3 files changed, 10 insertions, 4 deletions

diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index 8638f61c8c9d..37eca00796ee 100644
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -263,19 +263,23 @@ 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 961acc788f44..91a9e6af2ec4 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -606,7 +606,7 @@ 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 984ddcb4786d..1b9c049bd5c5 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1127,7 +1127,6 @@ static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn)
  */
 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);
 }
@@ -2226,6 +2225,9 @@ 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