bnxt_en: Do not send firmware messages if firmware is in error state.

Add a flag to mark that the firmware has encountered fatal condition.
The driver will not send any more firmware messages and will return
error to the caller.  Fix up some clean up functions to continue
and not abort when the firmware message function returns error.

This is preparation work to fully handle firmware error recovery
under fatal conditions.

Signed-off-by: Michael Chan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: Michael Chan

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -4173,6 +4173,9 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
 	u16 dst = BNXT_HWRM_CHNL_CHIMP;
 
+	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+		return -EBUSY;
+
 	if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
 		if (msg_len > bp->hwrm_max_ext_req_len ||
 		    !bp->hwrm_short_cmd_req_addr)
@@ -5042,8 +5045,6 @@ static int bnxt_hwrm_vnic_free_one(struct bnxt *bp, u16 vnic_id)
 			cpu_to_le32(bp->vnic_info[vnic_id].fw_vnic_id);
 
 		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-		if (rc)
-			return rc;
 		bp->vnic_info[vnic_id].fw_vnic_id = INVALID_HW_RING_ID;
 	}
 	return rc;
@@ -5183,8 +5184,6 @@ static int bnxt_hwrm_ring_grp_free(struct bnxt *bp)
 
 		rc = _hwrm_send_message(bp, &req, sizeof(req),
 					HWRM_CMD_TIMEOUT);
-		if (rc)
-			break;
 		bp->grp_info[i].fw_grp_id = INVALID_HW_RING_ID;
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
@@ -5503,6 +5502,9 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp,
 	struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr;
 	u16 error_code;
 
+	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+		return 0;
+
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1);
 	req.ring_type = ring_type;
 	req.ring_id = cpu_to_le16(ring->fw_ring_id);
@@ -6300,8 +6302,6 @@ static int bnxt_hwrm_stat_ctx_free(struct bnxt *bp)
 
 			rc = _hwrm_send_message(bp, &req, sizeof(req),
 						HWRM_CMD_TIMEOUT);
-			if (rc)
-				break;
 
 			cpr->hw_stats_ctx_id = INVALID_STATS_CTX_ID;
 		}
@@ -7415,6 +7415,8 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa)
 
 	if (set_tpa)
 		tpa_flags = bp->flags & BNXT_FLAG_TPA;
+	else if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+		return 0;
 	for (i = 0; i < bp->nr_vnics; i++) {
 		rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
 		if (rc) {
@@ -10009,7 +10011,8 @@ void bnxt_fw_reset(struct bnxt *bp)
 	if (test_bit(BNXT_STATE_OPEN, &bp->state) &&
 	    !test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-		if (BNXT_PF(bp) && bp->pf.active_vfs) {
+		if (BNXT_PF(bp) && bp->pf.active_vfs &&
+		    !test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) {
 			rc = bnxt_hwrm_func_qcfg(bp);
 			if (rc) {
 				netdev_err(bp->dev, "Firmware reset aborted, first func_qcfg cmd failed, rc = %d\n",
@@ -10439,6 +10442,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		bnxt_queue_fw_reset_work(bp, bp->fw_reset_min_dsecs * HZ / 10);
 		return;
 	case BNXT_FW_RESET_STATE_ENABLE_DEV:
+		clear_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
 		if (pci_enable_device(bp->pdev)) {
 			netdev_err(bp->dev, "Cannot re-enable PCI device\n");
 			goto fw_reset_abort;

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -1617,6 +1617,7 @@ struct bnxt {
 #define BNXT_STATE_FW_RESET_DET 3
 #define BNXT_STATE_IN_FW_RESET	4
 #define BNXT_STATE_ABORT_ERR	5
+#define BNXT_STATE_FW_FATAL_COND	6
 
 	struct bnxt_irq	*irq_tbl;
 	int			total_irqs;