1 files changed, 179 insertions, 4 deletions

diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 4309979eeb36..64cc2a9c38c8 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -44,6 +44,19 @@ static inline int zonefs_zone_mgmt(struct inode *inode,
 	return 0;
 }
 
+static inline void zonefs_i_size_write(struct inode *inode, loff_t isize)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+	i_size_write(inode, isize);
+	/*
+	 * A full zone is no longer open/active and does not need
+	 * explicit closing.
+	 */
+	if (isize >= zi->i_max_size)
+		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
+}
+
 static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 			      unsigned int flags, struct iomap *iomap,
 			      struct iomap *srcmap)
@@ -322,6 +335,17 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	}
 
 	/*
+	 * If the filesystem is mounted with the explicit-open mount option, we
+	 * need to clear the ZONEFS_ZONE_OPEN flag if the zone transitioned to
+	 * the read-only or offline condition, to avoid attempting an explicit
+	 * close of the zone when the inode file is closed.
+	 */
+	if ((sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) &&
+	    (zone->cond == BLK_ZONE_COND_OFFLINE ||
+	     zone->cond == BLK_ZONE_COND_READONLY))
+		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
+
+	/*
 	 * If error=remount-ro was specified, any error result in remounting
 	 * the volume as read-only.
 	 */
@@ -335,7 +359,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 * invalid data.
 	 */
 	zonefs_update_stats(inode, data_size);
-	i_size_write(inode, data_size);
+	zonefs_i_size_write(inode, data_size);
 	zi->i_wpoffset = data_size;
 
 	return 0;
@@ -426,6 +450,25 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize)
 	if (ret)
 		goto unlock;
 
+	/*
+	 * If the mount option ZONEFS_MNTOPT_EXPLICIT_OPEN is set,
+	 * take care of open zones.
+	 */
+	if (zi->i_flags & ZONEFS_ZONE_OPEN) {
+		/*
+		 * Truncating a zone to EMPTY or FULL is the equivalent of
+		 * closing the zone. For a truncation to 0, we need to
+		 * re-open the zone to ensure new writes can be processed.
+		 * For a truncation to the maximum file size, the zone is
+		 * closed and writes cannot be accepted anymore, so clear
+		 * the open flag.
+		 */
+		if (!isize)
+			ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
+		else
+			zi->i_flags &= ~ZONEFS_ZONE_OPEN;
+	}
+
 	zonefs_update_stats(inode, isize);
 	truncate_setsize(inode, isize);
 	zi->i_wpoffset = isize;
@@ -604,7 +647,7 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
 		mutex_lock(&zi->i_truncate_mutex);
 		if (i_size_read(inode) < iocb->ki_pos + size) {
 			zonefs_update_stats(inode, iocb->ki_pos + size);
-			i_size_write(inode, iocb->ki_pos + size);
+			zonefs_i_size_write(inode, iocb->ki_pos + size);
 		}
 		mutex_unlock(&zi->i_truncate_mutex);
 	}
@@ -885,8 +928,128 @@ inode_unlock:
 	return ret;
 }
 
+static inline bool zonefs_file_use_exp_open(struct inode *inode, struct file *file)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
+
+	if (!(sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN))
+		return false;
+
+	if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+		return false;
+
+	if (!(file->f_mode & FMODE_WRITE))
+		return false;
+
+	return true;
+}
+
+static int zonefs_open_zone(struct inode *inode)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
+	int ret = 0;
+
+	mutex_lock(&zi->i_truncate_mutex);
+
+	zi->i_wr_refcnt++;
+	if (zi->i_wr_refcnt == 1) {
+
+		if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) {
+			atomic_dec(&sbi->s_open_zones);
+			ret = -EBUSY;
+			goto unlock;
+		}
+
+		if (i_size_read(inode) < zi->i_max_size) {
+			ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
+			if (ret) {
+				zi->i_wr_refcnt--;
+				atomic_dec(&sbi->s_open_zones);
+				goto unlock;
+			}
+			zi->i_flags |= ZONEFS_ZONE_OPEN;
+		}
+	}
+
+unlock:
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	return ret;
+}
+
+static int zonefs_file_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = generic_file_open(inode, file);
+	if (ret)
+		return ret;
+
+	if (zonefs_file_use_exp_open(inode, file))
+		return zonefs_open_zone(inode);
+
+	return 0;
+}
+
+static void zonefs_close_zone(struct inode *inode)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	int ret = 0;
+
+	mutex_lock(&zi->i_truncate_mutex);
+	zi->i_wr_refcnt--;
+	if (!zi->i_wr_refcnt) {
+		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
+		struct super_block *sb = inode->i_sb;
+
+		/*
+		 * If the file zone is full, it is not open anymore and we only
+		 * need to decrement the open count.
+		 */
+		if (!(zi->i_flags & ZONEFS_ZONE_OPEN))
+			goto dec;
+
+		ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
+		if (ret) {
+			__zonefs_io_error(inode, false);
+			/*
+			 * Leaving zones explicitly open may lead to a state
+			 * where most zones cannot be written (zone resources
+			 * exhausted). So take preventive action by remounting
+			 * read-only.
+			 */
+			if (zi->i_flags & ZONEFS_ZONE_OPEN &&
+			    !(sb->s_flags & SB_RDONLY)) {
+				zonefs_warn(sb, "closing zone failed, remounting filesystem read-only\n");
+				sb->s_flags |= SB_RDONLY;
+			}
+		}
+		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
+dec:
+		atomic_dec(&sbi->s_open_zones);
+	}
+	mutex_unlock(&zi->i_truncate_mutex);
+}
+
+static int zonefs_file_release(struct inode *inode, struct file *file)
+{
+	/*
+	 * If we explicitly open a zone we must close it again as well, but the
+	 * zone management operation can fail (either due to an IO error or as
+	 * the zone has gone offline or read-only). Make sure we don't fail the
+	 * close(2) for user-space.
+	 */
+	if (zonefs_file_use_exp_open(inode, file))
+		zonefs_close_zone(inode);
+
+	return 0;
+}
+
 static const struct file_operations zonefs_file_operations = {
-	.open		= generic_file_open,
+	.open		= zonefs_file_open,
+	.release	= zonefs_file_release,
 	.fsync		= zonefs_file_fsync,
 	.mmap		= zonefs_file_mmap,
 	.llseek		= zonefs_file_llseek,
@@ -910,6 +1073,7 @@ static struct inode *zonefs_alloc_inode(struct super_block *sb)
 	inode_init_once(&zi->i_vnode);
 	mutex_init(&zi->i_truncate_mutex);
 	init_rwsem(&zi->i_mmap_sem);
+	zi->i_wr_refcnt = 0;
 
 	return &zi->i_vnode;
 }
@@ -960,7 +1124,7 @@ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 enum {
 	Opt_errors_ro, Opt_errors_zro, Opt_errors_zol, Opt_errors_repair,
-	Opt_err,
+	Opt_explicit_open, Opt_err,
 };
 
 static const match_table_t tokens = {
@@ -968,6 +1132,7 @@ static const match_table_t tokens = {
 	{ Opt_errors_zro,	"errors=zone-ro"},
 	{ Opt_errors_zol,	"errors=zone-offline"},
 	{ Opt_errors_repair,	"errors=repair"},
+	{ Opt_explicit_open,	"explicit-open" },
 	{ Opt_err,		NULL}
 };
 
@@ -1004,6 +1169,9 @@ static int zonefs_parse_options(struct super_block *sb, char *options)
 			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
 			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_REPAIR;
 			break;
+		case Opt_explicit_open:
+			sbi->s_mount_opts |= ZONEFS_MNTOPT_EXPLICIT_OPEN;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -1423,6 +1591,13 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_gid = GLOBAL_ROOT_GID;
 	sbi->s_perm = 0640;
 	sbi->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO;
+	sbi->s_max_open_zones = bdev_max_open_zones(sb->s_bdev);
+	atomic_set(&sbi->s_open_zones, 0);
+	if (!sbi->s_max_open_zones &&
+	    sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
+		zonefs_info(sb, "No open zones limit. Ignoring explicit_open mount option\n");
+		sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
+	}
 
 	ret = zonefs_read_super(sb);
 	if (ret)