Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/wireless/ath/ath9k/recv.c
	drivers/net/wireless/mwifiex/pcie.c
	net/ipv6/sit.c

The SIT driver conflict consists of a bug fix being done by hand
in 'net' (missing u64_stats_init()) whilst in 'net-next' a helper
was created (netdev_alloc_pcpu_stats()) which takes care of this.

The two wireless conflicts were overlapping changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

31 files changed, 209 insertions, 113 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e0259a1..d754e3c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -40,18 +40,13 @@
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
-	/*
-	 * Write only inodes dirtied before this time. Don't forget to set
-	 * older_than_this_is_set when you set this.
-	 */
-	unsigned long older_than_this;
+	unsigned long *older_than_this;
 	enum writeback_sync_modes sync_mode;
 	unsigned int tagged_writepages:1;
 	unsigned int for_kupdate:1;
 	unsigned int range_cyclic:1;
 	unsigned int for_background:1;
 	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
-	unsigned int older_than_this_is_set:1;
 	enum wb_reason reason;		/* why was writeback initiated? */
 
 	struct list_head list;		/* pending work list */
@@ -252,10 +247,10 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 	int moved = 0;
 
-	WARN_ON_ONCE(!work->older_than_this_is_set);
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (inode_dirtied_after(inode, work->older_than_this))
+		if (work->older_than_this &&
+		    inode_dirtied_after(inode, *work->older_than_this))
 			break;
 		list_move(&inode->i_wb_list, &tmp);
 		moved++;
@@ -742,8 +737,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 		.sync_mode	= WB_SYNC_NONE,
 		.range_cyclic	= 1,
 		.reason		= reason,
-		.older_than_this = jiffies,
-		.older_than_this_is_set = 1,
 	};
 
 	spin_lock(&wb->list_lock);
@@ -802,13 +795,12 @@ static long wb_writeback(struct bdi_writeback *wb,
 {
 	unsigned long wb_start = jiffies;
 	long nr_pages = work->nr_pages;
+	unsigned long oldest_jif;
 	struct inode *inode;
 	long progress;
 
-	if (!work->older_than_this_is_set) {
-		work->older_than_this = jiffies;
-		work->older_than_this_is_set = 1;
-	}
+	oldest_jif = jiffies;
+	work->older_than_this = &oldest_jif;
 
 	spin_lock(&wb->list_lock);
 	for (;;) {
@@ -842,10 +834,10 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * safe.
 		 */
 		if (work->for_kupdate) {
-			work->older_than_this = jiffies -
+			oldest_jif = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
 		} else if (work->for_background)
-			work->older_than_this = jiffies;
+			oldest_jif = jiffies;
 
 		trace_writeback_start(wb->bdi, work);
 		if (list_empty(&wb->b_io))
@@ -1357,21 +1349,18 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb);
 
 /**
  * sync_inodes_sb	-	sync sb inode pages
- * @sb:			the superblock
- * @older_than_this:	timestamp
+ * @sb: the superblock
  *
  * This function writes and waits on any dirty inode belonging to this
- * superblock that has been dirtied before given timestamp.
+ * super_block.
  */
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this)
+void sync_inodes_sb(struct super_block *sb)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct wb_writeback_work work = {
 		.sb		= sb,
 		.sync_mode	= WB_SYNC_ALL,
 		.nr_pages	= LONG_MAX,
-		.older_than_this = older_than_this,
-		.older_than_this_is_set = 1,
 		.range_cyclic	= 0,
 		.done		= &done,
 		.reason		= WB_REASON_SYNC,
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 968eab5..68537e8 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -75,7 +75,7 @@ int hfsplus_parse_options_remount(char *input, int *force)
 	int token;
 
 	if (!input)
-		return 0;
+		return 1;
 
 	while ((p = strsep(&input, ",")) != NULL) {
 		if (!*p)
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 0d6ce89..0f4152d 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -94,6 +94,7 @@ const void *kernfs_super_ns(struct super_block *sb)
  * @fs_type: file_system_type of the fs being mounted
  * @flags: mount flags specified for the mount
  * @root: kernfs_root of the hierarchy being mounted
+ * @new_sb_created: tell the caller if we allocated a new superblock
  * @ns: optional namespace tag of the mount
  *
  * This is to be called from each kernfs user's file_system_type->mount()
@@ -104,7 +105,8 @@ const void *kernfs_super_ns(struct super_block *sb)
  * The return value can be passed to the vfs layer verbatim.
  */
 struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-			       struct kernfs_root *root, const void *ns)
+			       struct kernfs_root *root, bool *new_sb_created,
+			       const void *ns)
 {
 	struct super_block *sb;
 	struct kernfs_super_info *info;
@@ -122,6 +124,10 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
 		kfree(info);
 	if (IS_ERR(sb))
 		return ERR_CAST(sb);
+
+	if (new_sb_created)
+		*new_sb_created = !sb->s_root;
+
 	if (!sb->s_root) {
 		error = kernfs_fill_super(sb);
 		if (error) {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 28a0a3c..360114a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -164,17 +164,16 @@ static void nfs_zap_caches_locked(struct inode *inode)
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
 		nfs_fscache_invalidate(inode);
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-					| NFS_INO_INVALID_LABEL
 					| NFS_INO_INVALID_DATA
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
 					| NFS_INO_REVAL_PAGECACHE;
 	} else
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-					| NFS_INO_INVALID_LABEL
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
 					| NFS_INO_REVAL_PAGECACHE;
+	nfs_zap_label_cache_locked(nfsi);
 }
 
 void nfs_zap_caches(struct inode *inode)
@@ -266,6 +265,13 @@ nfs_init_locked(struct inode *inode, void *opaque)
 }
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
+static void nfs_clear_label_invalid(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL;
+	spin_unlock(&inode->i_lock);
+}
+
 void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 					struct nfs4_label *label)
 {
@@ -283,6 +289,7 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 					__func__,
 					(char *)label->label,
 					label->len, error);
+		nfs_clear_label_invalid(inode);
 	}
 }
 
@@ -1648,7 +1655,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		inode->i_blocks = fattr->du.nfs2.blocks;
 
 	/* Update attrtimeo value if we're out of the unstable period */
-	if (invalid & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) {
+	if (invalid & NFS_INO_INVALID_ATTR) {
 		nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 		nfsi->attrtimeo_timestamp = now;
@@ -1661,7 +1668,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		}
 	}
 	invalid &= ~NFS_INO_INVALID_ATTR;
-	invalid &= ~NFS_INO_INVALID_LABEL;
 	/* Don't invalidate the data if we were to blame */
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
 				|| S_ISLNK(inode->i_mode)))
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 8b5cc04..b46cf5a 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -176,7 +176,8 @@ extern struct nfs_server *nfs4_create_server(
 extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
 						      struct nfs_fh *);
 extern int nfs4_update_server(struct nfs_server *server, const char *hostname,
-					struct sockaddr *sap, size_t salen);
+					struct sockaddr *sap, size_t salen,
+					struct net *net);
 extern void nfs_free_server(struct nfs_server *server);
 extern struct nfs_server *nfs_clone_server(struct nfs_server *,
 					   struct nfs_fh *,
@@ -279,9 +280,18 @@ static inline void nfs4_label_free(struct nfs4_label *label)
 	}
 	return;
 }
+
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+	if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL))
+		nfsi->cache_validity |= NFS_INO_INVALID_LABEL;
+}
 #else
 static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; }
 static inline void nfs4_label_free(void *label) {}
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+}
 #endif /* CONFIG_NFS_V4_SECURITY_LABEL */
 
 /* proc.c */
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index aa9bc97..a462ef0 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -18,6 +18,7 @@
 #include <linux/lockd/bind.h>
 #include <linux/nfs_mount.h>
 #include <linux/freezer.h>
+#include <linux/xattr.h>
 
 #include "iostat.h"
 #include "internal.h"
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 860ad26..0e46d3d 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1135,6 +1135,7 @@ static int nfs_probe_destination(struct nfs_server *server)
  * @hostname: new end-point's hostname
  * @sap: new end-point's socket address
  * @salen: size of "sap"
+ * @net: net namespace
  *
  * The nfs_server must be quiescent before this function is invoked.
  * Either its session is drained (NFSv4.1+), or its transport is
@@ -1143,13 +1144,13 @@ static int nfs_probe_destination(struct nfs_server *server)
  * Returns zero on success, or a negative errno value.
  */
 int nfs4_update_server(struct nfs_server *server, const char *hostname,
-		       struct sockaddr *sap, size_t salen)
+		       struct sockaddr *sap, size_t salen, struct net *net)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct rpc_clnt *clnt = server->client;
 	struct xprt_create xargs = {
 		.ident		= clp->cl_proto,
-		.net		= &init_net,
+		.net		= net,
 		.dstaddr	= sap,
 		.addrlen	= salen,
 		.servername	= hostname,
@@ -1189,7 +1190,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
 	error = nfs4_set_client(server, hostname, sap, salen, buf,
 				clp->cl_rpcclient->cl_auth->au_flavor,
 				clp->cl_proto, clnt->cl_timeout,
-				clp->cl_minorversion, clp->cl_net);
+				clp->cl_minorversion, net);
 	nfs_put_client(clp);
 	if (error != 0) {
 		nfs_server_insert_lists(server);
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 4e7f05d..3d5dbf8 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -121,9 +121,8 @@ static int nfs4_validate_fspath(struct dentry *dentry,
 }
 
 static size_t nfs_parse_server_name(char *string, size_t len,
-		struct sockaddr *sa, size_t salen, struct nfs_server *server)
+		struct sockaddr *sa, size_t salen, struct net *net)
 {
-	struct net *net = rpc_net_ns(server->client);
 	ssize_t ret;
 
 	ret = rpc_pton(net, string, len, sa, salen);
@@ -223,6 +222,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 				     const struct nfs4_fs_location *location)
 {
 	const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+	struct net *net = rpc_net_ns(NFS_SB(mountdata->sb)->client);
 	struct vfsmount *mnt = ERR_PTR(-ENOENT);
 	char *mnt_path;
 	unsigned int maxbuflen;
@@ -248,8 +248,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 			continue;
 
 		mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len,
-				mountdata->addr, addr_bufsize,
-				NFS_SB(mountdata->sb));
+				mountdata->addr, addr_bufsize, net);
 		if (mountdata->addrlen == 0)
 			continue;
 
@@ -419,6 +418,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
 		const struct nfs4_fs_location *location)
 {
 	const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+	struct net *net = rpc_net_ns(server->client);
 	struct sockaddr *sap;
 	unsigned int s;
 	size_t salen;
@@ -440,7 +440,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
 			continue;
 
 		salen = nfs_parse_server_name(buf->data, buf->len,
-						sap, addr_bufsize, server);
+						sap, addr_bufsize, net);
 		if (salen == 0)
 			continue;
 		rpc_set_port(sap, NFS_PORT);
@@ -450,7 +450,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
 		if (hostname == NULL)
 			break;
 
-		error = nfs4_update_server(server, hostname, sap, salen);
+		error = nfs4_update_server(server, hostname, sap, salen, net);
 		kfree(hostname);
 		if (error == 0)
 			break;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e5be725..e1a4721 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1015,8 +1015,11 @@ int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
 	if (ret == -EIO)
 		/* A lost lock - don't even consider delegations */
 		goto out;
-	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
+	/* returns true if delegation stateid found and copied */
+	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) {
+		ret = 0;
 		goto out;
+	}
 	if (ret != -ENOENT)
 		/* nfs4_copy_delegation_stateid() didn't over-write
 		 * dst, so it still has the lock stateid which we now
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 0b9ff43..abc8cbc 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -86,7 +86,7 @@ static int dnotify_handle_event(struct fsnotify_group *group,
 				struct fsnotify_mark *inode_mark,
 				struct fsnotify_mark *vfsmount_mark,
 				u32 mask, void *data, int data_type,
-				const unsigned char *file_name)
+				const unsigned char *file_name, u32 cookie)
 {
 	struct dnotify_mark *dn_mark;
 	struct dnotify_struct *dn;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 0e792f5..dc638f7 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -147,7 +147,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 				 struct fsnotify_mark *inode_mark,
 				 struct fsnotify_mark *fanotify_mark,
 				 u32 mask, void *data, int data_type,
-				 const unsigned char *file_name)
+				 const unsigned char *file_name, u32 cookie)
 {
 	int ret = 0;
 	struct fanotify_event_info *event;
@@ -192,10 +192,12 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 
 	ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge);
 	if (ret) {
-		BUG_ON(mask & FAN_ALL_PERM_EVENTS);
+		/* Permission events shouldn't be merged */
+		BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS);
 		/* Our event wasn't used in the end. Free it. */
 		fsnotify_destroy_event(group, fsn_event);
-		ret = 0;
+
+		return 0;
 	}
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index b6175fa..287a22c 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -698,6 +698,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	struct fsnotify_group *group;
 	int f_flags, fd;
 	struct user_struct *user;
+	struct fanotify_event_info *oevent;
 
 	pr_debug("%s: flags=%d event_f_flags=%d\n",
 		__func__, flags, event_f_flags);
@@ -730,8 +731,20 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	group->fanotify_data.user = user;
 	atomic_inc(&user->fanotify_listeners);
 
+	oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+	if (unlikely(!oevent)) {
+		fd = -ENOMEM;
+		goto out_destroy_group;
+	}
+	group->overflow_event = &oevent->fse;
+	fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+	oevent->tgid = get_pid(task_tgid(current));
+	oevent->path.mnt = NULL;
+	oevent->path.dentry = NULL;
+
 	group->fanotify_data.f_flags = event_f_flags;
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	oevent->response = 0;
 	mutex_init(&group->fanotify_data.access_mutex);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 1d4e1ea..9d3e9c5 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -179,7 +179,7 @@ static int send_to_group(struct inode *to_tell,
 
 	return group->ops->handle_event(group, to_tell, inode_mark,
 					vfsmount_mark, mask, data, data_is,
-					file_name);
+					file_name, cookie);
 }
 
 /*
diff --git a/fs/notify/group.c b/fs/notify/group.c
index ee674fe..ad19959 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -55,6 +55,13 @@ void fsnotify_destroy_group(struct fsnotify_group *group)
 	/* clear the notification queue of all events */
 	fsnotify_flush_notify(group);
 
+	/*
+	 * Destroy overflow event (we cannot use fsnotify_destroy_event() as
+	 * that deliberately ignores overflow events.
+	 */
+	if (group->overflow_event)
+		group->ops->free_event(group->overflow_event);
+
 	fsnotify_put_group(group);
 }
 
@@ -99,7 +106,6 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
 	INIT_LIST_HEAD(&group->marks_list);
 
 	group->ops = ops;
-	fsnotify_init_event(&group->overflow_event, NULL, FS_Q_OVERFLOW);
 
 	return group;
 }
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index 485eef3..ed855ef 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -27,6 +27,6 @@ extern int inotify_handle_event(struct fsnotify_group *group,
 				struct fsnotify_mark *inode_mark,
 				struct fsnotify_mark *vfsmount_mark,
 				u32 mask, void *data, int data_type,
-				const unsigned char *file_name);
+				const unsigned char *file_name, u32 cookie);
 
 extern const struct fsnotify_ops inotify_fsnotify_ops;
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index d5ee563..43ab1e1 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -67,7 +67,7 @@ int inotify_handle_event(struct fsnotify_group *group,
 			 struct fsnotify_mark *inode_mark,
 			 struct fsnotify_mark *vfsmount_mark,
 			 u32 mask, void *data, int data_type,
-			 const unsigned char *file_name)
+			 const unsigned char *file_name, u32 cookie)
 {
 	struct inotify_inode_mark *i_mark;
 	struct inotify_event_info *event;
@@ -103,6 +103,7 @@ int inotify_handle_event(struct fsnotify_group *group,
 	fsn_event = &event->fse;
 	fsnotify_init_event(fsn_event, inode, mask);
 	event->wd = i_mark->wd;
+	event->sync_cookie = cookie;
 	event->name_len = len;
 	if (len)
 		strcpy(event->name, file_name);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 497395c..78a2ca3 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -495,7 +495,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
 
 	/* Queue ignore event for the watch */
 	inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
-			     NULL, FSNOTIFY_EVENT_NONE, NULL);
+			     NULL, FSNOTIFY_EVENT_NONE, NULL, 0);
 
 	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
 	/* remove this mark from the idr */
@@ -633,11 +633,23 @@ static int inotify_update_watch(struct fsnotify_group *group, struct inode *inod
 static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 {
 	struct fsnotify_group *group;
+	struct inotify_event_info *oevent;
 
 	group = fsnotify_alloc_group(&inotify_fsnotify_ops);
 	if (IS_ERR(group))
 		return group;
 
+	oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL);
+	if (unlikely(!oevent)) {
+		fsnotify_destroy_group(group);
+		return ERR_PTR(-ENOMEM);
+	}
+	group->overflow_event = &oevent->fse;
+	fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+	oevent->wd = -1;
+	oevent->sync_cookie = 0;
+	oevent->name_len = 0;
+
 	group->max_events = max_events;
 
 	spin_lock_init(&group->inotify_data.idr_lock);
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 18b3c44..1e58402 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -80,7 +80,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
 /*
  * Add an event to the group notification queue.  The group can later pull this
  * event off the queue to deal with.  The function returns 0 if the event was
- * added to the queue, 1 if the event was merged with some other queued event.
+ * added to the queue, 1 if the event was merged with some other queued event,
+ * 2 if the queue of events has overflown.
  */
 int fsnotify_add_notify_event(struct fsnotify_group *group,
 			      struct fsnotify_event *event,
@@ -95,10 +96,14 @@ int fsnotify_add_notify_event(struct fsnotify_group *group,
 	mutex_lock(&group->notification_mutex);
 
 	if (group->q_len >= group->max_events) {
+		ret = 2;
 		/* Queue overflow event only if it isn't already queued */
-		if (list_empty(&group->overflow_event.list))
-			event = &group->overflow_event;
-		ret = 1;
+		if (!list_empty(&group->overflow_event->list)) {
+			mutex_unlock(&group->notification_mutex);
+			return ret;
+		}
+		event = group->overflow_event;
+		goto queue;
 	}
 
 	if (!list_empty(list) && merge) {
@@ -109,6 +114,7 @@ int fsnotify_add_notify_event(struct fsnotify_group *group,
 		}
 	}
 
+queue:
 	group->q_len++;
 	list_add_tail(&event->list, list);
 	mutex_unlock(&group->notification_mutex);
@@ -132,7 +138,11 @@ struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group
 
 	event = list_first_entry(&group->notification_list,
 				 struct fsnotify_event, list);
-	list_del(&event->list);
+	/*
+	 * We need to init list head for the case of overflow event so that
+	 * check in fsnotify_add_notify_events() works
+	 */
+	list_del_init(&event->list);
 	group->q_len--;
 
 	return event;
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index aaa5061..d7b5108 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -717,6 +717,12 @@ static int ocfs2_release_dquot(struct dquot *dquot)
 	 */
 	if (status < 0)
 		mlog_errno(status);
+	/*
+	 * Clear dq_off so that we search for the structure in quota file next
+	 * time we acquire it. The structure might be deleted and reallocated
+	 * elsewhere by another node while our dquot structure is on freelist.
+	 */
+	dquot->dq_off = 0;
 	clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
 out_trans:
 	ocfs2_commit_trans(osb, handle);
@@ -756,16 +762,17 @@ static int ocfs2_acquire_dquot(struct dquot *dquot)
 	status = ocfs2_lock_global_qf(info, 1);
 	if (status < 0)
 		goto out;
-	if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
-		status = ocfs2_qinfo_lock(info, 0);
-		if (status < 0)
-			goto out_dq;
-		status = qtree_read_dquot(&info->dqi_gi, dquot);
-		ocfs2_qinfo_unlock(info, 0);
-		if (status < 0)
-			goto out_dq;
-	}
-	set_bit(DQ_READ_B, &dquot->dq_flags);
+	status = ocfs2_qinfo_lock(info, 0);
+	if (status < 0)
+		goto out_dq;
+	/*
+	 * We always want to read dquot structure from disk because we don't
+	 * know what happened with it while it was on freelist.
+	 */
+	status = qtree_read_dquot(&info->dqi_gi, dquot);
+	ocfs2_qinfo_unlock(info, 0);
+	if (status < 0)
+		goto out_dq;
 
 	OCFS2_DQUOT(dquot)->dq_use_count++;
 	OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2e4344b..2001862 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -1303,10 +1303,6 @@ int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot)
 	ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
 
 out:
-	/* Clear the read bit so that next time someone uses this
-	 * dquot he reads fresh info from disk and allocates local
-	 * dquot structure */
-	clear_bit(DQ_READ_B, &dquot->dq_flags);
 	return status;
 }
 
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 02174a6..e647c55 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -121,9 +121,8 @@ u64 stable_page_flags(struct page *page)
 	 * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
 	 * to make sure a given page is a thp, not a non-huge compound page.
 	 */
-	else if (PageTransCompound(page) &&
-		 (PageLRU(compound_trans_head(page)) ||
-		  PageAnon(compound_trans_head(page))))
+	else if (PageTransCompound(page) && (PageLRU(compound_head(page)) ||
+					     PageAnon(compound_head(page))))
 		u |= 1 << KPF_THP;
 
 	/*
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 831d49a..cfc8dcc 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -581,9 +581,17 @@ int dquot_scan_active(struct super_block *sb,
 		dqstats_inc(DQST_LOOKUPS);
 		dqput(old_dquot);
 		old_dquot = dquot;
-		ret = fn(dquot, priv);
-		if (ret < 0)
-			goto out;
+		/*
+		 * ->release_dquot() can be racing with us. Our reference
+		 * protects us from new calls to it so just wait for any
+		 * outstanding call and recheck the DQ_ACTIVE_B after that.
+		 */
+		wait_on_dquot(dquot);
+		if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+			ret = fn(dquot, priv);
+			if (ret < 0)
+				goto out;
+		}
 		spin_lock(&dq_list_lock);
 		/* We are safe to continue now because our dquot could not
 		 * be moved out of the inuse list while we hold the reference */
diff --git a/fs/sync.c b/fs/sync.c
index e8ba024..b28d1dd 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -27,11 +27,10 @@
  * wait == 1 case since in that case write_inode() functions do
  * sync_dirty_buffer() and thus effectively write one block at a time.
  */
-static int __sync_filesystem(struct super_block *sb, int wait,
-			     unsigned long start)
+static int __sync_filesystem(struct super_block *sb, int wait)
 {
 	if (wait)
-		sync_inodes_sb(sb, start);
+		sync_inodes_sb(sb);
 	else
 		writeback_inodes_sb(sb, WB_REASON_SYNC);
 
@@ -48,7 +47,6 @@ static int __sync_filesystem(struct super_block *sb, int wait,
 int sync_filesystem(struct super_block *sb)
 {
 	int ret;
-	unsigned long start = jiffies;
 
 	/*
 	 * We need to be protected against the filesystem going from
@@ -62,17 +60,17 @@ int sync_filesystem(struct super_block *sb)
 	if (sb->s_flags & MS_RDONLY)
 		return 0;
 
-	ret = __sync_filesystem(sb, 0, start);
+	ret = __sync_filesystem(sb, 0);
 	if (ret < 0)
 		return ret;
-	return __sync_filesystem(sb, 1, start);
+	return __sync_filesystem(sb, 1);
 }
 EXPORT_SYMBOL_GPL(sync_filesystem);
 
 static void sync_inodes_one_sb(struct super_block *sb, void *arg)
 {
 	if (!(sb->s_flags & MS_RDONLY))
-		sync_inodes_sb(sb, *((unsigned long *)arg));
+		sync_inodes_sb(sb);
 }
 
 static void sync_fs_one_sb(struct super_block *sb, void *arg)
@@ -104,10 +102,9 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
 SYSCALL_DEFINE0(sync)
 {
 	int nowait = 0, wait = 1;
-	unsigned long start = jiffies;
 
 	wakeup_flusher_threads(0, WB_REASON_SYNC);
-	iterate_supers(sync_inodes_one_sb, &start);
+	iterate_supers(sync_inodes_one_sb, NULL);
 	iterate_supers(sync_fs_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &wait);
 	iterate_bdevs(fdatawrite_one_bdev, NULL);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 6211230..3eaf5c6 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -27,6 +27,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 {
 	struct dentry *root;
 	void *ns;
+	bool new_sb;
 
 	if (!(flags & MS_KERNMOUNT)) {
 		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
@@ -37,8 +38,8 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	}
 
 	ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
-	root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns);
-	if (IS_ERR(root))
+	root = kernfs_mount_ns(fs_type, flags, sysfs_root, &new_sb, ns);
+	if (IS_ERR(root) || !new_sb)
 		kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
 	return root;
 }
diff --git a/fs/udf/file.c b/fs/udf/file.c
index c02a27a..1037637 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -144,6 +144,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	size_t count = iocb->ki_nbytes;
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
+	mutex_lock(&inode->i_mutex);
 	down_write(&iinfo->i_data_sem);
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
 		if (file->f_flags & O_APPEND)
@@ -156,6 +157,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 						pos + count)) {
 			err = udf_expand_file_adinicb(inode);
 			if (err) {
+				mutex_unlock(&inode->i_mutex);
 				udf_debug("udf_expand_adinicb: err=%d\n", err);
 				return err;
 			}
@@ -169,9 +171,17 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	} else
 		up_write(&iinfo->i_data_sem);
 
-	retval = generic_file_aio_write(iocb, iov, nr_segs, ppos);
-	if (retval > 0)
+	retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	mutex_unlock(&inode->i_mutex);
+
+	if (retval > 0) {
+		ssize_t err;
+
 		mark_inode_dirty(inode);
+		err = generic_write_sync(file, iocb->ki_pos - retval, retval);
+		if (err < 0)
+			retval = err;
+	}
 
 	return retval;
 }
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 062b792..982ce05 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -265,6 +265,7 @@ int udf_expand_file_adinicb(struct inode *inode)
 		.nr_to_write = 1,
 	};
 
+	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
 	if (!iinfo->i_lenAlloc) {
 		if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
 			iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index f35d5c9..9ddfb81 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -705,7 +705,6 @@ xfs_setattr_size(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct inode		*inode = VFS_I(ip);
-	int			mask = iattr->ia_valid;
 	xfs_off_t		oldsize, newsize;
 	struct xfs_trans	*tp;
 	int			error;
@@ -726,8 +725,8 @@ xfs_setattr_size(
 
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(S_ISREG(ip->i_d.di_mode));
-	ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
-			ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
+	ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
+		ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
 
 	oldsize = inode->i_size;
 	newsize = iattr->ia_size;
@@ -736,7 +735,7 @@ xfs_setattr_size(
 	 * Short circuit the truncate case for zero length files.
 	 */
 	if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
-		if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
+		if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
 			return 0;
 
 		/*
@@ -824,10 +823,11 @@ xfs_setattr_size(
 	 * these flags set.  For all other operations the VFS set these flags
 	 * explicitly if it wants a timestamp update.
 	 */
-	if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
+	if (newsize != oldsize &&
+	    !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
 		iattr->ia_ctime = iattr->ia_mtime =
 			current_fs_time(inode->i_sb);
-		mask |= ATTR_CTIME | ATTR_MTIME;
+		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
 	}
 
 	/*
@@ -863,9 +863,9 @@ xfs_setattr_size(
 		xfs_inode_clear_eofblocks_tag(ip);
 	}
 
-	if (mask & ATTR_MODE)
+	if (iattr->ia_valid & ATTR_MODE)
 		xfs_setattr_mode(ip, iattr);
-	if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
+	if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
 		xfs_setattr_time(ip, iattr);
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index cdebd83..4ef6fdb 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -205,16 +205,25 @@ xlog_cil_insert_format_items(
 		/*
 		 * We 64-bit align the length of each iovec so that the start
 		 * of the next one is naturally aligned.  We'll need to
-		 * account for that slack space here.
+		 * account for that slack space here. Then round nbytes up
+		 * to 64-bit alignment so that the initial buffer alignment is
+		 * easy to calculate and verify.
 		 */
 		nbytes += niovecs * sizeof(uint64_t);
+		nbytes = round_up(nbytes, sizeof(uint64_t));
 
 		/* grab the old item if it exists for reservation accounting */
 		old_lv = lip->li_lv;
 
-		/* calc buffer size */
-		buf_size = sizeof(struct xfs_log_vec) + nbytes +
-				niovecs * sizeof(struct xfs_log_iovec);
+		/*
+		 * The data buffer needs to start 64-bit aligned, so round up
+		 * that space to ensure we can align it appropriately and not
+		 * overrun the buffer.
+		 */
+		buf_size = nbytes +
+			   round_up((sizeof(struct xfs_log_vec) +
+				     niovecs * sizeof(struct xfs_log_iovec)),
+				    sizeof(uint64_t));
 
 		/* compare to existing item size */
 		if (lip->li_lv && buf_size <= lip->li_lv->lv_size) {
@@ -251,6 +260,8 @@ xlog_cil_insert_format_items(
 		/* The allocated data region lies beyond the iovec region */
 		lv->lv_buf_len = 0;
 		lv->lv_buf = (char *)lv + buf_size - nbytes;
+		ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
+
 		lip->li_ops->iop_format(lip, lv);
 insert:
 		ASSERT(lv->lv_buf_len <= nbytes);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 02df7b4..f96c056 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -282,22 +282,29 @@ xfs_readsb(
 	struct xfs_sb	*sbp = &mp->m_sb;
 	int		error;
 	int		loud = !(flags & XFS_MFSI_QUIET);
+	const struct xfs_buf_ops *buf_ops;
 
 	ASSERT(mp->m_sb_bp == NULL);
 	ASSERT(mp->m_ddev_targp != NULL);
 
 	/*
+	 * For the initial read, we must guess at the sector
+	 * size based on the block device.  It's enough to
+	 * get the sb_sectsize out of the superblock and
+	 * then reread with the proper length.
+	 * We don't verify it yet, because it may not be complete.
+	 */
+	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
+	buf_ops = NULL;
+
+	/*
 	 * Allocate a (locked) buffer to hold the superblock.
 	 * This will be kept around at all times to optimize
 	 * access to the superblock.
 	 */
-	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
-
 reread:
 	bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
-				   BTOBB(sector_size), 0,
-				   loud ? &xfs_sb_buf_ops
-				        : &xfs_sb_quiet_buf_ops);
+				   BTOBB(sector_size), 0, buf_ops);
 	if (!bp) {
 		if (loud)
 			xfs_warn(mp, "SB buffer read failed");
@@ -328,12 +335,13 @@ reread:
 	}
 
 	/*
-	 * If device sector size is smaller than the superblock size,
-	 * re-read the superblock so the buffer is correctly sized.
+	 * Re-read the superblock so the buffer is correctly sized,
+	 * and properly verified.
 	 */
-	if (sector_size < sbp->sb_sectsize) {
+	if (buf_ops == NULL) {
 		xfs_buf_relse(bp);
 		sector_size = sbp->sb_sectsize;
+		buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
 		goto reread;
 	}
 
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index b7c9aea..1e11679 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -295,8 +295,7 @@ xfs_mount_validate_sb(
 	    sbp->sb_dblocks == 0					||
 	    sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp)			||
 	    sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) {
-		XFS_CORRUPTION_ERROR("SB sanity check failed",
-				XFS_ERRLEVEL_LOW, mp, sbp);
+		xfs_notice(mp, "SB sanity check failed");
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 
@@ -611,10 +610,10 @@ xfs_sb_read_verify(
 						XFS_SB_VERSION_5) ||
 	     dsb->sb_crc != 0)) {
 
-		if (!xfs_verify_cksum(bp->b_addr, be16_to_cpu(dsb->sb_sectsize),
+		if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
 				      offsetof(struct xfs_sb, sb_crc))) {
 			/* Only fail bad secondaries on a known V5 filesystem */
-			if (bp->b_bn != XFS_SB_DADDR &&
+			if (bp->b_bn == XFS_SB_DADDR ||
 			    xfs_sb_version_hascrc(&mp->m_sb)) {
 				error = EFSCORRUPTED;
 				goto out_error;
@@ -625,7 +624,7 @@ xfs_sb_read_verify(
 
 out_error:
 	if (error) {
-		if (error != EWRONGFS)
+		if (error == EFSCORRUPTED)
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
 					     mp, bp->b_addr);
 		xfs_buf_ioerror(bp, error);
@@ -644,7 +643,6 @@ xfs_sb_quiet_read_verify(
 {
 	struct xfs_dsb	*dsb = XFS_BUF_TO_SBP(bp);
 
-
 	if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) {
 		/* XFS filesystem, verify noisily! */
 		xfs_sb_read_verify(bp);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index f317488..d971f49 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -913,7 +913,7 @@ xfs_flush_inodes(
 	struct super_block	*sb = mp->m_super;
 
 	if (down_read_trylock(&sb->s_umount)) {
-		sync_inodes_sb(sb, jiffies);
+		sync_inodes_sb(sb);
 		up_read(&sb->s_umount);
 	}
 }