bdev->bd_contains;
 		bdev->bd_contains = NULL;
+
+		put_disk(disk);
+		module_put(owner);
 	}
 	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 2451627..b775809 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2767,10 +2767,10 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 
 /*
  * When the server doesn't allow large posix writes, only allow a wsize of
- * 128k minus the size of the WRITE_AND_X header. That allows for a write up
+ * 2^17-1 minus the size of the WRITE_AND_X header. That allows for a write up
  * to the maximum size described by RFC1002.
  */
-#define CIFS_MAX_RFC1002_WSIZE (128 * 1024 - sizeof(WRITE_REQ) + 4)
+#define CIFS_MAX_RFC1002_WSIZE ((1<<17) - 1 - sizeof(WRITE_REQ) + 4)
 
 /*
  * The default wsize is 1M. find_get_pages seems to return a maximum of 256
@@ -3004,7 +3004,7 @@ cifs_get_volume_info(char *mount_data, const char *devname)
 int
 cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 {
-	int rc = 0;
+	int rc;
 	int xid;
 	struct cifs_ses *pSesInfo;
 	struct cifs_tcon *tcon;
@@ -3033,6 +3033,7 @@ try_mount_again:
 		FreeXid(xid);
 	}
 #endif
+	rc = 0;
 	tcon = NULL;
 	pSesInfo = NULL;
 	srvTcp = NULL;
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 16cdd6d..ed5c07b 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -583,10 +583,26 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 			 * If either that or op not supported returned, follow
 			 * the normal lookup.
 			 */
-			if ((rc == 0) || (rc == -ENOENT))
+			switch (rc) {
+			case 0:
+				/*
+				 * The server may allow us to open things like
+				 * FIFOs, but the client isn't set up to deal
+				 * with that. If it's not a regular file, just
+				 * close it and proceed as if it were a normal
+				 * lookup.
+				 */
+				if (newInode && !S_ISREG(newInode->i_mode)) {
+					CIFSSMBClose(xid, pTcon, fileHandle);
+					break;
+				}
+			case -ENOENT:
 				posix_open = true;
-			else if ((rc == -EINVAL) || (rc != -EOPNOTSUPP))
+			case -EOPNOTSUPP:
+				break;
+			default:
 				pTcon->broken_posix_open = true;
+			}
 		}
 		if (!posix_open)
 			rc = cifs_get_inode_info_unix(&newInode, full_path,
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a7b2dcd..745e5cd 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -562,7 +562,16 @@ int cifs_get_file_info(struct file *filp)
 
 	xid = GetXid();
 	rc = CIFSSMBQFileInfo(xid, tcon, cfile->netfid, &find_data);
-	if (rc == -EOPNOTSUPP || rc == -EINVAL) {
+	switch (rc) {
+	case 0:
+		cifs_all_info_to_fattr(&fattr, &find_data, cifs_sb, false);
+		break;
+	case -EREMOTE:
+		cifs_create_dfs_fattr(&fattr, inode->i_sb);
+		rc = 0;
+		break;
+	case -EOPNOTSUPP:
+	case -EINVAL:
 		/*
 		 * FIXME: legacy server -- fall back to path-based call?
 		 * for now, just skip revalidating and mark inode for
@@ -570,18 +579,14 @@ int cifs_get_file_info(struct file *filp)
 		 */
 		rc = 0;
 		CIFS_I(inode)->time = 0;
+	default:
 		goto cgfi_exit;
-	} else if (rc == -EREMOTE) {
-		cifs_create_dfs_fattr(&fattr, inode->i_sb);
-		rc = 0;
-	} else if (rc)
-		goto cgfi_exit;
+	}
 
 	/*
 	 * don't bother with SFU junk here -- just mark inode as needing
 	 * revalidation.
 	 */
-	cifs_all_info_to_fattr(&fattr, &find_data, cifs_sb, false);
 	fattr.cf_uniqueid = CIFS_I(inode)->uniqueid;
 	fattr.cf_flags |= CIFS_FATTR_NEED_REVAL;
 	cifs_fattr_to_inode(inode, &fattr);
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index d3e6196..0cfae19 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -244,16 +244,15 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
 	/* copy user */
 	/* BB what about null user mounts - check that we do this BB */
 	/* copy user */
-	if (ses->user_name != NULL)
+	if (ses->user_name != NULL) {
 		strncpy(bcc_ptr, ses->user_name, MAX_USERNAME_SIZE);
+		bcc_ptr += strnlen(ses->user_name, MAX_USERNAME_SIZE);
+	}
 	/* else null user mount */
-
-	bcc_ptr += strnlen(ses->user_name, MAX_USERNAME_SIZE);
 	*bcc_ptr = 0;
 	bcc_ptr++; /* account for null termination */
 
 	/* copy domain */
-
 	if (ses->domainName != NULL) {
 		strncpy(bcc_ptr, ses->domainName, 256);
 		bcc_ptr += strnlen(ses->domainName, 256);
diff --git a/fs/dcache.c b/fs/dcache.c
index fbdcbca..0b51cfc 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -241,6 +241,7 @@ static void dentry_lru_add(struct dentry *dentry)
 static void __dentry_lru_del(struct dentry *dentry)
 {
 	list_del_init(&dentry->d_lru);
+	dentry->d_flags &= ~DCACHE_SHRINK_LIST;
 	dentry->d_sb->s_nr_dentry_unused--;
 	dentry_stat.nr_unused--;
 }
@@ -753,6 +754,7 @@ relock:
 			spin_unlock(&dentry->d_lock);
 		} else {
 			list_move_tail(&dentry->d_lru, &tmp);
+			dentry->d_flags |= DCACHE_SHRINK_LIST;
 			spin_unlock(&dentry->d_lock);
 			if (!--cnt)
 				break;
@@ -1144,14 +1146,18 @@ resume:
 		/* 
 		 * move only zero ref count dentries to the end 
 		 * of the unused list for prune_dcache
+		 *
+		 * Those which are presently on the shrink list, being processed
+		 * by shrink_dentry_list(), shouldn't be moved.  Otherwise the
+		 * loop in shrink_dcache_parent() might not make any progress
+		 * and loop forever.
 		 */
-		if (!dentry->d_count) {
+		if (dentry->d_count) {
+			dentry_lru_del(dentry);
+		} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
 			dentry_lru_move_tail(dentry);
 			found++;
-		} else {
-			dentry_lru_del(dentry);
 		}
-
 		/*
 		 * We can return to the caller if we have found some (this
 		 * ensures forward progress). We'll be coming back to find
@@ -2427,6 +2433,7 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 			if (d_ancestor(alias, dentry)) {
 				/* Check for loops */
 				actual = ERR_PTR(-ELOOP);
+				spin_unlock(&inode->i_lock);
 			} else if (IS_ROOT(alias)) {
 				/* Is this an anonymous mountpoint that we
 				 * could splice into our tree? */
@@ -2436,7 +2443,7 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 				goto found;
 			} else {
 				/* Nope, but we must(!) avoid directory
-				 * aliasing */
+				 * aliasing. This drops inode->i_lock */
 				actual = __d_unalias(inode, dentry, alias);
 			}
 			write_sequnlock(&rename_lock);
@@ -2487,16 +2494,14 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 /**
  * prepend_path - Prepend path string to a buffer
  * @path: the dentry/vfsmount to report
- * @root: root vfsmnt/dentry (may be modified by this function)
+ * @root: root vfsmnt/dentry
  * @buffer: pointer to the end of the buffer
  * @buflen: pointer to buffer length
  *
  * Caller holds the rename_lock.
- *
- * If path is not reachable from the supplied root, then the value of
- * root is changed (without modifying refcounts).
  */
-static int prepend_path(const struct path *path, struct path *root,
+static int prepend_path(const struct path *path,
+			const struct path *root,
 			char **buffer, int *buflen)
 {
 	struct dentry *dentry = path->dentry;
@@ -2531,10 +2536,10 @@ static int prepend_path(const struct path *path, struct path *root,
 		dentry = parent;
 	}
 
-out:
 	if (!error && !slash)
 		error = prepend(buffer, buflen, "/", 1);
 
+out:
 	br_read_unlock(vfsmount_lock);
 	return error;
 
@@ -2548,15 +2553,17 @@ global_root:
 		WARN(1, "Root dentry has weird name <%.*s>\n",
 		     (int) dentry->d_name.len, dentry->d_name.name);
 	}
-	root->mnt = vfsmnt;
-	root->dentry = dentry;
+	if (!slash)
+		error = prepend(buffer, buflen, "/", 1);
+	if (!error)
+		error = vfsmnt->mnt_ns ? 1 : 2;
 	goto out;
 }
 
 /**
  * __d_path - return the path of a dentry
  * @path: the dentry/vfsmount to report
- * @root: root vfsmnt/dentry (may be modified by this function)
+ * @root: root vfsmnt/dentry
  * @buf: buffer to return value in
  * @buflen: buffer length
  *
@@ -2567,10 +2574,10 @@ global_root:
  *
  * "buflen" should be positive.
  *
- * If path is not reachable from the supplied root, then the value of
- * root is changed (without modifying refcounts).
+ * If the path is not reachable from the supplied root, return %NULL.
  */
-char *__d_path(const struct path *path, struct path *root,
+char *__d_path(const struct path *path,
+	       const struct path *root,
 	       char *buf, int buflen)
 {
 	char *res = buf + buflen;
@@ -2581,7 +2588,28 @@ char *__d_path(const struct path *path, struct path *root,
 	error = prepend_path(path, root, &res, &buflen);
 	write_sequnlock(&rename_lock);
 
-	if (error)
+	if (error < 0)
+		return ERR_PTR(error);
+	if (error > 0)
+		return NULL;
+	return res;
+}
+
+char *d_absolute_path(const struct path *path,
+	       char *buf, int buflen)
+{
+	struct path root = {};
+	char *res = buf + buflen;
+	int error;
+
+	prepend(&res, &buflen, "\0", 1);
+	write_seqlock(&rename_lock);
+	error = prepend_path(path, &root, &res, &buflen);
+	write_sequnlock(&rename_lock);
+
+	if (error > 1)
+		error = -EINVAL;
+	if (error < 0)
 		return ERR_PTR(error);
 	return res;
 }
@@ -2589,8 +2617,9 @@ char *__d_path(const struct path *path, struct path *root,
 /*
  * same as __d_path but appends "(deleted)" for unlinked files.
  */
-static int path_with_deleted(const struct path *path, struct path *root,
-				 char **buf, int *buflen)
+static int path_with_deleted(const struct path *path,
+			     const struct path *root,
+			     char **buf, int *buflen)
 {
 	prepend(buf, buflen, "\0", 1);
 	if (d_unlinked(path->dentry)) {
@@ -2627,7 +2656,6 @@ char *d_path(const struct path *path, char *buf, int buflen)
 {
 	char *res = buf + buflen;
 	struct path root;
-	struct path tmp;
 	int error;
 
 	/*
@@ -2642,9 +2670,8 @@ char *d_path(const struct path *path, char *buf, int buflen)
 
 	get_fs_root(current->fs, &root);
 	write_seqlock(&rename_lock);
-	tmp = root;
-	error = path_with_deleted(path, &tmp, &res, &buflen);
-	if (error)
+	error = path_with_deleted(path, &root, &res, &buflen);
+	if (error < 0)
 		res = ERR_PTR(error);
 	write_sequnlock(&rename_lock);
 	path_put(&root);
@@ -2665,7 +2692,6 @@ char *d_path_with_unreachable(const struct path *path, char *buf, int buflen)
 {
 	char *res = buf + buflen;
 	struct path root;
-	struct path tmp;
 	int error;
 
 	if (path->dentry->d_op && path->dentry->d_op->d_dname)
@@ -2673,9 +2699,8 @@ char *d_path_with_unreachable(const struct path *path, char *buf, int buflen)
 
 	get_fs_root(current->fs, &root);
 	write_seqlock(&rename_lock);
-	tmp = root;
-	error = path_with_deleted(path, &tmp, &res, &buflen);
-	if (!error && !path_equal(&tmp, &root))
+	error = path_with_deleted(path, &root, &res, &buflen);
+	if (error > 0)
 		error = prepend_unreachable(&res, &buflen);
 	write_sequnlock(&rename_lock);
 	path_put(&root);
@@ -2806,19 +2831,18 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 	write_seqlock(&rename_lock);
 	if (!d_unlinked(pwd.dentry)) {
 		unsigned long len;
-		struct path tmp = root;
 		char *cwd = page + PAGE_SIZE;
 		int buflen = PAGE_SIZE;
 
 		prepend(&cwd, &buflen, "\0", 1);
-		error = prepend_path(&pwd, &tmp, &cwd, &buflen);
+		error = prepend_path(&pwd, &root, &cwd, &buflen);
 		write_sequnlock(&rename_lock);
 
-		if (error)
+		if (error < 0)
 			goto out;
 
 		/* Unreachable from current root */
-		if (!path_equal(&tmp, &root)) {
+		if (error > 0) {
 			error = prepend_unreachable(&cwd, &buflen);
 			if (error)
 				goto out;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 58609bd..c6602d2 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -417,17 +417,6 @@ static int ecryptfs_encrypt_extent(struct page *enc_extent_page,
 			(unsigned long long)(extent_base + extent_offset), rc);
 		goto out;
 	}
-	if (unlikely(ecryptfs_verbosity > 0)) {
-		ecryptfs_printk(KERN_DEBUG, "Encrypting extent "
-				"with iv:\n");
-		ecryptfs_dump_hex(extent_iv, crypt_stat->iv_bytes);
-		ecryptfs_printk(KERN_DEBUG, "First 8 bytes before "
-				"encryption:\n");
-		ecryptfs_dump_hex((char *)
-				  (page_address(page)
-				   + (extent_offset * crypt_stat->extent_size)),
-				  8);
-	}
 	rc = ecryptfs_encrypt_page_offset(crypt_stat, enc_extent_page, 0,
 					  page, (extent_offset
 						 * crypt_stat->extent_size),
@@ -440,14 +429,6 @@ static int ecryptfs_encrypt_extent(struct page *enc_extent_page,
 		goto out;
 	}
 	rc = 0;
-	if (unlikely(ecryptfs_verbosity > 0)) {
-		ecryptfs_printk(KERN_DEBUG, "Encrypt extent [0x%.16llx]; "
-			"rc = [%d]\n",
-			(unsigned long long)(extent_base + extent_offset), rc);
-		ecryptfs_printk(KERN_DEBUG, "First 8 bytes after "
-				"encryption:\n");
-		ecryptfs_dump_hex((char *)(page_address(enc_extent_page)), 8);
-	}
 out:
 	return rc;
 }
@@ -543,17 +524,6 @@ static int ecryptfs_decrypt_extent(struct page *page,
 			(unsigned long long)(extent_base + extent_offset), rc);
 		goto out;
 	}
-	if (unlikely(ecryptfs_verbosity > 0)) {
-		ecryptfs_printk(KERN_DEBUG, "Decrypting extent "
-				"with iv:\n");
-		ecryptfs_dump_hex(extent_iv, crypt_stat->iv_bytes);
-		ecryptfs_printk(KERN_DEBUG, "First 8 bytes before "
-				"decryption:\n");
-		ecryptfs_dump_hex((char *)
-				  (page_address(enc_extent_page)
-				   + (extent_offset * crypt_stat->extent_size)),
-				  8);
-	}
 	rc = ecryptfs_decrypt_page_offset(crypt_stat, page,
 					  (extent_offset
 					   * crypt_stat->extent_size),
@@ -567,16 +537,6 @@ static int ecryptfs_decrypt_extent(struct page *page,
 		goto out;
 	}
 	rc = 0;
-	if (unlikely(ecryptfs_verbosity > 0)) {
-		ecryptfs_printk(KERN_DEBUG, "Decrypt extent [0x%.16llx]; "
-			"rc = [%d]\n",
-			(unsigned long long)(extent_base + extent_offset), rc);
-		ecryptfs_printk(KERN_DEBUG, "First 8 bytes after "
-				"decryption:\n");
-		ecryptfs_dump_hex((char *)(page_address(page)
-					   + (extent_offset
-					      * crypt_stat->extent_size)), 8);
-	}
 out:
 	return rc;
 }
@@ -1618,7 +1578,8 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
 		rc = ecryptfs_read_xattr_region(page_virt, ecryptfs_inode);
 		if (rc) {
 			printk(KERN_DEBUG "Valid eCryptfs headers not found in "
-			       "file header region or xattr region\n");
+			       "file header region or xattr region, inode %lu\n",
+				ecryptfs_inode->i_ino);
 			rc = -EINVAL;
 			goto out;
 		}
@@ -1627,7 +1588,8 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
 						ECRYPTFS_DONT_VALIDATE_HEADER_SIZE);
 		if (rc) {
 			printk(KERN_DEBUG "Valid eCryptfs headers not found in "
-			       "file xattr region either\n");
+			       "file xattr region either, inode %lu\n",
+				ecryptfs_inode->i_ino);
 			rc = -EINVAL;
 		}
 		if (crypt_stat->mount_crypt_stat->flags
@@ -1638,7 +1600,8 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
 			       "crypto metadata only in the extended attribute "
 			       "region, but eCryptfs was mounted without "
 			       "xattr support enabled. eCryptfs will not treat "
-			       "this like an encrypted file.\n");
+			       "this like an encrypted file, inode %lu\n",
+				ecryptfs_inode->i_ino);
 			rc = -EINVAL;
 		}
 	}
@@ -1943,7 +1906,7 @@ static unsigned char *portable_filename_chars = ("-.0123456789ABCD"
 
 /* We could either offset on every reverse map or just pad some 0x00's
  * at the front here */
-static const unsigned char filename_rev_map[] = {
+static const unsigned char filename_rev_map[256] = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 7 */
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 15 */
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 23 */
@@ -1959,7 +1922,7 @@ static const unsigned char filename_rev_map[] = {
 	0x00, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, 0x2C, /* 103 */
 	0x2D, 0x2E, 0x2F, 0x30, 0x31, 0x32, 0x33, 0x34, /* 111 */
 	0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, /* 119 */
-	0x3D, 0x3E, 0x3F
+	0x3D, 0x3E, 0x3F /* 123 - 255 initialized to 0x00 */
 };
 
 /**
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 4ec9eb0..0c1a652 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -139,6 +139,27 @@ out:
 	return rc;
 }
 
+static void ecryptfs_vma_close(struct vm_area_struct *vma)
+{
+	filemap_write_and_wait(vma->vm_file->f_mapping);
+}
+
+static const struct vm_operations_struct ecryptfs_file_vm_ops = {
+	.close		= ecryptfs_vma_close,
+	.fault		= filemap_fault,
+};
+
+static int ecryptfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int rc;
+
+	rc = generic_file_mmap(file, vma);
+	if (!rc)
+		vma->vm_ops = &ecryptfs_file_vm_ops;
+
+	return rc;
+}
+
 struct kmem_cache *ecryptfs_file_info_cache;
 
 /**
@@ -348,7 +369,7 @@ const struct file_operations ecryptfs_main_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
 #endif
-	.mmap = generic_file_mmap,
+	.mmap = ecryptfs_file_mmap,
 	.open = ecryptfs_open,
 	.flush = ecryptfs_flush,
 	.release = ecryptfs_release,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 4a4fad7..2717329 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -854,18 +854,6 @@ static int truncate_upper(struct dentry *dentry, struct iattr *ia,
 		size_t num_zeros = (PAGE_CACHE_SIZE
 				    - (ia->ia_size & ~PAGE_CACHE_MASK));
 
-
-		/*
-		 * XXX(truncate) this should really happen at the begginning
-		 * of ->setattr.  But the code is too messy to that as part
-		 * of a larger patch.  ecryptfs is also totally missing out
-		 * on the inode_change_ok check at the beginning of
-		 * ->setattr while would include this.
-		 */
-		rc = inode_newsize_ok(inode, ia->ia_size);
-		if (rc)
-			goto out;
-
 		if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
 			truncate_setsize(inode, ia->ia_size);
 			lower_ia->ia_size = ia->ia_size;
@@ -915,6 +903,28 @@ out:
 	return rc;
 }
 
+static int ecryptfs_inode_newsize_ok(struct inode *inode, loff_t offset)
+{
+	struct ecryptfs_crypt_stat *crypt_stat;
+	loff_t lower_oldsize, lower_newsize;
+
+	crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat;
+	lower_oldsize = upper_size_to_lower_size(crypt_stat,
+						 i_size_read(inode));
+	lower_newsize = upper_size_to_lower_size(crypt_stat, offset);
+	if (lower_newsize > lower_oldsize) {
+		/*
+		 * The eCryptfs inode and the new *lower* size are mixed here
+		 * because we may not have the lower i_mutex held and/or it may
+		 * not be appropriate to call inode_newsize_ok() with inodes
+		 * from other filesystems.
+		 */
+		return inode_newsize_ok(inode, lower_newsize);
+	}
+
+	return 0;
+}
+
 /**
  * ecryptfs_truncate
  * @dentry: The ecryptfs layer dentry
@@ -931,6 +941,10 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 	struct iattr lower_ia = { .ia_valid = 0 };
 	int rc;
 
+	rc = ecryptfs_inode_newsize_ok(dentry->d_inode, new_length);
+	if (rc)
+		return rc;
+
 	rc = truncate_upper(dentry, &ia, &lower_ia);
 	if (!rc && lower_ia.ia_valid & ATTR_SIZE) {
 		struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
@@ -1012,6 +1026,16 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 		}
 	}
 	mutex_unlock(&crypt_stat->cs_mutex);
+
+	rc = inode_change_ok(inode, ia);
+	if (rc)
+		goto out;
+	if (ia->ia_valid & ATTR_SIZE) {
+		rc = ecryptfs_inode_newsize_ok(inode, ia->ia_size);
+		if (rc)
+			goto out;
+	}
+
 	if (S_ISREG(inode->i_mode)) {
 		rc = filemap_write_and_wait(inode->i_mapping);
 		if (rc)
@@ -1095,6 +1119,8 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	}
 
 	rc = vfs_setxattr(lower_dentry, name, value, size, flags);
+	if (!rc)
+		fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode);
 out:
 	return rc;
 }
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 940a82e..0dc5a3d 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -409,11 +409,47 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf,
 	ssize_t sz = 0;
 	char *data;
 	uid_t euid = current_euid();
+	unsigned char packet_size_peek[3];
 	int rc;
 
-	if (count == 0)
+	if (count == 0) {
 		goto out;
+	} else if (count == (1 + 4)) {
+		/* Likely a harmless MSG_HELO or MSG_QUIT - no packet length */
+		goto memdup;
+	} else if (count < (1 + 4 + 1)
+		   || count > (1 + 4 + 2 + sizeof(struct ecryptfs_message) + 4
+			       + ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES)) {
+		printk(KERN_WARNING "%s: Acceptable packet size range is "
+		       "[%d-%lu], but amount of data written is [%zu].",
+		       __func__, (1 + 4 + 1),
+		       (1 + 4 + 2 + sizeof(struct ecryptfs_message) + 4
+			+ ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES), count);
+		return -EINVAL;
+	}
+
+	if (copy_from_user(packet_size_peek, (buf + 1 + 4),
+			   sizeof(packet_size_peek))) {
+		printk(KERN_WARNING "%s: Error while inspecting packet size\n",
+		       __func__);
+		return -EFAULT;
+	}
+
+	rc = ecryptfs_parse_packet_length(packet_size_peek, &packet_size,
+					  &packet_size_length);
+	if (rc) {
+		printk(KERN_WARNING "%s: Error parsing packet length; "
+		       "rc = [%d]\n", __func__, rc);
+		return rc;
+	}
+
+	if ((1 + 4 + packet_size_length + packet_size) != count) {
+		printk(KERN_WARNING "%s: Invalid packet size [%zu]\n", __func__,
+		       packet_size);
+		return -EINVAL;
+	}
 
+memdup:
 	data = memdup_user(buf, count);
 	if (IS_ERR(data)) {
 		printk(KERN_ERR "%s: memdup_user returned error [%ld]\n",
@@ -435,23 +471,7 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf,
 		}
 		memcpy(&counter_nbo, &data[i], 4);
 		seq = be32_to_cpu(counter_nbo);
-		i += 4;
-		rc = ecryptfs_parse_packet_length(&data[i], &packet_size,
-						  &packet_size_length);
-		if (rc) {
-			printk(KERN_WARNING "%s: Error parsing packet length; "
-			       "rc = [%d]\n", __func__, rc);
-			goto out_free;
-		}
-		i += packet_size_length;
-		if ((1 + 4 + packet_size_length + packet_size) != count) {
-			printk(KERN_WARNING "%s: (1 + packet_size_length([%zd])"
-			       " + packet_size([%zd]))([%zd]) != "
-			       "count([%zd]). Invalid packet format.\n",
-			       __func__, packet_size_length, packet_size,
-			       (1 + packet_size_length + packet_size), count);
-			goto out_free;
-		}
+		i += 4 + packet_size_length;
 		rc = ecryptfs_miscdev_response(&data[i], packet_size,
 					       euid, current_user_ns(),
 					       task_pid(current), seq);
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index 3745f7c..608c1c3 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -130,13 +130,18 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
 		pgoff_t ecryptfs_page_idx = (pos >> PAGE_CACHE_SHIFT);
 		size_t start_offset_in_page = (pos & ~PAGE_CACHE_MASK);
 		size_t num_bytes = (PAGE_CACHE_SIZE - start_offset_in_page);
-		size_t total_remaining_bytes = ((offset + size) - pos);
+		loff_t total_remaining_bytes = ((offset + size) - pos);
+
+		if (fatal_signal_pending(current)) {
+			rc = -EINTR;
+			break;
+		}
 
 		if (num_bytes > total_remaining_bytes)
 			num_bytes = total_remaining_bytes;
 		if (pos < offset) {
 			/* remaining zeros to write, up to destination offset */
-			size_t total_remaining_zeros = (offset - pos);
+			loff_t total_remaining_zeros = (offset - pos);
 
 			if (num_bytes > total_remaining_zeros)
 				num_bytes = total_remaining_zeros;
@@ -193,15 +198,19 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
 		}
 		pos += num_bytes;
 	}
-	if ((offset + size) > ecryptfs_file_size) {
-		i_size_write(ecryptfs_inode, (offset + size));
+	if (pos > ecryptfs_file_size) {
+		i_size_write(ecryptfs_inode, pos);
 		if (crypt_stat->flags & ECRYPTFS_ENCRYPTED) {
-			rc = ecryptfs_write_inode_size_to_metadata(
+			int rc2;
+
+			rc2 = ecryptfs_write_inode_size_to_metadata(
 								ecryptfs_inode);
-			if (rc) {
+			if (rc2) {
 				printk(KERN_ERR	"Problem with "
 				       "ecryptfs_write_inode_size_to_metadata; "
-				       "rc = [%d]\n", rc);
+				       "rc = [%d]\n", rc2);
+				if (!rc)
+					rc = rc2;
 				goto out;
 			}
 		}
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index f9cfd16..6879d0c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -70,6 +70,15 @@
  * simultaneous inserts (A into B and B into A) from racing and
  * constructing a cycle without either insert observing that it is
  * going to.
+ * It is necessary to acquire multiple "ep->mtx"es at once in the
+ * case when one epoll fd is added to another. In this case, we
+ * always acquire the locks in the order of nesting (i.e. after
+ * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired
+ * before e2->mtx). Since we disallow cycles of epoll file
+ * descriptors, this ensures that the mutexes are well-ordered. In
+ * order to communicate this nesting to lockdep, when walking a tree
+ * of epoll file descriptors, we use the current recursion depth as
+ * the lockdep subkey.
  * It is possible to drop the "ep->mtx" and to use the global
  * mutex "epmutex" (together with "ep->lock") to have it working,
  * but having "ep->mtx" will make the interface more scalable.
@@ -188,6 +197,12 @@ struct eventpoll {
 
 	/* The user that created the eventpoll descriptor */
 	struct user_struct *user;
+
+	struct file *file;
+
+	/* used to optimize loop detection check */
+	int visited;
+	struct list_head visited_list_link;
 };
 
 /* Wait structure used by the poll hooks */
@@ -246,6 +261,15 @@ static struct kmem_cache *epi_cache __read_mostly;
 /* Slab cache used to allocate "struct eppoll_entry" */
 static struct kmem_cache *pwq_cache __read_mostly;
 
+/* Visited nodes during ep_loop_check(), so we can unset them when we finish */
+static LIST_HEAD(visited_list);
+
+/*
+ * List of files with newly added links, where we may need to limit the number
+ * of emanating paths. Protected by the epmutex.
+ */
+static LIST_HEAD(tfile_check_list);
+
 #ifdef CONFIG_SYSCTL
 
 #include <linux/sysctl.h>
@@ -267,6 +291,12 @@ ctl_table epoll_table[] = {
 };
 #endif /* CONFIG_SYSCTL */
 
+static const struct file_operations eventpoll_fops;
+
+static inline int is_file_epoll(struct file *f)
+{
+	return f->f_op == &eventpoll_fops;
+}
 
 /* Setup the structure that is used as key for the RB tree */
 static inline void ep_set_ffd(struct epoll_filefd *ffd,
@@ -290,6 +320,11 @@ static inline int ep_is_linked(struct list_head *p)
 	return !list_empty(p);
 }
 
+static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_t *p)
+{
+	return container_of(p, struct eppoll_entry, wait);
+}
+
 /* Get the "struct epitem" from a wait queue pointer */
 static inline struct epitem *ep_item_from_wait(wait_queue_t *p)
 {
@@ -437,6 +472,18 @@ static void ep_poll_safewake(wait_queue_head_t *wq)
 	put_cpu();
 }
 
+static void ep_remove_wait_queue(struct eppoll_entry *pwq)
+{
+	wait_queue_head_t *whead;
+
+	rcu_read_lock();
+	/* If it is cleared by POLLFREE, it should be rcu-safe */
+	whead = rcu_dereference(pwq->whead);
+	if (whead)
+		remove_wait_queue(whead, &pwq->wait);
+	rcu_read_unlock();
+}
+
 /*
  * This function unregisters poll callbacks from the associated file
  * descriptor.  Must be called with "mtx" held (or "epmutex" if called from
@@ -451,7 +498,7 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
 		pwq = list_first_entry(lsthead, struct eppoll_entry, llink);
 
 		list_del(&pwq->llink);
-		remove_wait_queue(pwq->whead, &pwq->wait);
+		ep_remove_wait_queue(pwq);
 		kmem_cache_free(pwq_cache, pwq);
 	}
 }
@@ -464,13 +511,15 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
  * @ep: Pointer to the epoll private data structure.
  * @sproc: Pointer to the scan callback.
  * @priv: Private opaque data passed to the @sproc callback.
+ * @depth: The current depth of recursive f_op->poll calls.
  *
  * Returns: The same integer error code returned by the @sproc callback.
  */
 static int ep_scan_ready_list(struct eventpoll *ep,
 			      int (*sproc)(struct eventpoll *,
 					   struct list_head *, void *),
-			      void *priv)
+			      void *priv,
+			      int depth)
 {
 	int error, pwake = 0;
 	unsigned long flags;
@@ -481,7 +530,7 @@ static int ep_scan_ready_list(struct eventpoll *ep,
 	 * We need to lock this because we could be hit by
 	 * eventpoll_release_file() and epoll_ctl().
 	 */
-	mutex_lock(&ep->mtx);
+	mutex_lock_nested(&ep->mtx, depth);
 
 	/*
 	 * Steal the ready list, and re-init the original one to the
@@ -670,7 +719,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
 
 static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests)
 {
-	return ep_scan_ready_list(priv, ep_read_events_proc, NULL);
+	return ep_scan_ready_list(priv, ep_read_events_proc, NULL, call_nests + 1);
 }
 
 static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
@@ -700,12 +749,6 @@ static const struct file_operations eventpoll_fops = {
 	.llseek		= noop_llseek,
 };
 
-/* Fast test to see if the file is an evenpoll file */
-static inline int is_file_epoll(struct file *f)
-{
-	return f->f_op == &eventpoll_fops;
-}
-
 /*
  * This is called from eventpoll_release() to unlink files from the eventpoll
  * interface. We need to have this facility to cleanup correctly files that are
@@ -737,7 +780,7 @@ void eventpoll_release_file(struct file *file)
 
 		ep = epi->ep;
 		list_del_init(&epi->fllink);
-		mutex_lock(&ep->mtx);
+		mutex_lock_nested(&ep->mtx, 0);
 		ep_remove(ep, epi);
 		mutex_unlock(&ep->mtx);
 	}
@@ -816,6 +859,17 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	struct epitem *epi = ep_item_from_wait(wait);
 	struct eventpoll *ep = epi->ep;
 
+	if ((unsigned long)key & POLLFREE) {
+		ep_pwq_from_wait(wait)->whead = NULL;
+		/*
+		 * whead = NULL above can race with ep_remove_wait_queue()
+		 * which can do another remove_wait_queue() after us, so we
+		 * can't use __remove_wait_queue(). whead->lock is held by
+		 * the caller.
+		 */
+		list_del_init(&wait->task_list);
+	}
+
 	spin_lock_irqsave(&ep->lock, flags);
 
 	/*
@@ -915,6 +969,99 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
 	rb_insert_color(&epi->rbn, &ep->rbr);
 }
 
+
+
+#define PATH_ARR_SIZE 5
+/*
+ * These are the number paths of length 1 to 5, that we are allowing to emanate
+ * from a single file of interest. For example, we allow 1000 paths of length
+ * 1, to emanate from each file of interest. This essentially represents the
+ * potential wakeup paths, which need to be limited in order to avoid massive
+ * uncontrolled wakeup storms. The common use case should be a single ep which
+ * is connected to n file sources. In this case each file source has 1 path
+ * of length 1. Thus, the numbers below should be more than sufficient. These
+ * path limits are enforced during an EPOLL_CTL_ADD operation, since a modify
+ * and delete can't add additional paths. Protected by the epmutex.
+ */
+static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 };
+static int path_count[PATH_ARR_SIZE];
+
+static int path_count_inc(int nests)
+{
+	if (++path_count[nests] > path_limits[nests])
+		return -1;
+	return 0;
+}
+
+static void path_count_init(void)
+{
+	int i;
+
+	for (i = 0; i < PATH_ARR_SIZE; i++)
+		path_count[i] = 0;
+}
+
+static int reverse_path_check_proc(void *priv, void *cookie, int call_nests)
+{
+	int error = 0;
+	struct file *file = priv;
+	struct file *child_file;
+	struct epitem *epi;
+
+	list_for_each_entry(epi, &file->f_ep_links, fllink) {
+		child_file = epi->ep->file;
+		if (is_file_epoll(child_file)) {
+			if (list_empty(&child_file->f_ep_links)) {
+				if (path_count_inc(call_nests)) {
+					error = -1;
+					break;
+				}
+			} else {
+				error = ep_call_nested(&poll_loop_ncalls,
+							EP_MAX_NESTS,
+							reverse_path_check_proc,
+							child_file, child_file,
+							current);
+			}
+			if (error != 0)
+				break;
+		} else {
+			printk(KERN_ERR "reverse_path_check_proc: "
+				"file is not an ep!\n");
+		}
+	}
+	return error;
+}
+
+/**
+ * reverse_path_check - The tfile_check_list is list of file *, which have
+ *                      links that are proposed to be newly added. We need to
+ *                      make sure that those added links don't add too many
+ *                      paths such that we will spend all our time waking up
+ *                      eventpoll objects.
+ *
+ * Returns: Returns zero if the proposed links don't create too many paths,
+ *	    -1 otherwise.
+ */
+static int reverse_path_check(void)
+{
+	int length = 0;
+	int error = 0;
+	struct file *current_file;
+
+	/* let's call this for all tfiles */
+	list_for_each_entry(current_file, &tfile_check_list, f_tfile_llink) {
+		length++;
+		path_count_init();
+		error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+					reverse_path_check_proc, current_file,
+					current_file, current);
+		if (error)
+			break;
+	}
+	return error;
+}
+
 /*
  * Must be called with "mtx" held.
  */
@@ -976,6 +1123,11 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	 */
 	ep_rbtree_insert(ep, epi);
 
+	/* now check if we've created too many backpaths */
+	error = -EINVAL;
+	if (reverse_path_check())
+		goto error_remove_epi;
+
 	/* We have to drop the new item inside our item list to keep track of it */
 	spin_lock_irqsave(&ep->lock, flags);
 
@@ -1000,6 +1152,14 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 
 	return 0;
 
+error_remove_epi:
+	spin_lock(&tfile->f_lock);
+	if (ep_is_linked(&epi->fllink))
+		list_del_init(&epi->fllink);
+	spin_unlock(&tfile->f_lock);
+
+	rb_erase(&epi->rbn, &ep->rbr);
+
 error_unregister:
 	ep_unregister_pollwait(ep, epi);
 
@@ -1134,7 +1294,7 @@ static int ep_send_events(struct eventpoll *ep,
 	esed.maxevents = maxevents;
 	esed.events = events;
 
-	return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
+	return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0);
 }
 
 static inline struct timespec ep_set_mstimeout(long ms)
@@ -1264,18 +1424,36 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
 	int error = 0;
 	struct file *file = priv;
 	struct eventpoll *ep = file->private_data;
+	struct eventpoll *ep_tovisit;
 	struct rb_node *rbp;
 	struct epitem *epi;
 
-	mutex_lock(&ep->mtx);
+	mutex_lock_nested(&ep->mtx, call_nests + 1);
+	ep->visited = 1;
+	list_add(&ep->visited_list_link, &visited_list);
 	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		if (unlikely(is_file_epoll(epi->ffd.file))) {
+			ep_tovisit = epi->ffd.file->private_data;
+			if (ep_tovisit->visited)
+				continue;
 			error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
-					       ep_loop_check_proc, epi->ffd.file,
-					       epi->ffd.file->private_data, current);
+					ep_loop_check_proc, epi->ffd.file,
+					ep_tovisit, current);
 			if (error != 0)
 				break;
+		} else {
+			/*
+			 * If we've reached a file that is not associated with
+			 * an ep, then we need to check if the newly added
+			 * links are going to add too many wakeup paths. We do
+			 * this by adding it to the tfile_check_list, if it's
+			 * not already there, and calling reverse_path_check()
+			 * during ep_insert().
+			 */
+			if (list_empty(&epi->ffd.file->f_tfile_llink))
+				list_add(&epi->ffd.file->f_tfile_llink,
+					 &tfile_check_list);
 		}
 	}
 	mutex_unlock(&ep->mtx);
@@ -1296,8 +1474,31 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
  */
 static int ep_loop_check(struct eventpoll *ep, struct file *file)
 {
-	return ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+	int ret;
+	struct eventpoll *ep_cur, *ep_next;
+
+	ret = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
 			      ep_loop_check_proc, file, ep, current);
+	/* clear visited list */
+	list_for_each_entry_safe(ep_cur, ep_next, &visited_list,
+							visited_list_link) {
+		ep_cur->visited = 0;
+		list_del(&ep_cur->visited_list_link);
+	}
+	return ret;
+}
+
+static void clear_tfile_check_list(void)
+{
+	struct file *file;
+
+	/* first clear the tfile_check_list */
+	while (!list_empty(&tfile_check_list)) {
+		file = list_first_entry(&tfile_check_list, struct file,
+					f_tfile_llink);
+		list_del_init(&file->f_tfile_llink);
+	}
+	INIT_LIST_HEAD(&tfile_check_list);
 }
 
 /*
@@ -1305,8 +1506,9 @@ static int ep_loop_check(struct eventpoll *ep, struct file *file)
  */
 SYSCALL_DEFINE1(epoll_create1, int, flags)
 {
-	int error;
+	int error, fd;
 	struct eventpoll *ep = NULL;
+	struct file *file;
 
 	/* Check the EPOLL_* constant for consistency.  */
 	BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
@@ -1323,11 +1525,25 @@ SYSCALL_DEFINE1(epoll_create1, int, flags)
 	 * Creates all the items needed to setup an eventpoll file. That is,
 	 * a file structure and a free file descriptor.
 	 */
-	error = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,
+	fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC));
+	if (fd < 0) {
+		error = fd;
+		goto out_free_ep;
+	}
+	file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,
 				 O_RDWR | (flags & O_CLOEXEC));
-	if (error < 0)
-		ep_free(ep);
-
+	if (IS_ERR(file)) {
+		error = PTR_ERR(file);
+		goto out_free_fd;
+	}
+	fd_install(fd, file);
+	ep->file = file;
+	return fd;
+
+out_free_fd:
+	put_unused_fd(fd);
+out_free_ep:
+	ep_free(ep);
 	return error;
 }
 
@@ -1393,23 +1609,29 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	/*
 	 * When we insert an epoll file descriptor, inside another epoll file
 	 * descriptor, there is the change of creating closed loops, which are
-	 * better be handled here, than in more critical paths.
+	 * better be handled here, than in more critical paths. While we are
+	 * checking for loops we also determine the list of files reachable
+	 * and hang them on the tfile_check_list, so we can check that we
+	 * haven't created too many possible wakeup paths.
 	 *
-	 * We hold epmutex across the loop check and the insert in this case, in
-	 * order to prevent two separate inserts from racing and each doing the
-	 * insert "at the same time" such that ep_loop_check passes on both
-	 * before either one does the insert, thereby creating a cycle.
+	 * We need to hold the epmutex across both ep_insert and ep_remove
+	 * b/c we want to make sure we are looking at a coherent view of
+	 * epoll network.
 	 */
-	if (unlikely(is_file_epoll(tfile) && op == EPOLL_CTL_ADD)) {
+	if (op == EPOLL_CTL_ADD || op == EPOLL_CTL_DEL) {
 		mutex_lock(&epmutex);
 		did_lock_epmutex = 1;
-		error = -ELOOP;
-		if (ep_loop_check(ep, tfile) != 0)
-			goto error_tgt_fput;
+	}
+	if (op == EPOLL_CTL_ADD) {
+		if (is_file_epoll(tfile)) {
+			error = -ELOOP;
+			if (ep_loop_check(ep, tfile) != 0)
+				goto error_tgt_fput;
+		} else
+			list_add(&tfile->f_tfile_llink, &tfile_check_list);
 	}
 
-
-	mutex_lock(&ep->mtx);
+	mutex_lock_nested(&ep->mtx, 0);
 
 	/*
 	 * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
@@ -1426,6 +1648,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 			error = ep_insert(ep, &epds, tfile, fd);
 		} else
 			error = -EEXIST;
+		clear_tfile_check_list();
 		break;
 	case EPOLL_CTL_DEL:
 		if (epi)
@@ -1444,7 +1667,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	mutex_unlock(&ep->mtx);
 
 error_tgt_fput:
-	if (unlikely(did_lock_epmutex))
+	if (did_lock_epmutex)
 		mutex_unlock(&epmutex);
 
 	fput(tfile);
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 3451d23..db9ba1a 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1568,7 +1568,13 @@ static int ext3_ordered_writepage(struct page *page,
 	int err;
 
 	J_ASSERT(PageLocked(page));
-	WARN_ON_ONCE(IS_RDONLY(inode));
+	/*
+	 * We don't want to warn for emergency remount. The condition is
+	 * ordered to avoid dereferencing inode->i_sb in non-error case to
+	 * avoid slow-downs.
+	 */
+	WARN_ON_ONCE(IS_RDONLY(inode) &&
+		     !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS));
 
 	/*
 	 * We give up here if we're reentered, because it might be for a
@@ -1642,7 +1648,13 @@ static int ext3_writeback_writepage(struct page *page,
 	int err;
 
 	J_ASSERT(PageLocked(page));
-	WARN_ON_ONCE(IS_RDONLY(inode));
+	/*
+	 * We don't want to warn for emergency remount. The condition is
+	 * ordered to avoid dereferencing inode->i_sb in non-error case to
+	 * avoid slow-downs.
+	 */
+	WARN_ON_ONCE(IS_RDONLY(inode) &&
+		     !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS));
 
 	if (ext3_journal_current_handle())
 		goto out_fail;
@@ -1684,7 +1696,13 @@ static int ext3_journalled_writepage(struct page *page,
 	int err;
 
 	J_ASSERT(PageLocked(page));
-	WARN_ON_ONCE(IS_RDONLY(inode));
+	/*
+	 * We don't want to warn for emergency remount. The condition is
+	 * ordered to avoid dereferencing inode->i_sb in non-error case to
+	 * avoid slow-downs.
+	 */
+	WARN_ON_ONCE(IS_RDONLY(inode) &&
+		     !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS));
 
 	if (ext3_journal_current_handle())
 		goto no_write;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 354619a..1a34c1c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -175,6 +175,7 @@ struct mpage_da_data {
  */
 #define	EXT4_IO_END_UNWRITTEN	0x0001
 #define EXT4_IO_END_ERROR	0x0002
+#define EXT4_IO_END_QUEUED	0x0004
 
 struct ext4_io_page {
 	struct page	*p_page;
@@ -357,8 +358,7 @@ struct flex_groups {
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
-			   EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\
-			   EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
+			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
 			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
 			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
 
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 5802fa1..95af6f8 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -261,43 +261,45 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle,
 /* super.c */
 int ext4_force_commit(struct super_block *sb);
 
-static inline int ext4_should_journal_data(struct inode *inode)
+/*
+ * Ext4 inode journal modes
+ */
+#define EXT4_INODE_JOURNAL_DATA_MODE	0x01 /* journal data mode */
+#define EXT4_INODE_ORDERED_DATA_MODE	0x02 /* ordered data mode */
+#define EXT4_INODE_WRITEBACK_DATA_MODE	0x04 /* writeback data mode */
+
+static inline int ext4_inode_journal_mode(struct inode *inode)
 {
 	if (EXT4_JOURNAL(inode) == NULL)
-		return 0;
-	if (!S_ISREG(inode->i_mode))
-		return 1;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
-		return 1;
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
-		return 1;
-	return 0;
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	/* We do not support data journalling with delayed allocation */
+	if (!S_ISREG(inode->i_mode) ||
+	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !test_opt(inode->i_sb, DELALLOC))
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	else
+		BUG();
+}
+
+static inline int ext4_should_journal_data(struct inode *inode)
+{
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE;
 }
 
 static inline int ext4_should_order_data(struct inode *inode)
 {
-	if (EXT4_JOURNAL(inode) == NULL)
-		return 0;
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
-		return 0;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
-		return 1;
-	return 0;
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
 }
 
 static inline int ext4_should_writeback_data(struct inode *inode)
 {
-	if (EXT4_JOURNAL(inode) == NULL)
-		return 1;
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
-		return 0;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
-		return 1;
-	return 0;
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
 }
 
 /*
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index f3aacb3..7fc10ed 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -341,6 +341,8 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 	ext4_fsblk_t block = ext4_ext_pblock(ext);
 	int len = ext4_ext_get_actual_len(ext);
 
+	if (len == 0)
+		return 0;
 	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c94774c..c1e6a72 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -190,9 +190,6 @@ void ext4_evict_inode(struct inode *inode)
 
 	trace_ext4_evict_inode(inode);
 
-	mutex_lock(&inode->i_mutex);
-	ext4_flush_completed_IO(inode);
-	mutex_unlock(&inode->i_mutex);
 	ext4_ioend_wait(inode);
 
 	if (inode->i_nlink) {
@@ -2129,8 +2126,11 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 					clear_buffer_unwritten(bh);
 				}
 
-				/* skip page if block allocation undone */
-				if (buffer_delay(bh) || buffer_unwritten(bh))
+				/*
+				 * skip page if block allocation undone and
+				 * block is dirty
+				 */
+				if (ext4_bh_delay_or_unwritten(NULL, bh))
 					skip_page = 1;
 				bh = bh->b_this_page;
 				block_start += bh->b_size;
@@ -3212,13 +3212,14 @@ static int ext4_da_write_end(struct file *file,
 	int write_mode = (int)(unsigned long)fsdata;
 
 	if (write_mode == FALL_BACK_TO_NONDELALLOC) {
-		if (ext4_should_order_data(inode)) {
+		switch (ext4_inode_journal_mode(inode)) {
+		case EXT4_INODE_ORDERED_DATA_MODE:
 			return ext4_ordered_write_end(file, mapping, pos,
 					len, copied, page, fsdata);
-		} else if (ext4_should_writeback_data(inode)) {
+		case EXT4_INODE_WRITEBACK_DATA_MODE:
 			return ext4_writeback_write_end(file, mapping, pos,
 					len, copied, page, fsdata);
-		} else {
+		default:
 			BUG();
 		}
 	}
@@ -3234,7 +3235,7 @@ static int ext4_da_write_end(struct file *file,
 	 */
 
 	new_i_size = pos + copied;
-	if (new_i_size > EXT4_I(inode)->i_disksize) {
+	if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
 		if (ext4_da_should_update_i_disksize(page, end)) {
 			down_write(&EXT4_I(inode)->i_data_sem);
 			if (new_i_size > EXT4_I(inode)->i_disksize) {
@@ -3510,12 +3511,17 @@ static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 	}
 
 retry:
-	if (rw == READ && ext4_should_dioread_nolock(inode))
+	if (rw == READ && ext4_should_dioread_nolock(inode)) {
+		if (unlikely(!list_empty(&ei->i_completed_io_list))) {
+			mutex_lock(&inode->i_mutex);
+			ext4_flush_completed_IO(inode);
+			mutex_unlock(&inode->i_mutex);
+		}
 		ret = __blockdev_direct_IO(rw, iocb, inode,
 				 inode->i_sb->s_bdev, iov,
 				 offset, nr_segs,
 				 ext4_get_block, NULL, NULL, 0);
-	else {
+	} else {
 		ret = blockdev_direct_IO(rw, iocb, inode,
 				 inode->i_sb->s_bdev, iov,
 				 offset, nr_segs,
@@ -3913,18 +3919,25 @@ static const struct address_space_operations ext4_da_aops = {
 
 void ext4_set_aops(struct inode *inode)
 {
-	if (ext4_should_order_data(inode) &&
-		test_opt(inode->i_sb, DELALLOC))
-		inode->i_mapping->a_ops = &ext4_da_aops;
-	else if (ext4_should_order_data(inode))
-		inode->i_mapping->a_ops = &ext4_ordered_aops;
-	else if (ext4_should_writeback_data(inode) &&
-		 test_opt(inode->i_sb, DELALLOC))
-		inode->i_mapping->a_ops = &ext4_da_aops;
-	else if (ext4_should_writeback_data(inode))
-		inode->i_mapping->a_ops = &ext4_writeback_aops;
-	else
+	switch (ext4_inode_journal_mode(inode)) {
+	case EXT4_INODE_ORDERED_DATA_MODE:
+		if (test_opt(inode->i_sb, DELALLOC))
+			inode->i_mapping->a_ops = &ext4_da_aops;
+		else
+			inode->i_mapping->a_ops = &ext4_ordered_aops;
+		break;
+	case EXT4_INODE_WRITEBACK_DATA_MODE:
+		if (test_opt(inode->i_sb, DELALLOC))
+			inode->i_mapping->a_ops = &ext4_da_aops;
+		else
+			inode->i_mapping->a_ops = &ext4_writeback_aops;
+		break;
+	case EXT4_INODE_JOURNAL_DATA_MODE:
 		inode->i_mapping->a_ops = &ext4_journalled_aops;
+		break;
+	default:
+		BUG();
+	}
 }
 
 /*
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 458a394..3d36d5a 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1589,7 +1589,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			dxtrace(dx_show_index("node", frames[1].entries));
 			dxtrace(dx_show_index("node",
 			       ((struct dx_node *) bh2->b_data)->entries));
-			err = ext4_handle_dirty_metadata(handle, inode, bh2);
+			err = ext4_handle_dirty_metadata(handle, dir, bh2);
 			if (err)
 				goto journal_error;
 			brelse (bh2);
@@ -1615,7 +1615,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			if (err)
 				goto journal_error;
 		}
-		err = ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
+		err = ext4_handle_dirty_metadata(handle, dir, frames[0].bh);
 		if (err) {
 			ext4_std_error(inode->i_sb, err);
 			goto cleanup;
@@ -1866,7 +1866,7 @@ retry:
 	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
 	inode->i_nlink = 2;
 	BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
-	err = ext4_handle_dirty_metadata(handle, dir, dir_block);
+	err = ext4_handle_dirty_metadata(handle, inode, dir_block);
 	if (err)
 		goto out_clear_inode;
 	err = ext4_mark_inode_dirty(handle, inode);
@@ -2540,7 +2540,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
 						cpu_to_le32(new_dir->i_ino);
 		BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
-		retval = ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
+		retval = ext4_handle_dirty_metadata(handle, old_inode, dir_bh);
 		if (retval) {
 			ext4_std_error(old_dir->i_sb, retval);
 			goto end_rename;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 97e5e98..d99d74a 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -142,7 +142,23 @@ static void ext4_end_io_work(struct work_struct *work)
 	unsigned long		flags;
 	int			ret;
 
-	mutex_lock(&inode->i_mutex);
+	if (!mutex_trylock(&inode->i_mutex)) {
+		/*
+		 * Requeue the work instead of waiting so that the work
+		 * items queued after this can be processed.
+		 */
+		queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
+		/*
+		 * To prevent the ext4-dio-unwritten thread from keeping
+		 * requeueing end_io requests and occupying cpu for too long,
+		 * yield the cpu if it sees an end_io request that has already
+		 * been requeued.
+		 */
+		if (io->flag & EXT4_IO_END_QUEUED)
+			yield();
+		io->flag |= EXT4_IO_END_QUEUED;
+		return;
+	}
 	ret = ext4_end_io_nolock(io);
 	if (ret < 0) {
 		mutex_unlock(&inode->i_mutex);
@@ -389,6 +405,18 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 
 		block_end = block_start + blocksize;
 		if (block_start >= len) {
+			/*
+			 * Comments copied from block_write_full_page_endio:
+			 *
+			 * The page straddles i_size.  It must be zeroed out on
+			 * each and every writepage invocation because it may
+			 * be mmapped.  "A file is mapped in multiples of the
+			 * page size.  For a file that is not a multiple of
+			 * the  page size, the remaining memory is zeroed when
+			 * mapped, and writes to that region are not written
+			 * out to the file."
+			 */
+			zero_user_segment(page, block_start, block_end);
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
 			continue;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 111ed9d..df121b2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1113,9 +1113,9 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",block_validity");
 
 	if (!test_opt(sb, INIT_INODE_TABLE))
-		seq_puts(seq, ",noinit_inode_table");
+		seq_puts(seq, ",noinit_itable");
 	else if (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)
-		seq_printf(seq, ",init_inode_table=%u",
+		seq_printf(seq, ",init_itable=%u",
 			   (unsigned) sbi->s_li_wait_mult);
 
 	ext4_show_quota_options(seq, sb);
@@ -1291,8 +1291,7 @@ enum {
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
 	Opt_dioread_nolock, Opt_dioread_lock,
-	Opt_discard, Opt_nodiscard,
-	Opt_init_inode_table, Opt_noinit_inode_table,
+	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 };
 
 static const match_table_t tokens = {
@@ -1365,9 +1364,9 @@ static const match_table_t tokens = {
 	{Opt_dioread_lock, "dioread_lock"},
 	{Opt_discard, "discard"},
 	{Opt_nodiscard, "nodiscard"},
-	{Opt_init_inode_table, "init_itable=%u"},
-	{Opt_init_inode_table, "init_itable"},
-	{Opt_noinit_inode_table, "noinit_itable"},
+	{Opt_init_itable, "init_itable=%u"},
+	{Opt_init_itable, "init_itable"},
+	{Opt_noinit_itable, "noinit_itable"},
 	{Opt_err, NULL},
 };
 
@@ -1844,7 +1843,7 @@ set_qf_format:
 		case Opt_dioread_lock:
 			clear_opt(sb, DIOREAD_NOLOCK);
 			break;
-		case Opt_init_inode_table:
+		case Opt_init_itable:
 			set_opt(sb, INIT_INODE_TABLE);
 			if (args[0].from) {
 				if (match_int(&args[0], &option))
@@ -1855,7 +1854,7 @@ set_qf_format:
 				return 0;
 			sbi->s_li_wait_mult = option;
 			break;
-		case Opt_noinit_inode_table:
+		case Opt_noinit_itable:
 			clear_opt(sb, INIT_INODE_TABLE);
 			break;
 		default:
@@ -1958,17 +1957,16 @@ static int ext4_fill_flex_info(struct super_block *sb)
 	struct ext4_group_desc *gdp = NULL;
 	ext4_group_t flex_group_count;
 	ext4_group_t flex_group;
-	int groups_per_flex = 0;
+	unsigned int groups_per_flex = 0;
 	size_t size;
 	int i;
 
 	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
-	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
-
-	if (groups_per_flex < 2) {
+	if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) {
 		sbi->s_log_groups_per_flex = 0;
 		return 1;
 	}
+	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
 
 	/* We allocate both existing and potentially added groups */
 	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c757adc..19fe4e3 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -820,8 +820,14 @@ inserted:
 			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
 
+			/*
+			 * take i_data_sem because we will test
+			 * i_delalloc_reserved_flag in ext4_mb_new_blocks
+			 */
+			down_read((&EXT4_I(inode)->i_data_sem));
 			block = ext4_new_meta_blocks(handle, inode, goal, 0,
 						     NULL, &error);
+			up_read((&EXT4_I(inode)->i_data_sem));
 			if (error)
 				goto cleanup;
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index fb6fc95..c858b5c 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1516,7 +1516,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
 	else if (outarg->offset + num > file_size)
 		num = file_size - outarg->offset;
 
-	while (num) {
+	while (num && req->num_pages < FUSE_MAX_PAGES_PER_REQ) {
 		struct page *page;
 		unsigned int this_num;
 
@@ -1530,6 +1530,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
 
 		num -= this_num;
 		total_len += this_num;
+		index++;
 	}
 	req->misc.retrieve_in.offset = outarg->offset;
 	req->misc.retrieve_in.size = total_len;
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 3ebc437..1cbdeea 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -46,11 +46,26 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke
 	case HFS_EXT_CNID:
 		hfs_inode_read_fork(tree->inode, mdb->drXTExtRec, mdb->drXTFlSize,
 				    mdb->drXTFlSize, be32_to_cpu(mdb->drXTClpSiz));
+		if (HFS_I(tree->inode)->alloc_blocks >
+					HFS_I(tree->inode)->first_blocks) {
+			printk(KERN_ERR "hfs: invalid btree extent records\n");
+			unlock_new_inode(tree->inode);
+			goto free_inode;
+		}
+
 		tree->inode->i_mapping->a_ops = &hfs_btree_aops;
 		break;
 	case HFS_CAT_CNID:
 		hfs_inode_read_fork(tree->inode, mdb->drCTExtRec, mdb->drCTFlSize,
 				    mdb->drCTFlSize, be32_to_cpu(mdb->drCTClpSiz));
+
+		if (!HFS_I(tree->inode)->first_blocks) {
+			printk(KERN_ERR "hfs: invalid btree extent records "
+								"(0 size).\n");
+			unlock_new_inode(tree->inode);
+			goto free_inode;
+		}
+
 		tree->inode->i_mapping->a_ops = &hfs_btree_aops;
 		break;
 	default:
@@ -59,11 +74,6 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke
 	}
 	unlock_new_inode(tree->inode);
 
-	if (!HFS_I(tree->inode)->first_blocks) {
-		printk(KERN_ERR "hfs: invalid btree extent records (0 size).\n");
-		goto free_inode;
-	}
-
 	mapping = tree->inode->i_mapping;
 	page = read_mapping_page(mapping, 0, NULL);
 	if (IS_ERR(page))
diff --git a/fs/hfs/trans.c b/fs/hfs/trans.c
index e673a88..b1ce4c7 100644
--- a/fs/hfs/trans.c
+++ b/fs/hfs/trans.c
@@ -40,6 +40,8 @@ int hfs_mac2asc(struct super_block *sb, char *out, const struct hfs_name *in)
 
 	src = in->name;
 	srclen = in->len;
+	if (srclen > HFS_NAMELEN)
+		srclen = HFS_NAMELEN;
 	dst = out;
 	dstlen = HFS_MAX_NAMELEN;
 	if (nls_io) {
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index 85c098a..9d71c95 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -16,6 +16,7 @@
 #include <linux/statfs.h>
 #include <linux/types.h>
 #include <linux/pid_namespace.h>
+#include <linux/namei.h>
 #include <asm/uaccess.h>
 #include "os.h"
 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 7aafeb8..8b0c875 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -238,17 +238,10 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 	loff_t isize;
 	ssize_t retval = 0;
 
-	mutex_lock(&inode->i_mutex);
-
 	/* validate length */
 	if (len == 0)
 		goto out;
 
-	isize = i_size_read(inode);
-	if (!isize)
-		goto out;
-
-	end_index = (isize - 1) >> huge_page_shift(h);
 	for (;;) {
 		struct page *page;
 		unsigned long nr, ret;
@@ -256,18 +249,21 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 
 		/* nr is the maximum number of bytes to copy from this page */
 		nr = huge_page_size(h);
+		isize = i_size_read(inode);
+		if (!isize)
+			goto out;
+		end_index = (isize - 1) >> huge_page_shift(h);
 		if (index >= end_index) {
 			if (index > end_index)
 				goto out;
 			nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
-			if (nr <= offset) {
+			if (nr <= offset)
 				goto out;
-			}
 		}
 		nr = nr - offset;
 
 		/* Find the page */
-		page = find_get_page(mapping, index);
+		page = find_lock_page(mapping, index);
 		if (unlikely(page == NULL)) {
 			/*
 			 * We have a HOLE, zero out the user-buffer for the
@@ -279,17 +275,18 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 			else
 				ra = 0;
 		} else {
+			unlock_page(page);
+
 			/*
 			 * We have the page, copy it to user space buffer.
 			 */
 			ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
 			ret = ra;
+			page_cache_release(page);
 		}
 		if (ra < 0) {
 			if (retval == 0)
 				retval = ra;
-			if (page)
-				page_cache_release(page);
 			goto out;
 		}
 
@@ -299,16 +296,12 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 		index += offset >> huge_page_shift(h);
 		offset &= ~huge_page_mask(h);
 
-		if (page)
-			page_cache_release(page);
-
 		/* short read or no more work */
 		if ((ret != nr) || (len == 0))
 			break;
 	}
 out:
 	*ppos = ((loff_t)index << huge_page_shift(h)) + offset;
-	mutex_unlock(&inode->i_mutex);
 	return retval;
 }
 
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index e2d4285..9f36384 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -1131,6 +1131,14 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}
 
+	if (be32_to_cpu(sb->s_first) == 0 ||
+	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+		printk(KERN_WARNING
+			"JBD: Invalid start block of journal: %u\n",
+			be32_to_cpu(sb->s_first));
+		goto out;
+	}
+
 	return 0;
 
 out:
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0dfa5b5..40c5fb7 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1251,6 +1251,14 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}
 
+	if (be32_to_cpu(sb->s_first) == 0 ||
+	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+		printk(KERN_WARNING
+			"JBD2: Invalid start block of journal: %u\n",
+			be32_to_cpu(sb->s_first));
+		goto out;
+	}
+
 	return 0;
 
 out:
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 2d71094..9baa39e 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1902,6 +1902,8 @@ zap_buffer_unlocked:
 	clear_buffer_mapped(bh);
 	clear_buffer_req(bh);
 	clear_buffer_new(bh);
+	clear_buffer_delay(bh);
+	clear_buffer_unwritten(bh);
 	bh->b_bdev = NULL;
 	return may_free;
 }
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index abfff9d..1743064 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -440,7 +440,7 @@ static int param_set_##name(const char *val, struct kernel_param *kp)	\
 	__typeof__(type) num = which_strtol(val, &endp, 0);		\
 	if (endp == val || *endp || num < (min) || num > (max))		\
 		return -EINVAL;						\
-	*((int *) kp->arg) = num;					\
+	*((type *) kp->arg) = num;					\
 	return 0;							\
 }
 
diff --git a/fs/namei.c b/fs/namei.c
index b456c7a..16bda6c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -136,7 +136,7 @@ static int do_getname(const char __user *filename, char *page)
 	return retval;
 }
 
-static char *getname_flags(const char __user * filename, int flags)
+static char *getname_flags(const char __user *filename, int flags, int *empty)
 {
 	char *tmp, *result;
 
@@ -147,6 +147,8 @@ static char *getname_flags(const char __user * filename, int flags)
 
 		result = tmp;
 		if (retval < 0) {
+			if (retval == -ENOENT && empty)
+				*empty = 1;
 			if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
 				__putname(tmp);
 				result = ERR_PTR(retval);
@@ -159,7 +161,7 @@ static char *getname_flags(const char __user * filename, int flags)
 
 char *getname(const char __user * filename)
 {
-	return getname_flags(filename, 0);
+	return getname_flags(filename, 0, 0);
 }
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -779,17 +781,20 @@ static int follow_automount(struct path *path, unsigned flags,
 	if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_CONTINUE))
 		return -EISDIR; /* we actually want to stop here */
 
-	/* We want to mount if someone is trying to open/create a file of any
-	 * type under the mountpoint, wants to traverse through the mountpoint
-	 * or wants to open the mounted directory.
+	/* We don't want to mount if someone's just doing a stat -
+	 * unless they're stat'ing a directory and appended a '/' to
+	 * the name.
 	 *
-	 * We don't want to mount if someone's just doing a stat and they've
-	 * set AT_SYMLINK_NOFOLLOW - unless they're stat'ing a directory and
-	 * appended a '/' to the name.
+	 * We do, however, want to mount if someone wants to open or
+	 * create a file of any type under the mountpoint, wants to
+	 * traverse through the mountpoint or wants to open the
+	 * mounted directory.  Also, autofs may mark negative dentries
+	 * as being automount points.  These will need the attentions
+	 * of the daemon to instantiate them before they can be used.
 	 */
-	if (!(flags & LOOKUP_FOLLOW) &&
-	    !(flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY |
-		       LOOKUP_OPEN | LOOKUP_CREATE)))
+	if (!(flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY |
+		     LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
+	    path->dentry->d_inode)
 		return -EISDIR;
 
 	current->total_link_count++;
@@ -905,7 +910,7 @@ static int follow_managed(struct path *path, unsigned flags)
 		mntput(path->mnt);
 	if (ret == -EISDIR)
 		ret = 0;
-	return ret;
+	return ret < 0 ? ret : need_mntput;
 }
 
 int follow_down_one(struct path *path)
@@ -953,6 +958,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 			break;
 		path->mnt = mounted;
 		path->dentry = mounted->mnt_root;
+		nd->flags |= LOOKUP_JUMPED;
 		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
 		/*
 		 * Update the inode too. We don't need to re-check the
@@ -1227,6 +1233,8 @@ retry:
 		path_put_conditional(path, nd);
 		return err;
 	}
+	if (err)
+		nd->flags |= LOOKUP_JUMPED;
 	*inode = path->dentry->d_inode;
 	return 0;
 }
@@ -1747,11 +1755,11 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 	return __lookup_hash(&this, base, NULL);
 }
 
-int user_path_at(int dfd, const char __user *name, unsigned flags,
-		 struct path *path)
+int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
+		 struct path *path, int *empty)
 {
 	struct nameidata nd;
-	char *tmp = getname_flags(name, flags);
+	char *tmp = getname_flags(name, flags, empty);
 	int err = PTR_ERR(tmp);
 	if (!IS_ERR(tmp)) {
 
@@ -1765,6 +1773,12 @@ int user_path_at(int dfd, const char __user *name, unsigned flags,
 	return err;
 }
 
+int user_path_at(int dfd, const char __user *name, unsigned flags,
+		 struct path *path)
+{
+	return user_path_at_empty(dfd, name, flags, path, 0);
+}
+
 static int user_path_parent(int dfd, const char __user *path,
 			struct nameidata *nd, char **name)
 {
@@ -2095,7 +2109,7 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 		/* sayonara */
 		error = complete_walk(nd);
 		if (error)
-			return ERR_PTR(-ECHILD);
+			return ERR_PTR(error);
 
 		error = -ENOTDIR;
 		if (nd->flags & LOOKUP_DIRECTORY) {
@@ -2107,6 +2121,10 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	}
 
 	/* create side of things */
+	/*
+	 * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED has been
+	 * cleared when we got to the last component we are about to look up
+	 */
 	error = complete_walk(nd);
 	if (error)
 		return ERR_PTR(error);
@@ -2175,6 +2193,9 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	if (error < 0)
 		goto exit_dput;
 
+	if (error)
+		nd->flags |= LOOKUP_JUMPED;
+
 	error = -ENOENT;
 	if (!path->dentry->d_inode)
 		goto exit_dput;
@@ -2184,6 +2205,10 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 
 	path_to_nameidata(path, nd);
 	nd->inode = path->dentry->d_inode;
+	/* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
+	error = complete_walk(nd);
+	if (error)
+		return ERR_PTR(error);
 	error = -EISDIR;
 	if (S_ISDIR(nd->inode->i_mode))
 		goto exit;
diff --git a/fs/namespace.c b/fs/namespace.c
index fe59bd1..edc1c4a 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1048,15 +1048,12 @@ static int show_mountinfo(struct seq_file *m, void *v)
 	if (err)
 		goto out;
 	seq_putc(m, ' ');
-	seq_path_root(m, &mnt_path, &root, " \t\n\\");
-	if (root.mnt != p->root.mnt || root.dentry != p->root.dentry) {
-		/*
-		 * Mountpoint is outside root, discard that one.  Ugly,
-		 * but less so than trying to do that in iterator in a
-		 * race-free way (due to renames).
-		 */
-		return SEQ_SKIP;
-	}
+
+	/* mountpoints outside of chroot jail will give SEQ_SKIP on this */
+	err = seq_path_root(m, &mnt_path, &root, " \t\n\\");
+	if (err)
+		goto out;
+
 	seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw");
 	show_mnt_opts(m, mnt);
 
@@ -1109,6 +1106,7 @@ static int show_vfsstat(struct seq_file *m, void *v)
 
 	/* device */
 	if (mnt->mnt_sb->s_op->show_devname) {
+		seq_puts(m, "device ");
 		err = mnt->mnt_sb->s_op->show_devname(m, mnt);
 	} else {
 		if (mnt->mnt_devname) {
@@ -1757,7 +1755,7 @@ static int do_loopback(struct path *path, char *old_name,
 		return err;
 	if (!old_name || !*old_name)
 		return -EINVAL;
-	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
+	err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path);
 	if (err)
 		return err;
 
@@ -2724,3 +2722,8 @@ struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
 	return vfs_kern_mount(type, MS_KERNMOUNT, type->name, data);
 }
 EXPORT_SYMBOL_GPL(kern_mount_data);
+
+bool our_mnt(struct vfsmount *mnt)
+{
+	return check_mnt(mnt);
+}
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index aaa09e9..b5c826e 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -324,7 +324,7 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
 	dprintk("%s enter. slotid %d seqid %d\n",
 		__func__, args->csa_slotid, args->csa_sequenceid);
 
-	if (args->csa_slotid > NFS41_BC_MAX_CALLBACKS)
+	if (args->csa_slotid >= NFS41_BC_MAX_CALLBACKS)
 		return htonl(NFS4ERR_BADSLOT);
 
 	slot = tbl->slots + args->csa_slotid;
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 321a66b..ecabbd8 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -466,6 +466,17 @@ static void nfs_delegation_run_state_manager(struct nfs_client *clp)
 		nfs4_schedule_state_manager(clp);
 }
 
+void nfs_remove_bad_delegation(struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+
+	delegation = nfs_detach_delegation(NFS_I(inode), NFS_SERVER(inode));
+	if (delegation) {
+		nfs_inode_find_state_and_recover(inode, &delegation->stateid);
+		nfs_free_delegation(delegation);
+	}
+}
+
 /**
  * nfs_expire_all_delegation_types
  * @clp: client to process
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index d9322e4..691a796 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -45,6 +45,7 @@ void nfs_expire_unreferenced_delegations(struct nfs_client *clp);
 void nfs_handle_cb_pathdown(struct nfs_client *clp);
 int nfs_client_return_marked_delegations(struct nfs_client *clp);
 int nfs_delegations_present(struct nfs_client *clp);
+void nfs_remove_bad_delegation(struct inode *inode);
 
 void nfs_delegation_mark_reclaim(struct nfs_client *clp);
 void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index f91c62d..462a006 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1458,12 +1458,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 				res = NULL;
 				goto out;
 			/* This turned out not to be a regular file */
+			case -EISDIR:
 			case -ENOTDIR:
 				goto no_open;
 			case -ELOOP:
 				if (!(nd->intent.open.flags & O_NOFOLLOW))
 					goto no_open;
-			/* case -EISDIR: */
 			/* case -EINVAL: */
 			default:
 				res = ERR_CAST(inode);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 2f093ed..dd2f130 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -887,3 +887,35 @@ static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
 			file->f_path.dentry->d_name.name, arg);
 	return -EINVAL;
 }
+
+#ifdef CONFIG_NFS_V4
+static int
+nfs4_file_open(struct inode *inode, struct file *filp)
+{
+	/*
+	 * NFSv4 opens are handled in d_lookup and d_revalidate. If we get to
+	 * this point, then something is very wrong
+	 */
+	dprintk("NFS: %s called! inode=%p filp=%p\n", __func__, inode, filp);
+	return -ENOTDIR;
+}
+
+const struct file_operations nfs4_file_operations = {
+	.llseek		= nfs_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= nfs_file_read,
+	.aio_write	= nfs_file_write,
+	.mmap		= nfs_file_mmap,
+	.open		= nfs4_file_open,
+	.flush		= nfs_file_flush,
+	.release	= nfs_file_release,
+	.fsync		= nfs_file_fsync,
+	.lock		= nfs_lock,
+	.flock		= nfs_flock,
+	.splice_read	= nfs_file_splice_read,
+	.splice_write	= nfs_file_splice_write,
+	.check_flags	= nfs_check_flags,
+	.setlease	= nfs_setlease,
+};
+#endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 6f4850d..c48f9f6 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -291,7 +291,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		 */
 		inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
 		if (S_ISREG(inode->i_mode)) {
-			inode->i_fop = &nfs_file_operations;
+			inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
 			inode->i_data.a_ops = &nfs_file_aops;
 			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
 		} else if (S_ISDIR(inode->i_mode)) {
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 38053d8..771741f 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -853,6 +853,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs3_dir_inode_operations,
 	.file_inode_ops	= &nfs3_file_inode_operations,
+	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs3_proc_get_root,
 	.getattr	= nfs3_proc_getattr,
 	.setattr	= nfs3_proc_setattr,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index c4a6983..e1c1365 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -209,6 +209,7 @@ struct nfs4_exception {
 	long timeout;
 	int retry;
 	struct nfs4_state *state;
+	struct inode *inode;
 };
 
 struct nfs4_state_recovery_ops {
@@ -344,6 +345,8 @@ extern void nfs4_put_open_state(struct nfs4_state *);
 extern void nfs4_close_state(struct path *, struct nfs4_state *, fmode_t);
 extern void nfs4_close_sync(struct path *, struct nfs4_state *, fmode_t);
 extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
+extern void nfs_inode_find_state_and_recover(struct inode *inode,
+		const nfs4_stateid *stateid);
 extern void nfs4_schedule_lease_recovery(struct nfs_client *);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 614c4d2..75af812 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -428,6 +428,14 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 
 	dprintk("--> %s\n", __func__);
 
+	/* FIXME: remove this check when layout segment support is added */
+	if (lgr->range.offset != 0 ||
+	    lgr->range.length != NFS4_MAX_UINT64) {
+		dprintk("%s Only whole file layouts supported. Use MDS i/o\n",
+			__func__);
+		goto out;
+	}
+
 	if (fl->pattern_offset > lgr->range.offset) {
 		dprintk("%s pattern_offset %lld too large\n",
 				__func__, fl->pattern_offset);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 92cfd2e..301b0c9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -254,15 +254,28 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_state *state = exception->state;
+	struct inode *inode = exception->inode;
 	int ret = errorcode;
 
 	exception->retry = 0;
 	switch(errorcode) {
 		case 0:
 			return 0;
+		case -NFS4ERR_OPENMODE:
+			if (nfs_have_delegation(inode, FMODE_READ)) {
+				nfs_inode_return_delegation(inode);
+				exception->retry = 1;
+				return 0;
+			}
+			if (state == NULL)
+				break;
+			nfs4_schedule_stateid_recovery(server, state);
+			goto wait_on_recovery;
+		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
-		case -NFS4ERR_OPENMODE:
+			if (state != NULL)
+				nfs_remove_bad_delegation(state->inode);
 			if (state == NULL)
 				break;
 			nfs4_schedule_stateid_recovery(server, state);
@@ -1305,8 +1318,11 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
 				 * The show must go on: exit, but mark the
 				 * stateid as needing recovery.
 				 */
+			case -NFS4ERR_DELEG_REVOKED:
 			case -NFS4ERR_ADMIN_REVOKED:
 			case -NFS4ERR_BAD_STATEID:
+				nfs_inode_find_state_and_recover(state->inode,
+						stateid);
 				nfs4_schedule_stateid_recovery(server, state);
 			case -EKEYEXPIRED:
 				/*
@@ -1862,7 +1878,10 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 			   struct nfs4_state *state)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
-	struct nfs4_exception exception = { };
+	struct nfs4_exception exception = {
+		.state = state,
+		.inode = inode,
+	};
 	int err;
 	do {
 		err = nfs4_handle_exception(server,
@@ -3678,8 +3697,11 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 	if (task->tk_status >= 0)
 		return 0;
 	switch(task->tk_status) {
+		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
+			if (state != NULL)
+				nfs_remove_bad_delegation(state->inode);
 		case -NFS4ERR_OPENMODE:
 			if (state == NULL)
 				break;
@@ -4484,7 +4506,9 @@ out:
 
 static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 {
-	struct nfs4_exception exception = { };
+	struct nfs4_exception exception = {
+		.state = state,
+	};
 	int err;
 
 	do {
@@ -4577,6 +4601,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
 				 * The show must go on: exit, but mark the
 				 * stateid as needing recovery.
 				 */
+			case -NFS4ERR_DELEG_REVOKED:
 			case -NFS4ERR_ADMIN_REVOKED:
 			case -NFS4ERR_BAD_STATEID:
 			case -NFS4ERR_OPENMODE:
@@ -6008,6 +6033,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.dentry_ops	= &nfs4_dentry_operations,
 	.dir_inode_ops	= &nfs4_dir_inode_operations,
 	.file_inode_ops	= &nfs4_file_inode_operations,
+	.file_ops	= &nfs4_file_operations,
 	.getroot	= nfs4_proc_get_root,
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e97dd21..c6e2769 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1069,6 +1069,33 @@ void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4
 	nfs4_schedule_state_manager(clp);
 }
 
+void nfs_inode_find_state_and_recover(struct inode *inode,
+		const nfs4_stateid *stateid)
+{
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct nfs_open_context *ctx;
+	struct nfs4_state *state;
+	bool found = false;
+
+	spin_lock(&inode->i_lock);
+	list_for_each_entry(ctx, &nfsi->open_files, list) {
+		state = ctx->state;
+		if (state == NULL)
+			continue;
+		if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
+			continue;
+		if (memcmp(state->stateid.data, stateid->data, sizeof(state->stateid.data)) != 0)
+			continue;
+		nfs4_state_mark_reclaim_nograce(clp, state);
+		found = true;
+	}
+	spin_unlock(&inode->i_lock);
+	if (found)
+		nfs4_schedule_state_manager(clp);
+}
+
+
 static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_recovery_ops *ops)
 {
 	struct inode *inode = state->inode;
@@ -1519,16 +1546,16 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
 {
 	if (!flags)
 		return;
-	else if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
+	if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
 		nfs41_handle_server_reboot(clp);
-	else if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
+	if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
 			    SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
 			    SEQ4_STATUS_ADMIN_STATE_REVOKED |
 			    SEQ4_STATUS_LEASE_MOVED))
 		nfs41_handle_state_revoked(clp);
-	else if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
+	if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
 		nfs41_handle_recallable_state_revoked(clp);
-	else if (flags & (SEQ4_STATUS_CB_PATH_DOWN |
+	if (flags & (SEQ4_STATUS_CB_PATH_DOWN |
 			    SEQ4_STATUS_BACKCHANNEL_FAULT |
 			    SEQ4_STATUS_CB_PATH_DOWN_SESSION))
 		nfs41_handle_cb_path_down(clp);
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 1d1dc1e..75fe694 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -1006,7 +1006,8 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
 static struct pnfs_layoutdriver_type objlayout_type = {
 	.id = LAYOUT_OSD2_OBJECTS,
 	.name = "LAYOUT_OSD2_OBJECTS",
-	.flags                   = PNFS_LAYOUTRET_ON_SETATTR,
+	.flags                   = PNFS_LAYOUTRET_ON_SETATTR |
+				   PNFS_LAYOUTRET_ON_ERROR,
 
 	.alloc_layout_hdr        = objlayout_alloc_layout_hdr,
 	.free_layout_hdr         = objlayout_free_layout_hdr,
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index 1d06f8e..fefa122 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -294,9 +294,11 @@ objlayout_read_done(struct objlayout_io_state *state, ssize_t status, bool sync)
 	dprintk("%s: Begin status=%zd eof=%d\n", __func__, status, eof);
 	rdata = state->rpcdata;
 	rdata->task.tk_status = status;
-	if (status >= 0) {
+	if (likely(status >= 0)) {
 		rdata->res.count = status;
 		rdata->res.eof = eof;
+	} else {
+		rdata->pnfs_error = status;
 	}
 	objlayout_iodone(state);
 	/* must not use state after this point */
@@ -380,15 +382,17 @@ objlayout_write_done(struct objlayout_io_state *state, ssize_t status,
 	wdata = state->rpcdata;
 	state->status = status;
 	wdata->task.tk_status = status;
-	if (status >= 0) {
+	if (likely(status >= 0)) {
 		wdata->res.count = status;
 		wdata->verf.committed = state->committed;
 		dprintk("%s: Return status %d committed %d\n",
 			__func__, wdata->task.tk_status,
 			wdata->verf.committed);
-	} else
+	} else {
+		wdata->pnfs_error = status;
 		dprintk("%s: Return status %d\n",
 			__func__, wdata->task.tk_status);
+	}
 	objlayout_iodone(state);
 	/* must not use state after this point */
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index a726c0a..9951887 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -980,7 +980,8 @@ pnfs_update_layout(struct inode *ino,
 		arg.offset -= pg_offset;
 		arg.length += pg_offset;
 	}
-	arg.length = PAGE_CACHE_ALIGN(arg.length);
+	if (arg.length != NFS4_MAX_UINT64)
+		arg.length = PAGE_CACHE_ALIGN(arg.length);
 
 	lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
 	if (!lseg && first) {
@@ -1118,6 +1119,14 @@ pnfs_ld_write_done(struct nfs_write_data *data)
 		data->mds_ops->rpc_release(data);
 		return 0;
 	}
+	if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags &
+					PNFS_LAYOUTRET_ON_ERROR) {
+		/* Don't lo_commit on error, Server will needs to
+		 * preform a file recovery.
+		 */
+		clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(data->inode)->flags);
+		pnfs_return_layout(data->inode);
+	}
 
 	dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
 		data->pnfs_error);
@@ -1166,6 +1175,10 @@ pnfs_ld_read_done(struct nfs_read_data *data)
 		return 0;
 	}
 
+	if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags &
+						PNFS_LAYOUTRET_ON_ERROR)
+		pnfs_return_layout(data->inode);
+
 	dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
 		data->pnfs_error);
 	status = nfs_initiate_read(data, NFS_CLIENT(data->inode),
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 9d147d9..bb8b324 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -68,6 +68,7 @@ enum {
 enum layoutdriver_policy_flags {
 	/* Should the pNFS client commit and return the layout upon a setattr */
 	PNFS_LAYOUTRET_ON_SETATTR	= 1 << 0,
+	PNFS_LAYOUTRET_ON_ERROR		= 1 << 1,
 };
 
 struct nfs4_deviceid_node;
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index ac40b85..f48125d 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -710,6 +710,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs_dir_inode_operations,
 	.file_inode_ops	= &nfs_file_inode_operations,
+	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs_proc_get_root,
 	.getattr	= nfs_proc_getattr,
 	.setattr	= nfs_proc_setattr,
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index ce40e5c..7e8b07d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -904,10 +904,24 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(unsigned int ve
 		data->auth_flavor_len	= 1;
 		data->version		= version;
 		data->minorversion	= 0;
+		security_init_mnt_opts(&data->lsm_opts);
 	}
 	return data;
 }
 
+static void nfs_free_parsed_mount_data(struct nfs_parsed_mount_data *data)
+{
+	if (data) {
+		kfree(data->client_address);
+		kfree(data->mount_server.hostname);
+		kfree(data->nfs_server.export_path);
+		kfree(data->nfs_server.hostname);
+		kfree(data->fscache_uniq);
+		security_free_mnt_opts(&data->lsm_opts);
+		kfree(data);
+	}
+}
+
 /*
  * Sanity-check a server address provided by the mount command.
  *
@@ -2218,9 +2232,7 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 	data = nfs_alloc_parsed_mount_data(NFS_DEFAULT_VERSION);
 	mntfh = nfs_alloc_fhandle();
 	if (data == NULL || mntfh == NULL)
-		goto out_free_fh;
-
-	security_init_mnt_opts(&data->lsm_opts);
+		goto out;
 
 	/* Validate the mount data */
 	error = nfs_validate_mount_data(raw_data, data, mntfh, dev_name);
@@ -2232,8 +2244,6 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 #ifdef CONFIG_NFS_V4
 	if (data->version == 4) {
 		mntroot = nfs4_try_mount(flags, dev_name, data);
-		kfree(data->client_address);
-		kfree(data->nfs_server.export_path);
 		goto out;
 	}
 #endif	/* CONFIG_NFS_V4 */
@@ -2284,13 +2294,8 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 	s->s_flags |= MS_ACTIVE;
 
 out:
-	kfree(data->nfs_server.hostname);
-	kfree(data->mount_server.hostname);
-	kfree(data->fscache_uniq);
-	security_free_mnt_opts(&data->lsm_opts);
-out_free_fh:
+	nfs_free_parsed_mount_data(data);
 	nfs_free_fhandle(mntfh);
-	kfree(data);
 	return mntroot;
 
 out_err_nosb:
@@ -2613,9 +2618,7 @@ nfs4_remote_mount(struct file_system_type *fs_type, int flags,
 
 	mntfh = nfs_alloc_fhandle();
 	if (data == NULL || mntfh == NULL)
-		goto out_free_fh;
-
-	security_init_mnt_opts(&data->lsm_opts);
+		goto out;
 
 	/* Get a volume representation */
 	server = nfs4_create_server(data, mntfh);
@@ -2663,13 +2666,10 @@ nfs4_remote_mount(struct file_system_type *fs_type, int flags,
 
 	s->s_flags |= MS_ACTIVE;
 
-	security_free_mnt_opts(&data->lsm_opts);
 	nfs_free_fhandle(mntfh);
 	return mntroot;
 
 out:
-	security_free_mnt_opts(&data->lsm_opts);
-out_free_fh:
 	nfs_free_fhandle(mntfh);
 	return ERR_PTR(error);
 
@@ -2793,7 +2793,7 @@ static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
 		goto out_put_mnt_ns;
 
 	ret = vfs_path_lookup(root_mnt->mnt_root, root_mnt,
-			export_path, LOOKUP_FOLLOW, nd);
+			export_path, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, nd);
 
 	nfs_referral_loop_unprotect();
 	put_mnt_ns(ns_private);
@@ -2855,7 +2855,7 @@ static struct dentry *nfs4_mount(struct file_system_type *fs_type,
 
 	data = nfs_alloc_parsed_mount_data(4);
 	if (data == NULL)
-		goto out_free_data;
+		goto out;
 
 	/* Validate the mount data */
 	error = nfs4_validate_mount_data(raw_data, data, dev_name);
@@ -2869,12 +2869,7 @@ static struct dentry *nfs4_mount(struct file_system_type *fs_type,
 		error = PTR_ERR(res);
 
 out:
-	kfree(data->client_address);
-	kfree(data->nfs_server.export_path);
-	kfree(data->nfs_server.hostname);
-	kfree(data->fscache_uniq);
-out_free_data:
-	kfree(data);
+	nfs_free_parsed_mount_data(data);
 	dprintk("<-- nfs4_mount() = %d%s\n", error,
 			error != 0 ? " [error]" : "");
 	return res;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 7271680..f2f80c0 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -428,7 +428,6 @@ static void
 nfs_mark_request_dirty(struct nfs_page *req)
 {
 	__set_page_dirty_nobuffers(req->wb_page);
-	__mark_inode_dirty(req->wb_page->mapping->host, I_DIRTY_DATASYNC);
 }
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
@@ -762,6 +761,8 @@ int nfs_updatepage(struct file *file, struct page *page,
 	status = nfs_writepage_setup(ctx, page, offset, count);
 	if (status < 0)
 		nfs_set_pageerror(page);
+	else
+		__set_page_dirty_nobuffers(page);
 
 	dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
 			status, (long long)i_size_read(inode));
@@ -1525,6 +1526,10 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr
 	int flags = FLUSH_SYNC;
 	int ret = 0;
 
+	/* no commits means nothing needs to be done */
+	if (!nfsi->ncommit)
+		return ret;
+
 	if (wbc->sync_mode == WB_SYNC_NONE) {
 		/* Don't commit yet if this is a non-blocking flush and there
 		 * are a lot of outstanding writes for this mapping.
@@ -1659,34 +1664,20 @@ out_error:
 int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 		struct page *page)
 {
-	struct nfs_page *req;
-	int ret;
+	/*
+	 * If PagePrivate is set, then the page is currently associated with
+	 * an in-progress read or write request. Don't try to migrate it.
+	 *
+	 * FIXME: we could do this in principle, but we'll need a way to ensure
+	 *        that we can safely release the inode reference while holding
+	 *        the page lock.
+	 */
+	if (PagePrivate(page))
+		return -EBUSY;
 
 	nfs_fscache_release_page(page, GFP_KERNEL);
 
-	req = nfs_find_and_lock_request(page, false);
-	ret = PTR_ERR(req);
-	if (IS_ERR(req))
-		goto out;
-
-	ret = migrate_page(mapping, newpage, page);
-	if (!req)
-		goto out;
-	if (ret)
-		goto out_unlock;
-	page_cache_get(newpage);
-	spin_lock(&mapping->host->i_lock);
-	req->wb_page = newpage;
-	SetPagePrivate(newpage);
-	set_page_private(newpage, (unsigned long)req);
-	ClearPagePrivate(page);
-	set_page_private(page, 0);
-	spin_unlock(&mapping->host->i_lock);
-	page_cache_release(page);
-out_unlock:
-	nfs_clear_page_tag_locked(req);
-out:
-	return ret;
+	return migrate_page(mapping, newpage, page);
 }
 #endif
 
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index b9566e4..4b470f6 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -88,7 +88,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
 	struct svc_expkey key;
 	struct svc_expkey *ek = NULL;
 
-	if (mesg[mlen-1] != '\n')
+	if (mlen < 1 || mesg[mlen-1] != '\n')
 		return -EINVAL;
 	mesg[mlen-1] = 0;
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 3a6dbd7..0b8830c 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -156,6 +156,8 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs
 		!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
 		return nfserr_inval;
 
+	accmode |= NFSD_MAY_READ_IF_EXEC;
+
 	if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
 		accmode |= NFSD_MAY_READ;
 	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
@@ -682,7 +684,7 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	readdir->rd_bmval[1] &= nfsd_suppattrs1(cstate->minorversion);
 	readdir->rd_bmval[2] &= nfsd_suppattrs2(cstate->minorversion);
 
-	if ((cookie > ~(u32)0) || (cookie == 1) || (cookie == 2) ||
+	if ((cookie == 1) || (cookie == 2) ||
 	    (cookie == 0 && memcmp(readdir->rd_verf.data, zeroverf.data, NFS4_VERIFIER_SIZE)))
 		return nfserr_bad_cookie;
 
@@ -921,7 +923,7 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	count = 4 + (verify->ve_attrlen >> 2);
 	buf = kmalloc(count << 2, GFP_KERNEL);
 	if (!buf)
-		return nfserr_resource;
+		return nfserr_jukebox;
 
 	status = nfsd4_encode_fattr(&cstate->current_fh,
 				    cstate->current_fh.fh_export,
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index ffb59ef..be26814 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -88,7 +88,7 @@ nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname)
 	struct xdr_netobj cksum;
 	struct hash_desc desc;
 	struct scatterlist sg;
-	__be32 status = nfserr_resource;
+	__be32 status = nfserr_jukebox;
 
 	dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
 			clname->len, clname->data);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 3b8ad35..ecd8152 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -188,8 +188,15 @@ static void nfs4_file_put_fd(struct nfs4_file *fp, int oflag)
 static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
 {
 	if (atomic_dec_and_test(&fp->fi_access[oflag])) {
-		nfs4_file_put_fd(fp, O_RDWR);
 		nfs4_file_put_fd(fp, oflag);
+		/*
+		 * It's also safe to get rid of the RDWR open *if*
+		 * we no longer have need of the other kind of access
+		 * or if we already have the other kind of open:
+		 */
+		if (fp->fi_fds[1-oflag]
+			|| atomic_read(&fp->fi_access[1 - oflag]) == 0)
+			nfs4_file_put_fd(fp, O_RDWR);
 	}
 }
 
@@ -1903,7 +1910,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * of 5 bullet points, labeled as CASE0 - CASE4 below.
 	 */
 	unconf = find_unconfirmed_client_by_str(dname, strhashval);
-	status = nfserr_resource;
+	status = nfserr_jukebox;
 	if (!conf) {
 		/*
 		 * RFC 3530 14.2.33 CASE 4:
@@ -2440,7 +2447,7 @@ renew:
 	if (open->op_stateowner == NULL) {
 		sop = alloc_init_open_stateowner(strhashval, clp, open);
 		if (sop == NULL)
-			return nfserr_resource;
+			return nfserr_jukebox;
 		open->op_stateowner = sop;
 	}
 	list_del_init(&sop->so_close_lru);
@@ -2576,7 +2583,7 @@ nfs4_new_open(struct svc_rqst *rqstp, struct nfs4_stateid **stpp,
 
 	stp = nfs4_alloc_stateid();
 	if (stp == NULL)
-		return nfserr_resource;
+		return nfserr_jukebox;
 
 	status = nfs4_get_vfs_file(rqstp, fp, cur_fh, open);
 	if (status) {
@@ -2807,7 +2814,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		status = nfserr_bad_stateid;
 		if (open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR)
 			goto out;
-		status = nfserr_resource;
+		status = nfserr_jukebox;
 		fp = alloc_init_file(ino);
 		if (fp == NULL)
 			goto out;
@@ -3381,8 +3388,9 @@ static inline void nfs4_file_downgrade(struct nfs4_stateid *stp, unsigned int to
 	int i;
 
 	for (i = 1; i < 4; i++) {
-		if (test_bit(i, &stp->st_access_bmap) && !(i & to_access)) {
-			nfs4_file_put_access(stp->st_file, i);
+		if (test_bit(i, &stp->st_access_bmap)
+					&& ((i & to_access) != i)) {
+			nfs4_file_put_access(stp->st_file, nfs4_access_to_omode(i));
 			__clear_bit(i, &stp->st_access_bmap);
 		}
 	}
@@ -3413,6 +3421,8 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 	if (!access_valid(od->od_share_access, cstate->minorversion)
 			|| !deny_valid(od->od_share_deny))
 		return nfserr_inval;
+	/* We don't yet support WANT bits: */
+	od->od_share_access &= NFS4_SHARE_ACCESS_MASK;
 
 	nfs4_lock_state();
 	if ((status = nfs4_preprocess_seqid_op(cstate,
@@ -3840,7 +3850,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		/* XXX: Do we need to check for duplicate stateowners on
 		 * the same file, or should they just be allowed (and
 		 * create new stateids)? */
-		status = nfserr_resource;
+		status = nfserr_jukebox;
 		lock_sop = alloc_init_lock_stateowner(strhashval,
 				open_sop->so_client, open_stp, lock);
 		if (lock_sop == NULL)
@@ -3924,9 +3934,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	case (EDEADLK):
 		status = nfserr_deadlock;
 		break;
-	default:        
+	default:
 		dprintk("NFSD: nfsd4_lock: vfs_lock_file() failed! status %d\n",err);
-		status = nfserr_resource;
+		status = nfserrno(err);
 		break;
 	}
 out:
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 9901811..6c74097 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1548,6 +1548,18 @@ static void write_cinfo(__be32 **p, struct nfsd4_change_info *c)
 								\
 	save = resp->p;
 
+static bool seqid_mutating_err(__be32 err)
+{
+	/* rfc 3530 section 8.1.5: */
+	return	err != nfserr_stale_clientid &&
+		err != nfserr_stale_stateid &&
+		err != nfserr_bad_stateid &&
+		err != nfserr_bad_seqid &&
+		err != nfserr_bad_xdr &&
+		err != nfserr_resource &&
+		err != nfserr_nofilehandle;
+}
+
 /*
  * Routine for encoding the result of a "seqid-mutating" NFSv4 operation.  This
  * is where sequence id's are incremented, and the replay cache is filled.
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 6bd2f3c..858c7ba 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -447,12 +447,6 @@ struct nfs4_stateid {
 #define WR_STATE	        0x00000020
 #define CLOSE_STATE             0x00000040
 
-#define seqid_mutating_err(err)                       \
-	(((err) != nfserr_stale_clientid) &&    \
-	((err) != nfserr_bad_seqid) &&          \
-	((err) != nfserr_stale_stateid) &&      \
-	((err) != nfserr_bad_stateid))
-
 struct nfsd4_compound_state;
 
 extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fd0acca..acf88ae 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -2114,7 +2114,8 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 
 	/* Allow read access to binaries even when mode 111 */
 	if (err == -EACCES && S_ISREG(inode->i_mode) &&
-	    acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE))
+	     (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) ||
+	      acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC)))
 		err = inode_permission(inode, MAY_EXEC);
 
 	return err? nfserrno(err) : 0;
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index e0bbac0..a22e40e 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -25,6 +25,7 @@
 #define NFSD_MAY_BYPASS_GSS_ON_ROOT 256
 #define NFSD_MAY_NOT_BREAK_LEASE 512
 #define NFSD_MAY_BYPASS_GSS	1024
+#define NFSD_MAY_READ_IF_EXEC	2048
 
 #define NFSD_MAY_CREATE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE)
 #define NFSD_MAY_REMOVE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 41d6743..3e65427 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -842,6 +842,19 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case FS_IOC32_GETVERSION:
 		cmd = FS_IOC_GETVERSION;
 		break;
+	case NILFS_IOCTL_CHANGE_CPMODE:
+	case NILFS_IOCTL_DELETE_CHECKPOINT:
+	case NILFS_IOCTL_GET_CPINFO:
+	case NILFS_IOCTL_GET_CPSTAT:
+	case NILFS_IOCTL_GET_SUINFO:
+	case NILFS_IOCTL_GET_SUSTAT:
+	case NILFS_IOCTL_GET_VINFO:
+	case NILFS_IOCTL_GET_BDESCS:
+	case NILFS_IOCTL_CLEAN_SEGMENTS:
+	case NILFS_IOCTL_SYNC:
+	case NILFS_IOCTL_RESIZE:
+	case NILFS_IOCTL_SET_ALLOC_RANGE:
+		break;
 	default:
 		return -ENOIOCTLCMD;
 	}
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index d327140..35a8970 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -515,6 +515,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
 		brelse(sbh[1]);
 		sbh[1] = NULL;
 		sbp[1] = NULL;
+		valid[1] = 0;
 		swp = 0;
 	}
 	if (!valid[swp]) {
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 252ab1f..42ed195 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -135,9 +135,6 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark)
 
 	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
 
-	/* 1 from caller and 1 for being on i_list/g_list */
-	BUG_ON(atomic_read(&mark->refcnt) < 2);
-
 	spin_lock(&group->mark_lock);
 
 	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
@@ -182,6 +179,11 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark)
 		iput(inode);
 
 	/*
+	 * We don't necessarily have a ref on mark from caller so the above iput
+	 * may have already destroyed it.  Don't touch from now on.
+	 */
+
+	/*
 	 * it's possible that this group tried to destroy itself, but this
 	 * this mark was simultaneously being freed by inode.  If that's the
 	 * case, we finish freeing the group here.
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index a0a041d..811960a 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -550,17 +550,11 @@ static bool disk_unlock_native_capacity(struct gendisk *disk)
 	}
 }
 
-int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
+static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
 {
-	struct parsed_partitions *state = NULL;
 	struct disk_part_iter piter;
 	struct hd_struct *part;
-	int p, highest, res;
-rescan:
-	if (state && !IS_ERR(state)) {
-		kfree(state);
-		state = NULL;
-	}
+	int res;
 
 	if (bdev->bd_part_count)
 		return -EBUSY;
@@ -573,6 +567,24 @@ rescan:
 		delete_partition(disk, part->partno);
 	disk_part_iter_exit(&piter);
 
+	return 0;
+}
+
+int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
+{
+	struct parsed_partitions *state = NULL;
+	struct hd_struct *part;
+	int p, highest, res;
+rescan:
+	if (state && !IS_ERR(state)) {
+		kfree(state);
+		state = NULL;
+	}
+
+	res = drop_partitions(disk, bdev);
+	if (res)
+		return res;
+
 	if (disk->fops->revalidate_disk)
 		disk->fops->revalidate_disk(disk);
 	check_disk_size_change(disk, bdev);
@@ -676,6 +688,26 @@ rescan:
 	return 0;
 }
 
+int invalidate_partitions(struct gendisk *disk, struct block_device *bdev)
+{
+	int res;
+
+	if (!bdev->bd_invalidated)
+		return 0;
+
+	res = drop_partitions(disk, bdev);
+	if (res)
+		return res;
+
+	set_capacity(disk, 0);
+	check_disk_size_change(disk, bdev);
+	bdev->bd_invalidated = 0;
+	/* tell userspace that the media / partition table may have changed */
+	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
+
+	return 0;
+}
+
 unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1a8d756..6a938aa 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -200,65 +200,7 @@ static int proc_root_link(struct inode *inode, struct path *path)
 	return result;
 }
 
-static struct mm_struct *__check_mem_permission(struct task_struct *task)
-{
-	struct mm_struct *mm;
-
-	mm = get_task_mm(task);
-	if (!mm)
-		return ERR_PTR(-EINVAL);
-
-	/*
-	 * A task can always look at itself, in case it chooses
-	 * to use system calls instead of load instructions.
-	 */
-	if (task == current)
-		return mm;
-
-	/*
-	 * If current is actively ptrace'ing, and would also be
-	 * permitted to freshly attach with ptrace now, permit it.
-	 */
-	if (task_is_stopped_or_traced(task)) {
-		int match;
-		rcu_read_lock();
-		match = (tracehook_tracer_task(task) == current);
-		rcu_read_unlock();
-		if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
-			return mm;
-	}
-
-	/*
-	 * No one else is allowed.
-	 */
-	mmput(mm);
-	return ERR_PTR(-EPERM);
-}
-
-/*
- * If current may access user memory in @task return a reference to the
- * corresponding mm, otherwise ERR_PTR.
- */
-static struct mm_struct *check_mem_permission(struct task_struct *task)
-{
-	struct mm_struct *mm;
-	int err;
-
-	/*
-	 * Avoid racing if task exec's as we might get a new mm but validate
-	 * against old credentials.
-	 */
-	err = mutex_lock_killable(&task->signal->cred_guard_mutex);
-	if (err)
-		return ERR_PTR(err);
-
-	mm = __check_mem_permission(task);
-	mutex_unlock(&task->signal->cred_guard_mutex);
-
-	return mm;
-}
-
-struct mm_struct *mm_for_maps(struct task_struct *task)
+static struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 {
 	struct mm_struct *mm;
 	int err;
@@ -269,7 +211,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task)
 
 	mm = get_task_mm(task);
 	if (mm && mm != current->mm &&
-			!ptrace_may_access(task, PTRACE_MODE_READ) &&
+			!ptrace_may_access(task, mode) &&
 			!capable(CAP_SYS_RESOURCE)) {
 		mmput(mm);
 		mm = ERR_PTR(-EACCES);
@@ -279,6 +221,11 @@ struct mm_struct *mm_for_maps(struct task_struct *task)
 	return mm;
 }
 
+struct mm_struct *mm_for_maps(struct task_struct *task)
+{
+	return mm_access(task, PTRACE_MODE_READ);
+}
+
 static int proc_pid_cmdline(struct task_struct *task, char * buffer)
 {
 	int res = 0;
@@ -823,136 +770,99 @@ static const struct file_operations proc_single_file_operations = {
 
 static int mem_open(struct inode* inode, struct file* file)
 {
-	file->private_data = (void*)((long)current->self_exec_id);
-	/* OK to pass negative loff_t, we can catch out-of-range */
-	file->f_mode |= FMODE_UNSIGNED_OFFSET;
-	return 0;
-}
-
-static ssize_t mem_read(struct file * file, char __user * buf,
-			size_t count, loff_t *ppos)
-{
 	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
-	char *page;
-	unsigned long src = *ppos;
-	int ret = -ESRCH;
 	struct mm_struct *mm;
 
 	if (!task)
-		goto out_no_task;
+		return -ESRCH;
 
-	ret = -ENOMEM;
-	page = (char *)__get_free_page(GFP_TEMPORARY);
-	if (!page)
-		goto out;
+	mm = mm_access(task, PTRACE_MODE_ATTACH);
+	put_task_struct(task);
 
-	mm = check_mem_permission(task);
-	ret = PTR_ERR(mm);
 	if (IS_ERR(mm))
-		goto out_free;
-
-	ret = -EIO;
- 
-	if (file->private_data != (void*)((long)current->self_exec_id))
-		goto out_put;
+		return PTR_ERR(mm);
 
-	ret = 0;
- 
-	while (count > 0) {
-		int this_len, retval;
-
-		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
-		retval = access_remote_vm(mm, src, page, this_len, 0);
-		if (!retval) {
-			if (!ret)
-				ret = -EIO;
-			break;
-		}
-
-		if (copy_to_user(buf, page, retval)) {
-			ret = -EFAULT;
-			break;
-		}
- 
-		ret += retval;
-		src += retval;
-		buf += retval;
-		count -= retval;
+	if (mm) {
+		/* ensure this mm_struct can't be freed */
+		atomic_inc(&mm->mm_count);
+		/* but do not pin its memory */
+		mmput(mm);
 	}
-	*ppos = src;
 
-out_put:
-	mmput(mm);
-out_free:
-	free_page((unsigned long) page);
-out:
-	put_task_struct(task);
-out_no_task:
-	return ret;
-}
+	/* OK to pass negative loff_t, we can catch out-of-range */
+	file->f_mode |= FMODE_UNSIGNED_OFFSET;
+	file->private_data = mm;
 
-#define mem_write NULL
+	return 0;
+}
 
-#ifndef mem_write
-/* This is a security hazard */
-static ssize_t mem_write(struct file * file, const char __user *buf,
-			 size_t count, loff_t *ppos)
+static ssize_t mem_rw(struct file *file, char __user *buf,
+			size_t count, loff_t *ppos, int write)
 {
-	int copied;
+	struct mm_struct *mm = file->private_data;
+	unsigned long addr = *ppos;
+	ssize_t copied;
 	char *page;
-	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
-	unsigned long dst = *ppos;
-	struct mm_struct *mm;
 
-	copied = -ESRCH;
-	if (!task)
-		goto out_no_task;
+	if (!mm)
+		return 0;
 
-	copied = -ENOMEM;
 	page = (char *)__get_free_page(GFP_TEMPORARY);
 	if (!page)
-		goto out_task;
-
-	mm = check_mem_permission(task);
-	copied = PTR_ERR(mm);
-	if (IS_ERR(mm))
-		goto out_free;
-
-	copied = -EIO;
-	if (file->private_data != (void *)((long)current->self_exec_id))
-		goto out_mm;
+		return -ENOMEM;
 
 	copied = 0;
+	if (!atomic_inc_not_zero(&mm->mm_users))
+		goto free;
+
 	while (count > 0) {
-		int this_len, retval;
+		int this_len = min_t(int, count, PAGE_SIZE);
 
-		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
-		if (copy_from_user(page, buf, this_len)) {
+		if (write && copy_from_user(page, buf, this_len)) {
 			copied = -EFAULT;
 			break;
 		}
-		retval = access_remote_vm(mm, dst, page, this_len, 1);
-		if (!retval) {
+
+		this_len = access_remote_vm(mm, addr, page, this_len, write);
+		if (!this_len) {
 			if (!copied)
 				copied = -EIO;
 			break;
 		}
-		copied += retval;
-		buf += retval;
-		dst += retval;
-		count -= retval;			
+
+		if (!write && copy_to_user(buf, page, this_len)) {
+			copied = -EFAULT;
+			break;
+		}
+
+		buf += this_len;
+		addr += this_len;
+		copied += this_len;
+		count -= this_len;
 	}
-	*ppos = dst;
+	*ppos = addr;
 
-out_mm:
 	mmput(mm);
-out_free:
+free:
 	free_page((unsigned long) page);
-out_task:
-	put_task_struct(task);
-out_no_task:
 	return copied;
 }
+
+static ssize_t mem_read(struct file *file, char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	return mem_rw(file, buf, count, ppos, 0);
+}
+
+#define mem_write NULL
+
+#ifndef mem_write
+/* This is a security hazard */
+static ssize_t mem_write(struct file *file, const char __user *buf,
+			 size_t count, loff_t *ppos)
+{
+	return mem_rw(file, (char __user*)buf, count, ppos, 1);
+}
 #endif
 
 loff_t mem_lseek(struct file *file, loff_t offset, int orig)
@@ -971,11 +881,20 @@ loff_t mem_lseek(struct file *file, loff_t offset, int orig)
 	return file->f_pos;
 }
 
+static int mem_release(struct inode *inode, struct file *file)
+{
+	struct mm_struct *mm = file->private_data;
+	if (mm)
+		mmdrop(mm);
+	return 0;
+}
+
 static const struct file_operations proc_mem_operations = {
 	.llseek		= mem_lseek,
 	.read		= mem_read,
 	.write		= mem_write,
 	.open		= mem_open,
+	.release	= mem_release,
 };
 
 static ssize_t environ_read(struct file *file, char __user *buf,
@@ -1965,6 +1884,14 @@ static int proc_fd_info(struct inode *inode, struct path *path, char *info)
 		spin_lock(&files->file_lock);
 		file = fcheck_files(files, fd);
 		if (file) {
+			unsigned int f_flags;
+			struct fdtable *fdt;
+
+			fdt = files_fdtable(files);
+			f_flags = file->f_flags & ~O_CLOEXEC;
+			if (FD_ISSET(fd, fdt->close_on_exec))
+				f_flags |= O_CLOEXEC;
+
 			if (path) {
 				*path = file->f_path;
 				path_get(&file->f_path);
@@ -1974,7 +1901,7 @@ static int proc_fd_info(struct inode *inode, struct path *path, char *info)
 					 "pos:\t%lli\n"
 					 "flags:\t0%o\n",
 					 (long long) file->f_pos,
-					 file->f_flags);
+					 f_flags);
 			spin_unlock(&files->file_lock);
 			put_files_struct(files);
 			return 0;
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index ed257d1..a962827 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -131,12 +131,13 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		K(i.freeswap),
 		K(global_page_state(NR_FILE_DIRTY)),
 		K(global_page_state(NR_WRITEBACK)),
-		K(global_page_state(NR_ANON_PAGES)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		K(global_page_state(NR_ANON_PAGES)
 		  + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
-		  HPAGE_PMD_NR
+		  HPAGE_PMD_NR),
+#else
+		K(global_page_state(NR_ANON_PAGES)),
 #endif
-		  ),
 		K(global_page_state(NR_FILE_MAPPED)),
 		K(global_page_state(NR_SHMEM)),
 		K(global_page_state(NR_SLAB_RECLAIMABLE) +
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index be177f7..d6c078e 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -54,7 +54,7 @@ static struct dentry *proc_ns_instantiate(struct inode *dir,
 	ei->ns_ops    = ns_ops;
 	ei->ns	      = ns;
 
-	dentry->d_op = &pid_dentry_operations;
+	d_set_d_op(dentry, &pid_dentry_operations);
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
 	if (pid_revalidate(dentry, NULL))
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5afaa58..55a1f49 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -407,6 +407,9 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	} else {
 		spin_unlock(&walk->mm->page_table_lock);
 	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	/*
 	 * The mmap_sem held all the way back in m_start() is what
 	 * keeps khugepaged out of here and from collapsing things
@@ -505,6 +508,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	struct page *page;
 
 	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
@@ -516,6 +521,9 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 		if (!page)
 			continue;
 
+		if (PageReserved(page))
+			continue;
+
 		/* Clear accessed and referenced bits. */
 		ptep_test_and_clear_young(vma, addr, pte);
 		ClearPageReferenced(page);
@@ -665,6 +673,8 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	int err = 0;
 
 	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
@@ -956,6 +966,8 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		spin_unlock(&walk->mm->page_table_lock);
 	}
 
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
 		struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
@@ -1039,6 +1051,9 @@ static int show_numa_map(struct seq_file *m, void *v)
 		seq_printf(m, " stack");
 	}
 
+	if (is_vm_hugetlb_page(vma))
+		seq_printf(m, " huge");
+
 	walk_page_range(vma->vm_start, vma->vm_end, &walk);
 
 	if (!md->pages)
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 766b1d4..29166ec 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -11,15 +11,20 @@ static int uptime_proc_show(struct seq_file *m, void *v)
 {
 	struct timespec uptime;
 	struct timespec idle;
+	cputime64_t idletime;
+	u64 nsec;
+	u32 rem;
 	int i;
-	cputime_t idletime = cputime_zero;
 
+	idletime = 0;
 	for_each_possible_cpu(i)
 		idletime = cputime64_add(idletime, kstat_cpu(i).cpustat.idle);
 
 	do_posix_clock_monotonic_gettime(&uptime);
 	monotonic_to_bootbased(&uptime);
-	cputime_to_timespec(idletime, &idle);
+	nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC;
+	idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
+	idle.tv_nsec = rem;
 	seq_printf(m, "%lu.%02lu %lu.%02lu\n",
 			(unsigned long) uptime.tv_sec,
 			(uptime.tv_nsec / (NSEC_PER_SEC / 100)),
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index b34bdb2..10b6be3 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -355,7 +355,7 @@ SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
 	 * resolution (think about autofs) and thus deadlocks could arise.
 	 */
 	if (cmds == Q_QUOTAON) {
-		ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW, &path);
+		ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
 		if (ret)
 			pathp = ERR_PTR(ret);
 		else
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index aa91089..f19dfbf 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -453,16 +453,20 @@ int remove_save_link(struct inode *inode, int truncate)
 static void reiserfs_kill_sb(struct super_block *s)
 {
 	if (REISERFS_SB(s)) {
-		if (REISERFS_SB(s)->xattr_root) {
-			d_invalidate(REISERFS_SB(s)->xattr_root);
-			dput(REISERFS_SB(s)->xattr_root);
-			REISERFS_SB(s)->xattr_root = NULL;
-		}
-		if (REISERFS_SB(s)->priv_root) {
-			d_invalidate(REISERFS_SB(s)->priv_root);
-			dput(REISERFS_SB(s)->priv_root);
-			REISERFS_SB(s)->priv_root = NULL;
-		}
+		/*
+		 * Force any pending inode evictions to occur now. Any
+		 * inodes to be removed that have extended attributes
+		 * associated with them need to clean them up before
+		 * we can release the extended attribute root dentries.
+		 * shrink_dcache_for_umount will BUG if we don't release
+		 * those before it's called so ->put_super is too late.
+		 */
+		shrink_dcache_sb(s);
+
+		dput(REISERFS_SB(s)->xattr_root);
+		REISERFS_SB(s)->xattr_root = NULL;
+		dput(REISERFS_SB(s)->priv_root);
+		REISERFS_SB(s)->priv_root = NULL;
 	}
 
 	kill_block_super(s);
@@ -1164,7 +1168,8 @@ static void handle_quota_files(struct super_block *s, char **qf_names,
 			kfree(REISERFS_SB(s)->s_qf_names[i]);
 		REISERFS_SB(s)->s_qf_names[i] = qf_names[i];
 	}
-	REISERFS_SB(s)->s_jquota_fmt = *qfmt;
+	if (*qfmt)
+		REISERFS_SB(s)->s_jquota_fmt = *qfmt;
 }
 #endif
 
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 05d6b0e..dba43c3 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -449,8 +449,6 @@ EXPORT_SYMBOL(seq_path);
 
 /*
  * Same as seq_path, but relative to supplied root.
- *
- * root may be changed, see __d_path().
  */
 int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
 		  char *esc)
@@ -463,6 +461,8 @@ int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
 		char *p;
 
 		p = __d_path(path, root, buf, size);
+		if (!p)
+			return SEQ_SKIP;
 		res = PTR_ERR(p);
 		if (!IS_ERR(p)) {
 			char *end = mangle_path(buf, p, esc);
@@ -474,7 +474,7 @@ int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
 	}
 	seq_commit(m, res);
 
-	return res < 0 ? res : 0;
+	return res < 0 && res != -ENAMETOOLONG ? res : 0;
 }
 
 /*
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 492465b..7ae2a57 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -30,6 +30,21 @@
 #include <linux/signalfd.h>
 #include <linux/syscalls.h>
 
+void signalfd_cleanup(struct sighand_struct *sighand)
+{
+	wait_queue_head_t *wqh = &sighand->signalfd_wqh;
+	/*
+	 * The lockless check can race with remove_wait_queue() in progress,
+	 * but in this case its caller should run under rcu_read_lock() and
+	 * sighand_cachep is SLAB_DESTROY_BY_RCU, we can safely return.
+	 */
+	if (likely(!waitqueue_active(wqh)))
+		return;
+
+	/* wait_queue_t->func(POLLFREE) should do remove_wait_queue() */
+	wake_up_poll(wqh, POLLHUP | POLLFREE);
+}
+
 struct signalfd_ctx {
 	sigset_t sigmask;
 };
diff --git a/fs/stat.c b/fs/stat.c
index 9610391..02a6061 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -296,15 +296,16 @@ SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
 {
 	struct path path;
 	int error;
+	int empty = 0;
 
 	if (bufsiz <= 0)
 		return -EINVAL;
 
-	error = user_path_at(dfd, pathname, LOOKUP_EMPTY, &path);
+	error = user_path_at_empty(dfd, pathname, LOOKUP_EMPTY, &path, &empty);
 	if (!error) {
 		struct inode *inode = path.dentry->d_inode;
 
-		error = -EINVAL;
+		error = empty ? -ENOENT : -EINVAL;
 		if (inode->i_op->readlink) {
 			error = security_inode_readlink(path.dentry);
 			if (!error) {
diff --git a/fs/statfs.c b/fs/statfs.c
index 8244924..9cf04a1 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -76,7 +76,7 @@ EXPORT_SYMBOL(vfs_statfs);
 int user_statfs(const char __user *pathname, struct kstatfs *st)
 {
 	struct path path;
-	int error = user_path(pathname, &path);
+	int error = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
 	if (!error) {
 		error = vfs_statfs(&path, st);
 		path_put(&path);
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 0a12eb8..a494413 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -136,12 +136,13 @@ static int sysfs_sd_setsecdata(struct sysfs_dirent *sd, void **secdata, u32 *sec
 	void *old_secdata;
 	size_t old_secdata_len;
 
-	iattrs = sd->s_iattr;
-	if (!iattrs)
-		iattrs = sysfs_init_inode_attrs(sd);
-	if (!iattrs)
-		return -ENOMEM;
+	if (!sd->s_iattr) {
+		sd->s_iattr = sysfs_init_inode_attrs(sd);
+		if (!sd->s_iattr)
+			return -ENOMEM;
+	}
 
+	iattrs = sd->s_iattr;
 	old_secdata = iattrs->ia_secdata;
 	old_secdata_len = iattrs->ia_secdata_len;
 
diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h
index a811ac4..fd75b63 100644
--- a/fs/ubifs/debug.h
+++ b/fs/ubifs/debug.h
@@ -121,20 +121,21 @@ const char *dbg_key_str1(const struct ubifs_info *c,
 			 const union ubifs_key *key);
 
 /*
- * DBGKEY macros require @dbg_lock to be held, which it is in the dbg message
- * macros.
+ * TODO: these macros are now broken because there is no locking around them
+ * and we use a global buffer for the key string. This means that in case of
+ * concurrent execution we will end up with incorrect and messy key strings.
  */
 #define DBGKEY(key) dbg_key_str0(c, (key))
 #define DBGKEY1(key) dbg_key_str1(c, (key))
 
-#define ubifs_dbg_msg(type, fmt, ...) do {                        \
-	spin_lock(&dbg_lock);                                     \
-	pr_debug("UBIFS DBG " type ": " fmt "\n", ##__VA_ARGS__); \
-	spin_unlock(&dbg_lock);                                   \
-} while (0)
+#define ubifs_dbg_msg(type, fmt, ...) \
+	pr_debug("UBIFS DBG " type ": " fmt "\n", ##__VA_ARGS__)
 
 /* Just a debugging messages not related to any specific UBIFS subsystem */
-#define dbg_msg(fmt, ...)   ubifs_dbg_msg("msg", fmt, ##__VA_ARGS__)
+#define dbg_msg(fmt, ...)                                                     \
+	printk(KERN_DEBUG "UBIFS DBG (pid %d): %s: " fmt "\n", current->pid,  \
+	       __func__, ##__VA_ARGS__)
+
 /* General messages */
 #define dbg_gen(fmt, ...)   ubifs_dbg_msg("gen", fmt, ##__VA_ARGS__)
 /* Additional journal messages */
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 2a346bb..3438b00 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -125,7 +125,6 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 			err = udf_expand_file_adinicb(inode);
 			if (err) {
 				udf_debug("udf_expand_adinicb: err=%d\n", err);
-				up_write(&iinfo->i_data_sem);
 				return err;
 			}
 		} else {
@@ -133,9 +132,10 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 				iinfo->i_lenAlloc = pos + count;
 			else
 				iinfo->i_lenAlloc = inode->i_size;
+			up_write(&iinfo->i_data_sem);
 		}
-	}
-	up_write(&iinfo->i_data_sem);
+	} else
+		up_write(&iinfo->i_data_sem);
 
 	retval = generic_file_aio_write(iocb, iov, nr_segs, ppos);
 	if (retval > 0)
@@ -201,12 +201,10 @@ out:
 static int udf_release_file(struct inode *inode, struct file *filp)
 {
 	if (filp->f_mode & FMODE_WRITE) {
-		mutex_lock(&inode->i_mutex);
 		down_write(&UDF_I(inode)->i_data_sem);
 		udf_discard_prealloc(inode);
 		udf_truncate_tail_extent(inode);
 		up_write(&UDF_I(inode)->i_data_sem);
-		mutex_unlock(&inode->i_mutex);
 	}
 	return 0;
 }
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 1d1358e..262050f 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -145,6 +145,12 @@ const struct address_space_operations udf_aops = {
 	.bmap		= udf_bmap,
 };
 
+/*
+ * Expand file stored in ICB to a normal one-block-file
+ *
+ * This function requires i_data_sem for writing and releases it.
+ * This function requires i_mutex held
+ */
 int udf_expand_file_adinicb(struct inode *inode)
 {
 	struct page *page;
@@ -163,9 +169,15 @@ int udf_expand_file_adinicb(struct inode *inode)
 			iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG;
 		/* from now on we have normal address_space methods */
 		inode->i_data.a_ops = &udf_aops;
+		up_write(&iinfo->i_data_sem);
 		mark_inode_dirty(inode);
 		return 0;
 	}
+	/*
+	 * Release i_data_sem so that we can lock a page - page lock ranks
+	 * above i_data_sem. i_mutex still protects us against file changes.
+	 */
+	up_write(&iinfo->i_data_sem);
 
 	page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS);
 	if (!page)
@@ -181,6 +193,7 @@ int udf_expand_file_adinicb(struct inode *inode)
 		SetPageUptodate(page);
 		kunmap(page);
 	}
+	down_write(&iinfo->i_data_sem);
 	memset(iinfo->i_ext.i_data + iinfo->i_lenEAttr, 0x00,
 	       iinfo->i_lenAlloc);
 	iinfo->i_lenAlloc = 0;
@@ -190,17 +203,20 @@ int udf_expand_file_adinicb(struct inode *inode)
 		iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG;
 	/* from now on we have normal address_space methods */
 	inode->i_data.a_ops = &udf_aops;
+	up_write(&iinfo->i_data_sem);
 	err = inode->i_data.a_ops->writepage(page, &udf_wbc);
 	if (err) {
 		/* Restore everything back so that we don't lose data... */
 		lock_page(page);
 		kaddr = kmap(page);
+		down_write(&iinfo->i_data_sem);
 		memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr,
 		       inode->i_size);
 		kunmap(page);
 		unlock_page(page);
 		iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB;
 		inode->i_data.a_ops = &udf_adinicb_aops;
+		up_write(&iinfo->i_data_sem);
 	}
 	page_cache_release(page);
 	mark_inode_dirty(inode);
@@ -1105,10 +1121,9 @@ int udf_setsize(struct inode *inode, loff_t newsize)
 			if (bsize <
 			    (udf_file_entry_alloc_offset(inode) + newsize)) {
 				err = udf_expand_file_adinicb(inode);
-				if (err) {
-					up_write(&iinfo->i_data_sem);
+				if (err)
 					return err;
-				}
+				down_write(&iinfo->i_data_sem);
 			} else
 				iinfo->i_lenAlloc = newsize;
 		}
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 7b27b06..7f0e18a 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -1830,6 +1830,12 @@ static void udf_close_lvid(struct super_block *sb)
 				le16_to_cpu(lvid->descTag.descCRCLength)));
 
 	lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag);
+	/*
+	 * We set buffer uptodate unconditionally here to avoid spurious
+	 * warnings from mark_buffer_dirty() when previous EIO has marked
+	 * the buffer as !uptodate
+	 */
+	set_buffer_uptodate(bh);
 	mark_buffer_dirty(bh);
 	sbi->s_lvid_dirty = 0;
 	mutex_unlock(&sbi->s_alloc_mutex);
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c
index 39f4f80..f86e034 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/linux-2.6/xfs_acl.c
@@ -39,9 +39,11 @@ xfs_acl_from_disk(struct xfs_acl *aclp)
 	struct posix_acl_entry *acl_e;
 	struct posix_acl *acl;
 	struct xfs_acl_entry *ace;
-	int count, i;
+	unsigned int count, i;
 
 	count = be32_to_cpu(aclp->acl_cnt);
+	if (count > XFS_ACL_MAX_ENTRIES)
+		return ERR_PTR(-EFSCORRUPTED);
 
 	acl = posix_acl_alloc(count, GFP_KERNEL);
 	if (!acl)
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 50a7d5f..36d6ee4 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -346,7 +346,6 @@ extern struct list_head *xfs_get_buftarg_list(void);
 #define xfs_getsize_buftarg(buftarg)	block_size((buftarg)->bt_bdev)
 #define xfs_readonly_buftarg(buftarg)	bdev_read_only((buftarg)->bt_bdev)
 
-#define xfs_binval(buftarg)		xfs_flush_buftarg(buftarg, 1)
 #define XFS_bflush(buftarg)		xfs_flush_buftarg(buftarg, 1)
 
 #endif	/* __XFS_BUF_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_discard.c b/fs/xfs/linux-2.6/xfs_discard.c
index 244e797..572494f 100644
--- a/fs/xfs/linux-2.6/xfs_discard.c
+++ b/fs/xfs/linux-2.6/xfs_discard.c
@@ -68,7 +68,7 @@ xfs_trim_extents(
 	 * Look up the longest btree in the AGF and start with it.
 	 */
 	error = xfs_alloc_lookup_le(cur, 0,
-				    XFS_BUF_TO_AGF(agbp)->agf_longest, &i);
+			    be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest), &i);
 	if (error)
 		goto out_del_cursor;
 
@@ -84,7 +84,7 @@ xfs_trim_extents(
 		if (error)
 			goto out_del_cursor;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, out_del_cursor);
-		ASSERT(flen <= XFS_BUF_TO_AGF(agbp)->agf_longest);
+		ASSERT(flen <= be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest));
 
 		/*
 		 * Too small?  Give up.
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index f4f878f..fed3f3c 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -98,22 +98,22 @@ xfs_fs_encode_fh(
 	switch (fileid_type) {
 	case FILEID_INO32_GEN_PARENT:
 		spin_lock(&dentry->d_lock);
-		fid->i32.parent_ino = dentry->d_parent->d_inode->i_ino;
+		fid->i32.parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino;
 		fid->i32.parent_gen = dentry->d_parent->d_inode->i_generation;
 		spin_unlock(&dentry->d_lock);
 		/*FALLTHRU*/
 	case FILEID_INO32_GEN:
-		fid->i32.ino = inode->i_ino;
+		fid->i32.ino = XFS_I(inode)->i_ino;
 		fid->i32.gen = inode->i_generation;
 		break;
 	case FILEID_INO32_GEN_PARENT | XFS_FILEID_TYPE_64FLAG:
 		spin_lock(&dentry->d_lock);
-		fid64->parent_ino = dentry->d_parent->d_inode->i_ino;
+		fid64->parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino;
 		fid64->parent_gen = dentry->d_parent->d_inode->i_generation;
 		spin_unlock(&dentry->d_lock);
 		/*FALLTHRU*/
 	case FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG:
-		fid64->ino = inode->i_ino;
+		fid64->ino = XFS_I(inode)->i_ino;
 		fid64->gen = inode->i_generation;
 		break;
 	}
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 7f782af..b679198 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -309,7 +309,19 @@ xfs_file_aio_read(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if (unlikely(ioflags & IO_ISDIRECT)) {
+	/*
+	 * Locking is a bit tricky here. If we take an exclusive lock
+	 * for direct IO, we effectively serialise all new concurrent
+	 * read IO to this file and block it behind IO that is currently in
+	 * progress because IO in progress holds the IO lock shared. We only
+	 * need to hold the lock exclusive to blow away the page cache, so
+	 * only take lock exclusively if the page cache needs invalidation.
+	 * This allows the normal direct IO case of no page cache pages to
+	 * proceeed concurrently without serialisation.
+	 */
+	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
+	if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
+		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
 
 		if (inode->i_mapping->nrpages) {
@@ -322,8 +334,7 @@ xfs_file_aio_read(
 			}
 		}
 		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
-	} else
-		xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
+	}
 
 	trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
 
@@ -658,6 +669,7 @@ xfs_file_aio_write_checks(
 	xfs_fsize_t		new_size;
 	int			error = 0;
 
+	xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
 	error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
 	if (error) {
 		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
@@ -749,14 +761,24 @@ xfs_file_dio_aio_write(
 		*iolock = XFS_IOLOCK_EXCL;
 	else
 		*iolock = XFS_IOLOCK_SHARED;
-	xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
+	xfs_rw_ilock(ip, *iolock);
 
 	ret = xfs_file_aio_write_checks(file, &pos, &count, iolock);
 	if (ret)
 		return ret;
 
+	/*
+	 * Recheck if there are cached pages that need invalidate after we got
+	 * the iolock to protect against other threads adding new pages while
+	 * we were waiting for the iolock.
+	 */
+	if (mapping->nrpages && *iolock == XFS_IOLOCK_SHARED) {
+		xfs_rw_iunlock(ip, *iolock);
+		*iolock = XFS_IOLOCK_EXCL;
+		xfs_rw_ilock(ip, *iolock);
+	}
+
 	if (mapping->nrpages) {
-		WARN_ON(*iolock != XFS_IOLOCK_EXCL);
 		ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
 							FI_REMAPF_LOCKED);
 		if (ret)
@@ -801,7 +823,7 @@ xfs_file_buffered_aio_write(
 	size_t			count = ocount;
 
 	*iolock = XFS_IOLOCK_EXCL;
-	xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
+	xfs_rw_ilock(ip, *iolock);
 
 	ret = xfs_file_aio_write_checks(file, &pos, &count, iolock);
 	if (ret)
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index d44d92c..f5b697b 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -69,9 +69,8 @@ xfs_synchronize_times(
 }
 
 /*
- * If the linux inode is valid, mark it dirty.
- * Used when committing a dirty inode into a transaction so that
- * the inode will get written back by the linux code
+ * If the linux inode is valid, mark it dirty, else mark the dirty state
+ * in the XFS inode to make sure we pick it up when reclaiming the inode.
  */
 void
 xfs_mark_inode_dirty_sync(
@@ -81,6 +80,10 @@ xfs_mark_inode_dirty_sync(
 
 	if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
 		mark_inode_dirty_sync(inode);
+	else {
+		barrier();
+		ip->i_update_core = 1;
+	}
 }
 
 void
@@ -91,6 +94,11 @@ xfs_mark_inode_dirty(
 
 	if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
 		mark_inode_dirty(inode);
+	else {
+		barrier();
+		ip->i_update_core = 1;
+	}
+
 }
 
 /*
@@ -456,7 +464,7 @@ xfs_vn_getattr(
 	trace_xfs_getattr(ip);
 
 	if (XFS_FORCED_SHUTDOWN(mp))
-		return XFS_ERROR(EIO);
+		return -XFS_ERROR(EIO);
 
 	stat->size = XFS_ISIZE(ip);
 	stat->dev = inode->i_sb->s_dev;
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 347cae9..e6ac98c 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -871,43 +871,6 @@ xfs_fs_dirty_inode(
 }
 
 STATIC int
-xfs_log_inode(
-	struct xfs_inode	*ip)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_trans	*tp;
-	int			error;
-
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
-	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
-
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		/* we need to return with the lock hold shared */
-		xfs_ilock(ip, XFS_ILOCK_SHARED);
-		return error;
-	}
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-	/*
-	 * Note - it's possible that we might have pushed ourselves out of the
-	 * way during trans_reserve which would flush the inode.  But there's
-	 * no guarantee that the inode buffer has actually gone out yet (it's
-	 * delwri).  Plus the buffer could be pinned anyway if it's part of
-	 * an inode in another recent transaction.  So we play it safe and
-	 * fire off the transaction anyway.
-	 */
-	xfs_trans_ijoin(tp, ip);
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-	error = xfs_trans_commit(tp, 0);
-	xfs_ilock_demote(ip, XFS_ILOCK_EXCL);
-
-	return error;
-}
-
-STATIC int
 xfs_fs_write_inode(
 	struct inode		*inode,
 	struct writeback_control *wbc)
@@ -919,9 +882,9 @@ xfs_fs_write_inode(
 	trace_xfs_write_inode(ip);
 
 	if (XFS_FORCED_SHUTDOWN(mp))
-		return XFS_ERROR(EIO);
+		return -XFS_ERROR(EIO);
 
-	if (wbc->sync_mode == WB_SYNC_ALL) {
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->for_kupdate) {
 		/*
 		 * Make sure the inode has made it it into the log.  Instead
 		 * of forcing it all the way to stable storage using a
@@ -930,13 +893,14 @@ xfs_fs_write_inode(
 		 * of synchronous log foces dramatically.
 		 */
 		xfs_ioend_wait(ip);
-		xfs_ilock(ip, XFS_ILOCK_SHARED);
-		if (ip->i_update_core) {
-			error = xfs_log_inode(ip);
-			if (error)
-				goto out_unlock;
-		}
+		error = xfs_log_dirty_inode(ip, NULL, 0);
+		if (error)
+			goto out;
+		return 0;
 	} else {
+		if (!ip->i_update_core)
+			return 0;
+
 		/*
 		 * We make this non-blocking if the inode is contended, return
 		 * EAGAIN to indicate to the caller that they did not succeed.
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 8ecad5f..2f277a0 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -336,6 +336,32 @@ xfs_sync_fsdata(
 	return xfs_bwrite(mp, bp);
 }
 
+int
+xfs_log_dirty_inode(
+	struct xfs_inode	*ip,
+	struct xfs_perag	*pag,
+	int			flags)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			error;
+
+	if (!ip->i_update_core)
+		return 0;
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		return error;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin_ref(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return xfs_trans_commit(tp, 0);
+}
+
 /*
  * When remounting a filesystem read-only or freezing the filesystem, we have
  * two phases to execute. This first phase is syncing the data before we
@@ -365,6 +391,17 @@ xfs_quiesce_data(
 
 	/* push and block till complete */
 	xfs_sync_data(mp, SYNC_WAIT);
+
+	/*
+	 * Log all pending size and timestamp updates.  The vfs writeback
+	 * code is supposed to do this, but due to its overagressive
+	 * livelock detection it will skip inodes where appending writes
+	 * were written out in the first non-blocking sync phase if their
+	 * completion took long enough that it happened after taking the
+	 * timestamp for the cut-off in the blocking phase.
+	 */
+	xfs_inode_ag_iterator(mp, xfs_log_dirty_inode, 0);
+
 	xfs_qm_sync(mp, SYNC_WAIT);
 
 	/* write superblock and hoover up shutdown errors */
@@ -772,6 +809,17 @@ restart:
 	if (!xfs_iflock_nowait(ip)) {
 		if (!(sync_mode & SYNC_WAIT))
 			goto out;
+
+		/*
+		 * If we only have a single dirty inode in a cluster there is
+		 * a fair chance that the AIL push may have pushed it into
+		 * the buffer, but xfsbufd won't touch it until 30 seconds
+		 * from now, and thus we will lock up here.
+		 *
+		 * Promote the inode buffer to the front of the delwri list
+		 * and wake up xfsbufd now.
+		 */
+		xfs_promote_inode(ip);
 		xfs_iflock(ip);
 	}
 
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index e3a6ad2..ef5b2ce 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -42,6 +42,8 @@ void xfs_quiesce_attr(struct xfs_mount *mp);
 
 void xfs_flush_inodes(struct xfs_inode *ip);
 
+int xfs_log_dirty_inode(struct xfs_inode *ip, struct xfs_perag *pag, int flags);
+
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index b94dace..e70c7fc 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -714,7 +714,8 @@ xfs_qm_dqattach_one(
 	 * disk and we didn't ask it to allocate;
 	 * ESRCH if quotas got turned off suddenly.
 	 */
-	error = xfs_qm_dqget(ip->i_mount, ip, id, type, XFS_QMOPT_DOWARN, &dqp);
+	error = xfs_qm_dqget(ip->i_mount, ip, id, type,
+			     doalloc | XFS_QMOPT_DOWARN, &dqp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index 01d2072..99d4011 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -822,17 +822,9 @@ xfs_attr_inactive(xfs_inode_t *dp)
 	error = xfs_attr_root_inactive(&trans, dp);
 	if (error)
 		goto out;
-	/*
-	 * signal synchronous inactive transactions unless this
-	 * is a synchronous mount filesystem in which case we
-	 * know that we're here because we've been called out of
-	 * xfs_inactive which means that the last reference is gone
-	 * and the unlink transaction has already hit the disk so
-	 * async inactive transactions are safe.
-	 */
-	if ((error = xfs_itruncate_finish(&trans, dp, 0LL, XFS_ATTR_FORK,
-				(!(mp->m_flags & XFS_MOUNT_WSYNC)
-				 ? 1 : 0))))
+
+	error = xfs_itruncate_finish(&trans, dp, 0LL, XFS_ATTR_FORK, 0);
+	if (error)
 		goto out;
 
 	/*
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 71e90dc2..f49ecf2 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -110,6 +110,7 @@ xfs_attr_namesp_match(int arg_flags, int ondisk_flags)
 /*
  * Query whether the requested number of additional bytes of extended
  * attribute space will be able to fit inline.
+ *
  * Returns zero if not, else the di_forkoff fork offset to be used in the
  * literal area for attribute data once the new bytes have been added.
  *
@@ -122,7 +123,7 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 	int offset;
 	int minforkoff;	/* lower limit on valid forkoff locations */
 	int maxforkoff;	/* upper limit on valid forkoff locations */
-	int dsize;	
+	int dsize;
 	xfs_mount_t *mp = dp->i_mount;
 
 	offset = (XFS_LITINO(mp) - bytes) >> 3; /* rounded down */
@@ -136,47 +137,60 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 		return (offset >= minforkoff) ? minforkoff : 0;
 	}
 
-	if (!(mp->m_flags & XFS_MOUNT_ATTR2)) {
-		if (bytes <= XFS_IFORK_ASIZE(dp))
-			return dp->i_d.di_forkoff;
+	/*
+	 * If the requested numbers of bytes is smaller or equal to the
+	 * current attribute fork size we can always proceed.
+	 *
+	 * Note that if_bytes in the data fork might actually be larger than
+	 * the current data fork size is due to delalloc extents. In that
+	 * case either the extent count will go down when they are converted
+	 * to real extents, or the delalloc conversion will take care of the
+	 * literal area rebalancing.
+	 */
+	if (bytes <= XFS_IFORK_ASIZE(dp))
+		return dp->i_d.di_forkoff;
+
+	/*
+	 * For attr2 we can try to move the forkoff if there is space in the
+	 * literal area, but for the old format we are done if there is no
+	 * space in the fixed attribute fork.
+	 */
+	if (!(mp->m_flags & XFS_MOUNT_ATTR2))
 		return 0;
-	}
 
 	dsize = dp->i_df.if_bytes;
-	
+
 	switch (dp->i_d.di_format) {
 	case XFS_DINODE_FMT_EXTENTS:
-		/* 
+		/*
 		 * If there is no attr fork and the data fork is extents, 
-		 * determine if creating the default attr fork will result 
-		 * in the extents form migrating to btree. If so, the 
-		 * minimum offset only needs to be the space required for 
+		 * determine if creating the default attr fork will result
+		 * in the extents form migrating to btree. If so, the
+		 * minimum offset only needs to be the space required for
 		 * the btree root.
-		 */ 
+		 */
 		if (!dp->i_d.di_forkoff && dp->i_df.if_bytes >
 		    xfs_default_attroffset(dp))
 			dsize = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
 		break;
-		
 	case XFS_DINODE_FMT_BTREE:
 		/*
-		 * If have data btree then keep forkoff if we have one,
-		 * otherwise we are adding a new attr, so then we set 
-		 * minforkoff to where the btree root can finish so we have 
+		 * If we have a data btree then keep forkoff if we have one,
+		 * otherwise we are adding a new attr, so then we set
+		 * minforkoff to where the btree root can finish so we have
 		 * plenty of room for attrs
 		 */
 		if (dp->i_d.di_forkoff) {
-			if (offset < dp->i_d.di_forkoff) 
+			if (offset < dp->i_d.di_forkoff)
 				return 0;
-			else 
-				return dp->i_d.di_forkoff;
-		} else
-			dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
+			return dp->i_d.di_forkoff;
+		}
+		dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
 		break;
 	}
-	
-	/* 
-	 * A data fork btree root must have space for at least 
+
+	/*
+	 * A data fork btree root must have space for at least
 	 * MINDBTPTRS key/ptr pairs if the data fork is small or empty.
 	 */
 	minforkoff = MAX(dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS));
@@ -186,10 +200,10 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 	maxforkoff = XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
 	maxforkoff = maxforkoff >> 3;	/* rounded down */
 
-	if (offset >= minforkoff && offset < maxforkoff)
-		return offset;
 	if (offset >= maxforkoff)
 		return maxforkoff;
+	if (offset >= minforkoff)
+		return offset;
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index e546a33..a175933 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -3785,19 +3785,11 @@ xfs_bmap_compute_maxlevels(
  * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
  * caller.  Frees all the extents that need freeing, which must be done
  * last due to locking considerations.  We never free any extents in
- * the first transaction.  This is to allow the caller to make the first
- * transaction a synchronous one so that the pointers to the data being
- * broken in this transaction will be permanent before the data is actually
- * freed.  This is necessary to prevent blocks from being reallocated
- * and written to before the free and reallocation are actually permanent.
- * We do not just make the first transaction synchronous here, because
- * there are more efficient ways to gain the same protection in some cases
- * (see the file truncation code).
+ * the first transaction.
  *
  * Return 1 if the given transaction was committed and a new one
  * started, and 0 otherwise in the committed parameter.
  */
-/*ARGSUSED*/
 int						/* error */
 xfs_bmap_finish(
 	xfs_trans_t		**tp,		/* transaction pointer addr */
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index a7342e8..7888a75 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -1023,7 +1023,6 @@ xfs_buf_iodone_callbacks(
 	XFS_BUF_UNDELAYWRITE(bp);
 
 	trace_xfs_buf_error_relse(bp, _RET_IP_);
-	xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
 
 do_callbacks:
 	xfs_buf_do_callbacks(bp);
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 3631783..ca752f0 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -356,9 +356,20 @@ xfs_iget_cache_miss(
 			BUG();
 	}
 
-	spin_lock(&pag->pag_ici_lock);
+	/*
+	 * These values must be set before inserting the inode into the radix
+	 * tree as the moment it is inserted a concurrent lookup (allowed by the
+	 * RCU locking mechanism) can find it and that lookup must see that this
+	 * is an inode currently under construction (i.e. that XFS_INEW is set).
+	 * The ip->i_flags_lock that protects the XFS_INEW flag forms the
+	 * memory barrier that ensures this detection works correctly at lookup
+	 * time.
+	 */
+	ip->i_udquot = ip->i_gdquot = NULL;
+	xfs_iflags_set(ip, XFS_INEW);
 
 	/* insert the new inode */
+	spin_lock(&pag->pag_ici_lock);
 	error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
 	if (unlikely(error)) {
 		WARN_ON(error != -EEXIST);
@@ -366,11 +377,6 @@ xfs_iget_cache_miss(
 		error = EAGAIN;
 		goto out_preload_end;
 	}
-
-	/* These values _must_ be set before releasing the radix tree lock! */
-	ip->i_udquot = ip->i_gdquot = NULL;
-	xfs_iflags_set(ip, XFS_INEW);
-
 	spin_unlock(&pag->pag_ici_lock);
 	radix_tree_preload_end();
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index a098a20..5715279 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1528,15 +1528,7 @@ xfs_itruncate_finish(
 				xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
 			}
 		}
-	} else if (sync) {
-		ASSERT(!(mp->m_flags & XFS_MOUNT_WSYNC));
-		if (ip->i_d.di_anextents > 0)
-			xfs_trans_set_sync(ntp);
 	}
-	ASSERT(fork == XFS_DATA_FORK ||
-		(fork == XFS_ATTR_FORK &&
-			((sync && !(mp->m_flags & XFS_MOUNT_WSYNC)) ||
-			 (sync == 0 && (mp->m_flags & XFS_MOUNT_WSYNC)))));
 
 	/*
 	 * Since it is possible for space to become allocated beyond
@@ -3099,6 +3091,27 @@ corrupt_out:
 	return XFS_ERROR(EFSCORRUPTED);
 }
 
+void
+xfs_promote_inode(
+	struct xfs_inode	*ip)
+{
+	struct xfs_buf		*bp;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
+
+	bp = xfs_incore(ip->i_mount->m_ddev_targp, ip->i_imap.im_blkno,
+			ip->i_imap.im_len, XBF_TRYLOCK);
+	if (!bp)
+		return;
+
+	if (XFS_BUF_ISDELAYWRITE(bp)) {
+		xfs_buf_delwri_promote(bp);
+		wake_up_process(ip->i_mount->m_ddev_targp->bt_task);
+	}
+
+	xfs_buf_relse(bp);
+}
+
 /*
  * Return a pointer to the extent record at file index idx.
  */
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 964cfea..28b3596 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -509,6 +509,7 @@ 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 *);
 int		xfs_iflush(xfs_inode_t *, uint);
+void		xfs_promote_inode(struct xfs_inode *);
 void		xfs_lock_inodes(xfs_inode_t **, int, uint);
 void		xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
 
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 04142ca..b75fd67 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3159,37 +3159,26 @@ xlog_recover_process_iunlinks(
 			 */
 			continue;
 		}
+		/*
+		 * Unlock the buffer so that it can be acquired in the normal
+		 * course of the transaction to truncate and free each inode.
+		 * Because we are not racing with anyone else here for the AGI
+		 * buffer, we don't even need to hold it locked to read the
+		 * initial unlinked bucket entries out of the buffer. We keep
+		 * buffer reference though, so that it stays pinned in memory
+		 * while we need the buffer.
+		 */
 		agi = XFS_BUF_TO_AGI(agibp);
+		xfs_buf_unlock(agibp);
 
 		for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++) {
 			agino = be32_to_cpu(agi->agi_unlinked[bucket]);
 			while (agino != NULLAGINO) {
-				/*
-				 * Release the agi buffer so that it can
-				 * be acquired in the normal course of the
-				 * transaction to truncate and free the inode.
-				 */
-				xfs_buf_relse(agibp);
-
 				agino = xlog_recover_process_one_iunlink(mp,
 							agno, agino, bucket);
-
-				/*
-				 * Reacquire the agibuffer and continue around
-				 * the loop. This should never fail as we know
-				 * the buffer was good earlier on.
-				 */
-				error = xfs_read_agi(mp, NULL, agno, &agibp);
-				ASSERT(error == 0);
-				agi = XFS_BUF_TO_AGI(agibp);
 			}
 		}
-
-		/*
-		 * Release the buffer for the current agi so we can
-		 * go on to the next one.
-		 */
-		xfs_buf_relse(agibp);
+		xfs_buf_rele(agibp);
 	}
 
 	mp->m_dmevmask = mp_dmevmask;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index b49b823..9afdd49 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -44,9 +44,6 @@
 #include "xfs_trace.h"
 
 
-STATIC void	xfs_unmountfs_wait(xfs_mount_t *);
-
-
 #ifdef HAVE_PERCPU_SB
 STATIC void	xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t,
 						int);
@@ -1507,11 +1504,6 @@ xfs_unmountfs(
 	 */
 	xfs_log_force(mp, XFS_LOG_SYNC);
 
-	xfs_binval(mp->m_ddev_targp);
-	if (mp->m_rtdev_targp) {
-		xfs_binval(mp->m_rtdev_targp);
-	}
-
 	/*
 	 * Unreserve any blocks we have so that when we unmount we don't account
 	 * the reserved free space as used. This is really only necessary for
@@ -1537,7 +1529,16 @@ xfs_unmountfs(
 		xfs_warn(mp, "Unable to update superblock counters. "
 				"Freespace may not be correct on next mount.");
 	xfs_unmountfs_writesb(mp);
-	xfs_unmountfs_wait(mp); 		/* wait for async bufs */
+
+	/*
+	 * Make sure all buffers have been flushed and completed before
+	 * unmounting the log.
+	 */
+	error = xfs_flush_buftarg(mp->m_ddev_targp, 1);
+	if (error)
+		xfs_warn(mp, "%d busy buffers during unmount.", error);
+	xfs_wait_buftarg(mp->m_ddev_targp);
+
 	xfs_log_unmount_write(mp);
 	xfs_log_unmount(mp);
 	xfs_uuid_unmount(mp);
@@ -1548,16 +1549,6 @@ xfs_unmountfs(
 	xfs_free_perag(mp);
 }
 
-STATIC void
-xfs_unmountfs_wait(xfs_mount_t *mp)
-{
-	if (mp->m_logdev_targp != mp->m_ddev_targp)
-		xfs_wait_buftarg(mp->m_logdev_targp);
-	if (mp->m_rtdev_targp)
-		xfs_wait_buftarg(mp->m_rtdev_targp);
-	xfs_wait_buftarg(mp->m_ddev_targp);
-}
-
 int
 xfs_fs_writable(xfs_mount_t *mp)
 {
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 6197207..59509ae 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -535,7 +535,7 @@ xfs_readlink(
 	char		*link)
 {
 	xfs_mount_t	*mp = ip->i_mount;
-	int		pathlen;
+	xfs_fsize_t	pathlen;
 	int		error = 0;
 
 	trace_xfs_readlink(ip);
@@ -545,13 +545,20 @@ xfs_readlink(
 
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 
-	ASSERT((ip->i_d.di_mode & S_IFMT) == S_IFLNK);
-	ASSERT(ip->i_d.di_size <= MAXPATHLEN);
-
 	pathlen = ip->i_d.di_size;
 	if (!pathlen)
 		goto out;
 
+	if (pathlen < 0 || pathlen > MAXPATHLEN) {
+		xfs_alert(mp, "%s: inode (%llu) bad symlink length (%lld)",
+			 __func__, (unsigned long long) ip->i_ino,
+			 (long long) pathlen);
+		ASSERT(0);
+		error = XFS_ERROR(EFSCORRUPTED);
+		goto out;
+	}
+
+
 	if (ip->i_df.if_flags & XFS_IFINLINE) {
 		memcpy(link, ip->i_df.if_u1.if_data, pathlen);
 		link[pathlen] = '\0';