dm: linear support discard

Allow discards to be passed through to linear mappings if at least one
underlying device supports it.  Discards will be forwarded only to
devices that support them.

A target that supports discards should set num_discard_requests to
indicate how many times each discard request must be submitted to it.

Verify table's underlying devices support discards prior to setting the
associated DM device as capable of discards (via QUEUE_FLAG_DISCARD).

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Reviewed-by: Joe Thornber <thornber@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 9200dbf..f043b5f 100644 (file)
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -53,6 +53,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
        }
 
        ti->num_flush_requests = 1;
+       ti->num_discard_requests = 1;
        ti->private = lc;
        return 0;
 

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index bc60ef7..f9fc07d 100644 (file)
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -54,6 +54,8 @@ struct dm_table {
        sector_t *highs;
        struct dm_target *targets;
 
+       unsigned discards_supported:1;
+
        /*
         * Indicates the rw permissions for the new logical
         * device.  This should be a combination of FMODE_READ
@@ -203,6 +205,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 
        INIT_LIST_HEAD(&t->devices);
        atomic_set(&t->holders, 0);
+       t->discards_supported = 1;
 
        if (!num_targets)
                num_targets = KEYS_PER_NODE;
@@ -770,6 +773,9 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 
        t->highs[t->num_targets++] = tgt->begin + tgt->len - 1;
 
+       if (!tgt->num_discard_requests)
+               t->discards_supported = 0;
+
        return 0;
 
  bad:
@@ -1135,6 +1141,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
        else
                queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, q);
 
+       if (!dm_table_supports_discards(t))
+               queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
+       else
+               queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+
        dm_table_set_integrity(t);
 
        /*
@@ -1281,6 +1292,39 @@ struct mapped_device *dm_table_get_md(struct dm_table *t)
        return t->md;
 }
 
+static int device_discard_capable(struct dm_target *ti, struct dm_dev *dev,
+                                 sector_t start, sector_t len, void *data)
+{
+       struct request_queue *q = bdev_get_queue(dev->bdev);
+
+       return q && blk_queue_discard(q);
+}
+
+bool dm_table_supports_discards(struct dm_table *t)
+{
+       struct dm_target *ti;
+       unsigned i = 0;
+
+       if (!t->discards_supported)
+               return 0;
+
+       /*
+        * Ensure that at least one underlying device supports discards.
+        * t->devices includes internal dm devices such as mirror logs
+        * so we need to use iterate_devices here, which targets
+        * supporting discard must provide.
+        */
+       while (i < dm_table_get_num_targets(t)) {
+               ti = dm_table_get_target(t, i++);
+
+               if (ti->type->iterate_devices &&
+                   ti->type->iterate_devices(ti, device_discard_capable, NULL))
+                       return 1;
+       }
+
+       return 0;
+}
+
 EXPORT_SYMBOL(dm_vcalloc);
 EXPORT_SYMBOL(dm_get_device);
 EXPORT_SYMBOL(dm_put_device);

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 0d47101..44aba29 100644 (file)
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1212,6 +1212,53 @@ static int __clone_and_map_empty_barrier(struct clone_info *ci)
        return 0;
 }
 
+/*
+ * Perform all io with a single clone.
+ */
+static void __clone_and_map_simple(struct clone_info *ci, struct dm_target *ti)
+{
+       struct bio *clone, *bio = ci->bio;
+       struct dm_target_io *tio;
+
+       tio = alloc_tio(ci, ti);
+       clone = clone_bio(bio, ci->sector, ci->idx,
+                         bio->bi_vcnt - ci->idx, ci->sector_count,
+                         ci->md->bs);
+       __map_bio(ti, clone, tio);
+       ci->sector_count = 0;
+}
+
+static int __clone_and_map_discard(struct clone_info *ci)
+{
+       struct dm_target *ti;
+       sector_t max;
+
+       ti = dm_table_find_target(ci->map, ci->sector);
+       if (!dm_target_is_valid(ti))
+               return -EIO;
+
+       /*
+        * Even though the device advertised discard support,
+        * reconfiguration might have changed that since the
+        * check was performed.
+        */
+
+       if (!ti->num_discard_requests)
+               return -EOPNOTSUPP;
+
+       max = max_io_len(ci->md, ci->sector, ti);
+
+       if (ci->sector_count > max)
+               /*
+                * FIXME: Handle a discard that spans two or more targets.
+                */
+               return -EOPNOTSUPP;
+
+       __clone_and_map_simple(ci, ti);
+
+       return 0;
+}
+
 static int __clone_and_map(struct clone_info *ci)
 {
        struct bio *clone, *bio = ci->bio;
@@ -1222,27 +1269,21 @@ static int __clone_and_map(struct clone_info *ci)
        if (unlikely(bio_empty_barrier(bio)))
                return __clone_and_map_empty_barrier(ci);
 
+       if (unlikely(bio->bi_rw & REQ_DISCARD))
+               return __clone_and_map_discard(ci);
+
        ti = dm_table_find_target(ci->map, ci->sector);
        if (!dm_target_is_valid(ti))
                return -EIO;
 
        max = max_io_len(ci->md, ci->sector, ti);
 
-       /*
-        * Allocate a target io object.
-        */
-       tio = alloc_tio(ci, ti);
-
        if (ci->sector_count <= max) {
                /*
                 * Optimise for the simple case where we can do all of
                 * the remaining io with a single clone.
                 */
-               clone = clone_bio(bio, ci->sector, ci->idx,
-                                 bio->bi_vcnt - ci->idx, ci->sector_count,
-                                 ci->md->bs);
-               __map_bio(ti, clone, tio);
-               ci->sector_count = 0;
+               __clone_and_map_simple(ci, ti);
 
        } else if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) {
                /*
@@ -1263,6 +1304,7 @@ static int __clone_and_map(struct clone_info *ci)
                        len += bv_len;
                }
 
+               tio = alloc_tio(ci, ti);
                clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len,
                                  ci->md->bs);
                __map_bio(ti, clone, tio);
@@ -1286,12 +1328,11 @@ static int __clone_and_map(struct clone_info *ci)
                                        return -EIO;
 
                                max = max_io_len(ci->md, ci->sector, ti);
-
-                               tio = alloc_tio(ci, ti);
                        }
 
                        len = min(remaining, max);
 
+                       tio = alloc_tio(ci, ti);
                        clone = split_bvec(bio, ci->sector, ci->idx,
                                           bv->bv_offset + offset, len,
                                           ci->md->bs);

diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 0d7b374..0c2dd5f 100644 (file)
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -61,6 +61,7 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits);
 int dm_table_any_busy_target(struct dm_table *t);
 unsigned dm_table_get_type(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
+bool dm_table_supports_discards(struct dm_table *t);
 int dm_table_alloc_md_mempools(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);

diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 531a6f2..751ce21 100644 (file)
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -180,6 +180,12 @@ struct dm_target {
         */
        unsigned num_flush_requests;
 
+       /*
+        * The number of discard requests that will be submitted to the
+        * target.  map_info->request_nr is used just like num_flush_requests.
+        */
+       unsigned num_discard_requests;
+
        /* target specific data */
        void *private;