be2net: gather debug info and reset adapter (only for Lancer) on a tx-timeout

This patch handles a TX-timeout as follows:

1) This patch gathers and prints the following info that can
   help in diagnosing the cause of a TX-timeout.
   a) TX queue and completion queue entries.
   b) SKB and TCP/UDP header details.

2) For Lancer NICs (TX-timeout recovery is not supported for
   BE3/Skyhawk-R NICs), it recovers from the TX timeout as follows:

   a) On a TX-timeout, driver sets the PHYSDEV_CONTROL_FW_RESET_MASK
      bit in the PHYSDEV_CONTROL register. Lancer firmware goes into
      an error state and indicates this back to the driver via a bit
      in a doorbell register.
   b) Driver detects this and calls be_err_recover(). DMA is disabled,
      all pending TX skbs are unmapped and freed (be_close()). All rings
      are destroyed (be_clear()).
   c) The driver waits for the FW to re-initialize and re-creates all
      rings along with other data structs (be_resume())

Signed-off-by: Suresh Reddy <suresh.reddy@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 79 insertions, 1 deletions

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 05e4c0bb25f4..580cdec2d2ce 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1412,6 +1412,83 @@ drop:
 	return NETDEV_TX_OK;
 }
 
+static void be_tx_timeout(struct net_device *netdev)
+{
+	struct be_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->pdev->dev;
+	struct be_tx_obj *txo;
+	struct sk_buff *skb;
+	struct tcphdr *tcphdr;
+	struct udphdr *udphdr;
+	u32 *entry;
+	int status;
+	int i, j;
+
+	for_all_tx_queues(adapter, txo, i) {
+		dev_info(dev, "TXQ Dump: %d H: %d T: %d used: %d, qid: 0x%x\n",
+			 i, txo->q.head, txo->q.tail,
+			 atomic_read(&txo->q.used), txo->q.id);
+
+		entry = txo->q.dma_mem.va;
+		for (j = 0; j < TX_Q_LEN * 4; j += 4) {
+			if (entry[j] != 0 || entry[j + 1] != 0 ||
+			    entry[j + 2] != 0 || entry[j + 3] != 0) {
+				dev_info(dev, "Entry %d 0x%x 0x%x 0x%x 0x%x\n",
+					 j, entry[j], entry[j + 1],
+					 entry[j + 2], entry[j + 3]);
+			}
+		}
+
+		entry = txo->cq.dma_mem.va;
+		dev_info(dev, "TXCQ Dump: %d  H: %d T: %d used: %d\n",
+			 i, txo->cq.head, txo->cq.tail,
+			 atomic_read(&txo->cq.used));
+		for (j = 0; j < TX_CQ_LEN * 4; j += 4) {
+			if (entry[j] != 0 || entry[j + 1] != 0 ||
+			    entry[j + 2] != 0 || entry[j + 3] != 0) {
+				dev_info(dev, "Entry %d 0x%x 0x%x 0x%x 0x%x\n",
+					 j, entry[j], entry[j + 1],
+					 entry[j + 2], entry[j + 3]);
+			}
+		}
+
+		for (j = 0; j < TX_Q_LEN; j++) {
+			if (txo->sent_skb_list[j]) {
+				skb = txo->sent_skb_list[j];
+				if (ip_hdr(skb)->protocol == IPPROTO_TCP) {
+					tcphdr = tcp_hdr(skb);
+					dev_info(dev, "TCP source port %d\n",
+						 ntohs(tcphdr->source));
+					dev_info(dev, "TCP dest port %d\n",
+						 ntohs(tcphdr->dest));
+					dev_info(dev, "TCP seqence num %d\n",
+						 ntohs(tcphdr->seq));
+					dev_info(dev, "TCP ack_seq %d\n",
+						 ntohs(tcphdr->ack_seq));
+				} else if (ip_hdr(skb)->protocol ==
+					   IPPROTO_UDP) {
+					udphdr = udp_hdr(skb);
+					dev_info(dev, "UDP source port %d\n",
+						 ntohs(udphdr->source));
+					dev_info(dev, "UDP dest port %d\n",
+						 ntohs(udphdr->dest));
+				}
+				dev_info(dev, "skb[%d] %p len %d proto 0x%x\n",
+					 j, skb, skb->len, skb->protocol);
+			}
+		}
+	}
+
+	if (lancer_chip(adapter)) {
+		dev_info(dev, "Initiating reset due to tx timeout\n");
+		dev_info(dev, "Resetting adapter\n");
+		status = lancer_physdev_ctrl(adapter,
+					     PHYSDEV_CONTROL_FW_RESET_MASK);
+		if (status)
+			dev_err(dev, "Reset failed .. Reboot server\n");
+	}
+}
+
 static inline bool be_in_all_promisc(struct be_adapter *adapter)
 {
 	return (adapter->if_flags & BE_IF_FLAGS_ALL_PROMISCUOUS) ==
@@ -3274,7 +3351,7 @@ void be_detect_error(struct be_adapter *adapter)
 			/* Do not log error messages if its a FW reset */
 			if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 &&
 			    sliport_err2 == SLIPORT_ERROR_FW_RESET2) {
-				dev_info(dev, "Firmware update in progress\n");
+				dev_info(dev, "Reset is in progress\n");
 			} else {
 				dev_err(dev, "Error detected in the card\n");
 				dev_err(dev, "ERR: sliport status 0x%x\n",
@@ -5218,6 +5295,7 @@ static const struct net_device_ops be_netdev_ops = {
 	.ndo_get_vf_config	= be_get_vf_config,
 	.ndo_set_vf_link_state  = be_set_vf_link_state,
 	.ndo_set_vf_spoofchk    = be_set_vf_spoofchk,
+	.ndo_tx_timeout		= be_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= be_netpoll,
 #endif