Merge branch 'bnxt_en-health-and-error-recovery'

Michael Chan says:

====================
bnxt_en: health and error recovery.

This patchset implements adapter health and error recovery.  The status
is reported through several devlink reporters and the driver will
initiate and complete the recovery process using the devlink infrastructure.

v2: Added 4 patches at the beginning of the patchset to clean up error code
    handling related to firmware messages and to convert to use standard
    error codes.

    Removed the dropping of rtnl_lock in bnxt_close().

    Broke up the patches some more for better patch organization and
    future bisection.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -254,6 +254,8 @@ static const u16 bnxt_async_events_arr[] = {
 	ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED,
 	ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE,
 	ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE,
+	ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY,
+	ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY,
 };
 
 static struct workqueue_struct *bnxt_pf_wq;
@@ -1138,6 +1140,14 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	return 0;
 }
 
+static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay)
+{
+	if (BNXT_PF(bp))
+		queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay);
+	else
+		schedule_delayed_work(&bp->fw_reset_task, delay);
+}
+
 static void bnxt_queue_sp_work(struct bnxt *bp)
 {
 	if (BNXT_PF(bp))
@@ -1896,6 +1906,33 @@ static int bnxt_force_rx_discard(struct bnxt *bp,
 	return bnxt_rx_pkt(bp, cpr, raw_cons, event);
 }
 
+u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx)
+{
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	u32 reg = fw_health->regs[reg_idx];
+	u32 reg_type, reg_off, val = 0;
+
+	reg_type = BNXT_FW_HEALTH_REG_TYPE(reg);
+	reg_off = BNXT_FW_HEALTH_REG_OFF(reg);
+	switch (reg_type) {
+	case BNXT_FW_HEALTH_REG_TYPE_CFG:
+		pci_read_config_dword(bp->pdev, reg_off, &val);
+		break;
+	case BNXT_FW_HEALTH_REG_TYPE_GRC:
+		reg_off = fw_health->mapped_regs[reg_idx];
+		/* fall through */
+	case BNXT_FW_HEALTH_REG_TYPE_BAR0:
+		val = readl(bp->bar0 + reg_off);
+		break;
+	case BNXT_FW_HEALTH_REG_TYPE_BAR1:
+		val = readl(bp->bar1 + reg_off);
+		break;
+	}
+	if (reg_idx == BNXT_FW_RESET_INPROG_REG)
+		val &= fw_health->fw_reset_inprog_reg_mask;
+	return val;
+}
+
 #define BNXT_GET_EVENT_PORT(data)	\
 	((data) &			\
 	 ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_MASK)
@@ -1951,6 +1988,55 @@ static int bnxt_async_event_process(struct bnxt *bp,
 			goto async_event_process_exit;
 		set_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event);
 		break;
+	case ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY: {
+		u32 data1 = le32_to_cpu(cmpl->event_data1);
+
+		bp->fw_reset_timestamp = jiffies;
+		bp->fw_reset_min_dsecs = cmpl->timestamp_lo;
+		if (!bp->fw_reset_min_dsecs)
+			bp->fw_reset_min_dsecs = BNXT_DFLT_FW_RST_MIN_DSECS;
+		bp->fw_reset_max_dsecs = le16_to_cpu(cmpl->timestamp_hi);
+		if (!bp->fw_reset_max_dsecs)
+			bp->fw_reset_max_dsecs = BNXT_DFLT_FW_RST_MAX_DSECS;
+		if (EVENT_DATA1_RESET_NOTIFY_FATAL(data1)) {
+			netdev_warn(bp->dev, "Firmware fatal reset event received\n");
+			set_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
+		} else {
+			netdev_warn(bp->dev, "Firmware non-fatal reset event received, max wait time %d msec\n",
+				    bp->fw_reset_max_dsecs * 100);
+		}
+		set_bit(BNXT_FW_RESET_NOTIFY_SP_EVENT, &bp->sp_event);
+		break;
+	}
+	case ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY: {
+		struct bnxt_fw_health *fw_health = bp->fw_health;
+		u32 data1 = le32_to_cpu(cmpl->event_data1);
+
+		if (!fw_health)
+			goto async_event_process_exit;
+
+		fw_health->enabled = EVENT_DATA1_RECOVERY_ENABLED(data1);
+		fw_health->master = EVENT_DATA1_RECOVERY_MASTER_FUNC(data1);
+		if (!fw_health->enabled)
+			break;
+
+		if (netif_msg_drv(bp))
+			netdev_info(bp->dev, "Error recovery info: error recovery[%d], master[%d], reset count[0x%x], health status: 0x%x\n",
+				    fw_health->enabled, fw_health->master,
+				    bnxt_fw_health_readl(bp,
+							 BNXT_FW_RESET_CNT_REG),
+				    bnxt_fw_health_readl(bp,
+							 BNXT_FW_HEALTH_REG));
+		fw_health->tmr_multiplier =
+			DIV_ROUND_UP(fw_health->polling_dsecs * HZ,
+				     bp->current_interval * 10);
+		fw_health->tmr_counter = fw_health->tmr_multiplier;
+		fw_health->last_fw_heartbeat =
+			bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG);
+		fw_health->last_fw_reset_cnt =
+			bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG);
+		goto async_event_process_exit;
+	}
 	default:
 		goto async_event_process_exit;
 	}
@@ -3555,6 +3641,9 @@ static int bnxt_alloc_kong_hwrm_resources(struct bnxt *bp)
 {
 	struct pci_dev *pdev = bp->pdev;
 
+	if (bp->hwrm_cmd_kong_resp_addr)
+		return 0;
+
 	bp->hwrm_cmd_kong_resp_addr =
 		dma_alloc_coherent(&pdev->dev, PAGE_SIZE,
 				   &bp->hwrm_cmd_kong_resp_dma_addr,
@@ -3594,6 +3683,9 @@ static int bnxt_alloc_hwrm_short_cmd_req(struct bnxt *bp)
 {
 	struct pci_dev *pdev = bp->pdev;
 
+	if (bp->hwrm_short_cmd_req_addr)
+		return 0;
+
 	bp->hwrm_short_cmd_req_addr =
 		dma_alloc_coherent(&pdev->dev, bp->hwrm_max_ext_req_len,
 				   &bp->hwrm_short_cmd_req_dma_addr,
@@ -4048,6 +4140,32 @@ void bnxt_hwrm_cmd_hdr_init(struct bnxt *bp, void *request, u16 req_type,
 		req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr);
 }
 
+static int bnxt_hwrm_to_stderr(u32 hwrm_err)
+{
+	switch (hwrm_err) {
+	case HWRM_ERR_CODE_SUCCESS:
+		return 0;
+	case HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED:
+		return -EACCES;
+	case HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR:
+		return -ENOSPC;
+	case HWRM_ERR_CODE_INVALID_PARAMS:
+	case HWRM_ERR_CODE_INVALID_FLAGS:
+	case HWRM_ERR_CODE_INVALID_ENABLES:
+	case HWRM_ERR_CODE_UNSUPPORTED_TLV:
+	case HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR:
+		return -EINVAL;
+	case HWRM_ERR_CODE_NO_BUFFER:
+		return -ENOMEM;
+	case HWRM_ERR_CODE_HOT_RESET_PROGRESS:
+		return -EAGAIN;
+	case HWRM_ERR_CODE_CMD_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	default:
+		return -EIO;
+	}
+}
+
 static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 				 int timeout, bool silent)
 {
@@ -4065,6 +4183,9 @@ 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)
@@ -4129,6 +4250,9 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	/* Ring channel doorbell */
 	writel(1, bp->bar0 + doorbell_offset);
 
+	if (!pci_is_enabled(bp->pdev))
+		return 0;
+
 	if (!timeout)
 		timeout = DFLT_HWRM_CMD_TIMEOUT;
 	/* convert timeout to usec */
@@ -4160,9 +4284,10 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 		}
 
 		if (bp->hwrm_intr_seq_id != (u16)~seq_id) {
-			netdev_err(bp->dev, "Resp cmpl intr err msg: 0x%x\n",
-				   le16_to_cpu(req->req_type));
-			return -1;
+			if (!silent)
+				netdev_err(bp->dev, "Resp cmpl intr err msg: 0x%x\n",
+					   le16_to_cpu(req->req_type));
+			return -EBUSY;
 		}
 		len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >>
 		      HWRM_RESP_LEN_SFT;
@@ -4186,11 +4311,12 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 		}
 
 		if (i >= tmo_count) {
-			netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d\n",
-				   HWRM_TOTAL_TIMEOUT(i),
-				   le16_to_cpu(req->req_type),
-				   le16_to_cpu(req->seq_id), len);
-			return -1;
+			if (!silent)
+				netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d\n",
+					   HWRM_TOTAL_TIMEOUT(i),
+					   le16_to_cpu(req->req_type),
+					   le16_to_cpu(req->seq_id), len);
+			return -EBUSY;
 		}
 
 		/* Last byte of resp contains valid bit */
@@ -4204,11 +4330,13 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 		}
 
 		if (j >= HWRM_VALID_BIT_DELAY_USEC) {
-			netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d v:%d\n",
-				   HWRM_TOTAL_TIMEOUT(i),
-				   le16_to_cpu(req->req_type),
-				   le16_to_cpu(req->seq_id), len, *valid);
-			return -1;
+			if (!silent)
+				netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d v:%d\n",
+					   HWRM_TOTAL_TIMEOUT(i),
+					   le16_to_cpu(req->req_type),
+					   le16_to_cpu(req->seq_id), len,
+					   *valid);
+			return -EBUSY;
 		}
 	}
 
@@ -4222,7 +4350,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 		netdev_err(bp->dev, "hwrm req_type 0x%x seq id 0x%x error 0x%x\n",
 			   le16_to_cpu(resp->req_type),
 			   le16_to_cpu(resp->seq_id), rc);
-	return rc;
+	return bnxt_hwrm_to_stderr(rc);
 }
 
 int _hwrm_send_message(struct bnxt *bp, void *msg, u32 msg_len, int timeout)
@@ -4271,9 +4399,14 @@ int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
 		cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD);
 
 	memset(async_events_bmap, 0, sizeof(async_events_bmap));
-	for (i = 0; i < ARRAY_SIZE(bnxt_async_events_arr); i++)
-		__set_bit(bnxt_async_events_arr[i], async_events_bmap);
+	for (i = 0; i < ARRAY_SIZE(bnxt_async_events_arr); i++) {
+		u16 event_id = bnxt_async_events_arr[i];
 
+		if (event_id == ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY &&
+		    !(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY))
+			continue;
+		__set_bit(bnxt_async_events_arr[i], async_events_bmap);
+	}
 	if (bmap && bmap_size) {
 		for (i = 0; i < bmap_size; i++) {
 			if (test_bit(i, bmap))
@@ -4291,6 +4424,7 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 {
 	struct hwrm_func_drv_rgtr_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_func_drv_rgtr_input req = {0};
+	u32 flags;
 	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_RGTR, -1, -1);
@@ -4300,7 +4434,11 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 			    FUNC_DRV_RGTR_REQ_ENABLES_VER);
 
 	req.os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX);
-	req.flags = cpu_to_le32(FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE);
+	flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE |
+		FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT;
+	if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)
+		flags |= FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT;
+	req.flags = cpu_to_le32(flags);
 	req.ver_maj_8b = DRV_VER_MAJ;
 	req.ver_min_8b = DRV_VER_MIN;
 	req.ver_upd_8b = DRV_VER_UPD;
@@ -4335,10 +4473,8 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
-		rc = -EIO;
-	else if (resp->flags &
-		 cpu_to_le32(FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED))
+	if (!rc && (resp->flags &
+		    cpu_to_le32(FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED)))
 		bp->fw_cap |= BNXT_FW_CAP_IF_CHANGE;
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -4761,7 +4897,7 @@ static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, u16 vnic_id, bool set_rss)
 		}
 		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 		if (rc)
-			return -EIO;
+			return rc;
 	}
 	return 0;
 }
@@ -4924,8 +5060,6 @@ 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;
@@ -4986,6 +5120,7 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 	int rc;
 
 	bp->hw_ring_stats_size = sizeof(struct ctx_hw_stats);
+	bp->flags &= ~(BNXT_FLAG_NEW_RSS_CAP | BNXT_FLAG_ROCE_MIRROR_CAP);
 	if (bp->hwrm_spec_code < 0x10600)
 		return 0;
 
@@ -5064,8 +5199,6 @@ 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);
@@ -5384,6 +5517,9 @@ 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);
@@ -5521,7 +5657,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc) {
 		mutex_unlock(&bp->hwrm_cmd_lock);
-		return -EIO;
+		return rc;
 	}
 
 	hw_resc->resv_tx_rings = le16_to_cpu(resp->alloc_tx_rings);
@@ -5685,7 +5821,7 @@ bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
-		return -ENOMEM;
+		return rc;
 
 	if (bp->hwrm_spec_code < 0x10601)
 		bp->hw_resc.resv_tx_rings = tx_rings;
@@ -5710,7 +5846,7 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 				     cp_rings, stats, vnics);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
-		return -ENOMEM;
+		return rc;
 
 	rc = bnxt_hwrm_get_rings(bp);
 	return rc;
@@ -5891,9 +6027,7 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 
 	req.flags = cpu_to_le32(flags);
 	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
-		return -ENOMEM;
-	return 0;
+	return rc;
 }
 
 static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
@@ -5921,9 +6055,7 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 
 	req.flags = cpu_to_le32(flags);
 	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
-		return -ENOMEM;
-	return 0;
+	return rc;
 }
 
 static int bnxt_hwrm_check_rings(struct bnxt *bp, int tx_rings, int rx_rings,
@@ -6185,8 +6317,6 @@ 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;
 		}
@@ -6248,6 +6378,8 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 		struct bnxt_vf_info *vf = &bp->vf;
 
 		vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK;
+	} else {
+		bp->pf.registered_vfs = le16_to_cpu(resp->registered_vfs);
 	}
 #endif
 	flags = le16_to_cpu(resp->flags);
@@ -6483,8 +6615,6 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 	}
 	req.flags = cpu_to_le32(flags);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
-		rc = -EIO;
 	return rc;
 }
 
@@ -6746,10 +6876,8 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message_silent(bp, &req, sizeof(req),
 				       HWRM_CMD_TIMEOUT);
-	if (rc) {
-		rc = -EIO;
+	if (rc)
 		goto hwrm_func_resc_qcaps_exit;
-	}
 
 	hw_resc->max_tx_sch_inputs = le16_to_cpu(resp->max_tx_scheduler_inputs);
 	if (!all)
@@ -6817,6 +6945,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_PCIE_STATS_SUPPORTED;
 	if (flags & FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED)
 		bp->fw_cap |= BNXT_FW_CAP_EXT_STATS_SUPPORTED;
+	if (flags &  FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE)
+		bp->fw_cap |= BNXT_FW_CAP_ERROR_RECOVERY;
 
 	bp->tx_push_thresh = 0;
 	if (flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED)
@@ -6848,6 +6978,7 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		pf->max_tx_wm_flows = le32_to_cpu(resp->max_tx_wm_flows);
 		pf->max_rx_em_flows = le32_to_cpu(resp->max_rx_em_flows);
 		pf->max_rx_wm_flows = le32_to_cpu(resp->max_rx_wm_flows);
+		bp->flags &= ~BNXT_FLAG_WOL_CAP;
 		if (flags & FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED)
 			bp->flags |= BNXT_FLAG_WOL_CAP;
 	} else {
@@ -6917,6 +7048,103 @@ static int bnxt_hwrm_cfa_adv_flow_mgnt_qcaps(struct bnxt *bp)
 	return rc;
 }
 
+static int bnxt_map_fw_health_regs(struct bnxt *bp)
+{
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	u32 reg_base = 0xffffffff;
+	int i;
+
+	/* Only pre-map the monitoring GRC registers using window 3 */
+	for (i = 0; i < 4; i++) {
+		u32 reg = fw_health->regs[i];
+
+		if (BNXT_FW_HEALTH_REG_TYPE(reg) != BNXT_FW_HEALTH_REG_TYPE_GRC)
+			continue;
+		if (reg_base == 0xffffffff)
+			reg_base = reg & BNXT_GRC_BASE_MASK;
+		if ((reg & BNXT_GRC_BASE_MASK) != reg_base)
+			return -ERANGE;
+		fw_health->mapped_regs[i] = BNXT_FW_HEALTH_WIN_BASE +
+					    (reg & BNXT_GRC_OFFSET_MASK);
+	}
+	if (reg_base == 0xffffffff)
+		return 0;
+
+	writel(reg_base, bp->bar0 + BNXT_GRCPF_REG_WINDOW_BASE_OUT +
+			 BNXT_FW_HEALTH_WIN_MAP_OFF);
+	return 0;
+}
+
+static int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp)
+{
+	struct hwrm_error_recovery_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	struct hwrm_error_recovery_qcfg_input req = {0};
+	int rc, i;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_ERROR_RECOVERY_QCFG, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		goto err_recovery_out;
+	if (!fw_health) {
+		fw_health = kzalloc(sizeof(*fw_health), GFP_KERNEL);
+		bp->fw_health = fw_health;
+		if (!fw_health) {
+			rc = -ENOMEM;
+			goto err_recovery_out;
+		}
+	}
+	fw_health->flags = le32_to_cpu(resp->flags);
+	if ((fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) &&
+	    !(bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL)) {
+		rc = -EINVAL;
+		goto err_recovery_out;
+	}
+	fw_health->polling_dsecs = le32_to_cpu(resp->driver_polling_freq);
+	fw_health->master_func_wait_dsecs =
+		le32_to_cpu(resp->master_func_wait_period);
+	fw_health->normal_func_wait_dsecs =
+		le32_to_cpu(resp->normal_func_wait_period);
+	fw_health->post_reset_wait_dsecs =
+		le32_to_cpu(resp->master_func_wait_period_after_reset);
+	fw_health->post_reset_max_wait_dsecs =
+		le32_to_cpu(resp->max_bailout_time_after_reset);
+	fw_health->regs[BNXT_FW_HEALTH_REG] =
+		le32_to_cpu(resp->fw_health_status_reg);
+	fw_health->regs[BNXT_FW_HEARTBEAT_REG] =
+		le32_to_cpu(resp->fw_heartbeat_reg);
+	fw_health->regs[BNXT_FW_RESET_CNT_REG] =
+		le32_to_cpu(resp->fw_reset_cnt_reg);
+	fw_health->regs[BNXT_FW_RESET_INPROG_REG] =
+		le32_to_cpu(resp->reset_inprogress_reg);
+	fw_health->fw_reset_inprog_reg_mask =
+		le32_to_cpu(resp->reset_inprogress_reg_mask);
+	fw_health->fw_reset_seq_cnt = resp->reg_array_cnt;
+	if (fw_health->fw_reset_seq_cnt >= 16) {
+		rc = -EINVAL;
+		goto err_recovery_out;
+	}
+	for (i = 0; i < fw_health->fw_reset_seq_cnt; i++) {
+		fw_health->fw_reset_seq_regs[i] =
+			le32_to_cpu(resp->reset_reg[i]);
+		fw_health->fw_reset_seq_vals[i] =
+			le32_to_cpu(resp->reset_reg_val[i]);
+		fw_health->fw_reset_seq_delay_msec[i] =
+			resp->delay_after_reset[i];
+	}
+err_recovery_out:
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	if (!rc)
+		rc = bnxt_map_fw_health_regs(bp);
+	if (rc)
+		bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY;
+	return rc;
+}
+
 static int bnxt_hwrm_func_reset(struct bnxt *bp)
 {
 	struct hwrm_func_reset_input req = {0};
@@ -6976,20 +7204,30 @@ static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp)
 	return rc;
 }
 
-static int bnxt_hwrm_ver_get(struct bnxt *bp)
+static int __bnxt_hwrm_ver_get(struct bnxt *bp, bool silent)
 {
-	int rc;
 	struct hwrm_ver_get_input req = {0};
-	struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr;
-	u32 dev_caps_cfg;
+	int rc;
 
-	bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN;
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VER_GET, -1, -1);
 	req.hwrm_intf_maj = HWRM_VERSION_MAJOR;
 	req.hwrm_intf_min = HWRM_VERSION_MINOR;
 	req.hwrm_intf_upd = HWRM_VERSION_UPDATE;
+
+	rc = bnxt_hwrm_do_send_msg(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT,
+				   silent);
+	return rc;
+}
+
+static int bnxt_hwrm_ver_get(struct bnxt *bp)
+{
+	struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr;
+	u32 dev_caps_cfg;
+	int rc;
+
+	bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN;
 	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = __bnxt_hwrm_ver_get(bp, false);
 	if (rc)
 		goto hwrm_ver_get_exit;
 
@@ -7192,6 +7430,8 @@ 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) {
@@ -7257,8 +7497,6 @@ static int bnxt_hwrm_set_br_mode(struct bnxt *bp, u16 br_mode)
 	else
 		return -EINVAL;
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
-		rc = -EIO;
 	return rc;
 }
 
@@ -7278,8 +7516,6 @@ static int bnxt_hwrm_set_cache_line_size(struct bnxt *bp, int size)
 		req.options = FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128;
 
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
-		rc = -EIO;
 	return rc;
 }
 
@@ -8162,6 +8398,9 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 	struct hwrm_port_phy_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
 	struct bnxt_link_info *link_info = &bp->link_info;
 
+	bp->flags &= ~BNXT_FLAG_EEE_CAP;
+	if (bp->test_info)
+		bp->test_info->flags &= ~BNXT_TEST_FL_EXT_LPBK;
 	if (bp->hwrm_spec_code < 0x10201)
 		return 0;
 
@@ -8483,11 +8722,14 @@ static int bnxt_hwrm_shutdown_link(struct bnxt *bp)
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 }
 
+static int bnxt_fw_init_one(struct bnxt *bp);
+
 static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 {
 	struct hwrm_func_drv_if_change_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_func_drv_if_change_input req = {0};
-	bool resc_reinit = false;
+	bool resc_reinit = false, fw_reset = false;
+	u32 flags = 0;
 	int rc;
 
 	if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE))
@@ -8498,26 +8740,57 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 		req.flags = cpu_to_le32(FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP);
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc && (resp->flags &
-		    cpu_to_le32(FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE)))
-		resc_reinit = true;
+	if (!rc)
+		flags = le32_to_cpu(resp->flags);
 	mutex_unlock(&bp->hwrm_cmd_lock);
+	if (rc)
+		return rc;
 
-	if (up && resc_reinit && BNXT_NEW_RM(bp)) {
-		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
+	if (!up)
+		return 0;
 
-		rc = bnxt_hwrm_func_resc_qcaps(bp, true);
-		hw_resc->resv_cp_rings = 0;
-		hw_resc->resv_stat_ctxs = 0;
-		hw_resc->resv_irqs = 0;
-		hw_resc->resv_tx_rings = 0;
-		hw_resc->resv_rx_rings = 0;
-		hw_resc->resv_hw_ring_grps = 0;
-		hw_resc->resv_vnics = 0;
-		bp->tx_nr_rings = 0;
-		bp->rx_nr_rings = 0;
+	if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE)
+		resc_reinit = true;
+	if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE)
+		fw_reset = true;
+
+	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state) && !fw_reset) {
+		netdev_err(bp->dev, "RESET_DONE not set during FW reset.\n");
+		return -ENODEV;
 	}
-	return rc;
+	if (resc_reinit || fw_reset) {
+		if (fw_reset) {
+			rc = bnxt_fw_init_one(bp);
+			if (rc) {
+				set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
+				return rc;
+			}
+			bnxt_clear_int_mode(bp);
+			rc = bnxt_init_int_mode(bp);
+			if (rc) {
+				netdev_err(bp->dev, "init int mode failed\n");
+				return rc;
+			}
+			set_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
+		}
+		if (BNXT_NEW_RM(bp)) {
+			struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
+
+			rc = bnxt_hwrm_func_resc_qcaps(bp, true);
+			hw_resc->resv_cp_rings = 0;
+			hw_resc->resv_stat_ctxs = 0;
+			hw_resc->resv_irqs = 0;
+			hw_resc->resv_tx_rings = 0;
+			hw_resc->resv_rx_rings = 0;
+			hw_resc->resv_hw_ring_grps = 0;
+			hw_resc->resv_vnics = 0;
+			if (!fw_reset) {
+				bp->tx_nr_rings = 0;
+				bp->rx_nr_rings = 0;
+			}
+		}
+	}
+	return 0;
 }
 
 static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp)
@@ -8527,6 +8800,7 @@ static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp)
 	struct bnxt_pf_info *pf = &bp->pf;
 	int rc;
 
+	bp->num_leds = 0;
 	if (BNXT_VF(bp) || bp->hwrm_spec_code < 0x10601)
 		return 0;
 
@@ -8621,6 +8895,7 @@ static void bnxt_get_wol_settings(struct bnxt *bp)
 {
 	u16 handle = 0;
 
+	bp->wol = 0;
 	if (!BNXT_PF(bp) || !(bp->flags & BNXT_FLAG_WOL_CAP))
 		return;
 
@@ -8667,6 +8942,9 @@ static void bnxt_hwmon_open(struct bnxt *bp)
 {
 	struct pci_dev *pdev = bp->pdev;
 
+	if (bp->hwmon_dev)
+		return;
+
 	bp->hwmon_dev = hwmon_device_register_with_groups(&pdev->dev,
 							  DRV_MODULE_NAME, bp,
 							  bnxt_groups);
@@ -8932,12 +9210,28 @@ static int bnxt_open(struct net_device *dev)
 	struct bnxt *bp = netdev_priv(dev);
 	int rc;
 
-	bnxt_hwrm_if_change(bp, true);
-	rc = __bnxt_open_nic(bp, true, true);
+	if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
+		netdev_err(bp->dev, "A previous firmware reset did not complete, aborting\n");
+		return -ENODEV;
+	}
+
+	rc = bnxt_hwrm_if_change(bp, true);
 	if (rc)
+		return rc;
+	rc = __bnxt_open_nic(bp, true, true);
+	if (rc) {
 		bnxt_hwrm_if_change(bp, false);
+	} else {
+		if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state) &&
+		    BNXT_PF(bp)) {
+			struct bnxt_pf_info *pf = &bp->pf;
+			int n = pf->active_vfs;
 
-	bnxt_hwmon_open(bp);
+			if (n)
+				bnxt_cfg_hw_sriov(bp, &n, true);
+		}
+		bnxt_hwmon_open(bp);
+	}
 
 	return rc;
 }
@@ -8974,6 +9268,10 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_debug_dev_exit(bp);
 	bnxt_disable_napi(bp);
 	del_timer_sync(&bp->timer);
+	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state) &&
+	    pci_is_enabled(bp->pdev))
+		pci_disable_device(bp->pdev);
+
 	bnxt_free_skbs(bp);
 
 	/* Save ring stats before shutdown */
@@ -8990,6 +9288,18 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
 
+	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
+		/* If we get here, it means firmware reset is in progress
+		 * while we are trying to close.  We can safely proceed with
+		 * the close because we are holding rtnl_lock().  Some firmware
+		 * messages may fail as we proceed to close.  We set the
+		 * ABORT_ERR flag here so that the FW reset thread will later
+		 * abort when it gets the rtnl_lock() and sees the flag.
+		 */
+		netdev_warn(bp->dev, "FW reset in progress during close, FW reset will be aborted\n");
+		set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
+	}
+
 #ifdef CONFIG_BNXT_SRIOV
 	if (bp->sriov_cfg) {
 		rc = wait_event_interruptible_timeout(bp->sriov_cfg_wait,
@@ -9631,6 +9941,38 @@ static void bnxt_tx_timeout(struct net_device *dev)
 	bnxt_queue_sp_work(bp);
 }
 
+static void bnxt_fw_health_check(struct bnxt *bp)
+{
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	u32 val;
+
+	if (!fw_health || !fw_health->enabled ||
+	    test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+		return;
+
+	if (fw_health->tmr_counter) {
+		fw_health->tmr_counter--;
+		return;
+	}
+
+	val = bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG);
+	if (val == fw_health->last_fw_heartbeat)
+		goto fw_reset;
+
+	fw_health->last_fw_heartbeat = val;
+
+	val = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG);
+	if (val != fw_health->last_fw_reset_cnt)
+		goto fw_reset;
+
+	fw_health->tmr_counter = fw_health->tmr_multiplier;
+	return;
+
+fw_reset:
+	set_bit(BNXT_FW_EXCEPTION_SP_EVENT, &bp->sp_event);
+	bnxt_queue_sp_work(bp);
+}
+
 static void bnxt_timer(struct timer_list *t)
 {
 	struct bnxt *bp = from_timer(bp, t, timer);
@@ -9642,6 +9984,9 @@ static void bnxt_timer(struct timer_list *t)
 	if (atomic_read(&bp->intr_sem) != 0)
 		goto bnxt_restart_timer;
 
+	if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)
+		bnxt_fw_health_check(bp);
+
 	if (bp->link_info.link_up && (bp->flags & BNXT_FLAG_PORT_STATS) &&
 	    bp->stats_coal_ticks) {
 		set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event);
@@ -9697,6 +10042,108 @@ static void bnxt_reset(struct bnxt *bp, bool silent)
 	bnxt_rtnl_unlock_sp(bp);
 }
 
+static void bnxt_fw_reset_close(struct bnxt *bp)
+{
+	__bnxt_close_nic(bp, true, false);
+	bnxt_ulp_irq_stop(bp);
+	bnxt_clear_int_mode(bp);
+	bnxt_hwrm_func_drv_unrgtr(bp);
+	bnxt_free_ctx_mem(bp);
+	kfree(bp->ctx);
+	bp->ctx = NULL;
+}
+
+static bool is_bnxt_fw_ok(struct bnxt *bp)
+{
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	bool no_heartbeat = false, has_reset = false;
+	u32 val;
+
+	val = bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG);
+	if (val == fw_health->last_fw_heartbeat)
+		no_heartbeat = true;
+
+	val = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG);
+	if (val != fw_health->last_fw_reset_cnt)
+		has_reset = true;
+
+	if (!no_heartbeat && has_reset)
+		return true;
+
+	return false;
+}
+
+/* rtnl_lock is acquired before calling this function */
+static void bnxt_force_fw_reset(struct bnxt *bp)
+{
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	u32 wait_dsecs;
+
+	if (!test_bit(BNXT_STATE_OPEN, &bp->state) ||
+	    test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+		return;
+
+	set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+	bnxt_fw_reset_close(bp);
+	wait_dsecs = fw_health->master_func_wait_dsecs;
+	if (fw_health->master) {
+		if (fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU)
+			wait_dsecs = 0;
+		bp->fw_reset_state = BNXT_FW_RESET_STATE_RESET_FW;
+	} else {
+		bp->fw_reset_timestamp = jiffies + wait_dsecs * HZ / 10;
+		wait_dsecs = fw_health->normal_func_wait_dsecs;
+		bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
+	}
+	bp->fw_reset_max_dsecs = fw_health->post_reset_max_wait_dsecs;
+	bnxt_queue_fw_reset_work(bp, wait_dsecs * HZ / 10);
+}
+
+void bnxt_fw_exception(struct bnxt *bp)
+{
+	set_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
+	bnxt_rtnl_lock_sp(bp);
+	bnxt_force_fw_reset(bp);
+	bnxt_rtnl_unlock_sp(bp);
+}
+
+void bnxt_fw_reset(struct bnxt *bp)
+{
+	int rc;
+
+	bnxt_rtnl_lock_sp(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 &&
+		    !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",
+					   rc);
+				clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+				dev_close(bp->dev);
+				goto fw_reset_exit;
+			}
+			if (bp->pf.registered_vfs || bp->sriov_cfg) {
+				u16 vf_tmo_dsecs = bp->pf.registered_vfs * 10;
+
+				if (bp->fw_reset_max_dsecs < vf_tmo_dsecs)
+					bp->fw_reset_max_dsecs = vf_tmo_dsecs;
+				bp->fw_reset_state =
+					BNXT_FW_RESET_STATE_POLL_VF;
+				bnxt_queue_fw_reset_work(bp, HZ / 10);
+				goto fw_reset_exit;
+			}
+		}
+		bnxt_fw_reset_close(bp);
+		bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
+		bnxt_queue_fw_reset_work(bp, bp->fw_reset_min_dsecs * HZ / 10);
+	}
+fw_reset_exit:
+	bnxt_rtnl_unlock_sp(bp);
+}
+
 static void bnxt_chk_missed_irq(struct bnxt *bp)
 {
 	int i;
@@ -9827,6 +10274,15 @@ static void bnxt_sp_task(struct work_struct *work)
 	if (test_and_clear_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event))
 		bnxt_reset(bp, true);
 
+	if (test_and_clear_bit(BNXT_FW_RESET_NOTIFY_SP_EVENT, &bp->sp_event))
+		bnxt_devlink_health_report(bp, BNXT_FW_RESET_NOTIFY_SP_EVENT);
+
+	if (test_and_clear_bit(BNXT_FW_EXCEPTION_SP_EVENT, &bp->sp_event)) {
+		if (!is_bnxt_fw_ok(bp))
+			bnxt_devlink_health_report(bp,
+						   BNXT_FW_EXCEPTION_SP_EVENT);
+	}
+
 	smp_mb__before_atomic();
 	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
 }
@@ -9967,6 +10423,11 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp)
 		netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n",
 			    rc);
 
+	rc = bnxt_hwrm_error_recovery_qcfg(bp);
+	if (rc)
+		netdev_warn(bp->dev, "hwrm query error recovery failure rc: %d\n",
+			    rc);
+
 	rc = bnxt_hwrm_func_drv_rgtr(bp);
 	if (rc)
 		return -ENODEV;
@@ -9983,6 +10444,241 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp)
 	return 0;
 }
 
+static void bnxt_set_dflt_rss_hash_type(struct bnxt *bp)
+{
+	bp->flags &= ~BNXT_FLAG_UDP_RSS_CAP;
+	bp->rss_hash_cfg = VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 |
+			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 |
+			   VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 |
+			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
+	if (BNXT_CHIP_P4(bp) && bp->hwrm_spec_code >= 0x10501) {
+		bp->flags |= BNXT_FLAG_UDP_RSS_CAP;
+		bp->rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 |
+				    VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
+	}
+}
+
+static void bnxt_set_dflt_rfs(struct bnxt *bp)
+{
+	struct net_device *dev = bp->dev;
+
+	dev->hw_features &= ~NETIF_F_NTUPLE;
+	dev->features &= ~NETIF_F_NTUPLE;
+	bp->flags &= ~BNXT_FLAG_RFS;
+	if (bnxt_rfs_supported(bp)) {
+		dev->hw_features |= NETIF_F_NTUPLE;
+		if (bnxt_rfs_capable(bp)) {
+			bp->flags |= BNXT_FLAG_RFS;
+			dev->features |= NETIF_F_NTUPLE;
+		}
+	}
+}
+
+static void bnxt_fw_init_one_p3(struct bnxt *bp)
+{
+	struct pci_dev *pdev = bp->pdev;
+
+	bnxt_set_dflt_rss_hash_type(bp);
+	bnxt_set_dflt_rfs(bp);
+
+	bnxt_get_wol_settings(bp);
+	if (bp->flags & BNXT_FLAG_WOL_CAP)
+		device_set_wakeup_enable(&pdev->dev, bp->wol);
+	else
+		device_set_wakeup_capable(&pdev->dev, false);
+
+	bnxt_hwrm_set_cache_line_size(bp, cache_line_size());
+	bnxt_hwrm_coal_params_qcaps(bp);
+}
+
+static int bnxt_fw_init_one(struct bnxt *bp)
+{
+	int rc;
+
+	rc = bnxt_fw_init_one_p1(bp);
+	if (rc) {
+		netdev_err(bp->dev, "Firmware init phase 1 failed\n");
+		return rc;
+	}
+	rc = bnxt_fw_init_one_p2(bp);
+	if (rc) {
+		netdev_err(bp->dev, "Firmware init phase 2 failed\n");
+		return rc;
+	}
+	rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false);
+	if (rc)
+		return rc;
+	bnxt_fw_init_one_p3(bp);
+	return 0;
+}
+
+static void bnxt_fw_reset_writel(struct bnxt *bp, int reg_idx)
+{
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	u32 reg = fw_health->fw_reset_seq_regs[reg_idx];
+	u32 val = fw_health->fw_reset_seq_vals[reg_idx];
+	u32 reg_type, reg_off, delay_msecs;
+
+	delay_msecs = fw_health->fw_reset_seq_delay_msec[reg_idx];
+	reg_type = BNXT_FW_HEALTH_REG_TYPE(reg);
+	reg_off = BNXT_FW_HEALTH_REG_OFF(reg);
+	switch (reg_type) {
+	case BNXT_FW_HEALTH_REG_TYPE_CFG:
+		pci_write_config_dword(bp->pdev, reg_off, val);
+		break;
+	case BNXT_FW_HEALTH_REG_TYPE_GRC:
+		writel(reg_off & BNXT_GRC_BASE_MASK,
+		       bp->bar0 + BNXT_GRCPF_REG_WINDOW_BASE_OUT + 4);
+		reg_off = (reg_off & BNXT_GRC_OFFSET_MASK) + 0x2000;
+		/* fall through */
+	case BNXT_FW_HEALTH_REG_TYPE_BAR0:
+		writel(val, bp->bar0 + reg_off);
+		break;
+	case BNXT_FW_HEALTH_REG_TYPE_BAR1:
+		writel(val, bp->bar1 + reg_off);
+		break;
+	}
+	if (delay_msecs) {
+		pci_read_config_dword(bp->pdev, 0, &val);
+		msleep(delay_msecs);
+	}
+}
+
+static void bnxt_reset_all(struct bnxt *bp)
+{
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	int i;
+
+	if (fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_HOST) {
+		for (i = 0; i < fw_health->fw_reset_seq_cnt; i++)
+			bnxt_fw_reset_writel(bp, i);
+	} else if (fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) {
+		struct hwrm_fw_reset_input req = {0};
+		int rc;
+
+		bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_RESET, -1, -1);
+		req.resp_addr = cpu_to_le64(bp->hwrm_cmd_kong_resp_dma_addr);
+		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP;
+		req.selfrst_status = FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP;
+		req.flags = FW_RESET_REQ_FLAGS_RESET_GRACEFUL;
+		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		if (rc)
+			netdev_warn(bp->dev, "Unable to reset FW rc=%d\n", rc);
+	}
+	bp->fw_reset_timestamp = jiffies;
+}
+
+static void bnxt_fw_reset_task(struct work_struct *work)
+{
+	struct bnxt *bp = container_of(work, struct bnxt, fw_reset_task.work);
+	int rc;
+
+	if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
+		netdev_err(bp->dev, "bnxt_fw_reset_task() called when not in fw reset mode!\n");
+		return;
+	}
+
+	switch (bp->fw_reset_state) {
+	case BNXT_FW_RESET_STATE_POLL_VF:
+		rc = bnxt_hwrm_func_qcfg(bp);
+		if (rc) {
+			netdev_err(bp->dev, "Firmware reset aborted, subsequent func_qcfg cmd failed, rc = %d, %d msecs since reset timestamp\n",
+				   rc, jiffies_to_msecs(jiffies -
+				   bp->fw_reset_timestamp));
+			goto fw_reset_abort;
+		}
+		if (bp->pf.registered_vfs || bp->sriov_cfg) {
+			if (time_after(jiffies, bp->fw_reset_timestamp +
+				       (bp->fw_reset_max_dsecs * HZ / 10))) {
+				clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+				bp->fw_reset_state = 0;
+				netdev_err(bp->dev, "Firmware reset aborted, %d VFs still registered, sriov_cfg %d\n",
+					   bp->pf.registered_vfs,
+					   bp->sriov_cfg);
+				return;
+			}
+			bnxt_queue_fw_reset_work(bp, HZ / 10);
+			return;
+		}
+		bp->fw_reset_timestamp = jiffies;
+		rtnl_lock();
+		bnxt_fw_reset_close(bp);
+		bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
+		rtnl_unlock();
+		bnxt_queue_fw_reset_work(bp, bp->fw_reset_min_dsecs * HZ / 10);
+		return;
+	case BNXT_FW_RESET_STATE_RESET_FW: {
+		u32 wait_dsecs = bp->fw_health->post_reset_wait_dsecs;
+
+		bnxt_reset_all(bp);
+		bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
+		bnxt_queue_fw_reset_work(bp, wait_dsecs * HZ / 10);
+		return;
+	}
+	case BNXT_FW_RESET_STATE_ENABLE_DEV:
+		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) &&
+		    bp->fw_health) {
+			u32 val;
+
+			val = bnxt_fw_health_readl(bp,
+						   BNXT_FW_RESET_INPROG_REG);
+			if (val)
+				netdev_warn(bp->dev, "FW reset inprog %x after min wait time.\n",
+					    val);
+		}
+		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;
+		}
+		pci_set_master(bp->pdev);
+		bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW;
+		/* fall through */
+	case BNXT_FW_RESET_STATE_POLL_FW:
+		bp->hwrm_cmd_timeout = SHORT_HWRM_CMD_TIMEOUT;
+		rc = __bnxt_hwrm_ver_get(bp, true);
+		if (rc) {
+			if (time_after(jiffies, bp->fw_reset_timestamp +
+				       (bp->fw_reset_max_dsecs * HZ / 10))) {
+				netdev_err(bp->dev, "Firmware reset aborted\n");
+				goto fw_reset_abort;
+			}
+			bnxt_queue_fw_reset_work(bp, HZ / 5);
+			return;
+		}
+		bp->hwrm_cmd_timeout = DFLT_HWRM_CMD_TIMEOUT;
+		bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING;
+		/* fall through */
+	case BNXT_FW_RESET_STATE_OPENING:
+		while (!rtnl_trylock()) {
+			bnxt_queue_fw_reset_work(bp, HZ / 10);
+			return;
+		}
+		rc = bnxt_open(bp->dev);
+		if (rc) {
+			netdev_err(bp->dev, "bnxt_open_nic() failed\n");
+			clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+			dev_close(bp->dev);
+		}
+		bnxt_ulp_irq_restart(bp, rc);
+		rtnl_unlock();
+
+		bp->fw_reset_state = 0;
+		/* Make sure fw_reset_state is 0 before clearing the flag */
+		smp_mb__before_atomic();
+		clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+		break;
+	}
+	return;
+
+fw_reset_abort:
+	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+	bp->fw_reset_state = 0;
+	rtnl_lock();
+	dev_close(bp->dev);
+	rtnl_unlock();
+}
+
 static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
 {
 	int rc;
@@ -10045,6 +10741,7 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
 	pci_enable_pcie_error_reporting(pdev);
 
 	INIT_WORK(&bp->sp_task, bnxt_sp_task);
+	INIT_DELAYED_WORK(&bp->fw_reset_task, bnxt_fw_reset_task);
 
 	spin_lock_init(&bp->ntp_fltr_lock);
 #if BITS_PER_LONG == 32
@@ -10588,7 +11285,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	free_netdev(dev);
 }
 
-static int bnxt_probe_phy(struct bnxt *bp)
+static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt)
 {
 	int rc = 0;
 	struct bnxt_link_info *link_info = &bp->link_info;
@@ -10599,8 +11296,6 @@ static int bnxt_probe_phy(struct bnxt *bp)
 			   rc);
 		return rc;
 	}
-	mutex_init(&bp->link_lock);
-
 	rc = bnxt_update_link(bp, false);
 	if (rc) {
 		netdev_err(bp->dev, "Probe phy can't update link (rc: %x)\n",
@@ -10614,6 +11309,9 @@ static int bnxt_probe_phy(struct bnxt *bp)
 	if (link_info->auto_link_speeds && !link_info->support_auto_speeds)
 		link_info->support_auto_speeds = link_info->support_speeds;
 
+	if (!fw_dflt)
+		return 0;
+
 	/*initialize the ethool setting copy with NVM settings */
 	if (BNXT_AUTO_MODE(link_info->auto_mode)) {
 		link_info->autoneg = BNXT_AUTONEG_SPEED;
@@ -10634,7 +11332,7 @@ static int bnxt_probe_phy(struct bnxt *bp)
 			link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH;
 	else
 		link_info->req_flow_ctrl = link_info->force_pause_setting;
-	return rc;
+	return 0;
 }
 
 static int bnxt_get_max_irq(struct pci_dev *pdev)
@@ -10938,6 +11636,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto init_err_pci_clean;
 
 	mutex_init(&bp->hwrm_cmd_lock);
+	mutex_init(&bp->link_lock);
 
 	rc = bnxt_fw_init_one_p1(bp);
 	if (rc)
@@ -11013,7 +11712,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->min_mtu = ETH_ZLEN;
 	dev->max_mtu = bp->max_mtu;
 
-	rc = bnxt_probe_phy(bp);
+	rc = bnxt_probe_phy(bp, true);
 	if (rc)
 		goto init_err_pci_clean;
 
@@ -11027,24 +11726,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto init_err_pci_clean;
 	}
 
-	/* Default RSS hash cfg. */
-	bp->rss_hash_cfg = VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 |
-			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 |
-			   VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 |
-			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
-	if (BNXT_CHIP_P4(bp) && bp->hwrm_spec_code >= 0x10501) {
-		bp->flags |= BNXT_FLAG_UDP_RSS_CAP;
-		bp->rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 |
-				    VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
-	}
-
-	if (bnxt_rfs_supported(bp)) {
-		dev->hw_features |= NETIF_F_NTUPLE;
-		if (bnxt_rfs_capable(bp)) {
-			bp->flags |= BNXT_FLAG_RFS;
-			dev->features |= NETIF_F_NTUPLE;
-		}
-	}
+	bnxt_fw_init_one_p3(bp);
 
 	if (dev->hw_features & NETIF_F_HW_VLAN_CTAG_RX)
 		bp->flags |= BNXT_FLAG_STRIP_VLAN;
@@ -11058,16 +11740,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 */
 	bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
 
-	bnxt_get_wol_settings(bp);
-	if (bp->flags & BNXT_FLAG_WOL_CAP)
-		device_set_wakeup_enable(&pdev->dev, bp->wol);
-	else
-		device_set_wakeup_capable(&pdev->dev, false);
-
-	bnxt_hwrm_set_cache_line_size(bp, cache_line_size());
-
-	bnxt_hwrm_coal_params_qcaps(bp);
-
 	if (BNXT_PF(bp)) {
 		if (!bnxt_pf_wq) {
 			bnxt_pf_wq =
@@ -11104,6 +11776,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
 	bp->ctx = NULL;
+	kfree(bp->fw_health);
+	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 
 init_err_free:

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

@@ -472,6 +472,19 @@ struct rx_tpa_end_cmp_ext {
 	((le32_to_cpu((rx_tpa_end_ext)->rx_tpa_end_cmp_dup_acks) &	\
 	 RX_TPA_END_CMP_AGG_BUFS_P5) >> RX_TPA_END_CMP_AGG_BUFS_SHIFT_P5)
 
+#define EVENT_DATA1_RESET_NOTIFY_FATAL(data1)				\
+	(((data1) &							\
+	  ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK) ==\
+	 ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL)
+
+#define EVENT_DATA1_RECOVERY_MASTER_FUNC(data1)				\
+	!!((data1) &							\
+	   ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC)
+
+#define EVENT_DATA1_RECOVERY_ENABLED(data1)				\
+	!!((data1) &							\
+	   ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED)
+
 struct nqe_cn {
 	__le16	type;
 	#define NQ_CN_TYPE_MASK           0x3fUL
@@ -632,6 +645,7 @@ struct nqe_cn {
 #define BNXT_HWRM_MAX_REQ_LEN		(bp->hwrm_max_req_len)
 #define BNXT_HWRM_SHORT_REQ_LEN		sizeof(struct hwrm_short_input)
 #define DFLT_HWRM_CMD_TIMEOUT		500
+#define SHORT_HWRM_CMD_TIMEOUT		20
 #define HWRM_CMD_TIMEOUT		(bp->hwrm_cmd_timeout)
 #define HWRM_RESET_TIMEOUT		((HWRM_CMD_TIMEOUT) * 4)
 #define HWRM_RESP_ERR_CODE_MASK		0xffff
@@ -1058,6 +1072,7 @@ struct bnxt_pf_info {
 	u8	mac_addr[ETH_ALEN];
 	u32	first_vf_id;
 	u16	active_vfs;
+	u16	registered_vfs;
 	u16	max_vfs;
 	u32	max_encap_records;
 	u32	max_decap_records;
@@ -1217,6 +1232,9 @@ struct bnxt_test_info {
 #define BNXT_GRCPF_REG_KONG_COMM		0xA00
 #define BNXT_GRCPF_REG_KONG_COMM_TRIGGER	0xB00
 
+#define BNXT_GRC_BASE_MASK			0xfffff000
+#define BNXT_GRC_OFFSET_MASK			0x00000ffc
+
 struct bnxt_tc_flow_stats {
 	u64		packets;
 	u64		bytes;
@@ -1333,6 +1351,53 @@ struct bnxt_ctx_mem_info {
 	struct bnxt_ctx_pg_info *tqm_mem[9];
 };
 
+struct bnxt_fw_health {
+	u32 flags;
+	u32 polling_dsecs;
+	u32 master_func_wait_dsecs;
+	u32 normal_func_wait_dsecs;
+	u32 post_reset_wait_dsecs;
+	u32 post_reset_max_wait_dsecs;
+	u32 regs[4];
+	u32 mapped_regs[4];
+#define BNXT_FW_HEALTH_REG		0
+#define BNXT_FW_HEARTBEAT_REG		1
+#define BNXT_FW_RESET_CNT_REG		2
+#define BNXT_FW_RESET_INPROG_REG	3
+	u32 fw_reset_inprog_reg_mask;
+	u32 last_fw_heartbeat;
+	u32 last_fw_reset_cnt;
+	u8 enabled:1;
+	u8 master:1;
+	u8 tmr_multiplier;
+	u8 tmr_counter;
+	u8 fw_reset_seq_cnt;
+	u32 fw_reset_seq_regs[16];
+	u32 fw_reset_seq_vals[16];
+	u32 fw_reset_seq_delay_msec[16];
+	struct devlink_health_reporter	*fw_reporter;
+	struct devlink_health_reporter *fw_reset_reporter;
+	struct devlink_health_reporter *fw_fatal_reporter;
+};
+
+struct bnxt_fw_reporter_ctx {
+	unsigned long sp_event;
+};
+
+#define BNXT_FW_HEALTH_REG_TYPE_MASK	3
+#define BNXT_FW_HEALTH_REG_TYPE_CFG	0
+#define BNXT_FW_HEALTH_REG_TYPE_GRC	1
+#define BNXT_FW_HEALTH_REG_TYPE_BAR0	2
+#define BNXT_FW_HEALTH_REG_TYPE_BAR1	3
+
+#define BNXT_FW_HEALTH_REG_TYPE(reg)	((reg) & BNXT_FW_HEALTH_REG_TYPE_MASK)
+#define BNXT_FW_HEALTH_REG_OFF(reg)	((reg) & ~BNXT_FW_HEALTH_REG_TYPE_MASK)
+
+#define BNXT_FW_HEALTH_WIN_BASE		0x3000
+#define BNXT_FW_HEALTH_WIN_MAP_OFF	8
+
+#define BNXT_FW_STATUS_HEALTHY		0x8000
+
 struct bnxt {
 	void __iomem		*bar0;
 	void __iomem		*bar1;
@@ -1555,6 +1620,10 @@ struct bnxt {
 #define BNXT_STATE_OPEN		0
 #define BNXT_STATE_IN_SP_TASK	1
 #define BNXT_STATE_READ_STATS	2
+#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;
@@ -1579,6 +1648,7 @@ struct bnxt {
 	#define BNXT_FW_CAP_KONG_MB_CHNL		0x00000080
 	#define BNXT_FW_CAP_OVS_64BIT_HANDLE		0x00000400
 	#define BNXT_FW_CAP_TRUSTED_VF			0x00000800
+	#define BNXT_FW_CAP_ERROR_RECOVERY		0x00002000
 	#define BNXT_FW_CAP_PKG_VER			0x00004000
 	#define BNXT_FW_CAP_CFA_ADV_FLOW		0x00008000
 	#define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX	0x00010000
@@ -1663,6 +1733,24 @@ struct bnxt {
 #define BNXT_FLOW_STATS_SP_EVENT	15
 #define BNXT_UPDATE_PHY_SP_EVENT	16
 #define BNXT_RING_COAL_NOW_SP_EVENT	17
+#define BNXT_FW_RESET_NOTIFY_SP_EVENT	18
+#define BNXT_FW_EXCEPTION_SP_EVENT	19
+
+	struct delayed_work	fw_reset_task;
+	int			fw_reset_state;
+#define BNXT_FW_RESET_STATE_POLL_VF	1
+#define BNXT_FW_RESET_STATE_RESET_FW	2
+#define BNXT_FW_RESET_STATE_ENABLE_DEV	3
+#define BNXT_FW_RESET_STATE_POLL_FW	4
+#define BNXT_FW_RESET_STATE_OPENING	5
+
+	u16			fw_reset_min_dsecs;
+#define BNXT_DFLT_FW_RST_MIN_DSECS	20
+	u16			fw_reset_max_dsecs;
+#define BNXT_DFLT_FW_RST_MAX_DSECS	60
+	unsigned long		fw_reset_timestamp;
+
+	struct bnxt_fw_health	*fw_health;
 
 	struct bnxt_hw_resc	hw_resc;
 	struct bnxt_pf_info	pf;
@@ -1868,6 +1956,7 @@ extern const u16 bnxt_lhint_arr[];
 int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		       u16 prod, gfp_t gfp);
 void bnxt_reuse_rx_data(struct bnxt_rx_ring_info *rxr, u16 cons, void *data);
+u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx);
 void bnxt_set_tpa_flags(struct bnxt *bp);
 void bnxt_set_ring_params(struct bnxt *);
 int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
@@ -1900,6 +1989,8 @@ int bnxt_open_nic(struct bnxt *, bool, bool);
 int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
 int bnxt_close_nic(struct bnxt *, bool, bool);
+void bnxt_fw_exception(struct bnxt *bp);
+void bnxt_fw_reset(struct bnxt *bp);
 int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		     int tx_xdp);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);

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

@@ -377,8 +377,6 @@ static int bnxt_hwrm_set_dcbx_app(struct bnxt *bp, struct dcb_app *app,
 	set.data_len = cpu_to_le16(sizeof(*data) + sizeof(*fw_app) * n);
 	set.hdr_cnt = 1;
 	rc = hwrm_send_message(bp, &set, sizeof(set), HWRM_CMD_TIMEOUT);
-	if (rc)
-		rc = -EIO;
 
 set_app_exit:
 	dma_free_coherent(&bp->pdev->dev, data_len, data, mapping);
@@ -391,6 +389,7 @@ static int bnxt_hwrm_queue_dscp_qcaps(struct bnxt *bp)
 	struct hwrm_queue_dscp_qcaps_input req = {0};
 	int rc;
 
+	bp->max_dscp_value = 0;
 	if (bp->hwrm_spec_code < 0x10800 || BNXT_VF(bp))
 		return 0;
 
@@ -433,8 +432,6 @@ static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app,
 	dscp2pri->pri = app->priority;
 	req.entry_cnt = cpu_to_le16(1);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
-		rc = -EIO;
 	dma_free_coherent(&bp->pdev->dev, sizeof(*dscp2pri), dscp2pri,
 			  mapping);
 	return rc;
@@ -722,6 +719,7 @@ static const struct dcbnl_rtnl_ops dcbnl_ops = {
 
 void bnxt_dcb_init(struct bnxt *bp)
 {
+	bp->dcbx_cap = 0;
 	if (bp->hwrm_spec_code < 0x10501)
 		return;
 

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

@@ -15,6 +15,192 @@
 #include "bnxt_vfr.h"
 #include "bnxt_devlink.h"
 
+static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
+				     struct devlink_fmsg *fmsg)
+{
+	struct bnxt *bp = devlink_health_reporter_priv(reporter);
+	struct bnxt_fw_health *health = bp->fw_health;
+	u32 val, health_status;
+	int rc;
+
+	if (!health || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+		return 0;
+
+	val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG);
+	health_status = val & 0xffff;
+
+	if (health_status == BNXT_FW_STATUS_HEALTHY) {
+		rc = devlink_fmsg_string_pair_put(fmsg, "FW status",
+						  "Healthy;");
+		if (rc)
+			return rc;
+	} else if (health_status < BNXT_FW_STATUS_HEALTHY) {
+		rc = devlink_fmsg_string_pair_put(fmsg, "FW status",
+						  "Not yet completed initialization;");
+		if (rc)
+			return rc;
+	} else if (health_status > BNXT_FW_STATUS_HEALTHY) {
+		rc = devlink_fmsg_string_pair_put(fmsg, "FW status",
+						  "Encountered fatal error and cannot recover;");
+		if (rc)
+			return rc;
+	}
+
+	if (val >> 16) {
+		rc = devlink_fmsg_u32_pair_put(fmsg, "Error", val >> 16);
+		if (rc)
+			return rc;
+	}
+
+	val = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG);
+	rc = devlink_fmsg_u32_pair_put(fmsg, "Reset count", val);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static const struct devlink_health_reporter_ops bnxt_dl_fw_reporter_ops = {
+	.name = "fw",
+	.diagnose = bnxt_fw_reporter_diagnose,
+};
+
+static int bnxt_fw_reset_recover(struct devlink_health_reporter *reporter,
+				 void *priv_ctx)
+{
+	struct bnxt *bp = devlink_health_reporter_priv(reporter);
+
+	if (!priv_ctx)
+		return -EOPNOTSUPP;
+
+	bnxt_fw_reset(bp);
+	return 0;
+}
+
+static const
+struct devlink_health_reporter_ops bnxt_dl_fw_reset_reporter_ops = {
+	.name = "fw_reset",
+	.recover = bnxt_fw_reset_recover,
+};
+
+static int bnxt_fw_fatal_recover(struct devlink_health_reporter *reporter,
+				 void *priv_ctx)
+{
+	struct bnxt *bp = devlink_health_reporter_priv(reporter);
+	struct bnxt_fw_reporter_ctx *fw_reporter_ctx = priv_ctx;
+	unsigned long event;
+
+	if (!priv_ctx)
+		return -EOPNOTSUPP;
+
+	event = fw_reporter_ctx->sp_event;
+	if (event == BNXT_FW_RESET_NOTIFY_SP_EVENT)
+		bnxt_fw_reset(bp);
+	else if (event == BNXT_FW_EXCEPTION_SP_EVENT)
+		bnxt_fw_exception(bp);
+
+	return 0;
+}
+
+static const
+struct devlink_health_reporter_ops bnxt_dl_fw_fatal_reporter_ops = {
+	.name = "fw_fatal",
+	.recover = bnxt_fw_fatal_recover,
+};
+
+static void bnxt_dl_fw_reporters_create(struct bnxt *bp)
+{
+	struct bnxt_fw_health *health = bp->fw_health;
+
+	if (!health)
+		return;
+
+	health->fw_reporter =
+		devlink_health_reporter_create(bp->dl, &bnxt_dl_fw_reporter_ops,
+					       0, false, bp);
+	if (IS_ERR(health->fw_reporter)) {
+		netdev_warn(bp->dev, "Failed to create FW health reporter, rc = %ld\n",
+			    PTR_ERR(health->fw_reporter));
+		health->fw_reporter = NULL;
+	}
+
+	health->fw_reset_reporter =
+		devlink_health_reporter_create(bp->dl,
+					       &bnxt_dl_fw_reset_reporter_ops,
+					       0, true, bp);
+	if (IS_ERR(health->fw_reset_reporter)) {
+		netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n",
+			    PTR_ERR(health->fw_reset_reporter));
+		health->fw_reset_reporter = NULL;
+	}
+
+	health->fw_fatal_reporter =
+		devlink_health_reporter_create(bp->dl,
+					       &bnxt_dl_fw_fatal_reporter_ops,
+					       0, true, bp);
+	if (IS_ERR(health->fw_fatal_reporter)) {
+		netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n",
+			    PTR_ERR(health->fw_fatal_reporter));
+		health->fw_fatal_reporter = NULL;
+	}
+}
+
+static void bnxt_dl_fw_reporters_destroy(struct bnxt *bp)
+{
+	struct bnxt_fw_health *health = bp->fw_health;
+
+	if (!health)
+		return;
+
+	if (health->fw_reporter)
+		devlink_health_reporter_destroy(health->fw_reporter);
+
+	if (health->fw_reset_reporter)
+		devlink_health_reporter_destroy(health->fw_reset_reporter);
+
+	if (health->fw_fatal_reporter)
+		devlink_health_reporter_destroy(health->fw_fatal_reporter);
+}
+
+void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event)
+{
+	struct bnxt_fw_health *fw_health = bp->fw_health;
+	struct bnxt_fw_reporter_ctx fw_reporter_ctx;
+
+	if (!fw_health)
+		return;
+
+	fw_reporter_ctx.sp_event = event;
+	switch (event) {
+	case BNXT_FW_RESET_NOTIFY_SP_EVENT:
+		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) {
+			if (!fw_health->fw_fatal_reporter)
+				return;
+
+			devlink_health_report(fw_health->fw_fatal_reporter,
+					      "FW fatal async event received",
+					      &fw_reporter_ctx);
+			return;
+		}
+		if (!fw_health->fw_reset_reporter)
+			return;
+
+		devlink_health_report(fw_health->fw_reset_reporter,
+				      "FW non-fatal reset event received",
+				      &fw_reporter_ctx);
+		return;
+
+	case BNXT_FW_EXCEPTION_SP_EVENT:
+		if (!fw_health->fw_fatal_reporter)
+			return;
+
+		devlink_health_report(fw_health->fw_fatal_reporter,
+				      "FW fatal error reported",
+				      &fw_reporter_ctx);
+		return;
+	}
+}
+
 static const struct devlink_ops bnxt_dl_ops = {
 #ifdef CONFIG_BNXT_SRIOV
 	.eswitch_mode_set = bnxt_dl_eswitch_mode_set,
@@ -109,13 +295,9 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 		memcpy(buf, data_addr, bytesize);
 
 	dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr);
-	if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
+	if (rc == -EACCES)
 		netdev_err(bp->dev, "PF does not have admin privileges to modify NVM config\n");
-		return -EACCES;
-	} else if (rc) {
-		return -EIO;
-	}
-	return 0;
+	return rc;
 }
 
 static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
@@ -251,6 +433,8 @@ int bnxt_dl_register(struct bnxt *bp)
 
 	devlink_params_publish(dl);
 
+	bnxt_dl_fw_reporters_create(bp);
+
 	return 0;
 
 err_dl_port_unreg:
@@ -273,6 +457,7 @@ void bnxt_dl_unregister(struct bnxt *bp)
 	if (!dl)
 		return;
 
+	bnxt_dl_fw_reporters_destroy(bp);
 	devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params,
 				       ARRAY_SIZE(bnxt_dl_port_params));
 	devlink_port_unregister(&bp->dl_port);

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

@@ -55,6 +55,7 @@ struct bnxt_dl_nvm_param {
 	u16 num_bits;
 };
 
+void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event);
 int bnxt_dl_register(struct bnxt *bp);
 void bnxt_dl_unregister(struct bnxt *bp);
 

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

@@ -1699,6 +1699,11 @@ static u32 bnxt_get_link(struct net_device *dev)
 	return bp->link_info.link_up;
 }
 
+static void bnxt_print_admin_err(struct bnxt *bp)
+{
+	netdev_info(bp->dev, "PF does not have admin privileges to flash or reset the device\n");
+}
+
 static int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal,
 				u16 ext, u16 *index, u32 *item_length,
 				u32 *data_length);
@@ -1738,13 +1743,8 @@ static int bnxt_flash_nvram(struct net_device *dev,
 	rc = hwrm_send_message(bp, &req, sizeof(req), FLASH_NVRAM_TIMEOUT);
 	dma_free_coherent(&bp->pdev->dev, data_len, kmem, dma_handle);
 
-	if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
-		netdev_info(dev,
-			    "PF does not have admin privileges to flash the device\n");
-		rc = -EACCES;
-	} else if (rc) {
-		rc = -EIO;
-	}
+	if (rc == -EACCES)
+		bnxt_print_admin_err(bp);
 	return rc;
 }
 
@@ -1794,13 +1794,8 @@ static int bnxt_firmware_reset(struct net_device *dev,
 	}
 
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
-		netdev_info(dev,
-			    "PF does not have admin privileges to reset the device\n");
-		rc = -EACCES;
-	} else if (rc) {
-		rc = -EIO;
-	}
+	if (rc == -EACCES)
+		bnxt_print_admin_err(bp);
 	return rc;
 }
 
@@ -2095,13 +2090,8 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 flash_pkg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 err_exit:
-	if (hwrm_err == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
-		netdev_info(dev,
-			    "PF does not have admin privileges to flash the device\n");
-		rc = -EACCES;
-	} else if (hwrm_err) {
-		rc = -EOPNOTSUPP;
-	}
+	if (hwrm_err == -EACCES)
+		bnxt_print_admin_err(bp);
 	return rc;
 }
 
@@ -2640,8 +2630,6 @@ static int bnxt_set_phys_id(struct net_device *dev,
 		led_cfg->led_group_id = bp->leds[i].led_group_id;
 	}
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
-		rc = -EIO;
 	return rc;
 }
 
@@ -3362,6 +3350,7 @@ void bnxt_ethtool_init(struct bnxt *bp)
 	if (!(bp->fw_cap & BNXT_FW_CAP_PKG_VER))
 		bnxt_get_pkgver(dev);
 
+	bp->num_tests = 0;
 	if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
 		return;
 
@@ -3371,7 +3360,9 @@ void bnxt_ethtool_init(struct bnxt *bp)
 	if (rc)
 		goto ethtool_init_exit;
 
-	test_info = kzalloc(sizeof(*bp->test_info), GFP_KERNEL);
+	test_info = bp->test_info;
+	if (!test_info)
+		test_info = kzalloc(sizeof(*bp->test_info), GFP_KERNEL);
 	if (!test_info)
 		goto ethtool_init_exit;
 

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

@@ -25,7 +25,6 @@
 static int bnxt_hwrm_fwd_async_event_cmpl(struct bnxt *bp,
 					  struct bnxt_vf_info *vf, u16 event_id)
 {
-	struct hwrm_fwd_async_event_cmpl_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_fwd_async_event_cmpl_input req = {0};
 	struct hwrm_async_event_cmpl *async_cmpl;
 	int rc = 0;
@@ -40,23 +39,10 @@ static int bnxt_hwrm_fwd_async_event_cmpl(struct bnxt *bp,
 	async_cmpl->type = cpu_to_le16(ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT);
 	async_cmpl->event_id = cpu_to_le16(event_id);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-
-	if (rc) {
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
 		netdev_err(bp->dev, "hwrm_fwd_async_event_cmpl failed. rc:%d\n",
 			   rc);
-		goto fwd_async_event_cmpl_exit;
-	}
-
-	if (resp->error_code) {
-		netdev_err(bp->dev, "hwrm_fwd_async_event_cmpl error %d\n",
-			   resp->error_code);
-		rc = -1;
-	}
-
-fwd_async_event_cmpl_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
 
@@ -133,7 +119,7 @@ static int bnxt_hwrm_func_qcfg_flags(struct bnxt *bp, struct bnxt_vf_info *vf)
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc) {
 		mutex_unlock(&bp->hwrm_cmd_lock);
-		return -EIO;
+		return rc;
 	}
 	vf->func_qcfg_flags = le16_to_cpu(resp->flags);
 	mutex_unlock(&bp->hwrm_cmd_lock);
@@ -164,9 +150,7 @@ static int bnxt_hwrm_set_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf)
 	else
 		req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc)
-		return -EIO;
-	return 0;
+	return rc;
 }
 
 int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trusted)
@@ -486,10 +470,43 @@ static int bnxt_hwrm_func_buf_rgtr(struct bnxt *bp)
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 }
 
+/* Caller holds bp->hwrm_cmd_lock mutex lock */
+static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id)
+{
+	struct hwrm_func_cfg_input req = {0};
+	struct bnxt_vf_info *vf;
+
+	vf = &bp->pf.vf[vf_id];
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
+	req.fid = cpu_to_le16(vf->fw_fid);
+	req.flags = cpu_to_le32(vf->func_flags);
+
+	if (is_valid_ether_addr(vf->mac_addr)) {
+		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
+		memcpy(req.dflt_mac_addr, vf->mac_addr, ETH_ALEN);
+	}
+	if (vf->vlan) {
+		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN);
+		req.dflt_vlan = cpu_to_le16(vf->vlan);
+	}
+	if (vf->max_tx_rate) {
+		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW);
+		req.max_bw = cpu_to_le32(vf->max_tx_rate);
+#ifdef HAVE_IFLA_TX_RATE
+		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW);
+		req.min_bw = cpu_to_le32(vf->min_tx_rate);
+#endif
+	}
+	if (vf->flags & BNXT_VF_TRUST)
+		req.flags |= cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE);
+
+	_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
 /* Only called by PF to reserve resources for VFs, returns actual number of
  * VFs configured, or < 0 on error.
  */
-static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
+static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 {
 	struct hwrm_func_vf_resource_cfg_input req = {0};
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
@@ -561,13 +578,14 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	for (i = 0; i < num_vfs; i++) {
+		if (reset)
+			__bnxt_set_vf_params(bp, i);
+
 		req.vf_id = cpu_to_le16(pf->first_vf_id + i);
 		rc = _hwrm_send_message(bp, &req, sizeof(req),
 					HWRM_CMD_TIMEOUT);
-		if (rc) {
-			rc = -ENOMEM;
+		if (rc)
 			break;
-		}
 		pf->active_vfs = i + 1;
 		pf->vf[i].fw_fid = pf->first_vf_id + i;
 	}
@@ -664,8 +682,6 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 		total_vf_tx_rings += vf_tx_rsvd;
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
-	if (rc)
-		rc = -ENOMEM;
 	if (pf->active_vfs) {
 		hw_resc->max_tx_rings -= total_vf_tx_rings;
 		hw_resc->max_rx_rings -= vf_rx_rings * num_vfs;
@@ -679,14 +695,40 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 	return rc;
 }
 
-static int bnxt_func_cfg(struct bnxt *bp, int num_vfs)
+static int bnxt_func_cfg(struct bnxt *bp, int num_vfs, bool reset)
 {
 	if (BNXT_NEW_RM(bp))
-		return bnxt_hwrm_func_vf_resc_cfg(bp, num_vfs);
+		return bnxt_hwrm_func_vf_resc_cfg(bp, num_vfs, reset);
 	else
 		return bnxt_hwrm_func_cfg(bp, num_vfs);
 }
 
+int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset)
+{
+	int rc;
+
+	/* Register buffers for VFs */
+	rc = bnxt_hwrm_func_buf_rgtr(bp);
+	if (rc)
+		return rc;
+
+	/* Reserve resources for VFs */
+	rc = bnxt_func_cfg(bp, *num_vfs, reset);
+	if (rc != *num_vfs) {
+		if (rc <= 0) {
+			netdev_warn(bp->dev, "Unable to reserve resources for SRIOV.\n");
+			*num_vfs = 0;
+			return rc;
+		}
+		netdev_warn(bp->dev, "Only able to reserve resources for %d VFs.\n",
+			    rc);
+		*num_vfs = rc;
+	}
+
+	bnxt_ulp_sriov_cfg(bp, *num_vfs);
+	return 0;
+}
+
 static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 {
 	int rc = 0, vfs_supported;
@@ -752,25 +794,10 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 	if (rc)
 		goto err_out1;
 
-	/* Reserve resources for VFs */
-	rc = bnxt_func_cfg(bp, *num_vfs);
-	if (rc != *num_vfs) {
-		if (rc <= 0) {
-			netdev_warn(bp->dev, "Unable to reserve resources for SRIOV.\n");
-			*num_vfs = 0;
-			goto err_out2;
-		}
-		netdev_warn(bp->dev, "Only able to reserve resources for %d VFs.\n", rc);
-		*num_vfs = rc;
-	}
-
-	/* Register buffers for VFs */
-	rc = bnxt_hwrm_func_buf_rgtr(bp);
+	rc = bnxt_cfg_hw_sriov(bp, num_vfs, false);
 	if (rc)
 		goto err_out2;
 
-	bnxt_ulp_sriov_cfg(bp, *num_vfs);
-
 	rc = pci_enable_sriov(bp->pdev, *num_vfs);
 	if (rc)
 		goto err_out2;
@@ -837,6 +864,11 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs)
 		rtnl_unlock();
 		return 0;
 	}
+	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
+		netdev_warn(dev, "Reject SRIOV config request when FW reset is in progress\n");
+		rtnl_unlock();
+		return 0;
+	}
 	bp->sriov_cfg = true;
 	rtnl_unlock();
 
@@ -870,7 +902,6 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 {
 	int rc = 0;
 	struct hwrm_fwd_resp_input req = {0};
-	struct hwrm_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr;
 
 	if (BNXT_FWD_RESP_SIZE_ERR(msg_size))
 		return -EINVAL;
@@ -885,22 +916,9 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 	req.encap_resp_cmpl_ring = encap_resp_cpr;
 	memcpy(req.encap_resp, encap_resp, msg_size);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-
-	if (rc) {
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
 		netdev_err(bp->dev, "hwrm_fwd_resp failed. rc:%d\n", rc);
-		goto fwd_resp_exit;
-	}
-
-	if (resp->error_code) {
-		netdev_err(bp->dev, "hwrm_fwd_resp error %d\n",
-			   resp->error_code);
-		rc = -1;
-	}
-
-fwd_resp_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
 
@@ -909,7 +927,6 @@ static int bnxt_hwrm_fwd_err_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 {
 	int rc = 0;
 	struct hwrm_reject_fwd_resp_input req = {0};
-	struct hwrm_reject_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr;
 
 	if (BNXT_REJ_FWD_RESP_SIZE_ERR(msg_size))
 		return -EINVAL;
@@ -920,22 +937,9 @@ static int bnxt_hwrm_fwd_err_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 	req.encap_resp_target_id = cpu_to_le16(vf->fw_fid);
 	memcpy(req.encap_request, vf->hwrm_cmd_req_addr, msg_size);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-
-	if (rc) {
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
 		netdev_err(bp->dev, "hwrm_fwd_err_resp failed. rc:%d\n", rc);
-		goto fwd_err_resp_exit;
-	}
-
-	if (resp->error_code) {
-		netdev_err(bp->dev, "hwrm_fwd_err_resp error %d\n",
-			   resp->error_code);
-		rc = -1;
-	}
-
-fwd_err_resp_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
 
@@ -944,7 +948,6 @@ static int bnxt_hwrm_exec_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 {
 	int rc = 0;
 	struct hwrm_exec_fwd_resp_input req = {0};
-	struct hwrm_exec_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr;
 
 	if (BNXT_EXEC_FWD_RESP_SIZE_ERR(msg_size))
 		return -EINVAL;
@@ -955,22 +958,9 @@ static int bnxt_hwrm_exec_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
 	req.encap_resp_target_id = cpu_to_le16(vf->fw_fid);
 	memcpy(req.encap_request, vf->hwrm_cmd_req_addr, msg_size);
 
-	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-
-	if (rc) {
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
 		netdev_err(bp->dev, "hwrm_exec_fw_resp failed. rc:%d\n", rc);
-		goto exec_fwd_resp_exit;
-	}
-
-	if (resp->error_code) {
-		netdev_err(bp->dev, "hwrm_exec_fw_resp error %d\n",
-			   resp->error_code);
-		rc = -1;
-	}
-
-exec_fwd_resp_exit:
-	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
 
@@ -1190,6 +1180,13 @@ int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict)
 }
 #else
 
+int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset)
+{
+	if (*num_vfs)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
 void bnxt_sriov_disable(struct bnxt *bp)
 {
 }

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

@@ -36,6 +36,7 @@ int bnxt_set_vf_link_state(struct net_device *, int, int);
 int bnxt_set_vf_spoofchk(struct net_device *, int, bool);
 int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trust);
 int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs);
+int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset);
 void bnxt_sriov_disable(struct bnxt *);
 void bnxt_hwrm_exec_fwd_req(struct bnxt *);
 void bnxt_update_vf_mac(struct bnxt *);

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

@@ -319,8 +319,6 @@ static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp,
 	if (rc)
 		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
 
-	if (rc)
-		rc = -EIO;
 	return rc;
 }
 
@@ -515,11 +513,6 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 		}
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
-
-	if (rc == HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR)
-		rc = -ENOSPC;
-	else if (rc)
-		rc = -EIO;
 	return rc;
 }
 
@@ -591,8 +584,6 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp,
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
-	if (rc)
-		rc = -EIO;
 	return rc;
 }
 
@@ -609,8 +600,6 @@ static int hwrm_cfa_decap_filter_free(struct bnxt *bp,
 	if (rc)
 		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
 
-	if (rc)
-		rc = -EIO;
 	return rc;
 }
 
@@ -660,8 +649,6 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
-	if (rc)
-		rc = -EIO;
 	return rc;
 }
 
@@ -678,8 +665,6 @@ static int hwrm_cfa_encap_record_free(struct bnxt *bp,
 	if (rc)
 		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
 
-	if (rc)
-		rc = -EIO;
 	return rc;
 }
 
@@ -1457,8 +1442,6 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
-	if (rc)
-		rc = -EIO;
 	return rc;
 }
 

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

@@ -226,6 +226,9 @@ static int bnxt_send_msg(struct bnxt_en_dev *edev, int ulp_id,
 	struct input *req;
 	int rc;
 
+	if (ulp_id != BNXT_ROCE_ULP && bp->fw_reset_state)
+		return -EBUSY;
+
 	mutex_lock(&bp->hwrm_cmd_lock);
 	req = fw_msg->msg;
 	req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr);