[dpdk-dev] [PATCH 10/16] net/ice/base: handle critical FW error

[Qi Zhang <qi.z.zhang@intel.com>]

A race condition between FW and SW can occur between admin queue setup and
the first command sent. A link event may occur and FW attempts to notify a
non-existent queue. FW will set the critical error bit and disable the
queue. When this happens retry queue setup.

Signed-off-by: Evan Swanson <evan.swanson@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
---
 drivers/net/ice/base/ice_controlq.c | 128 +++++++++++++++++++++---------------
 drivers/net/ice/base/ice_controlq.h |   3 +
 drivers/net/ice/base/ice_status.h   |   1 +
 3 files changed, 78 insertions(+), 54 deletions(-)

diff --git a/drivers/net/ice/base/ice_controlq.c b/drivers/net/ice/base/ice_controlq.c
index 0fcf62e20..41c8c7e05 100644
--- a/drivers/net/ice/base/ice_controlq.c
+++ b/drivers/net/ice/base/ice_controlq.c
@@ -13,6 +13,7 @@ do {								\
 	(qinfo)->sq.bal = prefix##_ATQBAL;			\
 	(qinfo)->sq.len_mask = prefix##_ATQLEN_ATQLEN_M;	\
 	(qinfo)->sq.len_ena_mask = prefix##_ATQLEN_ATQENABLE_M;	\
+	(qinfo)->sq.len_crit_mask = prefix##_ATQLEN_ATQCRIT_M;	\
 	(qinfo)->sq.head_mask = prefix##_ATQH_ATQH_M;		\
 	(qinfo)->rq.head = prefix##_ARQH;			\
 	(qinfo)->rq.tail = prefix##_ARQT;			\
@@ -21,6 +22,7 @@ do {								\
 	(qinfo)->rq.bal = prefix##_ARQBAL;			\
 	(qinfo)->rq.len_mask = prefix##_ARQLEN_ARQLEN_M;	\
 	(qinfo)->rq.len_ena_mask = prefix##_ARQLEN_ARQENABLE_M;	\
+	(qinfo)->rq.len_crit_mask = prefix##_ARQLEN_ARQCRIT_M;	\
 	(qinfo)->rq.head_mask = prefix##_ARQH_ARQH_M;		\
 } while (0)
 
@@ -610,6 +612,53 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
 }
 
 /**
+ * ice_shutdown_ctrlq - shutdown routine for any control queue
+ * @hw: pointer to the hardware structure
+ * @q_type: specific Control queue type
+ *
+ * NOTE: this function does not destroy the control queue locks.
+ */
+static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
+{
+	struct ice_ctl_q_info *cq;
+
+	ice_debug(hw, ICE_DBG_TRACE, "%s\n", __func__);
+
+	switch (q_type) {
+	case ICE_CTL_Q_ADMIN:
+		cq = &hw->adminq;
+		if (ice_check_sq_alive(hw, cq))
+			ice_aq_q_shutdown(hw, true);
+		break;
+	case ICE_CTL_Q_MAILBOX:
+		cq = &hw->mailboxq;
+		break;
+	default:
+		return;
+	}
+
+	ice_shutdown_sq(hw, cq);
+	ice_shutdown_rq(hw, cq);
+}
+
+/**
+ * ice_shutdown_all_ctrlq - shutdown routine for all control queues
+ * @hw: pointer to the hardware structure
+ *
+ * NOTE: this function does not destroy the control queue locks. The driver
+ * may call this at runtime to shutdown and later restart control queues, such
+ * as in response to a reset event.
+ */
+void ice_shutdown_all_ctrlq(struct ice_hw *hw)
+{
+	ice_debug(hw, ICE_DBG_TRACE, "%s\n", __func__);
+	/* Shutdown FW admin queue */
+	ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN);
+	/* Shutdown PF-VF Mailbox */
+	ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX);
+}
+
+/**
  * ice_init_all_ctrlq - main initialization routine for all control queues
  * @hw: pointer to the hardware structure
  *
@@ -625,15 +674,26 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
 enum ice_status ice_init_all_ctrlq(struct ice_hw *hw)
 {
 	enum ice_status status;
+	u32 retry = 0;
 
 	ice_debug(hw, ICE_DBG_TRACE, "%s\n", __func__);
 
 	/* Init FW admin queue */
-	status = ice_init_ctrlq(hw, ICE_CTL_Q_ADMIN);
-	if (status)
-		return status;
+	do {
+		status = ice_init_ctrlq(hw, ICE_CTL_Q_ADMIN);
+		if (status)
+			return status;
+
+		status = ice_init_check_adminq(hw);
+		if (status != ICE_ERR_AQ_FW_CRITICAL)
+			break;
+
+		ice_debug(hw, ICE_DBG_AQ_MSG,
+			  "Retry Admin Queue init due to FW critical error\n");
+		ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN);
+		ice_msec_delay(ICE_CTL_Q_ADMIN_INIT_MSEC, true);
+	} while (retry++ < ICE_CTL_Q_ADMIN_INIT_TIMEOUT);
 
-	status = ice_init_check_adminq(hw);
 	if (status)
 		return status;
 	/* Init Mailbox queue */
@@ -677,53 +737,6 @@ enum ice_status ice_create_all_ctrlq(struct ice_hw *hw)
 }
 
 /**
- * ice_shutdown_ctrlq - shutdown routine for any control queue
- * @hw: pointer to the hardware structure
- * @q_type: specific Control queue type
- *
- * NOTE: this function does not destroy the control queue locks.
- */
-static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
-{
-	struct ice_ctl_q_info *cq;
-
-	ice_debug(hw, ICE_DBG_TRACE, "%s\n", __func__);
-
-	switch (q_type) {
-	case ICE_CTL_Q_ADMIN:
-		cq = &hw->adminq;
-		if (ice_check_sq_alive(hw, cq))
-			ice_aq_q_shutdown(hw, true);
-		break;
-	case ICE_CTL_Q_MAILBOX:
-		cq = &hw->mailboxq;
-		break;
-	default:
-		return;
-	}
-
-	ice_shutdown_sq(hw, cq);
-	ice_shutdown_rq(hw, cq);
-}
-
-/**
- * ice_shutdown_all_ctrlq - shutdown routine for all control queues
- * @hw: pointer to the hardware structure
- *
- * NOTE: this function does not destroy the control queue locks. The driver
- * may call this at runtime to shutdown and later restart control queues, such
- * as in response to a reset event.
- */
-void ice_shutdown_all_ctrlq(struct ice_hw *hw)
-{
-	ice_debug(hw, ICE_DBG_TRACE, "%s\n", __func__);
-	/* Shutdown FW admin queue */
-	ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN);
-	/* Shutdown PF-VF Mailbox */
-	ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX);
-}
-
-/**
  * ice_destroy_ctrlq_locks - Destroy locks for a control queue
  * @cq: pointer to the control queue
  *
@@ -1025,9 +1038,16 @@ ice_sq_send_cmd_nolock(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 
 	/* update the error if time out occurred */
 	if (!cmd_completed) {
-		ice_debug(hw, ICE_DBG_AQ_MSG,
-			  "Control Send Queue Writeback timeout.\n");
-		status = ICE_ERR_AQ_TIMEOUT;
+		if (rd32(hw, cq->rq.len) & cq->rq.len_crit_mask ||
+		    rd32(hw, cq->sq.len) & cq->sq.len_crit_mask) {
+			ice_debug(hw, ICE_DBG_AQ_MSG,
+				  "Critical FW error.\n");
+			status = ICE_ERR_AQ_FW_CRITICAL;
+		} else {
+			ice_debug(hw, ICE_DBG_AQ_MSG,
+				  "Control Send Queue Writeback timeout.\n");
+			status = ICE_ERR_AQ_TIMEOUT;
+		}
 	}
 
 sq_send_command_error:
diff --git a/drivers/net/ice/base/ice_controlq.h b/drivers/net/ice/base/ice_controlq.h
index 464a2adb7..f47fd4346 100644
--- a/drivers/net/ice/base/ice_controlq.h
+++ b/drivers/net/ice/base/ice_controlq.h
@@ -35,6 +35,8 @@ enum ice_ctl_q {
 /* Control Queue timeout settings - max delay 250ms */
 #define ICE_CTL_Q_SQ_CMD_TIMEOUT	2500  /* Count 2500 times */
 #define ICE_CTL_Q_SQ_CMD_USEC		100   /* Check every 100usec */
+#define ICE_CTL_Q_ADMIN_INIT_TIMEOUT	10    /* Count 10 times */
+#define ICE_CTL_Q_ADMIN_INIT_MSEC	100   /* Check every 100msec */
 
 struct ice_ctl_q_ring {
 	void *dma_head;			/* Virtual address to DMA head */
@@ -60,6 +62,7 @@ struct ice_ctl_q_ring {
 	u32 bal;
 	u32 len_mask;
 	u32 len_ena_mask;
+	u32 len_crit_mask;
 	u32 head_mask;
 };
 
diff --git a/drivers/net/ice/base/ice_status.h b/drivers/net/ice/base/ice_status.h
index 7bcccd39a..446702f9a 100644
--- a/drivers/net/ice/base/ice_status.h
+++ b/drivers/net/ice/base/ice_status.h
@@ -42,6 +42,7 @@ enum ice_status {
 	ICE_ERR_AQ_FULL				= -102,
 	ICE_ERR_AQ_NO_WORK			= -103,
 	ICE_ERR_AQ_EMPTY			= -104,
+	ICE_ERR_AQ_FW_CRITICAL			= -105,
 };
 
 #endif /* _ICE_STATUS_H_ */
-- 
2.13.6