scsi: fix race between simultaneous decrements of ->host_failed

commit 72d8c36ec364c82bf1bf0c64dfa1041cfaf139f7 upstream.

sas_ata_strategy_handler() adds the works of the ata error handler to
system_unbound_wq. This workqueue asynchronously runs work items, so the
ata error handler will be performed concurrently on different CPUs. In
this case, ->host_failed will be decreased simultaneously in
scsi_eh_finish_cmd() on different CPUs, and become abnormal.

It will lead to permanently inequality between ->host_failed and
->host_busy, and scsi error handler thread won't start running. IO
errors after that won't be handled.

Since all scmds must have been handled in the strategy handler, just
remove the decrement in scsi_eh_finish_cmd() and zero ->host_busy after
the strategy handler to fix this race.

Fixes: 50824d6c5657 ("[SCSI] libsas: async ata-eh")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <fangwei1@huawei.com>
Reviewed-by: James Bottomley <jejb@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>

diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index 6ff16b620d84cf63d3e6e669a0cb7dab7d350c54..c08b62d63afa1bc2c81f9607a8921e774c856ad5 100644 (file)
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -255,19 +255,23 @@ scmd->allowed.
 
  3. scmd recovered
     ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd
-       - shost->host_failed--
        - clear scmd->eh_eflags
        - scsi_setup_cmd_retry()
        - move from local eh_work_q to local eh_done_q
     LOCKING: none
+    CONCURRENCY: at most one thread per separate eh_work_q to
+                keep queue manipulation lockless
 
  4. EH completes
     ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper
-           layer of failure.
+           layer of failure. May be called concurrently but must have
+           a no more than one thread per separate eh_work_q to
+           manipulate the queue locklessly
        - scmd is removed from eh_done_q and scmd->eh_entry is cleared
        - if retry is necessary, scmd is requeued using
           scsi_queue_insert()
        - otherwise, scsi_finish_command() is invoked for scmd
+       - zero shost->host_failed
     LOCKING: queue or finish function performs appropriate locking
 
 

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 063036d876b0a896dc4438f0cd4b6562ce7b29bb..126eb86f239fd0faca27eea628a9305096d1a93c 100644 (file)
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -604,7 +604,7 @@ void ata_scsi_error(struct Scsi_Host *host)
        ata_scsi_port_error_handler(host, ap);
 
        /* finish or retry handled scmd's and clean up */
-       WARN_ON(host->host_failed || !list_empty(&eh_work_q));
+       WARN_ON(!list_empty(&eh_work_q));
 
        DPRINTK("EXIT\n");
 }

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 9acbc885239b3e4a659535b8e9bc2dcbb6afe355..5ba69ea8eb92e9c80e19980f0b88e31b124b87d5 100644 (file)
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -898,7 +898,6 @@ static int scsi_request_sense(struct scsi_cmnd *scmd)
  */
 void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q)
 {
-       scmd->device->host->host_failed--;
        scmd->eh_eflags = 0;
        list_move_tail(&scmd->eh_entry, done_q);
 }
@@ -1892,6 +1891,9 @@ int scsi_error_handler(void *data)
                else
                        scsi_unjam_host(shost);
 
+               /* All scmds have been handled */
+               shost->host_failed = 0;
+
                /*
                 * Note - if the above fails completely, the action is to take
                 * individual devices offline and flush the queue of any