vfs-6.18-rc7.fixes

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCaRtBJwAKCRCRxhvAZXjc
 ou5CAQCJb5y2ULKklblICU1wR7Nr15WvTW7VVOcv44RJ22S3NgEAy4DLDBFBw8zC
 8e7Hp8gxbjsq8ZJmU088aobFcqbZOwk=
 =TAnu
 -----END PGP SIGNATURE-----

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()

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)

drivers/mtd/mtdchar.c

@@ -599,6 +599,7 @@ mtdchar_write_ioctl(struct mtd_info *mtd, struct mtd_write_req __user *argp)
 	uint8_t *datbuf = NULL, *oobbuf = NULL;
 	size_t datbuf_len, oobbuf_len;
 	int ret = 0;
+	u64 end;
 
 	if (copy_from_user(&req, argp, sizeof(req)))
 		return -EFAULT;
@@ -618,7 +619,7 @@ mtdchar_write_ioctl(struct mtd_info *mtd, struct mtd_write_req __user *argp)
 	req.len &= 0xffffffff;
 	req.ooblen &= 0xffffffff;
 
-	if (req.start + req.len > mtd->size)
+	if (check_add_overflow(req.start, req.len, &end) || end > mtd->size)
 		return -EINVAL;
 
 	datbuf_len = min_t(size_t, req.len, mtd->erasesize);
@@ -698,6 +699,7 @@ mtdchar_read_ioctl(struct mtd_info *mtd, struct mtd_read_req __user *argp)
 	size_t datbuf_len, oobbuf_len;
 	size_t orig_len, orig_ooblen;
 	int ret = 0;
+	u64 end;
 
 	if (copy_from_user(&req, argp, sizeof(req)))
 		return -EFAULT;
@@ -724,7 +726,7 @@ mtdchar_read_ioctl(struct mtd_info *mtd, struct mtd_read_req __user *argp)
 	req.len &= 0xffffffff;
 	req.ooblen &= 0xffffffff;
 
-	if (req.start + req.len > mtd->size) {
+	if (check_add_overflow(req.start, req.len, &end) || end > mtd->size) {
 		ret = -EINVAL;
 		goto out;
 	}

drivers/mtd/nand/Kconfig

@@ -63,7 +63,7 @@ config MTD_NAND_ECC_MEDIATEK
 
 config MTD_NAND_ECC_REALTEK
         tristate "Realtek RTL93xx hardware ECC engine"
-        depends on HAS_IOMEM
+        depends on HAS_IOMEM && HAS_DMA
         depends on MACH_REALTEK_RTL || COMPILE_TEST
         select MTD_NAND_ECC
         help

drivers/mtd/nand/ecc-realtek.c

@@ -380,7 +380,7 @@ static void rtl_ecc_cleanup_ctx(struct nand_device *nand)
 		nand_ecc_cleanup_req_tweaking(&ctx->req_ctx);
 }
 
-static struct nand_ecc_engine_ops rtl_ecc_engine_ops = {
+static const struct nand_ecc_engine_ops rtl_ecc_engine_ops = {
 	.init_ctx = rtl_ecc_init_ctx,
 	.cleanup_ctx = rtl_ecc_cleanup_ctx,
 	.prepare_io_req = rtl_ecc_prepare_io_req,
@@ -418,8 +418,8 @@ static int rtl_ecc_probe(struct platform_device *pdev)
 
 	rtlc->buf = dma_alloc_noncoherent(dev, RTL_ECC_DMA_SIZE, &rtlc->buf_dma,
 					  DMA_BIDIRECTIONAL, GFP_KERNEL);
-	if (IS_ERR(rtlc->buf))
-		return PTR_ERR(rtlc->buf);
+	if (!rtlc->buf)
+		return -ENOMEM;
 
 	rtlc->dev = dev;
 	rtlc->engine.dev = dev;

drivers/mtd/nand/onenand/onenand_samsung.c

@@ -906,7 +906,7 @@ static int s3c_onenand_probe(struct platform_device *pdev)
 			err = devm_request_irq(&pdev->dev, r->start,
 					       s5pc110_onenand_irq,
 					       IRQF_SHARED, "onenand",
-					       &onenand);
+					       onenand);
 			if (err) {
 				dev_err(&pdev->dev, "failed to get irq\n");
 				return err;

drivers/mtd/nand/raw/cadence-nand-controller.c

@@ -2871,7 +2871,7 @@ cadence_nand_irq_cleanup(int irqnum, struct cdns_nand_ctrl *cdns_ctrl)
 static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 {
 	dma_cap_mask_t mask;
-	struct dma_device *dma_dev = cdns_ctrl->dmac->device;
+	struct dma_device *dma_dev;
 	int ret;
 
 	cdns_ctrl->cdma_desc = dma_alloc_coherent(cdns_ctrl->dev,
@@ -2915,6 +2915,7 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 		}
 	}
 
+	dma_dev = cdns_ctrl->dmac->device;
 	cdns_ctrl->io.iova_dma = dma_map_resource(dma_dev->dev, cdns_ctrl->io.dma,
 						  cdns_ctrl->io.size,
 						  DMA_BIDIRECTIONAL, 0);

drivers/mtd/nand/spi/fmsh.c

@@ -58,7 +58,7 @@ static const struct spinand_info fmsh_spinand_table[] = {
 		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
 					      &write_cache_variants,
 					      &update_cache_variants),
-		     SPINAND_HAS_QE_BIT,
+		     0,
 		     SPINAND_ECCINFO(&fm25s01a_ooblayout, NULL)),
 };
 

fs/afs/cell.c

@@ -229,7 +229,7 @@ error:
  * @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
@@ -239,7 +239,8 @@ error:
  */
 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;
@@ -247,12 +248,18 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net,
 	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
@@ -298,26 +305,69 @@ 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;
@@ -325,7 +375,7 @@ wait_for_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 @@ set_up_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 @@ cell_is_active:
 		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 @@ out:
 	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;
 	}

fs/efivarfs/super.c

@@ -533,6 +533,7 @@ static struct file_system_type efivarfs_type = {
 	.init_fs_context = efivarfs_init_fs_context,
 	.kill_sb = efivarfs_kill_sb,
 	.parameters = efivarfs_parameters,
+	.fs_flags = FS_POWER_FREEZE,
 };
 
 static __init int efivarfs_init(void)

fs/exfat/super.c

@@ -433,7 +433,10 @@ static int exfat_read_boot_sector(struct super_block *sb)
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
 
 	/* set block size to read super block */
-	sb_min_blocksize(sb, 512);
+	if (!sb_min_blocksize(sb, 512)) {
+		exfat_err(sb, "unable to set blocksize");
+		return -EINVAL;
+	}
 
 	/* read boot sector */
 	sbi->boot_bh = sb_bread(sb, 0);

fs/fat/inode.c

@@ -1595,8 +1595,12 @@ int fat_fill_super(struct super_block *sb, struct fs_context *fc,
 
 	setup(sb); /* flavour-specific stuff that needs options */
 
+	error = -EINVAL;
+	if (!sb_min_blocksize(sb, 512)) {
+		fat_msg(sb, KERN_ERR, "unable to set blocksize");
+		goto out_fail;
+	}
 	error = -EIO;
-	sb_min_blocksize(sb, 512);
 	bh = sb_bread(sb, 0);
 	if (bh == NULL) {
 		fat_msg(sb, KERN_ERR, "unable to read boot sector");

fs/fuse/virtio_fs.c

@@ -373,7 +373,7 @@ static int virtio_fs_add_queues_sysfs(struct virtio_fs *fs)
 
 		sprintf(buff, "%d", i);
 		fsvq->kobj = kobject_create_and_add(buff, fs->mqs_kobj);
-		if (!fs->mqs_kobj) {
+		if (!fsvq->kobj) {
 			ret = -ENOMEM;
 			goto out_del;
 		}

fs/hostfs/hostfs_kern.c

@@ -979,7 +979,7 @@ static int hostfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
 	struct hostfs_fs_info *fsi = fc->s_fs_info;
 	struct fs_parse_result result;
-	char *host_root;
+	char *host_root, *tmp_root;
 	int opt;
 
 	opt = fs_parse(fc, hostfs_param_specs, param, &result);
@@ -990,11 +990,13 @@ static int hostfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	case Opt_hostfs:
 		host_root = param->string;
 		if (!*host_root)
-			host_root = "";
-		fsi->host_root_path =
-			kasprintf(GFP_KERNEL, "%s/%s", root_ino, host_root);
-		if (fsi->host_root_path == NULL)
+			break;
+		tmp_root = kasprintf(GFP_KERNEL, "%s%s",
+				     fsi->host_root_path, host_root);
+		if (!tmp_root)
 			return -ENOMEM;
+		kfree(fsi->host_root_path);
+		fsi->host_root_path = tmp_root;
 		break;
 	}
 
@@ -1004,17 +1006,17 @@ static int hostfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 static int hostfs_parse_monolithic(struct fs_context *fc, void *data)
 {
 	struct hostfs_fs_info *fsi = fc->s_fs_info;
-	char *host_root = (char *)data;
+	char *tmp_root, *host_root = (char *)data;
 
 	/* NULL is printed as '(null)' by printf(): avoid that. */
 	if (host_root == NULL)
-		host_root = "";
+		return 0;
 
-	fsi->host_root_path =
-		kasprintf(GFP_KERNEL, "%s/%s", root_ino, host_root);
-	if (fsi->host_root_path == NULL)
+	tmp_root = kasprintf(GFP_KERNEL, "%s%s", fsi->host_root_path, host_root);
+	if (!tmp_root)
 		return -ENOMEM;
-
+	kfree(fsi->host_root_path);
+	fsi->host_root_path = tmp_root;
 	return 0;
 }
 
@@ -1049,6 +1051,11 @@ static int hostfs_init_fs_context(struct fs_context *fc)
 	if (!fsi)
 		return -ENOMEM;
 
+	fsi->host_root_path = kasprintf(GFP_KERNEL, "%s/", root_ino);
+	if (!fsi->host_root_path) {
+		kfree(fsi);
+		return -ENOMEM;
+	}
 	fc->s_fs_info = fsi;
 	fc->ops = &hostfs_context_ops;
 	return 0;

fs/inode.c

@@ -1967,6 +1967,18 @@ retry:
 }
 EXPORT_SYMBOL(iput);
 
+/**
+ *	iput_not_last	- put an inode assuming this is not the last reference
+ *	@inode: inode to put
+ */
+void iput_not_last(struct inode *inode)
+{
+	VFS_BUG_ON_INODE(atomic_read(&inode->i_count) < 2, inode);
+
+	WARN_ON(atomic_sub_return(1, &inode->i_count) == 0);
+}
+EXPORT_SYMBOL(iput_not_last);
+
 #ifdef CONFIG_BLOCK
 /**
  *	bmap	- find a block number in a file

fs/isofs/inode.c

@@ -610,6 +610,11 @@ static int isofs_fill_super(struct super_block *s, struct fs_context *fc)
 		goto out_freesbi;
 	}
 	opt->blocksize = sb_min_blocksize(s, opt->blocksize);
+	if (!opt->blocksize) {
+		printk(KERN_ERR
+		       "ISOFS: unable to set blocksize\n");
+		goto out_freesbi;
+	}
 
 	sbi->s_high_sierra = 0; /* default is iso9660 */
 	sbi->s_session = opt->session;

fs/namespace.c

@@ -132,16 +132,6 @@ EXPORT_SYMBOL_GPL(fs_kobj);
  */
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
 
-static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node)
-{
-	struct ns_common *ns;
-
-	if (!node)
-		return NULL;
-	ns = rb_entry(node, struct ns_common, ns_tree_node);
-	return container_of(ns, struct mnt_namespace, ns);
-}
-
 static void mnt_ns_release(struct mnt_namespace *ns)
 {
 	/* keep alive for {list,stat}mount() */
@@ -151,7 +141,8 @@ static void mnt_ns_release(struct mnt_namespace *ns)
 		kfree(ns);
 	}
 }
-DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (_T) mnt_ns_release(_T))
+DEFINE_FREE(mnt_ns_release, struct mnt_namespace *,
+	    if (!IS_ERR(_T)) mnt_ns_release(_T))
 
 static void mnt_ns_release_rcu(struct rcu_head *rcu)
 {
@@ -5454,11 +5445,11 @@ static int statmount_string(struct kstatmount *s, u64 flag)
 		ret = statmount_sb_source(s, seq);
 		break;
 	case STATMOUNT_MNT_UIDMAP:
-		sm->mnt_uidmap = start;
+		offp = &sm->mnt_uidmap;
 		ret = statmount_mnt_uidmap(s, seq);
 		break;
 	case STATMOUNT_MNT_GIDMAP:
-		sm->mnt_gidmap = start;
+		offp = &sm->mnt_gidmap;
 		ret = statmount_mnt_gidmap(s, seq);
 		break;
 	default:
@@ -5736,7 +5727,7 @@ static int copy_mnt_id_req(const struct mnt_id_req __user *req,
 	ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize);
 	if (ret)
 		return ret;
-	if (kreq->spare != 0)
+	if (kreq->mnt_ns_fd != 0 && kreq->mnt_ns_id)
 		return -EINVAL;
 	/* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */
 	if (kreq->mnt_id <= MNT_UNIQUE_ID_OFFSET)
@@ -5753,16 +5744,12 @@ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq
 {
 	struct mnt_namespace *mnt_ns;
 
-	if (kreq->mnt_ns_id && kreq->spare)
-		return ERR_PTR(-EINVAL);
-
-	if (kreq->mnt_ns_id)
-		return lookup_mnt_ns(kreq->mnt_ns_id);
-
-	if (kreq->spare) {
+	if (kreq->mnt_ns_id) {
+		mnt_ns = lookup_mnt_ns(kreq->mnt_ns_id);
+	} else if (kreq->mnt_ns_fd) {
 		struct ns_common *ns;
 
-		CLASS(fd, f)(kreq->spare);
+		CLASS(fd, f)(kreq->mnt_ns_fd);
 		if (fd_empty(f))
 			return ERR_PTR(-EBADF);
 
@@ -5777,6 +5764,8 @@ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq
 	} else {
 		mnt_ns = current->nsproxy->mnt_ns;
 	}
+	if (!mnt_ns)
+		return ERR_PTR(-ENOENT);
 
 	refcount_inc(&mnt_ns->passive);
 	return mnt_ns;
@@ -5801,8 +5790,8 @@ SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req,
 		return ret;
 
 	ns = grab_requested_mnt_ns(&kreq);
-	if (!ns)
-		return -ENOENT;
+	if (IS_ERR(ns))
+		return PTR_ERR(ns);
 
 	if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) &&
 	    !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
@@ -5912,8 +5901,8 @@ static void __free_klistmount_free(const struct klistmount *kls)
 static inline int prepare_klistmount(struct klistmount *kls, struct mnt_id_req *kreq,
 				     size_t nr_mnt_ids)
 {
-
 	u64 last_mnt_id = kreq->param;
+	struct mnt_namespace *ns;
 
 	/* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */
 	if (last_mnt_id != 0 && last_mnt_id <= MNT_UNIQUE_ID_OFFSET)
@@ -5927,9 +5916,10 @@ static inline int prepare_klistmount(struct klistmount *kls, struct mnt_id_req *
 	if (!kls->kmnt_ids)
 		return -ENOMEM;
 
-	kls->ns = grab_requested_mnt_ns(kreq);
-	if (!kls->ns)
-		return -ENOENT;
+	ns = grab_requested_mnt_ns(kreq);
+	if (IS_ERR(ns))
+		return PTR_ERR(ns);
+	kls->ns = ns;
 
 	kls->mnt_parent_id = kreq->mnt_id;
 	return 0;

fs/super.c

@@ -1183,11 +1183,14 @@ static inline bool get_active_super(struct super_block *sb)
 
 static const char *filesystems_freeze_ptr = "filesystems_freeze";
 
-static void filesystems_freeze_callback(struct super_block *sb, void *unused)
+static void filesystems_freeze_callback(struct super_block *sb, void *freeze_all_ptr)
 {
 	if (!sb->s_op->freeze_fs && !sb->s_op->freeze_super)
 		return;
 
+	if (freeze_all_ptr && !(sb->s_type->fs_flags & FS_POWER_FREEZE))
+		return;
+
 	if (!get_active_super(sb))
 		return;
 
@@ -1201,9 +1204,13 @@ static void filesystems_freeze_callback(struct super_block *sb, void *unused)
 	deactivate_super(sb);
 }
 
-void filesystems_freeze(void)
+void filesystems_freeze(bool freeze_all)
 {
-	__iterate_supers(filesystems_freeze_callback, NULL,
+	void *freeze_all_ptr = NULL;
+
+	if (freeze_all)
+		freeze_all_ptr = &freeze_all;
+	__iterate_supers(filesystems_freeze_callback, freeze_all_ptr,
 			 SUPER_ITER_UNLOCKED | SUPER_ITER_REVERSE);
 }
 

fs/xfs/xfs_super.c

@@ -1693,7 +1693,10 @@ xfs_fs_fill_super(
 	if (error)
 		return error;
 
-	sb_min_blocksize(sb, BBSIZE);
+	if (!sb_min_blocksize(sb, BBSIZE)) {
+		xfs_err(mp, "unable to set blocksize");
+		return -EINVAL;
+	}
 	sb->s_xattr = xfs_xattr_handlers;
 	sb->s_export_op = &xfs_export_operations;
 #ifdef CONFIG_XFS_QUOTA

include/linux/fs.h

@@ -2689,6 +2689,7 @@ struct file_system_type {
 #define FS_ALLOW_IDMAP         32      /* FS has been updated to handle vfs idmappings. */
 #define FS_MGTIME		64	/* FS uses multigrain timestamps */
 #define FS_LBS			128	/* FS supports LBS */
+#define FS_POWER_FREEZE		256	/* Always freeze on suspend/hibernate */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
@@ -2823,6 +2824,7 @@ extern int current_umask(void);
 
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
+void iput_not_last(struct inode *);
 int inode_update_timestamps(struct inode *inode, int flags);
 int generic_update_time(struct inode *, int);
 
@@ -3423,8 +3425,8 @@ static inline void remove_inode_hash(struct inode *inode)
 extern void inode_sb_list_add(struct inode *inode);
 extern void inode_add_lru(struct inode *inode);
 
-extern int sb_set_blocksize(struct super_block *, int);
-extern int sb_min_blocksize(struct super_block *, int);
+int sb_set_blocksize(struct super_block *sb, int size);
+int __must_check sb_min_blocksize(struct super_block *sb, int size);
 
 int generic_file_mmap(struct file *, struct vm_area_struct *);
 int generic_file_mmap_prepare(struct vm_area_desc *desc);
@@ -3606,7 +3608,7 @@ extern void drop_super_exclusive(struct super_block *sb);
 extern void iterate_supers(void (*f)(struct super_block *, void *), void *arg);
 extern void iterate_supers_type(struct file_system_type *,
 			        void (*)(struct super_block *, void *), void *);
-void filesystems_freeze(void);
+void filesystems_freeze(bool freeze_all);
 void filesystems_thaw(void);
 
 extern int dcache_dir_open(struct inode *, struct file *);

include/uapi/linux/mount.h

@@ -197,7 +197,7 @@ struct statmount {
  */
 struct mnt_id_req {
 	__u32 size;
-	__u32 spare;
+	__u32 mnt_ns_fd;
 	__u64 mnt_id;
 	__u64 param;
 	__u64 mnt_ns_id;

kernel/power/hibernate.c

@@ -821,8 +821,7 @@ int hibernate(void)
 		goto Restore;
 
 	ksys_sync_helper();
-	if (filesystem_freeze_enabled)
-		filesystems_freeze();
+	filesystems_freeze(filesystem_freeze_enabled);
 
 	error = freeze_processes();
 	if (error)
@@ -928,8 +927,7 @@ int hibernate_quiet_exec(int (*func)(void *data), void *data)
 	if (error)
 		goto restore;
 
-	if (filesystem_freeze_enabled)
-		filesystems_freeze();
+	filesystems_freeze(filesystem_freeze_enabled);
 
 	error = freeze_processes();
 	if (error)
@@ -1079,8 +1077,7 @@ static int software_resume(void)
 	if (error)
 		goto Restore;
 
-	if (filesystem_freeze_enabled)
-		filesystems_freeze();
+	filesystems_freeze(filesystem_freeze_enabled);
 
 	pm_pr_dbg("Preparing processes for hibernation restore.\n");
 	error = freeze_processes();

kernel/power/suspend.c

@@ -375,8 +375,7 @@ static int suspend_prepare(suspend_state_t state)
 	if (error)
 		goto Restore;
 
-	if (filesystem_freeze_enabled)
-		filesystems_freeze();
+	filesystems_freeze(filesystem_freeze_enabled);
 	trace_suspend_resume(TPS("freeze_processes"), 0, true);
 	error = suspend_freeze_processes();
 	trace_suspend_resume(TPS("freeze_processes"), 0, false);

kernel/sched/ext.c

@@ -25,7 +25,7 @@ static struct scx_sched __rcu *scx_root;
  * guarantee system safety. Maintain a dedicated task list which contains every
  * task between its fork and eventual free.
  */
-static DEFINE_SPINLOCK(scx_tasks_lock);
+static DEFINE_RAW_SPINLOCK(scx_tasks_lock);
 static LIST_HEAD(scx_tasks);
 
 /* ops enable/disable */
@@ -476,7 +476,7 @@ static void scx_task_iter_start(struct scx_task_iter *iter)
 	BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS &
 		     ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1));
 
-	spin_lock_irq(&scx_tasks_lock);
+	raw_spin_lock_irq(&scx_tasks_lock);
 
 	iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR };
 	list_add(&iter->cursor.tasks_node, &scx_tasks);
@@ -507,14 +507,14 @@ static void scx_task_iter_unlock(struct scx_task_iter *iter)
 	__scx_task_iter_rq_unlock(iter);
 	if (iter->list_locked) {
 		iter->list_locked = false;
-		spin_unlock_irq(&scx_tasks_lock);
+		raw_spin_unlock_irq(&scx_tasks_lock);
 	}
 }
 
 static void __scx_task_iter_maybe_relock(struct scx_task_iter *iter)
 {
 	if (!iter->list_locked) {
-		spin_lock_irq(&scx_tasks_lock);
+		raw_spin_lock_irq(&scx_tasks_lock);
 		iter->list_locked = true;
 	}
 }
@@ -2940,9 +2940,9 @@ void scx_post_fork(struct task_struct *p)
 		}
 	}
 
-	spin_lock_irq(&scx_tasks_lock);
+	raw_spin_lock_irq(&scx_tasks_lock);
 	list_add_tail(&p->scx.tasks_node, &scx_tasks);
-	spin_unlock_irq(&scx_tasks_lock);
+	raw_spin_unlock_irq(&scx_tasks_lock);
 
 	percpu_up_read(&scx_fork_rwsem);
 }
@@ -2966,9 +2966,9 @@ void sched_ext_free(struct task_struct *p)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&scx_tasks_lock, flags);
+	raw_spin_lock_irqsave(&scx_tasks_lock, flags);
 	list_del_init(&p->scx.tasks_node);
-	spin_unlock_irqrestore(&scx_tasks_lock, flags);
+	raw_spin_unlock_irqrestore(&scx_tasks_lock, flags);
 
 	/*
 	 * @p is off scx_tasks and wholly ours. scx_enable()'s READY -> ENABLED
@@ -4276,7 +4276,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 		size_t avail, used;
 		bool idle;
 
-		rq_lock(rq, &rf);
+		rq_lock_irqsave(rq, &rf);
 
 		idle = list_empty(&rq->scx.runnable_list) &&
 			rq->curr->sched_class == &idle_sched_class;
@@ -4345,7 +4345,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 		list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node)
 			scx_dump_task(&s, &dctx, p, ' ');
 	next:
-		rq_unlock(rq, &rf);
+		rq_unlock_irqrestore(rq, &rf);
 	}
 
 	dump_newline(&s);
@@ -5321,8 +5321,8 @@ void __init init_sched_ext_class(void)
 		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_kick_if_idle, GFP_KERNEL, n));
 		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_preempt, GFP_KERNEL, n));
 		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_wait, GFP_KERNEL, n));
-		init_irq_work(&rq->scx.deferred_irq_work, deferred_irq_workfn);
-		init_irq_work(&rq->scx.kick_cpus_irq_work, kick_cpus_irq_workfn);
+		rq->scx.deferred_irq_work = IRQ_WORK_INIT_HARD(deferred_irq_workfn);
+		rq->scx.kick_cpus_irq_work = IRQ_WORK_INIT_HARD(kick_cpus_irq_workfn);
 
 		if (cpu_online(cpu))
 			cpu_rq(cpu)->scx.flags |= SCX_RQ_ONLINE;
@@ -6401,7 +6401,7 @@ __bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf)
 
 	guard(rcu)();
 
-	sch = rcu_dereference(sch);
+	sch = rcu_dereference(scx_root);
 	if (unlikely(!sch))
 		return;
 

mm/shmem.c

@@ -131,8 +131,7 @@ struct shmem_options {
 #define SHMEM_SEEN_INODES 2
 #define SHMEM_SEEN_HUGE 4
 #define SHMEM_SEEN_INUMS 8
-#define SHMEM_SEEN_NOSWAP 16
-#define SHMEM_SEEN_QUOTA 32
+#define SHMEM_SEEN_QUOTA 16
 };
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -4680,7 +4679,6 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param)
 				       "Turning off swap in unprivileged tmpfs mounts unsupported");
 		}
 		ctx->noswap = true;
-		ctx->seen |= SHMEM_SEEN_NOSWAP;
 		break;
 	case Opt_quota:
 		if (fc->user_ns != &init_user_ns)
@@ -4830,14 +4828,15 @@ static int shmem_reconfigure(struct fs_context *fc)
 		err = "Current inum too high to switch to 32-bit inums";
 		goto out;
 	}
-	if ((ctx->seen & SHMEM_SEEN_NOSWAP) && ctx->noswap && !sbinfo->noswap) {
+
+	/*
+	 * "noswap" doesn't use fsparam_flag_no, i.e. there's no "swap"
+	 * counterpart for (re-)enabling swap.
+	 */
+	if (ctx->noswap && !sbinfo->noswap) {
 		err = "Cannot disable swap on remount";
 		goto out;
 	}
-	if (!(ctx->seen & SHMEM_SEEN_NOSWAP) && !ctx->noswap && sbinfo->noswap) {
-		err = "Cannot enable swap on remount if it was disabled on first mount";
-		goto out;
-	}
 
 	if (ctx->seen & SHMEM_SEEN_QUOTA &&
 	    !sb_any_quota_loaded(fc->root->d_sb)) {

security/landlock/fs.c

@@ -1335,11 +1335,10 @@ static void hook_sb_delete(struct super_block *const sb)
 			 * At this point, we own the ihold() reference that was
 			 * originally set up by get_inode_object() and the
 			 * __iget() reference that we just set in this loop
-			 * walk.  Therefore the following call to iput() will
-			 * not sleep nor drop the inode because there is now at
-			 * least two references to it.
+			 * walk.  Therefore there are at least two references
+			 * on the inode.
 			 */
-			iput(inode);
+			iput_not_last(inode);
 		} else {
 			spin_unlock(&object->lock);
 			rcu_read_unlock();