@@ -590,7 +590,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
return BLK_STS_IOERR;
/* Make sure the BIO is small enough and will not get split */
- if (nr_sectors > q->limits.max_zone_append_sectors)
+ if (nr_sectors > queue_max_zone_append_sectors(q))
return BLK_STS_IOERR;
bio->bi_opf |= REQ_NOMERGE;
@@ -211,24 +211,32 @@ EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);
* blk_queue_max_zone_append_sectors - set max sectors for a single zone append
* @q: the request queue for the device
* @max_zone_append_sectors: maximum number of sectors to write per command
+ *
+ * Sets the maximum number of sectors allowed for zone append commands. If
+ * Specifying 0 for @max_zone_append_sectors indicates that the queue does
+ * not natively support zone append operations and that the block layer must
+ * emulate these operations using regular writes.
**/
void blk_queue_max_zone_append_sectors(struct request_queue *q,
unsigned int max_zone_append_sectors)
{
- unsigned int max_sectors;
+ unsigned int max_sectors = 0;
if (WARN_ON(!blk_queue_is_zoned(q)))
return;
- max_sectors = min(q->limits.max_hw_sectors, max_zone_append_sectors);
- max_sectors = min(q->limits.chunk_sectors, max_sectors);
-
- /*
- * Signal eventual driver bugs resulting in the max_zone_append sectors limit
- * being 0 due to a 0 argument, the chunk_sectors limit (zone size) not set,
- * or the max_hw_sectors limit not set.
- */
- WARN_ON(!max_sectors);
+ if (max_zone_append_sectors) {
+ max_sectors = min(q->limits.max_hw_sectors,
+ max_zone_append_sectors);
+ max_sectors = min(q->limits.chunk_sectors, max_sectors);
+
+ /*
+ * Signal eventual driver bugs resulting in the max_zone_append
+ * sectors limit being 0 due to the chunk_sectors limit (zone
+ * size) not set or the max_hw_sectors limit not set.
+ */
+ WARN_ON(!max_sectors);
+ }
q->limits.max_zone_append_sectors = max_sectors;
}
@@ -563,8 +571,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
b->max_write_zeroes_sectors);
- t->max_zone_append_sectors = min(t->max_zone_append_sectors,
- b->max_zone_append_sectors);
+ t->max_zone_append_sectors = min(queue_limits_max_zone_append_sectors(t),
+ queue_limits_max_zone_append_sectors(b));
t->bounce = max(t->bounce, b->bounce);
t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
@@ -689,6 +697,9 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
t->zone_write_granularity = max(t->zone_write_granularity,
b->zone_write_granularity);
t->zoned = max(t->zoned, b->zoned);
+ if (!t->zoned)
+ t->max_zone_append_sectors = 0;
+
return ret;
}
EXPORT_SYMBOL(blk_stack_limits);
@@ -218,7 +218,7 @@ static ssize_t queue_zone_write_granularity_show(struct request_queue *q,
static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page)
{
- unsigned long long max_sectors = q->limits.max_zone_append_sectors;
+ unsigned long long max_sectors = queue_max_zone_append_sectors(q);
return sprintf(page, "%llu\n", max_sectors << SECTOR_SHIFT);
}
@@ -946,7 +946,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
return -ENODEV;
}
- if (!q->limits.max_zone_append_sectors) {
+ if (!queue_max_zone_append_sectors(q)) {
pr_warn("%s: Invalid 0 maximum zone append limit\n",
disk->disk_name);
return -ENODEV;
@@ -1137,12 +1137,26 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
return q->limits.max_segment_size;
}
-static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
+static inline unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l)
{
+ unsigned int max_sectors = min(l->chunk_sectors, l->max_sectors);
- const struct queue_limits *l = &q->limits;
+ return min_not_zero(l->max_zone_append_sectors, max_sectors);
+}
+
+static inline unsigned int queue_max_zone_append_sectors(struct request_queue *q)
+{
+ return queue_limits_max_zone_append_sectors(&q->limits);
+}
- return min(l->max_zone_append_sectors, l->max_sectors);
+static inline bool queue_emulates_zone_append(struct request_queue *q)
+{
+ return blk_queue_is_zoned(q) && !q->limits.max_zone_append_sectors;
+}
+
+static inline bool bdev_emulates_zone_append(struct block_device *bdev)
+{
+ return queue_emulates_zone_append(bdev_get_queue(bdev));
}
static inline unsigned int
In preparation for adding a generic zone append emulation using zone write plugging, allow device drivers supporting zoned block device to set a the max_zone_append_sectors queue limit of a device to 0 to indicate the lack of native support for zone append operations and that the block layer should emulate these operations using regular write operations. blk_queue_max_zone_append_sectors() is modified to allow passing 0 as the max_zone_append_sectors argument. The function queue_max_zone_append_sectors() is also modified to ensure that the minimum of the max_sectors and chunk_sectors limit is used whenever the max_zone_append_sectors limit is 0. The helper functions queue_emulates_zone_append() and bdev_emulates_zone_append() are added to test if a queue (or block device) emulates zone append operations. In order for blk_revalidate_disk_zones() to accept zoned block devices relying on zone append emulation, the direct check to the max_zone_append_sectors queue limit of the disk is replaced by a check using the value returned by queue_max_zone_append_sectors(). Similarly, queue_zone_append_max_show() is modified to use the same accessor so that the sysfs attribute advertizes the non-zero limit that will be used, regardless if it is for native or emulated commands. For stacking drivers, a top device should not need to care if the underlying devices have native or emulated zone append operations. blk_stack_limits() is thus modified to set the top device max_zone_append_sectors limit using the new accessor queue_limits_max_zone_append_sectors(). queue_max_zone_append_sectors() is modified to use this function as well. Stacking drivers that require zone append emulation, e.g. dm-crypt, can still request this feature by calling blk_queue_max_zone_append_sectors() with a 0 limit. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> --- block/blk-core.c | 2 +- block/blk-settings.c | 35 +++++++++++++++++++++++------------ block/blk-sysfs.c | 2 +- block/blk-zoned.c | 2 +- include/linux/blkdev.h | 20 +++++++++++++++++--- 5 files changed, 43 insertions(+), 18 deletions(-)