Merge tag 'vfs-7.2-rc2.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:

 - netfs:

    - fix the decision when to disallow write-streaming with fscache in
      use, handling of asynchronous cache object creation, a double fput
      in cachefiles, clearing S_KERNEL_FILE without the inode lock held,
      page extraction bugs in the iov_iter helpers (a potential
      underflow, a missing allocation failure check, a memory leak, and
      a folio offset miscalculation), writeback error and ENOMEM
      handling, DIO write retry for filesystems without a
      ->prepare_write() method, and the replacement of the wb_lock mutex
      with a bit lock plus writethrough collection offload so that
      multiple asynchronous writebacks don't interfere with each other.

    - Fix the barriering when walking the netfs subrequest list during
      retries as it was possible to see a subrequest that was just added
      by the application thread.

 - iomap:

    - Change iomap to submit read bios after each extent instead of
      building them up across extents. The old behavior was considered
      problematic for a while and now caused an actual erofs bug.

    - Guard the ioend io_size EOF trim in iomap against underflow when a
      concurrent truncate moves EOF below the start of the ioend,
      wrapping io_size to a huge value.

 - overlayfs

    - Fix a stale overlayfs comment about the locking order.

    - Store the linked-in upper dentry instead of the disconnected
      O_TMPFILE dentry during overlayfs tmpfile copy-up. With a FUSE or
      virtiofs upper layer ->d_revalidate() would try to look up "/" in
      the workdir and fail, causing persistent ESTALE errors that broke
      dpkg and apt.

 - vfs-bpf:

   Have the bpf_real_data_inode() kfunc take a struct file instead of a
   dentry so it is usable from the bprm_check_security, mmap_file, and
   file_mprotect hooks, and rename it from bpf_real_inode() to make the
   data-inode semantics explicit. The kfunc landed this cycle so the
   change is safe.

 - afs:

   NULL pointer dereferences in the callback service and in
   afs_get_tree(), several memory and refcount leaks, missing locking
   around the dynamic root inode numbers and premature cell exposure
   through /afs, a netns destruction hang caused by a misplaced
   increment of net->cells_outstanding, a bulk lookup malfunction caused
   by the dir_emit() API change, inode (re)initialisation issues, and
   assorted smaller fixes to error codes, seqlock handling, and debug
   output.

 - vfs:

   Refuse O_TMPFILE creation with an unmapped fsuid or fsgid and add a
   selftest for it.

 - vboxsf:

   Add Jori Koolstra as vboxsf maintainer, taking over from Hans de
   Goede.

 - dio:

   Release the pages attached to a short atomic dio bio; the REQ_ATOMIC
   size check error path leaked them.

 - procfs:

   Only bump the parent directory link count when registering
   directories in procfs. Registering regular files inflated the count
   and leaked a link on every create and remove cycle.

 - minix:

   Avoid an unsigned overflow in the minix bitmap block count
   calculation that let crafted images with huge inode or zone counts
   pass superblock validation and crash the kernel during mount.

 - cachefiles:

   Fix a double unlock in the cachefiles nomem_d_alloc error path left
   over from the start_creating() conversion.

 - fat:

   Stop fat from reading directory entries past the 0x00
   end-of-directory marker. If the trailing on-disk slots aren't
   zero-filled the driver surfaced arbitrary garbage as directory
   entries.

 - freexvfs:

   Don't BUG() on unknown typed-extent types in freevxfs, reachable via
   ioctl(FIBMAP) on a crafted image; fail with an I/O error instead.

 - orangefs:

   Keep the readdir entry size 64-bit in orangefs fill_from_part().
   Truncating it to __u32 bypassed the bounds check and led to
   out-of-bounds reads triggerable by the userspace client.

 - xfs:

   Fix the error unwind in xfs_open_devices() which released the rt
   device file twice and left dangling buftarg pointers behind that were
   freed again when the failed mount was torn down.

 - exec:

   Fix an off-by-one in the comment documenting the maximum binfmt
   rewrite depth in exec_binprm(). The code allows five rewrites, not
   four; restricting the code would break userspace so the comment is
   fixed instead.

 - file handles:

   Reject detached mounts in capable_wrt_mount(). A detached mount can
   be dissolved concurrently, leaving a NULL mount namespace that
   open_by_handle_at() would dereference.

* tag 'vfs-7.2-rc2.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (57 commits)
  netfs: Fix barriering when walking subrequest list
  iomap: submit read bio after each extent
  fuse: call fuse_send_readpages explicitly from fuse_readahead
  iomap: consolidate bio submission
  fhandle: reject detached mounts in capable_wrt_mount()
  netfs: Fix DIO write retry for filesystems without a ->prepare_write()
  netfs: Fix folio state after ENOMEM whilst under writeback iteration
  netfs: Fix writeback error handling
  netfs: Fix writethrough to use collection offload
  netfs: Replace wb_lock with a bit lock for asynchronicity
  netfs: Fix kdoc warning
  scatterlist: Fix offset in folio calc in extract_xarray_to_sg()
  iov_iter: Remove unused variable in kunit_iov_iter.c
  iov_iter: Fix a memory leak in iov_iter_extract_user_pages()
  iov_iter: Fix missing alloc fail check in iov_iter_extract_bvec_pages()
  iov_iter: Fix potential underflow in iov_iter_extract_xarray_pages()
  cachefiles: Fix file burial to take lock when unsetting S_KERNEL_FILE
  cachefiles: Fix double fput
  netfs: Fix netfs_create_write_req() to handle async cache object creation
  netfs: Fix decision whether to disallow write-streaming due to fscache use
  ...

43 files changed, 384 insertions, 170 deletions

diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 894d2bad6b6c..61354003c006 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -113,16 +113,12 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell,
 {
 	struct afs_volume *volume = NULL;
 	struct rb_node *p;
-	int seq = 1;
 
-	for (;;) {
+	scoped_seqlock_read(&cell->volume_lock, ss_lock) {
 		/* Unfortunately, rbtree walking doesn't give reliable results
 		 * under just the RCU read lock, so we have to check for
 		 * changes.
 		 */
-		seq++; /* 2 on the 1st/lockless path, otherwise odd */
-		read_seqbegin_or_lock(&cell->volume_lock, &seq);
-
 		p = rcu_dereference_raw(cell->volumes.rb_node);
 		while (p) {
 			volume = rb_entry(p, struct afs_volume, cell_node);
@@ -138,12 +134,9 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell,
 
 		if (volume && afs_try_get_volume(volume, afs_volume_trace_get_callback))
 			break;
-		if (!need_seqretry(&cell->volume_lock, seq))
-			break;
-		seq |= 1; /* Want a lock next time */
+		volume = NULL;
 	}
 
-	done_seqretry(&cell->volume_lock, seq);
 	return volume;
 }
 
@@ -221,7 +214,11 @@ static void afs_break_some_callbacks(struct afs_server *server,
 
 	rcu_read_lock();
 	volume = afs_lookup_volume_rcu(server->cell, vid);
-	if (cbb->fid.vnode == 0 && cbb->fid.unique == 0) {
+	if (!volume) {
+		/* Ignore breaks on unknown volumes. */
+		rcu_read_unlock();
+		*_count = 0;
+	} else if (cbb->fid.vnode == 0 && cbb->fid.unique == 0) {
 		afs_break_volume_callback(server, volume);
 		*_count -= 1;
 		if (*_count)
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 9738684dbdd2..47a2645768d7 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -206,11 +206,6 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 	cell->dns_status = vllist->status;
 	smp_store_release(&cell->dns_lookup_count, 1); /* vs source/status */
 	atomic_inc(&net->cells_outstanding);
-	ret = idr_alloc_cyclic(&net->cells_dyn_ino, cell,
-			       2, INT_MAX / 2, GFP_KERNEL);
-	if (ret < 0)
-		goto error;
-	cell->dynroot_ino = ret;
 	cell->debug_id = atomic_inc_return(&cell_debug_id);
 
 	trace_afs_cell(cell->debug_id, 1, 0, afs_cell_trace_alloc);
@@ -304,6 +299,13 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net,
 			goto cell_already_exists;
 	}
 
+	ret = idr_alloc_cyclic(&net->cells_dyn_ino, candidate,
+			       2, INT_MAX / 2, GFP_KERNEL);
+	if (ret < 0)
+		goto cant_alloc_ino;
+	candidate->dynroot_ino = ret;
+	set_bit(AFS_CELL_FL_HAVE_INO, &candidate->flags);
+
 	cell = candidate;
 	candidate = NULL;
 	afs_use_cell(cell, trace);
@@ -378,6 +380,11 @@ no_wait:
 	_leave(" = %p [cell]", cell);
 	return cell;
 
+cant_alloc_ino:
+	up_write(&net->cells_lock);
+	afs_put_cell(candidate, afs_cell_trace_put_candidate);
+	goto error_noput;
+
 cell_already_exists:
 	_debug("cell exists");
 	cell = cursor;
@@ -547,6 +554,8 @@ static int afs_update_cell(struct afs_cell *cell)
 		rcu_assign_pointer(cell->vl_servers, vllist);
 		cell->dns_source = vllist->source;
 		old = p;
+	} else {
+		old = vllist;
 	}
 	write_unlock(&cell->vl_servers_lock);
 	afs_put_vlserverlist(cell->net, old);
@@ -577,7 +586,6 @@ static void afs_cell_destroy(struct rcu_head *rcu)
 	afs_put_vlserverlist(net, rcu_access_pointer(cell->vl_servers));
 	afs_unuse_cell(cell->alias_of, afs_cell_trace_unuse_alias);
 	key_put(cell->anonymous_key);
-	idr_remove(&net->cells_dyn_ino, cell->dynroot_ino);
 	kfree(cell->name - 1);
 	kfree(cell);
 
@@ -592,6 +600,13 @@ static void afs_destroy_cell_work(struct work_struct *work)
 	afs_see_cell(cell, afs_cell_trace_destroy);
 	timer_delete_sync(&cell->management_timer);
 	cancel_work_sync(&cell->manager);
+
+	if (test_bit(AFS_CELL_FL_HAVE_INO, &cell->flags)) {
+		down_write(&cell->net->cells_lock);
+		idr_remove(&cell->net->cells_dyn_ino, cell->dynroot_ino);
+		up_write(&cell->net->cells_lock);
+	}
+
 	call_rcu(&cell->rcu, afs_cell_destroy);
 }
 
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 5540ae1cad59..db394f101fc6 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -334,7 +334,6 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 		ret = afs_extract_data(call, false);
 		switch (ret) {
 		case 0:		break;
-		case -EAGAIN:	return 0;
 		default:	return ret;
 		}
 
@@ -364,6 +363,11 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 	if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING))
 		return afs_io_error(call, afs_io_error_cm_reply);
 
+	if (!call->server) {
+		trace_afs_cm_no_server_u(call, call->request);
+		return 0;
+	}
+
 	if (memcmp(call->request, &call->server->_uuid, sizeof(call->server->_uuid)) != 0) {
 		pr_notice("Callback UUID does not match fileserver UUID\n");
 		trace_afs_cm_no_server_u(call, call->request);
@@ -451,7 +455,6 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call)
 		ret = afs_extract_data(call, false);
 		switch (ret) {
 		case 0:		break;
-		case -EAGAIN:	return 0;
 		default:	return ret;
 		}
 
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 498b99ccdf0e..6df56fe9163f 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -28,9 +28,11 @@ static int afs_d_revalidate(struct inode *dir, const struct qstr *name,
 static int afs_d_delete(const struct dentry *dentry);
 static void afs_d_iput(struct dentry *dentry, struct inode *inode);
 static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name, int nlen,
-				  loff_t fpos, u64 ino, unsigned dtype);
+				   u64 ino, u32 uniquifier);
+#define AFS_LOOKUP_ONE ((filldir_t)0x123UL)
 static bool afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen,
-			      loff_t fpos, u64 ino, unsigned dtype);
+			       u64 ino, u32 uniquifier);
+#define AFS_LOOKUP ((filldir_t)0x137UL)
 static int afs_create(struct mnt_idmap *idmap, struct inode *dir,
 		      struct dentry *dentry, umode_t mode, bool excl);
 static struct dentry *afs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
@@ -421,11 +423,18 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
 		}
 
 		/* found the next entry */
-		if (!dir_emit(ctx, dire->u.name, nlen,
-			      ntohl(dire->u.vnode),
-			      (ctx->actor == afs_lookup_filldir ||
-			       ctx->actor == afs_lookup_one_filldir)?
-			      ntohl(dire->u.unique) : DT_UNKNOWN)) {
+		if (ctx->actor == AFS_LOOKUP) {
+			if (!afs_lookup_filldir(ctx, dire->u.name, nlen,
+						ntohl(dire->u.vnode),
+						ntohl(dire->u.unique)))
+				return 0;
+		} else if (ctx->actor == AFS_LOOKUP_ONE) {
+			if (!afs_lookup_one_filldir(ctx, dire->u.name, nlen,
+						    ntohl(dire->u.vnode),
+						    ntohl(dire->u.unique)))
+				return 0;
+		} else if (!dir_emit(ctx, dire->u.name, nlen,
+				     ntohl(dire->u.vnode), DT_UNKNOWN)) {
 			_leave(" = 0 [full]");
 			return 0;
 		}
@@ -545,6 +554,7 @@ static int afs_readdir(struct file *file, struct dir_context *ctx)
 {
 	afs_dataversion_t dir_version;
 
+	ctx->dt_flags_mask = UINT_MAX;
 	return afs_dir_iterate(file_inode(file), ctx, file, &dir_version);
 }
 
@@ -554,14 +564,14 @@ static int afs_readdir(struct file *file, struct dir_context *ctx)
  *   uniquifier through dtype
  */
 static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name,
-				  int nlen, loff_t fpos, u64 ino, unsigned dtype)
+				  int nlen, u64 ino, u32 uniquifier)
 {
 	struct afs_lookup_one_cookie *cookie =
 		container_of(ctx, struct afs_lookup_one_cookie, ctx);
 
 	_enter("{%s,%u},%s,%u,,%llu,%u",
 	       cookie->name.name, cookie->name.len, name, nlen,
-	       (unsigned long long) ino, dtype);
+	       (unsigned long long) ino, uniquifier);
 
 	/* insanity checks first */
 	BUILD_BUG_ON(sizeof(union afs_xdr_dir_block) != 2048);
@@ -574,7 +584,7 @@ static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name,
 	}
 
 	cookie->fid.vnode = ino;
-	cookie->fid.unique = dtype;
+	cookie->fid.unique = uniquifier;
 	cookie->found = 1;
 
 	_leave(" = false [found]");
@@ -591,7 +601,7 @@ static int afs_do_lookup_one(struct inode *dir, const struct qstr *name,
 {
 	struct afs_super_info *as = dir->i_sb->s_fs_info;
 	struct afs_lookup_one_cookie cookie = {
-		.ctx.actor = afs_lookup_one_filldir,
+		.ctx.actor = AFS_LOOKUP_ONE,
 		.name = *name,
 		.fid.vid = as->volume->vid
 	};
@@ -622,14 +632,14 @@ static int afs_do_lookup_one(struct inode *dir, const struct qstr *name,
  *   uniquifier through dtype
  */
 static bool afs_lookup_filldir(struct dir_context *ctx, const char *name,
-			      int nlen, loff_t fpos, u64 ino, unsigned dtype)
+			      int nlen, u64 ino, u32 uniquifier)
 {
 	struct afs_lookup_cookie *cookie =
 		container_of(ctx, struct afs_lookup_cookie, ctx);
 
 	_enter("{%s,%u},%s,%u,,%llu,%u",
 	       cookie->name.name, cookie->name.len, name, nlen,
-	       (unsigned long long) ino, dtype);
+	       (unsigned long long) ino, uniquifier);
 
 	/* insanity checks first */
 	BUILD_BUG_ON(sizeof(union afs_xdr_dir_block) != 2048);
@@ -637,7 +647,7 @@ static bool afs_lookup_filldir(struct dir_context *ctx, const char *name,
 
 	if (cookie->nr_fids < 50) {
 		cookie->fids[cookie->nr_fids].vnode	= ino;
-		cookie->fids[cookie->nr_fids].unique	= dtype;
+		cookie->fids[cookie->nr_fids].unique	= uniquifier;
 		cookie->nr_fids++;
 	}
 
@@ -778,7 +788,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry)
 
 	for (i = 0; i < ARRAY_SIZE(cookie->fids); i++)
 		cookie->fids[i].vid = dvnode->fid.vid;
-	cookie->ctx.actor = afs_lookup_filldir;
+	cookie->ctx.actor = AFS_LOOKUP;
 	cookie->name = dentry->d_name;
 	cookie->nr_fids = 2; /* slot 1 is saved for the fid we actually want
 			      * and slot 0 for the directory */
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 1d5e33bc7502..6e3c8c691ba9 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -278,7 +278,7 @@ static struct dentry *afs_lookup_atcell(struct inode *dir, struct dentry *dentry
 }
 
 /*
- * Transcribe the cell database into readdir content under the RCU read lock.
+ * Transcribe the cell database into readdir content under net->cells_lock.
  * Each cell produces two entries, one prefixed with a dot and one not.
  */
 static int afs_dynroot_readdir_cells(struct afs_net *net, struct dir_context *ctx)
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index c0dbbc6d3716..20801b29521d 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -348,7 +348,7 @@ int afs_put_operation(struct afs_operation *op)
 		for (i = 0; i < op->nr_files - 2; i++)
 			if (op->more_files[i].put_vnode)
 				iput(&op->more_files[i].vnode->netfs.inode);
-		kfree(op->more_files);
+		kvfree(op->more_files);
 	}
 
 	if (op->estate) {
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 3f48458694ba..14f39a9bea6c 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -52,9 +52,9 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren
 /*
  * Set parameters for the netfs library
  */
-static void afs_set_netfs_context(struct afs_vnode *vnode)
+static void afs_set_netfs_context(struct afs_vnode *vnode, bool is_file)
 {
-	netfs_inode_init(&vnode->netfs, &afs_req_ops, true);
+	netfs_inode_init(&vnode->netfs, &afs_req_ops, is_file);
 }
 
 /*
@@ -93,6 +93,10 @@ static int afs_inode_init_from_status(struct afs_operation *op,
 	inode->i_gid = make_kgid(&init_user_ns, status->group);
 	set_nlink(&vnode->netfs.inode, status->nlink);
 
+	i_size_write(inode, status->size);
+	inode_set_bytes(inode, status->size);
+	afs_set_netfs_context(vnode, status->type == AFS_FTYPE_FILE);
+
 	switch (status->type) {
 	case AFS_FTYPE_FILE:
 		inode->i_mode	= S_IFREG | (status->mode & S_IALLUGO);
@@ -126,7 +130,6 @@ static int afs_inode_init_from_status(struct afs_operation *op,
 		}
 		inode->i_mapping->a_ops	= &afs_symlink_aops;
 		inode_nohighmem(inode);
-		mapping_set_release_always(inode->i_mapping);
 		break;
 	default:
 		dump_vnode(vnode, op->file[0].vnode != vnode ? op->file[0].vnode : NULL);
@@ -134,10 +137,6 @@ static int afs_inode_init_from_status(struct afs_operation *op,
 		return afs_protocol_error(NULL, afs_eproto_file_type);
 	}
 
-	i_size_write(inode, status->size);
-	inode_set_bytes(inode, status->size);
-	afs_set_netfs_context(vnode);
-
 	vnode->invalid_before	= status->data_version;
 	trace_afs_set_dv(vnode, status->data_version);
 	inode_set_iversion_raw(&vnode->netfs.inode, status->data_version);
@@ -566,7 +565,6 @@ struct inode *afs_root_iget(struct super_block *sb, struct key *key)
 
 	vnode = AFS_FS_I(inode);
 	vnode->cb_v_check = atomic_read(&as->volume->cb_v_break);
-	afs_set_netfs_context(vnode);
 
 	op = afs_alloc_operation(key, as->volume);
 	if (IS_ERR(op)) {
@@ -682,6 +680,7 @@ void afs_evict_inode(struct inode *inode)
 		inode->i_mapping->a_ops->writepages(inode->i_mapping, &wbc);
 	}
 
+	flush_delayed_work(&vnode->lock_work);
 	netfs_wait_for_outstanding_io(inode);
 	truncate_inode_pages_final(&inode->i_data);
 	netfs_free_folioq_buffer(vnode->directory);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 0b72a8566299..601f01e5c15f 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -388,6 +388,7 @@ struct afs_cell {
 #define AFS_CELL_FL_NO_GC	0		/* The cell was added manually, don't auto-gc */
 #define AFS_CELL_FL_DO_LOOKUP	1		/* DNS lookup requested */
 #define AFS_CELL_FL_CHECK_ALIAS	2		/* Need to check for aliases */
+#define AFS_CELL_FL_HAVE_INO	3		/* Have dynroot_ino */
 	enum afs_cell_state	state;
 	short			error;
 	enum dns_record_source	dns_source:8;	/* Latest source of data from lookup */
@@ -750,8 +751,6 @@ static inline void afs_vnode_set_cache(struct afs_vnode *vnode,
 {
 #ifdef CONFIG_AFS_FSCACHE
 	vnode->netfs.cache = cookie;
-	if (cookie)
-		mapping_set_release_always(vnode->netfs.inode.i_mapping);
 #endif
 }
 
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 942f3e9800d7..82bb713825a0 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -587,7 +587,8 @@ static int afs_get_tree(struct fs_context *fc)
 	}
 
 	fc->root = dget(sb->s_root);
-	trace_afs_get_tree(as->cell, as->volume);
+	if (!ctx->dyn_root)
+		trace_afs_get_tree(as->cell, as->volume);
 	_leave(" = 0 [%p]", sb);
 	return 0;
 
@@ -659,7 +660,6 @@ static void afs_i_init_once(void *_vnode)
 	INIT_LIST_HEAD(&vnode->wb_keys);
 	INIT_LIST_HEAD(&vnode->pending_locks);
 	INIT_LIST_HEAD(&vnode->granted_locks);
-	INIT_DELAYED_WORK(&vnode->lock_work, afs_lock_work);
 	INIT_LIST_HEAD(&vnode->cb_mmap_link);
 	seqlock_init(&vnode->cb_lock);
 }
@@ -693,6 +693,7 @@ static struct inode *afs_alloc_inode(struct super_block *sb)
 
 	init_rwsem(&vnode->rmdir_lock);
 	INIT_WORK(&vnode->cb_work, afs_invalidate_mmap_work);
+	INIT_DELAYED_WORK(&vnode->lock_work, afs_lock_work);
 
 	_leave(" = %p", &vnode->netfs.inode);
 	return &vnode->netfs.inode;
diff --git a/fs/afs/symlink.c b/fs/afs/symlink.c
index ed5868369f37..16b4823cb7b7 100644
--- a/fs/afs/symlink.c
+++ b/fs/afs/symlink.c
@@ -255,11 +255,11 @@ int afs_symlink_writepages(struct address_space *mapping,
 	}
 
 	if (ret == 0) {
-		mutex_lock(&vnode->netfs.wb_lock);
+		netfs_wb_begin(&vnode->netfs, false);
 		netfs_free_folioq_buffer(vnode->directory);
 		vnode->directory = NULL;
 		vnode->directory_size = 0;
-		mutex_unlock(&vnode->netfs.wb_lock);
+		netfs_wb_end(&vnode->netfs);
 	} else if (ret == 1) {
 		ret = 0; /* Skipped write due to lock conflict. */
 	}
diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c
index 3e4966915ea4..c1dac5dbed0d 100644
--- a/fs/afs/vl_list.c
+++ b/fs/afs/vl_list.c
@@ -92,7 +92,7 @@ static struct afs_addr_list *afs_extract_vl_addrs(struct afs_net *net,
 {
 	struct afs_addr_list *alist;
 	const u8 *b = *_b;
-	int ret = -EINVAL;
+	int ret;
 
 	alist = afs_alloc_addrlist(nr_addrs);
 	if (!alist)
@@ -110,6 +110,7 @@ static struct afs_addr_list *afs_extract_vl_addrs(struct afs_net *net,
 		case DNS_ADDRESS_IS_IPV4:
 			if (end - b < 4) {
 				_leave(" = -EINVAL [short inet]");
+				ret = -EINVAL;
 				goto error;
 			}
 			memcpy(x, b, 4);
@@ -122,6 +123,7 @@ static struct afs_addr_list *afs_extract_vl_addrs(struct afs_net *net,
 		case DNS_ADDRESS_IS_IPV6:
 			if (end - b < 16) {
 				_leave(" = -EINVAL [short inet6]");
+				ret = -EINVAL;
 				goto error;
 			}
 			memcpy(x, b, 16);
@@ -198,6 +200,8 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 
 	b += sizeof(*hdr);
 	while (end - b >= sizeof(bs)) {
+		int nlen;
+
 		bs.name_len	= afs_extract_le16(&b);
 		bs.priority	= afs_extract_le16(&b);
 		bs.weight	= afs_extract_le16(&b);
@@ -207,10 +211,12 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 		bs.protocol	= *b++;
 		bs.nr_addrs	= *b++;
 
+		nlen = min3(bs.name_len, end - b, 255);
+
 		_debug("extract %u %u %u %u %u %u %*.*s",
 		       bs.name_len, bs.priority, bs.weight,
 		       bs.port, bs.protocol, bs.nr_addrs,
-		       bs.name_len, bs.name_len, b);
+		       bs.name_len, nlen, b);
 
 		if (end - b < bs.name_len)
 			break;
@@ -287,8 +293,20 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 			afs_put_addrlist(old, afs_alist_trace_put_vlserver_old);
 		}
 
+		/* Check for duplicates in the server list */
+		for (j = 0; j < vllist->nr_servers; j++) {
+			struct afs_vlserver *s = vllist->servers[j].server;
 
-		/* TODO: Might want to check for duplicates */
+			if (s->name_len == server->name_len &&
+			    s->port == server->port &&
+			    strncasecmp(s->name, server->name, server->name_len) == 0) {
+				afs_put_vlserver(cell->net, server);
+				server = NULL;
+				break;
+			}
+		}
+		if (!server)
+			continue;
 
 		/* Insertion-sort by priority and weight */
 		for (j = 0; j < vllist->nr_servers; j++) {
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 9ae5c8ad2e04..4f79d25ec37f 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -40,7 +40,7 @@ static struct afs_volume *afs_insert_volume_into_cell(struct afs_cell *cell,
 				goto found;
 			}
 
-			set_bit(AFS_VOLUME_RM_TREE, &volume->flags);
+			set_bit(AFS_VOLUME_RM_TREE, &p->flags);
 			rb_replace_node_rcu(&p->cell_node, &volume->cell_node, &cell->volumes);
 		}
 	}
diff --git a/fs/bpf_fs_kfuncs.c b/fs/bpf_fs_kfuncs.c
index 768aca2dc0f0..f1863a891db6 100644
--- a/fs/bpf_fs_kfuncs.c
+++ b/fs/bpf_fs_kfuncs.c
@@ -360,18 +360,23 @@ __bpf_kfunc int bpf_cgroup_read_xattr(struct cgroup *cgroup, const char *name__s
 #endif /* CONFIG_CGROUPS */
 
 /**
- * bpf_real_inode - get the real inode backing a dentry
- * @dentry: dentry to resolve
+ * bpf_real_data_inode - get the real inode hosting a file's data
+ * @file: file to resolve
  *
- * If the dentry is on a union/overlay filesystem, return the underlying, real
- * inode that hosts the data.  Otherwise return the inode attached to the
- * dentry itself.
+ * Resolve @file to the inode that hosts its data. For a regular file on a
+ * union/overlay filesystem this is the underlying (upper or lower) inode that
+ * stores the data, not the overlay inode.
  *
- * Return: The real inode backing the dentry, or NULL for a negative dentry.
+ * Data resolution only applies to regular files. For a non-regular file (e.g.
+ * a device node, fifo or socket) on a union/overlay filesystem the overlay
+ * inode itself is returned; for any file on a non-union filesystem the inode
+ * attached to @file is returned.
+ *
+ * Return: The inode hosting @file's data, or NULL.
  */
-__bpf_kfunc struct inode *bpf_real_inode(struct dentry *dentry)
+__bpf_kfunc struct inode *bpf_real_data_inode(struct file *file)
 {
-	return d_real_inode(dentry);
+	return d_real_inode(file_dentry(file));
 }
 
 __bpf_kfunc_end_defs();
@@ -384,7 +389,7 @@ BTF_ID_FLAGS(func, bpf_get_dentry_xattr, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_set_dentry_xattr, KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_remove_dentry_xattr, KF_SLEEPABLE)
-BTF_ID_FLAGS(func, bpf_real_inode, KF_SLEEPABLE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_real_data_inode, KF_SLEEPABLE | KF_RET_NULL)
 BTF_KFUNCS_END(bpf_fs_kfunc_set_ids)
 
 static int bpf_fs_kfuncs_filter(const struct bpf_prog *prog, u32 kfunc_id)
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 2937db690b40..8a9f6be15828 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -209,7 +209,6 @@ lookup_error:
 	return ERR_PTR(ret);
 
 nomem_d_alloc:
-	inode_unlock(d_inode(dir));
 	_leave(" = -ENOMEM");
 	return ERR_PTR(-ENOMEM);
 }
@@ -375,7 +374,7 @@ try_again:
 					    "Rename failed with error %d", ret);
 	}
 
-	__cachefiles_unmark_inode_in_use(object, d_inode(rep));
+	cachefiles_do_unmark_inode_in_use(object, d_inode(rep));
 	end_renaming(&rd);
 	_leave(" = 0");
 	return 0;
@@ -467,7 +466,6 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object)
 	ret = -EINVAL;
 	if (unlikely(!file->f_op->read_iter) ||
 	    unlikely(!file->f_op->write_iter)) {
-		fput(file);
 		pr_notice("Cache does not support read_iter and write_iter\n");
 		goto err_unuse;
 	}
diff --git a/fs/exec.c b/fs/exec.c
index b92fe7db176c..d5993cedc829 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1717,7 +1717,7 @@ static int exec_binprm(struct linux_binprm *bprm)
 	old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
 	rcu_read_unlock();
 
-	/* This allows 4 levels of binfmt rewrites before failing hard. */
+	/* This allows 5 levels of binfmt rewrites before failing hard. */
 	for (depth = 0;; depth++) {
 		struct file *exec;
 		if (depth > 5)
diff --git a/fs/exfat/iomap.c b/fs/exfat/iomap.c
index 1aac38e63fe6..190fc6471f84 100644
--- a/fs/exfat/iomap.c
+++ b/fs/exfat/iomap.c
@@ -253,10 +253,7 @@ static void exfat_iomap_read_end_io(struct bio *bio)
 static void exfat_iomap_bio_submit_read(const struct iomap_iter *iter,
 		struct iomap_read_folio_ctx *ctx)
 {
-	struct bio *bio = ctx->read_ctx;
-
-	bio->bi_end_io = exfat_iomap_read_end_io;
-	submit_bio(bio);
+	iomap_bio_submit_read_endio(iter, ctx, exfat_iomap_read_end_io);
 }
 
 const struct iomap_read_ops exfat_iomap_bio_read_ops = {
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 4f6f42f33613..c6cca5d00ffd 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -131,6 +131,31 @@ static inline int fat_get_entry(struct inode *dir, loff_t *pos,
 }
 
 /*
+ * Like fat_get_entry(), but honour the FAT end-of-directory marker:
+ * a dirent whose first name byte is NUL terminates iteration per the
+ * spec, which also guarantees that every following slot is zeroed.
+ * Skip straight to the end of the directory so the next call returns
+ * -1 from fat_bmap() without re-reading the trailing zero slots, and
+ * so callers that persist *pos across invocations (e.g. readdir's
+ * ctx->pos) keep reporting EOD.  Release *bh and set it to NULL to
+ * match fat_get_entry()'s contract that *bh is NULL on the -1 return.
+ */
+static int fat_get_entry_eod(struct inode *dir, loff_t *pos,
+			     struct buffer_head **bh,
+			     struct msdos_dir_entry **de)
+{
+	int err = fat_get_entry(dir, pos, bh, de);
+
+	if (err == 0 && (*de)->name[0] == 0) {
+		brelse(*bh);
+		*bh = NULL;
+		*pos = dir->i_size;
+		return -1;
+	}
+	return err;
+}
+
+/*
  * Convert Unicode 16 to UTF-8, translated Unicode, or ASCII.
  * If uni_xlate is enabled and we can't get a 1:1 conversion, use a
  * colon as an escape character since it is normally invalid on the vfat
@@ -327,7 +352,7 @@ parse_long:
 
 		if (ds->id & 0x40)
 			(*unicode)[offset + 13] = 0;
-		if (fat_get_entry(dir, pos, bh, de) < 0)
+		if (fat_get_entry_eod(dir, pos, bh, de) < 0)
 			return PARSE_EOF;
 		if (slot == 0)
 			break;
@@ -489,7 +514,7 @@ int fat_search_long(struct inode *inode, const unsigned char *name,
 
 	err = -ENOENT;
 	while (1) {
-		if (fat_get_entry(inode, &cpos, &bh, &de) == -1)
+		if (fat_get_entry_eod(inode, &cpos, &bh, &de) == -1)
 			goto end_of_dir;
 parse_record:
 		nr_slots = 0;
@@ -601,7 +626,7 @@ static int __fat_readdir(struct inode *inode, struct file *file,
 
 	bh = NULL;
 get_new:
-	if (fat_get_entry(inode, &cpos, &bh, &de) == -1)
+	if (fat_get_entry_eod(inode, &cpos, &bh, &de) == -1)
 		goto end_of_dir;
 parse_record:
 	nr_slots = 0;
@@ -885,7 +910,7 @@ static int fat_get_short_entry(struct inode *dir, loff_t *pos,
 			       struct buffer_head **bh,
 			       struct msdos_dir_entry **de)
 {
-	while (fat_get_entry(dir, pos, bh, de) >= 0) {
+	while (fat_get_entry_eod(dir, pos, bh, de) >= 0) {
 		/* free entry or long name entry or volume label */
 		if (!IS_FREE((*de)->name) && !((*de)->attr & ATTR_VOLUME))
 			return 0;
@@ -1302,6 +1327,7 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots,
 	struct msdos_dir_entry *de;
 	int err, free_slots, i, nr_bhs;
 	loff_t pos;
+	bool saw_eod;
 
 	sinfo->nr_slots = nr_slots;
 
@@ -1310,12 +1336,15 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots,
 	bh = prev = NULL;
 	pos = 0;
 	err = -ENOSPC;
+	saw_eod = false;
 	while (fat_get_entry(dir, &pos, &bh, &de) > -1) {
 		/* check the maximum size of directory */
 		if (pos >= FAT_MAX_DIR_SIZE)
 			goto error;
 
 		if (IS_FREE(de->name)) {
+			if (de->name[0] == 0)
+				saw_eod = true;
 			if (prev != bh) {
 				get_bh(bh);
 				bhs[nr_bhs] = prev = bh;
@@ -1325,6 +1354,13 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots,
 			if (free_slots == nr_slots)
 				goto found;
 		} else {
+			if (saw_eod) {
+				fat_fs_error_ratelimit(sb,
+					"allocated dir entry found after end-of-directory marker (i_pos %lld)",
+					MSDOS_I(dir)->i_pos);
+				err = -EIO;
+				goto error;
+			}
 			for (i = 0; i < nr_bhs; i++)
 				brelse(bhs[i]);
 			prev = NULL;
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 1ca7eb3a6cb5..f8829231e3d7 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -295,7 +295,7 @@ static bool capable_wrt_mount(struct mount *mount)
 	 */
 	guard(rcu)();
 	mnt_ns = READ_ONCE(mount->mnt_ns);
-	return ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN);
+	return mnt_ns && ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN);
 }
 
 static inline int may_decode_fh(struct handle_to_path_ctx *ctx,
diff --git a/fs/freevxfs/vxfs_bmap.c b/fs/freevxfs/vxfs_bmap.c
index e85222892038..1b8216eb1d90 100644
--- a/fs/freevxfs/vxfs_bmap.c
+++ b/fs/freevxfs/vxfs_bmap.c
@@ -227,7 +227,8 @@ vxfs_bmap_typed(struct inode *ip, long iblock)
 			return 0;
 		}
 		default:
-			BUG();
+			WARN_ON_ONCE(1);
+			return 0;
 		}
 	}
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e052a0d44dee..ceada75310b8 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -981,19 +981,8 @@ static int fuse_iomap_read_folio_range_async(const struct iomap_iter *iter,
 	return ret;
 }
 
-static void fuse_iomap_submit_read(const struct iomap_iter *iter,
-		struct iomap_read_folio_ctx *ctx)
-{
-	struct fuse_fill_read_data *data = ctx->read_ctx;
-
-	if (data->ia)
-		fuse_send_readpages(data->ia, data->file, data->nr_bytes,
-				    data->fc->async_read);
-}
-
 static const struct iomap_read_ops fuse_iomap_read_ops = {
 	.read_folio_range = fuse_iomap_read_folio_range_async,
-	.submit_read = fuse_iomap_submit_read,
 };
 
 static int fuse_read_folio(struct file *file, struct folio *folio)
@@ -1116,6 +1105,9 @@ static void fuse_readahead(struct readahead_control *rac)
 		return;
 
 	iomap_readahead(&fuse_iomap_ops, &ctx, NULL);
+	if (data.ia)
+		fuse_send_readpages(data.ia, data.file, data.nr_bytes,
+				    fc->async_read);
 }
 
 static ssize_t fuse_cache_read_iter(struct kiocb *iocb, struct iov_iter *to)
diff --git a/fs/iomap/bio.c b/fs/iomap/bio.c
index 4504f4633f17..dc8ac7e370a5 100644
--- a/fs/iomap/bio.c
+++ b/fs/iomap/bio.c
@@ -78,14 +78,24 @@ u32 iomap_finish_ioend_buffered_read(struct iomap_ioend *ioend)
 	return __iomap_read_end_io(&ioend->io_bio, ioend->io_error);
 }
 
-static void iomap_bio_submit_read(const struct iomap_iter *iter,
-		struct iomap_read_folio_ctx *ctx)
+void iomap_bio_submit_read_endio(const struct iomap_iter *iter,
+		struct iomap_read_folio_ctx *ctx, bio_end_io_t end_io)
 {
 	struct bio *bio = ctx->read_ctx;
 
+	bio->bi_end_io = end_io;
 	if (iter->iomap.flags & IOMAP_F_INTEGRITY)
 		fs_bio_integrity_alloc(bio);
 	submit_bio(bio);
+
+	ctx->read_ctx = NULL;
+}
+EXPORT_SYMBOL_GPL(iomap_bio_submit_read_endio);
+
+static void iomap_bio_submit_read(const struct iomap_iter *iter,
+		struct iomap_read_folio_ctx *ctx)
+{
+	return iomap_bio_submit_read_endio(iter, ctx, iomap_read_end_io);
 }
 
 static struct bio_set *iomap_read_bio_set(struct iomap_read_folio_ctx *ctx)
@@ -127,7 +137,6 @@ static void iomap_read_alloc_bio(const struct iomap_iter *iter,
 	if (ctx->rac)
 		bio->bi_opf |= REQ_RAHEAD;
 	bio->bi_iter.bi_sector = iomap_sector(iomap, iter->pos);
-	bio->bi_end_io = iomap_read_end_io;
 	bio_add_folio_nofail(bio, folio, plen,
 			offset_in_folio(folio, iter->pos));
 	ctx->read_ctx = bio;
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 8d4806dc46d4..276720bc18dc 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -642,12 +642,12 @@ void iomap_read_folio(const struct iomap_ops *ops,
 		fsverity_readahead(ctx->vi, folio->index,
 				   folio_nr_pages(folio));
 
-	while ((ret = iomap_iter(&iter, ops)) > 0)
+	while ((ret = iomap_iter(&iter, ops)) > 0) {
 		iter.status = iomap_read_folio_iter(&iter, ctx,
 				&bytes_submitted);
-
-	if (ctx->read_ctx && ctx->ops->submit_read)
-		ctx->ops->submit_read(&iter, ctx);
+		if (ctx->read_ctx && ctx->ops->submit_read)
+			ctx->ops->submit_read(&iter, ctx);
+	}
 
 	if (ctx->cur_folio)
 		iomap_read_end(ctx->cur_folio, bytes_submitted);
@@ -718,12 +718,12 @@ void iomap_readahead(const struct iomap_ops *ops,
 		fsverity_readahead(ctx->vi, readahead_index(rac),
 				readahead_count(rac));
 
-	while (iomap_iter(&iter, ops) > 0)
+	while (iomap_iter(&iter, ops) > 0) {
 		iter.status = iomap_readahead_iter(&iter, ctx,
 					&cur_bytes_submitted);
-
-	if (ctx->read_ctx && ctx->ops->submit_read)
-		ctx->ops->submit_read(&iter, ctx);
+		if (ctx->read_ctx && ctx->ops->submit_read)
+			ctx->ops->submit_read(&iter, ctx);
+	}
 
 	if (ctx->cur_folio)
 		iomap_read_end(ctx->cur_folio, cur_bytes_submitted);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index b485e3b191da..e2cd5f92babe 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -369,7 +369,7 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter,
 	 */
 	if ((op & REQ_ATOMIC) && WARN_ON_ONCE(ret != iomap_length(iter))) {
 		ret = -EINVAL;
-		goto out_put_bio;
+		goto out_bio_release_pages;
 	}
 
 	if (iter->iomap.flags & IOMAP_F_INTEGRITY) {
@@ -393,6 +393,11 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter,
 	iomap_dio_submit_bio(iter, dio, bio, pos);
 	return ret;
 
+out_bio_release_pages:
+	if (dio->flags & IOMAP_DIO_BOUNCE)
+		bio_iov_iter_unbounce(bio, true, false);
+	else
+		bio_release_pages(bio, false);
 out_put_bio:
 	bio_put(bio);
 	return ret;
diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
index f7c3e0c70fd7..0565328764c1 100644
--- a/fs/iomap/ioend.c
+++ b/fs/iomap/ioend.c
@@ -298,8 +298,12 @@ new_ioend:
 	 * appending writes.
 	 */
 	ioend->io_size += map_len;
-	if (ioend->io_offset + ioend->io_size > end_pos)
-		ioend->io_size = end_pos - ioend->io_offset;
+	if (ioend->io_offset + ioend->io_size > end_pos) {
+		if (ioend->io_offset >= end_pos)
+			ioend->io_size = 0;
+		else
+			ioend->io_size = end_pos - ioend->io_offset;
+	}
 
 	wbc_account_cgroup_owner(wpc->wbc, folio, map_len);
 	return map_len;
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index f2025c9b5825..9e52d4302f0d 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -97,7 +97,7 @@ static inline struct minix_inode_info *minix_i(struct inode *inode)
 
 static inline unsigned minix_blocks_needed(unsigned bits, unsigned blocksize)
 {
-	return DIV_ROUND_UP(bits, blocksize * 8);
+	return DIV_ROUND_UP_POW2(bits, blocksize * 8);
 }
 
 #if defined(CONFIG_MINIX_FS_NATIVE_ENDIAN) && \
diff --git a/fs/namei.c b/fs/namei.c
index 5cc9f0f466b8..19ce43c9a6e6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4736,6 +4736,10 @@ int vfs_tmpfile(struct mnt_idmap *idmap,
 	int error;
 	int open_flag = file->f_flags;
 
+	/* A tmpfile is I_LINKABLE, so guard its owner like may_o_create(). */
+	if (!fsuidgid_has_mapping(dir->i_sb, idmap))
+		return -EOVERFLOW;
+
 	/* we want directory to be writable */
 	error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC);
 	if (error)
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 76d0f6a29aba..24a8a5418e31 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -659,7 +659,7 @@ retry:
 	 * within the cache granule containing the EOF, in which case we need
 	 * to preload the granule.
 	 */
-	if (!netfs_is_cache_enabled(ctx) &&
+	if (!netfs_is_cache_maybe_enabled(ctx) &&
 	    netfs_skip_folio_read(folio, pos, len, false)) {
 		netfs_stat(&netfs_n_rh_write_zskip);
 		goto have_folio_no_wait;
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 6bde3320bcec..2cdb68e6b16f 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -277,7 +277,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		 * caching service temporarily because the backing store got
 		 * culled.
 		 */
-		if (netfs_is_cache_enabled(ctx)) {
+		if (netfs_is_cache_maybe_enabled(ctx)) {
 			if (finfo) {
 				netfs_stat(&netfs_n_wh_wstream_conflict);
 				goto flush_content;
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index 25f8ceb15fad..c16fbad286a1 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -166,13 +166,16 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq)
 		 */
 		subreq->error = -EAGAIN;
 		trace_netfs_sreq(subreq, netfs_sreq_trace_retry);
-		if (subreq->transferred > 0)
+		if (subreq->transferred > 0) {
 			iov_iter_advance(&wreq->buffer.iter, subreq->transferred);
+			wreq->transferred += subreq->transferred;
+		}
 
 		if (stream->source == NETFS_UPLOAD_TO_SERVER &&
 		    wreq->netfs_ops->retry_request)
 			wreq->netfs_ops->retry_request(wreq, stream);
 
+		__clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
 		__clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags);
 		__clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags);
 		__clear_bit(NETFS_SREQ_FAILED, &subreq->flags);
@@ -186,17 +189,10 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq)
 
 		netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
 
-		if (stream->prepare_write) {
+		if (stream->prepare_write)
 			stream->prepare_write(subreq);
-			__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
-			netfs_stat(&netfs_n_wh_retry_write_subreq);
-		} else {
-			struct iov_iter source;
-
-			netfs_reset_iter(subreq);
-			source = subreq->io_iter;
-			netfs_reissue_write(stream, subreq, &source);
-		}
+		__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
+		netfs_stat(&netfs_n_wh_retry_write_subreq);
 	}
 
 	netfs_unbuffered_write_done(wreq);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 645996ecfc80..d889caa401dc 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -239,6 +239,18 @@ static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx)
 #endif
 }
 
+static inline bool netfs_is_cache_maybe_enabled(struct netfs_inode *ctx)
+{
+#if IS_ENABLED(CONFIG_FSCACHE)
+	struct fscache_cookie *cookie = ctx->cache;
+
+	return fscache_cookie_valid(cookie) &&
+		test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags);
+#else
+	return false;
+#endif
+}
+
 /*
  * Get a ref on a netfs group attached to a dirty page (e.g. a ceph snap).
  */
diff --git a/fs/netfs/locking.c b/fs/netfs/locking.c
index 2249ecd09d0a..4e3be2b81504 100644
--- a/fs/netfs/locking.c
+++ b/fs/netfs/locking.c
@@ -9,6 +9,11 @@
 #include <linux/netfs.h>
 #include "internal.h"
 
+struct netfs_wb_waiter {
+	struct list_head	link;		/* Link in ictx->wb_queue */
+	struct task_struct	*waiter;	/* Waiter task; cleared when lock granted */
+};
+
 /*
  * inode_dio_wait_interruptible - wait for outstanding DIO requests to finish
  * @inode: inode to wait for
@@ -203,3 +208,93 @@ void netfs_end_io_direct(struct inode *inode)
 	up_read(&inode->i_rwsem);
 }
 EXPORT_SYMBOL(netfs_end_io_direct);
+
+/*
+ * Wait to have exclusive access to writeback.
+ */
+static bool netfs_wb_begin_wait(struct netfs_inode *ictx)
+{
+	struct netfs_wb_waiter waiter = {};
+	struct task_struct *tsk = current;
+	bool got = false;
+
+	spin_lock(&ictx->lock);
+
+	if (test_and_set_bit_lock(NETFS_ICTX_WB_LOCK, &ictx->flags)) {
+		get_task_struct(tsk);
+		waiter.waiter = tsk;
+		list_add_tail(&waiter.link, &ictx->wb_queue);
+	} else {
+		got = true;
+	}
+	spin_unlock(&ictx->lock);
+
+	if (!got) {
+		for (;;) {
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			/* Read waiter before accessing inode state. */
+			if (smp_load_acquire(&waiter.waiter) == NULL)
+				break;
+			schedule();
+		}
+	}
+	__set_current_state(TASK_RUNNING);
+	return true;
+}
+
+/**
+ * netfs_wb_begin - Begin writeback, waiting if need be
+ * @ictx: The inode to get writeback access on
+ * @nowait: Return failure immediately rather than waiting if true
+ *
+ * Begin writeback to an inode, waiting for exclusive access if @nowait is
+ * false.  This prevents collection from being done out of order with respect
+ * to the issuance of write subrequests.
+ *
+ * Note that writeback may be ended in a different process (e.g. the collection
+ * function on a workqueue) than started it.
+ *
+ * Return: True if can proceed, false if denied.
+ */
+bool netfs_wb_begin(struct netfs_inode *ictx, bool nowait)
+{
+	if (!test_and_set_bit_lock(NETFS_ICTX_WB_LOCK, &ictx->flags))
+		return true;
+	if (nowait) {
+		netfs_stat(&netfs_n_wb_lock_skip);
+		return false;
+	}
+	netfs_stat(&netfs_n_wb_lock_wait);
+	return netfs_wb_begin_wait(ictx);
+}
+EXPORT_SYMBOL(netfs_wb_begin);
+
+/* netfs_wb_end - End writeback
+ * @ictx: The inode we have writeback access to
+ *
+ * End writeback access on an inode, waking up the next writeback request.
+ */
+void netfs_wb_end(struct netfs_inode *ictx)
+{
+	struct netfs_wb_waiter *waiter;
+	struct task_struct *tsk;
+
+	WARN_ON_ONCE(!test_bit(NETFS_ICTX_WB_LOCK, &ictx->flags));
+
+	spin_lock(&ictx->lock);
+
+	waiter = list_first_entry_or_null(&ictx->wb_queue, struct netfs_wb_waiter, link);
+	if (waiter) {
+		list_del(&waiter->link);
+		tsk = waiter->waiter;
+		/* Write inode state before clearing waiter. */
+		smp_store_release(&waiter->waiter, NULL);
+		wake_up_process(tsk);
+		put_task_struct(tsk);
+	} else {
+		clear_bit_unlock(NETFS_ICTX_WB_LOCK, &ictx->flags);
+	}
+
+	spin_unlock(&ictx->lock);
+}
+EXPORT_SYMBOL(netfs_wb_end);
diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c
index f59a70f3a086..2b42758e01ec 100644
--- a/fs/netfs/read_retry.c
+++ b/fs/netfs/read_retry.c
@@ -98,7 +98,12 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq)
 			goto abandon;
 		}
 
-		list_for_each_continue(next, &stream->subrequests) {
+		for (;;) {
+			/* Read pointer to subreq before reading subreq state. */
+			next = smp_load_acquire(&next->next);
+			if (next == &stream->subrequests)
+				break;
+
 			subreq = list_entry(next, struct netfs_io_subrequest, rreq_link);
 			if (subreq->start + subreq->transferred != start + len ||
 			    test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags) ||
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 24fc2bb2f8a4..210eb8f3958d 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -408,6 +408,16 @@ bool netfs_write_collection(struct netfs_io_request *wreq)
 	netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip);
 	/* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */
 
+	switch (wreq->origin) {
+	case NETFS_WRITEBACK:
+	case NETFS_WRITEBACK_SINGLE:
+	case NETFS_WRITETHROUGH:
+		netfs_wb_end(ictx);
+		break;
+	default:
+		break;
+	}
+
 	if (wreq->iocb) {
 		size_t written = min(wreq->transferred, wreq->len);
 		wreq->iocb->ki_pos += written;
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index c03c7cc45e47..f2761c99795a 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -106,7 +106,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
 	_enter("R=%x", wreq->debug_id);
 
 	ictx = netfs_inode(wreq->inode);
-	if (is_cacheable && netfs_is_cache_enabled(ictx))
+	if (is_cacheable)
 		fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx));
 	if (rolling_buffer_init(&wreq->buffer, wreq->debug_id, ITER_SOURCE) < 0)
 		goto nomem;
@@ -551,14 +551,8 @@ int netfs_writepages(struct address_space *mapping,
 	struct folio *folio;
 	int error = 0;
 
-	if (!mutex_trylock(&ictx->wb_lock)) {
-		if (wbc->sync_mode == WB_SYNC_NONE) {
-			netfs_stat(&netfs_n_wb_lock_skip);
-			return 0;
-		}
-		netfs_stat(&netfs_n_wb_lock_wait);
-		mutex_lock(&ictx->wb_lock);
-	}
+	if (!netfs_wb_begin(ictx, wbc->sync_mode == WB_SYNC_NONE))
+		return 0;
 
 	/* Need the first folio to be able to set up the op. */
 	folio = writeback_iter(mapping, wbc, NULL, &error);
@@ -588,13 +582,13 @@ int netfs_writepages(struct address_space *mapping,
 		}
 
 		error = netfs_write_folio(wreq, wbc, folio);
-		if (error < 0)
-			break;
+		if (error == -ENOMEM) {
+			folio_redirty_for_writepage(wbc, folio);
+			folio_unlock(folio);
+		}
 	} while ((folio = writeback_iter(mapping, wbc, folio, &error)));
 
 	netfs_end_issue_write(wreq);
-
-	mutex_unlock(&ictx->wb_lock);
 	netfs_wake_collector(wreq);
 
 	netfs_put_request(wreq, netfs_rreq_trace_put_return);
@@ -602,9 +596,16 @@ int netfs_writepages(struct address_space *mapping,
 	return error;
 
 couldnt_start:
-	netfs_kill_dirty_pages(mapping, wbc, folio);
+	if (error == -ENOMEM) {
+		folio_redirty_for_writepage(wbc, folio);
+		folio_unlock(folio);
+		folio = writeback_iter(mapping, wbc, folio, &error);
+		WARN_ON_ONCE(folio != NULL);
+	} else {
+		netfs_kill_dirty_pages(mapping, wbc, folio);
+	}
 out:
-	mutex_unlock(&ictx->wb_lock);
+	netfs_wb_end(ictx);
 	_leave(" = %d", error);
 	return error;
 }
@@ -618,16 +619,17 @@ struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len
 	struct netfs_io_request *wreq = NULL;
 	struct netfs_inode *ictx = netfs_inode(file_inode(iocb->ki_filp));
 
-	mutex_lock(&ictx->wb_lock);
+	netfs_wb_begin(ictx, false);
 
 	wreq = netfs_create_write_req(iocb->ki_filp->f_mapping, iocb->ki_filp,
 				      iocb->ki_pos, NETFS_WRITETHROUGH);
 	if (IS_ERR(wreq)) {
-		mutex_unlock(&ictx->wb_lock);
+		netfs_wb_end(ictx);
 		return wreq;
 	}
 
 	wreq->io_streams[0].avail = true;
+	__set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags);
 	trace_netfs_write(wreq, netfs_write_trace_writethrough);
 	return wreq;
 }
@@ -685,7 +687,6 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c
 ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc,
 			       struct folio *writethrough_cache)
 {
-	struct netfs_inode *ictx = netfs_inode(wreq->inode);
 	ssize_t ret;
 
 	_enter("R=%x", wreq->debug_id);
@@ -699,8 +700,6 @@ ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_c
 
 	netfs_end_issue_write(wreq);
 
-	mutex_unlock(&ictx->wb_lock);
-
 	if (wreq->iocb)
 		ret = -EIOCBQUEUED;
 	else
@@ -847,15 +846,10 @@ int netfs_writeback_single(struct address_space *mapping,
 	if (WARN_ON_ONCE(!iov_iter_is_folioq(iter)))
 		return -EIO;
 
-	if (!mutex_trylock(&ictx->wb_lock)) {
-		if (wbc->sync_mode == WB_SYNC_NONE) {
-			/* The VFS will have undirtied the inode. */
-			netfs_single_mark_inode_dirty(&ictx->inode);
-			netfs_stat(&netfs_n_wb_lock_skip);
-			return 1;
-		}
-		netfs_stat(&netfs_n_wb_lock_wait);
-		mutex_lock(&ictx->wb_lock);
+	if (!netfs_wb_begin(ictx, wbc->sync_mode == WB_SYNC_NONE)) {
+		/* The VFS will have undirtied the inode. */
+		netfs_single_mark_inode_dirty(&ictx->inode);
+		return 1;
 	}
 
 	wreq = netfs_create_write_req(mapping, NULL, 0, NETFS_WRITEBACK_SINGLE);
@@ -893,7 +887,6 @@ stop:
 	smp_wmb(); /* Write lists before ALL_QUEUED. */
 	set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags);
 
-	mutex_unlock(&ictx->wb_lock);
 	netfs_wake_collector(wreq);
 
 	netfs_put_request(wreq, netfs_rreq_trace_put_return);
@@ -901,7 +894,7 @@ stop:
 	return ret;
 
 couldnt_start:
-	mutex_unlock(&ictx->wb_lock);
+	netfs_wb_end(ictx);
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c
index 32735abfa03f..058bc7a166a5 100644
--- a/fs/netfs/write_retry.c
+++ b/fs/netfs/write_retry.c
@@ -72,7 +72,12 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq,
 		    !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags))
 			return;
 
-		list_for_each_continue(next, &stream->subrequests) {
+		for (;;) {
+			/* Read pointer to subreq before reading subreq state. */
+			next = smp_load_acquire(&next->next);
+			if (next == &stream->subrequests)
+				break;
+
 			subreq = list_entry(next, struct netfs_io_subrequest, rreq_link);
 			if (subreq->start + subreq->transferred != start + len ||
 			    test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags) ||
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 1fbf832ad165..f2bb56506046 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -38,11 +38,9 @@ static void ntfs_iomap_read_end_io(struct bio *bio)
 }
 
 static void ntfs_iomap_bio_submit_read(const struct iomap_iter *iter,
-	struct iomap_read_folio_ctx *ctx)
+		struct iomap_read_folio_ctx *ctx)
 {
-	struct bio *bio = ctx->read_ctx;
-	bio->bi_end_io = ntfs_iomap_read_end_io;
-	submit_bio(bio);
+	iomap_bio_submit_read_endio(iter, ctx, ntfs_iomap_read_end_io);
 }
 
 static const struct iomap_read_ops ntfs_iomap_bio_read_ops = {
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index c43101cc064d..0c9bd669117d 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -608,10 +608,7 @@ static void ntfs_iomap_read_end_io(struct bio *bio)
 static void ntfs_iomap_bio_submit_read(const struct iomap_iter *iter,
 		struct iomap_read_folio_ctx *ctx)
 {
-	struct bio *bio = ctx->read_ctx;
-
-	bio->bi_end_io = ntfs_iomap_read_end_io;
-	submit_bio(bio);
+	iomap_bio_submit_read_endio(iter, ctx, ntfs_iomap_read_end_io);
 }
 
 static const struct iomap_read_ops ntfs_iomap_bio_read_ops = {
diff --git a/fs/orangefs/dir.c b/fs/orangefs/dir.c
index 6e2ebc8b9867..115b2c2f5269 100644
--- a/fs/orangefs/dir.c
+++ b/fs/orangefs/dir.c
@@ -191,7 +191,8 @@ static int fill_from_part(struct orangefs_dir_part *part,
 {
 	const int offset = sizeof(struct orangefs_readdir_response_s);
 	struct orangefs_khandle *khandle;
-	__u32 *len, padlen;
+	__u32 *len;
+	u64 padlen;
 	loff_t i;
 	char *s;
 	i = ctx->pos & ~PART_MASK;
@@ -215,8 +216,8 @@ static int fill_from_part(struct orangefs_dir_part *part,
 		 * len is the size of the string itself.  padlen is the
 		 * total size of the encoded string.
 		 */
-		padlen = (sizeof *len + *len + 1) +
-		    (8 - (sizeof *len + *len + 1)%8)%8;
+		padlen = (u64)sizeof *len + *len + 1;
+		padlen += (8 - padlen % 8) % 8;
 		if (part->len < i + padlen + sizeof *khandle)
 			goto next;
 		s = (void *)part + offset + i + sizeof *len;
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 13cb60b52bd6..e963701b4c87 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -853,7 +853,7 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c)
 {
 	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
 	struct inode *udir = d_inode(c->destdir);
-	struct dentry *temp, *upper;
+	struct dentry *temp, *upper, *newdentry = NULL;
 	struct file *tmpfile;
 	int err;
 
@@ -889,6 +889,14 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c)
 	err = PTR_ERR(upper);
 	if (!IS_ERR(upper)) {
 		err = ovl_do_link(ofs, temp, udir, upper);
+		if (!err) {
+			/*
+			 * Record the linked dentry -- not the disconnected
+			 * O_TMPFILE dentry -- so that ->d_revalidate() on
+			 * the upper fs sees the real parent/name.
+			 */
+			newdentry = dget(upper);
+		}
 		end_creating(upper);
 	}
 
@@ -903,7 +911,7 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c)
 
 	if (!c->metacopy)
 		ovl_set_upperdata(d_inode(c->dentry));
-	ovl_inode_update(d_inode(c->dentry), dget(temp));
+	ovl_inode_update(d_inode(c->dentry), newdentry);
 
 out:
 	ovl_end_write(c->dentry);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 00c69707bda9..bc71231cad53 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -783,8 +783,8 @@ static const struct address_space_operations ovl_aops = {
  *
  * This chain is valid:
  * - inode->i_rwsem			(inode_lock[2])
- * - upper_mnt->mnt_sb->s_writers	(ovl_want_write[0])
  * - OVL_I(inode)->lock			(ovl_inode_lock[2])
+ * - upper_mnt->mnt_sb->s_writers	(ovl_want_write[0])
  * - OVL_I(lowerinode)->lock		(ovl_inode_lock[1])
  *
  * And this chain is valid:
@@ -797,8 +797,8 @@ static const struct address_space_operations ovl_aops = {
  * held, because it is in reverse order of the non-nested case using the same
  * upper fs:
  * - inode->i_rwsem			(inode_lock[1])
- * - upper_mnt->mnt_sb->s_writers	(ovl_want_write[0])
  * - OVL_I(inode)->lock			(ovl_inode_lock[1])
+ * - upper_mnt->mnt_sb->s_writers	(ovl_want_write[0])
  */
 #define OVL_MAX_NESTING FILESYSTEM_MAX_STACK_DEPTH
 
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index adc9b9a092b0..26086a283672 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -112,6 +112,8 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir,
 	/* Add new node and rebalance tree. */
 	rb_link_node(&de->subdir_node, parent, new);
 	rb_insert_color(&de->subdir_node, root);
+	if (S_ISDIR(de->mode))
+		dir->nlink++;
 	return true;
 }
 
@@ -404,7 +406,6 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
 		write_unlock(&proc_subdir_lock);
 		goto out_free_inum;
 	}
-	dir->nlink++;
 	write_unlock(&proc_subdir_lock);
 
 	return dp;
@@ -706,6 +707,8 @@ static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent)
 {
 	rb_erase(&pde->subdir_node, &parent->subdir);
 	RB_CLEAR_NODE(&pde->subdir_node);
+	if (S_ISDIR(pde->mode))
+		parent->nlink--;
 }
 
 /*
@@ -731,8 +734,6 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 			de = NULL;
 		} else {
 			pde_erase(de, parent);
-			if (S_ISDIR(de->mode))
-				parent->nlink--;
 		}
 	}
 	write_unlock(&proc_subdir_lock);
@@ -791,8 +792,6 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
 			continue;
 		}
 		next = de->parent;
-		if (S_ISDIR(de->mode))
-			next->nlink--;
 		write_unlock(&proc_subdir_lock);
 
 		proc_entry_rundown(de);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 2a0c54256e93..51293b6f331f 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -764,8 +764,7 @@ xfs_bio_submit_read(
 
 	/* defer read completions to the ioend workqueue */
 	iomap_init_ioend(iter->inode, bio, ctx->read_ctx_file_offset, 0);
-	bio->bi_end_io = xfs_end_bio;
-	submit_bio(bio);
+	iomap_bio_submit_read_endio(iter, ctx, xfs_end_bio);
 }
 
 static const struct iomap_read_ops xfs_iomap_read_ops = {
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index eac7f9503805..8531d526fc44 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -534,8 +534,11 @@ xfs_open_devices(
  out_free_rtdev_targ:
 	if (mp->m_rtdev_targp)
 		xfs_free_buftarg(mp->m_rtdev_targp);
+	mp->m_rtdev_targp = NULL;
+	rtdev_file = NULL;	/* released by xfs_free_buftarg() */
  out_free_ddev_targ:
 	xfs_free_buftarg(mp->m_ddev_targp);
+	mp->m_ddev_targp = NULL;
  out_close_rtdev:
 	 if (rtdev_file)
 		bdev_fput(rtdev_file);