[PATCH] Ensure that the SCSI error handler gets woken up

[Bart Van Assche]

If scsi_eh_scmd_add() is called concurrently with scsi_host_queue_ready()
while shost->host_blocked > 0 then it can happen that neither function
wakes up the SCSI error handler. Fix this by making every function that
decreases the host_busy counter to wake up the error handler if necessary.

Reported-by: Pavel Tikhomirov <ptikhomi...@virtuozzo.com>
Fixes: commit 746650160866 ("scsi: convert host_busy to atomic_t")
Signed-off-by: Bart Van Assche <bart.vanass...@wdc.com>
Cc: Konstantin Khorenko <khore...@virtuozzo.com>
Cc: Stuart Hayes <stuart.w.ha...@gmail.com>
Cc: Christoph Hellwig <h...@lst.de>
Cc: Hannes Reinecke <h...@suse.com>
Cc: Johannes Thumshirn <jthumsh...@suse.de>
Cc: <sta...@vger.kernel.org>
---
 drivers/scsi/scsi_error.c |  3 ++-
 drivers/scsi/scsi_lib.c   | 22 ++++++++++++++--------
 2 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 5e89049e9b4e..f7f014c755d7 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -61,9 +61,10 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd);
 static int scsi_try_to_abort_cmd(struct scsi_host_template *,
                                 struct scsi_cmnd *);
 
-/* called with shost->host_lock held */
 void scsi_eh_wakeup(struct Scsi_Host *shost)
 {
+       lockdep_assert_held(shost->host_lock);
+
        if (atomic_read(&shost->host_busy) == shost->host_failed) {
                trace_scsi_eh_wakeup(shost);
                wake_up_process(shost->ehandler);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 1e05e1885ac8..abd37d77af2d 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -318,22 +318,28 @@ static void scsi_init_cmd_errh(struct scsi_cmnd *cmd)
                cmd->cmd_len = scsi_command_size(cmd->cmnd);
 }
 
-void scsi_device_unbusy(struct scsi_device *sdev)
+static void scsi_dec_host_busy(struct Scsi_Host *shost)
 {
-       struct Scsi_Host *shost = sdev->host;
-       struct scsi_target *starget = scsi_target(sdev);
        unsigned long flags;
 
        atomic_dec(&shost->host_busy);
-       if (starget->can_queue > 0)
-               atomic_dec(&starget->target_busy);
-
        if (unlikely(scsi_host_in_recovery(shost) &&
                     (shost->host_failed || shost->host_eh_scheduled))) {
                spin_lock_irqsave(shost->host_lock, flags);
                scsi_eh_wakeup(shost);
                spin_unlock_irqrestore(shost->host_lock, flags);
        }
+}
+
+void scsi_device_unbusy(struct scsi_device *sdev)
+{
+       struct Scsi_Host *shost = sdev->host;
+       struct scsi_target *starget = scsi_target(sdev);
+
+       scsi_dec_host_busy(shost);
+
+       if (starget->can_queue > 0)
+               atomic_dec(&starget->target_busy);
 
        atomic_dec(&sdev->device_busy);
 }
@@ -1532,7 +1538,7 @@ static inline int scsi_host_queue_ready(struct 
request_queue *q,
                list_add_tail(&sdev->starved_entry, &shost->starved_list);
        spin_unlock_irq(shost->host_lock);
 out_dec:
-       atomic_dec(&shost->host_busy);
+       scsi_dec_host_busy(shost);
        return 0;
 }
 
@@ -2020,7 +2026,7 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx 
*hctx,
        return BLK_STS_OK;
 
 out_dec_host_busy:
-       atomic_dec(&shost->host_busy);
+       scsi_dec_host_busy(shost);
 out_dec_target_busy:
        if (scsi_target(sdev)->can_queue > 0)
                atomic_dec(&scsi_target(sdev)->target_busy);
-- 
2.15.0