dm mpath: fix stall when requeueing io

This patch fixes the problem that system may stall if target's ->map_rq
returns DM_MAPIO_REQUEUE in map_request().
E.g. stall happens on 1 CPU box when a dm-mpath device with queue_if_no_path
     bounces between all-paths-down and paths-up on I/O load.

When target's ->map_rq returns DM_MAPIO_REQUEUE, map_request() requeues
the request and returns to dm_request_fn().  Then, dm_request_fn()
doesn't exit the I/O dispatching loop and continues processing
the requeued request again.
This map and requeue loop can be done with interrupt disabled,
so 1 CPU system can be stalled if this situation happens.

For example, commands below can stall my 1 CPU box within 1 minute or so:
  # dmsetup table mp
  mp: 0 2097152 multipath 1 queue_if_no_path 0 1 1 service-time 0 1 2 8:144 1 1
  # while true; do dd if=/dev/mapper/mp of=/dev/null bs=1M count=100; done &
  # while true; do \
  > dmsetup message mp 0 "fail_path 8:144" \
  > dmsetup suspend --noflush mp \
  > dmsetup resume mp \
  > dmsetup message mp 0 "reinstate_path 8:144" \
  > done

To fix the problem above, this patch changes dm_request_fn() to exit
the I/O dispatching loop once if a request is requeued in map_request().

Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Cc: stable@kernel.org
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3167480b532cd92e64c12831bb3ac4d424f37270..aa4e2aa86d490c5aa1af423d23c176ed69c25302 100644 (file)
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1595,10 +1595,15 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq)
        return BLKPREP_OK;
 }
 
-static void map_request(struct dm_target *ti, struct request *clone,
-                       struct mapped_device *md)
+/*
+ * Returns:
+ * 0  : the request has been processed (not requeued)
+ * !0 : the request has been requeued
+ */
+static int map_request(struct dm_target *ti, struct request *clone,
+                      struct mapped_device *md)
 {
-       int r;
+       int r, requeued = 0;
        struct dm_rq_target_io *tio = clone->end_io_data;
 
        /*
@@ -1625,6 +1630,7 @@ static void map_request(struct dm_target *ti, struct request *clone,
        case DM_MAPIO_REQUEUE:
                /* The target wants to requeue the I/O */
                dm_requeue_unmapped_request(clone);
+               requeued = 1;
                break;
        default:
                if (r > 0) {
@@ -1636,6 +1642,8 @@ static void map_request(struct dm_target *ti, struct request *clone,
                dm_kill_unmapped_request(clone, r);
                break;
        }
+
+       return requeued;
 }
 
 /*
@@ -1677,12 +1685,17 @@ static void dm_request_fn(struct request_queue *q)
                atomic_inc(&md->pending[rq_data_dir(clone)]);
 
                spin_unlock(q->queue_lock);
-               map_request(ti, clone, md);
+               if (map_request(ti, clone, md))
+                       goto requeued;
+
                spin_lock_irq(q->queue_lock);
        }
 
        goto out;
 
+requeued:
+       spin_lock_irq(q->queue_lock);
+
 plug_and_out:
        if (!elv_queue_empty(q))
                /* Some requests still remain, retry later */