Merge tag 'asoc-v5.9' of https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus

ASoC: Updates for v5.9 The biggest changes here one again come from Mormioto-san who has continued his dilligent work cleaning up long standing issues in the APIs, it's particularly nice to see the transition from digital_mute() to mute_stream() finally completed. There's also been a lot of work on the x86 code again, this time a big focus has been on cleaning up some issues identified by various static tests, and on the Freescale systems. Otherwise the biggest thing has been a lot of driver additions: - Convert users of digital_mute() to mute_stream(). - Simplify I/O helper functions. - Add a helper for getting the RTD from a substream. - Many, many fixes and cleanups to the x86 code. - New drivers for Freescale MQS and i.MX6sx, Intel KeemBay I2S, Maxim MAX98360A and MAX98373 Soundwire, several Mediatek boards, nVidia Tegra 186 and 210, RealTek RL6231, Samsung Midas and Aries boards (some of the first phones I worked on!) and TI J721e EVM.
author: Takashi Iwai <tiwai@suse.de> 2020-08-03 15:41:43 +0300
committer: Takashi Iwai <tiwai@suse.de> 2020-08-03 15:41:43 +0300
commit: 103f528d3bc35d2b6e726a3fffd879e492d191c2 (patch)
tree: 2829604c2386f96e228fac7841e49906f698dfff /fs
parent: 07c9983b567d0ef33aefc063299de95a987e12a8 (diff)
parent: 84569f329f7fcb40b7b1860f273b2909dabf2a2b (diff)
download: linux-103f528d3bc35d2b6e726a3fffd879e492d191c2.tar.xz
113 files changed, 1620 insertions, 805 deletions
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 005921e3b38d..5b79cdceefa0 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -154,10 +154,17 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	cell->name = kmalloc(namelen + 1, GFP_KERNEL);
+	if (!cell->name) {
+		kfree(cell);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	cell->net = net;
 	cell->name_len = namelen;
 	for (i = 0; i < namelen; i++)
 		cell->name[i] = tolower(name[i]);
+	cell->name[i] = 0;
 
 	atomic_set(&cell->usage, 2);
 	INIT_WORK(&cell->manager, afs_manage_cell);
@@ -207,6 +214,7 @@ parse_failed:
 	if (ret == -EINVAL)
 		printk(KERN_ERR "kAFS: bad VL server IP address\n");
 error:
+	kfree(cell->name);
 	kfree(cell);
 	_leave(" = %d", ret);
 	return ERR_PTR(ret);
@@ -489,6 +497,7 @@ static void afs_cell_destroy(struct rcu_head *rcu)
 	afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers));
 	afs_put_cell(cell->net, cell->alias_of);
 	key_put(cell->anonymous_key);
+	kfree(cell->name);
 	kfree(cell);
 
 	_leave(" [destroyed]");
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index aa1d34141ea3..96757f3abd74 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -648,7 +648,7 @@ static void afs_do_lookup_success(struct afs_operation *op)
 			vp = &op->file[0];
 			abort_code = vp->scb.status.abort_code;
 			if (abort_code != 0) {
-				op->abort_code = abort_code;
+				op->ac.abort_code = abort_code;
 				op->error = afs_abort_to_error(abort_code);
 			}
 			break;
@@ -696,10 +696,11 @@ static const struct afs_operation_ops afs_inline_bulk_status_operation = {
 	.success	= afs_do_lookup_success,
 };
 
-static const struct afs_operation_ops afs_fetch_status_operation = {
+static const struct afs_operation_ops afs_lookup_fetch_status_operation = {
 	.issue_afs_rpc	= afs_fs_fetch_status,
 	.issue_yfs_rpc	= yfs_fs_fetch_status,
 	.success	= afs_do_lookup_success,
+	.aborted	= afs_check_for_remote_deletion,
 };
 
 /*
@@ -844,7 +845,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 		 * to FS.FetchStatus for op->file[1].
 		 */
 		op->fetch_status.which = 1;
-		op->ops = &afs_fetch_status_operation;
+		op->ops = &afs_lookup_fetch_status_operation;
 		afs_begin_vnode_operation(op);
 		afs_wait_for_operation(op);
 	}
@@ -1236,6 +1237,17 @@ void afs_d_release(struct dentry *dentry)
 	_enter("%pd", dentry);
 }
 
+void afs_check_for_remote_deletion(struct afs_operation *op)
+{
+	struct afs_vnode *vnode = op->file[0].vnode;
+
+	switch (op->ac.abort_code) {
+	case VNOVNODE:
+		set_bit(AFS_VNODE_DELETED, &vnode->flags);
+		afs_break_callback(vnode, afs_cb_break_for_deleted);
+	}
+}
+
 /*
  * Create a new inode for create/mkdir/symlink
  */
@@ -1268,7 +1280,7 @@ static void afs_vnode_new_inode(struct afs_operation *op)
 static void afs_create_success(struct afs_operation *op)
 {
 	_enter("op=%08x", op->debug_id);
-	afs_check_for_remote_deletion(op, op->file[0].vnode);
+	op->ctime = op->file[0].scb.status.mtime_client;
 	afs_vnode_commit_status(op, &op->file[0]);
 	afs_update_dentry_version(op, &op->file[0], op->dentry);
 	afs_vnode_new_inode(op);
@@ -1302,6 +1314,7 @@ static const struct afs_operation_ops afs_mkdir_operation = {
 	.issue_afs_rpc	= afs_fs_make_dir,
 	.issue_yfs_rpc	= yfs_fs_make_dir,
 	.success	= afs_create_success,
+	.aborted	= afs_check_for_remote_deletion,
 	.edit_dir	= afs_create_edit_dir,
 	.put		= afs_create_put,
 };
@@ -1325,6 +1338,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	afs_op_set_vnode(op, 0, dvnode);
 	op->file[0].dv_delta = 1;
+	op->file[0].update_ctime = true;
 	op->dentry	= dentry;
 	op->create.mode	= S_IFDIR | mode;
 	op->create.reason = afs_edit_dir_for_mkdir;
@@ -1350,7 +1364,7 @@ static void afs_dir_remove_subdir(struct dentry *dentry)
 static void afs_rmdir_success(struct afs_operation *op)
 {
 	_enter("op=%08x", op->debug_id);
-	afs_check_for_remote_deletion(op, op->file[0].vnode);
+	op->ctime = op->file[0].scb.status.mtime_client;
 	afs_vnode_commit_status(op, &op->file[0]);
 	afs_update_dentry_version(op, &op->file[0], op->dentry);
 }
@@ -1382,6 +1396,7 @@ static const struct afs_operation_ops afs_rmdir_operation = {
 	.issue_afs_rpc	= afs_fs_remove_dir,
 	.issue_yfs_rpc	= yfs_fs_remove_dir,
 	.success	= afs_rmdir_success,
+	.aborted	= afs_check_for_remote_deletion,
 	.edit_dir	= afs_rmdir_edit_dir,
 	.put		= afs_rmdir_put,
 };
@@ -1404,6 +1419,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	afs_op_set_vnode(op, 0, dvnode);
 	op->file[0].dv_delta = 1;
+	op->file[0].update_ctime = true;
 
 	op->dentry	= dentry;
 	op->ops		= &afs_rmdir_operation;
@@ -1479,7 +1495,8 @@ static void afs_dir_remove_link(struct afs_operation *op)
 static void afs_unlink_success(struct afs_operation *op)
 {
 	_enter("op=%08x", op->debug_id);
-	afs_check_for_remote_deletion(op, op->file[0].vnode);
+	op->ctime = op->file[0].scb.status.mtime_client;
+	afs_check_dir_conflict(op, &op->file[0]);
 	afs_vnode_commit_status(op, &op->file[0]);
 	afs_vnode_commit_status(op, &op->file[1]);
 	afs_update_dentry_version(op, &op->file[0], op->dentry);
@@ -1511,6 +1528,7 @@ static const struct afs_operation_ops afs_unlink_operation = {
 	.issue_afs_rpc	= afs_fs_remove_file,
 	.issue_yfs_rpc	= yfs_fs_remove_file,
 	.success	= afs_unlink_success,
+	.aborted	= afs_check_for_remote_deletion,
 	.edit_dir	= afs_unlink_edit_dir,
 	.put		= afs_unlink_put,
 };
@@ -1537,6 +1555,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
 
 	afs_op_set_vnode(op, 0, dvnode);
 	op->file[0].dv_delta = 1;
+	op->file[0].update_ctime = true;
 
 	/* Try to make sure we have a callback promise on the victim. */
 	ret = afs_validate(vnode, op->key);
@@ -1561,9 +1580,25 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
 	spin_unlock(&dentry->d_lock);
 
 	op->file[1].vnode = vnode;
+	op->file[1].update_ctime = true;
+	op->file[1].op_unlinked = true;
 	op->dentry	= dentry;
 	op->ops		= &afs_unlink_operation;
-	return afs_do_sync_operation(op);
+	afs_begin_vnode_operation(op);
+	afs_wait_for_operation(op);
+
+	/* If there was a conflict with a third party, check the status of the
+	 * unlinked vnode.
+	 */
+	if (op->error == 0 && (op->flags & AFS_OPERATION_DIR_CONFLICT)) {
+		op->file[1].update_ctime = false;
+		op->fetch_status.which = 1;
+		op->ops = &afs_fetch_status_operation;
+		afs_begin_vnode_operation(op);
+		afs_wait_for_operation(op);
+	}
+
+	return afs_put_operation(op);
 
 error:
 	return afs_put_operation(op);
@@ -1573,6 +1608,7 @@ static const struct afs_operation_ops afs_create_operation = {
 	.issue_afs_rpc	= afs_fs_create_file,
 	.issue_yfs_rpc	= yfs_fs_create_file,
 	.success	= afs_create_success,
+	.aborted	= afs_check_for_remote_deletion,
 	.edit_dir	= afs_create_edit_dir,
 	.put		= afs_create_put,
 };
@@ -1601,6 +1637,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	afs_op_set_vnode(op, 0, dvnode);
 	op->file[0].dv_delta = 1;
+	op->file[0].update_ctime = true;
 
 	op->dentry	= dentry;
 	op->create.mode	= S_IFREG | mode;
@@ -1620,6 +1657,7 @@ static void afs_link_success(struct afs_operation *op)
 	struct afs_vnode_param *vp = &op->file[1];
 
 	_enter("op=%08x", op->debug_id);
+	op->ctime = dvp->scb.status.mtime_client;
 	afs_vnode_commit_status(op, dvp);
 	afs_vnode_commit_status(op, vp);
 	afs_update_dentry_version(op, dvp, op->dentry);
@@ -1640,6 +1678,7 @@ static const struct afs_operation_ops afs_link_operation = {
 	.issue_afs_rpc	= afs_fs_link,
 	.issue_yfs_rpc	= yfs_fs_link,
 	.success	= afs_link_success,
+	.aborted	= afs_check_for_remote_deletion,
 	.edit_dir	= afs_create_edit_dir,
 	.put		= afs_link_put,
 };
@@ -1672,6 +1711,8 @@ static int afs_link(struct dentry *from, struct inode *dir,
 	afs_op_set_vnode(op, 0, dvnode);
 	afs_op_set_vnode(op, 1, vnode);
 	op->file[0].dv_delta = 1;
+	op->file[0].update_ctime = true;
+	op->file[1].update_ctime = true;
 
 	op->dentry		= dentry;
 	op->dentry_2		= from;
@@ -1689,6 +1730,7 @@ static const struct afs_operation_ops afs_symlink_operation = {
 	.issue_afs_rpc	= afs_fs_symlink,
 	.issue_yfs_rpc	= yfs_fs_symlink,
 	.success	= afs_create_success,
+	.aborted	= afs_check_for_remote_deletion,
 	.edit_dir	= afs_create_edit_dir,
 	.put		= afs_create_put,
 };
@@ -1740,9 +1782,13 @@ static void afs_rename_success(struct afs_operation *op)
 {
 	_enter("op=%08x", op->debug_id);
 
+	op->ctime = op->file[0].scb.status.mtime_client;
+	afs_check_dir_conflict(op, &op->file[1]);
 	afs_vnode_commit_status(op, &op->file[0]);
-	if (op->file[1].vnode != op->file[0].vnode)
+	if (op->file[1].vnode != op->file[0].vnode) {
+		op->ctime = op->file[1].scb.status.mtime_client;
 		afs_vnode_commit_status(op, &op->file[1]);
+	}
 }
 
 static void afs_rename_edit_dir(struct afs_operation *op)
@@ -1860,6 +1906,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	afs_op_set_vnode(op, 1, new_dvnode); /* May be same as orig_dvnode */
 	op->file[0].dv_delta = 1;
 	op->file[1].dv_delta = 1;
+	op->file[0].update_ctime = true;
+	op->file[1].update_ctime = true;
 
 	op->dentry		= old_dentry;
 	op->dentry_2		= new_dentry;
diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c
index b14e3d9a25e2..04f75a44f243 100644
--- a/fs/afs/dir_silly.c
+++ b/fs/afs/dir_silly.c
@@ -16,6 +16,7 @@ static void afs_silly_rename_success(struct afs_operation *op)
 {
 	_enter("op=%08x", op->debug_id);
 
+	afs_check_dir_conflict(op, &op->file[0]);
 	afs_vnode_commit_status(op, &op->file[0]);
 }
 
@@ -69,6 +70,11 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode
 		return PTR_ERR(op);
 
 	afs_op_set_vnode(op, 0, dvnode);
+	afs_op_set_vnode(op, 1, dvnode);
+	op->file[0].dv_delta = 1;
+	op->file[1].dv_delta = 1;
+	op->file[0].update_ctime = true;
+	op->file[1].update_ctime = true;
 
 	op->dentry		= old;
 	op->dentry_2		= new;
@@ -129,6 +135,7 @@ int afs_sillyrename(struct afs_vnode *dvnode, struct afs_vnode *vnode,
 	switch (ret) {
 	case 0:
 		/* The rename succeeded. */
+		set_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags);
 		d_move(dentry, sdentry);
 		break;
 	case -ERESTARTSYS:
@@ -148,19 +155,11 @@ out:
 
 static void afs_silly_unlink_success(struct afs_operation *op)
 {
-	struct afs_vnode *vnode = op->file[1].vnode;
-
 	_enter("op=%08x", op->debug_id);
-	afs_check_for_remote_deletion(op, op->file[0].vnode);
+	afs_check_dir_conflict(op, &op->file[0]);
 	afs_vnode_commit_status(op, &op->file[0]);
 	afs_vnode_commit_status(op, &op->file[1]);
 	afs_update_dentry_version(op, &op->file[0], op->dentry);
-
-	drop_nlink(&vnode->vfs_inode);
-	if (vnode->vfs_inode.i_nlink == 0) {
-		set_bit(AFS_VNODE_DELETED, &vnode->flags);
-		clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
-	}
 }
 
 static void afs_silly_unlink_edit_dir(struct afs_operation *op)
@@ -181,6 +180,7 @@ static const struct afs_operation_ops afs_silly_unlink_operation = {
 	.issue_afs_rpc	= afs_fs_remove_file,
 	.issue_yfs_rpc	= yfs_fs_remove_file,
 	.success	= afs_silly_unlink_success,
+	.aborted	= afs_check_for_remote_deletion,
 	.edit_dir	= afs_silly_unlink_edit_dir,
 };
 
@@ -200,12 +200,30 @@ static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode
 
 	afs_op_set_vnode(op, 0, dvnode);
 	afs_op_set_vnode(op, 1, vnode);
+	op->file[0].dv_delta = 1;
+	op->file[0].update_ctime = true;
+	op->file[1].op_unlinked = true;
+	op->file[1].update_ctime = true;
 
 	op->dentry	= dentry;
 	op->ops		= &afs_silly_unlink_operation;
 
 	trace_afs_silly_rename(vnode, true);
-	return afs_do_sync_operation(op);
+	afs_begin_vnode_operation(op);
+	afs_wait_for_operation(op);
+
+	/* If there was a conflict with a third party, check the status of the
+	 * unlinked vnode.
+	 */
+	if (op->error == 0 && (op->flags & AFS_OPERATION_DIR_CONFLICT)) {
+		op->file[1].update_ctime = false;
+		op->fetch_status.which = 1;
+		op->ops = &afs_fetch_status_operation;
+		afs_begin_vnode_operation(op);
+		afs_wait_for_operation(op);
+	}
+
+	return afs_put_operation(op);
 }
 
 /*
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 506c47471b42..6f6ed1605cfe 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -225,7 +225,6 @@ static void afs_fetch_data_success(struct afs_operation *op)
 	struct afs_vnode *vnode = op->file[0].vnode;
 
 	_enter("op=%08x", op->debug_id);
-	afs_check_for_remote_deletion(op, vnode);
 	afs_vnode_commit_status(op, &op->file[0]);
 	afs_stat_v(vnode, n_fetches);
 	atomic_long_add(op->fetch.req->actual_len, &op->net->n_fetch_bytes);
@@ -240,6 +239,7 @@ static const struct afs_operation_ops afs_fetch_data_operation = {
 	.issue_afs_rpc	= afs_fs_fetch_data,
 	.issue_yfs_rpc	= yfs_fs_fetch_data,
 	.success	= afs_fetch_data_success,
+	.aborted	= afs_check_for_remote_deletion,
 	.put		= afs_fetch_data_put,
 };
 
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 71eea2a908c7..ffb8575345ca 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -175,10 +175,7 @@ static void afs_kill_lockers_enoent(struct afs_vnode *vnode)
 
 static void afs_lock_success(struct afs_operation *op)
 {
-	struct afs_vnode *vnode = op->file[0].vnode;
-
 	_enter("op=%08x", op->debug_id);
-	afs_check_for_remote_deletion(op, vnode);
 	afs_vnode_commit_status(op, &op->file[0]);
 }
 
@@ -186,6 +183,7 @@ static const struct afs_operation_ops afs_set_lock_operation = {
 	.issue_afs_rpc	= afs_fs_set_lock,
 	.issue_yfs_rpc	= yfs_fs_set_lock,
 	.success	= afs_lock_success,
+	.aborted	= afs_check_for_remote_deletion,
 };
 
 /*
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index 2d2dff5688a4..24fd163c6323 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -71,7 +71,7 @@ static bool afs_get_io_locks(struct afs_operation *op)
 		swap(vnode, vnode2);
 
 	if (mutex_lock_interruptible(&vnode->io_lock) < 0) {
-		op->error = -EINTR;
+		op->error = -ERESTARTSYS;
 		op->flags |= AFS_OPERATION_STOP;
 		_leave(" = f [I 0]");
 		return false;
@@ -80,7 +80,7 @@ static bool afs_get_io_locks(struct afs_operation *op)
 
 	if (vnode2) {
 		if (mutex_lock_interruptible_nested(&vnode2->io_lock, 1) < 0) {
-			op->error = -EINTR;
+			op->error = -ERESTARTSYS;
 			op->flags |= AFS_OPERATION_STOP;
 			mutex_unlock(&vnode->io_lock);
 			op->flags &= ~AFS_OPERATION_LOCK_0;
@@ -187,9 +187,17 @@ void afs_wait_for_operation(struct afs_operation *op)
 		op->error = afs_wait_for_call_to_complete(op->call, &op->ac);
 	}
 
-	if (op->error == 0) {
+	switch (op->error) {
+	case 0:
 		_debug("success");
 		op->ops->success(op);
+		break;
+	case -ECONNABORTED:
+		if (op->ops->aborted)
+			op->ops->aborted(op);
+		break;
+	default:
+		break;
 	}
 
 	afs_end_vnode_operation(op);
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index b34f74b0f319..5d9ef517cf81 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -314,7 +314,7 @@ void afs_fs_probe_timer(struct timer_list *timer)
 {
 	struct afs_net *net = container_of(timer, struct afs_net, fs_probe_timer);
 
-	if (!queue_work(afs_wq, &net->fs_prober))
+	if (!net->live || !queue_work(afs_wq, &net->fs_prober))
 		afs_dec_servers_outstanding(net);
 }
 
@@ -458,3 +458,12 @@ dont_wait:
 		return -ETIME;
 	return -EDESTADDRREQ;
 }
+
+/*
+ * Clean up the probing when the namespace is killed off.
+ */
+void afs_fs_probe_cleanup(struct afs_net *net)
+{
+	if (del_timer_sync(&net->fs_probe_timer))
+		afs_dec_servers_outstanding(net);
+}
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index cd0a0060950b..1d13d2e882ad 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -165,9 +165,11 @@ static void afs_apply_status(struct afs_operation *op,
 {
 	struct afs_file_status *status = &vp->scb.status;
 	struct afs_vnode *vnode = vp->vnode;
+	struct inode *inode = &vnode->vfs_inode;
 	struct timespec64 t;
 	umode_t mode;
 	bool data_changed = false;
+	bool change_size = vp->set_size;
 
 	_enter("{%llx:%llu.%u} %s",
 	       vp->fid.vid, vp->fid.vnode, vp->fid.unique,
@@ -186,25 +188,25 @@ static void afs_apply_status(struct afs_operation *op,
 	}
 
 	if (status->nlink != vnode->status.nlink)
-		set_nlink(&vnode->vfs_inode, status->nlink);
+		set_nlink(inode, status->nlink);
 
 	if (status->owner != vnode->status.owner)
-		vnode->vfs_inode.i_uid = make_kuid(&init_user_ns, status->owner);
+		inode->i_uid = make_kuid(&init_user_ns, status->owner);
 
 	if (status->group != vnode->status.group)
-		vnode->vfs_inode.i_gid = make_kgid(&init_user_ns, status->group);
+		inode->i_gid = make_kgid(&init_user_ns, status->group);
 
 	if (status->mode != vnode->status.mode) {
-		mode = vnode->vfs_inode.i_mode;
+		mode = inode->i_mode;
 		mode &= ~S_IALLUGO;
 		mode |= status->mode;
-		WRITE_ONCE(vnode->vfs_inode.i_mode, mode);
+		WRITE_ONCE(inode->i_mode, mode);
 	}
 
 	t = status->mtime_client;
-	vnode->vfs_inode.i_ctime = t;
-	vnode->vfs_inode.i_mtime = t;
-	vnode->vfs_inode.i_atime = t;
+	inode->i_mtime = t;
+	if (vp->update_ctime)
+		inode->i_ctime = op->ctime;
 
 	if (vnode->status.data_version != status->data_version)
 		data_changed = true;
@@ -226,6 +228,7 @@ static void afs_apply_status(struct afs_operation *op,
 		} else {
 			set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags);
 		}
+		change_size = true;
 	} else if (vnode->status.type == AFS_FTYPE_DIR) {
 		/* Expected directory change is handled elsewhere so
 		 * that we can locally edit the directory and save on a
@@ -233,11 +236,22 @@ static void afs_apply_status(struct afs_operation *op,
 		 */
 		if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
 			data_changed = false;
+		change_size = true;
 	}
 
 	if (data_changed) {
-		inode_set_iversion_raw(&vnode->vfs_inode, status->data_version);
-		afs_set_i_size(vnode, status->size);
+		inode_set_iversion_raw(inode, status->data_version);
+
+		/* Only update the size if the data version jumped.  If the
+		 * file is being modified locally, then we might have our own
+		 * idea of what the size should be that's not the same as
+		 * what's on the server.
+		 */
+		if (change_size) {
+			afs_set_i_size(vnode, status->size);
+			inode->i_ctime = t;
+			inode->i_atime = t;
+		}
 	}
 }
 
@@ -267,32 +281,39 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v
 
 	_enter("");
 
-	ASSERTCMP(op->error, ==, 0);
-
 	write_seqlock(&vnode->cb_lock);
 
 	if (vp->scb.have_error) {
+		/* A YFS server will return this from RemoveFile2 and AFS and
+		 * YFS will return this from InlineBulkStatus.
+		 */
 		if (vp->scb.status.abort_code == VNOVNODE) {
 			set_bit(AFS_VNODE_DELETED, &vnode->flags);
 			clear_nlink(&vnode->vfs_inode);
 			__afs_break_callback(vnode, afs_cb_break_for_deleted);
+			op->flags &= ~AFS_OPERATION_DIR_CONFLICT;
 		}
-	} else {
-		if (vp->scb.have_status)
-			afs_apply_status(op, vp);
+	} else if (vp->scb.have_status) {
+		afs_apply_status(op, vp);
 		if (vp->scb.have_cb)
 			afs_apply_callback(op, vp);
+	} else if (vp->op_unlinked && !(op->flags & AFS_OPERATION_DIR_CONFLICT)) {
+		drop_nlink(&vnode->vfs_inode);
+		if (vnode->vfs_inode.i_nlink == 0) {
+			set_bit(AFS_VNODE_DELETED, &vnode->flags);
+			__afs_break_callback(vnode, afs_cb_break_for_deleted);
+		}
 	}
 
 	write_sequnlock(&vnode->cb_lock);
 
-	if (op->error == 0 && vp->scb.have_status)
+	if (vp->scb.have_status)
 		afs_cache_permit(vnode, op->key, vp->cb_break_before, &vp->scb);
 }
 
 static void afs_fetch_status_success(struct afs_operation *op)
 {
-	struct afs_vnode_param *vp = &op->file[0];
+	struct afs_vnode_param *vp = &op->file[op->fetch_status.which];
 	struct afs_vnode *vnode = vp->vnode;
 	int ret;
 
@@ -306,10 +327,11 @@ static void afs_fetch_status_success(struct afs_operation *op)
 	}
 }
 
-static const struct afs_operation_ops afs_fetch_status_operation = {
+const struct afs_operation_ops afs_fetch_status_operation = {
 	.issue_afs_rpc	= afs_fs_fetch_status,
 	.issue_yfs_rpc	= yfs_fs_fetch_status,
 	.success	= afs_fetch_status_success,
+	.aborted	= afs_check_for_remote_deletion,
 };
 
 /*
@@ -716,6 +738,9 @@ int afs_getattr(const struct path *path, struct kstat *stat,
 	do {
 		read_seqbegin_or_lock(&vnode->cb_lock, &seq);
 		generic_fillattr(inode, stat);
+		if (test_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags) &&
+		    stat->nlink > 0)
+			stat->nlink -= 1;
 	} while (need_seqretry(&vnode->cb_lock, seq));
 
 	done_seqretry(&vnode->cb_lock, seq);
@@ -785,7 +810,15 @@ void afs_evict_inode(struct inode *inode)
 
 static void afs_setattr_success(struct afs_operation *op)
 {
+	struct inode *inode = &op->file[0].vnode->vfs_inode;
+
 	afs_vnode_commit_status(op, &op->file[0]);
+	if (op->setattr.attr->ia_valid & ATTR_SIZE) {
+		loff_t i_size = inode->i_size, size = op->setattr.attr->ia_size;
+		if (size > i_size)
+			pagecache_isize_extended(inode, i_size, size);
+		truncate_pagecache(inode, size);
+	}
 }
 
 static const struct afs_operation_ops afs_setattr_operation = {
@@ -801,17 +834,31 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct afs_operation *op;
 	struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
+	int ret;
 
 	_enter("{%llx:%llu},{n=%pd},%x",
 	       vnode->fid.vid, vnode->fid.vnode, dentry,
 	       attr->ia_valid);
 
 	if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID |
-				ATTR_MTIME))) {
+				ATTR_MTIME | ATTR_MTIME_SET | ATTR_TIMES_SET |
+				ATTR_TOUCH))) {
 		_leave(" = 0 [unsupported]");
 		return 0;
 	}
 
+	if (attr->ia_valid & ATTR_SIZE) {
+		if (!S_ISREG(vnode->vfs_inode.i_mode))
+			return -EISDIR;
+
+		ret = inode_newsize_ok(&vnode->vfs_inode, attr->ia_size);
+		if (ret)
+			return ret;
+
+		if (attr->ia_size == i_size_read(&vnode->vfs_inode))
+			attr->ia_valid &= ~ATTR_SIZE;
+	}
+
 	/* flush any dirty data outstanding on a regular file */
 	if (S_ISREG(vnode->vfs_inode.i_mode))
 		filemap_write_and_wait(vnode->vfs_inode.i_mapping);
@@ -825,8 +872,12 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr)
 	afs_op_set_vnode(op, 0, vnode);
 	op->setattr.attr = attr;
 
-	if (attr->ia_valid & ATTR_SIZE)
+	if (attr->ia_valid & ATTR_SIZE) {
 		op->file[0].dv_delta = 1;
+		op->file[0].set_size = true;
+	}
+	op->ctime = attr->ia_ctime;
+	op->file[0].update_ctime = 1;
 
 	op->ops = &afs_setattr_operation;
 	return afs_do_sync_operation(op);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 0c9806ef2a19..792ac711985e 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -388,7 +388,7 @@ struct afs_cell {
 	struct afs_vlserver_list __rcu *vl_servers;
 
 	u8			name_len;	/* Length of name */
-	char			name[64 + 1];	/* Cell name, case-flattened and NUL-padded */
+	char			*name;		/* Cell name, case-flattened and NUL-padded */
 };
 
 /*
@@ -634,6 +634,7 @@ struct afs_vnode {
 #define AFS_VNODE_AUTOCELL	6		/* set if Vnode is an auto mount point */
 #define AFS_VNODE_PSEUDODIR	7 		/* set if Vnode is a pseudo directory */
 #define AFS_VNODE_NEW_CONTENT	8		/* Set if file has new content (create/trunc-0) */
+#define AFS_VNODE_SILLY_DELETED	9		/* Set if file has been silly-deleted */
 
 	struct list_head	wb_keys;	/* List of keys available for writeback */
 	struct list_head	pending_locks;	/* locks waiting to be granted */
@@ -744,8 +745,11 @@ struct afs_vnode_param {
 	afs_dataversion_t	dv_before;	/* Data version before the call */
 	unsigned int		cb_break_before; /* cb_break + cb_s_break before the call */
 	u8			dv_delta;	/* Expected change in data version */
-	bool			put_vnode;	/* T if we have a ref on the vnode */
-	bool			need_io_lock;	/* T if we need the I/O lock on this */
+	bool			put_vnode:1;	/* T if we have a ref on the vnode */
+	bool			need_io_lock:1;	/* T if we need the I/O lock on this */
+	bool			update_ctime:1;	/* Need to update the ctime */
+	bool			set_size:1;	/* Must update i_size */
+	bool			op_unlinked:1;	/* True if file was unlinked by op */
 };
 
 /*
@@ -766,9 +770,9 @@ struct afs_operation {
 	struct dentry		*dentry;	/* Dentry to be altered */
 	struct dentry		*dentry_2;	/* Second dentry to be altered */
 	struct timespec64	mtime;		/* Modification time to record */
+	struct timespec64	ctime;		/* Change time to set */
 	short			nr_files;	/* Number of entries in file[], more_files */
 	short			error;
-	unsigned int		abort_code;
 	unsigned int		debug_id;
 
 	unsigned int		cb_v_break;	/* Volume break counter before op */
@@ -837,6 +841,7 @@ struct afs_operation {
 #define AFS_OPERATION_LOCK_1		0x0200	/* Set if have io_lock on file[1] */
 #define AFS_OPERATION_TRIED_ALL		0x0400	/* Set if we've tried all the fileservers */
 #define AFS_OPERATION_RETRY_SERVER	0x0800	/* Set if we should retry the current server */
+#define AFS_OPERATION_DIR_CONFLICT	0x1000	/* Set if we detected a 3rd-party dir change */
 };
 
 /*
@@ -932,6 +937,7 @@ extern const struct address_space_operations afs_dir_aops;
 extern const struct dentry_operations afs_fs_dentry_operations;
 
 extern void afs_d_release(struct dentry *);
+extern void afs_check_for_remote_deletion(struct afs_operation *);
 
 /*
  * dir_edit.c
@@ -1059,10 +1065,13 @@ extern int afs_wait_for_fs_probes(struct afs_server_list *, unsigned long);
 extern void afs_probe_fileserver(struct afs_net *, struct afs_server *);
 extern void afs_fs_probe_dispatcher(struct work_struct *);
 extern int afs_wait_for_one_fs_probe(struct afs_server *, bool);
+extern void afs_fs_probe_cleanup(struct afs_net *);
 
 /*
  * inode.c
  */
+extern const struct afs_operation_ops afs_fetch_status_operation;
+
 extern void afs_vnode_commit_status(struct afs_operation *, struct afs_vnode_param *);
 extern int afs_fetch_status(struct afs_vnode *, struct key *, bool, afs_access_t *);
 extern int afs_ilookup5_test_by_fid(struct inode *, void *);
@@ -1435,7 +1444,6 @@ extern ssize_t afs_listxattr(struct dentry *, char *, size_t);
 /*
  * yfsclient.c
  */
-extern void yfs_fs_fetch_file_status(struct afs_operation *);
 extern void yfs_fs_fetch_data(struct afs_operation *);
 extern void yfs_fs_create_file(struct afs_operation *);
 extern void yfs_fs_make_dir(struct afs_operation *);
@@ -1481,15 +1489,6 @@ static inline struct inode *AFS_VNODE_TO_I(struct afs_vnode *vnode)
 	return &vnode->vfs_inode;
 }
 
-static inline void afs_check_for_remote_deletion(struct afs_operation *op,
-						 struct afs_vnode *vnode)
-{
-	if (op->error == -ENOENT) {
-		set_bit(AFS_VNODE_DELETED, &vnode->flags);
-		afs_break_callback(vnode, afs_cb_break_for_deleted);
-	}
-}
-
 /*
  * Note that a dentry got changed.  We need to set d_fsdata to the data version
  * number derived from the result of the operation.  It doesn't matter if
@@ -1504,6 +1503,18 @@ static inline void afs_update_dentry_version(struct afs_operation *op,
 			(void *)(unsigned long)dir_vp->scb.status.data_version;
 }
 
+/*
+ * Check for a conflicting operation on a directory that we just unlinked from.
+ * If someone managed to sneak a link or an unlink in on the file we just
+ * unlinked, we won't be able to trust nlink on an AFS file (but not YFS).
+ */
+static inline void afs_check_dir_conflict(struct afs_operation *op,
+					  struct afs_vnode_param *dvp)
+{
+	if (dvp->dv_before + dvp->dv_delta != dvp->scb.status.data_version)
+		op->flags |= AFS_OPERATION_DIR_CONFLICT;
+}
+
 static inline int afs_io_error(struct afs_call *call, enum afs_io_error where)
 {
 	trace_afs_io_error(call->debug_id, -EIO, where);
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 9c79c91e8005..31b472f7c734 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -100,6 +100,7 @@ static int __net_init afs_net_init(struct net *net_ns)
 	timer_setup(&net->fs_timer, afs_servers_timer, 0);
 	INIT_WORK(&net->fs_prober, afs_fs_probe_dispatcher);
 	timer_setup(&net->fs_probe_timer, afs_fs_probe_timer, 0);
+	atomic_set(&net->servers_outstanding, 1);
 
 	ret = -ENOMEM;
 	sysnames = kzalloc(sizeof(*sysnames), GFP_KERNEL);
@@ -130,6 +131,7 @@ static int __net_init afs_net_init(struct net *net_ns)
 
 error_open_socket:
 	net->live = false;
+	afs_fs_probe_cleanup(net);
 	afs_cell_purge(net);
 	afs_purge_servers(net);
 error_cell_init:
@@ -150,6 +152,7 @@ static void __net_exit afs_net_exit(struct net *net_ns)
 	struct afs_net *net = afs_net(net_ns);
 
 	net->live = false;
+	afs_fs_probe_cleanup(net);
 	afs_cell_purge(net);
 	afs_purge_servers(net);
 	afs_close_socket(net);
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 52b19e9c1535..5334f1bd2bca 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -83,6 +83,7 @@ int afs_abort_to_error(u32 abort_code)
 	case UAENOLCK:			return -ENOLCK;
 	case UAENOTEMPTY:		return -ENOTEMPTY;
 	case UAELOOP:			return -ELOOP;
+	case UAEOVERFLOW:		return -EOVERFLOW;
 	case UAENOMEDIUM:		return -ENOMEDIUM;
 	case UAEDQUOT:			return -EDQUOT;
 
diff --git a/fs/afs/server.c b/fs/afs/server.c
index 039e3488511c..e82e452e2612 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -605,11 +605,12 @@ void afs_purge_servers(struct afs_net *net)
 	_enter("");
 
 	if (del_timer_sync(&net->fs_timer))
-		atomic_dec(&net->servers_outstanding);
+		afs_dec_servers_outstanding(net);
 
 	afs_queue_server_manager(net);
 
 	_debug("wait");
+	atomic_dec(&net->servers_outstanding);
 	wait_var_event(&net->servers_outstanding,
 		       !atomic_read(&net->servers_outstanding));
 	_leave("");
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 768497f82aee..a121c247d95a 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -194,11 +194,11 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 
 	i_size = i_size_read(&vnode->vfs_inode);
 	if (maybe_i_size > i_size) {
-		spin_lock(&vnode->wb_lock);
+		write_seqlock(&vnode->cb_lock);
 		i_size = i_size_read(&vnode->vfs_inode);
 		if (maybe_i_size > i_size)
 			i_size_write(&vnode->vfs_inode, maybe_i_size);
-		spin_unlock(&vnode->wb_lock);
+		write_sequnlock(&vnode->cb_lock);
 	}
 
 	if (!PageUptodate(page)) {
@@ -393,6 +393,7 @@ static void afs_store_data_success(struct afs_operation *op)
 {
 	struct afs_vnode *vnode = op->file[0].vnode;
 
+	op->ctime = op->file[0].scb.status.mtime_client;
 	afs_vnode_commit_status(op, &op->file[0]);
 	if (op->error == 0) {
 		afs_pages_written_back(vnode, op->store.first, op->store.last);
@@ -448,6 +449,7 @@ static int afs_store_data(struct address_space *mapping,
 	op->store.first_offset = offset;
 	op->store.last_to = to;
 	op->mtime = vnode->vfs_inode.i_mtime;
+	op->flags |= AFS_OPERATION_UNINTR;
 	op->ops = &afs_store_data_operation;
 
 try_next_key:
@@ -491,6 +493,7 @@ static int afs_write_back_from_locked_page(struct address_space *mapping,
 	unsigned long count, priv;
 	unsigned n, offset, to, f, t;
 	pgoff_t start, first, last;
+	loff_t i_size, end;
 	int loop, ret;
 
 	_enter(",%lx", primary_page->index);
@@ -591,7 +594,12 @@ no_more:
 	first = primary_page->index;
 	last = first + count - 1;
 
+	end = (loff_t)last * PAGE_SIZE + to;
+	i_size = i_size_read(&vnode->vfs_inode);
+
 	_debug("write back %lx[%u..] to %lx[..%u]", first, offset, last, to);
+	if (end > i_size)
+		to = i_size & ~PAGE_MASK;
 
 	ret = afs_store_data(mapping, first, last, offset, to);
 	switch (ret) {
@@ -844,6 +852,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 			     vmf->page->index, priv);
 	SetPagePrivate(vmf->page);
 	set_page_private(vmf->page, priv);
+	file_update_time(file);
 
 	sb_end_pagefault(inode->i_sb);
 	return VM_FAULT_LOCKED;
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 52d5af5fcd44..8c24fdc899e3 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -330,29 +330,6 @@ static void xdr_decode_YFSFetchVolumeStatus(const __be32 **_bp,
 }
 
 /*
- * Deliver a reply that's a status, callback and volsync.
- */
-static int yfs_deliver_fs_status_cb_and_volsync(struct afs_call *call)
-{
-	struct afs_operation *op = call->op;
-	const __be32 *bp;
-	int ret;
-
-	ret = afs_transfer_reply(call);
-	if (ret < 0)
-		return ret;
-
-	/* unmarshall the reply once we've received all of it */
-	bp = call->buffer;
-	xdr_decode_YFSFetchStatus(&bp, call, &op->file[0].scb);
-	xdr_decode_YFSCallBack(&bp, call, &op->file[0].scb);
-	xdr_decode_YFSVolSync(&bp, &op->volsync);
-
-	_leave(" = 0 [done]");
-	return 0;
-}
-
-/*
  * Deliver reply data to operations that just return a file status and a volume
  * sync record.
  */
@@ -375,48 +352,6 @@ static int yfs_deliver_status_and_volsync(struct afs_call *call)
 }
 
 /*
- * YFS.FetchStatus operation type
- */
-static const struct afs_call_type yfs_RXYFSFetchStatus_vnode = {
-	.name		= "YFS.FetchStatus(vnode)",
-	.op		= yfs_FS_FetchStatus,
-	.deliver	= yfs_deliver_fs_status_cb_and_volsync,
-	.destructor	= afs_flat_call_destructor,
-};
-
-/*
- * Fetch the status information for a file.
- */
-void yfs_fs_fetch_file_status(struct afs_operation *op)
-{
-	struct afs_vnode_param *vp = &op->file[0];
-	struct afs_call *call;
-	__be32 *bp;
-
-	_enter(",%x,{%llx:%llu},,",
-	       key_serial(op->key), vp->fid.vid, vp->fid.vnode);
-
-	call = afs_alloc_flat_call(op->net, &yfs_RXYFSFetchStatus_vnode,
-				   sizeof(__be32) * 2 +
-				   sizeof(struct yfs_xdr_YFSFid),
-				   sizeof(struct yfs_xdr_YFSFetchStatus) +
-				   sizeof(struct yfs_xdr_YFSCallBack) +
-				   sizeof(struct yfs_xdr_YFSVolSync));
-	if (!call)
-		return afs_op_nomem(op);
-
-	/* marshall the parameters */
-	bp = call->request;
-	bp = xdr_encode_u32(bp, YFSFETCHSTATUS);
-	bp = xdr_encode_u32(bp, 0); /* RPC flags */
-	bp = xdr_encode_YFSFid(bp, &vp->fid);
-	yfs_check_req(call, bp);
-
-	trace_afs_make_fs_call(call, &vp->fid);
-	afs_make_op_call(op, call, GFP_NOFS);
-}
-
-/*
  * Deliver reply data to an YFS.FetchData64.
  */
 static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
@@ -1605,12 +1540,36 @@ void yfs_fs_release_lock(struct afs_operation *op)
 }
 
 /*
+ * Deliver a reply to YFS.FetchStatus
+ */
+static int yfs_deliver_fs_fetch_status(struct afs_call *call)
+{
+	struct afs_operation *op = call->op;
+	struct afs_vnode_param *vp = &op->file[op->fetch_status.which];
+	const __be32 *bp;
+	int ret;
+
+	ret = afs_transfer_reply(call);
+	if (ret < 0)
+		return ret;
+
+	/* unmarshall the reply once we've received all of it */
+	bp = call->buffer;
+	xdr_decode_YFSFetchStatus(&bp, call, &vp->scb);
+	xdr_decode_YFSCallBack(&bp, call, &vp->scb);
+	xdr_decode_YFSVolSync(&bp, &op->volsync);
+
+	_leave(" = 0 [done]");
+	return 0;
+}
+
+/*
  * YFS.FetchStatus operation type
  */
 static const struct afs_call_type yfs_RXYFSFetchStatus = {
 	.name		= "YFS.FetchStatus",
 	.op		= yfs_FS_FetchStatus,
-	.deliver	= yfs_deliver_fs_status_cb_and_volsync,
+	.deliver	= yfs_deliver_fs_fetch_status,
 	.destructor	= afs_flat_call_destructor,
 };
 
@@ -1619,7 +1578,7 @@ static const struct afs_call_type yfs_RXYFSFetchStatus = {
  */
 void yfs_fs_fetch_status(struct afs_operation *op)
 {
-	struct afs_vnode_param *vp = &op->file[0];
+	struct afs_vnode_param *vp = &op->file[op->fetch_status.which];
 	struct afs_call *call;
 	__be32 *bp;
 
diff --git a/fs/aio.c b/fs/aio.c
index 7ecddc2f38db..91e7cc4a9f17 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -67,7 +67,7 @@ struct aio_ring {
 	unsigned	header_length;	/* size of aio_ring */
 
 
-	struct io_event		io_events[0];
+	struct io_event		io_events[];
 }; /* 128 bytes + ring size */
 
 /*
diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c
index b04c528b19d3..74c886f7c51c 100644
--- a/fs/autofs/waitq.c
+++ b/fs/autofs/waitq.c
@@ -53,7 +53,7 @@ static int autofs_write(struct autofs_sb_info *sbi,
 
 	mutex_lock(&sbi->pipe_mutex);
 	while (bytes) {
-		wr = __kernel_write(file, data, bytes, &file->f_pos);
+		wr = kernel_write(file, data, bytes, &file->f_pos);
 		if (wr <= 0)
 			break;
 		data += wr;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 47860e589388..0ae656e022fd 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -75,7 +75,7 @@ static void bdev_write_inode(struct block_device *bdev)
 }
 
 /* Kill _all_ buffers and pagecache , dirty or not.. */
-void kill_bdev(struct block_device *bdev)
+static void kill_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
@@ -84,8 +84,7 @@ void kill_bdev(struct block_device *bdev)
 
 	invalidate_bh_lrus();
 	truncate_inode_pages(mapping, 0);
-}	
-EXPORT_SYMBOL(kill_bdev);
+}
 
 /* Invalidate clean unused buffers and pagecache. */
 void invalidate_bdev(struct block_device *bdev)
@@ -1565,10 +1564,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	 */
 	if (!for_part) {
 		ret = devcgroup_inode_permission(bdev->bd_inode, perm);
-		if (ret != 0) {
-			bdput(bdev);
+		if (ret != 0)
 			return ret;
-		}
 	}
 
  restart:
@@ -1637,8 +1634,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				goto out_clear;
 			BUG_ON(for_part);
 			ret = __blkdev_get(whole, mode, 1);
-			if (ret)
+			if (ret) {
+				bdput(whole);
 				goto out_clear;
+			}
 			bdev->bd_contains = whole;
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
@@ -1688,7 +1687,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	disk_unblock_events(disk);
 	put_disk_and_module(disk);
  out:
-	bdput(bdev);
 
 	return ret;
 }
@@ -1755,6 +1753,9 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 		bdput(whole);
 	}
 
+	if (res)
+		bdput(bdev);
+
 	return res;
 }
 EXPORT_SYMBOL(blkdev_get);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index d888e71e66b6..ea10f7bc99ab 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1461,6 +1461,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans,
 		if (ret < 0 && ret != -ENOENT) {
 			ulist_free(tmp);
 			ulist_free(*roots);
+			*roots = NULL;
 			return ret;
 		}
 		node = ulist_next(tmp, &uiter);
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 176e8a292fd1..c037ef514b64 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -940,7 +940,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
-		goto out_put_group;
+		goto out;
 	}
 
 	/*
@@ -978,7 +978,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		if (ret) {
 			btrfs_add_delayed_iput(inode);
-			goto out_put_group;
+			goto out;
 		}
 		clear_nlink(inode);
 		/* One for the block groups ref */
@@ -1001,13 +1001,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
 	if (ret < 0)
-		goto out_put_group;
+		goto out;
 	if (ret > 0)
 		btrfs_release_path(path);
 	if (ret == 0) {
 		ret = btrfs_del_item(trans, tree_root, path);
 		if (ret)
-			goto out_put_group;
+			goto out;
 		btrfs_release_path(path);
 	}
 
@@ -1016,6 +1016,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		 &fs_info->block_group_cache_tree);
 	RB_CLEAR_NODE(&block_group->cache_node);
 
+	/* Once for the block groups rbtree */
+	btrfs_put_block_group(block_group);
+
 	if (fs_info->first_logical_byte == block_group->start)
 		fs_info->first_logical_byte = (u64)-1;
 	spin_unlock(&fs_info->block_group_cache_lock);
@@ -1089,6 +1092,25 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	spin_unlock(&block_group->space_info->lock);
 
+	/*
+	 * Remove the free space for the block group from the free space tree
+	 * and the block group's item from the extent tree before marking the
+	 * block group as removed. This is to prevent races with tasks that
+	 * freeze and unfreeze a block group, this task and another task
+	 * allocating a new block group - the unfreeze task ends up removing
+	 * the block group's extent map before the task calling this function
+	 * deletes the block group item from the extent tree, allowing for
+	 * another task to attempt to create another block group with the same
+	 * item key (and failing with -EEXIST and a transaction abort).
+	 */
+	ret = remove_block_group_free_space(trans, block_group);
+	if (ret)
+		goto out;
+
+	ret = remove_block_group_item(trans, path, block_group);
+	if (ret < 0)
+		goto out;
+
 	mutex_lock(&fs_info->chunk_mutex);
 	spin_lock(&block_group->lock);
 	block_group->removed = 1;
@@ -1123,17 +1145,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	mutex_unlock(&fs_info->chunk_mutex);
 
-	ret = remove_block_group_free_space(trans, block_group);
-	if (ret)
-		goto out_put_group;
-
-	/* Once for the block groups rbtree */
-	btrfs_put_block_group(block_group);
-
-	ret = remove_block_group_item(trans, path, block_group);
-	if (ret < 0)
-		goto out;
-
 	if (remove_em) {
 		struct extent_map_tree *em_tree;
 
@@ -1145,10 +1156,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		free_extent_map(em);
 	}
 
-out_put_group:
+out:
 	/* Once for the lookup reference */
 	btrfs_put_block_group(block_group);
-out:
 	if (remove_rsv)
 		btrfs_delayed_refs_rsv_release(fs_info, 1);
 	btrfs_free_path(path);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 3a7648bff42c..82ab6e5a386d 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1196,7 +1196,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 		switch (tm->op) {
 		case MOD_LOG_KEY_REMOVE_WHILE_FREEING:
 			BUG_ON(tm->slot < n);
-			/* Fallthrough */
+			fallthrough;
 		case MOD_LOG_KEY_REMOVE_WHILE_MOVING:
 		case MOD_LOG_KEY_REMOVE:
 			btrfs_set_node_key(eb, &tm->key, tm->slot);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 30ce7039bc27..d404cce8ae40 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1009,6 +1009,8 @@ enum {
 	BTRFS_ROOT_DEAD_RELOC_TREE,
 	/* Mark dead root stored on device whose cleanup needs to be resumed */
 	BTRFS_ROOT_DEAD_TREE,
+	/* The root has a log tree. Used only for subvolume roots. */
+	BTRFS_ROOT_HAS_LOG_TREE,
 };
 
 /*
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 5615320fa659..741c7e19c32f 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -619,6 +619,7 @@ void btrfs_discard_punt_unused_bgs_list(struct btrfs_fs_info *fs_info)
 	list_for_each_entry_safe(block_group, next, &fs_info->unused_bgs,
 				 bg_list) {
 		list_del_init(&block_group->bg_list);
+		btrfs_put_block_group(block_group);
 		btrfs_discard_queue_work(&fs_info->discard_ctl, block_group);
 	}
 	spin_unlock(&fs_info->unused_bgs_lock);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7c6f0bbb54a5..b1a148058773 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2593,10 +2593,12 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 		    !extent_buffer_uptodate(tree_root->node)) {
 			handle_error = true;
 
-			if (IS_ERR(tree_root->node))
+			if (IS_ERR(tree_root->node)) {
 				ret = PTR_ERR(tree_root->node);
-			else if (!extent_buffer_uptodate(tree_root->node))
+				tree_root->node = NULL;
+			} else if (!extent_buffer_uptodate(tree_root->node)) {
 				ret = -EUCLEAN;
+			}
 
 			btrfs_warn(fs_info, "failed to read tree root");
 			continue;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 68c96057ad2d..60278e52c37a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1999,7 +1999,8 @@ static int __process_pages_contig(struct address_space *mapping,
 				if (!PageDirty(pages[i]) ||
 				    pages[i]->mapping != mapping) {
 					unlock_page(pages[i]);
-					put_page(pages[i]);
+					for (; i < ret; i++)
+						put_page(pages[i]);
 					err = -EAGAIN;
 					goto out;
 				}
@@ -5058,25 +5059,28 @@ struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 static void check_buffer_tree_ref(struct extent_buffer *eb)
 {
 	int refs;
-	/* the ref bit is tricky.  We have to make sure it is set
-	 * if we have the buffer dirty.   Otherwise the
-	 * code to free a buffer can end up dropping a dirty
-	 * page
+	/*
+	 * The TREE_REF bit is first set when the extent_buffer is added
+	 * to the radix tree. It is also reset, if unset, when a new reference
+	 * is created by find_extent_buffer.
 	 *
-	 * Once the ref bit is set, it won't go away while the
-	 * buffer is dirty or in writeback, and it also won't
-	 * go away while we have the reference count on the
-	 * eb bumped.
+	 * It is only cleared in two cases: freeing the last non-tree
+	 * reference to the extent_buffer when its STALE bit is set or
+	 * calling releasepage when the tree reference is the only reference.
 	 *
-	 * We can't just set the ref bit without bumping the
-	 * ref on the eb because free_extent_buffer might
-	 * see the ref bit and try to clear it.  If this happens
-	 * free_extent_buffer might end up dropping our original
-	 * ref by mistake and freeing the page before we are able
-	 * to add one more ref.
+	 * In both cases, care is taken to ensure that the extent_buffer's
+	 * pages are not under io. However, releasepage can be concurrently
+	 * called with creating new references, which is prone to race
+	 * conditions between the calls to check_buffer_tree_ref in those
+	 * codepaths and clearing TREE_REF in try_release_extent_buffer.
 	 *
-	 * So bump the ref count first, then set the bit.  If someone
-	 * beat us to it, drop the ref we added.
+	 * The actual lifetime of the extent_buffer in the radix tree is
+	 * adequately protected by the refcount, but the TREE_REF bit and
+	 * its corresponding reference are not. To protect against this
+	 * class of races, we call check_buffer_tree_ref from the codepaths
+	 * which trigger io after they set eb->io_pages. Note that once io is
+	 * initiated, TREE_REF can no longer be cleared, so that is the
+	 * moment at which any such race is best fixed.
 	 */
 	refs = atomic_read(&eb->refs);
 	if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
@@ -5527,6 +5531,11 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num)
 	clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = 0;
 	atomic_set(&eb->io_pages, num_reads);
+	/*
+	 * It is possible for releasepage to clear the TREE_REF bit before we
+	 * set io_pages. See check_buffer_tree_ref for a more detailed comment.
+	 */
+	check_buffer_tree_ref(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 2c14312b05e8..b0d2c976587e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1533,7 +1533,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 }
 
 static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
-				    size_t *write_bytes)
+				    size_t *write_bytes, bool nowait)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_root *root = inode->root;
@@ -1541,27 +1541,43 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 	u64 num_bytes;
 	int ret;
 
-	if (!btrfs_drew_try_write_lock(&root->snapshot_lock))
+	if (!nowait && !btrfs_drew_try_write_lock(&root->snapshot_lock))
 		return -EAGAIN;
 
 	lockstart = round_down(pos, fs_info->sectorsize);
 	lockend = round_up(pos + *write_bytes,
 			   fs_info->sectorsize) - 1;
+	num_bytes = lockend - lockstart + 1;
 
-	btrfs_lock_and_flush_ordered_range(inode, lockstart,
-					   lockend, NULL);
+	if (nowait) {
+		struct btrfs_ordered_extent *ordered;
+
+		if (!try_lock_extent(&inode->io_tree, lockstart, lockend))
+			return -EAGAIN;
+
+		ordered = btrfs_lookup_ordered_range(inode, lockstart,
+						     num_bytes);
+		if (ordered) {
+			btrfs_put_ordered_extent(ordered);
+			ret = -EAGAIN;
+			goto out_unlock;
+		}
+	} else {
+		btrfs_lock_and_flush_ordered_range(inode, lockstart,
+						   lockend, NULL);
+	}
 
-	num_bytes = lockend - lockstart + 1;
 	ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes,
 			NULL, NULL, NULL);
 	if (ret <= 0) {
 		ret = 0;
-		btrfs_drew_write_unlock(&root->snapshot_lock);
+		if (!nowait)
+			btrfs_drew_write_unlock(&root->snapshot_lock);
 	} else {
 		*write_bytes = min_t(size_t, *write_bytes ,
 				     num_bytes - pos + lockstart);
 	}
-
+out_unlock:
 	unlock_extent(&inode->io_tree, lockstart, lockend);
 
 	return ret;
@@ -1633,7 +1649,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 			if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
 						      BTRFS_INODE_PREALLOC)) &&
 			    check_can_nocow(BTRFS_I(inode), pos,
-					&write_bytes) > 0) {
+					    &write_bytes, false) > 0) {
 				/*
 				 * For nodata cow case, no need to reserve
 				 * data space.
@@ -1904,13 +1920,25 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	pos = iocb->ki_pos;
 	count = iov_iter_count(from);
 	if (iocb->ki_flags & IOCB_NOWAIT) {
+		size_t nocow_bytes = count;
+
 		/*
 		 * We will allocate space in case nodatacow is not set,
 		 * so bail
 		 */
 		if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
 					      BTRFS_INODE_PREALLOC)) ||
-		    check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) {
+		    check_can_nocow(BTRFS_I(inode), pos, &nocow_bytes,
+				    true) <= 0) {
+			inode_unlock(inode);
+			return -EAGAIN;
+		}
+		/*
+		 * There are holes in the range or parts of the range that must
+		 * be COWed (shared extents, RO block groups, etc), so just bail
+		 * out.
+		 */
+		if (nocow_bytes < count) {
 			inode_unlock(inode);
 			return -EAGAIN;
 		}
@@ -3481,6 +3509,7 @@ const struct file_operations btrfs_file_operations = {
 	.read_iter      = generic_file_read_iter,
 	.splice_read	= generic_file_splice_read,
 	.write_iter	= btrfs_file_write_iter,
+	.splice_write	= iter_file_splice_write,
 	.mmap		= btrfs_file_mmap,
 	.open		= btrfs_file_open,
 	.release	= btrfs_release_file,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d04c82c88418..6862cd7e21a9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -985,6 +985,7 @@ static noinline int cow_file_range(struct inode *inode,
 	u64 num_bytes;
 	unsigned long ram_size;
 	u64 cur_alloc_size = 0;
+	u64 min_alloc_size;
 	u64 blocksize = fs_info->sectorsize;
 	struct btrfs_key ins;
 	struct extent_map *em;
@@ -1035,10 +1036,26 @@ static noinline int cow_file_range(struct inode *inode,
 	btrfs_drop_extent_cache(BTRFS_I(inode), start,
 			start + num_bytes - 1, 0);
 
+	/*
+	 * Relocation relies on the relocated extents to have exactly the same
+	 * size as the original extents. Normally writeback for relocation data
+	 * extents follows a NOCOW path because relocation preallocates the
+	 * extents. However, due to an operation such as scrub turning a block
+	 * group to RO mode, it may fallback to COW mode, so we must make sure
+	 * an extent allocated during COW has exactly the requested size and can
+	 * not be split into smaller extents, otherwise relocation breaks and
+	 * fails during the stage where it updates the bytenr of file extent
+	 * items.
+	 */
+	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
+		min_alloc_size = num_bytes;
+	else
+		min_alloc_size = fs_info->sectorsize;
+
 	while (num_bytes > 0) {
 		cur_alloc_size = num_bytes;
 		ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
-					   fs_info->sectorsize, 0, alloc_hint,
+					   min_alloc_size, 0, alloc_hint,
 					   &ins, 1, 1);
 		if (ret < 0)
 			goto out_unlock;
@@ -1361,6 +1378,8 @@ static int fallback_to_cow(struct inode *inode, struct page *locked_page,
 			   int *page_started, unsigned long *nr_written)
 {
 	const bool is_space_ino = btrfs_is_free_space_inode(BTRFS_I(inode));
+	const bool is_reloc_ino = (BTRFS_I(inode)->root->root_key.objectid ==
+				   BTRFS_DATA_RELOC_TREE_OBJECTID);
 	const u64 range_bytes = end + 1 - start;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	u64 range_start = start;
@@ -1391,18 +1410,23 @@ static int fallback_to_cow(struct inode *inode, struct page *locked_page,
 	 *    data space info, which we incremented in the step above.
 	 *
 	 * If we need to fallback to cow and the inode corresponds to a free
-	 * space cache inode, we must also increment bytes_may_use of the data
-	 * space_info for the same reason. Space caches always get a prealloc
+	 * space cache inode or an inode of the data relocation tree, we must
+	 * also increment bytes_may_use of the data space_info for the same
+	 * reason. Space caches and relocated data extents always get a prealloc
 	 * extent for them, however scrub or balance may have set the block
-	 * group that contains that extent to RO mode.
+	 * group that contains that extent to RO mode and therefore force COW
+	 * when starting writeback.
 	 */
 	count = count_range_bits(io_tree, &range_start, end, range_bytes,
 				 EXTENT_NORESERVE, 0);
-	if (count > 0 || is_space_ino) {
-		const u64 bytes = is_space_ino ? range_bytes : count;
+	if (count > 0 || is_space_ino || is_reloc_ino) {
+		u64 bytes = count;
 		struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 		struct btrfs_space_info *sinfo = fs_info->data_sinfo;
 
+		if (is_space_ino || is_reloc_ino)
+			bytes = range_bytes;
+
 		spin_lock(&sinfo->lock);
 		btrfs_space_info_update_bytes_may_use(fs_info, sinfo, bytes);
 		spin_unlock(&sinfo->lock);
@@ -1666,12 +1690,8 @@ out_check:
 			ret = fallback_to_cow(inode, locked_page, cow_start,
 					      found_key.offset - 1,
 					      page_started, nr_written);
-			if (ret) {
-				if (nocow)
-					btrfs_dec_nocow_writers(fs_info,
-								disk_bytenr);
+			if (ret)
 				goto error;
-			}
 			cow_start = (u64)-1;
 		}
 
@@ -1687,9 +1707,6 @@ out_check:
 					  ram_bytes, BTRFS_COMPRESS_NONE,
 					  BTRFS_ORDERED_PREALLOC);
 			if (IS_ERR(em)) {
-				if (nocow)
-					btrfs_dec_nocow_writers(fs_info,
-								disk_bytenr);
 				ret = PTR_ERR(em);
 				goto error;
 			}
@@ -7865,9 +7882,6 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 			dio_data.overwrite = 1;
 			inode_unlock(inode);
 			relock = true;
-		} else if (iocb->ki_flags & IOCB_NOWAIT) {
-			ret = -EAGAIN;
-			goto out;
 		}
 		ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
 						   offset, count);
@@ -8109,20 +8123,17 @@ again:
 	/*
 	 * Qgroup reserved space handler
 	 * Page here will be either
-	 * 1) Already written to disk
-	 *    In this case, its reserved space is released from data rsv map
-	 *    and will be freed by delayed_ref handler finally.
-	 *    So even we call qgroup_free_data(), it won't decrease reserved
-	 *    space.
-	 * 2) Not written to disk
-	 *    This means the reserved space should be freed here. However,
-	 *    if a truncate invalidates the page (by clearing PageDirty)
-	 *    and the page is accounted for while allocating extent
-	 *    in btrfs_check_data_free_space() we let delayed_ref to
-	 *    free the entire extent.
+	 * 1) Already written to disk or ordered extent already submitted
+	 *    Then its QGROUP_RESERVED bit in io_tree is already cleaned.
+	 *    Qgroup will be handled by its qgroup_record then.
+	 *    btrfs_qgroup_free_data() call will do nothing here.
+	 *
+	 * 2) Not written to disk yet
+	 *    Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED
+	 *    bit of its io_tree, and free the qgroup reserved data space.
+	 *    Since the IO will never happen for this page.
 	 */
-	if (PageDirty(page))
-		btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
+	btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED |
 				 EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 168deb8ef68a..e8f7c5f00894 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2692,7 +2692,7 @@ out:
 	btrfs_put_root(root);
 out_free:
 	btrfs_free_path(path);
-	kzfree(subvol_info);
+	kfree(subvol_info);
 	return ret;
 }
 
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 7887317033c9..af92525dbb16 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -509,7 +509,7 @@ static int process_leaf(struct btrfs_root *root,
 		switch (key.type) {
 		case BTRFS_EXTENT_ITEM_KEY:
 			*num_bytes = key.offset;
-			/* fall through */
+			fallthrough;
 		case BTRFS_METADATA_ITEM_KEY:
 			*bytenr = key.objectid;
 			ret = process_extent_item(fs_info, path, &key, i,
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 41ee88633769..c7bd3fdd7792 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -879,8 +879,8 @@ static bool steal_from_global_rsv(struct btrfs_fs_info *fs_info,
 		return false;
 	}
 	global_rsv->reserved -= ticket->bytes;
+	remove_ticket(space_info, ticket);
 	ticket->bytes = 0;
-	list_del_init(&ticket->list);
 	wake_up(&ticket->wait);
 	space_info->tickets_id++;
 	if (global_rsv->reserved < global_rsv->size)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index bc73fd670702..c3826ae883f0 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -523,7 +523,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_compress_force:
 		case Opt_compress_force_type:
 			compress_force = true;
-			/* Fallthrough */
+			fallthrough;
 		case Opt_compress:
 		case Opt_compress_type:
 			saved_compress_type = btrfs_test_opt(info,
@@ -622,7 +622,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			btrfs_set_opt(info->mount_opt, NOSSD);
 			btrfs_clear_and_info(info, SSD,
 					     "not using ssd optimizations");
-			/* Fallthrough */
+			fallthrough;
 		case Opt_nossd_spread:
 			btrfs_clear_and_info(info, SSD_SPREAD,
 					     "not using spread ssd allocation scheme");
@@ -793,7 +793,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_recovery:
 			btrfs_warn(info,
 				   "'recovery' is deprecated, use 'usebackuproot' instead");
-			/* fall through */
+			fallthrough;
 		case Opt_usebackuproot:
 			btrfs_info(info,
 				   "trying to use backup root at mount time");
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 920cee312f4e..cd5348f352dd 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -169,6 +169,7 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 		if (ret)
 			goto out;
 
+		set_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state);
 		clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
 		root->log_start_pid = current->pid;
 	}
@@ -195,6 +196,9 @@ static int join_running_log_trans(struct btrfs_root *root)
 {
 	int ret = -ENOENT;
 
+	if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state))
+		return ret;
+
 	mutex_lock(&root->log_mutex);
 	if (root->log_root) {
 		ret = 0;
@@ -3303,6 +3307,7 @@ int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root)
 	if (root->log_root) {
 		free_log_tree(trans, root->log_root);
 		root->log_root = NULL;
+		clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state);
 	}
 	return 0;
 }
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0d6e785bcb98..f403fb1e6d37 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7052,6 +7052,14 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 	mutex_lock(&fs_info->chunk_mutex);
 
 	/*
+	 * It is possible for mount and umount to race in such a way that
+	 * we execute this code path, but open_fs_devices failed to clear
+	 * total_rw_bytes. We certainly want it cleared before reading the
+	 * device items, so clear it here.
+	 */
+	fs_info->fs_devices->total_rw_bytes = 0;
+
+	/*
 	 * Read all device items, and then all the chunk items. All
 	 * device items are found before any chunk item (their object id
 	 * is smaller than the lowest possible object id for a chunk
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index f067b5934c46..75af2334b2e3 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -408,7 +408,7 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio)
 		return BTRFS_MAP_WRITE;
 	default:
 		WARN_ON_ONCE(1);
-		/* fall through */
+		fallthrough;
 	case REQ_OP_READ:
 		return BTRFS_MAP_READ;
 	}
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index e7726f5f1241..3080cda9e824 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -937,7 +937,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	}
 
 	data = kmap(page);
-	ret = __kernel_write(file, data, len, &pos);
+	ret = kernel_write(file, data, len, &pos);
 	kunmap(page);
 	fput(file);
 	if (ret != len)
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index fc98b97b396a..53588d7517b4 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -399,6 +399,10 @@ skip_rdma:
 			if (ses->sign)
 				seq_puts(m, " signed");
 
+			seq_printf(m, "\n\tUser: %d Cred User: %d",
+				   from_kuid(&init_user_ns, ses->linux_uid),
+				   from_kuid(&init_user_ns, ses->cred_uid));
+
 			if (ses->chan_count > 1) {
 				seq_printf(m, "\n\n\tExtra Channels: %zu\n",
 					   ses->chan_count-1);
@@ -406,7 +410,7 @@ skip_rdma:
 					cifs_dump_channel(m, j, &ses->chans[j]);
 			}
 
-			seq_puts(m, "\n\tShares:");
+			seq_puts(m, "\n\n\tShares:");
 			j = 0;
 
 			seq_printf(m, "\n\t%d) IPC: ", j);
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index c7a311d28d3d..99b3180c613a 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -156,5 +156,5 @@ extern int cifs_truncate_page(struct address_space *mapping, loff_t from);
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
-#define CIFS_VERSION   "2.27"
+#define CIFS_VERSION   "2.28"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 5fac34f192af..a61abde09ffe 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -5306,9 +5306,15 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 	vol_info->nocase = master_tcon->nocase;
 	vol_info->nohandlecache = master_tcon->nohandlecache;
 	vol_info->local_lease = master_tcon->local_lease;
+	vol_info->no_lease = master_tcon->no_lease;
+	vol_info->resilient = master_tcon->use_resilient;
+	vol_info->persistent = master_tcon->use_persistent;
+	vol_info->handle_timeout = master_tcon->handle_timeout;
 	vol_info->no_linux_ext = !master_tcon->unix_ext;
+	vol_info->linux_ext = master_tcon->posix_extensions;
 	vol_info->sectype = master_tcon->ses->sectype;
 	vol_info->sign = master_tcon->ses->sign;
+	vol_info->seal = master_tcon->seal;
 
 	rc = cifs_set_vol_auth(vol_info, master_tcon->ses);
 	if (rc) {
@@ -5334,10 +5340,6 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 		goto out;
 	}
 
-	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
-	if (tcon->posix_extensions)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-
 	if (cap_unix(ses))
 		reset_cifs_unix_caps(0, tcon, NULL, vol_info);
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 4fe757cfc360..be46fab4c96d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1149,20 +1149,20 @@ cifs_posix_lock_test(struct file *file, struct file_lock *flock)
 
 /*
  * Set the byte-range lock (posix style). Returns:
- * 1) 0, if we set the lock and don't need to request to the server;
- * 2) 1, if we need to request to the server;
- * 3) <0, if the error occurs while setting the lock.
+ * 1) <0, if the error occurs while setting the lock;
+ * 2) 0, if we set the lock and don't need to request to the server;
+ * 3) FILE_LOCK_DEFERRED, if we will wait for some other file_lock;
+ * 4) FILE_LOCK_DEFERRED + 1, if we need to request to the server.
  */
 static int
 cifs_posix_lock_set(struct file *file, struct file_lock *flock)
 {
 	struct cifsInodeInfo *cinode = CIFS_I(file_inode(file));
-	int rc = 1;
+	int rc = FILE_LOCK_DEFERRED + 1;
 
 	if ((flock->fl_flags & FL_POSIX) == 0)
 		return rc;
 
-try_again:
 	cifs_down_write(&cinode->lock_sem);
 	if (!cinode->can_cache_brlcks) {
 		up_write(&cinode->lock_sem);
@@ -1171,13 +1171,6 @@ try_again:
 
 	rc = posix_lock_file(file, flock, NULL);
 	up_write(&cinode->lock_sem);
-	if (rc == FILE_LOCK_DEFERRED) {
-		rc = wait_event_interruptible(flock->fl_wait,
-					list_empty(&flock->fl_blocked_member));
-		if (!rc)
-			goto try_again;
-		locks_delete_block(flock);
-	}
 	return rc;
 }
 
@@ -1652,7 +1645,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 		int posix_lock_type;
 
 		rc = cifs_posix_lock_set(file, flock);
-		if (!rc || rc < 0)
+		if (rc <= FILE_LOCK_DEFERRED)
 			return rc;
 
 		if (type & server->vals->shared_lock_type)
@@ -4336,7 +4329,8 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 			break;
 
 		__SetPageLocked(page);
-		if (add_to_page_cache_locked(page, mapping, page->index, gfp)) {
+		rc = add_to_page_cache_locked(page, mapping, page->index, gfp);
+		if (rc) {
 			__ClearPageLocked(page);
 			break;
 		}
@@ -4352,6 +4346,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 	struct list_head *page_list, unsigned num_pages)
 {
 	int rc;
+	int err = 0;
 	struct list_head tmplist;
 	struct cifsFileInfo *open_file = file->private_data;
 	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
@@ -4396,7 +4391,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 	 * the order of declining indexes. When we put the pages in
 	 * the rdata->pages, then we want them in increasing order.
 	 */
-	while (!list_empty(page_list)) {
+	while (!list_empty(page_list) && !err) {
 		unsigned int i, nr_pages, bytes, rsize;
 		loff_t offset;
 		struct page *page, *tpage;
@@ -4429,9 +4424,10 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 			return 0;
 		}
 
-		rc = readpages_get_pages(mapping, page_list, rsize, &tmplist,
+		nr_pages = 0;
+		err = readpages_get_pages(mapping, page_list, rsize, &tmplist,
 					 &nr_pages, &offset, &bytes);
-		if (rc) {
+		if (!nr_pages) {
 			add_credits_and_wake_if(server, credits, 0);
 			break;
 		}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 583f5e4008c2..ce95801e9b66 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2535,6 +2535,15 @@ set_size_out:
 	if (rc == 0) {
 		cifsInode->server_eof = attrs->ia_size;
 		cifs_setsize(inode, attrs->ia_size);
+
+		/*
+		 * The man page of truncate says if the size changed,
+		 * then the st_ctime and st_mtime fields for the file
+		 * are updated.
+		 */
+		attrs->ia_ctime = attrs->ia_mtime = current_time(inode);
+		attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME;
+
 		cifs_truncate_page(inode->i_mapping, inode->i_size);
 	}
 
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 4a73e63c4d43..dcde44ff6cf9 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -169,6 +169,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 	unsigned int xid;
 	struct cifsFileInfo *pSMBFile = filep->private_data;
 	struct cifs_tcon *tcon;
+	struct tcon_link *tlink;
 	struct cifs_sb_info *cifs_sb;
 	__u64	ExtAttrBits = 0;
 	__u64   caps;
@@ -307,13 +308,19 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 				break;
 			}
 			cifs_sb = CIFS_SB(inode->i_sb);
-			tcon = tlink_tcon(cifs_sb_tlink(cifs_sb));
+			tlink = cifs_sb_tlink(cifs_sb);
+			if (IS_ERR(tlink)) {
+				rc = PTR_ERR(tlink);
+				break;
+			}
+			tcon = tlink_tcon(tlink);
 			if (tcon && tcon->ses->server->ops->notify) {
 				rc = tcon->ses->server->ops->notify(xid,
 						filep, (void __user *)arg);
 				cifs_dbg(FYI, "ioctl notify rc %d\n", rc);
 			} else
 				rc = -EOPNOTSUPP;
+			cifs_put_tlink(tlink);
 			break;
 		default:
 			cifs_dbg(FYI, "unsupported ioctl\n");
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 56791a692c8b..e44d049142d0 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -844,28 +844,26 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw)
 	struct bio_vec *bv = NULL;
 
 	if (iov_iter_is_kvec(iter)) {
-		memcpy(&ctx->iter, iter, sizeof(struct iov_iter));
+		memcpy(&ctx->iter, iter, sizeof(*iter));
 		ctx->len = count;
 		iov_iter_advance(iter, count);
 		return 0;
 	}
 
-	if (max_pages * sizeof(struct bio_vec) <= CIFS_AIO_KMALLOC_LIMIT)
-		bv = kmalloc_array(max_pages, sizeof(struct bio_vec),
-				   GFP_KERNEL);
+	if (array_size(max_pages, sizeof(*bv)) <= CIFS_AIO_KMALLOC_LIMIT)
+		bv = kmalloc_array(max_pages, sizeof(*bv), GFP_KERNEL);
 
 	if (!bv) {
-		bv = vmalloc(array_size(max_pages, sizeof(struct bio_vec)));
+		bv = vmalloc(array_size(max_pages, sizeof(*bv)));
 		if (!bv)
 			return -ENOMEM;
 	}
 
-	if (max_pages * sizeof(struct page *) <= CIFS_AIO_KMALLOC_LIMIT)
-		pages = kmalloc_array(max_pages, sizeof(struct page *),
-				      GFP_KERNEL);
+	if (array_size(max_pages, sizeof(*pages)) <= CIFS_AIO_KMALLOC_LIMIT)
+		pages = kmalloc_array(max_pages, sizeof(*pages), GFP_KERNEL);
 
 	if (!pages) {
-		pages = vmalloc(array_size(max_pages, sizeof(struct page *)));
+		pages = vmalloc(array_size(max_pages, sizeof(*pages)));
 		if (!pages) {
 			kvfree(bv);
 			return -ENOMEM;
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 6a39451973f8..157992864ce7 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -354,9 +354,13 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr)
 		  ((struct smb2_ioctl_rsp *)shdr)->OutputCount);
 		break;
 	case SMB2_CHANGE_NOTIFY:
+		*off = le16_to_cpu(
+		  ((struct smb2_change_notify_rsp *)shdr)->OutputBufferOffset);
+		*len = le32_to_cpu(
+		  ((struct smb2_change_notify_rsp *)shdr)->OutputBufferLength);
+		break;
 	default:
-		/* BB FIXME for unimplemented cases above */
-		cifs_dbg(VFS, "no length check for command\n");
+		cifs_dbg(VFS, "no length check for command %d\n", le16_to_cpu(shdr->Command));
 		break;
 	}
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 736d86b8a910..32f90dc82c84 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -763,6 +763,7 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
 			/* close extra handle outside of crit sec */
 			SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 		}
+		rc = 0;
 		goto oshr_free;
 	}
 
@@ -2147,7 +2148,7 @@ smb3_notify(const unsigned int xid, struct file *pfile,
 
 	tcon = cifs_sb_master_tcon(cifs_sb);
 	oparms.tcon = tcon;
-	oparms.desired_access = FILE_READ_ATTRIBUTES;
+	oparms.desired_access = FILE_READ_ATTRIBUTES | FILE_READ_DATA;
 	oparms.disposition = FILE_OPEN;
 	oparms.create_options = cifs_create_options(cifs_sb, 0);
 	oparms.fid = &fid;
@@ -3187,6 +3188,11 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid,
 			      ses->Suid, offset, len);
 
+	/*
+	 * We zero the range through ioctl, so we need remove the page caches
+	 * first, otherwise the data may be inconsistent with the server.
+	 */
+	truncate_pagecache_range(inode, offset, offset + len - 1);
 
 	/* if file not oplocked can't be sure whether asking to extend size */
 	if (!CIFS_CACHE_READ(cifsi))
@@ -3253,6 +3259,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 		return rc;
 	}
 
+	/*
+	 * We implement the punch hole through ioctl, so we need remove the page
+	 * caches first, otherwise the data may be inconsistent with the server.
+	 */
+	truncate_pagecache_range(inode, offset, offset + len - 1);
+
 	cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len);
 
 	fsctl_buf.FileOffset = cpu_to_le64(offset);
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index d11e31064679..84433d0653f9 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -523,7 +523,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits,
 		      const int timeout, const int flags,
 		      unsigned int *instance)
 {
-	int rc;
+	long rc;
 	int *credits;
 	int optype;
 	long int t;
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index e9e27a271af0..feaa5e182b7b 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -51,6 +51,7 @@ static ssize_t efivarfs_file_write(struct file *file,
 	} else {
 		inode_lock(inode);
 		i_size_write(inode, datasize + sizeof(attributes));
+		inode->i_mtime = current_time(inode);
 		inode_unlock(inode);
 	}
 
@@ -72,10 +73,8 @@ static ssize_t efivarfs_file_read(struct file *file, char __user *userbuf,
 	ssize_t size = 0;
 	int err;
 
-	while (!__ratelimit(&file->f_cred->user->ratelimit)) {
-		if (!msleep_interruptible(50))
-			return -EINTR;
-	}
+	while (!__ratelimit(&file->f_cred->user->ratelimit))
+		msleep(50);
 
 	err = efivar_entry_size(var, &datasize);
 
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 12c66f5d92dd..28bb5689333a 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -201,6 +201,9 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_d_op		= &efivarfs_d_ops;
 	sb->s_time_gran         = 1;
 
+	if (!efivar_supports_writes())
+		sb->s_flags |= SB_RDONLY;
+
 	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true);
 	if (!inode)
 		return -ENOMEM;
@@ -252,9 +255,6 @@ static struct file_system_type efivarfs_type = {
 
 static __init int efivarfs_init(void)
 {
-	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES))
-		return -ENODEV;
-
 	if (!efivars_kobject())
 		return -ENODEV;
 
diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h
index 7824f5563a55..9b66c28b3ae9 100644
--- a/fs/erofs/zdata.h
+++ b/fs/erofs/zdata.h
@@ -144,22 +144,22 @@ static inline void z_erofs_onlinepage_init(struct page *page)
 static inline void z_erofs_onlinepage_fixup(struct page *page,
 	uintptr_t index, bool down)
 {
-	unsigned long *p, o, v, id;
-repeat:
-	p = &page_private(page);
-	o = READ_ONCE(*p);
+	union z_erofs_onlinepage_converter u = { .v = &page_private(page) };
+	int orig, orig_index, val;
 
-	id = o >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT;
-	if (id) {
+repeat:
+	orig = atomic_read(u.o);
+	orig_index = orig >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT;
+	if (orig_index) {
 		if (!index)
 			return;
 
-		DBG_BUGON(id != index);
+		DBG_BUGON(orig_index != index);
 	}
 
-	v = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) |
-		((o & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down);
-	if (cmpxchg(p, o, v) != o)
+	val = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) |
+		((orig & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down);
+	if (atomic_cmpxchg(u.o, orig, val) != orig)
 		goto repeat;
 }
 
diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c
index de43534aa299..119abf0d8dd6 100644
--- a/fs/exfat/dir.c
+++ b/fs/exfat/dir.c
@@ -309,7 +309,7 @@ const struct file_operations exfat_dir_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
 	.iterate	= exfat_iterate,
-	.fsync		= generic_file_fsync,
+	.fsync		= exfat_file_fsync,
 };
 
 int exfat_alloc_new_dir(struct inode *inode, struct exfat_chain *clu)
@@ -425,10 +425,12 @@ static void exfat_init_name_entry(struct exfat_dentry *ep,
 	ep->dentry.name.flags = 0x0;
 
 	for (i = 0; i < EXFAT_FILE_NAME_LEN; i++) {
-		ep->dentry.name.unicode_0_14[i] = cpu_to_le16(*uniname);
-		if (*uniname == 0x0)
-			break;
-		uniname++;
+		if (*uniname != 0x0) {
+			ep->dentry.name.unicode_0_14[i] = cpu_to_le16(*uniname);
+			uniname++;
+		} else {
+			ep->dentry.name.unicode_0_14[i] = 0x0;
+		}
 	}
 }
 
@@ -1110,7 +1112,7 @@ found:
 			ret = exfat_get_next_cluster(sb, &clu.dir);
 		}
 
-		if (ret || clu.dir != EXFAT_EOF_CLUSTER) {
+		if (ret || clu.dir == EXFAT_EOF_CLUSTER) {
 			/* just initialized hint_stat */
 			hint_stat->clu = p_dir->dir;
 			hint_stat->eidx = 0;
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 595f3117f492..75c7bdbeba6d 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -371,7 +371,7 @@ static inline bool exfat_is_last_sector_in_cluster(struct exfat_sb_info *sbi,
 static inline sector_t exfat_cluster_to_sector(struct exfat_sb_info *sbi,
 		unsigned int clus)
 {
-	return ((clus - EXFAT_RESERVED_CLUSTERS) << sbi->sect_per_clus_bits) +
+	return ((sector_t)(clus - EXFAT_RESERVED_CLUSTERS) << sbi->sect_per_clus_bits) +
 		sbi->data_start_sector;
 }
 
@@ -420,6 +420,7 @@ void exfat_truncate(struct inode *inode, loff_t size);
 int exfat_setattr(struct dentry *dentry, struct iattr *attr);
 int exfat_getattr(const struct path *path, struct kstat *stat,
 		unsigned int request_mask, unsigned int query_flags);
+int exfat_file_fsync(struct file *file, loff_t start, loff_t end, int datasync);
 
 /* namei.c */
 extern const struct dentry_operations exfat_dentry_ops;
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index fce03f318787..a6a063830edc 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/cred.h>
 #include <linux/buffer_head.h>
+#include <linux/blkdev.h>
 
 #include "exfat_raw.h"
 #include "exfat_fs.h"
@@ -175,7 +176,7 @@ int __exfat_truncate(struct inode *inode, loff_t new_size)
 			ep2->dentry.stream.size = 0;
 		} else {
 			ep2->dentry.stream.valid_size = cpu_to_le64(new_size);
-			ep2->dentry.stream.size = ep->dentry.stream.valid_size;
+			ep2->dentry.stream.size = ep2->dentry.stream.valid_size;
 		}
 
 		if (new_size == 0) {
@@ -346,12 +347,28 @@ out:
 	return error;
 }
 
+int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
+{
+	struct inode *inode = filp->f_mapping->host;
+	int err;
+
+	err = __generic_file_fsync(filp, start, end, datasync);
+	if (err)
+		return err;
+
+	err = sync_blockdev(inode->i_sb->s_bdev);
+	if (err)
+		return err;
+
+	return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
+}
+
 const struct file_operations exfat_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= generic_file_read_iter,
 	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
-	.fsync		= generic_file_fsync,
+	.fsync		= exfat_file_fsync,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 };
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 5b0f35329d63..2b9e21094a96 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -975,7 +975,6 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 		goto unlock;
 	}
 
-	exfat_set_vol_flags(sb, VOL_DIRTY);
 	exfat_chain_set(&clu_to_free, ei->start_clu,
 		EXFAT_B_TO_CLU_ROUND_UP(i_size_read(inode), sbi), ei->flags);
 
@@ -1002,6 +1001,7 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 	num_entries++;
 	brelse(bh);
 
+	exfat_set_vol_flags(sb, VOL_DIRTY);
 	err = exfat_remove_entries(dir, &cdir, entry, 0, num_entries);
 	if (err) {
 		exfat_err(sb, "failed to exfat_remove_entries : err(%d)", err);
@@ -1077,10 +1077,14 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir,
 
 		epold = exfat_get_dentry(sb, p_dir, oldentry + 1, &old_bh,
 			&sector_old);
+		if (!epold)
+			return -EIO;
 		epnew = exfat_get_dentry(sb, p_dir, newentry + 1, &new_bh,
 			&sector_new);
-		if (!epold || !epnew)
+		if (!epnew) {
+			brelse(old_bh);
 			return -EIO;
+		}
 
 		memcpy(epnew, epold, DENTRY_SIZE);
 		exfat_update_bh(sb, new_bh, sync);
@@ -1161,10 +1165,14 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir,
 
 	epmov = exfat_get_dentry(sb, p_olddir, oldentry + 1, &mov_bh,
 		&sector_mov);
+	if (!epmov)
+		return -EIO;
 	epnew = exfat_get_dentry(sb, p_newdir, newentry + 1, &new_bh,
 		&sector_new);
-	if (!epmov || !epnew)
+	if (!epnew) {
+		brelse(mov_bh);
 		return -EIO;
+	}
 
 	memcpy(epnew, epmov, DENTRY_SIZE);
 	exfat_update_bh(sb, new_bh, IS_DIRSYNC(inode));
diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c
index 57b5a7a4d1f7..a3c927501e67 100644
--- a/fs/exfat/nls.c
+++ b/fs/exfat/nls.c
@@ -495,7 +495,7 @@ static int exfat_utf8_to_utf16(struct super_block *sb,
 		struct exfat_uni_name *p_uniname, int *p_lossy)
 {
 	int i, unilen, lossy = NLS_NAME_NO_LOSSY;
-	unsigned short upname[MAX_NAME_LENGTH + 1];
+	__le16 upname[MAX_NAME_LENGTH + 1];
 	unsigned short *uniname = p_uniname->name;
 
 	WARN_ON(!len);
@@ -519,7 +519,7 @@ static int exfat_utf8_to_utf16(struct super_block *sb,
 		    exfat_wstrchr(bad_uni_chars, *uniname))
 			lossy |= NLS_NAME_LOSSY;
 
-		upname[i] = exfat_toupper(sb, *uniname);
+		upname[i] = cpu_to_le16(exfat_toupper(sb, *uniname));
 		uniname++;
 	}
 
@@ -597,7 +597,7 @@ static int exfat_nls_to_ucs2(struct super_block *sb,
 		struct exfat_uni_name *p_uniname, int *p_lossy)
 {
 	int i = 0, unilen = 0, lossy = NLS_NAME_NO_LOSSY;
-	unsigned short upname[MAX_NAME_LENGTH + 1];
+	__le16 upname[MAX_NAME_LENGTH + 1];
 	unsigned short *uniname = p_uniname->name;
 	struct nls_table *nls = EXFAT_SB(sb)->nls_io;
 
@@ -611,7 +611,7 @@ static int exfat_nls_to_ucs2(struct super_block *sb,
 		    exfat_wstrchr(bad_uni_chars, *uniname))
 			lossy |= NLS_NAME_LOSSY;
 
-		upname[unilen] = exfat_toupper(sb, *uniname);
+		upname[unilen] = cpu_to_le16(exfat_toupper(sb, *uniname));
 		uniname++;
 		unilen++;
 	}
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index e650e65536f8..253a92460d52 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -693,10 +693,20 @@ static void exfat_free(struct fs_context *fc)
 	}
 }
 
+static int exfat_reconfigure(struct fs_context *fc)
+{
+	fc->sb_flags |= SB_NODIRATIME;
+
+	/* volume flag will be updated in exfat_sync_fs */
+	sync_filesystem(fc->root->d_sb);
+	return 0;
+}
+
 static const struct fs_context_operations exfat_context_ops = {
 	.parse_param	= exfat_parse_param,
 	.get_tree	= exfat_get_tree,
 	.free		= exfat_free,
+	.reconfigure	= exfat_reconfigure,
 };
 
 static int exfat_init_fs_context(struct fs_context *fc)
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 4ccb3c9189d8..2e42f47a7f98 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -9,7 +9,8 @@ ext4-y	:= balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
 		extents_status.o file.o fsmap.o fsync.o hash.o ialloc.o \
 		indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \
 		mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \
-		super.o symlink.o sysfs.o xattr.o xattr_trusted.o xattr_user.o
+		super.o symlink.o sysfs.o xattr.o xattr_hurd.o xattr_trusted.o \
+		xattr_user.o
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index c654205f648d..1d82336b1cd4 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -675,6 +675,7 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
 	struct qstr qstr = {.name = str, .len = len };
 	const struct dentry *parent = READ_ONCE(dentry->d_parent);
 	const struct inode *inode = READ_ONCE(parent->d_inode);
+	char strbuf[DNAME_INLINE_LEN];
 
 	if (!inode || !IS_CASEFOLDED(inode) ||
 	    !EXT4_SB(inode->i_sb)->s_encoding) {
@@ -683,6 +684,21 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
 		return memcmp(str, name->name, len);
 	}
 
+	/*
+	 * If the dentry name is stored in-line, then it may be concurrently
+	 * modified by a rename.  If this happens, the VFS will eventually retry
+	 * the lookup, so it doesn't matter what ->d_compare() returns.
+	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
+	 * string.  Therefore, we have to copy the name into a temporary buffer.
+	 */
+	if (len <= DNAME_INLINE_LEN - 1) {
+		memcpy(strbuf, str, len);
+		strbuf[len] = 0;
+		qstr.name = strbuf;
+		/* prevent compiler from optimizing out the temporary buffer */
+		barrier();
+	}
+
 	return ext4_ci_compare(inode, name, &qstr, false);
 }
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b08841f70b69..42f5060f3cdf 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -426,13 +426,16 @@ struct flex_groups {
 #define EXT4_VERITY_FL			0x00100000 /* Verity protected inode */
 #define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
 /* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */
+
+#define EXT4_DAX_FL			0x02000000 /* Inode is DAX */
+
 #define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
 #define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
 #define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded directory */
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
-#define EXT4_FL_USER_VISIBLE		0x705BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE		0x604BC0FF /* User modifiable flags */
+#define EXT4_FL_USER_VISIBLE		0x725BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE		0x624BC0FF /* User modifiable flags */
 
 /* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */
 #define EXT4_FL_XFLAG_VISIBLE		(EXT4_SYNC_FL | \
@@ -440,14 +443,16 @@ struct flex_groups {
 					 EXT4_APPEND_FL | \
 					 EXT4_NODUMP_FL | \
 					 EXT4_NOATIME_FL | \
-					 EXT4_PROJINHERIT_FL)
+					 EXT4_PROJINHERIT_FL | \
+					 EXT4_DAX_FL)
 
 /* 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_NODUMP_FL | EXT4_NOATIME_FL |\
 			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
 			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
-			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL)
+			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\
+			   EXT4_DAX_FL)
 
 /* Flags that are appropriate for regular files (all but dir-specific ones). */
 #define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\
@@ -459,6 +464,10 @@ struct flex_groups {
 /* The only flags that should be swapped */
 #define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL)
 
+/* Flags which are mutually exclusive to DAX */
+#define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\
+			   EXT4_JOURNAL_DATA_FL)
+
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
 {
@@ -499,6 +508,7 @@ enum {
 	EXT4_INODE_VERITY	= 20,	/* Verity protected inode */
 	EXT4_INODE_EA_INODE	= 21,	/* Inode used for large EA */
 /* 22 was formerly EXT4_INODE_EOFBLOCKS */
+	EXT4_INODE_DAX		= 25,	/* Inode is DAX */
 	EXT4_INODE_INLINE_DATA	= 28,	/* Data in inode. */
 	EXT4_INODE_PROJINHERIT	= 29,	/* Create with parents projid */
 	EXT4_INODE_CASEFOLD	= 30,	/* Casefolded directory */
@@ -1135,9 +1145,9 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
 #define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
 #ifdef CONFIG_FS_DAX
-#define EXT4_MOUNT_DAX			0x00200	/* Direct Access */
+#define EXT4_MOUNT_DAX_ALWAYS		0x00200	/* Direct Access */
 #else
-#define EXT4_MOUNT_DAX			0
+#define EXT4_MOUNT_DAX_ALWAYS		0
 #endif
 #define EXT4_MOUNT_DATA_FLAGS		0x00C00	/* Mode for data writes: */
 #define EXT4_MOUNT_JOURNAL_DATA		0x00400	/* Write data to journal */
@@ -1180,6 +1190,8 @@ struct ext4_inode_info {
 						      blocks */
 #define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
 						      file systems */
+#define EXT4_MOUNT2_DAX_NEVER		0x00000008 /* Do not allow Direct Access */
+#define EXT4_MOUNT2_DAX_INODE		0x00000010 /* For printing options only */
 
 #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
 						specified journal checksum */
@@ -1992,6 +2004,7 @@ static inline bool ext4_has_incompat_features(struct super_block *sb)
  */
 #define EXT4_FLAGS_RESIZING	0
 #define EXT4_FLAGS_SHUTDOWN	1
+#define EXT4_FLAGS_BDEV_IS_DAX	2
 
 static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
 {
@@ -2705,7 +2718,7 @@ extern int ext4_can_truncate(struct inode *inode);
 extern int ext4_truncate(struct inode *);
 extern int ext4_break_layouts(struct inode *);
 extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
-extern void ext4_set_inode_flags(struct inode *);
+extern void ext4_set_inode_flags(struct inode *, bool init);
 extern int ext4_alloc_da_blocks(struct inode *inode);
 extern void ext4_set_aops(struct inode *inode);
 extern int ext4_writepage_trans_blocks(struct inode *);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7d088ff1e902..221f240eae60 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2844,7 +2844,7 @@ again:
 			 * in use to avoid freeing it when removing blocks.
 			 */
 			if (sbi->s_cluster_ratio > 1) {
-				pblk = ext4_ext_pblock(ex) + end - ee_block + 2;
+				pblk = ext4_ext_pblock(ex) + end - ee_block + 1;
 				partial.pclu = EXT4_B2C(sbi, pblk);
 				partial.state = nofree;
 			}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 54d324e80fe5..df25d38d6539 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1116,7 +1116,7 @@ got:
 	ei->i_block_group = group;
 	ei->i_last_alloc_group = ~0;
 
-	ext4_set_inode_flags(inode);
+	ext4_set_inode_flags(inode, true);
 	if (IS_DIRSYNC(inode))
 		ext4_handle_sync(handle);
 	if (insert_inode_locked(inode) < 0) {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 40ec5c7ef0d3..10dd470876b3 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4403,9 +4403,11 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 		!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
 }
 
-static bool ext4_should_use_dax(struct inode *inode)
+static bool ext4_should_enable_dax(struct inode *inode)
 {
-	if (!test_opt(inode->i_sb, DAX))
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+	if (test_opt2(inode->i_sb, DAX_NEVER))
 		return false;
 	if (!S_ISREG(inode->i_mode))
 		return false;
@@ -4417,14 +4419,21 @@ static bool ext4_should_use_dax(struct inode *inode)
 		return false;
 	if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY))
 		return false;
-	return true;
+	if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags))
+		return false;
+	if (test_opt(inode->i_sb, DAX_ALWAYS))
+		return true;
+
+	return ext4_test_inode_flag(inode, EXT4_INODE_DAX);
 }
 
-void ext4_set_inode_flags(struct inode *inode)
+void ext4_set_inode_flags(struct inode *inode, bool init)
 {
 	unsigned int flags = EXT4_I(inode)->i_flags;
 	unsigned int new_fl = 0;
 
+	WARN_ON_ONCE(IS_DAX(inode) && init);
+
 	if (flags & EXT4_SYNC_FL)
 		new_fl |= S_SYNC;
 	if (flags & EXT4_APPEND_FL)
@@ -4435,8 +4444,13 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	if (ext4_should_use_dax(inode))
+
+	/* Because of the way inode_set_flags() works we must preserve S_DAX
+	 * here if already set. */
+	new_fl |= (inode->i_flags & S_DAX);
+	if (init && ext4_should_enable_dax(inode))
 		new_fl |= S_DAX;
+
 	if (flags & EXT4_ENCRYPT_FL)
 		new_fl |= S_ENCRYPTED;
 	if (flags & EXT4_CASEFOLD_FL)
@@ -4650,7 +4664,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		 * not initialized on a new filesystem. */
 	}
 	ei->i_flags = le32_to_cpu(raw_inode->i_flags);
-	ext4_set_inode_flags(inode);
+	ext4_set_inode_flags(inode, true);
 	inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
 	ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
 	if (ext4_has_feature_64bit(sb))
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 2162db0c747d..999cf6add39c 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -292,6 +292,38 @@ static int ext4_ioctl_check_immutable(struct inode *inode, __u32 new_projid,
 	return 0;
 }
 
+static void ext4_dax_dontcache(struct inode *inode, unsigned int flags)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (S_ISDIR(inode->i_mode))
+		return;
+
+	if (test_opt2(inode->i_sb, DAX_NEVER) ||
+	    test_opt(inode->i_sb, DAX_ALWAYS))
+		return;
+
+	if ((ei->i_flags ^ flags) & EXT4_DAX_FL)
+		d_mark_dontcache(inode);
+}
+
+static bool dax_compatible(struct inode *inode, unsigned int oldflags,
+			   unsigned int flags)
+{
+	if (flags & EXT4_DAX_FL) {
+		if ((oldflags & EXT4_DAX_MUT_EXCL) ||
+		     ext4_test_inode_state(inode,
+					  EXT4_STATE_VERITY_IN_PROGRESS)) {
+			return false;
+		}
+	}
+
+	if ((flags & EXT4_DAX_MUT_EXCL) && (oldflags & EXT4_DAX_FL))
+			return false;
+
+	return true;
+}
+
 static int ext4_ioctl_setflags(struct inode *inode,
 			       unsigned int flags)
 {
@@ -300,7 +332,6 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	int err = -EPERM, migrate = 0;
 	struct ext4_iloc iloc;
 	unsigned int oldflags, mask, i;
-	unsigned int jflag;
 	struct super_block *sb = inode->i_sb;
 
 	/* Is it quota file? Do not allow user to mess with it */
@@ -309,9 +340,6 @@ static int ext4_ioctl_setflags(struct inode *inode,
 
 	oldflags = ei->i_flags;
 
-	/* The JOURNAL_DATA flag is modifiable only by root */
-	jflag = flags & EXT4_JOURNAL_DATA_FL;
-
 	err = vfs_ioc_setflags_prepare(inode, oldflags, flags);
 	if (err)
 		goto flags_out;
@@ -320,10 +348,16 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	 * The JOURNAL_DATA flag can only be changed by
 	 * the relevant capability.
 	 */
-	if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
+	if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
 		if (!capable(CAP_SYS_RESOURCE))
 			goto flags_out;
 	}
+
+	if (!dax_compatible(inode, oldflags, flags)) {
+		err = -EOPNOTSUPP;
+		goto flags_out;
+	}
+
 	if ((flags ^ oldflags) & EXT4_EXTENTS_FL)
 		migrate = 1;
 
@@ -369,6 +403,8 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	if (err)
 		goto flags_err;
 
+	ext4_dax_dontcache(inode, flags);
+
 	for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
 		if (!(mask & EXT4_FL_USER_MODIFIABLE))
 			continue;
@@ -381,7 +417,8 @@ static int ext4_ioctl_setflags(struct inode *inode,
 			ext4_clear_inode_flag(inode, i);
 	}
 
-	ext4_set_inode_flags(inode);
+	ext4_set_inode_flags(inode, false);
+
 	inode->i_ctime = current_time(inode);
 
 	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
@@ -390,17 +427,18 @@ flags_err:
 	if (err)
 		goto flags_out;
 
-	if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
+	if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
 		/*
 		 * Changes to the journaling mode can cause unsafe changes to
-		 * S_DAX if we are using the DAX mount option.
+		 * S_DAX if the inode is DAX
 		 */
-		if (test_opt(inode->i_sb, DAX)) {
+		if (IS_DAX(inode)) {
 			err = -EBUSY;
 			goto flags_out;
 		}
 
-		err = ext4_change_inode_journal_flag(inode, jflag);
+		err = ext4_change_inode_journal_flag(inode,
+						     flags & EXT4_JOURNAL_DATA_FL);
 		if (err)
 			goto flags_out;
 	}
@@ -527,12 +565,15 @@ static inline __u32 ext4_iflags_to_xflags(unsigned long iflags)
 		xflags |= FS_XFLAG_NOATIME;
 	if (iflags & EXT4_PROJINHERIT_FL)
 		xflags |= FS_XFLAG_PROJINHERIT;
+	if (iflags & EXT4_DAX_FL)
+		xflags |= FS_XFLAG_DAX;
 	return xflags;
 }
 
 #define EXT4_SUPPORTED_FS_XFLAGS (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | \
 				  FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \
-				  FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT)
+				  FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT | \
+				  FS_XFLAG_DAX)
 
 /* Transfer xflags flags to internal */
 static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
@@ -551,6 +592,8 @@ static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
 		iflags |= EXT4_NOATIME_FL;
 	if (xflags & FS_XFLAG_PROJINHERIT)
 		iflags |= EXT4_PROJINHERIT_FL;
+	if (xflags & FS_XFLAG_DAX)
+		iflags |= EXT4_DAX_FL;
 
 	return iflags;
 }
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a9083113a8c0..c0a331e2feb0 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4708,7 +4708,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	}
 
 	ac->ac_op = EXT4_MB_HISTORY_PREALLOC;
-	seq = *this_cpu_ptr(&discard_pa_seq);
+	seq = this_cpu_read(discard_pa_seq);
 	if (!ext4_mb_use_preallocated(ac)) {
 		ac->ac_op = EXT4_MB_HISTORY_ALLOC;
 		ext4_mb_normalize_request(ac, ar);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c668f6b42374..330957ed1f05 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -522,9 +522,6 @@ static void ext4_handle_error(struct super_block *sb)
 		smp_wmb();
 		sb->s_flags |= SB_RDONLY;
 	} else if (test_opt(sb, ERRORS_PANIC)) {
-		if (EXT4_SB(sb)->s_journal &&
-		  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
-			return;
 		panic("EXT4-fs (device %s): panic forced after error\n",
 			sb->s_id);
 	}
@@ -725,23 +722,20 @@ void __ext4_abort(struct super_block *sb, const char *function,
 	va_end(args);
 
 	if (sb_rdonly(sb) == 0) {
-		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		if (EXT4_SB(sb)->s_journal)
+			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+
+		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		/*
 		 * Make sure updated value of ->s_mount_flags will be visible
 		 * before ->s_flags update
 		 */
 		smp_wmb();
 		sb->s_flags |= SB_RDONLY;
-		if (EXT4_SB(sb)->s_journal)
-			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 	}
-	if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) {
-		if (EXT4_SB(sb)->s_journal &&
-		  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
-			return;
+	if (test_opt(sb, ERRORS_PANIC) && !system_going_down())
 		panic("EXT4-fs panic from previous error\n");
-	}
 }
 
 void __ext4_msg(struct super_block *sb,
@@ -1324,6 +1318,9 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 	if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode)))
 		return -EINVAL;
 
+	if (ext4_test_inode_flag(inode, EXT4_INODE_DAX))
+		return -EOPNOTSUPP;
+
 	res = ext4_convert_inline_data(inode);
 	if (res)
 		return res;
@@ -1349,7 +1346,7 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 			 * Update inode->i_flags - S_ENCRYPTED will be enabled,
 			 * S_DAX may be disabled
 			 */
-			ext4_set_inode_flags(inode);
+			ext4_set_inode_flags(inode, false);
 		}
 		return res;
 	}
@@ -1376,7 +1373,7 @@ retry:
 		 * Update inode->i_flags - S_ENCRYPTED will be enabled,
 		 * S_DAX may be disabled
 		 */
-		ext4_set_inode_flags(inode);
+		ext4_set_inode_flags(inode, false);
 		res = ext4_mark_inode_dirty(handle, inode);
 		if (res)
 			EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
@@ -1514,7 +1511,8 @@ enum {
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
-	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
+	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version,
+	Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
 	Opt_nowarn_on_error, Opt_mblk_io_submit,
 	Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
@@ -1581,6 +1579,9 @@ static const match_table_t tokens = {
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_i_version, "i_version"},
 	{Opt_dax, "dax"},
+	{Opt_dax_always, "dax=always"},
+	{Opt_dax_inode, "dax=inode"},
+	{Opt_dax_never, "dax=never"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
 	{Opt_warn_on_error, "warn_on_error"},
@@ -1729,6 +1730,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
 #define MOPT_NO_EXT3	0x0200
 #define MOPT_EXT4_ONLY	(MOPT_NO_EXT2 | MOPT_NO_EXT3)
 #define MOPT_STRING	0x0400
+#define MOPT_SKIP	0x0800
 
 static const struct mount_opts {
 	int	token;
@@ -1778,7 +1780,13 @@ static const struct mount_opts {
 	{Opt_min_batch_time, 0, MOPT_GTE0},
 	{Opt_inode_readahead_blks, 0, MOPT_GTE0},
 	{Opt_init_itable, 0, MOPT_GTE0},
-	{Opt_dax, EXT4_MOUNT_DAX, MOPT_SET},
+	{Opt_dax, EXT4_MOUNT_DAX_ALWAYS, MOPT_SET | MOPT_SKIP},
+	{Opt_dax_always, EXT4_MOUNT_DAX_ALWAYS,
+		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
+	{Opt_dax_inode, EXT4_MOUNT2_DAX_INODE,
+		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
+	{Opt_dax_never, EXT4_MOUNT2_DAX_NEVER,
+		MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
 	{Opt_stripe, 0, MOPT_GTE0},
 	{Opt_resuid, 0, MOPT_GTE0},
 	{Opt_resgid, 0, MOPT_GTE0},
@@ -2123,13 +2131,56 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		}
 		sbi->s_jquota_fmt = m->mount_opt;
 #endif
-	} else if (token == Opt_dax) {
+	} else if (token == Opt_dax || token == Opt_dax_always ||
+		   token == Opt_dax_inode || token == Opt_dax_never) {
 #ifdef CONFIG_FS_DAX
-		ext4_msg(sb, KERN_WARNING,
-		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
-		sbi->s_mount_opt |= m->mount_opt;
+		switch (token) {
+		case Opt_dax:
+		case Opt_dax_always:
+			if (is_remount &&
+			    (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) ||
+			     (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) {
+			fail_dax_change_remount:
+				ext4_msg(sb, KERN_ERR, "can't change "
+					 "dax mount option while remounting");
+				return -1;
+			}
+			if (is_remount &&
+			    (test_opt(sb, DATA_FLAGS) ==
+			     EXT4_MOUNT_JOURNAL_DATA)) {
+				    ext4_msg(sb, KERN_ERR, "can't mount with "
+					     "both data=journal and dax");
+				    return -1;
+			}
+			ext4_msg(sb, KERN_WARNING,
+				"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+			sbi->s_mount_opt |= EXT4_MOUNT_DAX_ALWAYS;
+			sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER;
+			break;
+		case Opt_dax_never:
+			if (is_remount &&
+			    (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) ||
+			     (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS)))
+				goto fail_dax_change_remount;
+			sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
+			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
+			break;
+		case Opt_dax_inode:
+			if (is_remount &&
+			    ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) ||
+			     (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) ||
+			     !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE)))
+				goto fail_dax_change_remount;
+			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
+			sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER;
+			/* Strictly for printing options */
+			sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_INODE;
+			break;
+		}
 #else
 		ext4_msg(sb, KERN_INFO, "dax option not supported");
+		sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
+		sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
 		return -1;
 #endif
 	} else if (token == Opt_data_err_abort) {
@@ -2293,7 +2344,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 	for (m = ext4_mount_opts; m->token != Opt_err; m++) {
 		int want_set = m->flags & MOPT_SET;
 		if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) ||
-		    (m->flags & MOPT_CLEAR_ERR))
+		    (m->flags & MOPT_CLEAR_ERR) || m->flags & MOPT_SKIP)
 			continue;
 		if (!nodefs && !(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt)))
 			continue; /* skip if same as the default */
@@ -2353,6 +2404,17 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 
 	fscrypt_show_test_dummy_encryption(seq, sep, sb);
 
+	if (test_opt(sb, DAX_ALWAYS)) {
+		if (IS_EXT2_SB(sb))
+			SEQ_OPTS_PUTS("dax");
+		else
+			SEQ_OPTS_PUTS("dax=always");
+	} else if (test_opt2(sb, DAX_NEVER)) {
+		SEQ_OPTS_PUTS("dax=never");
+	} else if (test_opt2(sb, DAX_INODE)) {
+		SEQ_OPTS_PUTS("dax=inode");
+	}
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -2383,6 +2445,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		ext4_msg(sb, KERN_ERR, "revision level too high, "
 			 "forcing read-only mode");
 		err = -EROFS;
+		goto done;
 	}
 	if (read_only)
 		goto done;
@@ -4017,7 +4080,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "both data=journal and delalloc");
 			goto failed_mount;
 		}
-		if (test_opt(sb, DAX)) {
+		if (test_opt(sb, DAX_ALWAYS)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
 				 "both data=journal and dax");
 			goto failed_mount;
@@ -4127,13 +4190,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
-	if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
+	if (bdev_dax_supported(sb->s_bdev, blocksize))
+		set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+
+	if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
 		if (ext4_has_feature_inline_data(sb)) {
 			ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem"
 					" that may contain inline data");
 			goto failed_mount;
 		}
-		if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
+		if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) {
 			ext4_msg(sb, KERN_ERR,
 				"DAX unsupported by block device.");
 			goto failed_mount;
@@ -5447,12 +5513,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			err = -EINVAL;
 			goto restore_opts;
 		}
-		if (test_opt(sb, DAX)) {
-			ext4_msg(sb, KERN_ERR, "can't mount with "
-				 "both data=journal and dax");
-			err = -EINVAL;
-			goto restore_opts;
-		}
 	} else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) {
 		if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
@@ -5468,12 +5528,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
-	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
-		ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
-			"dax flag with busy inodes while remounting");
-		sbi->s_mount_opt ^= EXT4_MOUNT_DAX;
-	}
-
 	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
 		ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user");
 
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index dec1244dd062..bbd5e7e0632b 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -113,6 +113,9 @@ static int ext4_begin_enable_verity(struct file *filp)
 	handle_t *handle;
 	int err;
 
+	if (IS_DAX(inode) || ext4_test_inode_flag(inode, EXT4_INODE_DAX))
+		return -EINVAL;
+
 	if (ext4_verity_in_progress(inode))
 		return -EBUSY;
 
@@ -241,7 +244,7 @@ static int ext4_end_enable_verity(struct file *filp, const void *desc,
 		if (err)
 			goto out_stop;
 		ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
-		ext4_set_inode_flags(inode);
+		ext4_set_inode_flags(inode, false);
 		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 	}
 out_stop:
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 9b29a40738ac..7d2f6576d954 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -93,6 +93,7 @@ static const struct xattr_handler * const ext4_xattr_handler_map[] = {
 #ifdef CONFIG_EXT4_FS_SECURITY
 	[EXT4_XATTR_INDEX_SECURITY]	     = &ext4_xattr_security_handler,
 #endif
+	[EXT4_XATTR_INDEX_HURD]		     = &ext4_xattr_hurd_handler,
 };
 
 const struct xattr_handler *ext4_xattr_handlers[] = {
@@ -105,6 +106,7 @@ const struct xattr_handler *ext4_xattr_handlers[] = {
 #ifdef CONFIG_EXT4_FS_SECURITY
 	&ext4_xattr_security_handler,
 #endif
+	&ext4_xattr_hurd_handler,
 	NULL
 };
 
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index ffe21ac77f78..730b91fa0dd7 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -124,6 +124,7 @@ struct ext4_xattr_inode_array {
 extern const struct xattr_handler ext4_xattr_user_handler;
 extern const struct xattr_handler ext4_xattr_trusted_handler;
 extern const struct xattr_handler ext4_xattr_security_handler;
+extern const struct xattr_handler ext4_xattr_hurd_handler;
 
 #define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c"
 
diff --git a/fs/ext4/xattr_hurd.c b/fs/ext4/xattr_hurd.c
new file mode 100644
index 000000000000..8cfa74a56361
--- /dev/null
+++ b/fs/ext4/xattr_hurd.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/xattr_hurd.c
+ * Handler for extended gnu attributes for the Hurd.
+ *
+ * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ * Copyright (C) 2020 by Jan (janneke) Nieuwenhuizen, <janneke@gnu.org>
+ */
+
+#include <linux/init.h>
+#include <linux/string.h>
+#include "ext4.h"
+#include "xattr.h"
+
+static bool
+ext4_xattr_hurd_list(struct dentry *dentry)
+{
+	return test_opt(dentry->d_sb, XATTR_USER);
+}
+
+static int
+ext4_xattr_hurd_get(const struct xattr_handler *handler,
+		    struct dentry *unused, struct inode *inode,
+		    const char *name, void *buffer, size_t size)
+{
+	if (!test_opt(inode->i_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+
+	return ext4_xattr_get(inode, EXT4_XATTR_INDEX_HURD,
+			      name, buffer, size);
+}
+
+static int
+ext4_xattr_hurd_set(const struct xattr_handler *handler,
+		    struct dentry *unused, struct inode *inode,
+		    const char *name, const void *value,
+		    size_t size, int flags)
+{
+	if (!test_opt(inode->i_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+
+	return ext4_xattr_set(inode, EXT4_XATTR_INDEX_HURD,
+			      name, value, size, flags);
+}
+
+const struct xattr_handler ext4_xattr_hurd_handler = {
+	.prefix	= XATTR_HURD_PREFIX,
+	.list	= ext4_xattr_hurd_list,
+	.get	= ext4_xattr_hurd_get,
+	.set	= ext4_xattr_hurd_set,
+};
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e573b0cd2737..83d917f7e542 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -18,6 +18,7 @@
 #include <linux/swap.h>
 #include <linux/falloc.h>
 #include <linux/uio.h>
+#include <linux/fs.h>
 
 static struct page **fuse_pages_alloc(unsigned int npages, gfp_t flags,
 				      struct fuse_page_desc **desc)
@@ -1586,7 +1587,6 @@ static void fuse_writepage_finish(struct fuse_conn *fc,
 	struct backing_dev_info *bdi = inode_to_bdi(inode);
 	int i;
 
-	rb_erase(&wpa->writepages_entry, &fi->writepages);
 	for (i = 0; i < ap->num_pages; i++) {
 		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
 		dec_node_page_state(ap->pages[i], NR_WRITEBACK_TEMP);
@@ -1637,6 +1637,7 @@ __acquires(fi->lock)
 
  out_free:
 	fi->writectr--;
+	rb_erase(&wpa->writepages_entry, &fi->writepages);
 	fuse_writepage_finish(fc, wpa);
 	spin_unlock(&fi->lock);
 
@@ -1674,7 +1675,8 @@ __acquires(fi->lock)
 	}
 }
 
-static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
+static struct fuse_writepage_args *fuse_insert_writeback(struct rb_root *root,
+						struct fuse_writepage_args *wpa)
 {
 	pgoff_t idx_from = wpa->ia.write.in.offset >> PAGE_SHIFT;
 	pgoff_t idx_to = idx_from + wpa->ia.ap.num_pages - 1;
@@ -1697,11 +1699,17 @@ static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
 		else if (idx_to < curr_index)
 			p = &(*p)->rb_left;
 		else
-			return (void) WARN_ON(true);
+			return curr;
 	}
 
 	rb_link_node(&wpa->writepages_entry, parent, p);
 	rb_insert_color(&wpa->writepages_entry, root);
+	return NULL;
+}
+
+static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
+{
+	WARN_ON(fuse_insert_writeback(root, wpa));
 }
 
 static void fuse_writepage_end(struct fuse_conn *fc, struct fuse_args *args,
@@ -1714,6 +1722,7 @@ static void fuse_writepage_end(struct fuse_conn *fc, struct fuse_args *args,
 
 	mapping_set_error(inode->i_mapping, error);
 	spin_lock(&fi->lock);
+	rb_erase(&wpa->writepages_entry, &fi->writepages);
 	while (wpa->next) {
 		struct fuse_conn *fc = get_fuse_conn(inode);
 		struct fuse_write_in *inarg = &wpa->ia.write.in;
@@ -1952,14 +1961,14 @@ static void fuse_writepages_send(struct fuse_fill_wb_data *data)
 }
 
 /*
- * First recheck under fi->lock if the offending offset is still under
- * writeback.  If yes, then iterate auxiliary write requests, to see if there's
+ * Check under fi->lock if the page is under writeback, and insert it onto the
+ * rb_tree if not. Otherwise iterate auxiliary write requests, to see if there's
  * one already added for a page at this offset.  If there's none, then insert
  * this new request onto the auxiliary list, otherwise reuse the existing one by
- * copying the new page contents over to the old temporary page.
+ * swapping the new temp page with the old one.
  */
-static bool fuse_writepage_in_flight(struct fuse_writepage_args *new_wpa,
-				     struct page *page)
+static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa,
+			       struct page *page)
 {
 	struct fuse_inode *fi = get_fuse_inode(new_wpa->inode);
 	struct fuse_writepage_args *tmp;
@@ -1967,17 +1976,15 @@ static bool fuse_writepage_in_flight(struct fuse_writepage_args *new_wpa,
 	struct fuse_args_pages *new_ap = &new_wpa->ia.ap;
 
 	WARN_ON(new_ap->num_pages != 0);
+	new_ap->num_pages = 1;
 
 	spin_lock(&fi->lock);
-	rb_erase(&new_wpa->writepages_entry, &fi->writepages);
-	old_wpa = fuse_find_writeback(fi, page->index, page->index);
+	old_wpa = fuse_insert_writeback(&fi->writepages, new_wpa);
 	if (!old_wpa) {
-		tree_insert(&fi->writepages, new_wpa);
 		spin_unlock(&fi->lock);
-		return false;
+		return true;
 	}
 
-	new_ap->num_pages = 1;
 	for (tmp = old_wpa->next; tmp; tmp = tmp->next) {
 		pgoff_t curr_index;
 
@@ -2006,7 +2013,41 @@ static bool fuse_writepage_in_flight(struct fuse_writepage_args *new_wpa,
 		fuse_writepage_free(new_wpa);
 	}
 
-	return true;
+	return false;
+}
+
+static bool fuse_writepage_need_send(struct fuse_conn *fc, struct page *page,
+				     struct fuse_args_pages *ap,
+				     struct fuse_fill_wb_data *data)
+{
+	WARN_ON(!ap->num_pages);
+
+	/*
+	 * Being under writeback is unlikely but possible.  For example direct
+	 * read to an mmaped fuse file will set the page dirty twice; once when
+	 * the pages are faulted with get_user_pages(), and then after the read
+	 * completed.
+	 */
+	if (fuse_page_is_writeback(data->inode, page->index))
+		return true;
+
+	/* Reached max pages */
+	if (ap->num_pages == fc->max_pages)
+		return true;
+
+	/* Reached max write bytes */
+	if ((ap->num_pages + 1) * PAGE_SIZE > fc->max_write)
+		return true;
+
+	/* Discontinuity */
+	if (data->orig_pages[ap->num_pages - 1]->index + 1 != page->index)
+		return true;
+
+	/* Need to grow the pages array?  If so, did the expansion fail? */
+	if (ap->num_pages == data->max_pages && !fuse_pages_realloc(data))
+		return true;
+
+	return false;
 }
 
 static int fuse_writepages_fill(struct page *page,
@@ -2019,7 +2060,6 @@ static int fuse_writepages_fill(struct page *page,
 	struct fuse_inode *fi = get_fuse_inode(inode);
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct page *tmp_page;
-	bool is_writeback;
 	int err;
 
 	if (!data->ff) {
@@ -2029,25 +2069,9 @@ static int fuse_writepages_fill(struct page *page,
 			goto out_unlock;
 	}
 
-	/*
-	 * Being under writeback is unlikely but possible.  For example direct
-	 * read to an mmaped fuse file will set the page dirty twice; once when
-	 * the pages are faulted with get_user_pages(), and then after the read
-	 * completed.
-	 */
-	is_writeback = fuse_page_is_writeback(inode, page->index);
-
-	if (wpa && ap->num_pages &&
-	    (is_writeback || ap->num_pages == fc->max_pages ||
-	     (ap->num_pages + 1) * PAGE_SIZE > fc->max_write ||
-	     data->orig_pages[ap->num_pages - 1]->index + 1 != page->index)) {
+	if (wpa && fuse_writepage_need_send(fc, page, ap, data)) {
 		fuse_writepages_send(data);
 		data->wpa = NULL;
-	} else if (wpa && ap->num_pages == data->max_pages) {
-		if (!fuse_pages_realloc(data)) {
-			fuse_writepages_send(data);
-			data->wpa = NULL;
-		}
 	}
 
 	err = -ENOMEM;
@@ -2085,12 +2109,6 @@ static int fuse_writepages_fill(struct page *page,
 		ap->args.end = fuse_writepage_end;
 		ap->num_pages = 0;
 		wpa->inode = inode;
-
-		spin_lock(&fi->lock);
-		tree_insert(&fi->writepages, wpa);
-		spin_unlock(&fi->lock);
-
-		data->wpa = wpa;
 	}
 	set_page_writeback(page);
 
@@ -2098,26 +2116,25 @@ static int fuse_writepages_fill(struct page *page,
 	ap->pages[ap->num_pages] = tmp_page;
 	ap->descs[ap->num_pages].offset = 0;
 	ap->descs[ap->num_pages].length = PAGE_SIZE;
+	data->orig_pages[ap->num_pages] = page;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;
-	if (is_writeback && fuse_writepage_in_flight(wpa, page)) {
+	if (data->wpa) {
+		/*
+		 * Protected by fi->lock against concurrent access by
+		 * fuse_page_is_writeback().
+		 */
+		spin_lock(&fi->lock);
+		ap->num_pages++;
+		spin_unlock(&fi->lock);
+	} else if (fuse_writepage_add(wpa, page)) {
+		data->wpa = wpa;
+	} else {
 		end_page_writeback(page);
-		data->wpa = NULL;
-		goto out_unlock;
 	}
-	data->orig_pages[ap->num_pages] = page;
-
-	/*
-	 * Protected by fi->lock against concurrent access by
-	 * fuse_page_is_writeback().
-	 */
-	spin_lock(&fi->lock);
-	ap->num_pages++;
-	spin_unlock(&fi->lock);
-
 out_unlock:
 	unlock_page(page);
 
@@ -2149,10 +2166,8 @@ static int fuse_writepages(struct address_space *mapping,
 
 	err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data);
 	if (data.wpa) {
-		/* Ignore errors if we can write at least one page */
 		WARN_ON(!data.wpa->ia.ap.num_pages);
 		fuse_writepages_send(&data);
-		err = 0;
 	}
 	if (data.ff)
 		fuse_file_put(data.ff, false, false);
@@ -2761,7 +2776,16 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 		struct iovec *iov = iov_page;
 
 		iov->iov_base = (void __user *)arg;
-		iov->iov_len = _IOC_SIZE(cmd);
+
+		switch (cmd) {
+		case FS_IOC_GETFLAGS:
+		case FS_IOC_SETFLAGS:
+			iov->iov_len = sizeof(int);
+			break;
+		default:
+			iov->iov_len = _IOC_SIZE(cmd);
+			break;
+		}
 
 		if (_IOC_DIR(cmd) & _IOC_WRITE) {
 			in_iov = iov;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 5b4aebf5821f..bba747520e9b 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -121,10 +121,12 @@ static void fuse_evict_inode(struct inode *inode)
 	}
 }
 
-static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
+static int fuse_reconfigure(struct fs_context *fc)
 {
+	struct super_block *sb = fc->root->d_sb;
+
 	sync_filesystem(sb);
-	if (*flags & SB_MANDLOCK)
+	if (fc->sb_flags & SB_MANDLOCK)
 		return -EINVAL;
 
 	return 0;
@@ -475,6 +477,17 @@ static int fuse_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	struct fuse_fs_context *ctx = fc->fs_private;
 	int opt;
 
+	if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+		/*
+		 * Ignore options coming from mount(MS_REMOUNT) for backward
+		 * compatibility.
+		 */
+		if (fc->oldapi)
+			return 0;
+
+		return invalfc(fc, "No changes allowed in reconfigure");
+	}
+
 	opt = fs_parse(fc, fuse_fs_parameters, param, &result);
 	if (opt < 0)
 		return opt;
@@ -817,7 +830,6 @@ static const struct super_operations fuse_super_operations = {
 	.evict_inode	= fuse_evict_inode,
 	.write_inode	= fuse_write_inode,
 	.drop_inode	= generic_delete_inode,
-	.remount_fs	= fuse_remount_fs,
 	.put_super	= fuse_put_super,
 	.umount_begin	= fuse_umount_begin,
 	.statfs		= fuse_statfs,
@@ -1296,6 +1308,7 @@ static int fuse_get_tree(struct fs_context *fc)
 static const struct fs_context_operations fuse_context_ops = {
 	.free		= fuse_free_fc,
 	.parse_param	= fuse_parse_param,
+	.reconfigure	= fuse_reconfigure,
 	.get_tree	= fuse_get_tree,
 };
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 72c9560f4467..68cd700a2719 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -468,21 +468,10 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 }
 
 
-/**
- * __gfs2_readpage - readpage
- * @file: The file to read a page for
- * @page: The page to read
- *
- * This is the core of gfs2's readpage. It's used by the internal file
- * reading code as in that case we already hold the glock. Also it's
- * called by gfs2_readpage() once the required lock has been granted.
- */
-
 static int __gfs2_readpage(void *file, struct page *page)
 {
 	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
 	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
-
 	int error;
 
 	if (i_blocksize(page->mapping->host) == PAGE_SIZE &&
@@ -505,36 +494,11 @@ static int __gfs2_readpage(void *file, struct page *page)
  * gfs2_readpage - read a page of a file
  * @file: The file to read
  * @page: The page of the file
- *
- * This deals with the locking required. We have to unlock and
- * relock the page in order to get the locking in the right
- * order.
  */
 
 static int gfs2_readpage(struct file *file, struct page *page)
 {
-	struct address_space *mapping = page->mapping;
-	struct gfs2_inode *ip = GFS2_I(mapping->host);
-	struct gfs2_holder gh;
-	int error;
-
-	unlock_page(page);
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
-	error = gfs2_glock_nq(&gh);
-	if (unlikely(error))
-		goto out;
-	error = AOP_TRUNCATED_PAGE;
-	lock_page(page);
-	if (page->mapping == mapping && !PageUptodate(page))
-		error = __gfs2_readpage(file, page);
-	else
-		unlock_page(page);
-	gfs2_glock_dq(&gh);
-out:
-	gfs2_holder_uninit(&gh);
-	if (error && error != AOP_TRUNCATED_PAGE)
-		lock_page(page);
-	return error;
+	return __gfs2_readpage(file, page);
 }
 
 /**
@@ -598,16 +562,9 @@ static void gfs2_readahead(struct readahead_control *rac)
 {
 	struct inode *inode = rac->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_holder gh;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
-	if (gfs2_glock_nq(&gh))
-		goto out_uninit;
 	if (!gfs2_is_stuffed(ip))
 		mpage_readahead(rac, gfs2_block_map);
-	gfs2_glock_dq(&gh);
-out_uninit:
-	gfs2_holder_uninit(&gh);
 }
 
 /**
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index fe305e4bfd37..bebde537ac8c 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -558,8 +558,29 @@ out_uninit:
 	return block_page_mkwrite_return(ret);
 }
 
+static vm_fault_t gfs2_fault(struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	vm_fault_t ret;
+	int err;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	err = gfs2_glock_nq(&gh);
+	if (err) {
+		ret = block_page_mkwrite_return(err);
+		goto out_uninit;
+	}
+	ret = filemap_fault(vmf);
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
 static const struct vm_operations_struct gfs2_vm_ops = {
-	.fault = filemap_fault,
+	.fault = gfs2_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = gfs2_page_mkwrite,
 };
@@ -824,6 +845,9 @@ out_uninit:
 
 static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	struct gfs2_inode *ip;
+	struct gfs2_holder gh;
+	size_t written = 0;
 	ssize_t ret;
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
@@ -832,7 +856,31 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			return ret;
 		iocb->ki_flags &= ~IOCB_DIRECT;
 	}
-	return generic_file_read_iter(iocb, to);
+	iocb->ki_flags |= IOCB_NOIO;
+	ret = generic_file_read_iter(iocb, to);
+	iocb->ki_flags &= ~IOCB_NOIO;
+	if (ret >= 0) {
+		if (!iov_iter_count(to))
+			return ret;
+		written = ret;
+	} else {
+		if (ret != -EAGAIN)
+			return ret;
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return ret;
+	}
+	ip = GFS2_I(iocb->ki_filp->f_mapping->host);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret)
+		goto out_uninit;
+	ret = generic_file_read_iter(iocb, to);
+	if (ret > 0)
+		written += ret;
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
+	return written ? written : ret;
 }
 
 /**
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 2299dcc417ea..8545024a1401 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1899,7 +1899,10 @@ bool gfs2_delete_work_queued(const struct gfs2_glock *gl)
 
 static void flush_delete_work(struct gfs2_glock *gl)
 {
-	flush_delayed_work(&gl->gl_delete);
+	if (cancel_delayed_work(&gl->gl_delete)) {
+		queue_delayed_work(gfs2_delete_workqueue,
+				   &gl->gl_delete, 0);
+	}
 	gfs2_glock_queue_work(gl, 0);
 }
 
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index c84887769b5a..de1d5f1d9ff8 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -531,8 +531,7 @@ static int freeze_go_sync(struct gfs2_glock *gl)
 	int error = 0;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
-	if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) &&
-	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+	if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) {
 		atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE);
 		error = freeze_super(sdp->sd_vfs);
 		if (error) {
@@ -545,8 +544,11 @@ static int freeze_go_sync(struct gfs2_glock *gl)
 			gfs2_assert_withdraw(sdp, 0);
 		}
 		queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work);
-		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
-			       GFS2_LFC_FREEZE_GO_SYNC);
+		if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+			gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
+				       GFS2_LFC_FREEZE_GO_SYNC);
+		else /* read-only mounts */
+			atomic_set(&sdp->sd_freeze_state, SFS_FROZEN);
 	}
 	return 0;
 }
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 03ab11fab962..ca2ec02436ec 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -399,7 +399,6 @@ enum {
 	GIF_QD_LOCKED		= 1,
 	GIF_ALLOC_FAILED	= 2,
 	GIF_SW_PAGED		= 3,
-	GIF_ORDERED		= 4,
 	GIF_FREE_VFS_INODE      = 5,
 	GIF_GLOP_PENDING	= 6,
 	GIF_DEFERRED_DELETE	= 7,
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 370c3a4b31ac..6774865f5b5b 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -207,10 +207,11 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 
 	if (no_formal_ino && ip->i_no_formal_ino &&
 	    no_formal_ino != ip->i_no_formal_ino) {
+		error = -ESTALE;
 		if (inode->i_state & I_NEW)
 			goto fail;
 		iput(inode);
-		return ERR_PTR(-ESTALE);
+		return ERR_PTR(error);
 	}
 
 	if (inode->i_state & I_NEW)
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 3e4734431783..a76e55bc28eb 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -613,6 +613,12 @@ static int ip_cmp(void *priv, struct list_head *a, struct list_head *b)
 	return 0;
 }
 
+static void __ordered_del_inode(struct gfs2_inode *ip)
+{
+	if (!list_empty(&ip->i_ordered))
+		list_del_init(&ip->i_ordered);
+}
+
 static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 {
 	struct gfs2_inode *ip;
@@ -623,8 +629,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 	while (!list_empty(&sdp->sd_log_ordered)) {
 		ip = list_first_entry(&sdp->sd_log_ordered, struct gfs2_inode, i_ordered);
 		if (ip->i_inode.i_mapping->nrpages == 0) {
-			test_and_clear_bit(GIF_ORDERED, &ip->i_flags);
-			list_del(&ip->i_ordered);
+			__ordered_del_inode(ip);
 			continue;
 		}
 		list_move(&ip->i_ordered, &written);
@@ -643,8 +648,7 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
 	spin_lock(&sdp->sd_ordered_lock);
 	while (!list_empty(&sdp->sd_log_ordered)) {
 		ip = list_first_entry(&sdp->sd_log_ordered, struct gfs2_inode, i_ordered);
-		list_del(&ip->i_ordered);
-		WARN_ON(!test_and_clear_bit(GIF_ORDERED, &ip->i_flags));
+		__ordered_del_inode(ip);
 		if (ip->i_inode.i_mapping->nrpages == 0)
 			continue;
 		spin_unlock(&sdp->sd_ordered_lock);
@@ -659,8 +663,7 @@ void gfs2_ordered_del_inode(struct gfs2_inode *ip)
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 
 	spin_lock(&sdp->sd_ordered_lock);
-	if (test_and_clear_bit(GIF_ORDERED, &ip->i_flags))
-		list_del(&ip->i_ordered);
+	__ordered_del_inode(ip);
 	spin_unlock(&sdp->sd_ordered_lock);
 }
 
@@ -1002,6 +1005,16 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 
 out:
 	if (gfs2_withdrawn(sdp)) {
+		/**
+		 * If the tr_list is empty, we're withdrawing during a log
+		 * flush that targets a transaction, but the transaction was
+		 * never queued onto any of the ail lists. Here we add it to
+		 * ail1 just so that ail_drain() will find and free it.
+		 */
+		spin_lock(&sdp->sd_ail_lock);
+		if (tr && list_empty(&tr->tr_list))
+			list_add(&tr->tr_list, &sdp->sd_ail1_list);
+		spin_unlock(&sdp->sd_ail_lock);
 		ail_drain(sdp); /* frees all transactions */
 		tr = NULL;
 	}
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index c1cd6ae17659..8965c751a303 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -53,9 +53,9 @@ static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
 	if (gfs2_is_jdata(ip) || !gfs2_is_ordered(sdp))
 		return;
 
-	if (!test_bit(GIF_ORDERED, &ip->i_flags)) {
+	if (list_empty(&ip->i_ordered)) {
 		spin_lock(&sdp->sd_ordered_lock);
-		if (!test_and_set_bit(GIF_ORDERED, &ip->i_flags))
+		if (list_empty(&ip->i_ordered))
 			list_add(&ip->i_ordered, &sdp->sd_log_ordered);
 		spin_unlock(&sdp->sd_ordered_lock);
 	}
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 733470ca6be9..c7393ee9cf68 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -39,6 +39,7 @@ static void gfs2_init_inode_once(void *foo)
 	atomic_set(&ip->i_sizehint, 0);
 	init_rwsem(&ip->i_rw_mutex);
 	INIT_LIST_HEAD(&ip->i_trunc_list);
+	INIT_LIST_HEAD(&ip->i_ordered);
 	ip->i_qadata = NULL;
 	gfs2_holder_mark_uninitialized(&ip->i_rgd_gh);
 	memset(&ip->i_res, 0, sizeof(ip->i_res));
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 094f5fe7c009..6d18d2c91add 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1136,7 +1136,18 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 		goto fail_per_node;
 	}
 
-	if (!sb_rdonly(sb)) {
+	if (sb_rdonly(sb)) {
+		struct gfs2_holder freeze_gh;
+
+		error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP | GL_EXACT,
+					   &freeze_gh);
+		if (error) {
+			fs_err(sdp, "can't make FS RO: %d\n", error);
+			goto fail_per_node;
+		}
+		gfs2_glock_dq_uninit(&freeze_gh);
+	} else {
 		error = gfs2_make_fs_rw(sdp);
 		if (error) {
 			fs_err(sdp, "can't make FS RW: %d\n", error);
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 96c345f49273..390ea79d682c 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -364,8 +364,8 @@ void gfs2_recover_func(struct work_struct *work)
 		/* Acquire a shared hold on the freeze lock */
 
 		error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP | LM_FLAG_PRIORITY,
-					   &thaw_gh);
+					   LM_FLAG_NOEXP | LM_FLAG_PRIORITY |
+					   GL_EXACT, &thaw_gh);
 		if (error)
 			goto fail_gunlock_ji;
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 32d8d26126a1..47d0ae158b69 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -167,7 +167,8 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 	if (error)
 		return error;
 
-	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0,
+	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+				   LM_FLAG_NOEXP | GL_EXACT,
 				   &freeze_gh);
 	if (error)
 		goto fail_threads;
@@ -203,7 +204,6 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 	return 0;
 
 fail:
-	freeze_gh.gh_flags |= GL_NOCACHE;
 	gfs2_glock_dq_uninit(&freeze_gh);
 fail_threads:
 	if (sdp->sd_quotad_process)
@@ -430,7 +430,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp)
 	}
 
 	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE,
-				   GL_NOCACHE, &sdp->sd_freeze_gh);
+				   LM_FLAG_NOEXP, &sdp->sd_freeze_gh);
 	if (error)
 		goto out;
 
@@ -613,13 +613,15 @@ int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 	    !gfs2_glock_is_locked_by_me(sdp->sd_freeze_gl)) {
 		if (!log_write_allowed) {
 			error = gfs2_glock_nq_init(sdp->sd_freeze_gl,
-						   LM_ST_SHARED, GL_NOCACHE |
-						   LM_FLAG_TRY, &freeze_gh);
+						   LM_ST_SHARED, LM_FLAG_TRY |
+						   LM_FLAG_NOEXP | GL_EXACT,
+						   &freeze_gh);
 			if (error == GLR_TRYFAILED)
 				error = 0;
 		} else {
 			error = gfs2_glock_nq_init(sdp->sd_freeze_gl,
-						   LM_ST_SHARED, GL_NOCACHE,
+						   LM_ST_SHARED,
+						   LM_FLAG_NOEXP | GL_EXACT,
 						   &freeze_gh);
 			if (error && !gfs2_withdrawn(sdp))
 				return error;
@@ -761,8 +763,8 @@ void gfs2_freeze_func(struct work_struct *work)
 	struct super_block *sb = sdp->sd_vfs;
 
 	atomic_inc(&sb->s_active);
-	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0,
-				   &freeze_gh);
+	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+				   LM_FLAG_NOEXP | GL_EXACT, &freeze_gh);
 	if (error) {
 		fs_info(sdp, "GFS2: couldn't get freeze lock : %d\n", error);
 		gfs2_assert_withdraw(sdp, 0);
@@ -774,8 +776,6 @@ void gfs2_freeze_func(struct work_struct *work)
 				error);
 			gfs2_assert_withdraw(sdp, 0);
 		}
-		if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
-			freeze_gh.gh_flags |= GL_NOCACHE;
 		gfs2_glock_dq_uninit(&freeze_gh);
 	}
 	deactivate_super(sb);
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 0b65a912b036..47c5f3aeb460 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -903,13 +903,15 @@ void io_wq_cancel_all(struct io_wq *wq)
 struct io_cb_cancel_data {
 	work_cancel_fn *fn;
 	void *data;
+	int nr_running;
+	int nr_pending;
+	bool cancel_all;
 };
 
 static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
 {
 	struct io_cb_cancel_data *match = data;
 	unsigned long flags;
-	bool ret = false;
 
 	/*
 	 * Hold the lock to avoid ->cur_work going out of scope, caller
@@ -920,74 +922,90 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
 	    !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL) &&
 	    match->fn(worker->cur_work, match->data)) {
 		send_sig(SIGINT, worker->task, 1);
-		ret = true;
+		match->nr_running++;
 	}
 	spin_unlock_irqrestore(&worker->lock, flags);
 
-	return ret;
+	return match->nr_running && !match->cancel_all;
 }
 
-static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
-					    struct io_cb_cancel_data *match)
+static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
+				       struct io_cb_cancel_data *match)
 {
 	struct io_wq_work_node *node, *prev;
 	struct io_wq_work *work;
 	unsigned long flags;
-	bool found = false;
 
-	/*
-	 * First check pending list, if we're lucky we can just remove it
-	 * from there. CANCEL_OK means that the work is returned as-new,
-	 * no completion will be posted for it.
-	 */
+retry:
 	spin_lock_irqsave(&wqe->lock, flags);
 	wq_list_for_each(node, prev, &wqe->work_list) {
 		work = container_of(node, struct io_wq_work, list);
+		if (!match->fn(work, match->data))
+			continue;
 
-		if (match->fn(work, match->data)) {
-			wq_list_del(&wqe->work_list, node, prev);
-			found = true;
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&wqe->lock, flags);
-
-	if (found) {
+		wq_list_del(&wqe->work_list, node, prev);
+		spin_unlock_irqrestore(&wqe->lock, flags);
 		io_run_cancel(work, wqe);
-		return IO_WQ_CANCEL_OK;
+		match->nr_pending++;
+		if (!match->cancel_all)
+			return;
+
+		/* not safe to continue after unlock */
+		goto retry;
 	}
+	spin_unlock_irqrestore(&wqe->lock, flags);
+}
 
-	/*
-	 * Now check if a free (going busy) or busy worker has the work
-	 * currently running. If we find it there, we'll return CANCEL_RUNNING
-	 * as an indication that we attempt to signal cancellation. The
-	 * completion will run normally in this case.
-	 */
+static void io_wqe_cancel_running_work(struct io_wqe *wqe,
+				       struct io_cb_cancel_data *match)
+{
 	rcu_read_lock();
-	found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, match);
+	io_wq_for_each_worker(wqe, io_wq_worker_cancel, match);
 	rcu_read_unlock();
-	return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
 }
 
 enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
-				  void *data)
+				  void *data, bool cancel_all)
 {
 	struct io_cb_cancel_data match = {
-		.fn	= cancel,
-		.data	= data,
+		.fn		= cancel,
+		.data		= data,
+		.cancel_all	= cancel_all,
 	};
-	enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
 	int node;
 
+	/*
+	 * First check pending list, if we're lucky we can just remove it
+	 * from there. CANCEL_OK means that the work is returned as-new,
+	 * no completion will be posted for it.
+	 */
 	for_each_node(node) {
 		struct io_wqe *wqe = wq->wqes[node];
 
-		ret = io_wqe_cancel_work(wqe, &match);
-		if (ret != IO_WQ_CANCEL_NOTFOUND)
-			break;
+		io_wqe_cancel_pending_work(wqe, &match);
+		if (match.nr_pending && !match.cancel_all)
+			return IO_WQ_CANCEL_OK;
 	}
 
-	return ret;
+	/*
+	 * Now check if a free (going busy) or busy worker has the work
+	 * currently running. If we find it there, we'll return CANCEL_RUNNING
+	 * as an indication that we attempt to signal cancellation. The
+	 * completion will run normally in this case.
+	 */
+	for_each_node(node) {
+		struct io_wqe *wqe = wq->wqes[node];
+
+		io_wqe_cancel_running_work(wqe, &match);
+		if (match.nr_running && !match.cancel_all)
+			return IO_WQ_CANCEL_RUNNING;
+	}
+
+	if (match.nr_running)
+		return IO_WQ_CANCEL_RUNNING;
+	if (match.nr_pending)
+		return IO_WQ_CANCEL_OK;
+	return IO_WQ_CANCEL_NOTFOUND;
 }
 
 static bool io_wq_io_cb_cancel_data(struct io_wq_work *work, void *data)
@@ -997,21 +1015,7 @@ static bool io_wq_io_cb_cancel_data(struct io_wq_work *work, void *data)
 
 enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
 {
-	return io_wq_cancel_cb(wq, io_wq_io_cb_cancel_data, (void *)cwork);
-}
-
-static bool io_wq_pid_match(struct io_wq_work *work, void *data)
-{
-	pid_t pid = (pid_t) (unsigned long) data;
-
-	return work->task_pid == pid;
-}
-
-enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid)
-{
-	void *data = (void *) (unsigned long) pid;
-
-	return io_wq_cancel_cb(wq, io_wq_pid_match, data);
+	return io_wq_cancel_cb(wq, io_wq_io_cb_cancel_data, (void *)cwork, false);
 }
 
 struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 8e138fa88b9f..071f1a997800 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -90,7 +90,6 @@ struct io_wq_work {
 	const struct cred *creds;
 	struct fs_struct *fs;
 	unsigned flags;
-	pid_t task_pid;
 };
 
 static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
@@ -125,12 +124,11 @@ static inline bool io_wq_is_hashed(struct io_wq_work *work)
 
 void io_wq_cancel_all(struct io_wq *wq);
 enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
-enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid);
 
 typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
 
 enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
-					void *data);
+					void *data, bool cancel_all);
 
 struct task_struct *io_wq_get_task(struct io_wq *wq);
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 155f3d830ddb..32b0064f806e 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -541,6 +541,7 @@ enum {
 	REQ_F_NO_FILE_TABLE_BIT,
 	REQ_F_QUEUE_TIMEOUT_BIT,
 	REQ_F_WORK_INITIALIZED_BIT,
+	REQ_F_TASK_PINNED_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -598,10 +599,13 @@ enum {
 	REQ_F_QUEUE_TIMEOUT	= BIT(REQ_F_QUEUE_TIMEOUT_BIT),
 	/* io_wq_work is initialized */
 	REQ_F_WORK_INITIALIZED	= BIT(REQ_F_WORK_INITIALIZED_BIT),
+	/* req->task is refcounted */
+	REQ_F_TASK_PINNED	= BIT(REQ_F_TASK_PINNED_BIT),
 };
 
 struct async_poll {
 	struct io_poll_iocb	poll;
+	struct io_poll_iocb	*double_poll;
 	struct io_wq_work	work;
 };
 
@@ -887,6 +891,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 				 struct io_uring_files_update *ip,
 				 unsigned nr_args);
 static int io_grab_files(struct io_kiocb *req);
+static void io_complete_rw_common(struct kiocb *kiocb, long res);
 static void io_cleanup_req(struct io_kiocb *req);
 static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
 		       int fd, struct file **out_file, bool fixed);
@@ -910,6 +915,21 @@ struct sock *io_uring_get_socket(struct file *file)
 }
 EXPORT_SYMBOL(io_uring_get_socket);
 
+static void io_get_req_task(struct io_kiocb *req)
+{
+	if (req->flags & REQ_F_TASK_PINNED)
+		return;
+	get_task_struct(req->task);
+	req->flags |= REQ_F_TASK_PINNED;
+}
+
+/* not idempotent -- it doesn't clear REQ_F_TASK_PINNED */
+static void __io_put_req_task(struct io_kiocb *req)
+{
+	if (req->flags & REQ_F_TASK_PINNED)
+		put_task_struct(req->task);
+}
+
 static void io_file_put_work(struct work_struct *work);
 
 /*
@@ -1045,8 +1065,6 @@ static inline void io_req_work_grab_env(struct io_kiocb *req,
 		}
 		spin_unlock(&current->fs->lock);
 	}
-	if (!req->work.task_pid)
-		req->work.task_pid = task_pid_vnr(current);
 }
 
 static inline void io_req_work_drop_env(struct io_kiocb *req)
@@ -1079,6 +1097,8 @@ static inline void io_prep_async_work(struct io_kiocb *req,
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
 
+	io_req_init_async(req);
+
 	if (req->flags & REQ_F_ISREG) {
 		if (def->hash_reg_file)
 			io_wq_hash_work(&req->work, file_inode(req->file));
@@ -1256,6 +1276,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 	if (cqe) {
 		clear_bit(0, &ctx->sq_check_overflow);
 		clear_bit(0, &ctx->cq_check_overflow);
+		ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
 	}
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 	io_cqring_ev_posted(ctx);
@@ -1293,6 +1314,7 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
 		if (list_empty(&ctx->cq_overflow_list)) {
 			set_bit(0, &ctx->sq_check_overflow);
 			set_bit(0, &ctx->cq_check_overflow);
+			ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
 		}
 		req->flags |= REQ_F_OVERFLOW;
 		refcount_inc(&req->refs);
@@ -1398,9 +1420,7 @@ static void __io_req_aux_free(struct io_kiocb *req)
 	kfree(req->io);
 	if (req->file)
 		io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE));
-	if (req->task)
-		put_task_struct(req->task);
-
+	__io_put_req_task(req);
 	io_req_work_drop_env(req);
 }
 
@@ -1727,6 +1747,26 @@ static int io_put_kbuf(struct io_kiocb *req)
 	return cflags;
 }
 
+static void io_iopoll_queue(struct list_head *again)
+{
+	struct io_kiocb *req;
+
+	do {
+		req = list_first_entry(again, struct io_kiocb, list);
+		list_del(&req->list);
+
+		/* shouldn't happen unless io_uring is dying, cancel reqs */
+		if (unlikely(!current->mm)) {
+			io_complete_rw_common(&req->rw.kiocb, -EAGAIN);
+			io_put_req(req);
+			continue;
+		}
+
+		refcount_inc(&req->refs);
+		io_queue_async_work(req);
+	} while (!list_empty(again));
+}
+
 /*
  * Find and free completed poll iocbs
  */
@@ -1735,12 +1775,21 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 {
 	struct req_batch rb;
 	struct io_kiocb *req;
+	LIST_HEAD(again);
+
+	/* order with ->result store in io_complete_rw_iopoll() */
+	smp_rmb();
 
 	rb.to_free = rb.need_iter = 0;
 	while (!list_empty(done)) {
 		int cflags = 0;
 
 		req = list_first_entry(done, struct io_kiocb, list);
+		if (READ_ONCE(req->result) == -EAGAIN) {
+			req->iopoll_completed = 0;
+			list_move_tail(&req->list, &again);
+			continue;
+		}
 		list_del(&req->list);
 
 		if (req->flags & REQ_F_BUFFER_SELECTED)
@@ -1758,18 +1807,9 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 	if (ctx->flags & IORING_SETUP_SQPOLL)
 		io_cqring_ev_posted(ctx);
 	io_free_req_many(ctx, &rb);
-}
-
-static void io_iopoll_queue(struct list_head *again)
-{
-	struct io_kiocb *req;
 
-	do {
-		req = list_first_entry(again, struct io_kiocb, list);
-		list_del(&req->list);
-		refcount_inc(&req->refs);
-		io_queue_async_work(req);
-	} while (!list_empty(again));
+	if (!list_empty(&again))
+		io_iopoll_queue(&again);
 }
 
 static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
@@ -1777,7 +1817,6 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 {
 	struct io_kiocb *req, *tmp;
 	LIST_HEAD(done);
-	LIST_HEAD(again);
 	bool spin;
 	int ret;
 
@@ -1803,13 +1842,6 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		if (!list_empty(&done))
 			break;
 
-		if (req->result == -EAGAIN) {
-			list_move_tail(&req->list, &again);
-			continue;
-		}
-		if (!list_empty(&again))
-			break;
-
 		ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin);
 		if (ret < 0)
 			break;
@@ -1822,9 +1854,6 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 	if (!list_empty(&done))
 		io_iopoll_complete(ctx, nr_events, &done);
 
-	if (!list_empty(&again))
-		io_iopoll_queue(&again);
-
 	return ret;
 }
 
@@ -1973,11 +2002,13 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
 	if (kiocb->ki_flags & IOCB_WRITE)
 		kiocb_end_write(req);
 
-	if (res != req->result)
+	if (res != -EAGAIN && res != req->result)
 		req_set_fail_links(req);
-	req->result = res;
-	if (res != -EAGAIN)
-		WRITE_ONCE(req->iopoll_completed, 1);
+
+	WRITE_ONCE(req->result, res);
+	/* order with io_poll_complete() checking ->result */
+	smp_wmb();
+	WRITE_ONCE(req->iopoll_completed, 1);
 }
 
 /*
@@ -2650,8 +2681,8 @@ copy_iov:
 		}
 	}
 out_free:
-	kfree(iovec);
-	req->flags &= ~REQ_F_NEED_CLEANUP;
+	if (!(req->flags & REQ_F_NEED_CLEANUP))
+		kfree(iovec);
 	return ret;
 }
 
@@ -2773,8 +2804,8 @@ copy_iov:
 		}
 	}
 out_free:
-	req->flags &= ~REQ_F_NEED_CLEANUP;
-	kfree(iovec);
+	if (!(req->flags & REQ_F_NEED_CLEANUP))
+		kfree(iovec);
 	return ret;
 }
 
@@ -3524,6 +3555,7 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
 
+	io->msg.msg.msg_name = &io->msg.addr;
 	io->msg.iov = io->msg.fast_iov;
 	ret = sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
 					&io->msg.iov);
@@ -3705,6 +3737,7 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
 
 static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_ctx *io)
 {
+	io->msg.msg.msg_name = &io->msg.addr;
 	io->msg.iov = io->msg.fast_iov;
 
 #ifdef CONFIG_COMPAT
@@ -3813,10 +3846,16 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock)
 
 		ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.msg,
 						kmsg->uaddr, flags);
-		if (force_nonblock && ret == -EAGAIN)
-			return io_setup_async_msg(req, kmsg);
+		if (force_nonblock && ret == -EAGAIN) {
+			ret = io_setup_async_msg(req, kmsg);
+			if (ret != -EAGAIN)
+				kfree(kbuf);
+			return ret;
+		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
+		if (kbuf)
+			kfree(kbuf);
 	}
 
 	if (kmsg && kmsg->iov != kmsg->fast_iov)
@@ -4045,6 +4084,29 @@ struct io_poll_table {
 	int error;
 };
 
+static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb)
+{
+	struct task_struct *tsk = req->task;
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret, notify = TWA_RESUME;
+
+	/*
+	 * SQPOLL kernel thread doesn't need notification, just a wakeup.
+	 * If we're not using an eventfd, then TWA_RESUME is always fine,
+	 * as we won't have dependencies between request completions for
+	 * other kernel wait conditions.
+	 */
+	if (ctx->flags & IORING_SETUP_SQPOLL)
+		notify = 0;
+	else if (ctx->cq_ev_fd)
+		notify = TWA_SIGNAL;
+
+	ret = task_work_add(tsk, cb, notify);
+	if (!ret)
+		wake_up_process(tsk);
+	return ret;
+}
+
 static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 			   __poll_t mask, task_work_func_t func)
 {
@@ -4068,13 +4130,13 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 	 * of executing it. We can't safely execute it anyway, as we may not
 	 * have the needed state needed for it anyway.
 	 */
-	ret = task_work_add(tsk, &req->task_work, true);
+	ret = io_req_task_work_add(req, &req->task_work);
 	if (unlikely(ret)) {
 		WRITE_ONCE(poll->canceled, true);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, true);
+		task_work_add(tsk, &req->task_work, 0);
+		wake_up_process(tsk);
 	}
-	wake_up_process(tsk);
 	return 1;
 }
 
@@ -4098,9 +4160,9 @@ static bool io_poll_rewait(struct io_kiocb *req, struct io_poll_iocb *poll)
 	return false;
 }
 
-static void io_poll_remove_double(struct io_kiocb *req)
+static void io_poll_remove_double(struct io_kiocb *req, void *data)
 {
-	struct io_poll_iocb *poll = (struct io_poll_iocb *) req->io;
+	struct io_poll_iocb *poll = data;
 
 	lockdep_assert_held(&req->ctx->completion_lock);
 
@@ -4120,7 +4182,7 @@ static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 
-	io_poll_remove_double(req);
+	io_poll_remove_double(req, req->io);
 	req->poll.done = true;
 	io_cqring_fill_event(req, error ? error : mangle_poll(mask));
 	io_commit_cqring(ctx);
@@ -4163,21 +4225,21 @@ static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode,
 			       int sync, void *key)
 {
 	struct io_kiocb *req = wait->private;
-	struct io_poll_iocb *poll = (struct io_poll_iocb *) req->io;
+	struct io_poll_iocb *poll = req->apoll->double_poll;
 	__poll_t mask = key_to_poll(key);
 
 	/* for instances that support it check for an event match first: */
 	if (mask && !(mask & poll->events))
 		return 0;
 
-	if (req->poll.head) {
+	if (poll && poll->head) {
 		bool done;
 
-		spin_lock(&req->poll.head->lock);
-		done = list_empty(&req->poll.wait.entry);
+		spin_lock(&poll->head->lock);
+		done = list_empty(&poll->wait.entry);
 		if (!done)
-			list_del_init(&req->poll.wait.entry);
-		spin_unlock(&req->poll.head->lock);
+			list_del_init(&poll->wait.entry);
+		spin_unlock(&poll->head->lock);
 		if (!done)
 			__io_async_wake(req, poll, mask, io_poll_task_func);
 	}
@@ -4197,7 +4259,8 @@ static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
 }
 
 static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
-			    struct wait_queue_head *head)
+			    struct wait_queue_head *head,
+			    struct io_poll_iocb **poll_ptr)
 {
 	struct io_kiocb *req = pt->req;
 
@@ -4208,7 +4271,7 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
 	 */
 	if (unlikely(poll->head)) {
 		/* already have a 2nd entry, fail a third attempt */
-		if (req->io) {
+		if (*poll_ptr) {
 			pt->error = -EINVAL;
 			return;
 		}
@@ -4220,7 +4283,7 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
 		io_init_poll_iocb(poll, req->poll.events, io_poll_double_wake);
 		refcount_inc(&req->refs);
 		poll->wait.private = req;
-		req->io = (void *) poll;
+		*poll_ptr = poll;
 	}
 
 	pt->error = 0;
@@ -4232,8 +4295,31 @@ static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
 			       struct poll_table_struct *p)
 {
 	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
+	struct async_poll *apoll = pt->req->apoll;
 
-	__io_queue_proc(&pt->req->apoll->poll, pt, head);
+	__io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll);
+}
+
+static void io_sq_thread_drop_mm(struct io_ring_ctx *ctx)
+{
+	struct mm_struct *mm = current->mm;
+
+	if (mm) {
+		kthread_unuse_mm(mm);
+		mmput(mm);
+	}
+}
+
+static int io_sq_thread_acquire_mm(struct io_ring_ctx *ctx,
+				   struct io_kiocb *req)
+{
+	if (io_op_defs[req->opcode].needs_mm && !current->mm) {
+		if (unlikely(!mmget_not_zero(ctx->sqo_mm)))
+			return -EFAULT;
+		kthread_use_mm(ctx->sqo_mm);
+	}
+
+	return 0;
 }
 
 static void io_async_task_func(struct callback_head *cb)
@@ -4261,20 +4347,27 @@ static void io_async_task_func(struct callback_head *cb)
 		}
 	}
 
+	io_poll_remove_double(req, apoll->double_poll);
 	spin_unlock_irq(&ctx->completion_lock);
 
 	/* restore ->work in case we need to retry again */
 	if (req->flags & REQ_F_WORK_INITIALIZED)
 		memcpy(&req->work, &apoll->work, sizeof(req->work));
+	kfree(apoll->double_poll);
 	kfree(apoll);
 
 	if (!canceled) {
 		__set_current_state(TASK_RUNNING);
+		if (io_sq_thread_acquire_mm(ctx, req)) {
+			io_cqring_add_event(req, -EFAULT);
+			goto end_req;
+		}
 		mutex_lock(&ctx->uring_lock);
 		__io_queue_sqe(req, NULL);
 		mutex_unlock(&ctx->uring_lock);
 	} else {
 		io_cqring_ev_posted(ctx);
+end_req:
 		req_set_fail_links(req);
 		io_double_put_req(req);
 	}
@@ -4348,7 +4441,6 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
 	struct async_poll *apoll;
 	struct io_poll_table ipt;
 	__poll_t mask, ret;
-	bool had_io;
 
 	if (!req->file || !file_can_poll(req->file))
 		return false;
@@ -4360,14 +4452,13 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
 	apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
 	if (unlikely(!apoll))
 		return false;
+	apoll->double_poll = NULL;
 
 	req->flags |= REQ_F_POLLED;
 	if (req->flags & REQ_F_WORK_INITIALIZED)
 		memcpy(&apoll->work, &req->work, sizeof(req->work));
-	had_io = req->io != NULL;
 
-	get_task_struct(current);
-	req->task = current;
+	io_get_req_task(req);
 	req->apoll = apoll;
 	INIT_HLIST_NODE(&req->hash_node);
 
@@ -4383,13 +4474,11 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
 	ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask,
 					io_async_wake);
 	if (ret) {
-		ipt.error = 0;
-		/* only remove double add if we did it here */
-		if (!had_io)
-			io_poll_remove_double(req);
+		io_poll_remove_double(req, apoll->double_poll);
 		spin_unlock_irq(&ctx->completion_lock);
 		if (req->flags & REQ_F_WORK_INITIALIZED)
 			memcpy(&req->work, &apoll->work, sizeof(req->work));
+		kfree(apoll->double_poll);
 		kfree(apoll);
 		return false;
 	}
@@ -4420,11 +4509,13 @@ static bool io_poll_remove_one(struct io_kiocb *req)
 	bool do_complete;
 
 	if (req->opcode == IORING_OP_POLL_ADD) {
-		io_poll_remove_double(req);
+		io_poll_remove_double(req, req->io);
 		do_complete = __io_poll_remove_one(req, &req->poll);
 	} else {
 		struct async_poll *apoll = req->apoll;
 
+		io_poll_remove_double(req, apoll->double_poll);
+
 		/* non-poll requests have submit ref still */
 		do_complete = __io_poll_remove_one(req, &apoll->poll);
 		if (do_complete) {
@@ -4437,6 +4528,7 @@ static bool io_poll_remove_one(struct io_kiocb *req)
 			if (req->flags & REQ_F_WORK_INITIALIZED)
 				memcpy(&req->work, &apoll->work,
 				       sizeof(req->work));
+			kfree(apoll->double_poll);
 			kfree(apoll);
 		}
 	}
@@ -4537,7 +4629,7 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
 {
 	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
 
-	__io_queue_proc(&pt->req->poll, pt, head);
+	__io_queue_proc(&pt->req->poll, pt, head, (struct io_poll_iocb **) &pt->req->io);
 }
 
 static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -4555,8 +4647,7 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
 	events = READ_ONCE(sqe->poll_events);
 	poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
 
-	get_task_struct(current);
-	req->task = current;
+	io_get_req_task(req);
 	return 0;
 }
 
@@ -4646,7 +4737,9 @@ static int io_timeout_remove_prep(struct io_kiocb *req,
 {
 	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
-	if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len)
+	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
+		return -EINVAL;
+	if (sqe->ioprio || sqe->buf_index || sqe->len)
 		return -EINVAL;
 
 	req->timeout.addr = READ_ONCE(sqe->addr);
@@ -4772,7 +4865,7 @@ static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr)
 	enum io_wq_cancel cancel_ret;
 	int ret = 0;
 
-	cancel_ret = io_wq_cancel_cb(ctx->io_wq, io_cancel_cb, sqe_addr);
+	cancel_ret = io_wq_cancel_cb(ctx->io_wq, io_cancel_cb, sqe_addr, false);
 	switch (cancel_ret) {
 	case IO_WQ_CANCEL_OK:
 		ret = 0;
@@ -4824,8 +4917,9 @@ static int io_async_cancel_prep(struct io_kiocb *req,
 {
 	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
-	if (sqe->flags || sqe->ioprio || sqe->off || sqe->len ||
-	    sqe->cancel_flags)
+	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
+		return -EINVAL;
+	if (sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags)
 		return -EINVAL;
 
 	req->cancel.addr = READ_ONCE(sqe->addr);
@@ -4843,7 +4937,9 @@ static int io_async_cancel(struct io_kiocb *req)
 static int io_files_update_prep(struct io_kiocb *req,
 				const struct io_uring_sqe *sqe)
 {
-	if (sqe->flags || sqe->ioprio || sqe->rw_flags)
+	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
+		return -EINVAL;
+	if (sqe->ioprio || sqe->rw_flags)
 		return -EINVAL;
 
 	req->files_update.offset = READ_ONCE(sqe->off);
@@ -5308,9 +5404,6 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) {
 		const bool in_async = io_wq_current_is_worker();
 
-		if (req->result == -EAGAIN)
-			return -EAGAIN;
-
 		/* workqueue context doesn't hold uring_lock, grab it now */
 		if (in_async)
 			mutex_lock(&ctx->uring_lock);
@@ -5637,6 +5730,7 @@ fail_req:
 		 * Never try inline submit of IOSQE_ASYNC is set, go straight
 		 * to async execution.
 		 */
+		io_req_init_async(req);
 		req->work.flags |= IO_WQ_WORK_CONCURRENT;
 		io_queue_async_work(req);
 	} else {
@@ -5817,17 +5911,14 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	req->flags = 0;
 	/* one is dropped after submission, the other at completion */
 	refcount_set(&req->refs, 2);
-	req->task = NULL;
+	req->task = current;
 	req->result = 0;
 
 	if (unlikely(req->opcode >= IORING_OP_LAST))
 		return -EINVAL;
 
-	if (io_op_defs[req->opcode].needs_mm && !current->mm) {
-		if (unlikely(!mmget_not_zero(ctx->sqo_mm)))
-			return -EFAULT;
-		kthread_use_mm(ctx->sqo_mm);
-	}
+	if (unlikely(io_sq_thread_acquire_mm(ctx, req)))
+		return -EFAULT;
 
 	sqe_flags = READ_ONCE(sqe->flags);
 	/* enforce forwards compatibility on users */
@@ -5936,16 +6027,6 @@ fail_req:
 	return submitted;
 }
 
-static inline void io_sq_thread_drop_mm(struct io_ring_ctx *ctx)
-{
-	struct mm_struct *mm = current->mm;
-
-	if (mm) {
-		kthread_unuse_mm(mm);
-		mmput(mm);
-	}
-}
-
 static int io_sq_thread(void *data)
 {
 	struct io_ring_ctx *ctx = data;
@@ -5979,7 +6060,7 @@ static int io_sq_thread(void *data)
 		 * If submit got -EBUSY, flag us as needing the application
 		 * to enter the kernel to reap and flush events.
 		 */
-		if (!to_submit || ret == -EBUSY) {
+		if (!to_submit || ret == -EBUSY || need_resched()) {
 			/*
 			 * Drop cur_mm before scheduling, we can't hold it for
 			 * long periods (or over schedule()). Do this before
@@ -5995,7 +6076,7 @@ static int io_sq_thread(void *data)
 			 * more IO, we should wait for the application to
 			 * reap events and wake us up.
 			 */
-			if (!list_empty(&ctx->poll_list) ||
+			if (!list_empty(&ctx->poll_list) || need_resched() ||
 			    (!time_after(jiffies, timeout) && ret != -EBUSY &&
 			    !percpu_ref_is_dying(&ctx->refs))) {
 				if (current->task_works)
@@ -6021,9 +6102,9 @@ static int io_sq_thread(void *data)
 			}
 
 			/* Tell userspace we may need a wakeup call */
+			spin_lock_irq(&ctx->completion_lock);
 			ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP;
-			/* make sure to read SQ tail after writing flags */
-			smp_mb();
+			spin_unlock_irq(&ctx->completion_lock);
 
 			to_submit = io_sqring_entries(ctx);
 			if (!to_submit || ret == -EBUSY) {
@@ -6041,13 +6122,17 @@ static int io_sq_thread(void *data)
 				schedule();
 				finish_wait(&ctx->sqo_wait, &wait);
 
+				spin_lock_irq(&ctx->completion_lock);
 				ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+				spin_unlock_irq(&ctx->completion_lock);
 				ret = 0;
 				continue;
 			}
 			finish_wait(&ctx->sqo_wait, &wait);
 
+			spin_lock_irq(&ctx->completion_lock);
 			ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+			spin_unlock_irq(&ctx->completion_lock);
 		}
 
 		mutex_lock(&ctx->uring_lock);
@@ -6146,15 +6231,23 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	do {
 		prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
 						TASK_INTERRUPTIBLE);
+		/* make sure we run task_work before checking for signals */
 		if (current->task_works)
 			task_work_run();
-		if (io_should_wake(&iowq, false))
-			break;
-		schedule();
 		if (signal_pending(current)) {
+			if (current->jobctl & JOBCTL_TASK_WORK) {
+				spin_lock_irq(&current->sighand->siglock);
+				current->jobctl &= ~JOBCTL_TASK_WORK;
+				recalc_sigpending();
+				spin_unlock_irq(&current->sighand->siglock);
+				continue;
+			}
 			ret = -EINTR;
 			break;
 		}
+		if (io_should_wake(&iowq, false))
+			break;
+		schedule();
 	} while (1);
 	finish_wait(&ctx->wait, &iowq.wq);
 
@@ -6626,6 +6719,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 		for (i = 0; i < nr_tables; i++)
 			kfree(ctx->file_data->table[i].files);
 
+		percpu_ref_exit(&ctx->file_data->refs);
 		kfree(ctx->file_data->table);
 		kfree(ctx->file_data);
 		ctx->file_data = NULL;
@@ -6778,8 +6872,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 			}
 			table->files[index] = file;
 			err = io_sqe_file_register(ctx, file, i);
-			if (err)
+			if (err) {
+				fput(file);
 				break;
+			}
 		}
 		nr_args--;
 		done++;
@@ -7275,9 +7371,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_mem_free(ctx->sq_sqes);
 
 	percpu_ref_exit(&ctx->refs);
-	if (ctx->account_mem)
-		io_unaccount_mem(ctx->user,
-				ring_pages(ctx->sq_entries, ctx->cq_entries));
 	free_uid(ctx->user);
 	put_cred(ctx->creds);
 	kfree(ctx->cancel_hash);
@@ -7331,7 +7424,17 @@ static void io_ring_exit_work(struct work_struct *work)
 	if (ctx->rings)
 		io_cqring_overflow_flush(ctx, true);
 
-	wait_for_completion(&ctx->ref_comp);
+	/*
+	 * If we're doing polled IO and end up having requests being
+	 * submitted async (out-of-line), then completions can come in while
+	 * we're waiting for refs to drop. We need to reap these manually,
+	 * as nobody else will be looking for them.
+	 */
+	while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20)) {
+		io_iopoll_reap_events(ctx);
+		if (ctx->rings)
+			io_cqring_overflow_flush(ctx, true);
+	}
 	io_ring_ctx_free(ctx);
 }
 
@@ -7352,6 +7455,16 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 	if (ctx->rings)
 		io_cqring_overflow_flush(ctx, true);
 	idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx);
+
+	/*
+	 * Do this upfront, so we won't have a grace period where the ring
+	 * is closed but resources aren't reaped yet. This can cause
+	 * spurious failure in setting up a new ring.
+	 */
+	if (ctx->account_mem)
+		io_unaccount_mem(ctx->user,
+				ring_pages(ctx->sq_entries, ctx->cq_entries));
+
 	INIT_WORK(&ctx->exit_work, io_ring_exit_work);
 	queue_work(system_wq, &ctx->exit_work);
 }
@@ -7365,9 +7478,22 @@ static int io_uring_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static bool io_wq_files_match(struct io_wq_work *work, void *data)
+{
+	struct files_struct *files = data;
+
+	return work->files == files;
+}
+
 static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 				  struct files_struct *files)
 {
+	if (list_empty_careful(&ctx->inflight_list))
+		return;
+
+	/* cancel all at once, should be faster than doing it one by one*/
+	io_wq_cancel_cb(ctx->io_wq, io_wq_files_match, files, true);
+
 	while (!list_empty_careful(&ctx->inflight_list)) {
 		struct io_kiocb *cancel_req = NULL, *req;
 		DEFINE_WAIT(wait);
@@ -7398,6 +7524,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 			if (list_empty(&ctx->cq_overflow_list)) {
 				clear_bit(0, &ctx->sq_check_overflow);
 				clear_bit(0, &ctx->cq_check_overflow);
+				ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
 			}
 			spin_unlock_irq(&ctx->completion_lock);
 
@@ -7423,6 +7550,14 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 	}
 }
 
+static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
+{
+	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+	struct task_struct *task = data;
+
+	return req->task == task;
+}
+
 static int io_uring_flush(struct file *file, void *data)
 {
 	struct io_ring_ctx *ctx = file->private_data;
@@ -7433,7 +7568,7 @@ static int io_uring_flush(struct file *file, void *data)
 	 * If the task is going away, cancel work it may have pending
 	 */
 	if (fatal_signal_pending(current) || (current->flags & PF_EXITING))
-		io_wq_cancel_pid(ctx->io_wq, task_pid_vnr(current));
+		io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, current, true);
 
 	return 0;
 }
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a49d0e670ddf..e4944436e733 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1140,6 +1140,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	init_waitqueue_head(&journal->j_wait_commit);
 	init_waitqueue_head(&journal->j_wait_updates);
 	init_waitqueue_head(&journal->j_wait_reserved);
+	mutex_init(&journal->j_abort_mutex);
 	mutex_init(&journal->j_barrier);
 	mutex_init(&journal->j_checkpoint_mutex);
 	spin_lock_init(&journal->j_revoke_lock);
@@ -1402,7 +1403,8 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
 		printk(KERN_ERR "JBD2: Error %d detected when updating "
 		       "journal superblock for %s.\n", ret,
 		       journal->j_devname);
-		jbd2_journal_abort(journal, ret);
+		if (!is_journal_aborted(journal))
+			jbd2_journal_abort(journal, ret);
 	}
 
 	return ret;
@@ -2154,6 +2156,13 @@ void jbd2_journal_abort(journal_t *journal, int errno)
 	transaction_t *transaction;
 
 	/*
+	 * Lock the aborting procedure until everything is done, this avoid
+	 * races between filesystem's error handling flow (e.g. ext4_abort()),
+	 * ensure panic after the error info is written into journal's
+	 * superblock.
+	 */
+	mutex_lock(&journal->j_abort_mutex);
+	/*
 	 * ESHUTDOWN always takes precedence because a file system check
 	 * caused by any other journal abort error is not required after
 	 * a shutdown triggered.
@@ -2167,6 +2176,7 @@ void jbd2_journal_abort(journal_t *journal, int errno)
 			journal->j_errno = errno;
 			jbd2_journal_update_sb_errno(journal);
 		}
+		mutex_unlock(&journal->j_abort_mutex);
 		return;
 	}
 
@@ -2188,10 +2198,7 @@ void jbd2_journal_abort(journal_t *journal, int errno)
 	 * layer could realise that a filesystem check is needed.
 	 */
 	jbd2_journal_update_sb_errno(journal);
-
-	write_lock(&journal->j_state_lock);
-	journal->j_flags |= JBD2_REC_ERR;
-	write_unlock(&journal->j_state_lock);
+	mutex_unlock(&journal->j_abort_mutex);
 }
 
 /**
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index 0637271f3770..8ff4d1a1e774 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -259,7 +259,7 @@ struct jffs2_full_dirent
 	uint32_t ino; /* == zero for unlink */
 	unsigned int nhash;
 	unsigned char type;
-	unsigned char name[0];
+	unsigned char name[];
 };
 
 /*
diff --git a/fs/jffs2/summary.h b/fs/jffs2/summary.h
index 60207a2ae952..e4131cb1f1d4 100644
--- a/fs/jffs2/summary.h
+++ b/fs/jffs2/summary.h
@@ -61,7 +61,7 @@ struct jffs2_sum_dirent_flash
 	jint32_t ino; 		/* == zero for unlink */
 	uint8_t nsize;		/* dirent name size */
 	uint8_t type;		/* dirent type */
-	uint8_t name[0];	/* dirent name */
+	uint8_t name[];	/* dirent name */
 } __attribute__((packed));
 
 struct jffs2_sum_xattr_flash
@@ -117,7 +117,7 @@ struct jffs2_sum_dirent_mem
 	jint32_t ino; 		/* == zero for unlink */
 	uint8_t nsize;		/* dirent name size */
 	uint8_t type;		/* dirent type */
-	uint8_t name[0];	/* dirent name */
+	uint8_t name[];	/* dirent name */
 } __attribute__((packed));
 
 struct jffs2_sum_xattr_mem
diff --git a/fs/namespace.c b/fs/namespace.c
index f30ed401cc6d..4a0f600a3328 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2603,6 +2603,7 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags,
 	if (IS_ERR(fc))
 		return PTR_ERR(fc);
 
+	fc->oldapi = true;
 	err = parse_monolithic_mount_data(fc, data);
 	if (!err) {
 		down_write(&sb->s_umount);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 7d399f72ebbb..de03e440b7ee 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -907,9 +907,8 @@ retry:
 		goto out_mds;
 
 	/* Use a direct mapping of ds_idx to pgio mirror_idx */
-	if (WARN_ON_ONCE(pgio->pg_mirror_count !=
-	    FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg)))
-		goto out_mds;
+	if (pgio->pg_mirror_count != FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))
+		goto out_eagain;
 
 	for (i = 0; i < pgio->pg_mirror_count; i++) {
 		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
@@ -931,7 +930,10 @@ retry:
 			(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
 		pgio->pg_maxretrans = io_maxretrans;
 	return;
-
+out_eagain:
+	pnfs_generic_pg_cleanup(pgio);
+	pgio->pg_error = -EAGAIN;
+	return;
 out_mds:
 	trace_pnfs_mds_fallback_pg_init_write(pgio->pg_inode,
 			0, NFS4_MAX_UINT64, IOMODE_RW,
@@ -941,6 +943,7 @@ out_mds:
 	pgio->pg_lseg = NULL;
 	pgio->pg_maxretrans = 0;
 	nfs_pageio_reset_write_mds(pgio);
+	pgio->pg_error = -EAGAIN;
 }
 
 static unsigned int
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index a3ab6e219061..873342308dc0 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -308,6 +308,7 @@ static int try_location(struct fs_context *fc,
 	if (IS_ERR(export_path))
 		return PTR_ERR(export_path);
 
+	kfree(ctx->nfs_server.export_path);
 	ctx->nfs_server.export_path = export_path;
 
 	source = kmalloc(len + 1 + ctx->nfs_server.export_path_len + 1,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e32717fd1169..2e2dac29a9e9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -774,6 +774,14 @@ static void nfs4_slot_sequence_acked(struct nfs4_slot *slot,
 	slot->seq_nr_last_acked = seqnr;
 }
 
+static void nfs4_probe_sequence(struct nfs_client *client, const struct cred *cred,
+				struct nfs4_slot *slot)
+{
+	struct rpc_task *task = _nfs41_proc_sequence(client, cred, slot, true);
+	if (!IS_ERR(task))
+		rpc_put_task_async(task);
+}
+
 static int nfs41_sequence_process(struct rpc_task *task,
 		struct nfs4_sequence_res *res)
 {
@@ -790,6 +798,7 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		goto out;
 
 	session = slot->table->session;
+	clp = session->clp;
 
 	trace_nfs4_sequence_done(session, res);
 
@@ -804,7 +813,6 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		nfs4_slot_sequence_acked(slot, slot->seq_nr);
 		/* Update the slot's sequence and clientid lease timer */
 		slot->seq_done = 1;
-		clp = session->clp;
 		do_renew_lease(clp, res->sr_timestamp);
 		/* Check sequence flags */
 		nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags,
@@ -852,10 +860,18 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		/*
 		 * Were one or more calls using this slot interrupted?
 		 * If the server never received the request, then our
-		 * transmitted slot sequence number may be too high.
+		 * transmitted slot sequence number may be too high. However,
+		 * if the server did receive the request then it might
+		 * accidentally give us a reply with a mismatched operation.
+		 * We can sort this out by sending a lone sequence operation
+		 * to the server on the same slot.
 		 */
 		if ((s32)(slot->seq_nr - slot->seq_nr_last_acked) > 1) {
 			slot->seq_nr--;
+			if (task->tk_msg.rpc_proc != &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE]) {
+				nfs4_probe_sequence(clp, task->tk_msg.rpc_cred, slot);
+				res->sr_slot = NULL;
+			}
 			goto retry_nowait;
 		}
 		/*
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index bb3d2c32664a..c9056316a0b3 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -507,6 +507,17 @@ find_any_file(struct nfs4_file *f)
 	return ret;
 }
 
+static struct nfsd_file *find_deleg_file(struct nfs4_file *f)
+{
+	struct nfsd_file *ret = NULL;
+
+	spin_lock(&f->fi_lock);
+	if (f->fi_deleg_file)
+		ret = nfsd_file_get(f->fi_deleg_file);
+	spin_unlock(&f->fi_lock);
+	return ret;
+}
+
 static atomic_long_t num_delegations;
 unsigned long max_delegations;
 
@@ -2444,6 +2455,8 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st)
 	oo = ols->st_stateowner;
 	nf = st->sc_file;
 	file = find_any_file(nf);
+	if (!file)
+		return 0;
 
 	seq_printf(s, "- ");
 	nfs4_show_stateid(s, &st->sc_stateid);
@@ -2481,6 +2494,8 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st)
 	oo = ols->st_stateowner;
 	nf = st->sc_file;
 	file = find_any_file(nf);
+	if (!file)
+		return 0;
 
 	seq_printf(s, "- ");
 	nfs4_show_stateid(s, &st->sc_stateid);
@@ -2513,7 +2528,9 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st)
 
 	ds = delegstateid(st);
 	nf = st->sc_file;
-	file = nf->fi_deleg_file;
+	file = find_deleg_file(nf);
+	if (!file)
+		return 0;
 
 	seq_printf(s, "- ");
 	nfs4_show_stateid(s, &st->sc_stateid);
@@ -2529,6 +2546,7 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st)
 	seq_printf(s, ", ");
 	nfs4_show_fname(s, file);
 	seq_printf(s, " }\n");
+	nfsd_file_put(file);
 
 	return 0;
 }
@@ -7912,9 +7930,14 @@ nfs4_state_start_net(struct net *net)
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	int ret;
 
-	ret = nfs4_state_create_net(net);
+	ret = get_nfsdfs(net);
 	if (ret)
 		return ret;
+	ret = nfs4_state_create_net(net);
+	if (ret) {
+		mntput(nn->nfsd_mnt);
+		return ret;
+	}
 	locks_start_grace(net, &nn->nfsd4_manager);
 	nfsd4_client_tracking_init(net);
 	if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0)
@@ -7984,6 +8007,7 @@ nfs4_state_shutdown_net(struct net *net)
 
 	nfsd4_client_tracking_exit(net);
 	nfs4_state_destroy_net(net);
+	mntput(nn->nfsd_mnt);
 }
 
 void
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index b68e96681522..cd05732f8eaa 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1335,6 +1335,7 @@ void nfsd_client_rmdir(struct dentry *dentry)
 	WARN_ON_ONCE(ret);
 	fsnotify_rmdir(dir, dentry);
 	d_delete(dentry);
+	dput(dentry);
 	inode_unlock(dir);
 }
 
@@ -1424,6 +1425,18 @@ static struct file_system_type nfsd_fs_type = {
 };
 MODULE_ALIAS_FS("nfsd");
 
+int get_nfsdfs(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct vfsmount *mnt;
+
+	mnt =  vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL);
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+	nn->nfsd_mnt = mnt;
+	return 0;
+}
+
 #ifdef CONFIG_PROC_FS
 static int create_proc_exports_entry(void)
 {
@@ -1451,7 +1464,6 @@ unsigned int nfsd_net_id;
 static __net_init int nfsd_init_net(struct net *net)
 {
 	int retval;
-	struct vfsmount *mnt;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	retval = nfsd_export_init(net);
@@ -1478,16 +1490,8 @@ static __net_init int nfsd_init_net(struct net *net)
 	init_waitqueue_head(&nn->ntf_wq);
 	seqlock_init(&nn->boot_lock);
 
-	mnt =  vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL);
-	if (IS_ERR(mnt)) {
-		retval = PTR_ERR(mnt);
-		goto out_mount_err;
-	}
-	nn->nfsd_mnt = mnt;
 	return 0;
 
-out_mount_err:
-	nfsd_reply_cache_shutdown(nn);
 out_drc_error:
 	nfsd_idmap_shutdown(net);
 out_idmap_error:
@@ -1500,7 +1504,6 @@ static __net_exit void nfsd_exit_net(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	mntput(nn->nfsd_mnt);
 	nfsd_reply_cache_shutdown(nn);
 	nfsd_idmap_shutdown(net);
 	nfsd_export_shutdown(net);
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 36cdd81b6688..57c832d1b30f 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -90,6 +90,8 @@ void		nfsd_destroy(struct net *net);
 
 bool		i_am_nfsd(void);
 
+int get_nfsdfs(struct net *);
+
 struct nfsdfs_client {
 	struct kref cl_ref;
 	void (*cl_release)(struct kref *kref);
@@ -100,6 +102,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
 		struct nfsdfs_client *ncl, u32 id, const struct tree_descr *);
 void nfsd_client_rmdir(struct dentry *dentry);
 
+
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 #ifdef CONFIG_NFSD_V2_ACL
 extern const struct svc_version nfsd_acl_version2;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c3fbab1753ec..d22a056da477 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1226,6 +1226,9 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		iap->ia_mode = 0;
 	iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;
 
+	if (!IS_POSIXACL(dirp))
+		iap->ia_mode &= ~current_umask();
+
 	err = 0;
 	host_err = 0;
 	switch (type) {
@@ -1458,6 +1461,9 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out;
 	}
 
+	if (!IS_POSIXACL(dirp))
+		iap->ia_mode &= ~current_umask();
+
 	host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
 	if (host_err < 0) {
 		fh_drop_write(fhp);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 152a0fc4e905..751bc4dc7466 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -689,6 +689,12 @@ static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res,
 				   &ocfs2_nfs_sync_lops, osb);
 }
 
+static void ocfs2_nfs_sync_lock_init(struct ocfs2_super *osb)
+{
+	ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb);
+	init_rwsem(&osb->nfs_sync_rwlock);
+}
+
 void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb)
 {
 	struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres;
@@ -2855,6 +2861,11 @@ int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex)
 	if (ocfs2_is_hard_readonly(osb))
 		return -EROFS;
 
+	if (ex)
+		down_write(&osb->nfs_sync_rwlock);
+	else
+		down_read(&osb->nfs_sync_rwlock);
+
 	if (ocfs2_mount_local(osb))
 		return 0;
 
@@ -2873,6 +2884,10 @@ void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex)
 	if (!ocfs2_mount_local(osb))
 		ocfs2_cluster_unlock(osb, lockres,
 				     ex ? LKM_EXMODE : LKM_PRMODE);
+	if (ex)
+		up_write(&osb->nfs_sync_rwlock);
+	else
+		up_read(&osb->nfs_sync_rwlock);
 }
 
 int ocfs2_trim_fs_lock(struct ocfs2_super *osb,
@@ -3340,7 +3355,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb)
 local:
 	ocfs2_super_lock_res_init(&osb->osb_super_lockres, osb);
 	ocfs2_rename_lock_res_init(&osb->osb_rename_lockres, osb);
-	ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb);
+	ocfs2_nfs_sync_lock_init(osb);
 	ocfs2_orphan_scan_lock_res_init(&osb->osb_orphan_scan.os_lockres, osb);
 
 	osb->cconn = conn;
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index ee5d98516212..2dd71d626196 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -395,6 +395,7 @@ struct ocfs2_super
 	struct ocfs2_lock_res osb_super_lockres;
 	struct ocfs2_lock_res osb_rename_lockres;
 	struct ocfs2_lock_res osb_nfs_sync_lockres;
+	struct rw_semaphore nfs_sync_rwlock;
 	struct ocfs2_lock_res osb_trim_fs_lockres;
 	struct mutex obs_trim_fs_mutex;
 	struct ocfs2_dlm_debug *osb_dlm_debug;
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 0dd8c41bafd4..19137c6d087b 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -290,7 +290,7 @@
 #define OCFS2_MAX_SLOTS			255
 
 /* Slot map indicator for an empty slot */
-#define OCFS2_INVALID_SLOT		-1
+#define OCFS2_INVALID_SLOT		((u16)-1)
 
 #define OCFS2_VOL_UUID_LEN		16
 #define OCFS2_MAX_VOL_LABEL_LEN		64
@@ -326,8 +326,8 @@ struct ocfs2_system_inode_info {
 enum {
 	BAD_BLOCK_SYSTEM_INODE = 0,
 	GLOBAL_INODE_ALLOC_SYSTEM_INODE,
+#define OCFS2_FIRST_ONLINE_SYSTEM_INODE GLOBAL_INODE_ALLOC_SYSTEM_INODE
 	SLOT_MAP_SYSTEM_INODE,
-#define OCFS2_FIRST_ONLINE_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE
 	HEARTBEAT_SYSTEM_INODE,
 	GLOBAL_BITMAP_SYSTEM_INODE,
 	USER_QUOTA_SYSTEM_INODE,
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 4836becb7578..45745cc3408a 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -2825,9 +2825,12 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res)
 		goto bail;
 	}
 
-	inode_alloc_inode =
-		ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE,
-					    suballoc_slot);
+	if (suballoc_slot == (u16)OCFS2_INVALID_SLOT)
+		inode_alloc_inode = ocfs2_get_system_file_inode(osb,
+			GLOBAL_INODE_ALLOC_SYSTEM_INODE, suballoc_slot);
+	else
+		inode_alloc_inode = ocfs2_get_system_file_inode(osb,
+			INODE_ALLOC_SYSTEM_INODE, suballoc_slot);
 	if (!inode_alloc_inode) {
 		/* the error code could be inaccurate, but we are not able to
 		 * get the correct one. */
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 79dd052c7dbf..5e0cde85bd6b 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -895,7 +895,7 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	return err;
 }
 
-int ovl_copy_up_flags(struct dentry *dentry, int flags)
+static int ovl_copy_up_flags(struct dentry *dentry, int flags)
 {
 	int err = 0;
 	const struct cred *old_cred = ovl_override_creds(dentry->d_sb);
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index 8f4286450f92..0e696f72cf65 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -476,7 +476,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb,
 	if (IS_ERR_OR_NULL(this))
 		return this;
 
-	if (WARN_ON(ovl_dentry_real_at(this, layer->idx) != real)) {
+	if (ovl_dentry_real_at(this, layer->idx) != real) {
 		dput(this);
 		this = ERR_PTR(-EIO);
 	}
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 01820e654a21..0d940e29d62b 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -33,13 +33,16 @@ static char ovl_whatisit(struct inode *inode, struct inode *realinode)
 		return 'm';
 }
 
+/* No atime modificaton nor notify on underlying */
+#define OVL_OPEN_FLAGS (O_NOATIME | FMODE_NONOTIFY)
+
 static struct file *ovl_open_realfile(const struct file *file,
 				      struct inode *realinode)
 {
 	struct inode *inode = file_inode(file);
 	struct file *realfile;
 	const struct cred *old_cred;
-	int flags = file->f_flags | O_NOATIME | FMODE_NONOTIFY;
+	int flags = file->f_flags | OVL_OPEN_FLAGS;
 	int acc_mode = ACC_MODE(flags);
 	int err;
 
@@ -72,8 +75,7 @@ static int ovl_change_flags(struct file *file, unsigned int flags)
 	struct inode *inode = file_inode(file);
 	int err;
 
-	/* No atime modificaton on underlying */
-	flags |= O_NOATIME | FMODE_NONOTIFY;
+	flags |= OVL_OPEN_FLAGS;
 
 	/* If some flag changed that cannot be changed then something's amiss */
 	if (WARN_ON((file->f_flags ^ flags) & ~OVL_SETFL_MASK))
@@ -126,7 +128,7 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real,
 	}
 
 	/* Did the flags change since open? */
-	if (unlikely((file->f_flags ^ real->file->f_flags) & ~O_NOATIME))
+	if (unlikely((file->f_flags ^ real->file->f_flags) & ~OVL_OPEN_FLAGS))
 		return ovl_change_flags(real->file, file->f_flags);
 
 	return 0;
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 3566282a9199..f7d4358db637 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -389,7 +389,7 @@ invalid:
 }
 
 static int ovl_check_origin(struct ovl_fs *ofs, struct dentry *upperdentry,
-			    struct ovl_path **stackp, unsigned int *ctrp)
+			    struct ovl_path **stackp)
 {
 	struct ovl_fh *fh = ovl_get_fh(upperdentry, OVL_XATTR_ORIGIN);
 	int err;
@@ -406,10 +406,6 @@ static int ovl_check_origin(struct ovl_fs *ofs, struct dentry *upperdentry,
 		return err;
 	}
 
-	if (WARN_ON(*ctrp))
-		return -EIO;
-
-	*ctrp = 1;
 	return 0;
 }
 
@@ -861,8 +857,6 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			goto out;
 		}
 		if (upperdentry && !d.is_dir) {
-			unsigned int origin_ctr = 0;
-
 			/*
 			 * Lookup copy up origin by decoding origin file handle.
 			 * We may get a disconnected dentry, which is fine,
@@ -873,8 +867,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			 * number - it's the same as if we held a reference
 			 * to a dentry in lower layer that was moved under us.
 			 */
-			err = ovl_check_origin(ofs, upperdentry, &origin_path,
-					       &origin_ctr);
+			err = ovl_check_origin(ofs, upperdentry, &origin_path);
 			if (err)
 				goto out_put_upper;
 
@@ -1073,6 +1066,10 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			upperredirect = NULL;
 			goto out_free_oe;
 		}
+		err = ovl_check_metacopy_xattr(upperdentry);
+		if (err < 0)
+			goto out_free_oe;
+		uppermetacopy = err;
 	}
 
 	if (upperdentry || ctr) {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index b725c7f15ff4..29bc1ec699e7 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -483,7 +483,6 @@ void ovl_aio_request_cache_destroy(void);
 /* copy_up.c */
 int ovl_copy_up(struct dentry *dentry);
 int ovl_copy_up_with_data(struct dentry *dentry);
-int ovl_copy_up_flags(struct dentry *dentry, int flags);
 int ovl_maybe_copy_up(struct dentry *dentry, int flags);
 int ovl_copy_xattr(struct dentry *old, struct dentry *new);
 int ovl_set_attr(struct dentry *upper, struct kstat *stat);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 91476bc422f9..4b38141c2985 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -580,12 +580,19 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 		}
 	}
 
-	/* Workdir is useless in non-upper mount */
-	if (!config->upperdir && config->workdir) {
-		pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
-			config->workdir);
-		kfree(config->workdir);
-		config->workdir = NULL;
+	/* Workdir/index are useless in non-upper mount */
+	if (!config->upperdir) {
+		if (config->workdir) {
+			pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
+				config->workdir);
+			kfree(config->workdir);
+			config->workdir = NULL;
+		}
+		if (config->index && index_opt) {
+			pr_info("option \"index=on\" is useless in a non-upper mount, ignore\n");
+			index_opt = false;
+		}
+		config->index = false;
 	}
 
 	err = ovl_parse_redirect_mode(config, config->redirect_mode);
@@ -622,11 +629,13 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 
 	/* Resolve nfs_export -> index dependency */
 	if (config->nfs_export && !config->index) {
-		if (nfs_export_opt && index_opt) {
+		if (!config->upperdir && config->redirect_follow) {
+			pr_info("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
+			config->nfs_export = false;
+		} else if (nfs_export_opt && index_opt) {
 			pr_err("conflicting options: nfs_export=on,index=off\n");
 			return -EINVAL;
-		}
-		if (index_opt) {
+		} else if (index_opt) {
 			/*
 			 * There was an explicit index=off that resulted
 			 * in this conflict.
@@ -1352,8 +1361,15 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 		goto out;
 	}
 
+	/* index dir will act also as workdir */
+	iput(ofs->workdir_trap);
+	ofs->workdir_trap = NULL;
+	dput(ofs->workdir);
+	ofs->workdir = NULL;
 	ofs->indexdir = ovl_workdir_create(ofs, OVL_INDEXDIR_NAME, true);
 	if (ofs->indexdir) {
+		ofs->workdir = dget(ofs->indexdir);
+
 		err = ovl_setup_trap(sb, ofs->indexdir, &ofs->indexdir_trap,
 				     "indexdir");
 		if (err)
@@ -1396,6 +1412,18 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid)
 	if (!ofs->config.nfs_export && !ovl_upper_mnt(ofs))
 		return true;
 
+	/*
+	 * We allow using single lower with null uuid for index and nfs_export
+	 * for example to support those features with single lower squashfs.
+	 * To avoid regressions in setups of overlay with re-formatted lower
+	 * squashfs, do not allow decoding origin with lower null uuid unless
+	 * user opted-in to one of the new features that require following the
+	 * lower inode of non-dir upper.
+	 */
+	if (!ofs->config.index && !ofs->config.metacopy && !ofs->config.xino &&
+	    uuid_is_null(uuid))
+		return false;
+
 	for (i = 0; i < ofs->numfs; i++) {
 		/*
 		 * We use uuid to associate an overlay lower file handle with a
@@ -1493,14 +1521,23 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
 		if (err < 0)
 			goto out;
 
+		/*
+		 * Check if lower root conflicts with this overlay layers before
+		 * checking if it is in-use as upperdir/workdir of "another"
+		 * mount, because we do not bother to check in ovl_is_inuse() if
+		 * the upperdir/workdir is in fact in-use by our
+		 * upperdir/workdir.
+		 */
 		err = ovl_setup_trap(sb, stack[i].dentry, &trap, "lowerdir");
 		if (err)
 			goto out;
 
 		if (ovl_is_inuse(stack[i].dentry)) {
 			err = ovl_report_in_use(ofs, "lowerdir");
-			if (err)
+			if (err) {
+				iput(trap);
 				goto out;
+			}
 		}
 
 		mnt = clone_private_mount(&stack[i]);
@@ -1575,10 +1612,6 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
 	if (!ofs->config.upperdir && numlower == 1) {
 		pr_err("at least 2 lowerdir are needed while upperdir nonexistent\n");
 		return ERR_PTR(-EINVAL);
-	} else if (!ofs->config.upperdir && ofs->config.nfs_export &&
-		   ofs->config.redirect_follow) {
-		pr_warn("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
-		ofs->config.nfs_export = false;
 	}
 
 	stack = kcalloc(numlower, sizeof(struct path), GFP_KERNEL);
@@ -1842,21 +1875,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ovl_upper_mnt(ofs))
 		sb->s_flags |= SB_RDONLY;
 
-	if (!(ovl_force_readonly(ofs)) && ofs->config.index) {
-		/* index dir will act also as workdir */
-		dput(ofs->workdir);
-		ofs->workdir = NULL;
-		iput(ofs->workdir_trap);
-		ofs->workdir_trap = NULL;
-
+	if (!ovl_force_readonly(ofs) && ofs->config.index) {
 		err = ovl_get_indexdir(sb, ofs, oe, &upperpath);
 		if (err)
 			goto out_free_oe;
 
 		/* Force r/o mount with no index dir */
-		if (ofs->indexdir)
-			ofs->workdir = dget(ofs->indexdir);
-		else
+		if (!ofs->indexdir)
 			sb->s_flags |= SB_RDONLY;
 	}
 
diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c
index 9955d75c0585..ad31ec4ad627 100644
--- a/fs/proc/bootconfig.c
+++ b/fs/proc/bootconfig.c
@@ -26,8 +26,9 @@ static int boot_config_proc_show(struct seq_file *m, void *v)
 static int __init copy_xbc_key_value_list(char *dst, size_t size)
 {
 	struct xbc_node *leaf, *vnode;
-	const char *val;
 	char *key, *end = dst + size;
+	const char *val;
+	char q;
 	int ret = 0;
 
 	key = kzalloc(XBC_KEYLEN_MAX, GFP_KERNEL);
@@ -41,16 +42,20 @@ static int __init copy_xbc_key_value_list(char *dst, size_t size)
 			break;
 		dst += ret;
 		vnode = xbc_node_get_child(leaf);
-		if (vnode && xbc_node_is_array(vnode)) {
+		if (vnode) {
 			xbc_array_for_each_value(vnode, val) {
-				ret = snprintf(dst, rest(dst, end), "\"%s\"%s",
-					val, vnode->next ? ", " : "\n");
+				if (strchr(val, '"'))
+					q = '\'';
+				else
+					q = '"';
+				ret = snprintf(dst, rest(dst, end), "%c%s%c%s",
+					q, val, q, vnode->next ? ", " : "\n");
 				if (ret < 0)
 					goto out;
 				dst += ret;
 			}
 		} else {
-			ret = snprintf(dst, rest(dst, end), "\"%s\"\n", val);
+			ret = snprintf(dst, rest(dst, end), "\"\"\n");
 			if (ret < 0)
 				break;
 			dst += ret;
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 8ba492d44e68..e502414b3556 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -512,7 +512,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 				 * Using bounce buffer to bypass the
 				 * hardened user copy kernel text checks.
 				 */
-				if (probe_kernel_read(buf, (void *) start, tsz)) {
+				if (copy_from_kernel_nofault(buf, (void *)start,
+						tsz)) {
 					if (clear_user(buffer, tsz)) {
 						ret = -EFAULT;
 						goto out;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 42c5128c7d1c..6c1166ccdaea 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -566,8 +566,9 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
 		goto out;
 
 	/* don't even try if the size is too large */
-	if (count > KMALLOC_MAX_SIZE)
-		return -ENOMEM;
+	error = -ENOMEM;
+	if (count >= KMALLOC_MAX_SIZE)
+		goto out;
 
 	if (write) {
 		kbuf = memdup_user_nul(ubuf, count);
@@ -576,7 +577,6 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
 			goto out;
 		}
 	} else {
-		error = -ENOMEM;
 		kbuf = kzalloc(count, GFP_KERNEL);
 		if (!kbuf)
 			goto out;
diff --git a/fs/read_write.c b/fs/read_write.c
index bbfa9b12b15e..4fb797822567 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -419,28 +419,42 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	return ret;
 }
 
-ssize_t __vfs_read(struct file *file, char __user *buf, size_t count,
-		   loff_t *pos)
+ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
+	mm_segment_t old_fs = get_fs();
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ)))
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_CAN_READ))
+		return -EINVAL;
+
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+	set_fs(KERNEL_DS);
 	if (file->f_op->read)
-		return file->f_op->read(file, buf, count, pos);
+		ret = file->f_op->read(file, (void __user *)buf, count, pos);
 	else if (file->f_op->read_iter)
-		return new_sync_read(file, buf, count, pos);
+		ret = new_sync_read(file, (void __user *)buf, count, pos);
 	else
-		return -EINVAL;
+		ret = -EINVAL;
+	set_fs(old_fs);
+	if (ret > 0) {
+		fsnotify_access(file);
+		add_rchar(current, ret);
+	}
+	inc_syscr(current);
+	return ret;
 }
 
 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs;
-	ssize_t result;
+	ssize_t ret;
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	result = vfs_read(file, (void __user *)buf, count, pos);
-	set_fs(old_fs);
-	return result;
+	ret = rw_verify_area(READ, file, pos, count);
+	if (ret)
+		return ret;
+	return __kernel_read(file, buf, count, pos);
 }
 EXPORT_SYMBOL(kernel_read);
 
@@ -456,17 +470,22 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
 		return -EFAULT;
 
 	ret = rw_verify_area(READ, file, pos, count);
-	if (!ret) {
-		if (count > MAX_RW_COUNT)
-			count =  MAX_RW_COUNT;
-		ret = __vfs_read(file, buf, count, pos);
-		if (ret > 0) {
-			fsnotify_access(file);
-			add_rchar(current, ret);
-		}
-		inc_syscr(current);
-	}
+	if (ret)
+		return ret;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
 
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, pos);
+	else if (file->f_op->read_iter)
+		ret = new_sync_read(file, buf, count, pos);
+	else
+		ret = -EINVAL;
+	if (ret > 0) {
+		fsnotify_access(file);
+		add_rchar(current, ret);
+	}
+	inc_syscr(current);
 	return ret;
 }
 
@@ -488,23 +507,15 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 	return ret;
 }
 
-static ssize_t __vfs_write(struct file *file, const char __user *p,
-			   size_t count, loff_t *pos)
-{
-	if (file->f_op->write)
-		return file->f_op->write(file, p, count, pos);
-	else if (file->f_op->write_iter)
-		return new_sync_write(file, p, count, pos);
-	else
-		return -EINVAL;
-}
-
+/* caller is responsible for file_start_write/file_end_write */
 ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
 {
 	mm_segment_t old_fs;
 	const char __user *p;
 	ssize_t ret;
 
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE)))
+		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 
@@ -513,7 +524,12 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 	p = (__force const char __user *)buf;
 	if (count > MAX_RW_COUNT)
 		count =  MAX_RW_COUNT;
-	ret = __vfs_write(file, p, count, pos);
+	if (file->f_op->write)
+		ret = file->f_op->write(file, p, count, pos);
+	else if (file->f_op->write_iter)
+		ret = new_sync_write(file, p, count, pos);
+	else
+		ret = -EINVAL;
 	set_fs(old_fs);
 	if (ret > 0) {
 		fsnotify_modify(file);
@@ -522,21 +538,20 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 	inc_syscw(current);
 	return ret;
 }
-EXPORT_SYMBOL(__kernel_write);
 
 ssize_t kernel_write(struct file *file, const void *buf, size_t count,
 			    loff_t *pos)
 {
-	mm_segment_t old_fs;
-	ssize_t res;
+	ssize_t ret;
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_write(file, (__force const char __user *)buf, count, pos);
-	set_fs(old_fs);
+	ret = rw_verify_area(WRITE, file, pos, count);
+	if (ret)
+		return ret;
 
-	return res;
+	file_start_write(file);
+	ret =  __kernel_write(file, buf, count, pos);
+	file_end_write(file);
+	return ret;
 }
 EXPORT_SYMBOL(kernel_write);
 
@@ -552,19 +567,23 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
 		return -EFAULT;
 
 	ret = rw_verify_area(WRITE, file, pos, count);
-	if (!ret) {
-		if (count > MAX_RW_COUNT)
-			count =  MAX_RW_COUNT;
-		file_start_write(file);
-		ret = __vfs_write(file, buf, count, pos);
-		if (ret > 0) {
-			fsnotify_modify(file);
-			add_wchar(current, ret);
-		}
-		inc_syscw(current);
-		file_end_write(file);
+	if (ret)
+		return ret;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+	file_start_write(file);
+	if (file->f_op->write)
+		ret = file->f_op->write(file, buf, count, pos);
+	else if (file->f_op->write_iter)
+		ret = new_sync_write(file, buf, count, pos);
+	else
+		ret = -EINVAL;
+	if (ret > 0) {
+		fsnotify_modify(file);
+		add_wchar(current, ret);
 	}
-
+	inc_syscw(current);
+	file_end_write(file);
 	return ret;
 }
 
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 64f61330564a..76bb1c846845 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -175,7 +175,7 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 		/* Extract the length of the metadata block */
 		data = page_address(bvec->bv_page) + bvec->bv_offset;
 		length = data[offset];
-		if (offset <= bvec->bv_len - 1) {
+		if (offset < bvec->bv_len - 1) {
 			length |= data[offset + 1] << 8;
 		} else {
 			if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) {
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 7187bd1a30ea..8d64edb80ebf 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -262,7 +262,7 @@ struct squashfs_dir_index {
 	__le32			index;
 	__le32			start_block;
 	__le32			size;
-	unsigned char		name[0];
+	unsigned char		name[];
 };
 
 struct squashfs_base_inode {
@@ -327,7 +327,7 @@ struct squashfs_symlink_inode {
 	__le32			inode_number;
 	__le32			nlink;
 	__le32			symlink_size;
-	char			symlink[0];
+	char			symlink[];
 };
 
 struct squashfs_reg_inode {
@@ -341,7 +341,7 @@ struct squashfs_reg_inode {
 	__le32			fragment;
 	__le32			offset;
 	__le32			file_size;
-	__le16			block_list[0];
+	__le16			block_list[];
 };
 
 struct squashfs_lreg_inode {
@@ -358,7 +358,7 @@ struct squashfs_lreg_inode {
 	__le32			fragment;
 	__le32			offset;
 	__le32			xattr;
-	__le16			block_list[0];
+	__le16			block_list[];
 };
 
 struct squashfs_dir_inode {
@@ -389,7 +389,7 @@ struct squashfs_ldir_inode {
 	__le16			i_count;
 	__le16			offset;
 	__le32			xattr;
-	struct squashfs_dir_index	index[0];
+	struct squashfs_dir_index	index[];
 };
 
 union squashfs_inode {
@@ -410,7 +410,7 @@ struct squashfs_dir_entry {
 	__le16			inode_number;
 	__le16			type;
 	__le16			size;
-	char			name[0];
+	char			name[];
 };
 
 struct squashfs_dir_header {
@@ -428,12 +428,12 @@ struct squashfs_fragment_entry {
 struct squashfs_xattr_entry {
 	__le16			type;
 	__le16			size;
-	char			data[0];
+	char			data[];
 };
 
 struct squashfs_xattr_val {
 	__le32			vsize;
-	char			value[0];
+	char			value[];
 };
 
 struct squashfs_xattr_id {
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index b43f0e8f43f2..9ed90368ab31 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -671,7 +671,8 @@ xlog_cil_push_work(
 	/*
 	 * Wake up any background push waiters now this context is being pushed.
 	 */
-	wake_up_all(&ctx->push_wait);
+	if (ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log))
+		wake_up_all(&cil->xc_push_wait);
 
 	/*
 	 * Check if we've anything to push. If there is nothing, then we don't
@@ -743,13 +744,12 @@ xlog_cil_push_work(
 
 	/*
 	 * initialise the new context and attach it to the CIL. Then attach
-	 * the current context to the CIL committing lsit so it can be found
+	 * the current context to the CIL committing list so it can be found
 	 * during log forces to extract the commit lsn of the sequence that
 	 * needs to be forced.
 	 */
 	INIT_LIST_HEAD(&new_ctx->committing);
 	INIT_LIST_HEAD(&new_ctx->busy_extents);
-	init_waitqueue_head(&new_ctx->push_wait);
 	new_ctx->sequence = ctx->sequence + 1;
 	new_ctx->cil = cil;
 	cil->xc_ctx = new_ctx;
@@ -937,7 +937,7 @@ xlog_cil_push_background(
 	if (cil->xc_ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) {
 		trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket);
 		ASSERT(cil->xc_ctx->space_used < log->l_logsize);
-		xlog_wait(&cil->xc_ctx->push_wait, &cil->xc_push_lock);
+		xlog_wait(&cil->xc_push_wait, &cil->xc_push_lock);
 		return;
 	}
 
@@ -1216,12 +1216,12 @@ xlog_cil_init(
 	INIT_LIST_HEAD(&cil->xc_committing);
 	spin_lock_init(&cil->xc_cil_lock);
 	spin_lock_init(&cil->xc_push_lock);
+	init_waitqueue_head(&cil->xc_push_wait);
 	init_rwsem(&cil->xc_ctx_lock);
 	init_waitqueue_head(&cil->xc_commit_wait);
 
 	INIT_LIST_HEAD(&ctx->committing);
 	INIT_LIST_HEAD(&ctx->busy_extents);
-	init_waitqueue_head(&ctx->push_wait);
 	ctx->sequence = 1;
 	ctx->cil = cil;
 	cil->xc_ctx = ctx;
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index ec22c7a3867f..75a62870b63a 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -240,7 +240,6 @@ struct xfs_cil_ctx {
 	struct xfs_log_vec	*lv_chain;	/* logvecs being pushed */
 	struct list_head	iclog_entry;
 	struct list_head	committing;	/* ctx committing list */
-	wait_queue_head_t	push_wait;	/* background push throttle */
 	struct work_struct	discard_endio_work;
 };
 
@@ -274,6 +273,7 @@ struct xfs_cil {
 	wait_queue_head_t	xc_commit_wait;
 	xfs_lsn_t		xc_current_sequence;
 	struct work_struct	xc_push_work;
+	wait_queue_head_t	xc_push_wait;	/* background push throttle */
 } ____cacheline_aligned_in_smp;
 
 /*
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 07bc42d62673..abfb17f88f9a 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -607,14 +607,14 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 	int nr_pages;
 	ssize_t ret;
 
-	nr_pages = iov_iter_npages(from, BIO_MAX_PAGES);
-	if (!nr_pages)
-		return 0;
-
 	max = queue_max_zone_append_sectors(bdev_get_queue(bdev));
 	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
 	iov_iter_truncate(from, max);
 
+	nr_pages = iov_iter_npages(from, BIO_MAX_PAGES);
+	if (!nr_pages)
+		return 0;
+
 	bio = bio_alloc_bioset(GFP_NOFS, nr_pages, &fs_bio_set);
 	if (!bio)
 		return -ENOMEM;
@@ -1119,7 +1119,7 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
 	char *file_name;
 	struct dentry *dir;
 	unsigned int n = 0;
-	int ret = -ENOMEM;
+	int ret;
 
 	/* If the group is empty, there is nothing to do */
 	if (!zd->nr_zones[type])
@@ -1135,8 +1135,10 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
 		zgroup_name = "seq";
 
 	dir = zonefs_create_inode(sb->s_root, zgroup_name, NULL, type);
-	if (!dir)
+	if (!dir) {
+		ret = -ENOMEM;
 		goto free;
+	}
 
 	/*
 	 * The first zone contains the super block: skip it.
@@ -1174,8 +1176,10 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
 		 * Use the file number within its group as file name.
 		 */
 		snprintf(file_name, ZONEFS_NAME_MAX - 1, "%u", n);
-		if (!zonefs_create_inode(dir, file_name, zone, type))
+		if (!zonefs_create_inode(dir, file_name, zone, type)) {
+			ret = -ENOMEM;
 			goto free;
+		}
 
 		n++;
 	}
author	Takashi Iwai <tiwai@suse.de>	2020-08-03 15:41:43 +0300
committer	Takashi Iwai <tiwai@suse.de>	2020-08-03 15:41:43 +0300
commit	103f528d3bc35d2b6e726a3fffd879e492d191c2 (patch)
tree	2829604c2386f96e228fac7841e49906f698dfff /fs
parent	07c9983b567d0ef33aefc063299de95a987e12a8 (diff)
parent	84569f329f7fcb40b7b1860f273b2909dabf2a2b (diff)
download	linux-103f528d3bc35d2b6e726a3fffd879e492d191c2.tar.xz