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

20 files changed, 281 insertions, 169 deletions

diff --git a/fs/aio.c b/fs/aio.c
index fb8e45b88cd4..4fe81d1c60f9 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -239,7 +239,12 @@ static struct dentry *aio_mount(struct file_system_type *fs_type,
 	static const struct dentry_operations ops = {
 		.d_dname	= simple_dname,
 	};
-	return mount_pseudo(fs_type, "aio:", NULL, &ops, AIO_RING_MAGIC);
+	struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+					   AIO_RING_MAGIC);
+
+	if (!IS_ERR(root))
+		root->d_sb->s_iflags |= SB_I_NOEXEC;
+	return root;
 }
 
 /* aio_setup
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index b493909e7492..d8e6d421c27f 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -417,6 +417,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	}
 	return NULL;
 }
+
 /*
  * Find an eligible tree to time-out
  * A tree is eligible if :-
@@ -432,6 +433,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	struct dentry *root = sb->s_root;
 	struct dentry *dentry;
 	struct dentry *expired;
+	struct dentry *found;
 	struct autofs_info *ino;
 
 	if (!root)
@@ -442,31 +444,46 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 
 	dentry = NULL;
 	while ((dentry = get_next_positive_subdir(dentry, root))) {
+		int flags = how;
+
 		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(dentry);
-		if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
-			expired = NULL;
-		else
-			expired = should_expire(dentry, mnt, timeout, how);
-		if (!expired) {
+		if (ino->flags & AUTOFS_INF_WANT_EXPIRE) {
 			spin_unlock(&sbi->fs_lock);
 			continue;
 		}
+		spin_unlock(&sbi->fs_lock);
+
+		expired = should_expire(dentry, mnt, timeout, flags);
+		if (!expired)
+			continue;
+
+		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(expired);
 		ino->flags |= AUTOFS_INF_WANT_EXPIRE;
 		spin_unlock(&sbi->fs_lock);
 		synchronize_rcu();
-		spin_lock(&sbi->fs_lock);
-		if (should_expire(expired, mnt, timeout, how)) {
-			if (expired != dentry)
-				dput(dentry);
-			goto found;
-		}
 
+		/* Make sure a reference is not taken on found if
+		 * things have changed.
+		 */
+		flags &= ~AUTOFS_EXP_LEAVES;
+		found = should_expire(expired, mnt, timeout, how);
+		if (!found || found != expired)
+			/* Something has changed, continue */
+			goto next;
+
+		if (expired != dentry)
+			dput(dentry);
+
+		spin_lock(&sbi->fs_lock);
+		goto found;
+next:
+		spin_lock(&sbi->fs_lock);
 		ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
+		spin_unlock(&sbi->fs_lock);
 		if (expired != dentry)
 			dput(expired);
-		spin_unlock(&sbi->fs_lock);
 	}
 	return NULL;
 
@@ -483,6 +500,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
+	int state;
 
 	/* Block on any pending expire */
 	if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE))
@@ -490,8 +508,19 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 	if (rcu_walk)
 		return -ECHILD;
 
+retry:
 	spin_lock(&sbi->fs_lock);
-	if (ino->flags & AUTOFS_INF_EXPIRING) {
+	state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING);
+	if (state == AUTOFS_INF_WANT_EXPIRE) {
+		spin_unlock(&sbi->fs_lock);
+		/*
+		 * Possibly being selected for expire, wait until
+		 * it's selected or not.
+		 */
+		schedule_timeout_uninterruptible(HZ/10);
+		goto retry;
+	}
+	if (state & AUTOFS_INF_EXPIRING) {
 		spin_unlock(&sbi->fs_lock);
 
 		pr_debug("waiting for expire %p name=%pd\n", dentry, dentry);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 6bbec5e784cd..14ae4b8e1a3c 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -609,6 +609,9 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 	char *s, *p;
 	char sep;
 
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+		return dget(sb->s_root);
+
 	full_path = cifs_build_path_to_root(vol, cifs_sb,
 					    cifs_sb_master_tcon(cifs_sb));
 	if (full_path == NULL)
@@ -686,26 +689,22 @@ cifs_do_mount(struct file_system_type *fs_type,
 	cifs_sb->mountdata = kstrndup(data, PAGE_SIZE, GFP_KERNEL);
 	if (cifs_sb->mountdata == NULL) {
 		root = ERR_PTR(-ENOMEM);
-		goto out_cifs_sb;
+		goto out_free;
 	}
 
-	if (volume_info->prepath) {
-		cifs_sb->prepath = kstrdup(volume_info->prepath, GFP_KERNEL);
-		if (cifs_sb->prepath == NULL) {
-			root = ERR_PTR(-ENOMEM);
-			goto out_cifs_sb;
-		}
+	rc = cifs_setup_cifs_sb(volume_info, cifs_sb);
+	if (rc) {
+		root = ERR_PTR(rc);
+		goto out_free;
 	}
 
-	cifs_setup_cifs_sb(volume_info, cifs_sb);
-
 	rc = cifs_mount(cifs_sb, volume_info);
 	if (rc) {
 		if (!(flags & MS_SILENT))
 			cifs_dbg(VFS, "cifs_mount failed w/return code = %d\n",
 				 rc);
 		root = ERR_PTR(rc);
-		goto out_mountdata;
+		goto out_free;
 	}
 
 	mnt_data.vol = volume_info;
@@ -735,11 +734,7 @@ cifs_do_mount(struct file_system_type *fs_type,
 		sb->s_flags |= MS_ACTIVE;
 	}
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
-		root = dget(sb->s_root);
-	else
-		root = cifs_get_root(volume_info, sb);
-
+	root = cifs_get_root(volume_info, sb);
 	if (IS_ERR(root))
 		goto out_super;
 
@@ -752,9 +747,9 @@ out:
 	cifs_cleanup_volume_info(volume_info);
 	return root;
 
-out_mountdata:
+out_free:
+	kfree(cifs_sb->prepath);
 	kfree(cifs_sb->mountdata);
-out_cifs_sb:
 	kfree(cifs_sb);
 out_nls:
 	unload_nls(volume_info->local_nls);
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 1243bd326591..95dab43646f0 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -184,7 +184,7 @@ extern int cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 			         unsigned int to_read);
 extern int cifs_read_page_from_socket(struct TCP_Server_Info *server,
 				      struct page *page, unsigned int to_read);
-extern void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
+extern int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 			       struct cifs_sb_info *cifs_sb);
 extern int cifs_match_super(struct super_block *, void *);
 extern void cifs_cleanup_volume_info(struct smb_vol *pvolume_info);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 7ae03283bd61..2e4f4bad8b1e 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2781,6 +2781,24 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data)
 	return 1;
 }
 
+static int
+match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data)
+{
+	struct cifs_sb_info *old = CIFS_SB(sb);
+	struct cifs_sb_info *new = mnt_data->cifs_sb;
+
+	if (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) {
+		if (!(new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH))
+			return 0;
+		/* The prepath should be null terminated strings */
+		if (strcmp(new->prepath, old->prepath))
+			return 0;
+
+		return 1;
+	}
+	return 0;
+}
+
 int
 cifs_match_super(struct super_block *sb, void *data)
 {
@@ -2808,7 +2826,8 @@ cifs_match_super(struct super_block *sb, void *data)
 
 	if (!match_server(tcp_srv, volume_info) ||
 	    !match_session(ses, volume_info) ||
-	    !match_tcon(tcon, volume_info->UNC)) {
+	    !match_tcon(tcon, volume_info->UNC) ||
+	    !match_prepath(sb, mnt_data)) {
 		rc = 0;
 		goto out;
 	}
@@ -3222,7 +3241,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
 	}
 }
 
-void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
+int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 			struct cifs_sb_info *cifs_sb)
 {
 	INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks);
@@ -3316,6 +3335,14 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 
 	if ((pvolume_info->cifs_acl) && (pvolume_info->dynperm))
 		cifs_dbg(VFS, "mount option dynperm ignored if cifsacl mount option supported\n");
+
+	if (pvolume_info->prepath) {
+		cifs_sb->prepath = kstrdup(pvolume_info->prepath, GFP_KERNEL);
+		if (cifs_sb->prepath == NULL)
+			return -ENOMEM;
+	}
+
+	return 0;
 }
 
 static void
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 0f56deb24ce6..c415668c86d4 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -568,7 +568,7 @@ static int ioctl_fsthaw(struct file *filp)
 	return thaw_super(sb);
 }
 
-static long ioctl_file_dedupe_range(struct file *file, void __user *arg)
+static int ioctl_file_dedupe_range(struct file *file, void __user *arg)
 {
 	struct file_dedupe_range __user *argp = arg;
 	struct file_dedupe_range *same = NULL;
@@ -582,6 +582,10 @@ static long ioctl_file_dedupe_range(struct file *file, void __user *arg)
 	}
 
 	size = offsetof(struct file_dedupe_range __user, info[count]);
+	if (size > PAGE_SIZE) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	same = memdup_user(argp, size);
 	if (IS_ERR(same)) {
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 7d620970f2e1..ca699ddc11c1 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -657,7 +657,10 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	if (result <= 0)
 		goto out;
 
-	written = generic_write_sync(iocb, result);
+	result = generic_write_sync(iocb, result);
+	if (result < 0)
+		goto out;
+	written = result;
 	iocb->ki_pos += written;
 
 	/* Return error values */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f5aecaabcb7c..a9dec32ba9ba 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7570,12 +7570,20 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
 	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	trace_nfs4_create_session(clp, status);
 
+	switch (status) {
+	case -NFS4ERR_STALE_CLIENTID:
+	case -NFS4ERR_DELAY:
+	case -ETIMEDOUT:
+	case -EACCES:
+	case -EAGAIN:
+		goto out;
+	};
+
+	clp->cl_seqid++;
 	if (!status) {
 		/* Verify the session's negotiated channel_attrs values */
 		status = nfs4_verify_channel_attrs(&args, &res);
 		/* Increment the clientid slot sequence id */
-		if (clp->cl_seqid == res.seqid)
-			clp->cl_seqid++;
 		if (status)
 			goto out;
 		nfs4_update_session(session, &res);
@@ -8190,10 +8198,13 @@ static void nfs4_layoutreturn_release(void *calldata)
 
 	dprintk("--> %s\n", __func__);
 	spin_lock(&lo->plh_inode->i_lock);
-	pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range,
-			be32_to_cpu(lrp->args.stateid.seqid));
-	if (lrp->res.lrs_present && pnfs_layout_is_valid(lo))
+	if (lrp->res.lrs_present) {
+		pnfs_mark_matching_lsegs_invalid(lo, &freeme,
+				&lrp->args.range,
+				be32_to_cpu(lrp->args.stateid.seqid));
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+	} else
+		pnfs_mark_layout_stateid_invalid(lo, &freeme);
 	pnfs_clear_layoutreturn_waitbit(lo);
 	spin_unlock(&lo->plh_inode->i_lock);
 	nfs4_sequence_free_slot(&lrp->res.seq_res);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 6daf034645c8..2c93a85eda51 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -365,7 +365,8 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
 	/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
 	atomic_dec(&lo->plh_refcount);
 	if (list_empty(&lo->plh_segs)) {
-		set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+		if (atomic_read(&lo->plh_outstanding) == 0)
+			set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
 		clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
 	}
 	rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
@@ -768,17 +769,32 @@ pnfs_destroy_all_layouts(struct nfs_client *clp)
 	pnfs_destroy_layouts_byclid(clp, false);
 }
 
+static void
+pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
+{
+	lo->plh_return_iomode = 0;
+	lo->plh_return_seq = 0;
+	clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+}
+
 /* update lo->plh_stateid with new if is more recent */
 void
 pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
 			bool update_barrier)
 {
 	u32 oldseq, newseq, new_barrier = 0;
-	bool invalid = !pnfs_layout_is_valid(lo);
 
 	oldseq = be32_to_cpu(lo->plh_stateid.seqid);
 	newseq = be32_to_cpu(new->seqid);
-	if (invalid || pnfs_seqid_is_newer(newseq, oldseq)) {
+
+	if (!pnfs_layout_is_valid(lo)) {
+		nfs4_stateid_copy(&lo->plh_stateid, new);
+		lo->plh_barrier = newseq;
+		pnfs_clear_layoutreturn_info(lo);
+		clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+		return;
+	}
+	if (pnfs_seqid_is_newer(newseq, oldseq)) {
 		nfs4_stateid_copy(&lo->plh_stateid, new);
 		/*
 		 * Because of wraparound, we want to keep the barrier
@@ -790,7 +806,7 @@ pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
 		new_barrier = be32_to_cpu(new->seqid);
 	else if (new_barrier == 0)
 		return;
-	if (invalid || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
+	if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
 		lo->plh_barrier = new_barrier;
 }
 
@@ -886,19 +902,14 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
 	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 }
 
-static void
-pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
-{
-	lo->plh_return_iomode = 0;
-	lo->plh_return_seq = 0;
-	clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
-}
-
 static bool
 pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo,
 		nfs4_stateid *stateid,
 		enum pnfs_iomode *iomode)
 {
+	/* Serialise LAYOUTGET/LAYOUTRETURN */
+	if (atomic_read(&lo->plh_outstanding) != 0)
+		return false;
 	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
 		return false;
 	pnfs_get_layout_hdr(lo);
@@ -1798,16 +1809,11 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		 */
 		pnfs_mark_layout_stateid_invalid(lo, &free_me);
 
-		nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
-		lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
+		pnfs_set_layout_stateid(lo, &res->stateid, true);
 	}
 
 	pnfs_get_lseg(lseg);
 	pnfs_layout_insert_lseg(lo, lseg, &free_me);
-	if (!pnfs_layout_is_valid(lo)) {
-		pnfs_clear_layoutreturn_info(lo);
-		clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-	}
 
 
 	if (res->return_on_close)
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index d2f97ecca6a5..e0e5f7c3c99f 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	wait_event(group->fanotify_data.access_waitq, event->response ||
-				atomic_read(&group->fanotify_data.bypass_perm));
-
-	if (!event->response) {	/* bypass_perm set */
-		/*
-		 * Event was canceled because group is being destroyed. Remove
-		 * it from group's event list because we are responsible for
-		 * freeing the permission event.
-		 */
-		fsnotify_remove_event(group, &event->fae.fse);
-		return 0;
-	}
+	wait_event(group->fanotify_data.access_waitq, event->response);
 
 	/* userspace responded, convert to something usable */
 	switch (event->response) {
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 8e8e6bcd1d43..a64313868d3a 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 	struct fanotify_perm_event_info *event, *next;
+	struct fsnotify_event *fsn_event;
 
 	/*
-	 * There may be still new events arriving in the notification queue
-	 * but since userspace cannot use fanotify fd anymore, no event can
-	 * enter or leave access_list by now.
+	 * Stop new events from arriving in the notification queue. since
+	 * userspace cannot use fanotify fd anymore, no event can enter or
+	 * leave access_list by now either.
 	 */
-	spin_lock(&group->fanotify_data.access_lock);
-
-	atomic_inc(&group->fanotify_data.bypass_perm);
+	fsnotify_group_stop_queueing(group);
 
+	/*
+	 * Process all permission events on access_list and notification queue
+	 * and simulate reply from userspace.
+	 */
+	spin_lock(&group->fanotify_data.access_lock);
 	list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
 				 fae.fse.list) {
 		pr_debug("%s: found group=%p event=%p\n", __func__, group,
@@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	spin_unlock(&group->fanotify_data.access_lock);
 
 	/*
-	 * Since bypass_perm is set, newly queued events will not wait for
-	 * access response. Wake up the already sleeping ones now.
-	 * synchronize_srcu() in fsnotify_destroy_group() will wait for all
-	 * processes sleeping in fanotify_handle_event() waiting for access
-	 * response and thus also for all permission events to be freed.
+	 * Destroy all non-permission events. For permission events just
+	 * dequeue them and set the response. They will be freed once the
+	 * response is consumed and fanotify_get_response() returns.
 	 */
+	mutex_lock(&group->notification_mutex);
+	while (!fsnotify_notify_queue_is_empty(group)) {
+		fsn_event = fsnotify_remove_first_event(group);
+		if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS))
+			fsnotify_destroy_event(group, fsn_event);
+		else
+			FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+	}
+	mutex_unlock(&group->notification_mutex);
+
+	/* Response for all permission events it set, wakeup waiters */
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
 
@@ -755,7 +768,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	spin_lock_init(&group->fanotify_data.access_lock);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
-	atomic_set(&group->fanotify_data.bypass_perm, 0);
 #endif
 	switch (flags & FAN_ALL_CLASS_BITS) {
 	case FAN_CLASS_NOTIF:
diff --git a/fs/notify/group.c b/fs/notify/group.c
index 3e2dd85be5dd..b47f7cfdcaa4 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -40,6 +40,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
 }
 
 /*
+ * Stop queueing new events for this group. Once this function returns
+ * fsnotify_add_event() will not add any new events to the group's queue.
+ */
+void fsnotify_group_stop_queueing(struct fsnotify_group *group)
+{
+	mutex_lock(&group->notification_mutex);
+	group->shutdown = true;
+	mutex_unlock(&group->notification_mutex);
+}
+
+/*
  * Trying to get rid of a group. Remove all marks, flush all events and release
  * the group reference.
  * Note that another thread calling fsnotify_clear_marks_by_group() may still
@@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
  */
 void fsnotify_destroy_group(struct fsnotify_group *group)
 {
+	/*
+	 * Stop queueing new events. The code below is careful enough to not
+	 * require this but fanotify needs to stop queuing events even before
+	 * fsnotify_destroy_group() is called and this makes the other callers
+	 * of fsnotify_destroy_group() to see the same behavior.
+	 */
+	fsnotify_group_stop_queueing(group);
+
 	/* clear all inode marks for this group, attach them to destroy_list */
 	fsnotify_detach_group_marks(group);
 
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index a95d8e037aeb..e455e83ceeeb 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -82,7 +82,8 @@ 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,
- * 2 if the queue of events has overflown.
+ * 2 if the event was not queued - either the queue of events has overflown
+ * or the group is shutting down.
  */
 int fsnotify_add_event(struct fsnotify_group *group,
 		       struct fsnotify_event *event,
@@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group,
 
 	mutex_lock(&group->notification_mutex);
 
+	if (group->shutdown) {
+		mutex_unlock(&group->notification_mutex);
+		return 2;
+	}
+
 	if (group->q_len >= group->max_events) {
 		ret = 2;
 		/* Queue overflow event only if it isn't already queued */
@@ -126,21 +132,6 @@ queue:
 }
 
 /*
- * Remove @event from group's notification queue. It is the responsibility of
- * the caller to destroy the event.
- */
-void fsnotify_remove_event(struct fsnotify_group *group,
-			   struct fsnotify_event *event)
-{
-	mutex_lock(&group->notification_mutex);
-	if (!list_empty(&event->list)) {
-		list_del_init(&event->list);
-		group->q_len--;
-	}
-	mutex_unlock(&group->notification_mutex);
-}
-
-/*
  * Remove and return the first event from the notification list.  It is the
  * responsibility of the caller to destroy the obtained event
  */
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 7dabbc31060e..f165f867f332 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5922,7 +5922,6 @@ bail:
 }
 
 static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
-					 handle_t *handle,
 					 struct inode *data_alloc_inode,
 					 struct buffer_head *data_alloc_bh)
 {
@@ -5935,11 +5934,19 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 	struct ocfs2_truncate_log *tl;
 	struct inode *tl_inode = osb->osb_tl_inode;
 	struct buffer_head *tl_bh = osb->osb_tl_bh;
+	handle_t *handle;
 
 	di = (struct ocfs2_dinode *) tl_bh->b_data;
 	tl = &di->id2.i_dealloc;
 	i = le16_to_cpu(tl->tl_used) - 1;
 	while (i >= 0) {
+		handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
+		if (IS_ERR(handle)) {
+			status = PTR_ERR(handle);
+			mlog_errno(status);
+			goto bail;
+		}
+
 		/* Caller has given us at least enough credits to
 		 * update the truncate log dinode */
 		status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh,
@@ -5974,12 +5981,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 			}
 		}
 
-		status = ocfs2_extend_trans(handle,
-				OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
-		if (status < 0) {
-			mlog_errno(status);
-			goto bail;
-		}
+		ocfs2_commit_trans(osb, handle);
 		i--;
 	}
 
@@ -5994,7 +5996,6 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 {
 	int status;
 	unsigned int num_to_flush;
-	handle_t *handle;
 	struct inode *tl_inode = osb->osb_tl_inode;
 	struct inode *data_alloc_inode = NULL;
 	struct buffer_head *tl_bh = osb->osb_tl_bh;
@@ -6038,21 +6039,11 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 		goto out_mutex;
 	}
 
-	handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
-	if (IS_ERR(handle)) {
-		status = PTR_ERR(handle);
-		mlog_errno(status);
-		goto out_unlock;
-	}
-
-	status = ocfs2_replay_truncate_records(osb, handle, data_alloc_inode,
+	status = ocfs2_replay_truncate_records(osb, data_alloc_inode,
 					       data_alloc_bh);
 	if (status < 0)
 		mlog_errno(status);
 
-	ocfs2_commit_trans(osb, handle);
-
-out_unlock:
 	brelse(data_alloc_bh);
 	ocfs2_inode_unlock(data_alloc_inode, 1);
 
@@ -6413,43 +6404,34 @@ static int ocfs2_free_cached_blocks(struct ocfs2_super *osb,
 		goto out_mutex;
 	}
 
-	handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
-	if (IS_ERR(handle)) {
-		ret = PTR_ERR(handle);
-		mlog_errno(ret);
-		goto out_unlock;
-	}
-
 	while (head) {
 		if (head->free_bg)
 			bg_blkno = head->free_bg;
 		else
 			bg_blkno = ocfs2_which_suballoc_group(head->free_blk,
 							      head->free_bit);
+		handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			mlog_errno(ret);
+			goto out_unlock;
+		}
+
 		trace_ocfs2_free_cached_blocks(
 		     (unsigned long long)head->free_blk, head->free_bit);
 
 		ret = ocfs2_free_suballoc_bits(handle, inode, di_bh,
 					       head->free_bit, bg_blkno, 1);
-		if (ret) {
+		if (ret)
 			mlog_errno(ret);
-			goto out_journal;
-		}
 
-		ret = ocfs2_extend_trans(handle, OCFS2_SUBALLOC_FREE);
-		if (ret) {
-			mlog_errno(ret);
-			goto out_journal;
-		}
+		ocfs2_commit_trans(osb, handle);
 
 		tmp = head;
 		head = head->free_next;
 		kfree(tmp);
 	}
 
-out_journal:
-	ocfs2_commit_trans(osb, handle);
-
 out_unlock:
 	ocfs2_inode_unlock(inode, 1);
 	brelse(di_bh);
diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h
index 94b18369b1cc..b95e7df5b76a 100644
--- a/fs/ocfs2/cluster/tcp_internal.h
+++ b/fs/ocfs2/cluster/tcp_internal.h
@@ -44,9 +44,6 @@
  * version here in tcp_internal.h should not need to be bumped for
  * filesystem locking changes.
  *
- * New in version 12
- *	- Negotiate hb timeout when storage is down.
- *
  * New in version 11
  * 	- Negotiation of filesystem locking in the dlm join.
  *
@@ -78,7 +75,7 @@
  * 	- full 64 bit i_size in the metadata lock lvbs
  * 	- introduction of "rw" lock and pushing meta/data locking down
  */
-#define O2NET_PROTOCOL_VERSION 12ULL
+#define O2NET_PROTOCOL_VERSION 11ULL
 struct o2net_handshake {
 	__be64	protocol_version;
 	__be64	connector_id;
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index cdeafb4e7ed6..0bb128659d4b 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -268,7 +268,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 				  struct dlm_lock *lock, int flags, int type)
 {
 	enum dlm_status status;
-	u8 old_owner = res->owner;
 
 	mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type,
 	     lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS);
@@ -335,7 +334,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 
 	spin_lock(&res->spinlock);
 	res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
-	lock->convert_pending = 0;
 	/* if it failed, move it back to granted queue.
 	 * if master returns DLM_NORMAL and then down before sending ast,
 	 * it may have already been moved to granted queue, reset to
@@ -344,12 +342,14 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 		if (status != DLM_NOTQUEUED)
 			dlm_error(status);
 		dlm_revert_pending_convert(res, lock);
-	} else if ((res->state & DLM_LOCK_RES_RECOVERING) ||
-			(old_owner != res->owner)) {
-		mlog(0, "res %.*s is in recovering or has been recovered.\n",
-				res->lockname.len, res->lockname.name);
+	} else if (!lock->convert_pending) {
+		mlog(0, "%s: res %.*s, owner died and lock has been moved back "
+				"to granted list, retry convert.\n",
+				dlm->name, res->lockname.len, res->lockname.name);
 		status = DLM_RECOVERING;
 	}
+
+	lock->convert_pending = 0;
 bail:
 	spin_unlock(&res->spinlock);
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 4e7b0dc22450..0b055bfb8e86 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1506,7 +1506,8 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
 				       u64 start, u64 len)
 {
 	int ret = 0;
-	u64 tmpend, end = start + len;
+	u64 tmpend = 0;
+	u64 end = start + len;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	unsigned int csize = osb->s_clustersize;
 	handle_t *handle;
@@ -1538,18 +1539,31 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
 	}
 
 	/*
-	 * We want to get the byte offset of the end of the 1st cluster.
+	 * If start is on a cluster boundary and end is somewhere in another
+	 * cluster, we have not COWed the cluster starting at start, unless
+	 * end is also within the same cluster. So, in this case, we skip this
+	 * first call to ocfs2_zero_range_for_truncate() truncate and move on
+	 * to the next one.
 	 */
-	tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1));
-	if (tmpend > end)
-		tmpend = end;
+	if ((start & (csize - 1)) != 0) {
+		/*
+		 * We want to get the byte offset of the end of the 1st
+		 * cluster.
+		 */
+		tmpend = (u64)osb->s_clustersize +
+			(start & ~(osb->s_clustersize - 1));
+		if (tmpend > end)
+			tmpend = end;
 
-	trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start,
-						 (unsigned long long)tmpend);
+		trace_ocfs2_zero_partial_clusters_range1(
+			(unsigned long long)start,
+			(unsigned long long)tmpend);
 
-	ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend);
-	if (ret)
-		mlog_errno(ret);
+		ret = ocfs2_zero_range_for_truncate(inode, handle, start,
+						    tmpend);
+		if (ret)
+			mlog_errno(ret);
+	}
 
 	if (tmpend < end) {
 		/*
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index ea47120a85ff..6ad3533940ba 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1199,14 +1199,24 @@ retry:
 			inode_unlock((*ac)->ac_inode);
 
 			ret = ocfs2_try_to_free_truncate_log(osb, bits_wanted);
-			if (ret == 1)
+			if (ret == 1) {
+				iput((*ac)->ac_inode);
+				(*ac)->ac_inode = NULL;
 				goto retry;
+			}
 
 			if (ret < 0)
 				mlog_errno(ret);
 
 			inode_lock((*ac)->ac_inode);
-			ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+			ret = ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+			if (ret < 0) {
+				mlog_errno(ret);
+				inode_unlock((*ac)->ac_inode);
+				iput((*ac)->ac_inode);
+				(*ac)->ac_inode = NULL;
+				goto bail;
+			}
 		}
 		if (status < 0) {
 			if (status != -ENOSPC)
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index a939f5ed7f89..5c89a07e3d7f 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -430,6 +430,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
 static ssize_t
 read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 {
+	char *buf = file->private_data;
 	ssize_t acc = 0;
 	size_t size, tsz;
 	size_t elf_buflen;
@@ -500,23 +501,20 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 			if (clear_user(buffer, tsz))
 				return -EFAULT;
 		} else if (is_vmalloc_or_module_addr((void *)start)) {
-			char * elf_buf;
-
-			elf_buf = kzalloc(tsz, GFP_KERNEL);
-			if (!elf_buf)
-				return -ENOMEM;
-			vread(elf_buf, (char *)start, tsz);
+			vread(buf, (char *)start, tsz);
 			/* we have to zero-fill user buffer even if no read */
-			if (copy_to_user(buffer, elf_buf, tsz)) {
-				kfree(elf_buf);
+			if (copy_to_user(buffer, buf, tsz))
 				return -EFAULT;
-			}
-			kfree(elf_buf);
 		} else {
 			if (kern_addr_valid(start)) {
 				unsigned long n;
 
-				n = copy_to_user(buffer, (char *)start, tsz);
+				/*
+				 * Using bounce buffer to bypass the
+				 * hardened user copy kernel text checks.
+				 */
+				memcpy(buf, (char *) start, tsz);
+				n = copy_to_user(buffer, buf, tsz);
 				/*
 				 * We cannot distinguish between fault on source
 				 * and fault on destination. When this happens
@@ -549,6 +547,11 @@ static int open_kcore(struct inode *inode, struct file *filp)
 {
 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
+
+	filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!filp->private_data)
+		return -ENOMEM;
+
 	if (kcore_need_update)
 		kcore_update_ram();
 	if (i_size_read(inode) != proc_root_kcore->size) {
@@ -559,10 +562,16 @@ static int open_kcore(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static int release_kcore(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
 
 static const struct file_operations proc_kcore_operations = {
 	.read		= read_kcore,
 	.open		= open_kcore,
+	.release	= release_kcore,
 	.llseek		= default_llseek,
 };
 
diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c
index 183a212694bf..12af0490322f 100644
--- a/fs/ramfs/file-mmu.c
+++ b/fs/ramfs/file-mmu.c
@@ -27,9 +27,17 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/ramfs.h>
+#include <linux/sched.h>
 
 #include "internal.h"
 
+static unsigned long ramfs_mmu_get_unmapped_area(struct file *file,
+		unsigned long addr, unsigned long len, unsigned long pgoff,
+		unsigned long flags)
+{
+	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
 const struct file_operations ramfs_file_operations = {
 	.read_iter	= generic_file_read_iter,
 	.write_iter	= generic_file_write_iter,
@@ -38,6 +46,7 @@ const struct file_operations ramfs_file_operations = {
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.llseek		= generic_file_llseek,
+	.get_unmapped_area	= ramfs_mmu_get_unmapped_area,
 };
 
 const struct inode_operations ramfs_file_inode_operations = {