summaryrefslogtreecommitdiff
path: root/drivers/md/dm.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/dm.c')
-rw-r--r--drivers/md/dm.c142
1 files changed, 140 insertions, 2 deletions
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 13e714ea7a42..2edbcc2d7d3f 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -19,6 +19,7 @@
#include <linux/dax.h>
#include <linux/slab.h>
#include <linux/idr.h>
+#include <linux/uio.h>
#include <linux/hdreg.h>
#include <linux/delay.h>
#include <linux/wait.h>
@@ -58,6 +59,9 @@ static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
static struct workqueue_struct *deferred_remove_workqueue;
+atomic_t dm_global_event_nr = ATOMIC_INIT(0);
+DECLARE_WAIT_QUEUE_HEAD(dm_global_eventq);
+
/*
* One of these is allocated per bio.
*/
@@ -969,6 +973,48 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
return ret;
}
+static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+ void *addr, size_t bytes, struct iov_iter *i)
+{
+ struct mapped_device *md = dax_get_private(dax_dev);
+ sector_t sector = pgoff * PAGE_SECTORS;
+ struct dm_target *ti;
+ long ret = 0;
+ int srcu_idx;
+
+ ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+ if (!ti)
+ goto out;
+ if (!ti->type->dax_copy_from_iter) {
+ ret = copy_from_iter(addr, bytes, i);
+ goto out;
+ }
+ ret = ti->type->dax_copy_from_iter(ti, pgoff, addr, bytes, i);
+ out:
+ dm_put_live_table(md, srcu_idx);
+
+ return ret;
+}
+
+static void dm_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+ size_t size)
+{
+ struct mapped_device *md = dax_get_private(dax_dev);
+ sector_t sector = pgoff * PAGE_SECTORS;
+ struct dm_target *ti;
+ int srcu_idx;
+
+ ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+ if (!ti)
+ goto out;
+ if (ti->type->dax_flush)
+ ti->type->dax_flush(ti, pgoff, addr, size);
+ out:
+ dm_put_live_table(md, srcu_idx);
+}
+
/*
* A target may call dm_accept_partial_bio only from the map routine. It is
* allowed for all bio types except REQ_PREFLUSH.
@@ -1010,6 +1056,85 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
/*
+ * The zone descriptors obtained with a zone report indicate
+ * zone positions within the target device. The zone descriptors
+ * must be remapped to match their position within the dm device.
+ * A target may call dm_remap_zone_report after completion of a
+ * REQ_OP_ZONE_REPORT bio to remap the zone descriptors obtained
+ * from the target device mapping to the dm device.
+ */
+void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start)
+{
+#ifdef CONFIG_BLK_DEV_ZONED
+ struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
+ struct bio *report_bio = tio->io->bio;
+ struct blk_zone_report_hdr *hdr = NULL;
+ struct blk_zone *zone;
+ unsigned int nr_rep = 0;
+ unsigned int ofst;
+ struct bio_vec bvec;
+ struct bvec_iter iter;
+ void *addr;
+
+ if (bio->bi_status)
+ return;
+
+ /*
+ * Remap the start sector of the reported zones. For sequential zones,
+ * also remap the write pointer position.
+ */
+ bio_for_each_segment(bvec, report_bio, iter) {
+ addr = kmap_atomic(bvec.bv_page);
+
+ /* Remember the report header in the first page */
+ if (!hdr) {
+ hdr = addr;
+ ofst = sizeof(struct blk_zone_report_hdr);
+ } else
+ ofst = 0;
+
+ /* Set zones start sector */
+ while (hdr->nr_zones && ofst < bvec.bv_len) {
+ zone = addr + ofst;
+ if (zone->start >= start + ti->len) {
+ hdr->nr_zones = 0;
+ break;
+ }
+ zone->start = zone->start + ti->begin - start;
+ if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) {
+ if (zone->cond == BLK_ZONE_COND_FULL)
+ zone->wp = zone->start + zone->len;
+ else if (zone->cond == BLK_ZONE_COND_EMPTY)
+ zone->wp = zone->start;
+ else
+ zone->wp = zone->wp + ti->begin - start;
+ }
+ ofst += sizeof(struct blk_zone);
+ hdr->nr_zones--;
+ nr_rep++;
+ }
+
+ if (addr != hdr)
+ kunmap_atomic(addr);
+
+ if (!hdr->nr_zones)
+ break;
+ }
+
+ if (hdr) {
+ hdr->nr_zones = nr_rep;
+ kunmap_atomic(hdr);
+ }
+
+ bio_advance(report_bio, report_bio->bi_iter.bi_size);
+
+#else /* !CONFIG_BLK_DEV_ZONED */
+ bio->bi_status = BLK_STS_NOTSUPP;
+#endif
+}
+EXPORT_SYMBOL_GPL(dm_remap_zone_report);
+
+/*
* Flush current->bio_list when the target map method blocks.
* This fixes deadlocks in snapshot and possibly in other targets.
*/
@@ -1149,7 +1274,8 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
return r;
}
- bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
+ if (bio_op(bio) != REQ_OP_ZONE_REPORT)
+ bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
clone->bi_iter.bi_size = to_bytes(len);
if (unlikely(bio_integrity(bio) != NULL))
@@ -1338,7 +1464,11 @@ static int __split_and_process_non_flush(struct clone_info *ci)
if (!dm_target_is_valid(ti))
return -EIO;
- len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);
+ if (bio_op(bio) == REQ_OP_ZONE_REPORT)
+ len = ci->sector_count;
+ else
+ len = min_t(sector_t, max_io_len(ci->sector, ti),
+ ci->sector_count);
r = __clone_and_map_data_bio(ci, ti, ci->sector, &len);
if (r < 0)
@@ -1381,6 +1511,10 @@ static void __split_and_process_bio(struct mapped_device *md,
ci.sector_count = 0;
error = __send_empty_flush(&ci);
/* dec_pending submits any data associated with flush */
+ } else if (bio_op(bio) == REQ_OP_ZONE_RESET) {
+ ci.bio = bio;
+ ci.sector_count = 0;
+ error = __split_and_process_non_flush(&ci);
} else {
ci.bio = bio;
ci.sector_count = bio_sectors(bio);
@@ -1759,7 +1893,9 @@ static void event_callback(void *context)
dm_send_uevents(&uevents, &disk_to_dev(md->disk)->kobj);
atomic_inc(&md->event_nr);
+ atomic_inc(&dm_global_event_nr);
wake_up(&md->eventq);
+ wake_up(&dm_global_eventq);
}
/*
@@ -2865,6 +3001,8 @@ static const struct block_device_operations dm_blk_dops = {
static const struct dax_operations dm_dax_ops = {
.direct_access = dm_dax_direct_access,
+ .copy_from_iter = dm_dax_copy_from_iter,
+ .flush = dm_dax_flush,
};
/*