zonefs: open/close zone on file open/close

NVMe Zoned Namespace introduced the concept of active zones, which are
zones in the implicit open, explicit open or closed condition. Drives may
have a limit on the number of zones that can be simultaneously active.
This potential limitation translate into a risk for applications to see
write IO errors due to this limit if the zone of a file being written to is
not already active when a write request is issued.

To avoid these potential errors, the zone of a file can explicitly be made
active using an open zone command when the file is open for the first
time. If the zone open command succeeds, the application is then
guaranteed that write requests can be processed. This indirect management
of active zones relies on the maximum number of open zones of a drive,
which is always lower or equal to the maximum number of active zones.

On the first open of a sequential zone file, send a REQ_OP_ZONE_OPEN
command to the block device. Conversely, on the last release of a zone
file and send a REQ_OP_ZONE_CLOSE to the device if the zone is not full or
empty.

As truncating a zone file to 0 or max can deactivate a zone as well, we
need to serialize against truncates and also be careful not to close a
zone as the file may still be open for writing, e.g. the user called
ftruncate(). If the zone file is not open and a process does a truncate(),
then no close operation is needed.

Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>

1 files changed, 10 insertions, 0 deletions

diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h
index 55b39970acb2..51141907097c 100644
--- a/fs/zonefs/zonefs.h
+++ b/fs/zonefs/zonefs.h
@@ -38,6 +38,8 @@ static inline enum zonefs_ztype zonefs_zone_type(struct blk_zone *zone)
 	return ZONEFS_ZTYPE_SEQ;
 }
 
+#define ZONEFS_ZONE_OPEN	(1 << 0)
+
 /*
  * In-memory inode data.
  */
@@ -74,6 +76,10 @@ struct zonefs_inode_info {
 	 */
 	struct mutex		i_truncate_mutex;
 	struct rw_semaphore	i_mmap_sem;
+
+	/* guarded by i_truncate_mutex */
+	unsigned int		i_wr_refcnt;
+	unsigned int		i_flags;
 };
 
 static inline struct zonefs_inode_info *ZONEFS_I(struct inode *inode)
@@ -154,6 +160,7 @@ enum zonefs_features {
 #define ZONEFS_MNTOPT_ERRORS_MASK	\
 	(ZONEFS_MNTOPT_ERRORS_RO | ZONEFS_MNTOPT_ERRORS_ZRO | \
 	 ZONEFS_MNTOPT_ERRORS_ZOL | ZONEFS_MNTOPT_ERRORS_REPAIR)
+#define ZONEFS_MNTOPT_EXPLICIT_OPEN	(1 << 4) /* Explicit open/close of zones on open/close */
 
 /*
  * In-memory Super block information.
@@ -175,6 +182,9 @@ struct zonefs_sb_info {
 
 	loff_t			s_blocks;
 	loff_t			s_used_blocks;
+
+	unsigned int		s_max_open_zones;
+	atomic_t		s_open_zones;
 };
 
 static inline struct zonefs_sb_info *ZONEFS_SB(struct super_block *sb)