dm: retain table limits when swapping to new table with no devices

Add a safety net that will re-use the DM device's existing limits in the
event that DM device has a temporary table that doesn't have any
component devices.  This is to reduce the chance that requests not
respecting the hardware limits will reach the device.

DM recalculates queue limits based only on devices which currently exist
in the table.  This creates a problem in the event all devices are
temporarily removed such as all paths being lost in multipath.  DM will
reset the limits to the maximum permissible, which can then assemble
requests which exceed the limits of the paths when the paths are
restored.  The request will fail the blk_rq_check_limits() test when
sent to a path with lower limits, and will be retried without end by
multipath.  This became a much bigger issue after v3.6 commit fe86cdcef
("block: do not artificially constrain max_sectors for stacking
drivers").

Reported-by: David Jeffery <djeffery@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

3 files changed, 50 insertions, 1 deletions

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 77b90ae66991..100368eb7991 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1212,6 +1212,41 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
         return &t->targets[(KEYS_PER_NODE * n) + k];
 }
 
+static int count_device(struct dm_target *ti, struct dm_dev *dev,
+                        sector_t start, sector_t len, void *data)
+{
+        unsigned *num_devices = data;
+
+        (*num_devices)++;
+
+        return 0;
+}
+
+/*
+ * Check whether a table has no data devices attached using each
+ * target's iterate_devices method.
+ * Returns false if the result is unknown because a target doesn't
+ * support iterate_devices.
+ */
+bool dm_table_has_no_data_devices(struct dm_table *table)
+{
+        struct dm_target *uninitialized_var(ti);
+        unsigned i = 0, num_devices = 0;
+
+        while (i < dm_table_get_num_targets(table)) {
+                ti = dm_table_get_target(table, i++);
+
+                if (!ti->type->iterate_devices)
+                        return false;
+
+                ti->type->iterate_devices(ti, count_device, &num_devices);
+                if (num_devices)
+                        return false;
+        }
+
+        return true;
+}
+
 /*
  * Establish the new table's queue_limits and validate them.
  */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6748e0c4df1f..67ffa391edcf 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2429,7 +2429,7 @@ static void dm_queue_flush(struct mapped_device *md)
  */
 struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table)
 {
-        struct dm_table *map = ERR_PTR(-EINVAL);
+        struct dm_table *live_map, *map = ERR_PTR(-EINVAL);
         struct queue_limits limits;
         int r;
 
@@ -2439,6 +2439,19 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table)
         if (!dm_suspended_md(md))
                 goto out;
 
+        /*
+         * If the new table has no data devices, retain the existing limits.
+         * This helps multipath with queue_if_no_path if all paths disappear,
+         * then new I/O is queued based on these limits, and then some paths
+         * reappear.
+         */
+        if (dm_table_has_no_data_devices(table)) {
+                live_map = dm_get_live_table(md);
+                if (live_map)
+                        limits = md->queue->limits;
+                dm_table_put(live_map);
+        }
+
         r = dm_calculate_queue_limits(table, &limits);
         if (r) {
                 map = ERR_PTR(r);
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 52eef493d266..6a99fefaa743 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -54,6 +54,7 @@ void dm_table_event_callback(struct dm_table *t,
                              void (*fn)(void *), void *context);
 struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index);
 struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector);
+bool dm_table_has_no_data_devices(struct dm_table *table);
 int dm_calculate_queue_limits(struct dm_table *table,
                               struct queue_limits *limits);
 void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,