return sect >> ilog2(dev->zone_size_sects);
}
+static inline void null_lock_zone_res(struct nullb_device *dev)
+{
+ if (dev->need_zone_res_mgmt)
+ spin_lock_irq(&dev->zone_res_lock);
+}
+
+static inline void null_unlock_zone_res(struct nullb_device *dev)
+{
+ if (dev->need_zone_res_mgmt)
+ spin_unlock_irq(&dev->zone_res_lock);
+}
+
+static inline void null_init_zone_lock(struct nullb_device *dev,
+ struct nullb_zone *zone)
+{
+ if (!dev->memory_backed)
+ spin_lock_init(&zone->spinlock);
+ else
+ mutex_init(&zone->mutex);
+}
+
+static inline void null_lock_zone(struct nullb_device *dev,
+ struct nullb_zone *zone)
+{
+ if (!dev->memory_backed)
+ spin_lock_irq(&zone->spinlock);
+ else
+ mutex_lock(&zone->mutex);
+}
+
+static inline void null_unlock_zone(struct nullb_device *dev,
+ struct nullb_zone *zone)
+{
+ if (!dev->memory_backed)
+ spin_unlock_irq(&zone->spinlock);
+ else
+ mutex_unlock(&zone->mutex);
+}
+
int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
{
sector_t dev_capacity_sects, zone_capacity_sects;
+ struct nullb_zone *zone;
sector_t sector = 0;
unsigned int i;
if (dev_capacity_sects & (dev->zone_size_sects - 1))
dev->nr_zones++;
- dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct blk_zone),
- GFP_KERNEL | __GFP_ZERO);
+ dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct nullb_zone),
+ GFP_KERNEL | __GFP_ZERO);
if (!dev->zones)
return -ENOMEM;
- /*
- * With memory backing, the zone_lock spinlock needs to be temporarily
- * released to avoid scheduling in atomic context. To guarantee zone
- * information protection, use a bitmap to lock zones with
- * wait_on_bit_lock_io(). Sleeping on the lock is OK as memory backing
- * implies that the queue is marked with BLK_MQ_F_BLOCKING.
- */
- spin_lock_init(&dev->zone_lock);
- if (dev->memory_backed) {
- dev->zone_locks = bitmap_zalloc(dev->nr_zones, GFP_KERNEL);
- if (!dev->zone_locks) {
- kvfree(dev->zones);
- return -ENOMEM;
- }
- }
+ spin_lock_init(&dev->zone_res_lock);
if (dev->zone_nr_conv >= dev->nr_zones) {
dev->zone_nr_conv = dev->nr_zones - 1;
dev->zone_max_open = 0;
pr_info("zone_max_open limit disabled, limit >= zone count\n");
}
+ dev->need_zone_res_mgmt = dev->zone_max_active || dev->zone_max_open;
for (i = 0; i < dev->zone_nr_conv; i++) {
- struct blk_zone *zone = &dev->zones[i];
+ zone = &dev->zones[i];
+ null_init_zone_lock(dev, zone);
zone->start = sector;
zone->len = dev->zone_size_sects;
zone->capacity = zone->len;
}
for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
- struct blk_zone *zone = &dev->zones[i];
+ zone = &dev->zones[i];
+ null_init_zone_lock(dev, zone);
zone->start = zone->wp = sector;
if (zone->start + dev->zone_size_sects > dev_capacity_sects)
zone->len = dev_capacity_sects - zone->start;
void null_free_zoned_dev(struct nullb_device *dev)
{
- bitmap_free(dev->zone_locks);
kvfree(dev->zones);
}
-static inline void null_lock_zone(struct nullb_device *dev, unsigned int zno)
-{
- if (dev->memory_backed)
- wait_on_bit_lock_io(dev->zone_locks, zno, TASK_UNINTERRUPTIBLE);
- spin_lock_irq(&dev->zone_lock);
-}
-
-static inline void null_unlock_zone(struct nullb_device *dev, unsigned int zno)
-{
- spin_unlock_irq(&dev->zone_lock);
-
- if (dev->memory_backed)
- clear_and_wake_up_bit(zno, dev->zone_locks);
-}
-
int null_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct nullb *nullb = disk->private_data;
struct nullb_device *dev = nullb->dev;
- unsigned int first_zone, i, zno;
- struct blk_zone zone;
+ unsigned int first_zone, i;
+ struct nullb_zone *zone;
+ struct blk_zone blkz;
int error;
first_zone = null_zone_no(dev, sector);
nr_zones = min(nr_zones, dev->nr_zones - first_zone);
trace_nullb_report_zones(nullb, nr_zones);
- zno = first_zone;
- for (i = 0; i < nr_zones; i++, zno++) {
+ memset(&blkz, 0, sizeof(struct blk_zone));
+ zone = &dev->zones[first_zone];
+ for (i = 0; i < nr_zones; i++, zone++) {
/*
* Stacked DM target drivers will remap the zone information by
* modifying the zone information passed to the report callback.
* So use a local copy to avoid corruption of the device zone
* array.
*/
- null_lock_zone(dev, zno);
- memcpy(&zone, &dev->zones[zno], sizeof(struct blk_zone));
- null_unlock_zone(dev, zno);
-
- error = cb(&zone, i, data);
+ null_lock_zone(dev, zone);
+ blkz.start = zone->start;
+ blkz.len = zone->len;
+ blkz.wp = zone->wp;
+ blkz.type = zone->type;
+ blkz.cond = zone->cond;
+ blkz.capacity = zone->capacity;
+ null_unlock_zone(dev, zone);
+
+ error = cb(&blkz, i, data);
if (error)
return error;
}
sector_t sector, unsigned int len)
{
struct nullb_device *dev = nullb->dev;
- struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
+ struct nullb_zone *zone = &dev->zones[null_zone_no(dev, sector)];
unsigned int nr_sectors = len >> SECTOR_SHIFT;
/* Read must be below the write pointer position */
return (zone->wp - sector) << SECTOR_SHIFT;
}
-static blk_status_t null_close_zone(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t __null_close_zone(struct nullb_device *dev,
+ struct nullb_zone *zone)
{
- if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
- return BLK_STS_IOERR;
-
switch (zone->cond) {
case BLK_ZONE_COND_CLOSED:
/* close operation on closed is not an error */
for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
if (dev->zones[i].cond == BLK_ZONE_COND_IMP_OPEN) {
- null_close_zone(dev, &dev->zones[i]);
+ __null_close_zone(dev, &dev->zones[i]);
return;
}
}
* it is not certain that closing an implicit open zone will allow a new zone
* to be opened, since we might already be at the active limit capacity.
*/
-static blk_status_t null_check_zone_resources(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t null_check_zone_resources(struct nullb_device *dev,
+ struct nullb_zone *zone)
{
blk_status_t ret;
{
struct nullb_device *dev = cmd->nq->dev;
unsigned int zno = null_zone_no(dev, sector);
- struct blk_zone *zone = &dev->zones[zno];
+ struct nullb_zone *zone = &dev->zones[zno];
blk_status_t ret;
trace_nullb_zone_op(cmd, zno, zone->cond);
return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
}
- null_lock_zone(dev, zno);
+ null_lock_zone(dev, zone);
- switch (zone->cond) {
- case BLK_ZONE_COND_FULL:
+ if (zone->cond == BLK_ZONE_COND_FULL) {
/* Cannot write to a full zone */
ret = BLK_STS_IOERR;
goto unlock;
- case BLK_ZONE_COND_EMPTY:
- case BLK_ZONE_COND_CLOSED:
- ret = null_check_zone_resources(dev, zone);
- if (ret != BLK_STS_OK)
- goto unlock;
- break;
- case BLK_ZONE_COND_IMP_OPEN:
- case BLK_ZONE_COND_EXP_OPEN:
- break;
- default:
- /* Invalid zone condition */
- ret = BLK_STS_IOERR;
- goto unlock;
}
/*
goto unlock;
}
- if (zone->cond == BLK_ZONE_COND_CLOSED) {
- dev->nr_zones_closed--;
- dev->nr_zones_imp_open++;
- } else if (zone->cond == BLK_ZONE_COND_EMPTY) {
- dev->nr_zones_imp_open++;
+ if (zone->cond == BLK_ZONE_COND_CLOSED ||
+ zone->cond == BLK_ZONE_COND_EMPTY) {
+ null_lock_zone_res(dev);
+
+ ret = null_check_zone_resources(dev, zone);
+ if (ret != BLK_STS_OK) {
+ null_unlock_zone_res(dev);
+ goto unlock;
+ }
+ if (zone->cond == BLK_ZONE_COND_CLOSED) {
+ dev->nr_zones_closed--;
+ dev->nr_zones_imp_open++;
+ } else if (zone->cond == BLK_ZONE_COND_EMPTY) {
+ dev->nr_zones_imp_open++;
+ }
+
+ if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
+ zone->cond = BLK_ZONE_COND_IMP_OPEN;
+
+ null_unlock_zone_res(dev);
}
- if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
- zone->cond = BLK_ZONE_COND_IMP_OPEN;
- /*
- * Memory backing allocation may sleep: release the zone_lock spinlock
- * to avoid scheduling in atomic context. Zone operation atomicity is
- * still guaranteed through the zone_locks bitmap.
- */
- if (dev->memory_backed)
- spin_unlock_irq(&dev->zone_lock);
ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
- if (dev->memory_backed)
- spin_lock_irq(&dev->zone_lock);
-
if (ret != BLK_STS_OK)
goto unlock;
zone->wp += nr_sectors;
if (zone->wp == zone->start + zone->capacity) {
+ null_lock_zone_res(dev);
if (zone->cond == BLK_ZONE_COND_EXP_OPEN)
dev->nr_zones_exp_open--;
else if (zone->cond == BLK_ZONE_COND_IMP_OPEN)
dev->nr_zones_imp_open--;
zone->cond = BLK_ZONE_COND_FULL;
+ null_unlock_zone_res(dev);
}
+
ret = BLK_STS_OK;
unlock:
- null_unlock_zone(dev, zno);
+ null_unlock_zone(dev, zone);
return ret;
}
-static blk_status_t null_open_zone(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t null_open_zone(struct nullb_device *dev,
+ struct nullb_zone *zone)
{
- blk_status_t ret;
+ blk_status_t ret = BLK_STS_OK;
if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
return BLK_STS_IOERR;
+ null_lock_zone_res(dev);
+
switch (zone->cond) {
case BLK_ZONE_COND_EXP_OPEN:
/* open operation on exp open is not an error */
- return BLK_STS_OK;
+ goto unlock;
case BLK_ZONE_COND_EMPTY:
ret = null_check_zone_resources(dev, zone);
if (ret != BLK_STS_OK)
- return ret;
+ goto unlock;
break;
case BLK_ZONE_COND_IMP_OPEN:
dev->nr_zones_imp_open--;
case BLK_ZONE_COND_CLOSED:
ret = null_check_zone_resources(dev, zone);
if (ret != BLK_STS_OK)
- return ret;
+ goto unlock;
dev->nr_zones_closed--;
break;
case BLK_ZONE_COND_FULL:
default:
- return BLK_STS_IOERR;
+ ret = BLK_STS_IOERR;
+ goto unlock;
}
zone->cond = BLK_ZONE_COND_EXP_OPEN;
dev->nr_zones_exp_open++;
- return BLK_STS_OK;
+unlock:
+ null_unlock_zone_res(dev);
+
+ return ret;
}
-static blk_status_t null_finish_zone(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t null_close_zone(struct nullb_device *dev,
+ struct nullb_zone *zone)
{
blk_status_t ret;
if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
return BLK_STS_IOERR;
+ null_lock_zone_res(dev);
+ ret = __null_close_zone(dev, zone);
+ null_unlock_zone_res(dev);
+
+ return ret;
+}
+
+static blk_status_t null_finish_zone(struct nullb_device *dev,
+ struct nullb_zone *zone)
+{
+ blk_status_t ret = BLK_STS_OK;
+
+ if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+ return BLK_STS_IOERR;
+
+ null_lock_zone_res(dev);
+
switch (zone->cond) {
case BLK_ZONE_COND_FULL:
/* finish operation on full is not an error */
- return BLK_STS_OK;
+ goto unlock;
case BLK_ZONE_COND_EMPTY:
ret = null_check_zone_resources(dev, zone);
if (ret != BLK_STS_OK)
- return ret;
+ goto unlock;
break;
case BLK_ZONE_COND_IMP_OPEN:
dev->nr_zones_imp_open--;
case BLK_ZONE_COND_CLOSED:
ret = null_check_zone_resources(dev, zone);
if (ret != BLK_STS_OK)
- return ret;
+ goto unlock;
dev->nr_zones_closed--;
break;
default:
- return BLK_STS_IOERR;
+ ret = BLK_STS_IOERR;
+ goto unlock;
}
zone->cond = BLK_ZONE_COND_FULL;
zone->wp = zone->start + zone->len;
- return BLK_STS_OK;
+unlock:
+ null_unlock_zone_res(dev);
+
+ return ret;
}
-static blk_status_t null_reset_zone(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t null_reset_zone(struct nullb_device *dev,
+ struct nullb_zone *zone)
{
if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
return BLK_STS_IOERR;
+ null_lock_zone_res(dev);
+
switch (zone->cond) {
case BLK_ZONE_COND_EMPTY:
/* reset operation on empty is not an error */
+ null_unlock_zone_res(dev);
return BLK_STS_OK;
case BLK_ZONE_COND_IMP_OPEN:
dev->nr_zones_imp_open--;
case BLK_ZONE_COND_FULL:
break;
default:
+ null_unlock_zone_res(dev);
return BLK_STS_IOERR;
}
zone->cond = BLK_ZONE_COND_EMPTY;
zone->wp = zone->start;
+ null_unlock_zone_res(dev);
+
return BLK_STS_OK;
}
{
struct nullb_device *dev = cmd->nq->dev;
unsigned int zone_no;
- struct blk_zone *zone;
+ struct nullb_zone *zone;
blk_status_t ret;
size_t i;
if (op == REQ_OP_ZONE_RESET_ALL) {
for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
- null_lock_zone(dev, i);
zone = &dev->zones[i];
+ null_lock_zone(dev, zone);
if (zone->cond != BLK_ZONE_COND_EMPTY) {
null_reset_zone(dev, zone);
trace_nullb_zone_op(cmd, i, zone->cond);
}
- null_unlock_zone(dev, i);
+ null_unlock_zone(dev, zone);
}
return BLK_STS_OK;
}
zone_no = null_zone_no(dev, sector);
zone = &dev->zones[zone_no];
- null_lock_zone(dev, zone_no);
+ null_lock_zone(dev, zone);
switch (op) {
case REQ_OP_ZONE_RESET:
if (ret == BLK_STS_OK)
trace_nullb_zone_op(cmd, zone_no, zone->cond);
- null_unlock_zone(dev, zone_no);
+ null_unlock_zone(dev, zone);
return ret;
}
blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_opf op,
sector_t sector, sector_t nr_sectors)
{
- struct nullb_device *dev = cmd->nq->dev;
- unsigned int zno = null_zone_no(dev, sector);
+ struct nullb_device *dev;
+ struct nullb_zone *zone;
blk_status_t sts;
switch (op) {
case REQ_OP_WRITE:
- sts = null_zone_write(cmd, sector, nr_sectors, false);
- break;
+ return null_zone_write(cmd, sector, nr_sectors, false);
case REQ_OP_ZONE_APPEND:
- sts = null_zone_write(cmd, sector, nr_sectors, true);
- break;
+ return null_zone_write(cmd, sector, nr_sectors, true);
case REQ_OP_ZONE_RESET:
case REQ_OP_ZONE_RESET_ALL:
case REQ_OP_ZONE_OPEN:
case REQ_OP_ZONE_CLOSE:
case REQ_OP_ZONE_FINISH:
- sts = null_zone_mgmt(cmd, op, sector);
- break;
+ return null_zone_mgmt(cmd, op, sector);
default:
- null_lock_zone(dev, zno);
+ dev = cmd->nq->dev;
+ zone = &dev->zones[null_zone_no(dev, sector)];
+
+ null_lock_zone(dev, zone);
sts = null_process_cmd(cmd, op, sector, nr_sectors);
- null_unlock_zone(dev, zno);
+ null_unlock_zone(dev, zone);
+ return sts;
}
-
- return sts;
}