[net PATCH 3/4] fbnic: Handle FW mailbox completions flagged with an error

@@ -1216,6 +1216,10 @@ enum {
 #define FBNIC_IPC_MBX_DESC_LEN_MASK	DESC_GENMASK(63, 48)
 #define FBNIC_IPC_MBX_DESC_EOM		DESC_BIT(46)
 #define FBNIC_IPC_MBX_DESC_ADDR_MASK	DESC_GENMASK(45, 3)
+/* Set with FW_CMPL when the FW completed a descriptor without successfully
+ * processing it (e.g. a mailbox DMA error); the completion has no valid data.
+ */
+#define FBNIC_IPC_MBX_DESC_FW_ERR	DESC_BIT(2)
 #define FBNIC_IPC_MBX_DESC_FW_CMPL	DESC_BIT(1)
 #define FBNIC_IPC_MBX_DESC_HOST_CMPL	DESC_BIT(0)
 

@@ -539,8 +539,8 @@ static void fbnic_dbg_fw_mbx_display(struct seq_file *s,
 	/* Generate header */
 	seq_puts(s, mbx_idx == FBNIC_IPC_MBX_RX_IDX ? "Rx\n" : "Tx\n");
 
-	seq_printf(s, "Rdy: %d Head: %d Tail: %d\n",
-		   mbx->ready, mbx->head, mbx->tail);
+	seq_printf(s, "Rdy: %d Head: %d Tail: %d resp_error: %lld\n",
+		   mbx->ready, mbx->head, mbx->tail, mbx->resp_error);
 
 	snprintf(hdr, sizeof(hdr), "%3s %-4s %s %-12s %s %-3s %-16s\n",
 		 "Idx", "Len", "E", "Addr", "F", "H", "Raw");

@@ -291,6 +291,12 @@ static void fbnic_mbx_process_tx_msgs(struct fbnic_dev *fbd)
 		if (!(desc & FBNIC_IPC_MBX_DESC_FW_CMPL))
 			break;
 
+		if (desc & FBNIC_IPC_MBX_DESC_FW_ERR) {
+			tx_mbx->resp_error++;
+			dev_warn(fbd->dev,
+				 "FW completed a Tx mailbox request with an error\n");
+		}
+
 		fbnic_mbx_unmap_and_free_msg(fbd, FBNIC_IPC_MBX_TX_IDX, head);
 
 		head++;

@@ -1672,6 +1678,13 @@ static void fbnic_mbx_process_rx_msgs(struct fbnic_dev *fbd)
 		if (!(desc & FBNIC_IPC_MBX_DESC_FW_CMPL))
 			break;
 
+		if (desc & FBNIC_IPC_MBX_DESC_FW_ERR) {
+			rx_mbx->resp_error++;
+			dev_warn(fbd->dev,
+				 "FW reported an error on an Rx mailbox message; dropping\n");
+			goto next_page;
+		}
+
 		dma_sync_single_for_cpu(fbd->dev, rx_mbx->buf_info[head].addr,
 					FBNIC_RX_PAGE_SIZE, DMA_FROM_DEVICE);
 

@@ -1740,6 +1753,7 @@ int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 {
 	struct fbnic_fw_mbx *tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
 	unsigned long timeout = jiffies + 10 * HZ + 1;
+	u64 resp_error;
 	int err, i;
 
 	do {

@@ -1770,6 +1784,8 @@ int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 	 * mgmt.version once we get the actual version from the firmware
 	 * in the capabilities request message.
 	 */
+send_cap_req:
+	resp_error = tx_mbx->resp_error;
 	err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
 	if (err)
 		goto clean_mbx;

@@ -1788,8 +1804,17 @@ int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 		fbnic_mbx_poll(fbd);
 
 		/* set err, but wait till mgmt.version check to report it */
-		if (!time_is_after_jiffies(timeout))
+		if (!time_is_after_jiffies(timeout)) {
 			err = -ETIMEDOUT;
+			continue;
+		}
+
+		/* If the FW completed our capabilities request with an error
+		 * (FW_ERR) it produced no response; the ring is not wedged, so
+		 * re-issue the request instead of timing out.
+		 */
+		if (tx_mbx->resp_error != resp_error)
+			goto send_cap_req;
 	}
 
 	return 0;

@@ -13,6 +13,7 @@ struct fbnic_tlv_msg;
 
 struct fbnic_fw_mbx {
 	u8 ready, head, tail;
+	u64 resp_error;
 	struct {
 		struct fbnic_tlv_msg	*msg;
 		dma_addr_t		addr;