Merging upstream version 6.9.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

21 files changed, 142 insertions, 47 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 1a66be33bb..60066822b5 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1924,8 +1924,17 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 next:
 		if (ret) {
 			/* Refcount held by the reclaim_bgs list after splice. */
-			btrfs_get_block_group(bg);
-			list_add_tail(&bg->bg_list, &retry_list);
+			spin_lock(&fs_info->unused_bgs_lock);
+			/*
+			 * This block group might be added to the unused list
+			 * during the above process. Move it back to the
+			 * reclaim list otherwise.
+			 */
+			if (list_empty(&bg->bg_list)) {
+				btrfs_get_block_group(bg);
+				list_add_tail(&bg->bg_list, &retry_list);
+			}
+			spin_unlock(&fs_info->unused_bgs_lock);
 		}
 		btrfs_put_block_group(bg);
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 41173701f1..1e02062074 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3526,7 +3526,7 @@ err:
 	for (int i = 0; i < num_folios; i++) {
 		if (eb->folios[i]) {
 			detach_extent_buffer_folio(eb, eb->folios[i]);
-			__folio_put(eb->folios[i]);
+			folio_put(eb->folios[i]);
 		}
 	}
 	__free_extent_buffer(eb);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 1167899a16..4caa078d97 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3065,8 +3065,6 @@ int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info,
 			       struct btrfs_qgroup_inherit *inherit,
 			       size_t size)
 {
-	if (!btrfs_qgroup_enabled(fs_info))
-		return 0;
 	if (inherit->flags & ~BTRFS_QGROUP_INHERIT_FLAGS_SUPP)
 		return -EOPNOTSUPP;
 	if (size < sizeof(*inherit) || size > PAGE_SIZE)
@@ -3091,6 +3089,14 @@ int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info,
 		return -EINVAL;
 
 	/*
+	 * Skip the inherit source qgroups check if qgroup is not enabled.
+	 * Qgroup can still be later enabled causing problems, but in that case
+	 * btrfs_qgroup_inherit() would just ignore those invalid ones.
+	 */
+	if (!btrfs_qgroup_enabled(fs_info))
+		return 0;
+
+	/*
 	 * Now check all the remaining qgroups, they should all:
 	 *
 	 * - Exist
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 4b22cfe9a9..afd6932f5e 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2100,7 +2100,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	const u64 logical_end = logical_start + logical_length;
 	u64 cur_logical = logical_start;
-	int ret;
+	int ret = 0;
 
 	/* The range must be inside the bg */
 	ASSERT(logical_start >= bg->start && logical_end <= bg->start + bg->length);
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index d620323d08..ae8c564425 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -373,11 +373,18 @@ static u64 calc_available_free_space(struct btrfs_fs_info *fs_info,
 	 * "optimal" chunk size based on the fs size.  However when we actually
 	 * allocate the chunk we will strip this down further, making it no more
 	 * than 10% of the disk or 1G, whichever is smaller.
+	 *
+	 * On the zoned mode, we need to use zone_size (=
+	 * data_sinfo->chunk_size) as it is.
 	 */
 	data_sinfo = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_DATA);
-	data_chunk_size = min(data_sinfo->chunk_size,
-			      mult_perc(fs_info->fs_devices->total_rw_bytes, 10));
-	data_chunk_size = min_t(u64, data_chunk_size, SZ_1G);
+	if (!btrfs_is_zoned(fs_info)) {
+		data_chunk_size = min(data_sinfo->chunk_size,
+				      mult_perc(fs_info->fs_devices->total_rw_bytes, 10));
+		data_chunk_size = min_t(u64, data_chunk_size, SZ_1G);
+	} else {
+		data_chunk_size = data_sinfo->chunk_size;
+	}
 
 	/*
 	 * Since data allocations immediately use block groups as part of the
@@ -405,6 +412,17 @@ static u64 calc_available_free_space(struct btrfs_fs_info *fs_info,
 		avail >>= 3;
 	else
 		avail >>= 1;
+
+	/*
+	 * On the zoned mode, we always allocate one zone as one chunk.
+	 * Returning non-zone size alingned bytes here will result in
+	 * less pressure for the async metadata reclaim process, and it
+	 * will over-commit too much leading to ENOSPC. Align down to the
+	 * zone size to avoid that.
+	 */
+	if (btrfs_is_zoned(fs_info))
+		avail = ALIGN_DOWN(avail, fs_info->zone_size);
+
 	return avail;
 }
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 07b3675ea1..6c60e43ec8 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -72,7 +72,7 @@ enum {
 
 struct f2fs_fault_info {
 	atomic_t inject_ops;
-	unsigned int inject_rate;
+	int inject_rate;
 	unsigned int inject_type;
 };
 
@@ -4597,10 +4597,14 @@ static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
 }
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
-							unsigned int type);
+extern int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
+							unsigned long type);
 #else
-#define f2fs_build_fault_attr(sbi, rate, type)		do { } while (0)
+static inline int f2fs_build_fault_attr(struct f2fs_sb_info *sbi,
+					unsigned long rate, unsigned long type)
+{
+	return 0;
+}
 #endif
 
 static inline bool is_journalled_quota(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 2f75a7dfc3..0c3ebe4d90 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -66,21 +66,31 @@ const char *f2fs_fault_name[FAULT_MAX] = {
 	[FAULT_NO_SEGMENT]		= "no free segment",
 };
 
-void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
-							unsigned int type)
+int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
+							unsigned long type)
 {
 	struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;
 
 	if (rate) {
+		if (rate > INT_MAX)
+			return -EINVAL;
 		atomic_set(&ffi->inject_ops, 0);
-		ffi->inject_rate = rate;
+		ffi->inject_rate = (int)rate;
 	}
 
-	if (type)
-		ffi->inject_type = type;
+	if (type) {
+		if (type >= BIT(FAULT_MAX))
+			return -EINVAL;
+		ffi->inject_type = (unsigned int)type;
+	}
 
 	if (!rate && !type)
 		memset(ffi, 0, sizeof(struct f2fs_fault_info));
+	else
+		f2fs_info(sbi,
+			"build fault injection attr: rate: %lu, type: 0x%lx",
+								rate, type);
+	return 0;
 }
 #endif
 
@@ -886,14 +896,17 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 		case Opt_fault_injection:
 			if (args->from && match_int(args, &arg))
 				return -EINVAL;
-			f2fs_build_fault_attr(sbi, arg, F2FS_ALL_FAULT_TYPE);
+			if (f2fs_build_fault_attr(sbi, arg,
+					F2FS_ALL_FAULT_TYPE))
+				return -EINVAL;
 			set_opt(sbi, FAULT_INJECTION);
 			break;
 
 		case Opt_fault_type:
 			if (args->from && match_int(args, &arg))
 				return -EINVAL;
-			f2fs_build_fault_attr(sbi, 0, arg);
+			if (f2fs_build_fault_attr(sbi, 0, arg))
+				return -EINVAL;
 			set_opt(sbi, FAULT_INJECTION);
 			break;
 #else
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index a568ce96cf..7aa3844e7a 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -484,10 +484,16 @@ out:
 	if (ret < 0)
 		return ret;
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (a->struct_type == FAULT_INFO_TYPE && t >= BIT(FAULT_MAX))
-		return -EINVAL;
-	if (a->struct_type == FAULT_INFO_RATE && t >= UINT_MAX)
-		return -EINVAL;
+	if (a->struct_type == FAULT_INFO_TYPE) {
+		if (f2fs_build_fault_attr(sbi, 0, t))
+			return -EINVAL;
+		return count;
+	}
+	if (a->struct_type == FAULT_INFO_RATE) {
+		if (f2fs_build_fault_attr(sbi, t, 0))
+			return -EINVAL;
+		return count;
+	}
 #endif
 	if (a->struct_type == RESERVED_BLOCKS) {
 		spin_lock(&sbi->stat_lock);
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index aede1be4dc..4545f885c4 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -58,6 +58,7 @@ static void jffs2_i_init_once(void *foo)
 	struct jffs2_inode_info *f = foo;
 
 	mutex_init(&f->sem);
+	f->target = NULL;
 	inode_init_once(&f->vfs_inode);
 }
 
diff --git a/fs/locks.c b/fs/locks.c
index 90c8746874..c360d1992d 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2448,8 +2448,9 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 	error = do_lock_file_wait(filp, cmd, file_lock);
 
 	/*
-	 * Attempt to detect a close/fcntl race and recover by releasing the
-	 * lock that was just acquired. There is no need to do that when we're
+	 * Detect close/fcntl races and recover by zapping all POSIX locks
+	 * associated with this file and our files_struct, just like on
+	 * filp_flush(). There is no need to do that when we're
 	 * unlocking though, or for OFD locks.
 	 */
 	if (!error && file_lock->c.flc_type != F_UNLCK &&
@@ -2464,9 +2465,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 		f = files_lookup_fd_locked(files, fd);
 		spin_unlock(&files->file_lock);
 		if (f != filp) {
-			file_lock->c.flc_type = F_UNLCK;
-			error = do_lock_file_wait(filp, cmd, file_lock);
-			WARN_ON_ONCE(error);
+			locks_remove_posix(filp, files);
 			error = -EBADF;
 		}
 	}
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 89caef7513..ba50388ee4 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -377,11 +377,12 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr,
  * @target: offset number of an entry in the group (start point)
  * @bsize: size in bits
  * @lock: spin lock protecting @bitmap
+ * @wrap: whether to wrap around
  */
 static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
 					    unsigned long target,
 					    unsigned int bsize,
-					    spinlock_t *lock)
+					    spinlock_t *lock, bool wrap)
 {
 	int pos, end = bsize;
 
@@ -397,6 +398,8 @@ static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
 
 		end = target;
 	}
+	if (!wrap)
+		return -ENOSPC;
 
 	/* wrap around */
 	for (pos = 0; pos < end; pos++) {
@@ -495,9 +498,10 @@ int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp)
  * nilfs_palloc_prepare_alloc_entry - prepare to allocate a persistent object
  * @inode: inode of metadata file using this allocator
  * @req: nilfs_palloc_req structure exchanged for the allocation
+ * @wrap: whether to wrap around
  */
 int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
-				     struct nilfs_palloc_req *req)
+				     struct nilfs_palloc_req *req, bool wrap)
 {
 	struct buffer_head *desc_bh, *bitmap_bh;
 	struct nilfs_palloc_group_desc *desc;
@@ -516,7 +520,7 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 	entries_per_group = nilfs_palloc_entries_per_group(inode);
 
 	for (i = 0; i < ngroups; i += n) {
-		if (group >= ngroups) {
+		if (group >= ngroups && wrap) {
 			/* wrap around */
 			group = 0;
 			maxgroup = nilfs_palloc_group(inode, req->pr_entry_nr,
@@ -550,7 +554,14 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 			bitmap_kaddr = kmap_local_page(bitmap_bh->b_page);
 			bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
 			pos = nilfs_palloc_find_available_slot(
-				bitmap, group_offset, entries_per_group, lock);
+				bitmap, group_offset, entries_per_group, lock,
+				wrap);
+			/*
+			 * Since the search for a free slot in the second and
+			 * subsequent bitmap blocks always starts from the
+			 * beginning, the wrap flag only has an effect on the
+			 * first search.
+			 */
 			kunmap_local(bitmap_kaddr);
 			if (pos >= 0)
 				goto found;
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index b667e869ac..d825a9faca 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -50,8 +50,8 @@ struct nilfs_palloc_req {
 	struct buffer_head *pr_entry_bh;
 };
 
-int nilfs_palloc_prepare_alloc_entry(struct inode *,
-				     struct nilfs_palloc_req *);
+int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
+				     struct nilfs_palloc_req *req, bool wrap);
 void nilfs_palloc_commit_alloc_entry(struct inode *,
 				     struct nilfs_palloc_req *);
 void nilfs_palloc_abort_alloc_entry(struct inode *, struct nilfs_palloc_req *);
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 180fc8d362..fc1caf63a4 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -75,7 +75,7 @@ int nilfs_dat_prepare_alloc(struct inode *dat, struct nilfs_palloc_req *req)
 {
 	int ret;
 
-	ret = nilfs_palloc_prepare_alloc_entry(dat, req);
+	ret = nilfs_palloc_prepare_alloc_entry(dat, req, true);
 	if (ret < 0)
 		return ret;
 
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 35e6c55a0d..d748d9dce7 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -135,6 +135,9 @@ static bool nilfs_check_folio(struct folio *folio, char *kaddr)
 			goto Enamelen;
 		if (((offs + rec_len - 1) ^ offs) & ~(chunk_size-1))
 			goto Espan;
+		if (unlikely(p->inode &&
+			     NILFS_PRIVATE_INODE(le64_to_cpu(p->inode))))
+			goto Einumber;
 	}
 	if (offs != limit)
 		goto Eend;
@@ -160,6 +163,9 @@ Enamelen:
 	goto bad_entry;
 Espan:
 	error = "directory entry across blocks";
+	goto bad_entry;
+Einumber:
+	error = "disallowed inode number";
 bad_entry:
 	nilfs_error(sb,
 		    "bad entry in directory #%lu: %s - offset=%lu, inode=%lu, rec_len=%zd, name_len=%d",
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 612e609158..1e86b9303b 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -56,13 +56,10 @@ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino,
 	struct nilfs_palloc_req req;
 	int ret;
 
-	req.pr_entry_nr = 0;  /*
-			       * 0 says find free inode from beginning
-			       * of a group. dull code!!
-			       */
+	req.pr_entry_nr = NILFS_FIRST_INO(ifile->i_sb);
 	req.pr_entry_bh = NULL;
 
-	ret = nilfs_palloc_prepare_alloc_entry(ifile, &req);
+	ret = nilfs_palloc_prepare_alloc_entry(ifile, &req, false);
 	if (!ret) {
 		ret = nilfs_palloc_get_entry_block(ifile, req.pr_entry_nr, 1,
 						   &req.pr_entry_bh);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 2e29b98ba8..fe982c3e08 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -116,9 +116,15 @@ enum {
 #define NILFS_FIRST_INO(sb) (((struct the_nilfs *)sb->s_fs_info)->ns_first_ino)
 
 #define NILFS_MDT_INODE(sb, ino) \
-	((ino) < NILFS_FIRST_INO(sb) && (NILFS_MDT_INO_BITS & BIT(ino)))
+	((ino) < NILFS_USER_INO && (NILFS_MDT_INO_BITS & BIT(ino)))
 #define NILFS_VALID_INODE(sb, ino) \
-	((ino) >= NILFS_FIRST_INO(sb) || (NILFS_SYS_INO_BITS & BIT(ino)))
+	((ino) >= NILFS_FIRST_INO(sb) ||				\
+	 ((ino) < NILFS_USER_INO && (NILFS_SYS_INO_BITS & BIT(ino))))
+
+#define NILFS_PRIVATE_INODE(ino) ({					\
+	ino_t __ino = (ino);						\
+	((__ino) < NILFS_USER_INO && (__ino) != NILFS_ROOT_INO &&	\
+	 (__ino) != NILFS_SKETCH_INO); })
 
 /**
  * struct nilfs_transaction_info: context information for synchronization
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 2ae2c1bbf6..5aac4f9118 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -452,6 +452,12 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 	}
 
 	nilfs->ns_first_ino = le32_to_cpu(sbp->s_first_ino);
+	if (nilfs->ns_first_ino < NILFS_USER_INO) {
+		nilfs_err(nilfs->ns_sb,
+			  "too small lower limit for non-reserved inode numbers: %u",
+			  nilfs->ns_first_ino);
+		return -EINVAL;
+	}
 
 	nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment);
 	if (nilfs->ns_blocks_per_segment < NILFS_SEG_MIN_BLOCKS) {
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index cd4ae1b8ae..17fee562ee 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -182,7 +182,7 @@ struct the_nilfs {
 	unsigned long		ns_nrsvsegs;
 	unsigned long		ns_first_data_block;
 	int			ns_inode_size;
-	int			ns_first_ino;
+	unsigned int		ns_first_ino;
 	u32			ns_crc_seed;
 
 	/* /sys/fs/<nilfs>/<device> */
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 53e7d1fa03..73785dece7 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -219,8 +219,11 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer,
 		if (!ea->name_len)
 			break;
 
-		if (ea->name_len > ea_size)
+		if (ea->name_len > ea_size) {
+			ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR);
+			err = -EINVAL; /* corrupted fs */
 			break;
+		}
 
 		if (buffer) {
 			/* Check if we can use field ea->name */
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
index 34849b4a32..9077656737 100644
--- a/fs/orangefs/super.c
+++ b/fs/orangefs/super.c
@@ -201,7 +201,8 @@ static int orangefs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		     (long)new_op->downcall.resp.statfs.files_avail);
 
 	buf->f_type = sb->s_magic;
-	memcpy(&buf->f_fsid, &ORANGEFS_SB(sb)->fs_id, sizeof(buf->f_fsid));
+	buf->f_fsid.val[0] = ORANGEFS_SB(sb)->fs_id;
+	buf->f_fsid.val[1] = ORANGEFS_SB(sb)->id;
 	buf->f_bsize = new_op->downcall.resp.statfs.block_size;
 	buf->f_namelen = ORANGEFS_NAME_MAX;
 
diff --git a/fs/super.c b/fs/super.c
index 69ce6c6009..4e52aba2fb 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1501,8 +1501,17 @@ static int fs_bdev_thaw(struct block_device *bdev)
 
 	lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
 
+	/*
+	 * The block device may have been frozen before it was claimed by a
+	 * filesystem. Concurrently another process might try to mount that
+	 * frozen block device and has temporarily claimed the block device for
+	 * that purpose causing a concurrent fs_bdev_thaw() to end up here. The
+	 * mounter is already about to abort mounting because they still saw an
+	 * elevanted bdev->bd_fsfreeze_count so get_bdev_super() will return
+	 * NULL in that case.
+	 */
 	sb = get_bdev_super(bdev);
-	if (WARN_ON_ONCE(!sb))
+	if (!sb)
 		return -EINVAL;
 
 	if (sb->s_op->thaw_super)