libiscsi: don't run scsi eh if iscsi task is making progress

If we are sending or receiving data for the task successfully do
not run the scsi eh, because we know the task is making progress.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>

3 files changed, 57 insertions, 15 deletions

diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 59908aead531..b55b7991d5fa 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -954,6 +954,7 @@ int __iscsi_complete_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
                 task = iscsi_itt_to_ctask(conn, hdr->itt);
                 if (!task)
                         return ISCSI_ERR_BAD_ITT;
+                task->last_xfer = jiffies;
                 break;
         case ISCSI_OP_R2T:
                 /*
@@ -1192,10 +1193,12 @@ static int iscsi_xmit_task(struct iscsi_conn *conn)
         spin_unlock_bh(&conn->session->lock);
         rc = conn->session->tt->xmit_task(task);
         spin_lock_bh(&conn->session->lock);
-        __iscsi_put_task(task);
-        if (!rc)
+        if (!rc) {
                 /* done with this task */
+                task->last_xfer = jiffies;
                 conn->task = NULL;
+        }
+        __iscsi_put_task(task);
         return rc;
 }
 
@@ -1361,6 +1364,9 @@ static inline struct iscsi_task *iscsi_alloc_task(struct iscsi_conn *conn,
         task->state = ISCSI_TASK_PENDING;
         task->conn = conn;
         task->sc = sc;
+        task->have_checked_conn = false;
+        task->last_timeout = jiffies;
+        task->last_xfer = jiffies;
         INIT_LIST_HEAD(&task->running);
         return task;
 }
@@ -1716,17 +1722,18 @@ static int iscsi_has_ping_timed_out(struct iscsi_conn *conn)
                 return 0;
 }
 
-static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *scmd)
+static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 {
+        enum blk_eh_timer_return rc = BLK_EH_NOT_HANDLED;
+        struct iscsi_task *task = NULL;
         struct iscsi_cls_session *cls_session;
         struct iscsi_session *session;
         struct iscsi_conn *conn;
-        enum blk_eh_timer_return rc = BLK_EH_NOT_HANDLED;
 
-        cls_session = starget_to_session(scsi_target(scmd->device));
+        cls_session = starget_to_session(scsi_target(sc->device));
         session = cls_session->dd_data;
 
-        ISCSI_DBG_SESSION(session, "scsi cmd %p timedout\n", scmd);
+        ISCSI_DBG_SESSION(session, "scsi cmd %p timedout\n", sc);
 
         spin_lock(&session->lock);
         if (session->state != ISCSI_STATE_LOGGED_IN) {
@@ -1745,6 +1752,26 @@ static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *scmd)
                 goto done;
         }
 
+        task = (struct iscsi_task *)sc->SCp.ptr;
+        if (!task)
+                goto done;
+        /*
+         * If we have sent (at least queued to the network layer) a pdu or
+         * recvd one for the task since the last timeout ask for
+         * more time. If on the next timeout we have not made progress
+         * we can check if it is the task or connection when we send the
+         * nop as a ping.
+         */
+        if (time_after_eq(task->last_xfer, task->last_timeout)) {
+                ISCSI_DBG_CONN(conn, "Command making progress. Asking "
+                               "scsi-ml for more time to complete. "
+                               "Last data recv at %lu. Last timeout was at "
+                               "%lu\n.", task->last_xfer, task->last_timeout);
+                task->have_checked_conn = false;
+                rc = BLK_EH_RESET_TIMER;
+                goto done;
+        }
+
         if (!conn->recv_timeout && !conn->ping_timeout)
                 goto done;
         /*
@@ -1755,20 +1782,29 @@ static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *scmd)
                 rc = BLK_EH_RESET_TIMER;
                 goto done;
         }
+
+        /* Assumes nop timeout is shorter than scsi cmd timeout */
+        if (task->have_checked_conn)
+                goto done;
+
         /*
-         * if we are about to check the transport then give the command
-         * more time
+         * Checking the transport already or nop from a cmd timeout still
+         * running
          */
-        if (time_before_eq(conn->last_recv + (conn->recv_timeout * HZ),
-                           jiffies)) {
+        if (conn->ping_task) {
+                task->have_checked_conn = true;
                 rc = BLK_EH_RESET_TIMER;
                 goto done;
         }
 
-        /* if in the middle of checking the transport then give us more time */
-        if (conn->ping_task)
-                rc = BLK_EH_RESET_TIMER;
+        /* Make sure there is a transport check done */
+        iscsi_send_nopout(conn, NULL);
+        task->have_checked_conn = true;
+        rc = BLK_EH_RESET_TIMER;
+
 done:
+        if (task)
+                task->last_timeout = jiffies;
         spin_unlock(&session->lock);
         ISCSI_DBG_SESSION(session, "return %s\n", rc == BLK_EH_RESET_TIMER ?
                           "timer reset" : "nh");
diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c
index 2bc07090321d..2e0746d70303 100644
--- a/drivers/scsi/libiscsi_tcp.c
+++ b/drivers/scsi/libiscsi_tcp.c
@@ -686,6 +686,7 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr)
                                      "offset=%d, datalen=%d)\n",
                                       tcp_task->data_offset,
                                       tcp_conn->in.datalen);
+                        task->last_xfer = jiffies;
                         rc = iscsi_segment_seek_sg(&tcp_conn->in.segment,
                                                    sdb->table.sgl,
                                                    sdb->table.nents,
@@ -713,9 +714,10 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr)
                         rc = ISCSI_ERR_BAD_ITT;
                 else if (ahslen)
                         rc = ISCSI_ERR_AHSLEN;
-                else if (task->sc->sc_data_direction == DMA_TO_DEVICE)
+                else if (task->sc->sc_data_direction == DMA_TO_DEVICE) {
+                        task->last_xfer = jiffies;
                         rc = iscsi_tcp_r2t_rsp(conn, task);
-                else
+                } else
                         rc = ISCSI_ERR_PROTO;
                 spin_unlock(&conn->session->lock);
                 break;
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 196525cd402f..61afeb59a836 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -125,6 +125,10 @@ struct iscsi_task {
         struct scsi_cmnd        *sc;            /* associated SCSI cmd*/
         struct iscsi_conn       *conn;          /* used connection    */
 
+        /* data processing tracking */
+        unsigned long           last_xfer;
+        unsigned long           last_timeout;
+        bool                    have_checked_conn;
         /* state set/tested under session->lock */
         int                     state;
         atomic_t                refcount;