1 files changed, 144 insertions, 64 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index f56245eeef7b..8a97640cdfe7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -72,7 +72,8 @@
 #include "bnxt_debugfs.h"
 
 #define BNXT_TX_TIMEOUT		(5 * HZ)
-#define BNXT_DEF_MSG_ENABLE	(NETIF_MSG_DRV | NETIF_MSG_HW)
+#define BNXT_DEF_MSG_ENABLE	(NETIF_MSG_DRV | NETIF_MSG_HW | \
+				 NETIF_MSG_TX_ERR)
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Broadcom BCM573xx network driver");
@@ -365,6 +366,33 @@ static u16 bnxt_xmit_get_cfa_action(struct sk_buff *skb)
 	return md_dst->u.port_info.port_id;
 }
 
+static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			     u16 prod)
+{
+	bnxt_db_write(bp, &txr->tx_db, prod);
+	txr->kick_pending = 0;
+}
+
+static bool bnxt_txr_netif_try_stop_queue(struct bnxt *bp,
+					  struct bnxt_tx_ring_info *txr,
+					  struct netdev_queue *txq)
+{
+	netif_tx_stop_queue(txq);
+
+	/* netif_tx_stop_queue() must be done before checking
+	 * tx index in bnxt_tx_avail() below, because in
+	 * bnxt_tx_int(), we update tx index before checking for
+	 * netif_tx_queue_stopped().
+	 */
+	smp_mb();
+	if (bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh) {
+		netif_tx_wake_queue(txq);
+		return false;
+	}
+
+	return true;
+}
+
 static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -384,6 +412,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	i = skb_get_queue_mapping(skb);
 	if (unlikely(i >= bp->tx_nr_rings)) {
 		dev_kfree_skb_any(skb);
+		atomic_long_inc(&dev->tx_dropped);
 		return NETDEV_TX_OK;
 	}
 
@@ -393,8 +422,12 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	free_size = bnxt_tx_avail(bp, txr);
 	if (unlikely(free_size < skb_shinfo(skb)->nr_frags + 2)) {
-		netif_tx_stop_queue(txq);
-		return NETDEV_TX_BUSY;
+		/* We must have raced with NAPI cleanup */
+		if (net_ratelimit() && txr->kick_pending)
+			netif_warn(bp, tx_err, dev,
+				   "bnxt: ring busy w/ flush pending!\n");
+		if (bnxt_txr_netif_try_stop_queue(bp, txr, txq))
+			return NETDEV_TX_BUSY;
 	}
 
 	length = skb->len;
@@ -426,7 +459,10 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		if (ptp && ptp->tx_tstamp_en && !skb_is_gso(skb) &&
 		    atomic_dec_if_positive(&ptp->tx_avail) >= 0) {
-			if (!bnxt_ptp_parse(skb, &ptp->tx_seqid)) {
+			if (!bnxt_ptp_parse(skb, &ptp->tx_seqid,
+					    &ptp->tx_hdr_off)) {
+				if (vlan_tag_flags)
+					ptp->tx_hdr_off += VLAN_HLEN;
 				lflags |= cpu_to_le32(TX_BD_FLAGS_STAMP);
 				skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			} else {
@@ -514,21 +550,16 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 normal_tx:
 	if (length < BNXT_MIN_PKT_SIZE) {
 		pad = BNXT_MIN_PKT_SIZE - length;
-		if (skb_pad(skb, pad)) {
+		if (skb_pad(skb, pad))
 			/* SKB already freed. */
-			tx_buf->skb = NULL;
-			return NETDEV_TX_OK;
-		}
+			goto tx_kick_pending;
 		length = BNXT_MIN_PKT_SIZE;
 	}
 
 	mapping = dma_map_single(&pdev->dev, skb->data, len, DMA_TO_DEVICE);
 
-	if (unlikely(dma_mapping_error(&pdev->dev, mapping))) {
-		dev_kfree_skb_any(skb);
-		tx_buf->skb = NULL;
-		return NETDEV_TX_OK;
-	}
+	if (unlikely(dma_mapping_error(&pdev->dev, mapping)))
+		goto tx_free;
 
 	dma_unmap_addr_set(tx_buf, mapping, mapping);
 	flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD |
@@ -615,24 +646,17 @@ normal_tx:
 	txr->tx_prod = prod;
 
 	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
-		bnxt_db_write(bp, &txr->tx_db, prod);
+		bnxt_txr_db_kick(bp, txr, prod);
+	else
+		txr->kick_pending = 1;
 
 tx_done:
 
 	if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
 		if (netdev_xmit_more() && !tx_buf->is_push)
-			bnxt_db_write(bp, &txr->tx_db, prod);
-
-		netif_tx_stop_queue(txq);
+			bnxt_txr_db_kick(bp, txr, prod);
 
-		/* netif_tx_stop_queue() must be done before checking
-		 * tx index in bnxt_tx_avail() below, because in
-		 * bnxt_tx_int(), we update tx index before checking for
-		 * netif_tx_queue_stopped().
-		 */
-		smp_mb();
-		if (bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh)
-			netif_tx_wake_queue(txq);
+		bnxt_txr_netif_try_stop_queue(bp, txr, txq);
 	}
 	return NETDEV_TX_OK;
 
@@ -645,7 +669,6 @@ tx_dma_error:
 	/* start back at beginning and unmap skb */
 	prod = txr->tx_prod;
 	tx_buf = &txr->tx_buf_ring[prod];
-	tx_buf->skb = NULL;
 	dma_unmap_single(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
 			 skb_headlen(skb), PCI_DMA_TODEVICE);
 	prod = NEXT_TX(prod);
@@ -659,7 +682,13 @@ tx_dma_error:
 			       PCI_DMA_TODEVICE);
 	}
 
+tx_free:
 	dev_kfree_skb_any(skb);
+tx_kick_pending:
+	if (txr->kick_pending)
+		bnxt_txr_db_kick(bp, txr, txr->tx_prod);
+	txr->tx_buf_ring[txr->tx_prod].skb = NULL;
+	atomic_long_inc(&dev->tx_dropped);
 	return NETDEV_TX_OK;
 }
 
@@ -729,14 +758,9 @@ next_tx_int:
 	smp_mb();
 
 	if (unlikely(netif_tx_queue_stopped(txq)) &&
-	    (bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh)) {
-		__netif_tx_lock(txq, smp_processor_id());
-		if (netif_tx_queue_stopped(txq) &&
-		    bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh &&
-		    txr->dev_state != BNXT_DEV_STATE_CLOSING)
-			netif_tx_wake_queue(txq);
-		__netif_tx_unlock(txq);
-	}
+	    bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh &&
+	    READ_ONCE(txr->dev_state) != BNXT_DEV_STATE_CLOSING)
+		netif_tx_wake_queue(txq);
 }
 
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
@@ -1671,11 +1695,16 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 
 	if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) &&
 	    (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
-		u16 vlan_proto = tpa_info->metadata >>
-			RX_CMP_FLAGS2_METADATA_TPID_SFT;
+		__be16 vlan_proto = htons(tpa_info->metadata >>
+					  RX_CMP_FLAGS2_METADATA_TPID_SFT);
 		u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK;
 
-		__vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
+		if (eth_type_vlan(vlan_proto)) {
+			__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+		} else {
+			dev_kfree_skb(skb);
+			return NULL;
+		}
 	}
 
 	skb_checksum_none_assert(skb);
@@ -1759,6 +1788,10 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons))
 		return -EBUSY;
 
+	/* The valid test of the entry must be done first before
+	 * reading any further.
+	 */
+	dma_rmb();
 	prod = rxr->rx_prod;
 
 	if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP) {
@@ -1897,9 +1930,15 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	    (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
 		u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
 		u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK;
-		u16 vlan_proto = meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT;
+		__be16 vlan_proto = htons(meta_data >>
+					  RX_CMP_FLAGS2_METADATA_TPID_SFT);
 
-		__vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
+		if (eth_type_vlan(vlan_proto)) {
+			__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+		} else {
+			dev_kfree_skb(skb);
+			goto next_rx;
+		}
 	}
 
 	skb_checksum_none_assert(skb);
@@ -1975,6 +2014,10 @@ static int bnxt_force_rx_discard(struct bnxt *bp,
 	if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons))
 		return -EBUSY;
 
+	/* The valid test of the entry must be done first before
+	 * reading any further.
+	 */
+	dma_rmb();
 	cmp_type = RX_CMP_TYPE(rxcmp);
 	if (cmp_type == CMP_TYPE_RX_L2_CMP) {
 		rxcmp1->rx_cmp_cfa_code_errors_v2 |=
@@ -2440,6 +2483,10 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget)
 		if (!TX_CMP_VALID(txcmp, raw_cons))
 			break;
 
+		/* The valid test of the entry must be done first before
+		 * reading any further.
+		 */
+		dma_rmb();
 		if ((TX_CMP_TYPE(txcmp) & 0x30) == 0x10) {
 			tmp_raw_cons = NEXT_RAW_CMP(raw_cons);
 			cp_cons = RING_CMP(tmp_raw_cons);
@@ -7563,8 +7610,12 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->flags &= ~BNXT_FLAG_WOL_CAP;
 		if (flags & FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED)
 			bp->flags |= BNXT_FLAG_WOL_CAP;
-		if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED)
+		if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED) {
 			__bnxt_hwrm_ptp_qcfg(bp);
+		} else {
+			kfree(bp->ptp_cfg);
+			bp->ptp_cfg = NULL;
+		}
 	} else {
 #ifdef CONFIG_BNXT_SRIOV
 		struct bnxt_vf_info *vf = &bp->vf;
@@ -9110,10 +9161,9 @@ static void bnxt_disable_napi(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring;
 
+		napi_disable(&bp->bnapi[i]->napi);
 		if (bp->bnapi[i]->rx_ring)
 			cancel_work_sync(&cpr->dim.work);
-
-		napi_disable(&bp->bnapi[i]->napi);
 	}
 }
 
@@ -9147,9 +9197,11 @@ void bnxt_tx_disable(struct bnxt *bp)
 	if (bp->tx_ring) {
 		for (i = 0; i < bp->tx_nr_rings; i++) {
 			txr = &bp->tx_ring[i];
-			txr->dev_state = BNXT_DEV_STATE_CLOSING;
+			WRITE_ONCE(txr->dev_state, BNXT_DEV_STATE_CLOSING);
 		}
 	}
+	/* Make sure napi polls see @dev_state change */
+	synchronize_net();
 	/* Drop carrier first to prevent TX timeout */
 	netif_carrier_off(bp->dev);
 	/* Stop all TX queues */
@@ -9163,8 +9215,10 @@ void bnxt_tx_enable(struct bnxt *bp)
 
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		txr = &bp->tx_ring[i];
-		txr->dev_state = 0;
+		WRITE_ONCE(txr->dev_state, 0);
 	}
+	/* Make sure napi polls see @dev_state change */
+	synchronize_net();
 	netif_tx_wake_all_queues(bp->dev);
 	if (bp->link_info.link_up)
 		netif_carrier_on(bp->dev);
@@ -10123,7 +10177,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		}
 	}
 
-	bnxt_ptp_start(bp);
 	rc = bnxt_init_nic(bp, irq_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
@@ -10197,6 +10250,12 @@ int bnxt_half_open_nic(struct bnxt *bp)
 {
 	int rc = 0;
 
+	if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
+		netdev_err(bp->dev, "A previous firmware reset has not completed, aborting half open\n");
+		rc = -ENODEV;
+		goto half_open_err;
+	}
+
 	rc = bnxt_alloc_mem(bp, false);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
@@ -10256,9 +10315,16 @@ static int bnxt_open(struct net_device *dev)
 	rc = bnxt_hwrm_if_change(bp, true);
 	if (rc)
 		return rc;
+
+	if (bnxt_ptp_init(bp)) {
+		netdev_warn(dev, "PTP initialization failed.\n");
+		kfree(bp->ptp_cfg);
+		bp->ptp_cfg = NULL;
+	}
 	rc = __bnxt_open_nic(bp, true, true);
 	if (rc) {
 		bnxt_hwrm_if_change(bp, false);
+		bnxt_ptp_clear(bp);
 	} else {
 		if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) {
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
@@ -10349,6 +10415,7 @@ static int bnxt_close(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
+	bnxt_ptp_clear(bp);
 	bnxt_hwmon_close(bp);
 	bnxt_close_nic(bp, true, true);
 	bnxt_hwrm_shutdown_link(bp);
@@ -10737,6 +10804,9 @@ static bool bnxt_rfs_supported(struct bnxt *bp)
 			return true;
 		return false;
 	}
+	/* 212 firmware is broken for aRFS */
+	if (BNXT_FW_MAJ(bp) == 212)
+		return false;
 	if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return true;
 	if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
@@ -11335,6 +11405,7 @@ static void bnxt_fw_reset_close(struct bnxt *bp)
 		bnxt_clear_int_mode(bp);
 		pci_disable_device(bp->pdev);
 	}
+	bnxt_ptp_clear(bp);
 	__bnxt_close_nic(bp, true, false);
 	bnxt_vf_reps_free(bp);
 	bnxt_clear_int_mode(bp);
@@ -11959,10 +12030,21 @@ static bool bnxt_fw_reset_timeout(struct bnxt *bp)
 			  (bp->fw_reset_max_dsecs * HZ / 10));
 }
 
+static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
+{
+	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+	if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF) {
+		bnxt_ulp_start(bp, rc);
+		bnxt_dl_health_status_update(bp, false);
+	}
+	bp->fw_reset_state = 0;
+	dev_close(bp->dev);
+}
+
 static void bnxt_fw_reset_task(struct work_struct *work)
 {
 	struct bnxt *bp = container_of(work, struct bnxt, fw_reset_task.work);
-	int rc;
+	int rc = 0;
 
 	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");
@@ -11992,6 +12074,11 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		}
 		bp->fw_reset_timestamp = jiffies;
 		rtnl_lock();
+		if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
+			bnxt_fw_reset_abort(bp, rc);
+			rtnl_unlock();
+			return;
+		}
 		bnxt_fw_reset_close(bp);
 		if (bp->fw_cap & BNXT_FW_CAP_ERR_RECOVER_RELOAD) {
 			bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW_DOWN;
@@ -12039,6 +12126,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			if (val == 0xffff) {
 				if (bnxt_fw_reset_timeout(bp)) {
 					netdev_err(bp->dev, "Firmware reset aborted, PCI config space invalid\n");
+					rc = -ETIMEDOUT;
 					goto fw_reset_abort;
 				}
 				bnxt_queue_fw_reset_work(bp, HZ / 1000);
@@ -12048,6 +12136,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		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");
+			rc = -ENODEV;
 			goto fw_reset_abort;
 		}
 		pci_set_master(bp->pdev);
@@ -12074,18 +12163,18 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		}
 		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);
+			netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
+			bnxt_fw_reset_abort(bp, rc);
+			rtnl_unlock();
+			return;
 		}
 
 		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);
-		bnxt_ulp_start(bp, rc);
-		if (!rc)
-			bnxt_reenable_sriov(bp);
+		bnxt_ulp_start(bp, 0);
+		bnxt_reenable_sriov(bp);
 		bnxt_vf_reps_alloc(bp);
 		bnxt_vf_reps_open(bp);
 		bnxt_dl_health_recovery_done(bp);
@@ -12103,12 +12192,8 @@ fw_reset_abort_status:
 		netdev_err(bp->dev, "fw_health_status 0x%x\n", sts);
 	}
 fw_reset_abort:
-	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-	if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
-		bnxt_dl_health_status_update(bp, false);
-	bp->fw_reset_state = 0;
 	rtnl_lock();
-	dev_close(bp->dev);
+	bnxt_fw_reset_abort(bp, rc);
 	rtnl_unlock();
 }
 
@@ -12662,7 +12747,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	if (BNXT_PF(bp))
 		devlink_port_type_clear(&bp->dl_port);
 
-	bnxt_ptp_clear(bp);
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
@@ -13246,11 +13330,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 				   rc);
 	}
 
-	if (bnxt_ptp_init(bp)) {
-		netdev_warn(dev, "PTP initialization failed.\n");
-		kfree(bp->ptp_cfg);
-		bp->ptp_cfg = NULL;
-	}
 	bnxt_inv_fw_health_reg(bp);
 	bnxt_dl_register(bp);
 
@@ -13436,7 +13515,8 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	if (netif_running(netdev))
 		bnxt_close(netdev);
 
-	pci_disable_device(pdev);
+	if (pci_is_enabled(pdev))
+		pci_disable_device(pdev);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
 	bp->ctx = NULL;