Merge branch 'bnxt_en-Error-recovery-fixes'

Michael Chan says:

====================
bnxt_en: Error recovery fixes.

This patch series contains fixes mostly for the error recovery feature
and related areas.  Please queue the series for -stable also.  Thanks.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -2001,6 +2001,9 @@ static int bnxt_async_event_process(struct bnxt *bp,
 	case ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY: {
 		u32 data1 = le32_to_cpu(cmpl->event_data1);
 
+		if (!bp->fw_health)
+			goto async_event_process_exit;
+
 		bp->fw_reset_timestamp = jiffies;
 		bp->fw_reset_min_dsecs = cmpl->timestamp_lo;
 		if (!bp->fw_reset_min_dsecs)
@@ -4421,8 +4424,9 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size,
 			    FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD);
 
 	req.os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX);
-	flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE |
-		FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT;
+	flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE;
+	if (bp->fw_cap & BNXT_FW_CAP_HOT_RESET)
+		flags |= 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 |
 			 FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT;
@@ -7115,14 +7119,6 @@ static int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp)
 	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)) {
@@ -8796,6 +8792,9 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 		if (fw_reset) {
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 				bnxt_ulp_stop(bp);
+			bnxt_free_ctx_mem(bp);
+			kfree(bp->ctx);
+			bp->ctx = NULL;
 			rc = bnxt_fw_init_one(bp);
 			if (rc) {
 				set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
@@ -9990,8 +9989,7 @@ 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))
+	if (!fw_health->enabled || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 		return;
 
 	if (fw_health->tmr_counter) {
@@ -10482,6 +10480,23 @@ static void bnxt_init_dflt_coal(struct bnxt *bp)
 	bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS;
 }
 
+static void bnxt_alloc_fw_health(struct bnxt *bp)
+{
+	if (bp->fw_health)
+		return;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) &&
+	    !(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY))
+		return;
+
+	bp->fw_health = kzalloc(sizeof(*bp->fw_health), GFP_KERNEL);
+	if (!bp->fw_health) {
+		netdev_warn(bp->dev, "Failed to allocate fw_health\n");
+		bp->fw_cap &= ~BNXT_FW_CAP_HOT_RESET;
+		bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY;
+	}
+}
+
 static int bnxt_fw_init_one_p1(struct bnxt *bp)
 {
 	int rc;
@@ -10528,6 +10543,7 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp)
 		netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n",
 			    rc);
 
+	bnxt_alloc_fw_health(bp);
 	rc = bnxt_hwrm_error_recovery_qcfg(bp);
 	if (rc)
 		netdev_warn(bp->dev, "hwrm query error recovery failure rc: %d\n",
@@ -10609,6 +10625,12 @@ static int bnxt_fw_init_one(struct bnxt *bp)
 	rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false);
 	if (rc)
 		return rc;
+
+	/* In case fw capabilities have changed, destroy the unneeded
+	 * reporters and create newly capable ones.
+	 */
+	bnxt_dl_fw_reporters_destroy(bp, false);
+	bnxt_dl_fw_reporters_create(bp);
 	bnxt_fw_init_one_p3(bp);
 	return 0;
 }
@@ -10751,8 +10773,7 @@ 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:
-		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) &&
-		    bp->fw_health) {
+		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) {
 			u32 val;
 
 			val = bnxt_fw_health_readl(bp,
@@ -11396,11 +11417,11 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (BNXT_PF(bp)) {
+	if (BNXT_PF(bp))
 		bnxt_sriov_disable(bp);
-		bnxt_dl_unregister(bp);
-	}
 
+	bnxt_dl_fw_reporters_destroy(bp, true);
+	bnxt_dl_unregister(bp);
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
 	bnxt_shutdown_tc(bp);
@@ -11415,6 +11436,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bnxt_dcb_free(bp);
 	kfree(bp->edev);
 	bp->edev = NULL;
+	kfree(bp->fw_health);
+	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
@@ -11875,8 +11898,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_cleanup_tc;
 
-	if (BNXT_PF(bp))
-		bnxt_dl_register(bp);
+	bnxt_dl_register(bp);
+	bnxt_dl_fw_reporters_create(bp);
 
 	netdev_info(dev, "%s found at mem %lx, node addr %pM\n",
 		    board_info[ent->driver_data].name,

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

@@ -39,11 +39,10 @@ static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
 				     struct netlink_ext_ack *extack)
 {
 	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))
+	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 		return 0;
 
 	val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG);
@@ -126,21 +125,15 @@ struct devlink_health_reporter_ops bnxt_dl_fw_fatal_reporter_ops = {
 	.recover = bnxt_fw_fatal_recover,
 };
 
-static void bnxt_dl_fw_reporters_create(struct bnxt *bp)
+void bnxt_dl_fw_reporters_create(struct bnxt *bp)
 {
 	struct bnxt_fw_health *health = bp->fw_health;
 
-	if (!health)
+	if (!bp->dl || !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;
-	}
+	if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) || health->fw_reset_reporter)
+		goto err_recovery;
 
 	health->fw_reset_reporter =
 		devlink_health_reporter_create(bp->dl,
@@ -150,8 +143,30 @@ static void bnxt_dl_fw_reporters_create(struct bnxt *bp)
 		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;
+		bp->fw_cap &= ~BNXT_FW_CAP_HOT_RESET;
+	}
+
+err_recovery:
+	if (!(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY))
+		return;
+
+	if (!health->fw_reporter) {
+		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;
+			bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY;
+			return;
+		}
 	}
 
+	if (health->fw_fatal_reporter)
+		return;
+
 	health->fw_fatal_reporter =
 		devlink_health_reporter_create(bp->dl,
 					       &bnxt_dl_fw_fatal_reporter_ops,
@@ -160,24 +175,35 @@ static void bnxt_dl_fw_reporters_create(struct bnxt *bp)
 		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;
+		bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY;
 	}
 }
 
-static void bnxt_dl_fw_reporters_destroy(struct bnxt *bp)
+void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all)
 {
 	struct bnxt_fw_health *health = bp->fw_health;
 
-	if (!health)
+	if (!bp->dl || !health)
 		return;
 
-	if (health->fw_reporter)
-		devlink_health_reporter_destroy(health->fw_reporter);
-
-	if (health->fw_reset_reporter)
+	if ((all || !(bp->fw_cap & BNXT_FW_CAP_HOT_RESET)) &&
+	    health->fw_reset_reporter) {
 		devlink_health_reporter_destroy(health->fw_reset_reporter);
+		health->fw_reset_reporter = NULL;
+	}
 
-	if (health->fw_fatal_reporter)
+	if ((bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) && !all)
+		return;
+
+	if (health->fw_reporter) {
+		devlink_health_reporter_destroy(health->fw_reporter);
+		health->fw_reporter = NULL;
+	}
+
+	if (health->fw_fatal_reporter) {
 		devlink_health_reporter_destroy(health->fw_fatal_reporter);
+		health->fw_fatal_reporter = NULL;
+	}
 }
 
 void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event)
@@ -185,9 +211,6 @@ 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:
@@ -247,6 +270,8 @@ static const struct devlink_ops bnxt_dl_ops = {
 	.flash_update	  = bnxt_dl_flash_update,
 };
 
+static const struct devlink_ops bnxt_vf_dl_ops;
+
 enum bnxt_dl_param_id {
 	BNXT_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK,
@@ -460,7 +485,10 @@ int bnxt_dl_register(struct bnxt *bp)
 		return -ENOTSUPP;
 	}
 
-	dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
+	if (BNXT_PF(bp))
+		dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
+	else
+		dl = devlink_alloc(&bnxt_vf_dl_ops, sizeof(struct bnxt_dl));
 	if (!dl) {
 		netdev_warn(bp->dev, "devlink_alloc failed");
 		return -ENOMEM;
@@ -479,6 +507,9 @@ int bnxt_dl_register(struct bnxt *bp)
 		goto err_dl_free;
 	}
 
+	if (!BNXT_PF(bp))
+		return 0;
+
 	rc = devlink_params_register(dl, bnxt_dl_params,
 				     ARRAY_SIZE(bnxt_dl_params));
 	if (rc) {
@@ -506,8 +537,6 @@ int bnxt_dl_register(struct bnxt *bp)
 
 	devlink_params_publish(dl);
 
-	bnxt_dl_fw_reporters_create(bp);
-
 	return 0;
 
 err_dl_port_unreg:
@@ -530,12 +559,14 @@ 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);
-	devlink_params_unregister(dl, bnxt_dl_params,
-				  ARRAY_SIZE(bnxt_dl_params));
+	if (BNXT_PF(bp)) {
+		devlink_port_params_unregister(&bp->dl_port,
+					       bnxt_dl_port_params,
+					       ARRAY_SIZE(bnxt_dl_port_params));
+		devlink_port_unregister(&bp->dl_port);
+		devlink_params_unregister(dl, bnxt_dl_params,
+					  ARRAY_SIZE(bnxt_dl_params));
+	}
 	devlink_unregister(dl);
 	devlink_free(dl);
 }

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

@@ -58,6 +58,8 @@ struct bnxt_dl_nvm_param {
 
 void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event);
 void bnxt_dl_health_status_update(struct bnxt *bp, bool healthy);
+void bnxt_dl_fw_reporters_create(struct bnxt *bp);
+void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all);
 int bnxt_dl_register(struct bnxt *bp);
 void bnxt_dl_unregister(struct bnxt *bp);
 

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

@@ -3071,8 +3071,15 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, int msg_len,
 			}
 		}
 
-		if (info->dest_buf)
-			memcpy(info->dest_buf + off, dma_buf, len);
+		if (info->dest_buf) {
+			if ((info->seg_start + off + len) <=
+			    BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
+				memcpy(info->dest_buf + off, dma_buf, len);
+			} else {
+				rc = -ENOBUFS;
+				break;
+			}
+		}
 
 		if (cmn_req->req_type ==
 				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
@@ -3126,7 +3133,7 @@ static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
 
 static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id,
 					   u16 segment_id, u32 *seg_len,
-					   void *buf, u32 offset)
+					   void *buf, u32 buf_len, u32 offset)
 {
 	struct hwrm_dbg_coredump_retrieve_input req = {0};
 	struct bnxt_hwrm_dbg_dma_info info = {NULL};
@@ -3141,8 +3148,11 @@ static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id,
 				seq_no);
 	info.data_len_off = offsetof(struct hwrm_dbg_coredump_retrieve_output,
 				     data_len);
-	if (buf)
+	if (buf) {
 		info.dest_buf = buf + offset;
+		info.buf_len = buf_len;
+		info.seg_start = offset;
+	}
 
 	rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info);
 	if (!rc)
@@ -3232,14 +3242,17 @@ bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record,
 static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
 {
 	u32 ver_get_resp_len = sizeof(struct hwrm_ver_get_output);
+	u32 offset = 0, seg_hdr_len, seg_record_len, buf_len = 0;
 	struct coredump_segment_record *seg_record = NULL;
-	u32 offset = 0, seg_hdr_len, seg_record_len;
 	struct bnxt_coredump_segment_hdr seg_hdr;
 	struct bnxt_coredump coredump = {NULL};
 	time64_t start_time;
 	u16 start_utc;
 	int rc = 0, i;
 
+	if (buf)
+		buf_len = *dump_len;
+
 	start_time = ktime_get_real_seconds();
 	start_utc = sys_tz.tz_minuteswest * 60;
 	seg_hdr_len = sizeof(seg_hdr);
@@ -3272,6 +3285,12 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
 		u32 duration = 0, seg_len = 0;
 		unsigned long start, end;
 
+		if (buf && ((offset + seg_hdr_len) >
+			    BNXT_COREDUMP_BUF_LEN(buf_len))) {
+			rc = -ENOBUFS;
+			goto err;
+		}
+
 		start = jiffies;
 
 		rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id);
@@ -3284,9 +3303,11 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
 
 		/* Write segment data into the buffer */
 		rc = bnxt_hwrm_dbg_coredump_retrieve(bp, comp_id, seg_id,
-						     &seg_len, buf,
+						     &seg_len, buf, buf_len,
 						     offset + seg_hdr_len);
-		if (rc)
+		if (rc && rc == -ENOBUFS)
+			goto err;
+		else if (rc)
 			netdev_err(bp->dev,
 				   "Failed to retrieve coredump for seg = %d\n",
 				   seg_record->segment_id);
@@ -3316,7 +3337,8 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
 					  rc);
 	kfree(coredump.data);
 	*dump_len += sizeof(struct bnxt_coredump_record);
-
+	if (rc == -ENOBUFS)
+		netdev_err(bp->dev, "Firmware returned large coredump buffer");
 	return rc;
 }
 

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

@@ -31,6 +31,8 @@ struct bnxt_coredump {
 	u16		total_segs;
 };
 
+#define BNXT_COREDUMP_BUF_LEN(len) ((len) - sizeof(struct bnxt_coredump_record))
+
 struct bnxt_hwrm_dbg_dma_info {
 	void *dest_buf;
 	int dest_buf_size;
@@ -38,6 +40,8 @@ struct bnxt_hwrm_dbg_dma_info {
 	u16 seq_off;
 	u16 data_len_off;
 	u16 segs;
+	u32 seg_start;
+	u32 buf_len;
 };
 
 struct hwrm_dbg_cmn_input {

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

@@ -113,8 +113,10 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 {
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_hw_resc *hw_resc;
 	int max_idx, max_cp_rings;
 	int avail_msix, idx;
+	int total_vecs;
 	int rc = 0;
 
 	ASSERT_RTNL();
@@ -142,7 +144,10 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 	}
 	edev->ulp_tbl[ulp_id].msix_base = idx;
 	edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
-	if (bp->total_irqs < (idx + avail_msix)) {
+	hw_resc = &bp->hw_resc;
+	total_vecs = idx + avail_msix;
+	if (bp->total_irqs < total_vecs ||
+	    (BNXT_NEW_RM(bp) && hw_resc->resv_irqs < total_vecs)) {
 		if (netif_running(dev)) {
 			bnxt_close_nic(bp, true, false);
 			rc = bnxt_open_nic(bp, true, false);
@@ -156,7 +161,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 	}
 
 	if (BNXT_NEW_RM(bp)) {
-		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 		int resv_msix;
 
 		resv_msix = hw_resc->resv_irqs - bp->cp_nr_rings;