Merge branch 'liquidio-next'

Raghu Vatsavayi says:

====================
liquidio: updates and bug fixes

Please consider following patch series for liquidio bug fixes
and updates on top of net-next. Following patches should be
applied in the following order as some of them depend on
earlier patches in the series.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/cavium/liquidio/cn66xx_device.c

@@ -367,7 +367,8 @@ void lio_cn6xxx_enable_io_queues(struct octeon_device *oct)
 
 void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 {
-	u32 mask, i, loop = HZ;
+	int i;
+	u32 mask, loop = HZ;
 	u32 d32;
 
 	/* Reset the Enable bits for Input Queues. */
@@ -376,7 +377,7 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 	octeon_write_csr(oct, CN6XXX_SLI_PKT_INSTR_ENB, mask);
 
 	/* Wait until hardware indicates that the queues are out of reset. */
-	mask = oct->io_qmask.iq;
+	mask = (u32)oct->io_qmask.iq;
 	d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_IQ);
 	while (((d32 & mask) != mask) && loop--) {
 		d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_IQ);
@@ -384,8 +385,8 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 	}
 
 	/* Reset the doorbell register for each Input queue. */
-	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-		if (!(oct->io_qmask.iq & (1UL << i)))
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+		if (!(oct->io_qmask.iq & (1ULL << i)))
 			continue;
 		octeon_write_csr(oct, CN6XXX_SLI_IQ_DOORBELL(i), 0xFFFFFFFF);
 		d32 = octeon_read_csr(oct, CN6XXX_SLI_IQ_DOORBELL(i));
@@ -398,7 +399,7 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 
 	/* Wait until hardware indicates that the queues are out of reset. */
 	loop = HZ;
-	mask = oct->io_qmask.oq;
+	mask = (u32)oct->io_qmask.oq;
 	d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_OQ);
 	while (((d32 & mask) != mask) && loop--) {
 		d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_OQ);
@@ -408,8 +409,8 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 
 	/* Reset the doorbell register for each Output queue. */
 	/* for (i = 0; i < oct->num_oqs; i++) { */
-	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-		if (!(oct->io_qmask.oq & (1UL << i)))
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+		if (!(oct->io_qmask.oq & (1ULL << i)))
 			continue;
 		octeon_write_csr(oct, CN6XXX_SLI_OQ_PKTS_CREDIT(i), 0xFFFFFFFF);
 		d32 = octeon_read_csr(oct, CN6XXX_SLI_OQ_PKTS_CREDIT(i));
@@ -429,16 +430,16 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
 
 void lio_cn6xxx_reinit_regs(struct octeon_device *oct)
 {
-	u32 i;
+	int i;
 
-	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-		if (!(oct->io_qmask.iq & (1UL << i)))
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+		if (!(oct->io_qmask.iq & (1ULL << i)))
 			continue;
 		oct->fn_list.setup_iq_regs(oct, i);
 	}
 
-	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-		if (!(oct->io_qmask.oq & (1UL << i)))
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+		if (!(oct->io_qmask.oq & (1ULL << i)))
 			continue;
 		oct->fn_list.setup_oq_regs(oct, i);
 	}
@@ -450,8 +451,8 @@ void lio_cn6xxx_reinit_regs(struct octeon_device *oct)
 	oct->fn_list.enable_io_queues(oct);
 
 	/* for (i = 0; i < oct->num_oqs; i++) { */
-	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-		if (!(oct->io_qmask.oq & (1UL << i)))
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+		if (!(oct->io_qmask.oq & (1ULL << i)))
 			continue;
 		writel(oct->droq[i]->max_count, oct->droq[i]->pkts_credit_reg);
 	}
@@ -495,8 +496,7 @@ u32 lio_cn6xxx_bar1_idx_read(struct octeon_device *oct, u32 idx)
 }
 
 u32
-lio_cn6xxx_update_read_index(struct octeon_device *oct __attribute__((unused)),
-			     struct octeon_instr_queue *iq)
+lio_cn6xxx_update_read_index(struct octeon_instr_queue *iq)
 {
 	u32 new_idx = readl(iq->inst_cnt_reg);
 
@@ -557,7 +557,8 @@ lio_cn6xxx_process_pcie_error_intr(struct octeon_device *oct, u64 intr64)
 int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct)
 {
 	struct octeon_droq *droq;
-	u32 oq_no, pkt_count, droq_time_mask, droq_mask, droq_int_enb;
+	int oq_no;
+	u32 pkt_count, droq_time_mask, droq_mask, droq_int_enb;
 	u32 droq_cnt_enb, droq_cnt_mask;
 
 	droq_cnt_enb = octeon_read_csr(oct, CN6XXX_SLI_PKT_CNT_INT_ENB);
@@ -573,8 +574,8 @@ int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct)
 	oct->droq_intr = 0;
 
 	/* for (oq_no = 0; oq_no < oct->num_oqs; oq_no++) { */
-	for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES; oq_no++) {
-		if (!(droq_mask & (1 << oq_no)))
+	for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES(oct); oq_no++) {
+		if (!(droq_mask & (1ULL << oq_no)))
 			continue;
 
 		droq = oct->droq[oq_no];

drivers/net/ethernet/cavium/liquidio/cn66xx_device.h

@@ -91,8 +91,7 @@ void lio_cn6xxx_bar1_idx_setup(struct octeon_device *oct, u64 core_addr,
 void lio_cn6xxx_bar1_idx_write(struct octeon_device *oct, u32 idx, u32 mask);
 u32 lio_cn6xxx_bar1_idx_read(struct octeon_device *oct, u32 idx);
 u32
-lio_cn6xxx_update_read_index(struct octeon_device *oct __attribute__((unused)),
-			     struct octeon_instr_queue *iq);
+lio_cn6xxx_update_read_index(struct octeon_instr_queue *iq);
 void lio_cn6xxx_enable_interrupt(void *chip);
 void lio_cn6xxx_disable_interrupt(void *chip);
 void cn6xxx_get_pcie_qlmport(struct octeon_device *oct);

drivers/net/ethernet/cavium/liquidio/lio_ethtool.c

@@ -40,6 +40,8 @@
 #include "cn68xx_device.h"
 #include "liquidio_image.h"
 
+static int octnet_get_link_stats(struct net_device *netdev);
+
 struct oct_mdio_cmd_context {
 	int octeon_id;
 	wait_queue_head_t wc;
@@ -71,34 +73,120 @@ enum {
 	INTERFACE_MODE_RXAUI,
 	INTERFACE_MODE_QSGMII,
 	INTERFACE_MODE_AGL,
+	INTERFACE_MODE_XLAUI,
+	INTERFACE_MODE_XFI,
+	INTERFACE_MODE_10G_KR,
+	INTERFACE_MODE_40G_KR4,
+	INTERFACE_MODE_MIXED,
 };
 
 #define ARRAY_LENGTH(a) (sizeof(a) / sizeof((a)[0]))
 #define OCT_ETHTOOL_REGDUMP_LEN  4096
 #define OCT_ETHTOOL_REGSVER  1
 
+/* statistics of PF */
+static const char oct_stats_strings[][ETH_GSTRING_LEN] = {
+	"rx_packets",
+	"tx_packets",
+	"rx_bytes",
+	"tx_bytes",
+	"rx_errors",	/*jabber_err+l2_err+frame_err */
+	"tx_errors",	/*fw_err_pko+fw_err_link+fw_err_drop */
+	"rx_dropped",   /*st->fromwire.total_rcvd - st->fromwire.fw_total_rcvd
+			*+st->fromwire.dmac_drop + st->fromwire.fw_err_drop
+			*/
+	"tx_dropped",
+
+	"tx_total_sent",
+	"tx_total_fwd",
+	"tx_err_pko",
+	"tx_err_link",
+	"tx_err_drop",
+
+	"tx_tso",
+	"tx_tso_packets",
+	"tx_tso_err",
+
+	"mac_tx_total_pkts",
+	"mac_tx_total_bytes",
+	"mac_tx_mcast_pkts",
+	"mac_tx_bcast_pkts",
+	"mac_tx_ctl_packets",	/*oct->link_stats.fromhost.ctl_sent */
+	"mac_tx_total_collisions",
+	"mac_tx_one_collision",
+	"mac_tx_multi_collison",
+	"mac_tx_max_collision_fail",
+	"mac_tx_max_deferal_fail",
+	"mac_tx_fifo_err",
+	"mac_tx_runts",
+
+	"rx_total_rcvd",
+	"rx_total_fwd",
+	"rx_jabber_err",
+	"rx_l2_err",
+	"rx_frame_err",
+	"rx_err_pko",
+	"rx_err_link",
+	"rx_err_drop",
+
+	"rx_lro_pkts",
+	"rx_lro_bytes",
+	"rx_total_lro",
+
+	"rx_lro_aborts",
+	"rx_lro_aborts_port",
+	"rx_lro_aborts_seq",
+	"rx_lro_aborts_tsval",
+	"rx_lro_aborts_timer",
+	"rx_fwd_rate",
+
+	"mac_rx_total_rcvd",
+	"mac_rx_bytes",
+	"mac_rx_total_bcst",
+	"mac_rx_total_mcst",
+	"mac_rx_runts",
+	"mac_rx_ctl_packets",
+	"mac_rx_fifo_err",
+	"mac_rx_dma_drop",
+	"mac_rx_fcs_err",
+
+	"link_state_changes",
+};
+
+/* statistics of host tx queue */
 static const char oct_iq_stats_strings[][ETH_GSTRING_LEN] = {
-	"Instr posted",
-	"Instr processed",
-	"Instr dropped",
-	"Bytes Sent",
-	"Sgentry_sent",
-	"Inst cntreg",
-	"Tx done",
-	"Tx Iq busy",
-	"Tx dropped",
-	"Tx bytes",
+	"packets",		/*oct->instr_queue[iq_no]->stats.tx_done*/
+	"bytes",		/*oct->instr_queue[iq_no]->stats.tx_tot_bytes*/
+	"dropped",
+	"iq_busy",
+	"sgentry_sent",
+
+	"fw_instr_posted",
+	"fw_instr_processed",
+	"fw_instr_dropped",
+	"fw_bytes_sent",
+
+	"tso",
+	"txq_restart",
 };
 
+/* statistics of host rx queue */
 static const char oct_droq_stats_strings[][ETH_GSTRING_LEN] = {
-	"OQ Pkts Received",
-	"OQ Bytes Received",
-	"Dropped no dispatch",
-	"Dropped nomem",
-	"Dropped toomany",
-	"Stack RX cnt",
-	"Stack RX Bytes",
-	"RX dropped",
+	"packets",		/*oct->droq[oq_no]->stats.rx_pkts_received */
+	"bytes",		/*oct->droq[oq_no]->stats.rx_bytes_received */
+	"dropped",		/*oct->droq[oq_no]->stats.rx_dropped+
+				 *oct->droq[oq_no]->stats.dropped_nodispatch+
+				 *oct->droq[oq_no]->stats.dropped_toomany+
+				 *oct->droq[oq_no]->stats.dropped_nomem
+				 */
+	"dropped_nomem",
+	"dropped_toomany",
+	"fw_dropped",
+	"fw_pkts_received",
+	"fw_bytes_received",
+	"fw_dropped_nodispatch",
+
+	"buffer_alloc_failure",
 };
 
 #define OCTNIC_NCMD_AUTONEG_ON  0x1
@@ -112,8 +200,9 @@ static int lio_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 
 	linfo = &lio->linfo;
 
-	if (linfo->link.s.interface == INTERFACE_MODE_XAUI ||
-	    linfo->link.s.interface == INTERFACE_MODE_RXAUI) {
+	if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI ||
+	    linfo->link.s.if_mode == INTERFACE_MODE_RXAUI ||
+	    linfo->link.s.if_mode == INTERFACE_MODE_XFI) {
 		ecmd->port = PORT_FIBRE;
 		ecmd->supported =
 			(SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE |
@@ -124,7 +213,8 @@ static int lio_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 		ecmd->autoneg = AUTONEG_DISABLE;
 
 	} else {
-		dev_err(&oct->pci_dev->dev, "Unknown link interface reported\n");
+		dev_err(&oct->pci_dev->dev, "Unknown link interface reported %d\n",
+			linfo->link.s.if_mode);
 	}
 
 	if (linfo->link.s.link_up) {
@@ -516,8 +606,13 @@ lio_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 	/* Notes: Not supporting any auto negotiation in these
 	 * drivers. Just report pause frame support.
 	 */
-	pause->tx_pause = 1;
-	pause->rx_pause = 1;    /* TODO: Need to support RX pause frame!!. */
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+
+	pause->autoneg = 0;
+
+	pause->tx_pause = oct->tx_pause;
+	pause->rx_pause = oct->rx_pause;
 }
 
 static void
@@ -526,51 +621,245 @@ lio_get_ethtool_stats(struct net_device *netdev,
 {
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct_dev = lio->oct_dev;
+	struct net_device_stats *netstats = &netdev->stats;
 	int i = 0, j;
 
-	for (j = 0; j < MAX_OCTEON_INSTR_QUEUES; j++) {
-		if (!(oct_dev->io_qmask.iq & (1UL << j)))
+	netdev->netdev_ops->ndo_get_stats(netdev);
+	octnet_get_link_stats(netdev);
+
+	/*sum of oct->droq[oq_no]->stats->rx_pkts_received */
+	data[i++] = CVM_CAST64(netstats->rx_packets);
+	/*sum of oct->instr_queue[iq_no]->stats.tx_done */
+	data[i++] = CVM_CAST64(netstats->tx_packets);
+	/*sum of oct->droq[oq_no]->stats->rx_bytes_received */
+	data[i++] = CVM_CAST64(netstats->rx_bytes);
+	/*sum of oct->instr_queue[iq_no]->stats.tx_tot_bytes */
+	data[i++] = CVM_CAST64(netstats->tx_bytes);
+	data[i++] = CVM_CAST64(netstats->rx_errors);
+	data[i++] = CVM_CAST64(netstats->tx_errors);
+	/*sum of oct->droq[oq_no]->stats->rx_dropped +
+	 *oct->droq[oq_no]->stats->dropped_nodispatch +
+	 *oct->droq[oq_no]->stats->dropped_toomany +
+	 *oct->droq[oq_no]->stats->dropped_nomem
+	 */
+	data[i++] = CVM_CAST64(netstats->rx_dropped);
+	/*sum of oct->instr_queue[iq_no]->stats.tx_dropped */
+	data[i++] = CVM_CAST64(netstats->tx_dropped);
+
+	/*data[i++] = CVM_CAST64(stats->multicast); */
+	/*data[i++] = CVM_CAST64(stats->collisions); */
+
+	/* firmware tx stats */
+	/*per_core_stats[cvmx_get_core_num()].link_stats[mdata->from_ifidx].
+	 *fromhost.fw_total_sent
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_total_sent);
+	/*per_core_stats[i].link_stats[port].fromwire.fw_total_fwd */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_total_fwd);
+	/*per_core_stats[j].link_stats[i].fromhost.fw_err_pko */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_pko);
+	/*per_core_stats[j].link_stats[i].fromhost.fw_err_link */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_link);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[idx].fromhost.
+	 *fw_err_drop
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_drop);
+
+	/*per_core_stats[cvmx_get_core_num()].link_stats[idx].fromhost.fw_tso */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_tso);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[idx].fromhost.
+	 *fw_tso_fwd
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_tso_fwd);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[idx].fromhost.
+	 *fw_err_tso
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_tso);
+
+	/* mac tx statistics */
+	/*CVMX_BGXX_CMRX_TX_STAT5 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.total_pkts_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT4 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.total_bytes_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT15 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.mcast_pkts_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT14 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.bcast_pkts_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT17 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.ctl_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT0 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.total_collisions);
+	/*CVMX_BGXX_CMRX_TX_STAT3 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.one_collision_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT2 */
+	data[i++] =
+		CVM_CAST64(oct_dev->link_stats.fromhost.multi_collision_sent);
+	/*CVMX_BGXX_CMRX_TX_STAT0 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.max_collision_fail);
+	/*CVMX_BGXX_CMRX_TX_STAT1 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.max_deferral_fail);
+	/*CVMX_BGXX_CMRX_TX_STAT16 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fifo_err);
+	/*CVMX_BGXX_CMRX_TX_STAT6 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.runts);
+
+	/* RX firmware stats */
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_total_rcvd
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_total_rcvd);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_total_fwd
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_total_fwd);
+	/*per_core_stats[core_id].link_stats[ifidx].fromwire.jabber_err */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.jabber_err);
+	/*per_core_stats[core_id].link_stats[ifidx].fromwire.l2_err */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.l2_err);
+	/*per_core_stats[core_id].link_stats[ifidx].fromwire.frame_err */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.frame_err);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_err_pko
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_err_pko);
+	/*per_core_stats[j].link_stats[i].fromwire.fw_err_link */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_err_link);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[lro_ctx->ifidx].
+	 *fromwire.fw_err_drop
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_err_drop);
+
+	/* LRO */
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_pkts
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_pkts);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_octs
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_octs);
+	/*per_core_stats[j].link_stats[i].fromwire.fw_total_lro */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_total_lro);
+	/*per_core_stats[j].link_stats[i].fromwire.fw_lro_aborts */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_aborts);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_aborts_port
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_aborts_port);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_aborts_seq
+	 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_aborts_seq);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_aborts_tsval
+	 */
+	data[i++] =
+		CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_aborts_tsval);
+	/*per_core_stats[cvmx_get_core_num()].link_stats[ifidx].fromwire.
+	 *fw_lro_aborts_timer
+	 */
+	/* intrmod: packet forward rate */
+	data[i++] =
+		CVM_CAST64(oct_dev->link_stats.fromwire.fw_lro_aborts_timer);
+	/*per_core_stats[j].link_stats[i].fromwire.fw_lro_aborts */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fwd_rate);
+
+	/* mac: link-level stats */
+	/*CVMX_BGXX_CMRX_RX_STAT0 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.total_rcvd);
+	/*CVMX_BGXX_CMRX_RX_STAT1 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.bytes_rcvd);
+	/*CVMX_PKI_STATX_STAT5 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.total_bcst);
+	/*CVMX_PKI_STATX_STAT5 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.total_mcst);
+	/*wqe->word2.err_code or wqe->word2.err_level */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.runts);
+	/*CVMX_BGXX_CMRX_RX_STAT2 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.ctl_rcvd);
+	/*CVMX_BGXX_CMRX_RX_STAT6 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fifo_err);
+	/*CVMX_BGXX_CMRX_RX_STAT4 */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.dmac_drop);
+	/*wqe->word2.err_code or wqe->word2.err_level */
+	data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fcs_err);
+	/*lio->link_changes*/
+	data[i++] = CVM_CAST64(lio->link_changes);
+
+	/* TX  -- lio_update_stats(lio); */
+	for (j = 0; j < MAX_OCTEON_INSTR_QUEUES(oct_dev); j++) {
+		if (!(oct_dev->io_qmask.iq & (1ULL << j)))
 			continue;
+		/*packets to network port*/
+		/*# of packets tx to network */
+		data[i++] = CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_done);
+		/*# of bytes tx to network */
 		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.instr_posted);
-		data[i++] =
-			CVM_CAST64(
-				oct_dev->instr_queue[j]->stats.instr_processed);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_tot_bytes);
+		/*# of packets dropped */
 		data[i++] =
-			CVM_CAST64(
-				oct_dev->instr_queue[j]->stats.instr_dropped);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_dropped);
+		/*# of tx fails due to queue full */
 		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.bytes_sent);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_iq_busy);
+		/*XXX gather entries sent */
 		data[i++] =
 			CVM_CAST64(oct_dev->instr_queue[j]->stats.sgentry_sent);
+
+		/*instruction to firmware: data and control */
+		/*# of instructions to the queue */
 		data[i++] =
-			readl(oct_dev->instr_queue[j]->inst_cnt_reg);
-		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_done);
-		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_iq_busy);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.instr_posted);
+		/*# of instructions processed */
+		data[i++] = CVM_CAST64(oct_dev->instr_queue[j]->
+				       stats.instr_processed);
+		/*# of instructions could not be processed */
+		data[i++] = CVM_CAST64(oct_dev->instr_queue[j]->
+				       stats.instr_dropped);
+		/*bytes sent through the queue */
 		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_dropped);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.bytes_sent);
+
+		/*tso request*/
+		data[i++] = CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_gso);
+		/*txq restart*/
 		data[i++] =
-			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_tot_bytes);
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_restart);
 	}
 
-	/* for (j = 0; j < oct_dev->num_oqs; j++){ */
-	for (j = 0; j < MAX_OCTEON_OUTPUT_QUEUES; j++) {
-		if (!(oct_dev->io_qmask.oq & (1UL << j)))
+	/* RX */
+	/* for (j = 0; j < oct_dev->num_oqs; j++) { */
+	for (j = 0; j < MAX_OCTEON_OUTPUT_QUEUES(oct_dev); j++) {
+		if (!(oct_dev->io_qmask.oq & (1ULL << j)))
 			continue;
-		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.pkts_received);
-		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.bytes_received);
-		data[i++] =
-			CVM_CAST64(oct_dev->droq[j]->stats.dropped_nodispatch);
-		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.dropped_nomem);
-		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.dropped_toomany);
+
+		/*packets send to TCP/IP network stack */
+		/*# of packets to network stack */
 		data[i++] =
 			CVM_CAST64(oct_dev->droq[j]->stats.rx_pkts_received);
+		/*# of bytes to network stack */
 		data[i++] =
 			CVM_CAST64(oct_dev->droq[j]->stats.rx_bytes_received);
+		/*# of packets dropped */
+		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.dropped_nomem +
+				       oct_dev->droq[j]->stats.dropped_toomany +
+				       oct_dev->droq[j]->stats.rx_dropped);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.dropped_nomem);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.dropped_toomany);
 		data[i++] =
 			CVM_CAST64(oct_dev->droq[j]->stats.rx_dropped);
+
+		/*control and data path*/
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.pkts_received);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.bytes_received);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.dropped_nodispatch);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.rx_alloc_failure);
 	}
 }
 
@@ -579,26 +868,43 @@ static void lio_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct_dev = lio->oct_dev;
 	int num_iq_stats, num_oq_stats, i, j;
+	int num_stats;
 
-	num_iq_stats = ARRAY_SIZE(oct_iq_stats_strings);
-	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-		if (!(oct_dev->io_qmask.iq & (1UL << i)))
-			continue;
-		for (j = 0; j < num_iq_stats; j++) {
-			sprintf(data, "IQ%d %s", i, oct_iq_stats_strings[j]);
+	switch (stringset) {
+	case ETH_SS_STATS:
+		num_stats = ARRAY_SIZE(oct_stats_strings);
+		for (j = 0; j < num_stats; j++) {
+			sprintf(data, "%s", oct_stats_strings[j]);
 			data += ETH_GSTRING_LEN;
 		}
-	}
 
-	num_oq_stats = ARRAY_SIZE(oct_droq_stats_strings);
-	/* for (i = 0; i < oct_dev->num_oqs; i++) { */
-	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-		if (!(oct_dev->io_qmask.oq & (1UL << i)))
-			continue;
-		for (j = 0; j < num_oq_stats; j++) {
-			sprintf(data, "OQ%d %s", i, oct_droq_stats_strings[j]);
-			data += ETH_GSTRING_LEN;
+		num_iq_stats = ARRAY_SIZE(oct_iq_stats_strings);
+		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct_dev); i++) {
+			if (!(oct_dev->io_qmask.iq & (1ULL << i)))
+				continue;
+			for (j = 0; j < num_iq_stats; j++) {
+				sprintf(data, "tx-%d-%s", i,
+					oct_iq_stats_strings[j]);
+				data += ETH_GSTRING_LEN;
+			}
 		}
+
+		num_oq_stats = ARRAY_SIZE(oct_droq_stats_strings);
+		/* for (i = 0; i < oct_dev->num_oqs; i++) { */
+		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct_dev); i++) {
+			if (!(oct_dev->io_qmask.oq & (1ULL << i)))
+				continue;
+			for (j = 0; j < num_oq_stats; j++) {
+				sprintf(data, "rx-%d-%s", i,
+					oct_droq_stats_strings[j]);
+				data += ETH_GSTRING_LEN;
+			}
+		}
+		break;
+
+	default:
+		netif_info(lio, drv, lio->netdev, "Unknown Stringset !!\n");
+		break;
 	}
 }
 
@@ -607,8 +913,14 @@ static int lio_get_sset_count(struct net_device *netdev, int sset)
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct_dev = lio->oct_dev;
 
-	return (ARRAY_SIZE(oct_iq_stats_strings) * oct_dev->num_iqs) +
-	       (ARRAY_SIZE(oct_droq_stats_strings) * oct_dev->num_oqs);
+	switch (sset) {
+	case ETH_SS_STATS:
+		return (ARRAY_SIZE(oct_stats_strings) +
+			ARRAY_SIZE(oct_iq_stats_strings) * oct_dev->num_iqs +
+			ARRAY_SIZE(oct_droq_stats_strings) * oct_dev->num_oqs);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int lio_get_intr_coalesce(struct net_device *netdev,
@@ -616,50 +928,50 @@ static int lio_get_intr_coalesce(struct net_device *netdev,
 {
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
-	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
 	struct octeon_instr_queue *iq;
 	struct oct_intrmod_cfg *intrmod_cfg;
 
 	intrmod_cfg = &oct->intrmod;
 
 	switch (oct->chip_id) {
-	/* case OCTEON_CN73XX: Todo */
-	/*      break; */
 	case OCTEON_CN68XX:
-	case OCTEON_CN66XX:
-		if (!intrmod_cfg->intrmod_enable) {
+	case OCTEON_CN66XX: {
+		struct octeon_cn6xxx *cn6xxx =
+			(struct octeon_cn6xxx *)oct->chip;
+
+		if (!intrmod_cfg->rx_enable) {
 			intr_coal->rx_coalesce_usecs =
 				CFG_GET_OQ_INTR_TIME(cn6xxx->conf);
 			intr_coal->rx_max_coalesced_frames =
 				CFG_GET_OQ_INTR_PKT(cn6xxx->conf);
-		} else {
-			intr_coal->use_adaptive_rx_coalesce =
-				intrmod_cfg->intrmod_enable;
-			intr_coal->rate_sample_interval =
-				intrmod_cfg->intrmod_check_intrvl;
-			intr_coal->pkt_rate_high =
-				intrmod_cfg->intrmod_maxpkt_ratethr;
-			intr_coal->pkt_rate_low =
-				intrmod_cfg->intrmod_minpkt_ratethr;
-			intr_coal->rx_max_coalesced_frames_high =
-				intrmod_cfg->intrmod_maxcnt_trigger;
-			intr_coal->rx_coalesce_usecs_high =
-				intrmod_cfg->intrmod_maxtmr_trigger;
-			intr_coal->rx_coalesce_usecs_low =
-				intrmod_cfg->intrmod_mintmr_trigger;
-			intr_coal->rx_max_coalesced_frames_low =
-				intrmod_cfg->intrmod_mincnt_trigger;
 		}
 
 		iq = oct->instr_queue[lio->linfo.txpciq[0].s.q_no];
 		intr_coal->tx_max_coalesced_frames = iq->fill_threshold;
 		break;
-
+	}
 	default:
 		netif_info(lio, drv, lio->netdev, "Unknown Chip !!\n");
 		return -EINVAL;
 	}
-
+	if (intrmod_cfg->rx_enable) {
+		intr_coal->use_adaptive_rx_coalesce =
+			intrmod_cfg->rx_enable;
+		intr_coal->rate_sample_interval =
+			intrmod_cfg->check_intrvl;
+		intr_coal->pkt_rate_high =
+			intrmod_cfg->maxpkt_ratethr;
+		intr_coal->pkt_rate_low =
+			intrmod_cfg->minpkt_ratethr;
+		intr_coal->rx_max_coalesced_frames_high =
+			intrmod_cfg->rx_maxcnt_trigger;
+		intr_coal->rx_coalesce_usecs_high =
+			intrmod_cfg->rx_maxtmr_trigger;
+		intr_coal->rx_coalesce_usecs_low =
+			intrmod_cfg->rx_mintmr_trigger;
+		intr_coal->rx_max_coalesced_frames_low =
+			intrmod_cfg->rx_mincnt_trigger;
+	}
 	return 0;
 }
 
@@ -679,19 +991,20 @@ static void octnet_intrmod_callback(struct octeon_device *oct_dev,
 	else
 		dev_info(&oct_dev->pci_dev->dev,
 			 "Rx-Adaptive Interrupt moderation enabled:%llx\n",
-			 oct_dev->intrmod.intrmod_enable);
+			 oct_dev->intrmod.rx_enable);
 
 	octeon_free_soft_command(oct_dev, sc);
 }
 
 /*  Configure interrupt moderation parameters */
-static int octnet_set_intrmod_cfg(void *oct, struct oct_intrmod_cfg *intr_cfg)
+static int octnet_set_intrmod_cfg(struct lio *lio,
+				  struct oct_intrmod_cfg *intr_cfg)
 {
 	struct octeon_soft_command *sc;
 	struct oct_intrmod_cmd *cmd;
 	struct oct_intrmod_cfg *cfg;
 	int retval;
-	struct octeon_device *oct_dev = (struct octeon_device *)oct;
+	struct octeon_device *oct_dev = lio->oct_dev;
 
 	/* Alloc soft command */
 	sc = (struct octeon_soft_command *)
@@ -712,6 +1025,8 @@ static int octnet_set_intrmod_cfg(void *oct, struct oct_intrmod_cfg *intr_cfg)
 	cmd->cfg = cfg;
 	cmd->oct_dev = oct_dev;
 
+	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
 	octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
 				    OPCODE_NIC_INTRMOD_CFG, 0, 0, 0);
 
@@ -728,9 +1043,158 @@ static int octnet_set_intrmod_cfg(void *oct, struct oct_intrmod_cfg *intr_cfg)
 	return 0;
 }
 
+void
+octnet_nic_stats_callback(struct octeon_device *oct_dev,
+			  u32 status, void *ptr)
+{
+	struct octeon_soft_command  *sc = (struct octeon_soft_command  *)ptr;
+	struct oct_nic_stats_resp *resp = (struct oct_nic_stats_resp *)
+		sc->virtrptr;
+	struct oct_nic_stats_ctrl *ctrl = (struct oct_nic_stats_ctrl *)
+		sc->ctxptr;
+	struct nic_rx_stats *rsp_rstats = &resp->stats.fromwire;
+	struct nic_tx_stats *rsp_tstats = &resp->stats.fromhost;
+
+	struct nic_rx_stats *rstats = &oct_dev->link_stats.fromwire;
+	struct nic_tx_stats *tstats = &oct_dev->link_stats.fromhost;
+
+	if ((status != OCTEON_REQUEST_TIMEOUT) && !resp->status) {
+		octeon_swap_8B_data((u64 *)&resp->stats,
+				    (sizeof(struct oct_link_stats)) >> 3);
+
+		/* RX link-level stats */
+		rstats->total_rcvd = rsp_rstats->total_rcvd;
+		rstats->bytes_rcvd = rsp_rstats->bytes_rcvd;
+		rstats->total_bcst = rsp_rstats->total_bcst;
+		rstats->total_mcst = rsp_rstats->total_mcst;
+		rstats->runts      = rsp_rstats->runts;
+		rstats->ctl_rcvd   = rsp_rstats->ctl_rcvd;
+		/* Accounts for over/under-run of buffers */
+		rstats->fifo_err  = rsp_rstats->fifo_err;
+		rstats->dmac_drop = rsp_rstats->dmac_drop;
+		rstats->fcs_err   = rsp_rstats->fcs_err;
+		rstats->jabber_err = rsp_rstats->jabber_err;
+		rstats->l2_err    = rsp_rstats->l2_err;
+		rstats->frame_err = rsp_rstats->frame_err;
+
+		/* RX firmware stats */
+		rstats->fw_total_rcvd = rsp_rstats->fw_total_rcvd;
+		rstats->fw_total_fwd = rsp_rstats->fw_total_fwd;
+		rstats->fw_err_pko = rsp_rstats->fw_err_pko;
+		rstats->fw_err_link = rsp_rstats->fw_err_link;
+		rstats->fw_err_drop = rsp_rstats->fw_err_drop;
+		/* Number of packets that are LROed      */
+		rstats->fw_lro_pkts = rsp_rstats->fw_lro_pkts;
+		/* Number of octets that are LROed       */
+		rstats->fw_lro_octs = rsp_rstats->fw_lro_octs;
+		/* Number of LRO packets formed          */
+		rstats->fw_total_lro = rsp_rstats->fw_total_lro;
+		/* Number of times lRO of packet aborted */
+		rstats->fw_lro_aborts = rsp_rstats->fw_lro_aborts;
+		rstats->fw_lro_aborts_port = rsp_rstats->fw_lro_aborts_port;
+		rstats->fw_lro_aborts_seq = rsp_rstats->fw_lro_aborts_seq;
+		rstats->fw_lro_aborts_tsval = rsp_rstats->fw_lro_aborts_tsval;
+		rstats->fw_lro_aborts_timer = rsp_rstats->fw_lro_aborts_timer;
+		/* intrmod: packet forward rate */
+		rstats->fwd_rate = rsp_rstats->fwd_rate;
+
+		/* TX link-level stats */
+		tstats->total_pkts_sent = rsp_tstats->total_pkts_sent;
+		tstats->total_bytes_sent = rsp_tstats->total_bytes_sent;
+		tstats->mcast_pkts_sent = rsp_tstats->mcast_pkts_sent;
+		tstats->bcast_pkts_sent = rsp_tstats->bcast_pkts_sent;
+		tstats->ctl_sent = rsp_tstats->ctl_sent;
+		/* Packets sent after one collision*/
+		tstats->one_collision_sent = rsp_tstats->one_collision_sent;
+		/* Packets sent after multiple collision*/
+		tstats->multi_collision_sent = rsp_tstats->multi_collision_sent;
+		/* Packets not sent due to max collisions */
+		tstats->max_collision_fail = rsp_tstats->max_collision_fail;
+		/* Packets not sent due to max deferrals */
+		tstats->max_deferral_fail = rsp_tstats->max_deferral_fail;
+		/* Accounts for over/under-run of buffers */
+		tstats->fifo_err = rsp_tstats->fifo_err;
+		tstats->runts = rsp_tstats->runts;
+		/* Total number of collisions detected */
+		tstats->total_collisions = rsp_tstats->total_collisions;
+
+		/* firmware stats */
+		tstats->fw_total_sent = rsp_tstats->fw_total_sent;
+		tstats->fw_total_fwd = rsp_tstats->fw_total_fwd;
+		tstats->fw_err_pko = rsp_tstats->fw_err_pko;
+		tstats->fw_err_link = rsp_tstats->fw_err_link;
+		tstats->fw_err_drop = rsp_tstats->fw_err_drop;
+		tstats->fw_tso = rsp_tstats->fw_tso;
+		tstats->fw_tso_fwd = rsp_tstats->fw_tso_fwd;
+		tstats->fw_err_tso = rsp_tstats->fw_err_tso;
+		resp->status = 1;
+	} else {
+		resp->status = -1;
+	}
+	complete(&ctrl->complete);
+}
+
+/*  Configure interrupt moderation parameters */
+static int octnet_get_link_stats(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct_dev = lio->oct_dev;
+
+	struct octeon_soft_command *sc;
+	struct oct_nic_stats_ctrl *ctrl;
+	struct oct_nic_stats_resp *resp;
+
+	int retval;
+
+	/* Alloc soft command */
+	sc = (struct octeon_soft_command *)
+		octeon_alloc_soft_command(oct_dev,
+					  0,
+					  sizeof(struct oct_nic_stats_resp),
+					  sizeof(struct octnic_ctrl_pkt));
+
+	if (!sc)
+		return -ENOMEM;
+
+	resp = (struct oct_nic_stats_resp *)sc->virtrptr;
+	memset(resp, 0, sizeof(struct oct_nic_stats_resp));
+
+	ctrl = (struct oct_nic_stats_ctrl *)sc->ctxptr;
+	memset(ctrl, 0, sizeof(struct oct_nic_stats_ctrl));
+	ctrl->netdev = netdev;
+	init_completion(&ctrl->complete);
+
+	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
+	octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
+				    OPCODE_NIC_PORT_STATS, 0, 0, 0);
+
+	sc->callback = octnet_nic_stats_callback;
+	sc->callback_arg = sc;
+	sc->wait_time = 500;	/*in milli seconds*/
+
+	retval = octeon_send_soft_command(oct_dev, sc);
+	if (retval == IQ_SEND_FAILED) {
+		octeon_free_soft_command(oct_dev, sc);
+		return -EINVAL;
+	}
+
+	wait_for_completion_timeout(&ctrl->complete, msecs_to_jiffies(1000));
+
+	if (resp->status != 1) {
+		octeon_free_soft_command(oct_dev, sc);
+
+		return -EINVAL;
+	}
+
+	octeon_free_soft_command(oct_dev, sc);
+
+	return 0;
+}
+
 /* Enable/Disable auto interrupt Moderation */
 static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
-				 *intr_coal, int adaptive)
+				 *intr_coal)
 {
 	int ret = 0;
 	struct octeon_device *oct = lio->oct_dev;
@@ -738,59 +1202,73 @@ static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
 
 	intrmod_cfg = &oct->intrmod;
 
-	if (adaptive) {
+	if (oct->intrmod.rx_enable || oct->intrmod.tx_enable) {
 		if (intr_coal->rate_sample_interval)
-			intrmod_cfg->intrmod_check_intrvl =
+			intrmod_cfg->check_intrvl =
 				intr_coal->rate_sample_interval;
 		else
-			intrmod_cfg->intrmod_check_intrvl =
+			intrmod_cfg->check_intrvl =
 				LIO_INTRMOD_CHECK_INTERVAL;
 
 		if (intr_coal->pkt_rate_high)
-			intrmod_cfg->intrmod_maxpkt_ratethr =
+			intrmod_cfg->maxpkt_ratethr =
 				intr_coal->pkt_rate_high;
 		else
-			intrmod_cfg->intrmod_maxpkt_ratethr =
+			intrmod_cfg->maxpkt_ratethr =
 				LIO_INTRMOD_MAXPKT_RATETHR;
 
 		if (intr_coal->pkt_rate_low)
-			intrmod_cfg->intrmod_minpkt_ratethr =
+			intrmod_cfg->minpkt_ratethr =
 				intr_coal->pkt_rate_low;
 		else
-			intrmod_cfg->intrmod_minpkt_ratethr =
+			intrmod_cfg->minpkt_ratethr =
 				LIO_INTRMOD_MINPKT_RATETHR;
-
+	}
+	if (oct->intrmod.rx_enable) {
 		if (intr_coal->rx_max_coalesced_frames_high)
-			intrmod_cfg->intrmod_maxcnt_trigger =
+			intrmod_cfg->rx_maxcnt_trigger =
 				intr_coal->rx_max_coalesced_frames_high;
 		else
-			intrmod_cfg->intrmod_maxcnt_trigger =
-				LIO_INTRMOD_MAXCNT_TRIGGER;
+			intrmod_cfg->rx_maxcnt_trigger =
+				LIO_INTRMOD_RXMAXCNT_TRIGGER;
 
 		if (intr_coal->rx_coalesce_usecs_high)
-			intrmod_cfg->intrmod_maxtmr_trigger =
+			intrmod_cfg->rx_maxtmr_trigger =
 				intr_coal->rx_coalesce_usecs_high;
 		else
-			intrmod_cfg->intrmod_maxtmr_trigger =
-				LIO_INTRMOD_MAXTMR_TRIGGER;
+			intrmod_cfg->rx_maxtmr_trigger =
+				LIO_INTRMOD_RXMAXTMR_TRIGGER;
 
 		if (intr_coal->rx_coalesce_usecs_low)
-			intrmod_cfg->intrmod_mintmr_trigger =
+			intrmod_cfg->rx_mintmr_trigger =
 				intr_coal->rx_coalesce_usecs_low;
 		else
-			intrmod_cfg->intrmod_mintmr_trigger =
-				LIO_INTRMOD_MINTMR_TRIGGER;
+			intrmod_cfg->rx_mintmr_trigger =
+				LIO_INTRMOD_RXMINTMR_TRIGGER;
 
 		if (intr_coal->rx_max_coalesced_frames_low)
-			intrmod_cfg->intrmod_mincnt_trigger =
+			intrmod_cfg->rx_mincnt_trigger =
 				intr_coal->rx_max_coalesced_frames_low;
 		else
-			intrmod_cfg->intrmod_mincnt_trigger =
-				LIO_INTRMOD_MINCNT_TRIGGER;
+			intrmod_cfg->rx_mincnt_trigger =
+				LIO_INTRMOD_RXMINCNT_TRIGGER;
+	}
+	if (oct->intrmod.tx_enable) {
+		if (intr_coal->tx_max_coalesced_frames_high)
+			intrmod_cfg->tx_maxcnt_trigger =
+				intr_coal->tx_max_coalesced_frames_high;
+		else
+			intrmod_cfg->tx_maxcnt_trigger =
+				LIO_INTRMOD_TXMAXCNT_TRIGGER;
+		if (intr_coal->tx_max_coalesced_frames_low)
+			intrmod_cfg->tx_mincnt_trigger =
+				intr_coal->tx_max_coalesced_frames_low;
+		else
+			intrmod_cfg->tx_mincnt_trigger =
+				LIO_INTRMOD_TXMINCNT_TRIGGER;
 	}
 
-	intrmod_cfg->intrmod_enable = adaptive;
-	ret = octnet_set_intrmod_cfg(oct, intrmod_cfg);
+	ret = octnet_set_intrmod_cfg(lio, intrmod_cfg);
 
 	return ret;
 }
@@ -798,54 +1276,82 @@ static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
 static int
 oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
 {
-	int ret;
 	struct octeon_device *oct = lio->oct_dev;
-	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
 	u32 rx_max_coalesced_frames;
 
-	if (!intr_coal->rx_max_coalesced_frames)
-		rx_max_coalesced_frames = CN6XXX_OQ_INTR_PKT;
-	else
-		rx_max_coalesced_frames = intr_coal->rx_max_coalesced_frames;
-
-	/* Disable adaptive interrupt modulation */
-	ret = oct_cfg_adaptive_intr(lio, intr_coal, 0);
-	if (ret)
-		return ret;
-
 	/* Config Cnt based interrupt values */
-	octeon_write_csr(oct, CN6XXX_SLI_OQ_INT_LEVEL_PKTS,
-			 rx_max_coalesced_frames);
-	CFG_SET_OQ_INTR_PKT(cn6xxx->conf, rx_max_coalesced_frames);
+	switch (oct->chip_id) {
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX: {
+		struct octeon_cn6xxx *cn6xxx =
+			(struct octeon_cn6xxx *)oct->chip;
+
+		if (!intr_coal->rx_max_coalesced_frames)
+			rx_max_coalesced_frames = CN6XXX_OQ_INTR_PKT;
+		else
+			rx_max_coalesced_frames =
+				intr_coal->rx_max_coalesced_frames;
+		octeon_write_csr(oct, CN6XXX_SLI_OQ_INT_LEVEL_PKTS,
+				 rx_max_coalesced_frames);
+		CFG_SET_OQ_INTR_PKT(cn6xxx->conf, rx_max_coalesced_frames);
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
 	return 0;
 }
 
 static int oct_cfg_rx_intrtime(struct lio *lio, struct ethtool_coalesce
 			       *intr_coal)
 {
-	int ret;
 	struct octeon_device *oct = lio->oct_dev;
-	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
 	u32 time_threshold, rx_coalesce_usecs;
 
-	if (!intr_coal->rx_coalesce_usecs)
-		rx_coalesce_usecs = CN6XXX_OQ_INTR_TIME;
-	else
-		rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
+	/* Config Time based interrupt values */
+	switch (oct->chip_id) {
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX: {
+		struct octeon_cn6xxx *cn6xxx =
+			(struct octeon_cn6xxx *)oct->chip;
+		if (!intr_coal->rx_coalesce_usecs)
+			rx_coalesce_usecs = CN6XXX_OQ_INTR_TIME;
+		else
+			rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
 
-	/* Disable adaptive interrupt modulation */
-	ret = oct_cfg_adaptive_intr(lio, intr_coal, 0);
-	if (ret)
-		return ret;
+		time_threshold = lio_cn6xxx_get_oq_ticks(oct,
+							 rx_coalesce_usecs);
+		octeon_write_csr(oct,
+				 CN6XXX_SLI_OQ_INT_LEVEL_TIME,
+				 time_threshold);
 
-	/* Config Time based interrupt values */
-	time_threshold = lio_cn6xxx_get_oq_ticks(oct, rx_coalesce_usecs);
-	octeon_write_csr(oct, CN6XXX_SLI_OQ_INT_LEVEL_TIME, time_threshold);
-	CFG_SET_OQ_INTR_TIME(cn6xxx->conf, rx_coalesce_usecs);
+		CFG_SET_OQ_INTR_TIME(cn6xxx->conf, rx_coalesce_usecs);
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
 
 	return 0;
 }
 
+static int
+oct_cfg_tx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal
+		   __attribute__((unused)))
+{
+	struct octeon_device *oct = lio->oct_dev;
+
+	/* Config Cnt based interrupt values */
+	switch (oct->chip_id) {
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX:
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int lio_set_intr_coalesce(struct net_device *netdev,
 				 struct ethtool_coalesce *intr_coal)
 {
@@ -853,59 +1359,48 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
 	int ret;
 	struct octeon_device *oct = lio->oct_dev;
 	u32 j, q_no;
+	int db_max, db_min;
 
-	if ((intr_coal->tx_max_coalesced_frames >= CN6XXX_DB_MIN) &&
-	    (intr_coal->tx_max_coalesced_frames <= CN6XXX_DB_MAX)) {
-		for (j = 0; j < lio->linfo.num_txpciq; j++) {
-			q_no = lio->linfo.txpciq[j].s.q_no;
-			oct->instr_queue[q_no]->fill_threshold =
-				intr_coal->tx_max_coalesced_frames;
+	switch (oct->chip_id) {
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX:
+		db_min = CN6XXX_DB_MIN;
+		db_max = CN6XXX_DB_MAX;
+		if ((intr_coal->tx_max_coalesced_frames >= db_min) &&
+		    (intr_coal->tx_max_coalesced_frames <= db_max)) {
+			for (j = 0; j < lio->linfo.num_txpciq; j++) {
+				q_no = lio->linfo.txpciq[j].s.q_no;
+				oct->instr_queue[q_no]->fill_threshold =
+					intr_coal->tx_max_coalesced_frames;
+			}
+		} else {
+			dev_err(&oct->pci_dev->dev,
+				"LIQUIDIO: Invalid tx-frames:%d. Range is min:%d max:%d\n",
+				intr_coal->tx_max_coalesced_frames, db_min,
+				db_max);
+			return -EINVAL;
 		}
-	} else {
-		dev_err(&oct->pci_dev->dev,
-			"LIQUIDIO: Invalid tx-frames:%d. Range is min:%d max:%d\n",
-			intr_coal->tx_max_coalesced_frames, CN6XXX_DB_MIN,
-			CN6XXX_DB_MAX);
+		break;
+	default:
 		return -EINVAL;
 	}
 
-	/* User requested adaptive-rx on */
-	if (intr_coal->use_adaptive_rx_coalesce) {
-		ret = oct_cfg_adaptive_intr(lio, intr_coal, 1);
-		if (ret)
-			goto ret_intrmod;
-	}
+	oct->intrmod.rx_enable = intr_coal->use_adaptive_rx_coalesce ? 1 : 0;
+	oct->intrmod.tx_enable = intr_coal->use_adaptive_tx_coalesce ? 1 : 0;
+
+	ret = oct_cfg_adaptive_intr(lio, intr_coal);
 
-	/* User requested adaptive-rx off and rx coalesce */
-	if ((intr_coal->rx_coalesce_usecs) &&
-	    (!intr_coal->use_adaptive_rx_coalesce)) {
+	if (!intr_coal->use_adaptive_rx_coalesce) {
 		ret = oct_cfg_rx_intrtime(lio, intr_coal);
 		if (ret)
 			goto ret_intrmod;
-	}
 
-	/* User requested adaptive-rx off and rx coalesce */
-	if ((intr_coal->rx_max_coalesced_frames) &&
-	    (!intr_coal->use_adaptive_rx_coalesce)) {
 		ret = oct_cfg_rx_intrcnt(lio, intr_coal);
 		if (ret)
 			goto ret_intrmod;
 	}
-
-	/* User requested adaptive-rx off, so use default coalesce params */
-	if ((!intr_coal->rx_max_coalesced_frames) &&
-	    (!intr_coal->use_adaptive_rx_coalesce) &&
-	    (!intr_coal->rx_coalesce_usecs)) {
-		dev_info(&oct->pci_dev->dev,
-			 "Turning off adaptive-rx interrupt moderation\n");
-		dev_info(&oct->pci_dev->dev,
-			 "Using RX Coalesce Default values rx_coalesce_usecs:%d rx_max_coalesced_frames:%d\n",
-			 CN6XXX_OQ_INTR_TIME, CN6XXX_OQ_INTR_PKT);
-		ret = oct_cfg_rx_intrtime(lio, intr_coal);
-		if (ret)
-			goto ret_intrmod;
-
-		ret = oct_cfg_rx_intrcnt(lio, intr_coal);
+	if (!intr_coal->use_adaptive_tx_coalesce) {
+		ret = oct_cfg_tx_intrcnt(lio, intr_coal);
 		if (ret)
 			goto ret_intrmod;
 	}
@@ -921,23 +1416,28 @@ static int lio_get_ts_info(struct net_device *netdev,
 	struct lio *lio = GET_LIO(netdev);
 
 	info->so_timestamping =
+#ifdef PTP_HARDWARE_TIMESTAMPING
 		SOF_TIMESTAMPING_TX_HARDWARE |
-		SOF_TIMESTAMPING_TX_SOFTWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
+		SOF_TIMESTAMPING_RAW_HARDWARE |
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+#endif
 		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_RAW_HARDWARE;
+		SOF_TIMESTAMPING_SOFTWARE;
 
 	if (lio->ptp_clock)
 		info->phc_index = ptp_clock_index(lio->ptp_clock);
 	else
 		info->phc_index = -1;
 
+#ifdef PTP_HARDWARE_TIMESTAMPING
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON);
 
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 			   (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
 			   (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
 			   (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT);
+#endif
 
 	return 0;
 }
@@ -962,12 +1462,14 @@ static int lio_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 						  ecmd->duplex != DUPLEX_FULL)))
 		return -EINVAL;
 
-	/* Ethtool Support is not provided for XAUI and RXAUI Interfaces
+	/* Ethtool Support is not provided for XAUI, RXAUI, and XFI Interfaces
 	 * as they operate at fixed Speed and Duplex settings
 	 */
-	if (linfo->link.s.interface == INTERFACE_MODE_XAUI ||
-	    linfo->link.s.interface == INTERFACE_MODE_RXAUI) {
-		dev_info(&oct->pci_dev->dev, "XAUI IFs settings cannot be modified.\n");
+	if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI ||
+	    linfo->link.s.if_mode == INTERFACE_MODE_RXAUI ||
+	    linfo->link.s.if_mode == INTERFACE_MODE_XFI) {
+		dev_info(&oct->pci_dev->dev,
+			 "Autonegotiation, duplex and speed settings cannot be modified.\n");
 		return -EINVAL;
 	}
 
@@ -1181,6 +1683,23 @@ static void lio_get_regs(struct net_device *dev,
 	}
 }
 
+static u32 lio_get_priv_flags(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	return lio->oct_dev->priv_flags;
+}
+
+static int lio_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct lio *lio = GET_LIO(netdev);
+	bool intr_by_tx_bytes = !!(flags & (0x1 << OCT_PRIV_FLAG_TX_BYTES));
+
+	lio_set_priv_flag(lio->oct_dev, OCT_PRIV_FLAG_TX_BYTES,
+			  intr_by_tx_bytes);
+	return 0;
+}
+
 static const struct ethtool_ops lio_ethtool_ops = {
 	.get_settings		= lio_get_settings,
 	.get_link		= ethtool_op_get_link,
@@ -1202,6 +1721,8 @@ static const struct ethtool_ops lio_ethtool_ops = {
 	.set_settings		= lio_set_settings,
 	.get_coalesce		= lio_get_intr_coalesce,
 	.set_coalesce		= lio_set_intr_coalesce,
+	.get_priv_flags		= lio_get_priv_flags,
+	.set_priv_flags		= lio_set_priv_flags,
 	.get_ts_info		= lio_get_ts_info,
 };
 

drivers/net/ethernet/cavium/liquidio/lio_main.c

@@ -72,6 +72,9 @@ MODULE_PARM_DESC(console_bitmask,
 
 #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
 
+#define INCR_INSTRQUEUE_PKT_COUNT(octeon_dev_ptr, iq_no, field, count)  \
+	(octeon_dev_ptr->instr_queue[iq_no]->stats.field += count)
+
 static int debug = -1;
 module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "NETIF_MSG debug bits");
@@ -224,8 +227,8 @@ static void octeon_droq_bh(unsigned long pdev)
 		(struct octeon_device_priv *)oct->priv;
 
 	/* for (q_no = 0; q_no < oct->num_oqs; q_no++) { */
-	for (q_no = 0; q_no < MAX_OCTEON_OUTPUT_QUEUES; q_no++) {
-		if (!(oct->io_qmask.oq & (1UL << q_no)))
+	for (q_no = 0; q_no < MAX_OCTEON_OUTPUT_QUEUES(oct); q_no++) {
+		if (!(oct->io_qmask.oq & (1ULL << q_no)))
 			continue;
 		reschedule |= octeon_droq_process_packets(oct, oct->droq[q_no],
 							  MAX_PACKET_BUDGET);
@@ -245,8 +248,8 @@ static int lio_wait_for_oq_pkts(struct octeon_device *oct)
 	do {
 		pending_pkts = 0;
 
-		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-			if (!(oct->io_qmask.oq & (1UL << i)))
+		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+			if (!(oct->io_qmask.oq & (1ULL << i)))
 				continue;
 			pkt_cnt += octeon_droq_check_hw_for_pkts(oct,
 								 oct->droq[i]);
@@ -365,7 +368,7 @@ static int wait_for_pending_requests(struct octeon_device *oct)
 				[OCTEON_ORDERED_SC_LIST].pending_req_count);
 		if (pcount)
 			schedule_timeout_uninterruptible(HZ / 10);
-		 else
+		else
 			break;
 	}
 
@@ -396,10 +399,10 @@ static inline void pcierror_quiesce_device(struct octeon_device *oct)
 		dev_err(&oct->pci_dev->dev, "There were pending requests\n");
 
 	/* Force all requests waiting to be fetched by OCTEON to complete. */
-	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
 		struct octeon_instr_queue *iq;
 
-		if (!(oct->io_qmask.iq & (1UL << i)))
+		if (!(oct->io_qmask.iq & (1ULL << i)))
 			continue;
 		iq = oct->instr_queue[i];
 
@@ -409,7 +412,7 @@ static inline void pcierror_quiesce_device(struct octeon_device *oct)
 			iq->octeon_read_index = iq->host_write_index;
 			iq->stats.instr_processed +=
 				atomic_read(&iq->instr_pending);
-			lio_process_iq_request_list(oct, iq);
+			lio_process_iq_request_list(oct, iq, 0);
 			spin_unlock_bh(&iq->lock);
 		}
 	}
@@ -682,13 +685,24 @@ static inline void txqs_start(struct net_device *netdev)
  */
 static inline void txqs_wake(struct net_device *netdev)
 {
+	struct lio *lio = GET_LIO(netdev);
+
 	if (netif_is_multiqueue(netdev)) {
 		int i;
 
-		for (i = 0; i < netdev->num_tx_queues; i++)
-			if (__netif_subqueue_stopped(netdev, i))
+		for (i = 0; i < netdev->num_tx_queues; i++) {
+			int qno = lio->linfo.txpciq[i %
+				(lio->linfo.num_txpciq)].s.q_no;
+
+			if (__netif_subqueue_stopped(netdev, i)) {
+				INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, qno,
+							  tx_restart, 1);
 				netif_wake_subqueue(netdev, i);
+			}
+		}
 	} else {
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, lio->txq,
+					  tx_restart, 1);
 		netif_wake_queue(netdev);
 	}
 }
@@ -763,6 +777,8 @@ static inline int check_txq_status(struct lio *lio)
 				continue;
 			if (__netif_subqueue_stopped(lio->netdev, q)) {
 				wake_q(lio->netdev, q);
+				INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq,
+							  tx_restart, 1);
 				ret_val++;
 			}
 		}
@@ -770,6 +786,8 @@ static inline int check_txq_status(struct lio *lio)
 		if (octnet_iq_is_full(lio->oct_dev, lio->txq))
 			return 0;
 		wake_q(lio->netdev, lio->txq);
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, lio->txq,
+					  tx_restart, 1);
 		ret_val = 1;
 	}
 	return ret_val;
@@ -959,6 +977,42 @@ static inline void update_link_status(struct net_device *netdev,
 	}
 }
 
+/* Runs in interrupt context. */
+static void update_txq_status(struct octeon_device *oct, int iq_num)
+{
+	struct net_device *netdev;
+	struct lio *lio;
+	struct octeon_instr_queue *iq = oct->instr_queue[iq_num];
+
+	/*octeon_update_iq_read_idx(oct, iq);*/
+
+	netdev = oct->props[iq->ifidx].netdev;
+
+	/* This is needed because the first IQ does not have
+	 * a netdev associated with it.
+	 */
+	if (!netdev)
+		return;
+
+	lio = GET_LIO(netdev);
+	if (netif_is_multiqueue(netdev)) {
+		if (__netif_subqueue_stopped(netdev, iq->q_index) &&
+		    lio->linfo.link.s.link_up &&
+		    (!octnet_iq_is_full(oct, iq_num))) {
+			INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num,
+						  tx_restart, 1);
+			netif_wake_subqueue(netdev, iq->q_index);
+		} else {
+			if (!octnet_iq_is_full(oct, lio->txq)) {
+				INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
+							  lio->txq,
+							  tx_restart, 1);
+				wake_q(netdev, lio->txq);
+			}
+		}
+	}
+}
+
 /**
  * \brief Droq packet processor sceduler
  * @param oct octeon device
@@ -972,8 +1026,9 @@ void liquidio_schedule_droq_pkt_handlers(struct octeon_device *oct)
 	struct octeon_droq *droq;
 
 	if (oct->int_status & OCT_DEV_INTR_PKT_DATA) {
-		for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES; oq_no++) {
-			if (!(oct->droq_intr & (1 << oq_no)))
+		for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES(oct);
+		     oq_no++) {
+			if (!(oct->droq_intr & (1ULL << oq_no)))
 				continue;
 
 			droq = oct->droq[oq_no];
@@ -1084,6 +1139,9 @@ static int liquidio_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENOMEM;
 	}
 
+	oct_dev->rx_pause = 1;
+	oct_dev->tx_pause = 1;
+
 	dev_dbg(&oct_dev->pci_dev->dev, "Device is ready\n");
 
 	return 0;
@@ -1149,19 +1207,13 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 		if (oct->flags & LIO_FLAG_MSI_ENABLED)
 			pci_disable_msi(oct->pci_dev);
 
-		/* Soft reset the octeon device before exiting */
-		oct->fn_list.soft_reset(oct);
-
-		/* Disable the device, releasing the PCI INT */
-		pci_disable_device(oct->pci_dev);
-
 		/* fallthrough */
 	case OCT_DEV_IN_RESET:
 	case OCT_DEV_DROQ_INIT_DONE:
 		/*atomic_set(&oct->status, OCT_DEV_DROQ_INIT_DONE);*/
 		mdelay(100);
-		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
-			if (!(oct->io_qmask.oq & (1UL << i)))
+		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
+			if (!(oct->io_qmask.oq & (1ULL << i)))
 				continue;
 			octeon_delete_droq(oct, i);
 		}
@@ -1188,8 +1240,8 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		/* fallthrough */
 	case OCT_DEV_INSTR_QUEUE_INIT_DONE:
-		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-			if (!(oct->io_qmask.iq & (1UL << i)))
+		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+			if (!(oct->io_qmask.iq & (1ULL << i)))
 				continue;
 			octeon_delete_instr_queue(oct, i);
 		}
@@ -1201,11 +1253,18 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		/* fallthrough */
 	case OCT_DEV_PCI_MAP_DONE:
+
+		/* Soft reset the octeon device before exiting */
+		oct->fn_list.soft_reset(oct);
+
 		octeon_unmap_pci_barx(oct, 0);
 		octeon_unmap_pci_barx(oct, 1);
 
 		/* fallthrough */
 	case OCT_DEV_BEGIN_STATE:
+		/* Disable the device, releasing the PCI INT */
+		pci_disable_device(oct->pci_dev);
+
 		/* Nothing to be done here either */
 		break;
 	}                       /* end switch(oct->status) */
@@ -1245,6 +1304,7 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 {
 	struct net_device *netdev = oct->props[ifidx].netdev;
 	struct lio *lio;
+	struct napi_struct *napi, *n;
 
 	if (!netdev) {
 		dev_err(&oct->pci_dev->dev, "%s No netdevice ptr for index %d\n",
@@ -1261,6 +1321,13 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_RUNNING)
 		txqs_stop(netdev);
 
+	if (oct->props[lio->ifidx].napi_enabled == 1) {
+		list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
+			napi_disable(napi);
+
+		oct->props[lio->ifidx].napi_enabled = 0;
+	}
+
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED)
 		unregister_netdev(netdev);
 
@@ -1288,6 +1355,10 @@ static int liquidio_stop_nic_module(struct octeon_device *oct)
 		return 1;
 	}
 
+	spin_lock_bh(&oct->cmd_resp_wqlock);
+	oct->cmd_resp_state = OCT_DRV_OFFLINE;
+	spin_unlock_bh(&oct->cmd_resp_wqlock);
+
 	for (i = 0; i < oct->ifcount; i++) {
 		lio = GET_LIO(oct->props[i].netdev);
 		for (j = 0; j < lio->linfo.num_rxpciq; j++)
@@ -1336,6 +1407,7 @@ static int octeon_chip_specific_setup(struct octeon_device *oct)
 {
 	u32 dev_id, rev_id;
 	int ret = 1;
+	char *s;
 
 	pci_read_config_dword(oct->pci_dev, 0, &dev_id);
 	pci_read_config_dword(oct->pci_dev, 8, &rev_id);
@@ -1345,22 +1417,27 @@ static int octeon_chip_specific_setup(struct octeon_device *oct)
 	case OCTEON_CN68XX_PCIID:
 		oct->chip_id = OCTEON_CN68XX;
 		ret = lio_setup_cn68xx_octeon_device(oct);
+		s = "CN68XX";
 		break;
 
 	case OCTEON_CN66XX_PCIID:
 		oct->chip_id = OCTEON_CN66XX;
 		ret = lio_setup_cn66xx_octeon_device(oct);
+		s = "CN66XX";
 		break;
+
 	default:
+		s = "?";
 		dev_err(&oct->pci_dev->dev, "Unknown device found (dev_id: %x)\n",
 			dev_id);
 	}
 
 	if (!ret)
-		dev_info(&oct->pci_dev->dev, "CN68XX PASS%d.%d %s\n",
+		dev_info(&oct->pci_dev->dev, "%s PASS%d.%d %s Version: %s\n", s,
 			 OCTEON_MAJOR_REV(oct),
 			 OCTEON_MINOR_REV(oct),
-			 octeon_get_conf(oct)->card_name);
+			 octeon_get_conf(oct)->card_name,
+			 LIQUIDIO_VERSION);
 
 	return ret;
 }
@@ -1418,8 +1495,10 @@ static inline int check_txq_state(struct lio *lio, struct sk_buff *skb)
 	if (octnet_iq_is_full(lio->oct_dev, iq))
 		return 0;
 
-	if (__netif_subqueue_stopped(lio->netdev, q))
+	if (__netif_subqueue_stopped(lio->netdev, q)) {
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq, tx_restart, 1);
 		wake_q(lio->netdev, q);
+	}
 	return 1;
 }
 
@@ -1733,6 +1812,7 @@ static int load_firmware(struct octeon_device *oct)
 	if (ret) {
 		dev_err(&oct->pci_dev->dev, "Request firmware failed. Could not find file %s.\n.",
 			fw_name);
+		release_firmware(fw);
 		return ret;
 	}
 
@@ -1802,6 +1882,9 @@ static void if_cfg_callback(struct octeon_device *oct,
 			CVM_CAST64(resp->status));
 	ACCESS_ONCE(ctx->cond) = 1;
 
+	snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s",
+		 resp->cfg_info.liquidio_firmware_version);
+
 	/* This barrier is required to be sure that the response has been
 	 * written fully before waking up the handler
 	 */
@@ -1848,6 +1931,7 @@ liquidio_push_packet(u32 octeon_id,
 	struct sk_buff *skb = (struct sk_buff *)skbuff;
 	struct skb_shared_hwtstamps *shhwtstamps;
 	u64 ns;
+	u16 vtag = 0;
 	struct net_device *netdev = (struct net_device *)arg;
 	struct octeon_droq *droq = container_of(param, struct octeon_droq,
 						napi);
@@ -1924,6 +2008,16 @@ liquidio_push_packet(u32 octeon_id,
 		else
 			skb->ip_summed = CHECKSUM_NONE;
 
+		/* inbound VLAN tag */
+		if ((netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+		    (rh->r_dh.vlan != 0)) {
+			u16 vid = rh->r_dh.vlan;
+			u16 priority = rh->r_dh.priority;
+
+			vtag = priority << 13 | vid;
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vtag);
+		}
+
 		packet_was_received = napi_gro_receive(napi, skb) != GRO_DROP;
 
 		if (packet_was_received) {
@@ -1977,39 +2071,6 @@ static void liquidio_napi_drv_callback(void *arg)
 	}
 }
 
-/**
- * \brief Main NAPI poll function
- * @param droq octeon output queue
- * @param budget maximum number of items to process
- */
-static int liquidio_napi_do_rx(struct octeon_droq *droq, int budget)
-{
-	int work_done;
-	struct lio *lio = GET_LIO(droq->napi.dev);
-	struct octeon_device *oct = lio->oct_dev;
-
-	work_done = octeon_process_droq_poll_cmd(oct, droq->q_no,
-						 POLL_EVENT_PROCESS_PKTS,
-						 budget);
-	if (work_done < 0) {
-		netif_info(lio, rx_err, lio->netdev,
-			   "Receive work_done < 0, rxq:%d\n", droq->q_no);
-		goto octnet_napi_finish;
-	}
-
-	if (work_done > budget)
-		dev_err(&oct->pci_dev->dev, ">>>> %s work_done: %d budget: %d\n",
-			__func__, work_done, budget);
-
-	return work_done;
-
-octnet_napi_finish:
-	napi_complete(&droq->napi);
-	octeon_process_droq_poll_cmd(oct, droq->q_no, POLL_EVENT_ENABLE_INTR,
-				     0);
-	return 0;
-}
-
 /**
  * \brief Entry point for NAPI polling
  * @param napi NAPI structure
@@ -2019,19 +2080,41 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct octeon_droq *droq;
 	int work_done;
+	int tx_done = 0, iq_no;
+	struct octeon_instr_queue *iq;
+	struct octeon_device *oct;
 
 	droq = container_of(napi, struct octeon_droq, napi);
+	oct = droq->oct_dev;
+	iq_no = droq->q_no;
+	/* Handle Droq descriptors */
+	work_done = octeon_process_droq_poll_cmd(oct, droq->q_no,
+						 POLL_EVENT_PROCESS_PKTS,
+						 budget);
 
-	work_done = liquidio_napi_do_rx(droq, budget);
+	/* Flush the instruction queue */
+	iq = oct->instr_queue[iq_no];
+	if (iq) {
+		/* Process iq buffers with in the budget limits */
+		tx_done = octeon_flush_iq(oct, iq, 1, budget);
+		/* Update iq read-index rather than waiting for next interrupt.
+		 * Return back if tx_done is false.
+		 */
+		update_txq_status(oct, iq_no);
+		/*tx_done = (iq->flush_index == iq->octeon_read_index);*/
+	} else {
+		dev_err(&oct->pci_dev->dev, "%s:  iq (%d) num invalid\n",
+			__func__, iq_no);
+	}
 
-	if (work_done < budget) {
+	if ((work_done < budget) && (tx_done)) {
 		napi_complete(napi);
 		octeon_process_droq_poll_cmd(droq->oct_dev, droq->q_no,
 					     POLL_EVENT_ENABLE_INTR, 0);
 		return 0;
 	}
 
-	return work_done;
+	return (!tx_done) ? (budget) : (work_done);
 }
 
 /**
@@ -2165,6 +2248,14 @@ static inline void setup_tx_poll_fn(struct net_device *netdev)
 			   &lio->txq_status_wq.wk.work, msecs_to_jiffies(1));
 }
 
+static inline void cleanup_tx_poll_fn(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	cancel_delayed_work_sync(&lio->txq_status_wq.wk.work);
+	destroy_workqueue(lio->txq_status_wq.wq);
+}
+
 /**
  * \brief Net device open for LiquidIO
  * @param netdev network device
@@ -2175,17 +2266,22 @@ static int liquidio_open(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 	struct napi_struct *napi, *n;
 
-	list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
-		napi_enable(napi);
+	if (oct->props[lio->ifidx].napi_enabled == 0) {
+		list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
+			napi_enable(napi);
+
+		oct->props[lio->ifidx].napi_enabled = 1;
+	}
 
 	oct_ptp_open(netdev);
 
 	ifstate_set(lio, LIO_IFSTATE_RUNNING);
+
 	setup_tx_poll_fn(netdev);
+
 	start_txq(netdev);
 
 	netif_info(lio, ifup, lio->netdev, "Interface Open, ready for traffic\n");
-	try_module_get(THIS_MODULE);
 
 	/* tell Octeon to start forwarding packets to host */
 	send_rx_ctrl_cmd(lio, 1);
@@ -2205,39 +2301,35 @@ static int liquidio_open(struct net_device *netdev)
  */
 static int liquidio_stop(struct net_device *netdev)
 {
-	struct napi_struct *napi, *n;
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 
-	netif_info(lio, ifdown, lio->netdev, "Stopping interface!\n");
+	ifstate_reset(lio, LIO_IFSTATE_RUNNING);
+
+	netif_tx_disable(netdev);
+
 	/* Inform that netif carrier is down */
+	netif_carrier_off(netdev);
 	lio->intf_open = 0;
 	lio->linfo.link.s.link_up = 0;
 	lio->link_changes++;
 
-	netif_carrier_off(netdev);
+	/* Pause for a moment and wait for Octeon to flush out (to the wire) any
+	 * egress packets that are in-flight.
+	 */
+	set_current_state(TASK_INTERRUPTIBLE);
+	schedule_timeout(msecs_to_jiffies(100));
 
-	/* tell Octeon to stop forwarding packets to host */
+	/* Now it should be safe to tell Octeon that nic interface is down. */
 	send_rx_ctrl_cmd(lio, 0);
 
-	cancel_delayed_work_sync(&lio->txq_status_wq.wk.work);
-	destroy_workqueue(lio->txq_status_wq.wq);
+	cleanup_tx_poll_fn(netdev);
 
 	if (lio->ptp_clock) {
 		ptp_clock_unregister(lio->ptp_clock);
 		lio->ptp_clock = NULL;
 	}
 
-	ifstate_reset(lio, LIO_IFSTATE_RUNNING);
-
-	/* This is a hack that allows DHCP to continue working. */
-	set_bit(__LINK_STATE_START, &lio->netdev->state);
-
-	list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
-		napi_disable(napi);
-
-	txqs_stop(netdev);
-
 	dev_info(&oct->pci_dev->dev, "%s interface is stopped\n", netdev->name);
 	module_put(THIS_MODULE);
 
@@ -2298,12 +2390,31 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
 			 netdev->name);
 		break;
 
+	case OCTNET_CMD_ENABLE_VLAN_FILTER:
+		dev_info(&oct->pci_dev->dev, "%s VLAN filter enabled\n",
+			 netdev->name);
+		break;
+
+	case OCTNET_CMD_ADD_VLAN_FILTER:
+		dev_info(&oct->pci_dev->dev, "%s VLAN filter %d added\n",
+			 netdev->name, nctrl->ncmd.s.param1);
+		break;
+
+	case OCTNET_CMD_DEL_VLAN_FILTER:
+		dev_info(&oct->pci_dev->dev, "%s VLAN filter %d removed\n",
+			 netdev->name, nctrl->ncmd.s.param1);
+		break;
+
 	case OCTNET_CMD_SET_SETTINGS:
 		dev_info(&oct->pci_dev->dev, "%s settings changed\n",
 			 netdev->name);
 
 		break;
 
+	case OCTNET_CMD_SET_FLOW_CTL:
+		netif_info(lio, probe, lio->netdev, "Set RX/TX flow control parameters\n");
+		break;
+
 	default:
 		dev_err(&oct->pci_dev->dev, "%s Unknown cmd %d\n", __func__,
 			nctrl->ncmd.s.cmd);
@@ -2898,6 +3009,13 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 	if (skb_shinfo(skb)->gso_size) {
 		tx_info->s.gso_size = skb_shinfo(skb)->gso_size;
 		tx_info->s.gso_segs = skb_shinfo(skb)->gso_segs;
+		stats->tx_gso++;
+	}
+
+	/* HW insert VLAN tag */
+	if (skb_vlan_tag_present(skb)) {
+		irh->priority = skb_vlan_tag_get(skb) >> 13;
+		irh->vlan = skb_vlan_tag_get(skb) & 0xfff;
 	}
 
 	xmit_more = skb->xmit_more;
@@ -2916,7 +3034,10 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	netif_trans_update(netdev);
 
-	stats->tx_done++;
+	if (skb_shinfo(skb)->gso_size)
+		stats->tx_done += skb_shinfo(skb)->gso_segs;
+	else
+		stats->tx_done++;
 	stats->tx_tot_bytes += skb->len;
 
 	return NETDEV_TX_OK;
@@ -2948,6 +3069,61 @@ static void liquidio_tx_timeout(struct net_device *netdev)
 	txqs_wake(netdev);
 }
 
+static int liquidio_vlan_rx_add_vid(struct net_device *netdev,
+				    __be16 proto __attribute__((unused)),
+				    u16 vid)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octnic_ctrl_pkt nctrl;
+	int ret = 0;
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = OCTNET_CMD_ADD_VLAN_FILTER;
+	nctrl.ncmd.s.param1 = vid;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+	nctrl.wait_time = 100;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
+			ret);
+	}
+
+	return ret;
+}
+
+static int liquidio_vlan_rx_kill_vid(struct net_device *netdev,
+				     __be16 proto __attribute__((unused)),
+				     u16 vid)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octnic_ctrl_pkt nctrl;
+	int ret = 0;
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = OCTNET_CMD_DEL_VLAN_FILTER;
+	nctrl.ncmd.s.param1 = vid;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+	nctrl.wait_time = 100;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
+			ret);
+	}
+	return ret;
+}
+
 int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1)
 {
 	struct lio *lio = GET_LIO(netdev);
@@ -3039,6 +3215,9 @@ static struct net_device_ops lionetdevops = {
 	.ndo_set_mac_address	= liquidio_set_mac,
 	.ndo_set_rx_mode	= liquidio_set_mcast_list,
 	.ndo_tx_timeout		= liquidio_tx_timeout,
+
+	.ndo_vlan_rx_add_vid    = liquidio_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid   = liquidio_vlan_rx_kill_vid,
 	.ndo_change_mtu		= liquidio_change_mtu,
 	.ndo_do_ioctl		= liquidio_ioctl,
 	.ndo_fix_features	= liquidio_fix_features,
@@ -3300,11 +3479,18 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 				| NETIF_F_LRO;
 		netif_set_gso_max_size(netdev, OCTNIC_GSO_MAX_SIZE);
 
-		netdev->features = (lio->dev_capability & ~NETIF_F_LRO);
-
 		netdev->vlan_features = lio->dev_capability;
+		/* Add any unchangeable hw features */
+		lio->dev_capability |=  NETIF_F_HW_VLAN_CTAG_FILTER |
+					NETIF_F_HW_VLAN_CTAG_RX |
+					NETIF_F_HW_VLAN_CTAG_TX;
+
+		netdev->features = (lio->dev_capability & ~NETIF_F_LRO);
 
 		netdev->hw_features = lio->dev_capability;
+		/*HW_VLAN_RX and HW_VLAN_FILTER is always on*/
+		netdev->hw_features = netdev->hw_features &
+			~NETIF_F_HW_VLAN_CTAG_RX;
 
 		/* Point to the  properties for octeon device to which this
 		 * interface belongs.
@@ -3349,14 +3535,17 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 
 		/* Register ethtool support */
 		liquidio_set_ethtool_ops(netdev);
+		octeon_dev->priv_flags = 0x0;
 
 		if (netdev->features & NETIF_F_LRO)
 		liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE,
 				     OCTNIC_LROIPV4 | OCTNIC_LROIPV6);
 
+		liquidio_set_feature(netdev, OCTNET_CMD_ENABLE_VLAN_FILTER, 0);
+
 		if ((debug != -1) && (debug & NETIF_MSG_HW))
-			liquidio_set_feature(netdev, OCTNET_CMD_VERBOSE_ENABLE,
-					     0);
+			liquidio_set_feature(netdev,
+					     OCTNET_CMD_VERBOSE_ENABLE, 0);
 
 		/* Register the network device with the OS */
 		if (register_netdev(netdev)) {
@@ -3429,15 +3618,19 @@ static int liquidio_init_nic_module(struct octeon_device *oct)
 
 	/* Initialize interrupt moderation params */
 	intrmod_cfg = &((struct octeon_device *)oct)->intrmod;
-	intrmod_cfg->intrmod_enable = 1;
-	intrmod_cfg->intrmod_check_intrvl = LIO_INTRMOD_CHECK_INTERVAL;
-	intrmod_cfg->intrmod_maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
-	intrmod_cfg->intrmod_minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
-	intrmod_cfg->intrmod_maxcnt_trigger = LIO_INTRMOD_MAXCNT_TRIGGER;
-	intrmod_cfg->intrmod_maxtmr_trigger = LIO_INTRMOD_MAXTMR_TRIGGER;
-	intrmod_cfg->intrmod_mintmr_trigger = LIO_INTRMOD_MINTMR_TRIGGER;
-	intrmod_cfg->intrmod_mincnt_trigger = LIO_INTRMOD_MINCNT_TRIGGER;
-
+	intrmod_cfg->rx_enable = 1;
+	intrmod_cfg->check_intrvl =   LIO_INTRMOD_CHECK_INTERVAL;
+	intrmod_cfg->maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
+	intrmod_cfg->minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
+	intrmod_cfg->rx_maxcnt_trigger = LIO_INTRMOD_RXMAXCNT_TRIGGER;
+	intrmod_cfg->rx_maxtmr_trigger = LIO_INTRMOD_RXMAXTMR_TRIGGER;
+	intrmod_cfg->rx_mintmr_trigger = LIO_INTRMOD_RXMINTMR_TRIGGER;
+	intrmod_cfg->rx_mincnt_trigger = LIO_INTRMOD_RXMINCNT_TRIGGER;
+	intrmod_cfg->tx_enable = 1;
+	intrmod_cfg->tx_maxcnt_trigger = LIO_INTRMOD_TXMAXCNT_TRIGGER;
+	intrmod_cfg->tx_mincnt_trigger = LIO_INTRMOD_TXMINCNT_TRIGGER;
+	intrmod_cfg->rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
+	intrmod_cfg->rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
 	dev_dbg(&oct->pci_dev->dev, "Network interfaces ready\n");
 
 	return retval;
@@ -3500,6 +3693,7 @@ static void nic_starter(struct work_struct *work)
 static int octeon_device_init(struct octeon_device *octeon_dev)
 {
 	int j, ret;
+	char bootcmd[] = "\n";
 	struct octeon_device_priv *oct_priv =
 		(struct octeon_device_priv *)octeon_dev->priv;
 	atomic_set(&octeon_dev->status, OCT_DEV_BEGIN_STATE);
@@ -3611,14 +3805,19 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 
 	dev_dbg(&octeon_dev->pci_dev->dev, "Waiting for DDR initialization...\n");
 
-	if (ddr_timeout == 0) {
-		dev_info(&octeon_dev->pci_dev->dev,
-			 "WAITING. Set ddr_timeout to non-zero value to proceed with initialization.\n");
-	}
+	if (ddr_timeout == 0)
+		dev_info(&octeon_dev->pci_dev->dev, "WAITING. Set ddr_timeout to non-zero value to proceed with initialization.\n");
 
 	schedule_timeout_uninterruptible(HZ * LIO_RESET_SECS);
 
 	/* Wait for the octeon to initialize DDR after the soft-reset. */
+	while (ddr_timeout == 0) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (schedule_timeout(HZ / 10)) {
+			/* user probably pressed Control-C */
+			return 1;
+		}
+	}
 	ret = octeon_wait_for_ddr_init(octeon_dev, &ddr_timeout);
 	if (ret) {
 		dev_err(&octeon_dev->pci_dev->dev,
@@ -3632,6 +3831,9 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 		return 1;
 	}
 
+	/* Divert uboot to take commands from host instead. */
+	ret = octeon_console_send_cmd(octeon_dev, bootcmd, 50);
+
 	dev_dbg(&octeon_dev->pci_dev->dev, "Initializing consoles\n");
 	ret = octeon_init_consoles(octeon_dev);
 	if (ret) {

drivers/net/ethernet/cavium/liquidio/liquidio_common.h

@@ -30,11 +30,10 @@
 
 #include "octeon_config.h"
 
-#define LIQUIDIO_VERSION        "1.1.9"
-#define LIQUIDIO_MAJOR_VERSION  1
-#define LIQUIDIO_MINOR_VERSION  1
-#define LIQUIDIO_MICRO_VERSION  9
-
+#define LIQUIDIO_BASE_VERSION   "1.4"
+#define LIQUIDIO_MICRO_VERSION  ".1"
+#define LIQUIDIO_PACKAGE ""
+#define LIQUIDIO_VERSION  "1.4.1"
 #define CONTROL_IQ 0
 /** Tag types used by Octeon cores in its work. */
 enum octeon_tag_type {
@@ -214,6 +213,10 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry,
 #define   OCTNET_CMD_VERBOSE_ENABLE   0x14
 #define   OCTNET_CMD_VERBOSE_DISABLE  0x15
 
+#define   OCTNET_CMD_ENABLE_VLAN_FILTER 0x16
+#define   OCTNET_CMD_ADD_VLAN_FILTER  0x17
+#define   OCTNET_CMD_DEL_VLAN_FILTER  0x18
+
 /* RX(packets coming from wire) Checksum verification flags */
 /* TCP/UDP csum */
 #define   CNNIC_L4SUM_VERIFIED             0x1
@@ -482,15 +485,15 @@ struct octeon_instr_irh {
 	u64 opcode:4;
 	u64 rflag:1;
 	u64 subcode:7;
-	u64 len:3;
-	u64 rid:13;
-	u64 reserved:4;
+	u64 vlan:12;
+	u64 priority:3;
+	u64 reserved:5;
 	u64 ossp:32;             /* opcode/subcode specific parameters */
 #else
 	u64 ossp:32;             /* opcode/subcode specific parameters */
-	u64 reserved:4;
-	u64 rid:13;
-	u64 len:3;
+	u64 reserved:5;
+	u64 priority:3;
+	u64 vlan:12;
 	u64 subcode:7;
 	u64 rflag:1;
 	u64 opcode:4;
@@ -517,28 +520,27 @@ union octeon_rh {
 	struct {
 		u64 opcode:4;
 		u64 subcode:8;
-		u64 len:3;       /** additional 64-bit words */
-		u64 rid:13;      /** request id in response to pkt sent by host */
-		u64 reserved:4;
-		u64 ossp:32;     /** opcode/subcode specific parameters */
+		u64 len:3;     /** additional 64-bit words */
+		u64 reserved:17;
+		u64 ossp:32;   /** opcode/subcode specific parameters */
 	} r;
 	struct {
 		u64 opcode:4;
 		u64 subcode:8;
-		u64 len:3;       /** additional 64-bit words */
-		u64 rid:13;      /** request id in response to pkt sent by host */
-		u64 extra:24;
-		u64 link:8;
+		u64 len:3;     /** additional 64-bit words */
+		u64 extra:28;
+		u64 vlan:12;
+		u64 priority:3;
 		u64 csum_verified:3;     /** checksum verified. */
 		u64 has_hwtstamp:1;      /** Has hardware timestamp. 1 = yes. */
 	} r_dh;
 	struct {
 		u64 opcode:4;
 		u64 subcode:8;
-		u64 len:3;       /** additional 64-bit words */
-		u64 rid:13;      /** request id in response to pkt sent by host */
+		u64 len:3;     /** additional 64-bit words */
+		u64 reserved:11;
 		u64 num_gmx_ports:8;
-		u64 max_nic_ports:8;
+		u64 max_nic_ports:10;
 		u64 app_cap_flags:4;
 		u64 app_mode:16;
 	} r_core_drv_init;
@@ -554,8 +556,7 @@ union octeon_rh {
 	u64 u64;
 	struct {
 		u64 ossp:32;  /** opcode/subcode specific parameters */
-		u64 reserved:4;
-		u64 rid:13;   /** req id in response to pkt sent by host */
+		u64 reserved:17;
 		u64 len:3;    /** additional 64-bit words */
 		u64 subcode:8;
 		u64 opcode:4;
@@ -563,9 +564,9 @@ union octeon_rh {
 	struct {
 		u64 has_hwtstamp:1;      /** 1 = has hwtstamp */
 		u64 csum_verified:3;     /** checksum verified. */
-		u64 link:8;
-		u64 extra:24;
-		u64 rid:13;   /** req id in response to pkt sent by host */
+		u64 priority:3;
+		u64 vlan:12;
+		u64 extra:28;
 		u64 len:3;    /** additional 64-bit words */
 		u64 subcode:8;
 		u64 opcode:4;
@@ -573,9 +574,9 @@ union octeon_rh {
 	struct {
 		u64 app_mode:16;
 		u64 app_cap_flags:4;
-		u64 max_nic_ports:8;
+		u64 max_nic_ports:10;
 		u64 num_gmx_ports:8;
-		u64 rid:13;
+		u64 reserved:11;
 		u64 len:3;       /** additional 64-bit words */
 		u64 subcode:8;
 		u64 opcode:4;
@@ -627,13 +628,13 @@ union oct_link_status {
 		u64 speed:16;
 		u64 link_up:1;
 		u64 autoneg:1;
-		u64 interface:4;
+		u64 if_mode:5;
 		u64 pause:1;
-		u64 reserved:17;
+		u64 reserved:16;
 #else
-		u64 reserved:17;
+		u64 reserved:16;
 		u64 pause:1;
-		u64 interface:4;
+		u64 if_mode:5;
 		u64 autoneg:1;
 		u64 link_up:1;
 		u64 speed:16;
@@ -710,6 +711,7 @@ struct liquidio_if_cfg_info {
 	u64 iqmask; /** mask for IQs enabled for  the port */
 	u64 oqmask; /** mask for OQs enabled for the port */
 	struct oct_link_info linfo; /** initial link information */
+	char   liquidio_firmware_version[32];
 };
 
 /** Stats for each NIC port in RX direction. */
@@ -734,10 +736,16 @@ struct nic_rx_stats {
 	u64 fw_err_pko;
 	u64 fw_err_link;
 	u64 fw_err_drop;
+
+	/* LRO */
 	u64 fw_lro_pkts;   /* Number of packets that are LROed      */
 	u64 fw_lro_octs;   /* Number of octets that are LROed       */
 	u64 fw_total_lro;  /* Number of LRO packets formed          */
 	u64 fw_lro_aborts; /* Number of times lRO of packet aborted */
+	u64 fw_lro_aborts_port;
+	u64 fw_lro_aborts_seq;
+	u64 fw_lro_aborts_tsval;
+	u64 fw_lro_aborts_timer;
 	/* intrmod: packet forward rate */
 	u64 fwd_rate;
 };
@@ -761,9 +769,13 @@ struct nic_tx_stats {
 	/* firmware stats */
 	u64 fw_total_sent;
 	u64 fw_total_fwd;
+	u64 fw_total_fwd_bytes;
 	u64 fw_err_pko;
 	u64 fw_err_link;
 	u64 fw_err_drop;
+	u64 fw_err_tso;
+	u64 fw_tso;		/* number of tso requests */
+	u64 fw_tso_fwd;		/* number of packets segmented in tso */
 };
 
 struct oct_link_stats {
@@ -794,23 +806,44 @@ struct oct_mdio_cmd {
 
 #define OCT_LINK_STATS_SIZE   (sizeof(struct oct_link_stats))
 
+/* intrmod: max. packet rate threshold */
+#define LIO_INTRMOD_MAXPKT_RATETHR	196608
+/* intrmod: min. packet rate threshold */
+#define LIO_INTRMOD_MINPKT_RATETHR	9216
+/* intrmod: max. packets to trigger interrupt */
+#define LIO_INTRMOD_RXMAXCNT_TRIGGER	384
+/* intrmod: min. packets to trigger interrupt */
+#define LIO_INTRMOD_RXMINCNT_TRIGGER	1
+/* intrmod: max. time to trigger interrupt */
+#define LIO_INTRMOD_RXMAXTMR_TRIGGER	128
+/* 66xx:intrmod: min. time to trigger interrupt
+ * (value of 1 is optimum for TCP_RR)
+ */
+#define LIO_INTRMOD_RXMINTMR_TRIGGER	1
+
+/* intrmod: max. packets to trigger interrupt */
+#define LIO_INTRMOD_TXMAXCNT_TRIGGER	64
+/* intrmod: min. packets to trigger interrupt */
+#define LIO_INTRMOD_TXMINCNT_TRIGGER	0
+
+/* intrmod: poll interval in seconds */
 #define LIO_INTRMOD_CHECK_INTERVAL  1
-#define LIO_INTRMOD_MAXPKT_RATETHR  196608 /* max pkt rate threshold */
-#define LIO_INTRMOD_MINPKT_RATETHR  9216   /* min pkt rate threshold */
-#define LIO_INTRMOD_MAXCNT_TRIGGER  384    /* max pkts to trigger interrupt */
-#define LIO_INTRMOD_MINCNT_TRIGGER  1      /* min pkts to trigger interrupt */
-#define LIO_INTRMOD_MAXTMR_TRIGGER  128    /* max time to trigger interrupt */
-#define LIO_INTRMOD_MINTMR_TRIGGER  32     /* min time to trigger interrupt */
 
 struct oct_intrmod_cfg {
-	u64 intrmod_enable;
-	u64 intrmod_check_intrvl;
-	u64 intrmod_maxpkt_ratethr;
-	u64 intrmod_minpkt_ratethr;
-	u64 intrmod_maxcnt_trigger;
-	u64 intrmod_maxtmr_trigger;
-	u64 intrmod_mincnt_trigger;
-	u64 intrmod_mintmr_trigger;
+	u64 rx_enable;
+	u64 tx_enable;
+	u64 check_intrvl;
+	u64 maxpkt_ratethr;
+	u64 minpkt_ratethr;
+	u64 rx_maxcnt_trigger;
+	u64 rx_mincnt_trigger;
+	u64 rx_maxtmr_trigger;
+	u64 rx_mintmr_trigger;
+	u64 tx_mincnt_trigger;
+	u64 tx_maxcnt_trigger;
+	u64 rx_frames;
+	u64 tx_frames;
+	u64 rx_usecs;
 };
 
 #define BASE_QUEUE_NOT_REQUESTED 65535

drivers/net/ethernet/cavium/liquidio/octeon_config.h

@@ -37,7 +37,7 @@
 /* Maximum octeon devices defined as MAX_OCTEON_NICIF to support
  * multiple(<= MAX_OCTEON_NICIF) Miniports
  */
-#define   MAX_OCTEON_NICIF             32
+#define   MAX_OCTEON_NICIF             128
 #define   MAX_OCTEON_DEVICES           MAX_OCTEON_NICIF
 #define   MAX_OCTEON_LINKS	       MAX_OCTEON_NICIF
 #define   MAX_OCTEON_MULTICAST_ADDR    32
@@ -135,7 +135,7 @@
 #define CFG_GET_IS_SLI_BP_ON(cfg)                ((cfg)->misc.enable_sli_oq_bp)
 
 /* Max IOQs per OCTEON Link */
-#define MAX_IOQS_PER_NICIF              32
+#define MAX_IOQS_PER_NICIF              64
 
 enum lio_card_type {
 	LIO_210SV = 0, /* Two port, 66xx */
@@ -416,9 +416,11 @@ struct octeon_config {
 #define DISPATCH_LIST_SIZE                      BIT(OPCODE_MASK_BITS)
 
 /* Maximum number of Octeon Instruction (command) queues */
-#define MAX_OCTEON_INSTR_QUEUES         CN6XXX_MAX_INPUT_QUEUES
+#define MAX_OCTEON_INSTR_QUEUES(oct)         CN6XXX_MAX_INPUT_QUEUES
+/* Maximum number of Octeon Output queues */
+#define MAX_OCTEON_OUTPUT_QUEUES(oct)         CN6XXX_MAX_OUTPUT_QUEUES
 
-/* Maximum number of Octeon Instruction (command) queues */
-#define MAX_OCTEON_OUTPUT_QUEUES        CN6XXX_MAX_OUTPUT_QUEUES
+#define MAX_POSSIBLE_OCTEON_INSTR_QUEUES       CN6XXX_MAX_INPUT_QUEUES
+#define MAX_POSSIBLE_OCTEON_OUTPUT_QUEUES      CN6XXX_MAX_OUTPUT_QUEUES
 
 #endif /* __OCTEON_CONFIG_H__  */

drivers/net/ethernet/cavium/liquidio/octeon_device.c

@@ -549,17 +549,19 @@ static char *get_oct_app_string(u32 app_mode)
 	return oct_dev_app_str[CVM_DRV_INVALID_APP - CVM_DRV_APP_START];
 }
 
+u8 fbuf[4 * 1024 * 1024];
+
 int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
 			     size_t size)
 {
 	int ret = 0;
-	u8 *p;
-	u8 *buffer;
+	u8 *p = fbuf;
 	u32 crc32_result;
 	u64 load_addr;
 	u32 image_len;
 	struct octeon_firmware_file_header *h;
-	u32 i;
+	u32 i, rem, base_len = strlen(LIQUIDIO_BASE_VERSION);
+	char *base;
 
 	if (size < sizeof(struct octeon_firmware_file_header)) {
 		dev_err(&oct->pci_dev->dev, "Firmware file too small (%d < %d).\n",
@@ -575,19 +577,26 @@ int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
 		return -EINVAL;
 	}
 
-	crc32_result =
-		crc32(~0, data,
-		      sizeof(struct octeon_firmware_file_header) -
-		      sizeof(u32)) ^ ~0U;
+	crc32_result = crc32((unsigned int)~0, data,
+			     sizeof(struct octeon_firmware_file_header) -
+			     sizeof(u32)) ^ ~0U;
 	if (crc32_result != be32_to_cpu(h->crc32)) {
 		dev_err(&oct->pci_dev->dev, "Firmware CRC mismatch (0x%08x != 0x%08x).\n",
 			crc32_result, be32_to_cpu(h->crc32));
 		return -EINVAL;
 	}
 
-	if (memcmp(LIQUIDIO_VERSION, h->version, strlen(LIQUIDIO_VERSION))) {
-		dev_err(&oct->pci_dev->dev, "Unmatched firmware version. Expected %s, got %s.\n",
-			LIQUIDIO_VERSION, h->version);
+	if (strncmp(LIQUIDIO_PACKAGE, h->version, strlen(LIQUIDIO_PACKAGE))) {
+		dev_err(&oct->pci_dev->dev, "Unmatched firmware package type. Expected %s, got %s.\n",
+			LIQUIDIO_PACKAGE, h->version);
+		return -EINVAL;
+	}
+
+	base = h->version + strlen(LIQUIDIO_PACKAGE);
+	ret = memcmp(LIQUIDIO_BASE_VERSION, base, base_len);
+	if (ret) {
+		dev_err(&oct->pci_dev->dev, "Unmatched firmware version. Expected %s.x, got %s.\n",
+			LIQUIDIO_BASE_VERSION, base);
 		return -EINVAL;
 	}
 
@@ -601,56 +610,56 @@ int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
 	snprintf(oct->fw_info.liquidio_firmware_version, 32, "LIQUIDIO: %s",
 		 h->version);
 
-	buffer = kmemdup(data, size, GFP_KERNEL);
-	if (!buffer)
-		return -ENOMEM;
-
-	p = buffer + sizeof(struct octeon_firmware_file_header);
+	data += sizeof(struct octeon_firmware_file_header);
 
+	dev_info(&oct->pci_dev->dev, "%s: Loading %d images\n", __func__,
+		 be32_to_cpu(h->num_images));
 	/* load all images */
 	for (i = 0; i < be32_to_cpu(h->num_images); i++) {
 		load_addr = be64_to_cpu(h->desc[i].addr);
 		image_len = be32_to_cpu(h->desc[i].len);
 
-		/* validate the image */
-		crc32_result = crc32(~0, p, image_len) ^ ~0U;
-		if (crc32_result != be32_to_cpu(h->desc[i].crc32)) {
-			dev_err(&oct->pci_dev->dev,
-				"Firmware CRC mismatch in image %d (0x%08x != 0x%08x).\n",
-				i, crc32_result,
-				be32_to_cpu(h->desc[i].crc32));
-			ret = -EINVAL;
-			goto done_downloading;
-		}
+		dev_info(&oct->pci_dev->dev, "Loading firmware %d at %llx\n",
+			 image_len, load_addr);
 
-		/* download the image */
-		octeon_pci_write_core_mem(oct, load_addr, p, image_len);
+		/* Write in 4MB chunks*/
+		rem = image_len;
 
-		p += image_len;
-		dev_dbg(&oct->pci_dev->dev,
-			"Downloaded image %d (%d bytes) to address 0x%016llx\n",
-			i, image_len, load_addr);
+		while (rem) {
+			if (rem < (4 * 1024 * 1024))
+				size = rem;
+			else
+				size = 4 * 1024 * 1024;
+
+			memcpy(p, data, size);
+
+			/* download the image */
+			octeon_pci_write_core_mem(oct, load_addr, p, (u32)size);
+
+			data += size;
+			rem -= (u32)size;
+			load_addr += size;
+		}
 	}
+	dev_info(&oct->pci_dev->dev, "Writing boot command: %s\n",
+		 h->bootcmd);
 
 	/* Invoke the bootcmd */
 	ret = octeon_console_send_cmd(oct, h->bootcmd, 50);
 
-done_downloading:
-	kfree(buffer);
-
-	return ret;
+	return 0;
 }
 
 void octeon_free_device_mem(struct octeon_device *oct)
 {
 	u32 i;
 
-	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
 		/* could check  mask as well */
 		vfree(oct->droq[i]);
 	}
 
-	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
 		/* could check mask as well */
 		vfree(oct->instr_queue[i]);
 	}
@@ -734,7 +743,7 @@ struct octeon_device *octeon_allocate_device(u32 pci_id,
 	octeon_device[oct_idx] = oct;
 
 	oct->octeon_id = oct_idx;
-	snprintf((oct->device_name), sizeof(oct->device_name),
+	snprintf(oct->device_name, sizeof(oct->device_name),
 		 "LiquidIO%d", (oct->octeon_id));
 
 	return oct;
@@ -1157,8 +1166,8 @@ core_drv_init_err:
 int octeon_get_tx_qsize(struct octeon_device *oct, u32 q_no)
 
 {
-	if (oct && (q_no < MAX_OCTEON_INSTR_QUEUES) &&
-	    (oct->io_qmask.iq & (1UL << q_no)))
+	if (oct && (q_no < MAX_OCTEON_INSTR_QUEUES(oct)) &&
+	    (oct->io_qmask.iq & (1ULL << q_no)))
 		return oct->instr_queue[q_no]->max_count;
 
 	return -1;
@@ -1166,8 +1175,8 @@ int octeon_get_tx_qsize(struct octeon_device *oct, u32 q_no)
 
 int octeon_get_rx_qsize(struct octeon_device *oct, u32 q_no)
 {
-	if (oct && (q_no < MAX_OCTEON_OUTPUT_QUEUES) &&
-	    (oct->io_qmask.oq & (1UL << q_no)))
+	if (oct && (q_no < MAX_OCTEON_OUTPUT_QUEUES(oct)) &&
+	    (oct->io_qmask.oq & (1ULL << q_no)))
 		return oct->droq[q_no]->max_count;
 	return -1;
 }
@@ -1258,10 +1267,10 @@ void lio_pci_writeq(struct octeon_device *oct,
 int octeon_mem_access_ok(struct octeon_device *oct)
 {
 	u64 access_okay = 0;
+	u64 lmc0_reset_ctl;
 
 	/* Check to make sure a DDR interface is enabled */
-	u64 lmc0_reset_ctl = lio_pci_readq(oct, CN6XXX_LMC0_RESET_CTL);
-
+	lmc0_reset_ctl = lio_pci_readq(oct, CN6XXX_LMC0_RESET_CTL);
 	access_okay = (lmc0_reset_ctl & CN6XXX_LMC0_RESET_CTL_DDR3RST_MASK);
 
 	return access_okay ? 0 : 1;
@@ -1275,9 +1284,6 @@ int octeon_wait_for_ddr_init(struct octeon_device *oct, u32 *timeout)
 	if (!timeout)
 		return ret;
 
-	while (*timeout == 0)
-		schedule_timeout_uninterruptible(HZ / 10);
-
 	for (ms = 0; (ret != 0) && ((*timeout == 0) || (ms <= *timeout));
 	     ms += HZ / 10) {
 		ret = octeon_mem_access_ok(oct);

drivers/net/ethernet/cavium/liquidio/octeon_device.h

@@ -152,9 +152,9 @@ struct octeon_mmio {
 #define   MAX_OCTEON_MAPS    32
 
 struct octeon_io_enable {
-	u32 iq;
-	u32 oq;
-	u32 iq64B;
+	u64 iq;
+	u64 oq;
+	u64 iq64B;
 };
 
 struct octeon_reg_list {
@@ -204,8 +204,7 @@ struct octeon_fn_list {
 	void (*bar1_idx_setup)(struct octeon_device *, u64, u32, int);
 	void (*bar1_idx_write)(struct octeon_device *, u32, u32);
 	u32 (*bar1_idx_read)(struct octeon_device *, u32);
-	u32 (*update_iq_read_idx)(struct octeon_device *,
-				  struct octeon_instr_queue *);
+	u32 (*update_iq_read_idx)(struct octeon_instr_queue *);
 
 	void (*enable_oq_pkt_time_intr)(struct octeon_device *, u32);
 	void (*disable_oq_pkt_time_intr)(struct octeon_device *, u32);
@@ -267,6 +266,7 @@ struct octdev_props {
 	/* Each interface in the Octeon device has a network
 	 * device pointer (used for OS specific calls).
 	 */
+	int    napi_enabled;
 	int    gmxport;
 	struct net_device *netdev;
 };
@@ -325,7 +325,8 @@ struct octeon_device {
 	struct octeon_sc_buffer_pool	sc_buf_pool;
 
 	/** The input instruction queues */
-	struct octeon_instr_queue *instr_queue[MAX_OCTEON_INSTR_QUEUES];
+	struct octeon_instr_queue *instr_queue
+		[MAX_POSSIBLE_OCTEON_INSTR_QUEUES];
 
 	/** The doubly-linked list of instruction response */
 	struct octeon_response_list response_list[MAX_RESPONSE_LISTS];
@@ -333,7 +334,7 @@ struct octeon_device {
 	u32 num_oqs;
 
 	/** The DROQ output queues  */
-	struct octeon_droq *droq[MAX_OCTEON_OUTPUT_QUEUES];
+	struct octeon_droq *droq[MAX_POSSIBLE_OCTEON_OUTPUT_QUEUES];
 
 	struct octeon_io_enable io_qmask;
 
@@ -382,15 +383,29 @@ struct octeon_device {
 
 	struct cavium_wq dma_comp_wq;
 
-	struct cavium_wq check_db_wq[MAX_OCTEON_INSTR_QUEUES];
+	/** Lock for dma response list */
+	spinlock_t cmd_resp_wqlock;
+	u32 cmd_resp_state;
+
+	struct cavium_wq check_db_wq[MAX_POSSIBLE_OCTEON_INSTR_QUEUES];
 
 	struct cavium_wk nic_poll_work;
 
 	struct cavium_wk console_poll_work[MAX_OCTEON_MAPS];
 
 	void *priv;
+
+	int rx_pause;
+	int tx_pause;
+
+	struct oct_link_stats link_stats; /*stastics from firmware*/
+
+	/* private flags to control driver-specific features through ethtool */
+	u32 priv_flags;
 };
 
+#define  OCT_DRV_ONLINE 1
+#define  OCT_DRV_OFFLINE 2
 #define  OCTEON_CN6XXX(oct)           ((oct->chip_id == OCTEON_CN66XX) || \
 				       (oct->chip_id == OCTEON_CN68XX))
 #define CHIP_FIELD(oct, TYPE, field)             \
@@ -647,4 +662,17 @@ void *oct_get_config_info(struct octeon_device *oct, u16 card_type);
  */
 struct octeon_config *octeon_get_conf(struct octeon_device *oct);
 
+/* LiquidIO driver pivate flags */
+enum {
+	OCT_PRIV_FLAG_TX_BYTES = 0, /* Tx interrupts by pending byte count */
+};
+
+static inline void lio_set_priv_flag(struct octeon_device *octdev, u32 flag,
+				     u32 val)
+{
+	if (val)
+		octdev->priv_flags |= (0x1 << flag);
+	else
+		octdev->priv_flags &= ~(0x1 << flag);
+}
 #endif

drivers/net/ethernet/cavium/liquidio/octeon_droq.c

@@ -337,7 +337,7 @@ int octeon_init_droq(struct octeon_device *oct,
 	/* For 56xx Pass1, this function won't be called, so no checks. */
 	oct->fn_list.setup_oq_regs(oct, q_no);
 
-	oct->io_qmask.oq |= (1 << q_no);
+	oct->io_qmask.oq |= (1ULL << q_no);
 
 	return 0;
 

drivers/net/ethernet/cavium/liquidio/octeon_iq.h

@@ -65,6 +65,10 @@ struct oct_iq_stats {
 	u64 tx_iq_busy;/**< Numof times this iq was found to be full. */
 	u64 tx_dropped;/**< Numof pkts dropped dueto xmitpath errors. */
 	u64 tx_tot_bytes;/**< Total count of bytes sento to network. */
+	u64 tx_gso;  /* count of tso */
+	u64 tx_dmamap_fail;
+	u64 tx_restart;
+	/*u64 tx_timeout_count;*/
 };
 
 #define OCT_IQ_STATS_SIZE   (sizeof(struct oct_iq_stats))
@@ -80,6 +84,12 @@ struct octeon_instr_queue {
 	/** A spinlock to protect access to the input ring.  */
 	spinlock_t lock;
 
+	/** A spinlock to protect while posting on the ring.  */
+	spinlock_t post_lock;
+
+	/** A spinlock to protect access to the input ring.*/
+	spinlock_t iq_flush_running_lock;
+
 	/** Flag that indicates if the queue uses 64 byte commands. */
 	u32 iqcmd_64B:1;
 
@@ -244,7 +254,7 @@ union octeon_instr_64B {
 
 /** The size of each buffer in soft command buffer pool
  */
-#define  SOFT_COMMAND_BUFFER_SIZE	1024
+#define  SOFT_COMMAND_BUFFER_SIZE	1536
 
 struct octeon_soft_command {
 	/** Soft command buffer info. */
@@ -282,7 +292,7 @@ struct octeon_soft_command {
 
 /** Maximum number of buffers to allocate into soft command buffer pool
  */
-#define  MAX_SOFT_COMMAND_BUFFERS	16
+#define  MAX_SOFT_COMMAND_BUFFERS	256
 
 /** Head of a soft command buffer pool.
  */
@@ -339,7 +349,7 @@ octeon_register_reqtype_free_fn(struct octeon_device *oct, int reqtype,
 
 int
 lio_process_iq_request_list(struct octeon_device *oct,
-			    struct octeon_instr_queue *iq);
+			    struct octeon_instr_queue *iq, u32 napi_budget);
 
 int octeon_send_command(struct octeon_device *oct, u32 iq_no,
 			u32 force_db, void *cmd, void *buf,
@@ -357,5 +367,7 @@ int octeon_send_soft_command(struct octeon_device *oct,
 int octeon_setup_iq(struct octeon_device *oct, int ifidx,
 		    int q_index, union oct_txpciq iq_no, u32 num_descs,
 		    void *app_ctx);
-
+int
+octeon_flush_iq(struct octeon_device *oct, struct octeon_instr_queue *iq,
+		u32 pending_thresh, u32 napi_budget);
 #endif				/* __OCTEON_IQ_H__ */

drivers/net/ethernet/cavium/liquidio/octeon_network.h

@@ -30,6 +30,17 @@
 #include <linux/dma-mapping.h>
 #include <linux/ptp_clock_kernel.h>
 
+struct oct_nic_stats_resp {
+	u64     rh;
+	struct oct_link_stats stats;
+	u64     status;
+};
+
+struct oct_nic_stats_ctrl {
+	struct completion complete;
+	struct net_device *netdev;
+};
+
 /** LiquidIO per-interface network private data */
 struct lio {
 	/** State of the interface. Rx/Tx happens only in the RUNNING state.  */

drivers/net/ethernet/cavium/liquidio/octeon_nic.c

@@ -171,20 +171,36 @@ octnet_send_nic_ctrl_pkt(struct octeon_device *oct,
 	int retval;
 	struct octeon_soft_command *sc = NULL;
 
+	spin_lock_bh(&oct->cmd_resp_wqlock);
+	/* Allow only rx ctrl command to stop traffic on the chip
+	 * during offline operations
+	 */
+	if ((oct->cmd_resp_state == OCT_DRV_OFFLINE) &&
+	    (nctrl->ncmd.s.cmd != OCTNET_CMD_RX_CTL)) {
+		spin_unlock_bh(&oct->cmd_resp_wqlock);
+		dev_err(&oct->pci_dev->dev,
+			"%s cmd:%d not processed since driver offline\n",
+			__func__, nctrl->ncmd.s.cmd);
+		return -1;
+	}
+
 	sc = octnic_alloc_ctrl_pkt_sc(oct, nctrl);
 	if (!sc) {
 		dev_err(&oct->pci_dev->dev, "%s soft command alloc failed\n",
 			__func__);
+		spin_unlock_bh(&oct->cmd_resp_wqlock);
 		return -1;
 	}
 
 	retval = octeon_send_soft_command(oct, sc);
 	if (retval == IQ_SEND_FAILED) {
 		octeon_free_soft_command(oct, sc);
-		dev_err(&oct->pci_dev->dev, "%s soft command send failed status: %x\n",
-			__func__, retval);
+		dev_err(&oct->pci_dev->dev, "%s soft command:%d send failed status: %x\n",
+			__func__, nctrl->ncmd.s.cmd, retval);
+		spin_unlock_bh(&oct->cmd_resp_wqlock);
 		return -1;
 	}
 
+	spin_unlock_bh(&oct->cmd_resp_wqlock);
 	return retval;
 }

drivers/net/ethernet/cavium/liquidio/request_manager.c

@@ -51,7 +51,7 @@ struct iq_post_status {
 };
 
 static void check_db_timeout(struct work_struct *work);
-static void  __check_db_timeout(struct octeon_device *oct, unsigned long iq_no);
+static void  __check_db_timeout(struct octeon_device *oct, u64 iq_no);
 
 static void (*reqtype_free_fn[MAX_OCTEON_DEVICES][REQTYPE_LAST + 1]) (void *);
 
@@ -149,8 +149,11 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 
 	/* Initialize the spinlock for this instruction queue */
 	spin_lock_init(&iq->lock);
+	spin_lock_init(&iq->post_lock);
 
-	oct->io_qmask.iq |= (1 << iq_no);
+	spin_lock_init(&iq->iq_flush_running_lock);
+
+	oct->io_qmask.iq |= (1ULL << iq_no);
 
 	/* Set the 32B/64B mode for each input queue */
 	oct->io_qmask.iq64B |= ((conf->instr_type == 64) << iq_no);
@@ -253,8 +256,8 @@ int lio_wait_for_instr_fetch(struct octeon_device *oct)
 		instr_cnt = 0;
 
 		/*for (i = 0; i < oct->num_iqs; i++) {*/
-		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
-			if (!(oct->io_qmask.iq & (1UL << i)))
+		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+			if (!(oct->io_qmask.iq & (1ULL << i)))
 				continue;
 			pending =
 			    atomic_read(&oct->
@@ -391,13 +394,13 @@ __add_to_request_list(struct octeon_instr_queue *iq,
 
 int
 lio_process_iq_request_list(struct octeon_device *oct,
-			    struct octeon_instr_queue *iq)
+			    struct octeon_instr_queue *iq, u32 napi_budget)
 {
 	int reqtype;
 	void *buf;
 	u32 old = iq->flush_index;
 	u32 inst_count = 0;
-	unsigned pkts_compl = 0, bytes_compl = 0;
+	unsigned int pkts_compl = 0, bytes_compl = 0;
 	struct octeon_soft_command *sc;
 	struct octeon_instr_irh *irh;
 
@@ -457,6 +460,9 @@ lio_process_iq_request_list(struct octeon_device *oct,
  skip_this:
 		inst_count++;
 		INCR_INDEX_BY1(old, iq->max_count);
+
+		if ((napi_budget) && (inst_count >= napi_budget))
+			break;
 	}
 	if (bytes_compl)
 		octeon_report_tx_completion_to_bql(iq->app_ctx, pkts_compl,
@@ -466,38 +472,63 @@ lio_process_iq_request_list(struct octeon_device *oct,
 	return inst_count;
 }
 
-static inline void
-update_iq_indices(struct octeon_device *oct, struct octeon_instr_queue *iq)
+/* Can only be called from process context */
+int
+octeon_flush_iq(struct octeon_device *oct, struct octeon_instr_queue *iq,
+		u32 pending_thresh, u32 napi_budget)
 {
 	u32 inst_processed = 0;
+	u32 tot_inst_processed = 0;
+	int tx_done = 1;
 
-	/* Calculate how many commands Octeon has read and move the read index
-	 * accordingly.
-	 */
-	iq->octeon_read_index = oct->fn_list.update_iq_read_idx(oct, iq);
+	if (!spin_trylock(&iq->iq_flush_running_lock))
+		return tx_done;
 
-	/* Move the NORESPONSE requests to the per-device completion list. */
-	if (iq->flush_index != iq->octeon_read_index)
-		inst_processed = lio_process_iq_request_list(oct, iq);
+	spin_lock_bh(&iq->lock);
 
-	if (inst_processed) {
-		atomic_sub(inst_processed, &iq->instr_pending);
-		iq->stats.instr_processed += inst_processed;
-	}
-}
+	iq->octeon_read_index = oct->fn_list.update_iq_read_idx(iq);
 
-static void
-octeon_flush_iq(struct octeon_device *oct, struct octeon_instr_queue *iq,
-		u32 pending_thresh)
-{
 	if (atomic_read(&iq->instr_pending) >= (s32)pending_thresh) {
-		spin_lock_bh(&iq->lock);
-		update_iq_indices(oct, iq);
-		spin_unlock_bh(&iq->lock);
+		do {
+			/* Process any outstanding IQ packets. */
+			if (iq->flush_index == iq->octeon_read_index)
+				break;
+
+			if (napi_budget)
+				inst_processed = lio_process_iq_request_list
+					(oct, iq,
+					 napi_budget - tot_inst_processed);
+			else
+				inst_processed =
+					lio_process_iq_request_list(oct, iq, 0);
+
+			if (inst_processed) {
+				atomic_sub(inst_processed, &iq->instr_pending);
+				iq->stats.instr_processed += inst_processed;
+			}
+
+			tot_inst_processed += inst_processed;
+			inst_processed = 0;
+
+		} while (tot_inst_processed < napi_budget);
+
+		if (napi_budget && (tot_inst_processed >= napi_budget))
+			tx_done = 0;
 	}
+
+	iq->last_db_time = jiffies;
+
+	spin_unlock_bh(&iq->lock);
+
+	spin_unlock(&iq->iq_flush_running_lock);
+
+	return tx_done;
 }
 
-static void __check_db_timeout(struct octeon_device *oct, unsigned long iq_no)
+/* Process instruction queue after timeout.
+ * This routine gets called from a workqueue or when removing the module.
+ */
+static void __check_db_timeout(struct octeon_device *oct, u64 iq_no)
 {
 	struct octeon_instr_queue *iq;
 	u64 next_time;
@@ -508,24 +539,17 @@ static void __check_db_timeout(struct octeon_device *oct, unsigned long iq_no)
 	if (!iq)
 		return;
 
+	/* return immediately, if no work pending */
+	if (!atomic_read(&iq->instr_pending))
+		return;
 	/* If jiffies - last_db_time < db_timeout do nothing  */
 	next_time = iq->last_db_time + iq->db_timeout;
 	if (!time_after(jiffies, (unsigned long)next_time))
 		return;
 	iq->last_db_time = jiffies;
 
-	/* Get the lock and prevent tasklets. This routine gets called from
-	 * the poll thread. Instructions can now be posted in tasklet context
-	 */
-	spin_lock_bh(&iq->lock);
-	if (iq->fill_cnt != 0)
-		ring_doorbell(oct, iq);
-
-	spin_unlock_bh(&iq->lock);
-
 	/* Flush the instruction queue */
-	if (iq->do_auto_flush)
-		octeon_flush_iq(oct, iq, 1);
+	octeon_flush_iq(oct, iq, 1, 0);
 }
 
 /* Called by the Poll thread at regular intervals to check the instruction
@@ -550,7 +574,10 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
 	struct iq_post_status st;
 	struct octeon_instr_queue *iq = oct->instr_queue[iq_no];
 
-	spin_lock_bh(&iq->lock);
+	/* Get the lock and prevent other tasks and tx interrupt handler from
+	 * running.
+	 */
+	spin_lock_bh(&iq->post_lock);
 
 	st = __post_command2(oct, iq, force_db, cmd);
 
@@ -566,10 +593,13 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
 		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, instr_dropped, 1);
 	}
 
-	spin_unlock_bh(&iq->lock);
+	spin_unlock_bh(&iq->post_lock);
 
-	if (iq->do_auto_flush)
-		octeon_flush_iq(oct, iq, 2);
+	/* This is only done here to expedite packets being flushed
+	 * for cases where there are no IQ completion interrupts.
+	 */
+	/*if (iq->do_auto_flush)*/
+	/*	octeon_flush_iq(oct, iq, 2, 0);*/
 
 	return st.status;
 }

drivers/net/ethernet/cavium/liquidio/response_manager.c

@@ -54,6 +54,7 @@ int octeon_setup_response_list(struct octeon_device *oct)
 		spin_lock_init(&oct->response_list[i].lock);
 		atomic_set(&oct->response_list[i].pending_req_count, 0);
 	}
+	spin_lock_init(&oct->cmd_resp_wqlock);
 
 	oct->dma_comp_wq.wq = alloc_workqueue("dma-comp", WQ_MEM_RECLAIM, 0);
 	if (!oct->dma_comp_wq.wq) {
@@ -64,6 +65,7 @@ int octeon_setup_response_list(struct octeon_device *oct)
 	cwq = &oct->dma_comp_wq;
 	INIT_DELAYED_WORK(&cwq->wk.work, oct_poll_req_completion);
 	cwq->wk.ctxptr = oct;
+	oct->cmd_resp_state = OCT_DRV_ONLINE;
 	queue_delayed_work(cwq->wq, &cwq->wk.work, msecs_to_jiffies(100));
 
 	return ret;