Merge tag 'vfs-6.18-rc7.fixes' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:

 - Fix unitialized variable in statmount_string()

 - Fix hostfs mounting when passing host root during boot

 - Fix dynamic lookup to fail on cell lookup failure

 - Fix missing file type when reading bfs inodes from disk

 - Enforce checking of sb_min_blocksize() calls and update all callers
   accordingly

 - Restore write access before closing files opened by open_exec() in
   binfmt_misc

 - Always freeze efivarfs during suspend/hibernate cycles

 - Fix statmount()'s and listmount()'s grab_requested_mnt_ns() helper to
   actually allow mount namespace file descriptor in addition to mount
   namespace ids

 - Fix tmpfs remount when noswap is specified

 - Switch Landlock to iput_not_last() to remove false-positives from
   might_sleep() annotations in iput()

 - Remove dead node_to_mnt_ns() code

 - Ensure that per-queue kobjects are successfully created

* tag 'vfs-6.18-rc7.fixes' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs:
  landlock: fix splats from iput() after it started calling might_sleep()
  fs: add iput_not_last()
  shmem: fix tmpfs reconfiguration (remount) when noswap is set
  fs/namespace: correctly handle errors returned by grab_requested_mnt_ns
  power: always freeze efivarfs
  binfmt_misc: restore write access before closing files opened by open_exec()
  block: add __must_check attribute to sb_min_blocksize()
  virtio-fs: fix incorrect check for fsvq->kobj
  xfs: check the return value of sb_min_blocksize() in xfs_fs_fill_super
  isofs: check the return value of sb_min_blocksize() in isofs_fill_super
  exfat: check return value of sb_min_blocksize in exfat_read_boot_sector
  vfat: fix missing sb_min_blocksize() return value checks
  mnt: Remove dead code which might prevent from building
  bfs: Reconstruct file type when loading from disk
  afs: Fix dynamic lookup to fail on cell lookup failure
  hostfs: Fix only passing host root in boot stage with new mount
  fs: Fix uninitialized 'offp' in statmount_string()

Author: torvalds

block/bdev.c

@@ -231,7 +231,7 @@ int sb_set_blocksize(struct super_block *sb, int size)
 
 EXPORT_SYMBOL(sb_set_blocksize);
 
-int sb_min_blocksize(struct super_block *sb, int size)
+int __must_check sb_min_blocksize(struct super_block *sb, int size)
 {
 	int minsize = bdev_logical_block_size(sb->s_bdev);
 	if (size < minsize)

fs/afs/cell.c

@@ -229,7 +229,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
  * @name:	The name of the cell.
  * @namesz:	The strlen of the cell name.
  * @vllist:	A colon/comma separated list of numeric IP addresses or NULL.
- * @excl:	T if an error should be given if the cell name already exists.
+ * @reason:	The reason we're doing the lookup
  * @trace:	The reason to be logged if the lookup is successful.
  *
  * Look up a cell record by name and query the DNS for VL server addresses if
@@ -239,20 +239,27 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
  */
 struct afs_cell *afs_lookup_cell(struct afs_net *net,
 				 const char *name, unsigned int namesz,
-				 const char *vllist, bool excl,
+				 const char *vllist,
+				 enum afs_lookup_cell_for reason,
 				 enum afs_cell_trace trace)
 {
 	struct afs_cell *cell, *candidate, *cursor;
 	struct rb_node *parent, **pp;
 	enum afs_cell_state state;
 	int ret, n;
 
-	_enter("%s,%s", name, vllist);
+	_enter("%s,%s,%u", name, vllist, reason);
 
-	if (!excl) {
+	if (reason != AFS_LOOKUP_CELL_PRELOAD) {
 		cell = afs_find_cell(net, name, namesz, trace);
-		if (!IS_ERR(cell))
+		if (!IS_ERR(cell)) {
+			if (reason == AFS_LOOKUP_CELL_DYNROOT)
+				goto no_wait;
+			if (cell->state == AFS_CELL_SETTING_UP ||
+			    cell->state == AFS_CELL_UNLOOKED)
+				goto lookup_cell;
 			goto wait_for_cell;
+		}
 	}
 
 	/* Assume we're probably going to create a cell and preallocate and
@@ -298,34 +305,77 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net,
 	rb_insert_color(&cell->net_node, &net->cells);
 	up_write(&net->cells_lock);
 
-	afs_queue_cell(cell, afs_cell_trace_queue_new);
+lookup_cell:
+	if (reason != AFS_LOOKUP_CELL_PRELOAD &&
+	    reason != AFS_LOOKUP_CELL_ROOTCELL) {
+		set_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags);
+		afs_queue_cell(cell, afs_cell_trace_queue_new);
+	}
 
 wait_for_cell:
-	_debug("wait_for_cell");
 	state = smp_load_acquire(&cell->state); /* vs error */
-	if (state != AFS_CELL_ACTIVE &&
-	    state != AFS_CELL_DEAD) {
+	switch (state) {
+	case AFS_CELL_ACTIVE:
+	case AFS_CELL_DEAD:
+		break;
+	case AFS_CELL_UNLOOKED:
+	default:
+		if (reason == AFS_LOOKUP_CELL_PRELOAD ||
+		    reason == AFS_LOOKUP_CELL_ROOTCELL)
+			break;
+		_debug("wait_for_cell");
 		afs_see_cell(cell, afs_cell_trace_wait);
 		wait_var_event(&cell->state,
 			       ({
 				       state = smp_load_acquire(&cell->state); /* vs error */
 				       state == AFS_CELL_ACTIVE || state == AFS_CELL_DEAD;
 			       }));
+		_debug("waited_for_cell %d %d", cell->state, cell->error);
 	}
 
+no_wait:
 	/* Check the state obtained from the wait check. */
+	state = smp_load_acquire(&cell->state); /* vs error */
 	if (state == AFS_CELL_DEAD) {
 		ret = cell->error;
 		goto error;
 	}
+	if (state == AFS_CELL_ACTIVE) {
+		switch (cell->dns_status) {
+		case DNS_LOOKUP_NOT_DONE:
+			if (cell->dns_source == DNS_RECORD_FROM_CONFIG) {
+				ret = 0;
+				break;
+			}
+			fallthrough;
+		default:
+			ret = -EIO;
+			goto error;
+		case DNS_LOOKUP_GOOD:
+		case DNS_LOOKUP_GOOD_WITH_BAD:
+			ret = 0;
+			break;
+		case DNS_LOOKUP_GOT_NOT_FOUND:
+			ret = -ENOENT;
+			goto error;
+		case DNS_LOOKUP_BAD:
+			ret = -EREMOTEIO;
+			goto error;
+		case DNS_LOOKUP_GOT_LOCAL_FAILURE:
+		case DNS_LOOKUP_GOT_TEMP_FAILURE:
+		case DNS_LOOKUP_GOT_NS_FAILURE:
+			ret = -EDESTADDRREQ;
+			goto error;
+		}
+	}
 
 	_leave(" = %p [cell]", cell);
 	return cell;
 
 cell_already_exists:
 	_debug("cell exists");
 	cell = cursor;
-	if (excl) {
+	if (reason == AFS_LOOKUP_CELL_PRELOAD) {
 		ret = -EEXIST;
 	} else {
 		afs_use_cell(cursor, trace);
@@ -384,7 +434,8 @@ int afs_cell_init(struct afs_net *net, const char *rootcell)
 		return -EINVAL;
 
 	/* allocate a cell record for the root/workstation cell */
-	new_root = afs_lookup_cell(net, rootcell, len, vllist, false,
+	new_root = afs_lookup_cell(net, rootcell, len, vllist,
+				   AFS_LOOKUP_CELL_ROOTCELL,
 				   afs_cell_trace_use_lookup_ws);
 	if (IS_ERR(new_root)) {
 		_leave(" = %ld", PTR_ERR(new_root));
@@ -777,6 +828,7 @@ static bool afs_manage_cell(struct afs_cell *cell)
 	switch (cell->state) {
 	case AFS_CELL_SETTING_UP:
 		goto set_up_cell;
+	case AFS_CELL_UNLOOKED:
 	case AFS_CELL_ACTIVE:
 		goto cell_is_active;
 	case AFS_CELL_REMOVING:
@@ -797,7 +849,7 @@ static bool afs_manage_cell(struct afs_cell *cell)
 		goto remove_cell;
 	}
 
-	afs_set_cell_state(cell, AFS_CELL_ACTIVE);
+	afs_set_cell_state(cell, AFS_CELL_UNLOOKED);
 
 cell_is_active:
 	if (afs_has_cell_expired(cell, &next_manage))
@@ -807,6 +859,8 @@ static bool afs_manage_cell(struct afs_cell *cell)
 		ret = afs_update_cell(cell);
 		if (ret < 0)
 			cell->error = ret;
+		if (cell->state == AFS_CELL_UNLOOKED)
+			afs_set_cell_state(cell, AFS_CELL_ACTIVE);
 	}
 
 	if (next_manage < TIME64_MAX && cell->net->live) {

fs/afs/dynroot.c

@@ -108,7 +108,8 @@ static struct dentry *afs_dynroot_lookup_cell(struct inode *dir, struct dentry *
 		dotted = true;
 	}
 
-	cell = afs_lookup_cell(net, name, len, NULL, false,
+	cell = afs_lookup_cell(net, name, len, NULL,
+			       AFS_LOOKUP_CELL_DYNROOT,
 			       afs_cell_trace_use_lookup_dynroot);
 	if (IS_ERR(cell)) {
 		ret = PTR_ERR(cell);

fs/afs/internal.h

@@ -343,6 +343,7 @@ extern const char afs_init_sysname[];
 
 enum afs_cell_state {
 	AFS_CELL_SETTING_UP,
+	AFS_CELL_UNLOOKED,
 	AFS_CELL_ACTIVE,
 	AFS_CELL_REMOVING,
 	AFS_CELL_DEAD,
@@ -1049,9 +1050,18 @@ static inline bool afs_cb_is_broken(unsigned int cb_break,
 extern int afs_cell_init(struct afs_net *, const char *);
 extern struct afs_cell *afs_find_cell(struct afs_net *, const char *, unsigned,
 				      enum afs_cell_trace);
+enum afs_lookup_cell_for {
+	AFS_LOOKUP_CELL_DYNROOT,
+	AFS_LOOKUP_CELL_MOUNTPOINT,
+	AFS_LOOKUP_CELL_DIRECT_MOUNT,
+	AFS_LOOKUP_CELL_PRELOAD,
+	AFS_LOOKUP_CELL_ROOTCELL,
+	AFS_LOOKUP_CELL_ALIAS_CHECK,
+};
 struct afs_cell *afs_lookup_cell(struct afs_net *net,
 				 const char *name, unsigned int namesz,
-				 const char *vllist, bool excl,
+				 const char *vllist,
+				 enum afs_lookup_cell_for reason,
 				 enum afs_cell_trace trace);
 extern struct afs_cell *afs_use_cell(struct afs_cell *, enum afs_cell_trace);
 void afs_unuse_cell(struct afs_cell *cell, enum afs_cell_trace reason);

fs/afs/mntpt.c

@@ -107,7 +107,8 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 		if (size > AFS_MAXCELLNAME)
 			return -ENAMETOOLONG;
 
-		cell = afs_lookup_cell(ctx->net, p, size, NULL, false,
+		cell = afs_lookup_cell(ctx->net, p, size, NULL,
+				       AFS_LOOKUP_CELL_MOUNTPOINT,
 				       afs_cell_trace_use_lookup_mntpt);
 		if (IS_ERR(cell)) {
 			pr_err("kAFS: unable to lookup cell '%pd'\n", mntpt);

fs/afs/proc.c

@@ -122,7 +122,8 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size)
 	if (strcmp(buf, "add") == 0) {
 		struct afs_cell *cell;
 
-		cell = afs_lookup_cell(net, name, strlen(name), args, true,
+		cell = afs_lookup_cell(net, name, strlen(name), args,
+				       AFS_LOOKUP_CELL_PRELOAD,
 				       afs_cell_trace_use_lookup_add);
 		if (IS_ERR(cell)) {
 			ret = PTR_ERR(cell);

fs/afs/super.c

@@ -290,7 +290,7 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param)
 	/* lookup the cell record */
 	if (cellname) {
 		cell = afs_lookup_cell(ctx->net, cellname, cellnamesz,
-				       NULL, false,
+				       NULL, AFS_LOOKUP_CELL_DIRECT_MOUNT,
 				       afs_cell_trace_use_lookup_mount);
 		if (IS_ERR(cell)) {
 			pr_err("kAFS: unable to lookup cell '%*.*s'\n",

fs/afs/vl_alias.c

@@ -269,7 +269,8 @@ static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key)
 	if (!name_len || name_len > AFS_MAXCELLNAME)
 		master = ERR_PTR(-EOPNOTSUPP);
 	else
-		master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, false,
+		master = afs_lookup_cell(cell->net, cell_name, name_len, NULL,
+					 AFS_LOOKUP_CELL_ALIAS_CHECK,
 					 afs_cell_trace_use_lookup_canonical);
 	kfree(cell_name);
 	if (IS_ERR(master))

fs/bfs/inode.c

@@ -61,7 +61,19 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino)
 	off = (ino - BFS_ROOT_INO) % BFS_INODES_PER_BLOCK;
 	di = (struct bfs_inode *)bh->b_data + off;
 
-	inode->i_mode = 0x0000FFFF & le32_to_cpu(di->i_mode);
+	/*
+	 * https://martin.hinner.info/fs/bfs/bfs-structure.html explains that
+	 * BFS in SCO UnixWare environment used only lower 9 bits of di->i_mode
+	 * value. This means that, although bfs_write_inode() saves whole
+	 * inode->i_mode bits (which include S_IFMT bits and S_IS{UID,GID,VTX}
+	 * bits), middle 7 bits of di->i_mode value can be garbage when these
+	 * bits were not saved by bfs_write_inode().
+	 * Since we can't tell whether middle 7 bits are garbage, use only
+	 * lower 12 bits (i.e. tolerate S_IS{UID,GID,VTX} bits possibly being
+	 * garbage) and reconstruct S_IFMT bits for Linux environment from
+	 * di->i_vtype value.
+	 */
+	inode->i_mode = 0x00000FFF & le32_to_cpu(di->i_mode);
 	if (le32_to_cpu(di->i_vtype) == BFS_VDIR) {
 		inode->i_mode |= S_IFDIR;
 		inode->i_op = &bfs_dir_inops;
@@ -71,6 +83,11 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino)
 		inode->i_op = &bfs_file_inops;
 		inode->i_fop = &bfs_file_operations;
 		inode->i_mapping->a_ops = &bfs_aops;
+	} else {
+		brelse(bh);
+		printf("Unknown vtype=%u %s:%08lx\n",
+		       le32_to_cpu(di->i_vtype), inode->i_sb->s_id, ino);
+		goto error;
 	}
 
 	BFS_I(inode)->i_sblock =  le32_to_cpu(di->i_sblock);

fs/binfmt_misc.c

@@ -837,8 +837,10 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 	inode_unlock(d_inode(root));
 
 	if (err) {
-		if (f)
+		if (f) {
+			exe_file_allow_write_access(f);
 			filp_close(f, NULL);
+		}
 		kfree(e);
 		return err;
 	}