block: Introduce blk_revalidate_disk_zones()

Drivers exposing zoned block devices have to initialize and maintain
correctness (i.e. revalidate) of the device zone bitmaps attached to
the device request queue (seq_zones_bitmap and seq_zones_wlock).

To simplify coding this, introduce a generic helper function
blk_revalidate_disk_zones() suitable for most (and likely all) cases.
This new function always update the seq_zones_bitmap and seq_zones_wlock
bitmaps as well as the queue nr_zones field when called for a disk
using a request based queue. For a disk using a BIO based queue, only
the number of zones is updated since these queues do not have
schedulers and so do not need the zone bitmaps.

With this change, the zone bitmap initialization code in sd_zbc.c can be
replaced with a call to this function in sd_zbc_read_zones(), which is
called from the disk revalidate block operation method.

A call to blk_revalidate_disk_zones() is also added to the null_blk
driver for devices created with the zoned mode enabled.

Finally, to ensure that zoned devices created with dm-linear or
dm-flakey expose the correct number of zones through sysfs, a call to
blk_revalidate_disk_zones() is added to dm_table_set_restrictions().

The zone bitmaps allocated and initialized with
blk_revalidate_disk_zones() are freed automatically from
__blk_release_queue() using the block internal function
blk_queue_free_zone_bitmaps().

Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 144 insertions, 0 deletions

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 92be8092ca4f..0641533597f1 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -852,6 +852,8 @@ static void __blk_release_queue(struct work_struct *work)
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);
 
+	blk_queue_free_zone_bitmaps(q);
+
 	if (!q->mq_ops) {
 		if (q->exit_rq_fn)
 			q->exit_rq_fn(q, q->fq->flush_rq);
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 90cf503091d5..13ba2011a306 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/rbtree.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 
 #include "blk.h"
 
@@ -359,3 +360,138 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
 				  GFP_KERNEL);
 }
+
+static inline unsigned long *blk_alloc_zone_bitmap(int node,
+						   unsigned int nr_zones)
+{
+	return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
+			    GFP_NOIO, node);
+}
+
+/*
+ * Allocate an array of struct blk_zone to get nr_zones zone information.
+ * The allocated array may be smaller than nr_zones.
+ */
+static struct blk_zone *blk_alloc_zones(int node, unsigned int *nr_zones)
+{
+	size_t size = *nr_zones * sizeof(struct blk_zone);
+	struct page *page;
+	int order;
+
+	for (order = get_order(size); order > 0; order--) {
+		page = alloc_pages_node(node, GFP_NOIO | __GFP_ZERO, order);
+		if (page) {
+			*nr_zones = min_t(unsigned int, *nr_zones,
+				(PAGE_SIZE << order) / sizeof(struct blk_zone));
+			return page_address(page);
+		}
+	}
+
+	return NULL;
+}
+
+void blk_queue_free_zone_bitmaps(struct request_queue *q)
+{
+	kfree(q->seq_zones_bitmap);
+	q->seq_zones_bitmap = NULL;
+	kfree(q->seq_zones_wlock);
+	q->seq_zones_wlock = NULL;
+}
+
+/**
+ * blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps
+ * @disk:	Target disk
+ *
+ * Helper function for low-level device drivers to (re) allocate and initialize
+ * a disk request queue zone bitmaps. This functions should normally be called
+ * within the disk ->revalidate method. For BIO based queues, no zone bitmap
+ * is allocated.
+ */
+int blk_revalidate_disk_zones(struct gendisk *disk)
+{
+	struct request_queue *q = disk->queue;
+	unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk));
+	unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
+	unsigned int i, rep_nr_zones = 0, z = 0, nrz;
+	struct blk_zone *zones = NULL;
+	sector_t sector = 0;
+	int ret = 0;
+
+	/*
+	 * BIO based queues do not use a scheduler so only q->nr_zones
+	 * needs to be updated so that the sysfs exposed value is correct.
+	 */
+	if (!queue_is_rq_based(q)) {
+		q->nr_zones = nr_zones;
+		return 0;
+	}
+
+	if (!blk_queue_is_zoned(q) || !nr_zones) {
+		nr_zones = 0;
+		goto update;
+	}
+
+	/* Allocate bitmaps */
+	ret = -ENOMEM;
+	seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones);
+	if (!seq_zones_wlock)
+		goto out;
+	seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones);
+	if (!seq_zones_bitmap)
+		goto out;
+
+	/* Get zone information and initialize seq_zones_bitmap */
+	rep_nr_zones = nr_zones;
+	zones = blk_alloc_zones(q->node, &rep_nr_zones);
+	if (!zones)
+		goto out;
+
+	while (z < nr_zones) {
+		nrz = min(nr_zones - z, rep_nr_zones);
+		ret = blk_report_zones(disk, sector, zones, &nrz, GFP_NOIO);
+		if (ret)
+			goto out;
+		if (!nrz)
+			break;
+		for (i = 0; i < nrz; i++) {
+			if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL)
+				set_bit(z, seq_zones_bitmap);
+			z++;
+		}
+		sector += nrz * blk_queue_zone_sectors(q);
+	}
+
+	if (WARN_ON(z != nr_zones)) {
+		ret = -EIO;
+		goto out;
+	}
+
+update:
+	/*
+	 * Install the new bitmaps, making sure the queue is stopped and
+	 * all I/Os are completed (i.e. a scheduler is not referencing the
+	 * bitmaps).
+	 */
+	blk_mq_freeze_queue(q);
+	q->nr_zones = nr_zones;
+	swap(q->seq_zones_wlock, seq_zones_wlock);
+	swap(q->seq_zones_bitmap, seq_zones_bitmap);
+	blk_mq_unfreeze_queue(q);
+
+out:
+	free_pages((unsigned long)zones,
+		   get_order(rep_nr_zones * sizeof(struct blk_zone)));
+	kfree(seq_zones_wlock);
+	kfree(seq_zones_bitmap);
+
+	if (ret) {
+		pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
+		blk_mq_freeze_queue(q);
+		blk_queue_free_zone_bitmaps(q);
+		blk_mq_unfreeze_queue(q);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
+
diff --git a/block/blk.h b/block/blk.h
index 93574baaa6b8..a1841b8ff129 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -490,4 +490,10 @@ static inline int blk_iolatency_init(struct request_queue *q) { return 0; }
 
 struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp);
 
+#ifdef CONFIG_BLK_DEV_ZONED
+void blk_queue_free_zone_bitmaps(struct request_queue *q);
+#else
+static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {}
+#endif
+
 #endif /* BLK_INTERNAL_H */