Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (867 commits)
  [SKY2]: status polling loop (post merge)
  [NET]: Fix NAPI completion handling in some drivers.
  [TCP]: Limit processing lost_retrans loop to work-to-do cases
  [TCP]: Fix lost_retrans loop vs fastpath problems
  [TCP]: No need to re-count fackets_out/sacked_out at RTO
  [TCP]: Extract tcp_match_queue_to_sack from sacktag code
  [TCP]: Kill almost unused variable pcount from sacktag
  [TCP]: Fix mark_head_lost to ignore R-bit when trying to mark L
  [TCP]: Add bytes_acked (ABC) clearing to FRTO too
  [IPv6]: Update setsockopt(IPV6_MULTICAST_IF) to support RFC 3493, try2
  [NETFILTER]: x_tables: add missing ip6t_modulename aliases
  [NETFILTER]: nf_conntrack_tcp: fix connection reopening
  [QETH]: fix qeth_main.c
  [NETLINK]: fib_frontend build fixes
  [IPv6]: Export userland ND options through netlink (RDNSS support)
  [9P]: build fix with !CONFIG_SYSCTL
  [NET]: Fix dev_put() and dev_hold() comments
  [NET]: make netlink user -> kernel interface synchronious
  [NET]: unify netlink kernel socket recognition
  [NET]: cleanup 3rd argument in netlink_sendskb
  ...

Fix up conflicts manually in Documentation/feature-removal-schedule.txt
and my new least favourite crap, the "mod_devicetable" support in the
files include/linux/mod_devicetable.h and scripts/mod/file2alias.c.

(The latter files seem to be explicitly _designed_ to get conflicts when
different subsystems work with them - that have an absolutely horrid
lack of subsystem separation!)

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

12 files changed, 336 insertions, 310 deletions

diff --git a/drivers/net/cxgb3/adapter.h b/drivers/net/cxgb3/adapter.h
index 20e887de2545..044261703381 100644
--- a/drivers/net/cxgb3/adapter.h
+++ b/drivers/net/cxgb3/adapter.h
@@ -49,11 +49,13 @@
 typedef irqreturn_t(*intr_handler_t) (int, void *);
 
 struct vlan_group;
-
 struct adapter;
+struct sge_qset;
+
 struct port_info {
 	struct adapter *adapter;
 	struct vlan_group *vlan_grp;
+	struct sge_qset *qs;
 	const struct port_type_info *port_type;
 	u8 port_id;
 	u8 rx_csum_offload;
@@ -173,10 +175,12 @@ enum {				/* per port SGE statistics */
 };
 
 struct sge_qset {		/* an SGE queue set */
+	struct adapter *adap;
+	struct napi_struct napi;
 	struct sge_rspq rspq;
 	struct sge_fl fl[SGE_RXQ_PER_SET];
 	struct sge_txq txq[SGE_TXQ_PER_SET];
-	struct net_device *netdev;	/* associated net device */
+	struct net_device *netdev;
 	unsigned long txq_stopped;	/* which Tx queues are stopped */
 	struct timer_list tx_reclaim_timer;	/* reclaims TX buffers */
 	unsigned long port_stats[SGE_PSTAT_MAX];
@@ -221,12 +225,6 @@ struct adapter {
 	struct delayed_work adap_check_task;
 	struct work_struct ext_intr_handler_task;
 
-	/*
-	 * Dummy netdevices are needed when using multiple receive queues with
-	 * NAPI as each netdevice can service only one queue.
-	 */
-	struct net_device *dummy_netdev[SGE_QSETS - 1];
-
 	struct dentry *debugfs_root;
 
 	struct mutex mdio_lock;
@@ -253,12 +251,6 @@ static inline struct port_info *adap2pinfo(struct adapter *adap, int idx)
 	return netdev_priv(adap->port[idx]);
 }
 
-/*
- * We use the spare atalk_ptr to map a net device to its SGE queue set.
- * This is a macro so it can be used as l-value.
- */
-#define dev2qset(netdev) ((netdev)->atalk_ptr)
-
 #define OFFLOAD_DEVMAP_BIT 15
 
 #define tdev2adap(d) container_of(d, struct adapter, tdev)
@@ -284,7 +276,7 @@ int t3_mgmt_tx(struct adapter *adap, struct sk_buff *skb);
 void t3_update_qset_coalesce(struct sge_qset *qs, const struct qset_params *p);
 int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 		      int irq_vec_idx, const struct qset_params *p,
-		      int ntxq, struct net_device *netdev);
+		      int ntxq, struct net_device *dev);
 int t3_get_desc(const struct sge_qset *qs, unsigned int qnum, unsigned int idx,
 		unsigned char *data);
 irqreturn_t t3_sge_intr_msix(int irq, void *cookie);
diff --git a/drivers/net/cxgb3/common.h b/drivers/net/cxgb3/common.h
index 2129210a67c1..99c75d30f67a 100644
--- a/drivers/net/cxgb3/common.h
+++ b/drivers/net/cxgb3/common.h
@@ -97,6 +97,7 @@ enum {
 	MAX_NPORTS = 2,		/* max # of ports */
 	MAX_FRAME_SIZE = 10240,	/* max MAC frame size, including header + FCS */
 	EEPROMSIZE = 8192,	/* Serial EEPROM size */
+	SERNUM_LEN     = 16,    /* Serial # length */
 	RSS_TABLE_SIZE = 64,	/* size of RSS lookup and mapping tables */
 	TCB_SIZE = 128,		/* TCB size */
 	NMTUS = 16,		/* size of MTU table */
@@ -104,7 +105,7 @@ enum {
 	PROTO_SRAM_LINES = 128, /* size of TP sram */
 };
 
-#define MAX_RX_COALESCING_LEN 16224U
+#define MAX_RX_COALESCING_LEN 12288U
 
 enum {
 	PAUSE_RX = 1 << 0,
@@ -126,8 +127,8 @@ enum {				/* adapter interrupt-maintained statistics */
 
 enum {
 	TP_VERSION_MAJOR	= 1,
-	TP_VERSION_MINOR	= 0,
-	TP_VERSION_MICRO	= 44
+	TP_VERSION_MINOR	= 1,
+	TP_VERSION_MICRO	= 0
 };
 
 #define S_TP_VERSION_MAJOR		16
@@ -167,8 +168,8 @@ enum {
 };
 
 struct sg_ent {			/* SGE scatter/gather entry */
-	u32 len[2];
-	u64 addr[2];
+	__be32 len[2];
+	__be64 addr[2];
 };
 
 #ifndef SGE_NUM_GENBITS
@@ -391,6 +392,7 @@ struct vpd_params {
 	unsigned int uclk;
 	unsigned int mdc;
 	unsigned int mem_timing;
+	u8 sn[SERNUM_LEN + 1];
 	u8 eth_base[6];
 	u8 port_type[MAX_NPORTS];
 	unsigned short xauicfg[2];
@@ -436,6 +438,7 @@ enum {					    /* chip revisions */
 	T3_REV_A  = 0,
 	T3_REV_B  = 2,
 	T3_REV_B2 = 3,
+	T3_REV_C  = 4,
 };
 
 struct trace_params {
@@ -507,9 +510,11 @@ struct cmac {
 	unsigned int tx_xcnt;
 	u64 tx_mcnt;
 	unsigned int rx_xcnt;
+	unsigned int rx_ocnt;
 	u64 rx_mcnt;
 	unsigned int toggle_cnt;
 	unsigned int txen;
+	u64 rx_pause;
 	struct mac_stats stats;
 };
 
@@ -687,7 +692,7 @@ int t3_read_flash(struct adapter *adapter, unsigned int addr,
 		  unsigned int nwords, u32 *data, int byte_oriented);
 int t3_load_fw(struct adapter *adapter, const u8 * fw_data, unsigned int size);
 int t3_get_fw_version(struct adapter *adapter, u32 *vers);
-int t3_check_fw_version(struct adapter *adapter);
+int t3_check_fw_version(struct adapter *adapter, int *must_load);
 int t3_init_hw(struct adapter *adapter, u32 fw_params);
 void mac_prep(struct cmac *mac, struct adapter *adapter, int index);
 void early_hw_init(struct adapter *adapter, const struct adapter_info *ai);
diff --git a/drivers/net/cxgb3/cxgb3_ctl_defs.h b/drivers/net/cxgb3/cxgb3_ctl_defs.h
index 2095ddacff78..6c4f32066919 100644
--- a/drivers/net/cxgb3/cxgb3_ctl_defs.h
+++ b/drivers/net/cxgb3/cxgb3_ctl_defs.h
@@ -33,27 +33,29 @@
 #define _CXGB3_OFFLOAD_CTL_DEFS_H
 
 enum {
-	GET_MAX_OUTSTANDING_WR,
-	GET_TX_MAX_CHUNK,
-	GET_TID_RANGE,
-	GET_STID_RANGE,
-	GET_RTBL_RANGE,
-	GET_L2T_CAPACITY,
-	GET_MTUS,
-	GET_WR_LEN,
-	GET_IFF_FROM_MAC,
-	GET_DDP_PARAMS,
-	GET_PORTS,
-
-	ULP_ISCSI_GET_PARAMS,
-	ULP_ISCSI_SET_PARAMS,
-
-	RDMA_GET_PARAMS,
-	RDMA_CQ_OP,
-	RDMA_CQ_SETUP,
-	RDMA_CQ_DISABLE,
-	RDMA_CTRL_QP_SETUP,
-	RDMA_GET_MEM,
+	GET_MAX_OUTSTANDING_WR 	= 0,
+	GET_TX_MAX_CHUNK	= 1,
+	GET_TID_RANGE		= 2,
+	GET_STID_RANGE		= 3,
+	GET_RTBL_RANGE		= 4,
+	GET_L2T_CAPACITY	= 5,
+	GET_MTUS		= 6,
+	GET_WR_LEN		= 7,
+	GET_IFF_FROM_MAC	= 8,
+	GET_DDP_PARAMS		= 9,
+	GET_PORTS		= 10,
+
+	ULP_ISCSI_GET_PARAMS	= 11,
+	ULP_ISCSI_SET_PARAMS	= 12,
+
+	RDMA_GET_PARAMS		= 13,
+	RDMA_CQ_OP		= 14,
+	RDMA_CQ_SETUP		= 15,
+	RDMA_CQ_DISABLE		= 16,
+	RDMA_CTRL_QP_SETUP	= 17,
+	RDMA_GET_MEM		= 18,
+
+	GET_RX_PAGE_INFO	= 50,
 };
 
 /*
@@ -161,4 +163,12 @@ struct rdma_ctrlqp_setup {
 	unsigned long long base_addr;
 	unsigned int size;
 };
+
+/*
+ * Offload TX/RX page information.
+ */
+struct ofld_page_info {
+	unsigned int page_size;  /* Page size, should be a power of 2 */
+	unsigned int num;        /* Number of pages */
+};
 #endif				/* _CXGB3_OFFLOAD_CTL_DEFS_H */
diff --git a/drivers/net/cxgb3/cxgb3_defs.h b/drivers/net/cxgb3/cxgb3_defs.h
index 483a594210a7..45e92164c260 100644
--- a/drivers/net/cxgb3/cxgb3_defs.h
+++ b/drivers/net/cxgb3/cxgb3_defs.h
@@ -79,9 +79,17 @@ static inline struct t3c_tid_entry *lookup_tid(const struct tid_info *t,
 static inline struct t3c_tid_entry *lookup_stid(const struct tid_info *t,
 						unsigned int tid)
 {
+	union listen_entry *e;
+
 	if (tid < t->stid_base || tid >= t->stid_base + t->nstids)
 		return NULL;
-	return &(stid2entry(t, tid)->t3c_tid);
+
+	e = stid2entry(t, tid);
+	if ((void *)e->next >= (void *)t->tid_tab &&
+	    (void *)e->next < (void *)&t->atid_tab[t->natids])
+		return NULL;
+
+	return &e->t3c_tid;
 }
 
 /*
@@ -90,9 +98,17 @@ static inline struct t3c_tid_entry *lookup_stid(const struct tid_info *t,
 static inline struct t3c_tid_entry *lookup_atid(const struct tid_info *t,
 						unsigned int tid)
 {
+	union active_open_entry *e;
+
 	if (tid < t->atid_base || tid >= t->atid_base + t->natids)
 		return NULL;
-	return &(atid2entry(t, tid)->t3c_tid);
+
+	e = atid2entry(t, tid);
+	if ((void *)e->next >= (void *)t->tid_tab &&
+	    (void *)e->next < (void *)&t->atid_tab[t->natids])
+		return NULL;
+
+	return &e->t3c_tid;
 }
 
 int process_rx(struct t3cdev *dev, struct sk_buff **skbs, int n);
diff --git a/drivers/net/cxgb3/cxgb3_main.c b/drivers/net/cxgb3/cxgb3_main.c
index 5ab319cfe5de..61ffc925eae7 100644
--- a/drivers/net/cxgb3/cxgb3_main.c
+++ b/drivers/net/cxgb3/cxgb3_main.c
@@ -339,49 +339,17 @@ static void setup_rss(struct adapter *adap)
 		      V_RRCPLCPUSIZE(6), cpus, rspq_map);
 }
 
-/*
- * If we have multiple receive queues per port serviced by NAPI we need one
- * netdevice per queue as NAPI operates on netdevices.  We already have one
- * netdevice, namely the one associated with the interface, so we use dummy
- * ones for any additional queues.  Note that these netdevices exist purely
- * so that NAPI has something to work with, they do not represent network
- * ports and are not registered.
- */
-static int init_dummy_netdevs(struct adapter *adap)
+static void init_napi(struct adapter *adap)
 {
-	int i, j, dummy_idx = 0;
-	struct net_device *nd;
-
-	for_each_port(adap, i) {
-		struct net_device *dev = adap->port[i];
-		const struct port_info *pi = netdev_priv(dev);
-
-		for (j = 0; j < pi->nqsets - 1; j++) {
-			if (!adap->dummy_netdev[dummy_idx]) {
-				struct port_info *p;
-
-				nd = alloc_netdev(sizeof(*p), "", ether_setup);
-				if (!nd)
-					goto free_all;
+	int i;
 
-				p = netdev_priv(nd);
-				p->adapter = adap;
-				nd->weight = 64;
-				set_bit(__LINK_STATE_START, &nd->state);
-				adap->dummy_netdev[dummy_idx] = nd;
-			}
-			strcpy(adap->dummy_netdev[dummy_idx]->name, dev->name);
-			dummy_idx++;
-		}
-	}
-	return 0;
+	for (i = 0; i < SGE_QSETS; i++) {
+		struct sge_qset *qs = &adap->sge.qs[i];
 
-free_all:
-	while (--dummy_idx >= 0) {
-		free_netdev(adap->dummy_netdev[dummy_idx]);
-		adap->dummy_netdev[dummy_idx] = NULL;
+		if (qs->adap)
+			netif_napi_add(qs->netdev, &qs->napi, qs->napi.poll,
+				       64);
 	}
-	return -ENOMEM;
 }
 
 /*
@@ -392,20 +360,18 @@ free_all:
 static void quiesce_rx(struct adapter *adap)
 {
 	int i;
-	struct net_device *dev;
 
-	for_each_port(adap, i) {
-		dev = adap->port[i];
-		while (test_bit(__LINK_STATE_RX_SCHED, &dev->state))
-			msleep(1);
-	}
+	for (i = 0; i < SGE_QSETS; i++)
+		if (adap->sge.qs[i].adap)
+			napi_disable(&adap->sge.qs[i].napi);
+}
 
-	for (i = 0; i < ARRAY_SIZE(adap->dummy_netdev); i++) {
-		dev = adap->dummy_netdev[i];
-		if (dev)
-			while (test_bit(__LINK_STATE_RX_SCHED, &dev->state))
-				msleep(1);
-	}
+static void enable_all_napi(struct adapter *adap)
+{
+	int i;
+	for (i = 0; i < SGE_QSETS; i++)
+		if (adap->sge.qs[i].adap)
+			napi_enable(&adap->sge.qs[i].napi);
 }
 
 /**
@@ -418,7 +384,7 @@ static void quiesce_rx(struct adapter *adap)
  */
 static int setup_sge_qsets(struct adapter *adap)
 {
-	int i, j, err, irq_idx = 0, qset_idx = 0, dummy_dev_idx = 0;
+	int i, j, err, irq_idx = 0, qset_idx = 0;
 	unsigned int ntxq = SGE_TXQ_PER_SET;
 
 	if (adap->params.rev > 0 && !(adap->flags & USING_MSI))
@@ -426,15 +392,14 @@ static int setup_sge_qsets(struct adapter *adap)
 
 	for_each_port(adap, i) {
 		struct net_device *dev = adap->port[i];
-		const struct port_info *pi = netdev_priv(dev);
+		struct port_info *pi = netdev_priv(dev);
 
+		pi->qs = &adap->sge.qs[pi->first_qset];
 		for (j = 0; j < pi->nqsets; ++j, ++qset_idx) {
 			err = t3_sge_alloc_qset(adap, qset_idx, 1,
 				(adap->flags & USING_MSIX) ? qset_idx + 1 :
 							     irq_idx,
-				&adap->params.sge.qset[qset_idx], ntxq,
-				j == 0 ? dev :
-					 adap-> dummy_netdev[dummy_dev_idx++]);
+				&adap->params.sge.qset[qset_idx], ntxq, dev);
 			if (err) {
 				t3_free_sge_resources(adap);
 				return err;
@@ -768,11 +733,14 @@ static inline char t3rev2char(struct adapter *adapter)
 	case T3_REV_B2:
 		rev = 'b';
 		break;
+	case T3_REV_C:
+		rev = 'c';
+		break;
 	}
 	return rev;
 }
 
-int update_tpsram(struct adapter *adap)
+static int update_tpsram(struct adapter *adap)
 {
 	const struct firmware *tpsram;
 	char buf[64];
@@ -828,15 +796,16 @@ release_tpsram:
  */
 static int cxgb_up(struct adapter *adap)
 {
-	int err = 0;
+	int err;
 	int must_load;
 
 	if (!(adap->flags & FULL_INIT_DONE)) {
-		err = t3_check_fw_version(adap);
-		if (err == -EINVAL)
+		err = t3_check_fw_version(adap, &must_load);
+		if (err == -EINVAL) {
 			err = upgrade_fw(adap);
-		if (err)
-			goto out;
+			if (err && must_load)
+				goto out;
+		}
 
 		err = t3_check_tpsram_version(adap, &must_load);
 		if (err == -EINVAL) {
@@ -845,21 +814,18 @@ static int cxgb_up(struct adapter *adap)
 				goto out;
 		}
 
-		err = init_dummy_netdevs(adap);
-		if (err)
-			goto out;
-
 		err = t3_init_hw(adap, 0);
 		if (err)
 			goto out;
 
 		t3_write_reg(adap, A_ULPRX_TDDP_PSZ, V_HPZ0(PAGE_SHIFT - 12));
-		
+
 		err = setup_sge_qsets(adap);
 		if (err)
 			goto out;
 
 		setup_rss(adap);
+		init_napi(adap);
 		adap->flags |= FULL_INIT_DONE;
 	}
 
@@ -886,6 +852,7 @@ static int cxgb_up(struct adapter *adap)
 				      adap->name, adap)))
 		goto irq_err;
 
+	enable_all_napi(adap);
 	t3_sge_start(adap);
 	t3_intr_enable(adap);
 
@@ -944,7 +911,7 @@ static int offload_open(struct net_device *dev)
 	struct adapter *adapter = pi->adapter;
 	struct t3cdev *tdev = dev2t3cdev(dev);
 	int adap_up = adapter->open_device_map & PORT_MASK;
-	int err = 0;
+	int err;
 
 	if (test_and_set_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map))
 		return 0;
@@ -1012,8 +979,10 @@ static int cxgb_open(struct net_device *dev)
 	int other_ports = adapter->open_device_map & PORT_MASK;
 	int err;
 
-	if (!adapter->open_device_map && (err = cxgb_up(adapter)) < 0)
+	if (!adapter->open_device_map && (err = cxgb_up(adapter)) < 0) {
+		quiesce_rx(adapter);
 		return err;
+	}
 
 	set_bit(pi->port_id, &adapter->open_device_map);
 	if (is_offload(adapter) && !ofld_disable) {
@@ -1162,9 +1131,14 @@ static char stats_strings[][ETH_GSTRING_LEN] = {
 
 };
 
-static int get_stats_count(struct net_device *dev)
+static int get_sset_count(struct net_device *dev, int sset)
 {
-	return ARRAY_SIZE(stats_strings);
+	switch (sset) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(stats_strings);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 #define T3_REGMAP_SIZE (3 * 1024)
@@ -1601,7 +1575,7 @@ static int set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 	struct adapter *adapter = pi->adapter;
 	u32 aligned_offset, aligned_len, *p;
 	u8 *buf;
-	int err = 0;
+	int err;
 
 	if (eeprom->magic != EEPROM_MAGIC)
 		return -EINVAL;
@@ -1665,20 +1639,17 @@ static const struct ethtool_ops cxgb_ethtool_ops = {
 	.set_pauseparam = set_pauseparam,
 	.get_rx_csum = get_rx_csum,
 	.set_rx_csum = set_rx_csum,
-	.get_tx_csum = ethtool_op_get_tx_csum,
 	.set_tx_csum = ethtool_op_set_tx_csum,
-	.get_sg = ethtool_op_get_sg,
 	.set_sg = ethtool_op_set_sg,
 	.get_link = ethtool_op_get_link,
 	.get_strings = get_strings,
 	.phys_id = cxgb3_phys_id,
 	.nway_reset = restart_autoneg,
-	.get_stats_count = get_stats_count,
+	.get_sset_count = get_sset_count,
 	.get_ethtool_stats = get_stats,
 	.get_regs_len = get_regs_len,
 	.get_regs = get_regs,
 	.get_wol = get_wol,
-	.get_tso = ethtool_op_get_tso,
 	.set_tso = ethtool_op_set_tso,
 };
 
@@ -1798,7 +1769,6 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 	}
 	case CHELSIO_SET_QSET_NUM:{
 		struct ch_reg edata;
-		struct port_info *pi = netdev_priv(dev);
 		unsigned int i, first_qset = 0, other_qsets = 0;
 
 		if (!capable(CAP_NET_ADMIN))
@@ -1830,7 +1800,6 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 	}
 	case CHELSIO_GET_QSET_NUM:{
 		struct ch_reg edata;
-		struct port_info *pi = netdev_priv(dev);
 
 		edata.cmd = CHELSIO_GET_QSET_NUM;
 		edata.val = pi->nqsets;
@@ -2332,6 +2301,10 @@ void t3_fatal_err(struct adapter *adapter)
 
 	if (adapter->flags & FULL_INIT_DONE) {
 		t3_sge_stop(adapter);
+		t3_write_reg(adapter, A_XGM_TX_CTRL, 0);
+		t3_write_reg(adapter, A_XGM_RX_CTRL, 0);
+		t3_write_reg(adapter, XGM_REG(A_XGM_TX_CTRL, 1), 0);
+		t3_write_reg(adapter, XGM_REG(A_XGM_RX_CTRL, 1), 0);
 		t3_intr_disable(adapter);
 	}
 	CH_ALERT(adapter, "encountered fatal error, operation suspended\n");
@@ -2391,10 +2364,12 @@ static void __devinit print_port_info(struct adapter *adap,
 		       (adap->flags & USING_MSIX) ? " MSI-X" :
 		       (adap->flags & USING_MSI) ? " MSI" : "");
 		if (adap->name == dev->name && adap->params.vpd.mclk)
-			printk(KERN_INFO "%s: %uMB CM, %uMB PMTX, %uMB PMRX\n",
+			printk(KERN_INFO
+			       "%s: %uMB CM, %uMB PMTX, %uMB PMRX, S/N: %s\n",
 			       adap->name, t3_mc7_size(&adap->cm) >> 20,
 			       t3_mc7_size(&adap->pmtx) >> 20,
-			       t3_mc7_size(&adap->pmrx) >> 20);
+			       t3_mc7_size(&adap->pmrx) >> 20,
+			       adap->params.vpd.sn);
 	}
 }
 
@@ -2490,7 +2465,6 @@ static int __devinit init_one(struct pci_dev *pdev,
 			goto out_free_dev;
 		}
 
-		SET_MODULE_OWNER(netdev);
 		SET_NETDEV_DEV(netdev, &pdev->dev);
 
 		adapter->port[i] = netdev;
@@ -2524,7 +2498,6 @@ static int __devinit init_one(struct pci_dev *pdev,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 		netdev->poll_controller = cxgb_netpoll;
 #endif
-		netdev->weight = 64;
 
 		SET_ETHTOOL_OPS(netdev, &cxgb_ethtool_ops);
 	}
@@ -2625,12 +2598,6 @@ static void __devexit remove_one(struct pci_dev *pdev)
 		t3_free_sge_resources(adapter);
 		cxgb_disable_msi(adapter);
 
-		for (i = 0; i < ARRAY_SIZE(adapter->dummy_netdev); i++)
-			if (adapter->dummy_netdev[i]) {
-				free_netdev(adapter->dummy_netdev[i]);
-				adapter->dummy_netdev[i] = NULL;
-			}
-
 		for_each_port(adapter, i)
 			if (adapter->port[i])
 				free_netdev(adapter->port[i]);
diff --git a/drivers/net/cxgb3/cxgb3_offload.c b/drivers/net/cxgb3/cxgb3_offload.c
index bdff7baeb59d..bd25421bc12a 100644
--- a/drivers/net/cxgb3/cxgb3_offload.c
+++ b/drivers/net/cxgb3/cxgb3_offload.c
@@ -57,7 +57,7 @@ static DEFINE_RWLOCK(adapter_list_lock);
 static LIST_HEAD(adapter_list);
 
 static const unsigned int MAX_ATIDS = 64 * 1024;
-static const unsigned int ATID_BASE = 0x100000;
+static const unsigned int ATID_BASE = 0x10000;
 
 static inline int offload_activated(struct t3cdev *tdev)
 {
@@ -222,32 +222,32 @@ static int cxgb_rdma_ctl(struct adapter *adapter, unsigned int req, void *data)
 	int ret = 0;
 
 	switch (req) {
-	case RDMA_GET_PARAMS:{
-		struct rdma_info *req = data;
+	case RDMA_GET_PARAMS: {
+		struct rdma_info *rdma = data;
 		struct pci_dev *pdev = adapter->pdev;
 
-		req->udbell_physbase = pci_resource_start(pdev, 2);
-		req->udbell_len = pci_resource_len(pdev, 2);
-		req->tpt_base =
+		rdma->udbell_physbase = pci_resource_start(pdev, 2);
+		rdma->udbell_len = pci_resource_len(pdev, 2);
+		rdma->tpt_base =
 			t3_read_reg(adapter, A_ULPTX_TPT_LLIMIT);
-		req->tpt_top = t3_read_reg(adapter, A_ULPTX_TPT_ULIMIT);
-		req->pbl_base =
+		rdma->tpt_top = t3_read_reg(adapter, A_ULPTX_TPT_ULIMIT);
+		rdma->pbl_base =
 			t3_read_reg(adapter, A_ULPTX_PBL_LLIMIT);
-		req->pbl_top = t3_read_reg(adapter, A_ULPTX_PBL_ULIMIT);
-		req->rqt_base = t3_read_reg(adapter, A_ULPRX_RQ_LLIMIT);
-		req->rqt_top = t3_read_reg(adapter, A_ULPRX_RQ_ULIMIT);
-		req->kdb_addr = adapter->regs + A_SG_KDOORBELL;
-		req->pdev = pdev;
+		rdma->pbl_top = t3_read_reg(adapter, A_ULPTX_PBL_ULIMIT);
+		rdma->rqt_base = t3_read_reg(adapter, A_ULPRX_RQ_LLIMIT);
+		rdma->rqt_top = t3_read_reg(adapter, A_ULPRX_RQ_ULIMIT);
+		rdma->kdb_addr = adapter->regs + A_SG_KDOORBELL;
+		rdma->pdev = pdev;
 		break;
 	}
 	case RDMA_CQ_OP:{
 		unsigned long flags;
-		struct rdma_cq_op *req = data;
+		struct rdma_cq_op *rdma = data;
 
 		/* may be called in any context */
 		spin_lock_irqsave(&adapter->sge.reg_lock, flags);
-		ret = t3_sge_cqcntxt_op(adapter, req->id, req->op,
-					req->credits);
+		ret = t3_sge_cqcntxt_op(adapter, rdma->id, rdma->op,
+					rdma->credits);
 		spin_unlock_irqrestore(&adapter->sge.reg_lock, flags);
 		break;
 	}
@@ -274,15 +274,15 @@ static int cxgb_rdma_ctl(struct adapter *adapter, unsigned int req, void *data)
 		break;
 	}
 	case RDMA_CQ_SETUP:{
-		struct rdma_cq_setup *req = data;
+		struct rdma_cq_setup *rdma = data;
 
 		spin_lock_irq(&adapter->sge.reg_lock);
 		ret =
-			t3_sge_init_cqcntxt(adapter, req->id,
-					req->base_addr, req->size,
+			t3_sge_init_cqcntxt(adapter, rdma->id,
+					rdma->base_addr, rdma->size,
 					ASYNC_NOTIF_RSPQ,
-					req->ovfl_mode, req->credits,
-					req->credit_thres);
+					rdma->ovfl_mode, rdma->credits,
+					rdma->credit_thres);
 		spin_unlock_irq(&adapter->sge.reg_lock);
 		break;
 	}
@@ -292,13 +292,13 @@ static int cxgb_rdma_ctl(struct adapter *adapter, unsigned int req, void *data)
 		spin_unlock_irq(&adapter->sge.reg_lock);
 		break;
 	case RDMA_CTRL_QP_SETUP:{
-		struct rdma_ctrlqp_setup *req = data;
+		struct rdma_ctrlqp_setup *rdma = data;
 
 		spin_lock_irq(&adapter->sge.reg_lock);
 		ret = t3_sge_init_ecntxt(adapter, FW_RI_SGEEC_START, 0,
 						SGE_CNTXT_RDMA,
 						ASYNC_NOTIF_RSPQ,
-						req->base_addr, req->size,
+						rdma->base_addr, rdma->size,
 						FW_RI_TID_START, 1, 0);
 		spin_unlock_irq(&adapter->sge.reg_lock);
 		break;
@@ -317,6 +317,8 @@ static int cxgb_offload_ctl(struct t3cdev *tdev, unsigned int req, void *data)
 	struct iff_mac *iffmacp;
 	struct ddp_params *ddpp;
 	struct adap_ports *ports;
+	struct ofld_page_info *rx_page_info;
+	struct tp_params *tp = &adapter->params.tp;
 	int i;
 
 	switch (req) {
@@ -382,6 +384,11 @@ static int cxgb_offload_ctl(struct t3cdev *tdev, unsigned int req, void *data)
 		if (!offload_running(adapter))
 			return -EAGAIN;
 		return cxgb_rdma_ctl(adapter, req, data);
+	case GET_RX_PAGE_INFO:
+		rx_page_info = data;
+		rx_page_info->page_size = tp->rx_pg_size;
+		rx_page_info->num = tp->rx_num_pgs;
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -687,10 +694,19 @@ static int do_cr(struct t3cdev *dev, struct sk_buff *skb)
 {
 	struct cpl_pass_accept_req *req = cplhdr(skb);
 	unsigned int stid = G_PASS_OPEN_TID(ntohl(req->tos_tid));
+	struct tid_info *t = &(T3C_DATA(dev))->tid_maps;
 	struct t3c_tid_entry *t3c_tid;
+	unsigned int tid = GET_TID(req);
 
-	t3c_tid = lookup_stid(&(T3C_DATA(dev))->tid_maps, stid);
-	if (t3c_tid->ctx && t3c_tid->client->handlers &&
+	if (unlikely(tid >= t->ntids)) {
+		printk("%s: passive open TID %u too large\n",
+		       dev->name, tid);
+		t3_fatal_err(tdev2adap(dev));
+		return CPL_RET_BUF_DONE;
+	}
+
+	t3c_tid = lookup_stid(t, stid);
+	if (t3c_tid && t3c_tid->ctx && t3c_tid->client->handlers &&
 	    t3c_tid->client->handlers[CPL_PASS_ACCEPT_REQ]) {
 		return t3c_tid->client->handlers[CPL_PASS_ACCEPT_REQ]
 		    (dev, skb, t3c_tid->ctx);
@@ -772,16 +788,25 @@ static int do_act_establish(struct t3cdev *dev, struct sk_buff *skb)
 {
 	struct cpl_act_establish *req = cplhdr(skb);
 	unsigned int atid = G_PASS_OPEN_TID(ntohl(req->tos_tid));
+	struct tid_info *t = &(T3C_DATA(dev))->tid_maps;
 	struct t3c_tid_entry *t3c_tid;
+	unsigned int tid = GET_TID(req);
 
-	t3c_tid = lookup_atid(&(T3C_DATA(dev))->tid_maps, atid);
+	if (unlikely(tid >= t->ntids)) {
+		printk("%s: active establish TID %u too large\n",
+		       dev->name, tid);
+		t3_fatal_err(tdev2adap(dev));
+		return CPL_RET_BUF_DONE;
+	}
+
+	t3c_tid = lookup_atid(t, atid);
 	if (t3c_tid && t3c_tid->ctx && t3c_tid->client->handlers &&
 	    t3c_tid->client->handlers[CPL_ACT_ESTABLISH]) {
 		return t3c_tid->client->handlers[CPL_ACT_ESTABLISH]
 		    (dev, skb, t3c_tid->ctx);
 	} else {
 		printk(KERN_ERR "%s: received clientless CPL command 0x%x\n",
-		       dev->name, CPL_PASS_ACCEPT_REQ);
+		       dev->name, CPL_ACT_ESTABLISH);
 		return CPL_RET_BUF_DONE | CPL_RET_BAD_MSG;
 	}
 }
diff --git a/drivers/net/cxgb3/regs.h b/drivers/net/cxgb3/regs.h
index aa80313c922e..5e1bc0dec5f1 100644
--- a/drivers/net/cxgb3/regs.h
+++ b/drivers/net/cxgb3/regs.h
@@ -172,6 +172,14 @@
 
 #define A_SG_INT_CAUSE 0x5c
 
+#define S_HIPIODRBDROPERR    11
+#define V_HIPIODRBDROPERR(x) ((x) << S_HIPIODRBDROPERR)
+#define F_HIPIODRBDROPERR    V_HIPIODRBDROPERR(1U)
+
+#define S_LOPIODRBDROPERR    10
+#define V_LOPIODRBDROPERR(x) ((x) << S_LOPIODRBDROPERR)
+#define F_LOPIODRBDROPERR    V_LOPIODRBDROPERR(1U)
+
 #define S_RSPQDISABLED    3
 #define V_RSPQDISABLED(x) ((x) << S_RSPQDISABLED)
 #define F_RSPQDISABLED    V_RSPQDISABLED(1U)
@@ -1318,6 +1326,7 @@
 #define V_D0_WEIGHT(x) ((x) << S_D0_WEIGHT)
 
 #define A_PM1_RX_CFG 0x5c0
+#define A_PM1_RX_MODE 0x5c4
 
 #define A_PM1_RX_INT_ENABLE 0x5d8
 
@@ -1386,6 +1395,7 @@
 #define A_PM1_RX_INT_CAUSE 0x5dc
 
 #define A_PM1_TX_CFG 0x5e0
+#define A_PM1_TX_MODE 0x5e4
 
 #define A_PM1_TX_INT_ENABLE 0x5f8
 
diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c
index 58a5f60521ed..994b5d6404df 100644
--- a/drivers/net/cxgb3/sge.c
+++ b/drivers/net/cxgb3/sge.c
@@ -79,7 +79,7 @@ enum {
 };
 
 struct tx_desc {
-	u64 flit[TX_DESC_FLITS];
+	__be64 flit[TX_DESC_FLITS];
 };
 
 struct rx_desc {
@@ -544,7 +544,7 @@ static void *alloc_ring(struct pci_dev *pdev, size_t nelem, size_t elem_size,
  *	as HW contexts, packet buffers, and descriptor rings.  Traffic to the
  *	queue set must be quiesced prior to calling this.
  */
-void t3_free_qset(struct adapter *adapter, struct sge_qset *q)
+static void t3_free_qset(struct adapter *adapter, struct sge_qset *q)
 {
 	int i;
 	struct pci_dev *pdev = adapter->pdev;
@@ -591,9 +591,6 @@ void t3_free_qset(struct adapter *adapter, struct sge_qset *q)
 				  q->rspq.desc, q->rspq.phys_addr);
 	}
 
-	if (q->netdev)
-		q->netdev->atalk_ptr = NULL;
-
 	memset(q, 0, sizeof(*q));
 }
 
@@ -907,8 +904,8 @@ static void write_wr_hdr_sgl(unsigned int ndesc, struct sk_buff *skb,
 			     const struct sge_txq *q,
 			     const struct sg_ent *sgl,
 			     unsigned int flits, unsigned int sgl_flits,
-			     unsigned int gen, unsigned int wr_hi,
-			     unsigned int wr_lo)
+			     unsigned int gen, __be32 wr_hi,
+			     __be32 wr_lo)
 {
 	struct work_request_hdr *wrp = (struct work_request_hdr *)d;
 	struct tx_sw_desc *sd = &q->sdesc[pidx];
@@ -1074,7 +1071,7 @@ int t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int ndesc, pidx, credits, gen, compl;
 	const struct port_info *pi = netdev_priv(dev);
 	struct adapter *adap = pi->adapter;
-	struct sge_qset *qs = dev2qset(dev);
+	struct sge_qset *qs = pi->qs;
 	struct sge_txq *q = &qs->txq[TXQ_ETH];
 
 	/*
@@ -1182,8 +1179,8 @@ int t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
  *
  *	Writes a packet as immediate data into a Tx descriptor.  The packet
  *	contains a work request at its beginning.  We must write the packet
- *	carefully so the SGE doesn't read accidentally before it's written in
- *	its entirety.
+ *	carefully so the SGE doesn't read it accidentally before it's written
+ *	in its entirety.
  */
 static inline void write_imm(struct tx_desc *d, struct sk_buff *skb,
 			     unsigned int len, unsigned int gen)
@@ -1191,7 +1188,11 @@ static inline void write_imm(struct tx_desc *d, struct sk_buff *skb,
 	struct work_request_hdr *from = (struct work_request_hdr *)skb->data;
 	struct work_request_hdr *to = (struct work_request_hdr *)d;
 
-	memcpy(&to[1], &from[1], len - sizeof(*from));
+	if (likely(!skb->data_len))
+		memcpy(&to[1], &from[1], len - sizeof(*from));
+	else
+		skb_copy_bits(skb, sizeof(*from), &to[1], len - sizeof(*from));
+
 	to->wr_hi = from->wr_hi | htonl(F_WR_SOP | F_WR_EOP |
 					V_WR_BCNTLFLT(len & 7));
 	wmb();
@@ -1261,7 +1262,7 @@ static inline void reclaim_completed_tx_imm(struct sge_txq *q)
 
 static inline int immediate(const struct sk_buff *skb)
 {
-	return skb->len <= WR_LEN && !skb->data_len;
+	return skb->len <= WR_LEN;
 }
 
 /**
@@ -1326,13 +1327,12 @@ static void restart_ctrlq(unsigned long data)
 	struct sk_buff *skb;
 	struct sge_qset *qs = (struct sge_qset *)data;
 	struct sge_txq *q = &qs->txq[TXQ_CTRL];
-	const struct port_info *pi = netdev_priv(qs->netdev);
-	struct adapter *adap = pi->adapter;
 
 	spin_lock(&q->lock);
       again:reclaim_completed_tx_imm(q);
 
-	while (q->in_use < q->size && (skb = __skb_dequeue(&q->sendq)) != NULL) {
+	while (q->in_use < q->size &&
+	       (skb = __skb_dequeue(&q->sendq)) != NULL) {
 
 		write_imm(&q->desc[q->pidx], skb, skb->len, q->gen);
 
@@ -1354,7 +1354,7 @@ static void restart_ctrlq(unsigned long data)
 	}
 
 	spin_unlock(&q->lock);
-	t3_write_reg(adap, A_SG_KDOORBELL,
+	t3_write_reg(qs->adap, A_SG_KDOORBELL,
 		     F_SELEGRCNTX | V_EGRCNTX(q->cntxt_id));
 }
 
@@ -1468,12 +1468,13 @@ static void write_ofld_wr(struct adapter *adap, struct sk_buff *skb,
  */
 static inline unsigned int calc_tx_descs_ofld(const struct sk_buff *skb)
 {
-	unsigned int flits, cnt = skb_shinfo(skb)->nr_frags;
+	unsigned int flits, cnt;
 
-	if (skb->len <= WR_LEN && cnt == 0)
+	if (skb->len <= WR_LEN)
 		return 1;	/* packet fits as immediate data */
 
 	flits = skb_transport_offset(skb) / 8;	/* headers */
+	cnt = skb_shinfo(skb)->nr_frags;
 	if (skb->tail != skb->transport_header)
 		cnt++;
 	return flits_to_desc(flits + sgl_len(cnt));
@@ -1638,8 +1639,7 @@ static inline void offload_enqueue(struct sge_rspq *q, struct sk_buff *skb)
 	else {
 		struct sge_qset *qs = rspq_to_qset(q);
 
-		if (__netif_rx_schedule_prep(qs->netdev))
-			__netif_rx_schedule(qs->netdev);
+		napi_schedule(&qs->napi);
 		q->rx_head = skb;
 	}
 	q->rx_tail = skb;
@@ -1675,34 +1675,30 @@ static inline void deliver_partial_bundle(struct t3cdev *tdev,
  *	receive handler.  Batches need to be of modest size as we do prefetches
  *	on the packets in each.
  */
-static int ofld_poll(struct net_device *dev, int *budget)
+static int ofld_poll(struct napi_struct *napi, int budget)
 {
-	const struct port_info *pi = netdev_priv(dev);
-	struct adapter *adapter = pi->adapter;
-	struct sge_qset *qs = dev2qset(dev);
+	struct sge_qset *qs = container_of(napi, struct sge_qset, napi);
 	struct sge_rspq *q = &qs->rspq;
-	int work_done, limit = min(*budget, dev->quota), avail = limit;
+	struct adapter *adapter = qs->adap;
+	int work_done = 0;
 
-	while (avail) {
+	while (work_done < budget) {
 		struct sk_buff *head, *tail, *skbs[RX_BUNDLE_SIZE];
 		int ngathered;
 
 		spin_lock_irq(&q->lock);
 		head = q->rx_head;
 		if (!head) {
-			work_done = limit - avail;
-			*budget -= work_done;
-			dev->quota -= work_done;
-			__netif_rx_complete(dev);
+			napi_complete(napi);
 			spin_unlock_irq(&q->lock);
-			return 0;
+			return work_done;
 		}
 
 		tail = q->rx_tail;
 		q->rx_head = q->rx_tail = NULL;
 		spin_unlock_irq(&q->lock);
 
-		for (ngathered = 0; avail && head; avail--) {
+		for (ngathered = 0; work_done < budget && head; work_done++) {
 			prefetch(head->data);
 			skbs[ngathered] = head;
 			head = head->next;
@@ -1724,10 +1720,8 @@ static int ofld_poll(struct net_device *dev, int *budget)
 		}
 		deliver_partial_bundle(&adapter->tdev, q, skbs, ngathered);
 	}
-	work_done = limit - avail;
-	*budget -= work_done;
-	dev->quota -= work_done;
-	return 1;
+
+	return work_done;
 }
 
 /**
@@ -2071,50 +2065,47 @@ static inline int is_pure_response(const struct rsp_desc *r)
 
 /**
  *	napi_rx_handler - the NAPI handler for Rx processing
- *	@dev: the net device
+ *	@napi: the napi instance
  *	@budget: how many packets we can process in this round
  *
  *	Handler for new data events when using NAPI.
  */
-static int napi_rx_handler(struct net_device *dev, int *budget)
+static int napi_rx_handler(struct napi_struct *napi, int budget)
 {
-	const struct port_info *pi = netdev_priv(dev);
-	struct adapter *adap = pi->adapter;
-	struct sge_qset *qs = dev2qset(dev);
-	int effective_budget = min(*budget, dev->quota);
+	struct sge_qset *qs = container_of(napi, struct sge_qset, napi);
+	struct adapter *adap = qs->adap;
+	int work_done = process_responses(adap, qs, budget);
 
-	int work_done = process_responses(adap, qs, effective_budget);
-	*budget -= work_done;
-	dev->quota -= work_done;
+	if (likely(work_done < budget)) {
+		napi_complete(napi);
 
-	if (work_done >= effective_budget)
-		return 1;
-
-	netif_rx_complete(dev);
-
-	/*
-	 * Because we don't atomically flush the following write it is
-	 * possible that in very rare cases it can reach the device in a way
-	 * that races with a new response being written plus an error interrupt
-	 * causing the NAPI interrupt handler below to return unhandled status
-	 * to the OS.  To protect against this would require flushing the write
-	 * and doing both the write and the flush with interrupts off.  Way too
-	 * expensive and unjustifiable given the rarity of the race.
-	 *
-	 * The race cannot happen at all with MSI-X.
-	 */
-	t3_write_reg(adap, A_SG_GTS, V_RSPQ(qs->rspq.cntxt_id) |
-		     V_NEWTIMER(qs->rspq.next_holdoff) |
-		     V_NEWINDEX(qs->rspq.cidx));
-	return 0;
+		/*
+		 * Because we don't atomically flush the following
+		 * write it is possible that in very rare cases it can
+		 * reach the device in a way that races with a new
+		 * response being written plus an error interrupt
+		 * causing the NAPI interrupt handler below to return
+		 * unhandled status to the OS.  To protect against
+		 * this would require flushing the write and doing
+		 * both the write and the flush with interrupts off.
+		 * Way too expensive and unjustifiable given the
+		 * rarity of the race.
+		 *
+		 * The race cannot happen at all with MSI-X.
+		 */
+		t3_write_reg(adap, A_SG_GTS, V_RSPQ(qs->rspq.cntxt_id) |
+			     V_NEWTIMER(qs->rspq.next_holdoff) |
+			     V_NEWINDEX(qs->rspq.cidx));
+	}
+	return work_done;
 }
 
 /*
  * Returns true if the device is already scheduled for polling.
  */
-static inline int napi_is_scheduled(struct net_device *dev)
+static inline int napi_is_scheduled(struct napi_struct *napi)
 {
-	return test_bit(__LINK_STATE_RX_SCHED, &dev->state);
+	return test_bit(NAPI_STATE_SCHED, &napi->state);
 }
 
 /**
@@ -2197,8 +2188,7 @@ static inline int handle_responses(struct adapter *adap, struct sge_rspq *q)
 			     V_NEWTIMER(q->holdoff_tmr) | V_NEWINDEX(q->cidx));
 		return 0;
 	}
-	if (likely(__netif_rx_schedule_prep(qs->netdev)))
-		__netif_rx_schedule(qs->netdev);
+	napi_schedule(&qs->napi);
 	return 1;
 }
 
@@ -2209,8 +2199,7 @@ static inline int handle_responses(struct adapter *adap, struct sge_rspq *q)
 irqreturn_t t3_sge_intr_msix(int irq, void *cookie)
 {
 	struct sge_qset *qs = cookie;
-	const struct port_info *pi = netdev_priv(qs->netdev);
-	struct adapter *adap = pi->adapter;
+	struct adapter *adap = qs->adap;
 	struct sge_rspq *q = &qs->rspq;
 
 	spin_lock(&q->lock);
@@ -2226,16 +2215,14 @@ irqreturn_t t3_sge_intr_msix(int irq, void *cookie)
  * The MSI-X interrupt handler for an SGE response queue for the NAPI case
  * (i.e., response queue serviced by NAPI polling).
  */
-irqreturn_t t3_sge_intr_msix_napi(int irq, void *cookie)
+static irqreturn_t t3_sge_intr_msix_napi(int irq, void *cookie)
 {
 	struct sge_qset *qs = cookie;
-	const struct port_info *pi = netdev_priv(qs->netdev);
-	struct adapter *adap = pi->adapter;
 	struct sge_rspq *q = &qs->rspq;
 
 	spin_lock(&q->lock);
 
-	if (handle_responses(adap, q) < 0)
+	if (handle_responses(qs->adap, q) < 0)
 		q->unhandled_irqs++;
 	spin_unlock(&q->lock);
 	return IRQ_HANDLED;
@@ -2278,11 +2265,13 @@ static irqreturn_t t3_intr_msi(int irq, void *cookie)
 	return IRQ_HANDLED;
 }
 
-static int rspq_check_napi(struct net_device *dev, struct sge_rspq *q)
+static int rspq_check_napi(struct sge_qset *qs)
 {
-	if (!napi_is_scheduled(dev) && is_new_response(&q->desc[q->cidx], q)) {
-		if (likely(__netif_rx_schedule_prep(dev)))
-			__netif_rx_schedule(dev);
+	struct sge_rspq *q = &qs->rspq;
+
+	if (!napi_is_scheduled(&qs->napi) &&
+	    is_new_response(&q->desc[q->cidx], q)) {
+		napi_schedule(&qs->napi);
 		return 1;
 	}
 	return 0;
@@ -2295,7 +2284,7 @@ static int rspq_check_napi(struct net_device *dev, struct sge_rspq *q)
  * one SGE response queue per port in this mode and protect all response
  * queues with queue 0's lock.
  */
-irqreturn_t t3_intr_msi_napi(int irq, void *cookie)
+static irqreturn_t t3_intr_msi_napi(int irq, void *cookie)
 {
 	int new_packets;
 	struct adapter *adap = cookie;
@@ -2303,10 +2292,9 @@ irqreturn_t t3_intr_msi_napi(int irq, void *cookie)
 
 	spin_lock(&q->lock);
 
-	new_packets = rspq_check_napi(adap->sge.qs[0].netdev, q);
+	new_packets = rspq_check_napi(&adap->sge.qs[0]);
 	if (adap->params.nports == 2)
-		new_packets += rspq_check_napi(adap->sge.qs[1].netdev,
-					       &adap->sge.qs[1].rspq);
+		new_packets += rspq_check_napi(&adap->sge.qs[1]);
 	if (!new_packets && t3_slow_intr_handler(adap) == 0)
 		q->unhandled_irqs++;
 
@@ -2409,9 +2397,9 @@ static irqreturn_t t3b_intr(int irq, void *cookie)
 static irqreturn_t t3b_intr_napi(int irq, void *cookie)
 {
 	u32 map;
-	struct net_device *dev;
 	struct adapter *adap = cookie;
-	struct sge_rspq *q0 = &adap->sge.qs[0].rspq;
+	struct sge_qset *qs0 = &adap->sge.qs[0];
+	struct sge_rspq *q0 = &qs0->rspq;
 
 	t3_write_reg(adap, A_PL_CLI, 0);
 	map = t3_read_reg(adap, A_SG_DATA_INTR);
@@ -2424,18 +2412,11 @@ static irqreturn_t t3b_intr_napi(int irq, void *cookie)
 	if (unlikely(map & F_ERRINTR))
 		t3_slow_intr_handler(adap);
 
-	if (likely(map & 1)) {
-		dev = adap->sge.qs[0].netdev;
-
-		if (likely(__netif_rx_schedule_prep(dev)))
-			__netif_rx_schedule(dev);
-	}
-	if (map & 2) {
-		dev = adap->sge.qs[1].netdev;
+	if (likely(map & 1))
+		napi_schedule(&qs0->napi);
 
-		if (likely(__netif_rx_schedule_prep(dev)))
-			__netif_rx_schedule(dev);
-	}
+	if (map & 2)
+		napi_schedule(&adap->sge.qs[1].napi);
 
 	spin_unlock(&q0->lock);
 	return IRQ_HANDLED;
@@ -2482,6 +2463,10 @@ void t3_sge_err_intr_handler(struct adapter *adapter)
 			 "(0x%x)\n", (v >> S_RSPQ0DISABLED) & 0xff);
 	}
 
+	if (status & (F_HIPIODRBDROPERR | F_LOPIODRBDROPERR))
+		CH_ALERT(adapter, "SGE dropped %s priority doorbell\n",
+			 status & F_HIPIODRBDROPERR ? "high" : "lo");
+
 	t3_write_reg(adapter, A_SG_INT_CAUSE, status);
 	if (status & (F_RSPQCREDITOVERFOW | F_RSPQDISABLED))
 		t3_fatal_err(adapter);
@@ -2514,8 +2499,7 @@ static void sge_timer_cb(unsigned long data)
 {
 	spinlock_t *lock;
 	struct sge_qset *qs = (struct sge_qset *)data;
-	const struct port_info *pi = netdev_priv(qs->netdev);
-	struct adapter *adap = pi->adapter;
+	struct adapter *adap = qs->adap;
 
 	if (spin_trylock(&qs->txq[TXQ_ETH].lock)) {
 		reclaim_completed_tx(adap, &qs->txq[TXQ_ETH]);
@@ -2526,9 +2510,9 @@ static void sge_timer_cb(unsigned long data)
 		spin_unlock(&qs->txq[TXQ_OFLD].lock);
 	}
 	lock = (adap->flags & USING_MSIX) ? &qs->rspq.lock :
-	    &adap->sge.qs[0].rspq.lock;
+					    &adap->sge.qs[0].rspq.lock;
 	if (spin_trylock_irq(lock)) {
-		if (!napi_is_scheduled(qs->netdev)) {
+		if (!napi_is_scheduled(&qs->napi)) {
 			u32 status = t3_read_reg(adap, A_SG_RSPQ_FL_STATUS);
 
 			if (qs->fl[0].credits < qs->fl[0].size)
@@ -2562,12 +2546,9 @@ static void sge_timer_cb(unsigned long data)
  */
 void t3_update_qset_coalesce(struct sge_qset *qs, const struct qset_params *p)
 {
-	if (!qs->netdev)
-		return;
-
 	qs->rspq.holdoff_tmr = max(p->coalesce_usecs * 10, 1U);/* can't be 0 */
 	qs->rspq.polling = p->polling;
-	qs->netdev->poll = p->polling ? napi_rx_handler : ofld_poll;
+	qs->napi.poll = p->polling ? napi_rx_handler : ofld_poll;
 }
 
 /**
@@ -2587,7 +2568,7 @@ void t3_update_qset_coalesce(struct sge_qset *qs, const struct qset_params *p)
  */
 int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 		      int irq_vec_idx, const struct qset_params *p,
-		      int ntxq, struct net_device *netdev)
+		      int ntxq, struct net_device *dev)
 {
 	int i, ret = -ENOMEM;
 	struct sge_qset *q = &adapter->sge.qs[id];
@@ -2708,16 +2689,10 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 	}
 
 	spin_unlock(&adapter->sge.reg_lock);
-	q->netdev = netdev;
-	t3_update_qset_coalesce(q, p);
 
-	/*
-	 * We use atalk_ptr as a backpointer to a qset.  In case a device is
-	 * associated with multiple queue sets only the first one sets
-	 * atalk_ptr.
-	 */
-	if (netdev->atalk_ptr == NULL)
-		netdev->atalk_ptr = q;
+	q->adap = adapter;
+	q->netdev = dev;
+	t3_update_qset_coalesce(q, p);
 
 	refill_fl(adapter, &q->fl[0], q->fl[0].size, GFP_KERNEL);
 	refill_fl(adapter, &q->fl[1], q->fl[1].size, GFP_KERNEL);
diff --git a/drivers/net/cxgb3/sge_defs.h b/drivers/net/cxgb3/sge_defs.h
index 514869e26a76..29b6c800b238 100644
--- a/drivers/net/cxgb3/sge_defs.h
+++ b/drivers/net/cxgb3/sge_defs.h
@@ -106,6 +106,10 @@
 #define V_CQ_GEN(x) ((x) << S_CQ_GEN)
 #define F_CQ_GEN    V_CQ_GEN(1U)
 
+#define S_CQ_ERR    30
+#define V_CQ_ERR(x) ((x) << S_CQ_ERR)
+#define F_CQ_ERR    V_CQ_ERR(1U)
+
 #define S_CQ_OVERFLOW_MODE    31
 #define V_CQ_OVERFLOW_MODE(x) ((x) << S_CQ_OVERFLOW_MODE)
 #define F_CQ_OVERFLOW_MODE    V_CQ_OVERFLOW_MODE(1U)
diff --git a/drivers/net/cxgb3/t3_hw.c b/drivers/net/cxgb3/t3_hw.c
index b02d15daf5d9..d4ee00d32219 100644
--- a/drivers/net/cxgb3/t3_hw.c
+++ b/drivers/net/cxgb3/t3_hw.c
@@ -119,9 +119,9 @@ void t3_set_reg_field(struct adapter *adapter, unsigned int addr, u32 mask,
  *	Reads registers that are accessed indirectly through an address/data
  *	register pair.
  */
-void t3_read_indirect(struct adapter *adap, unsigned int addr_reg,
-		      unsigned int data_reg, u32 *vals, unsigned int nregs,
-		      unsigned int start_idx)
+static void t3_read_indirect(struct adapter *adap, unsigned int addr_reg,
+			     unsigned int data_reg, u32 *vals,
+			     unsigned int nregs, unsigned int start_idx)
 {
 	while (nregs--) {
 		t3_write_reg(adap, addr_reg, start_idx);
@@ -505,7 +505,7 @@ struct t3_vpd {
 	u8 vpdr_len[2];
 	VPD_ENTRY(pn, 16);	/* part number */
 	VPD_ENTRY(ec, 16);	/* EC level */
-	VPD_ENTRY(sn, 16);	/* serial number */
+	VPD_ENTRY(sn, SERNUM_LEN); /* serial number */
 	VPD_ENTRY(na, 12);	/* MAC address base */
 	VPD_ENTRY(cclk, 6);	/* core clock */
 	VPD_ENTRY(mclk, 6);	/* mem clock */
@@ -648,6 +648,7 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	p->uclk = simple_strtoul(vpd.uclk_data, NULL, 10);
 	p->mdc = simple_strtoul(vpd.mdc_data, NULL, 10);
 	p->mem_timing = simple_strtoul(vpd.mt_data, NULL, 10);
+	memcpy(p->sn, vpd.sn_data, SERNUM_LEN);
 
 	/* Old eeproms didn't have port information */
 	if (adapter->params.rev == 0 && !vpd.port0_data[0]) {
@@ -959,16 +960,18 @@ int t3_get_fw_version(struct adapter *adapter, u32 *vers)
 /**
  *	t3_check_fw_version - check if the FW is compatible with this driver
  *	@adapter: the adapter
- *
+ *	@must_load: set to 1 if loading a new FW image is required
+
  *	Checks if an adapter's FW is compatible with the driver.  Returns 0
  *	if the versions are compatible, a negative error otherwise.
  */
-int t3_check_fw_version(struct adapter *adapter)
+int t3_check_fw_version(struct adapter *adapter, int *must_load)
 {
 	int ret;
 	u32 vers;
 	unsigned int type, major, minor;
 
+	*must_load = 1;
 	ret = t3_get_fw_version(adapter, &vers);
 	if (ret)
 		return ret;
@@ -981,9 +984,17 @@ int t3_check_fw_version(struct adapter *adapter)
 	    minor == FW_VERSION_MINOR)
 		return 0;
 
-	CH_ERR(adapter, "found wrong FW version(%u.%u), "
-	       "driver needs version %u.%u\n", major, minor,
-	       FW_VERSION_MAJOR, FW_VERSION_MINOR);
+	if (major != FW_VERSION_MAJOR)
+		CH_ERR(adapter, "found wrong FW version(%u.%u), "
+		       "driver needs version %u.%u\n", major, minor,
+		       FW_VERSION_MAJOR, FW_VERSION_MINOR);
+	else {
+		*must_load = 0;
+		CH_WARN(adapter, "found wrong FW minor version(%u.%u), "
+		        "driver compiled for version %u.%u\n", major, minor,
+			FW_VERSION_MAJOR, FW_VERSION_MINOR);
+	}
+
 	return -EINVAL;
 }
 
@@ -1347,6 +1358,10 @@ static void pcie_intr_handler(struct adapter *adapter)
 		{0}
 	};
 
+	if (t3_read_reg(adapter, A_PCIE_INT_CAUSE) & F_PEXERR)
+		CH_ALERT(adapter, "PEX error code 0x%x\n",
+			 t3_read_reg(adapter, A_PCIE_PEX_ERR));
+
 	if (t3_handle_intr_status(adapter, A_PCIE_INT_CAUSE, PCIE_INTR_MASK,
 				  pcie_intr_info, adapter->irq_stats))
 		t3_fatal_err(adapter);
@@ -1798,6 +1813,8 @@ void t3_intr_clear(struct adapter *adapter)
 	for (i = 0; i < ARRAY_SIZE(cause_reg_addr); ++i)
 		t3_write_reg(adapter, cause_reg_addr[i], 0xffffffff);
 
+	if (is_pcie(adapter))
+		t3_write_reg(adapter, A_PCIE_PEX_ERR, 0xffffffff);
 	t3_write_reg(adapter, A_PL_INT_CAUSE0, 0xffffffff);
 	t3_read_reg(adapter, A_PL_INT_CAUSE0);	/* flush */
 }
@@ -1853,6 +1870,8 @@ void t3_port_intr_clear(struct adapter *adapter, int idx)
 	phy->ops->intr_clear(phy);
 }
 
+#define SG_CONTEXT_CMD_ATTEMPTS 100
+
 /**
  * 	t3_sge_write_context - write an SGE context
  * 	@adapter: the adapter
@@ -1872,7 +1891,7 @@ static int t3_sge_write_context(struct adapter *adapter, unsigned int id,
 	t3_write_reg(adapter, A_SG_CONTEXT_CMD,
 		     V_CONTEXT_CMD_OPCODE(1) | type | V_CONTEXT(id));
 	return t3_wait_op_done(adapter, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY,
-			       0, 5, 1);
+			       0, SG_CONTEXT_CMD_ATTEMPTS, 1);
 }
 
 /**
@@ -2029,7 +2048,8 @@ int t3_sge_init_cqcntxt(struct adapter *adapter, unsigned int id, u64 base_addr,
 	base_addr >>= 32;
 	t3_write_reg(adapter, A_SG_CONTEXT_DATA2,
 		     V_CQ_BASE_HI((u32) base_addr) | V_CQ_RSPQ(rspq) |
-		     V_CQ_GEN(1) | V_CQ_OVERFLOW_MODE(ovfl_mode));
+		     V_CQ_GEN(1) | V_CQ_OVERFLOW_MODE(ovfl_mode) |
+		     V_CQ_ERR(ovfl_mode));
 	t3_write_reg(adapter, A_SG_CONTEXT_DATA3, V_CQ_CREDITS(credits) |
 		     V_CQ_CREDIT_THRES(credit_thres));
 	return t3_sge_write_context(adapter, id, F_CQ);
@@ -2057,7 +2077,7 @@ int t3_sge_enable_ecntxt(struct adapter *adapter, unsigned int id, int enable)
 	t3_write_reg(adapter, A_SG_CONTEXT_CMD,
 		     V_CONTEXT_CMD_OPCODE(1) | F_EGRESS | V_CONTEXT(id));
 	return t3_wait_op_done(adapter, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY,
-			       0, 5, 1);
+			       0, SG_CONTEXT_CMD_ATTEMPTS, 1);
 }
 
 /**
@@ -2081,7 +2101,7 @@ int t3_sge_disable_fl(struct adapter *adapter, unsigned int id)
 	t3_write_reg(adapter, A_SG_CONTEXT_CMD,
 		     V_CONTEXT_CMD_OPCODE(1) | F_FREELIST | V_CONTEXT(id));
 	return t3_wait_op_done(adapter, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY,
-			       0, 5, 1);
+			       0, SG_CONTEXT_CMD_ATTEMPTS, 1);
 }
 
 /**
@@ -2105,7 +2125,7 @@ int t3_sge_disable_rspcntxt(struct adapter *adapter, unsigned int id)
 	t3_write_reg(adapter, A_SG_CONTEXT_CMD,
 		     V_CONTEXT_CMD_OPCODE(1) | F_RESPONSEQ | V_CONTEXT(id));
 	return t3_wait_op_done(adapter, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY,
-			       0, 5, 1);
+			       0, SG_CONTEXT_CMD_ATTEMPTS, 1);
 }
 
 /**
@@ -2129,7 +2149,7 @@ int t3_sge_disable_cqcntxt(struct adapter *adapter, unsigned int id)
 	t3_write_reg(adapter, A_SG_CONTEXT_CMD,
 		     V_CONTEXT_CMD_OPCODE(1) | F_CQ | V_CONTEXT(id));
 	return t3_wait_op_done(adapter, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY,
-			       0, 5, 1);
+			       0, SG_CONTEXT_CMD_ATTEMPTS, 1);
 }
 
 /**
@@ -2154,7 +2174,7 @@ int t3_sge_cqcntxt_op(struct adapter *adapter, unsigned int id, unsigned int op,
 	t3_write_reg(adapter, A_SG_CONTEXT_CMD, V_CONTEXT_CMD_OPCODE(op) |
 		     V_CONTEXT(id) | F_CQ);
 	if (t3_wait_op_done_val(adapter, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY,
-				0, 5, 1, &val))
+				0, SG_CONTEXT_CMD_ATTEMPTS, 1, &val))
 		return -EIO;
 
 	if (op >= 2 && op < 7) {
@@ -2164,7 +2184,8 @@ int t3_sge_cqcntxt_op(struct adapter *adapter, unsigned int id, unsigned int op,
 		t3_write_reg(adapter, A_SG_CONTEXT_CMD,
 			     V_CONTEXT_CMD_OPCODE(0) | F_CQ | V_CONTEXT(id));
 		if (t3_wait_op_done(adapter, A_SG_CONTEXT_CMD,
-				    F_CONTEXT_CMD_BUSY, 0, 5, 1))
+				    F_CONTEXT_CMD_BUSY, 0,
+				    SG_CONTEXT_CMD_ATTEMPTS, 1))
 			return -EIO;
 		return G_CQ_INDEX(t3_read_reg(adapter, A_SG_CONTEXT_DATA0));
 	}
@@ -2190,7 +2211,7 @@ static int t3_sge_read_context(unsigned int type, struct adapter *adapter,
 	t3_write_reg(adapter, A_SG_CONTEXT_CMD,
 		     V_CONTEXT_CMD_OPCODE(0) | type | V_CONTEXT(id));
 	if (t3_wait_op_done(adapter, A_SG_CONTEXT_CMD, F_CONTEXT_CMD_BUSY, 0,
-			    5, 1))
+			    SG_CONTEXT_CMD_ATTEMPTS, 1))
 		return -EIO;
 	data[0] = t3_read_reg(adapter, A_SG_CONTEXT_DATA0);
 	data[1] = t3_read_reg(adapter, A_SG_CONTEXT_DATA1);
@@ -3222,6 +3243,8 @@ int t3_init_hw(struct adapter *adapter, u32 fw_params)
 		t3_set_reg_field(adapter, A_PCIX_CFG, 0, F_CLIDECEN);
 
 	t3_write_reg(adapter, A_PM1_RX_CFG, 0xffffffff);
+	t3_write_reg(adapter, A_PM1_RX_MODE, 0);
+	t3_write_reg(adapter, A_PM1_TX_MODE, 0);
 	init_hw_for_avail_ports(adapter, adapter->params.nports);
 	t3_sge_init(adapter, &adapter->params.sge);
 
@@ -3384,7 +3407,7 @@ void early_hw_init(struct adapter *adapter, const struct adapter_info *ai)
  * Older PCIe cards lose their config space during reset, PCI-X
  * ones don't.
  */
-int t3_reset_adapter(struct adapter *adapter)
+static int t3_reset_adapter(struct adapter *adapter)
 {
 	int i, save_and_restore_pcie = 
 	    adapter->params.rev < T3_REV_B2 && is_pcie(adapter);
diff --git a/drivers/net/cxgb3/version.h b/drivers/net/cxgb3/version.h
index eb508bf8022a..ef1c6339c806 100644
--- a/drivers/net/cxgb3/version.h
+++ b/drivers/net/cxgb3/version.h
@@ -39,6 +39,6 @@
 
 /* Firmware version */
 #define FW_VERSION_MAJOR 4
-#define FW_VERSION_MINOR 3
+#define FW_VERSION_MINOR 6
 #define FW_VERSION_MICRO 0
 #endif				/* __CHELSIO_VERSION_H */
diff --git a/drivers/net/cxgb3/xgmac.c b/drivers/net/cxgb3/xgmac.c
index c302b1a30cba..eeb766aeced9 100644
--- a/drivers/net/cxgb3/xgmac.c
+++ b/drivers/net/cxgb3/xgmac.c
@@ -142,7 +142,7 @@ int t3_mac_reset(struct cmac *mac)
 	return 0;
 }
 
-int t3b2_mac_reset(struct cmac *mac)
+static int t3b2_mac_reset(struct cmac *mac)
 {
 	struct adapter *adap = mac->adapter;
 	unsigned int oft = mac->offset;
@@ -437,12 +437,13 @@ int t3_mac_enable(struct cmac *mac, int which)
 	struct mac_stats *s = &mac->stats;
 	
 	if (which & MAC_DIRECTION_TX) {
-		t3_write_reg(adap, A_XGM_TX_CTRL + oft, F_TXEN);
 		t3_write_reg(adap, A_TP_PIO_ADDR, A_TP_TX_DROP_CFG_CH0 + idx);
 		t3_write_reg(adap, A_TP_PIO_DATA, 0xc0ede401);
 		t3_write_reg(adap, A_TP_PIO_ADDR, A_TP_TX_DROP_MODE);
 		t3_set_reg_field(adap, A_TP_PIO_DATA, 1 << idx, 1 << idx);
 
+		t3_write_reg(adap, A_XGM_TX_CTRL + oft, F_TXEN);
+
 		t3_write_reg(adap, A_TP_PIO_ADDR, A_TP_TX_DROP_CNT_CH0 + idx);
 		mac->tx_mcnt = s->tx_frames;
 		mac->tx_tcnt = (G_TXDROPCNTCH0RCVD(t3_read_reg(adap,
@@ -451,9 +452,11 @@ int t3_mac_enable(struct cmac *mac, int which)
 						A_XGM_TX_SPI4_SOP_EOP_CNT +
 						oft)));
 		mac->rx_mcnt = s->rx_frames;
+		mac->rx_pause = s->rx_pause;
 		mac->rx_xcnt = (G_TXSPI4SOPCNT(t3_read_reg(adap,
 						A_XGM_RX_SPI4_SOP_EOP_CNT +
 						oft)));
+		mac->rx_ocnt = s->rx_fifo_ovfl;
 		mac->txen = F_TXEN;
 		mac->toggle_cnt = 0;
 	}
@@ -464,24 +467,19 @@ int t3_mac_enable(struct cmac *mac, int which)
 
 int t3_mac_disable(struct cmac *mac, int which)
 {
-	int idx = macidx(mac);
 	struct adapter *adap = mac->adapter;
-	int val;
 
 	if (which & MAC_DIRECTION_TX) {
 		t3_write_reg(adap, A_XGM_TX_CTRL + mac->offset, 0);
-		t3_write_reg(adap, A_TP_PIO_ADDR, A_TP_TX_DROP_CFG_CH0 + idx);
-		t3_write_reg(adap, A_TP_PIO_DATA, 0xc000001f);
-		t3_write_reg(adap, A_TP_PIO_ADDR, A_TP_TX_DROP_MODE);
-		t3_set_reg_field(adap, A_TP_PIO_DATA, 1 << idx, 1 << idx);
 		mac->txen = 0;
 	}
 	if (which & MAC_DIRECTION_RX) {
+		int val = F_MAC_RESET_;
+
 		t3_set_reg_field(mac->adapter, A_XGM_RESET_CTRL + mac->offset,
 				 F_PCS_RESET_, 0);
 		msleep(100);
 		t3_write_reg(adap, A_XGM_RX_CTRL + mac->offset, 0);
-		val = F_MAC_RESET_;
 		if (is_10G(adap))
 			val |= F_PCS_RESET_;
 		else if (uses_xaui(adap))
@@ -507,7 +505,7 @@ int t3b2_mac_watchdog_task(struct cmac *mac)
 	tx_xcnt = 1;		/* By default tx_xcnt is making progress */
 	tx_tcnt = mac->tx_tcnt;	/* If tx_mcnt is progressing ignore tx_tcnt */
 	rx_xcnt = 1;		/* By default rx_xcnt is making progress */
-	if (tx_mcnt == mac->tx_mcnt) {
+	if (tx_mcnt == mac->tx_mcnt && mac->rx_pause == s->rx_pause) {
 		tx_xcnt = (G_TXSPI4SOPCNT(t3_read_reg(adap,
 						A_XGM_TX_SPI4_SOP_EOP_CNT +
 					       	mac->offset)));
@@ -524,10 +522,7 @@ int t3b2_mac_watchdog_task(struct cmac *mac)
 		goto rxcheck;
 	}
 
-	if (((tx_tcnt != mac->tx_tcnt) &&
-	     (tx_xcnt == 0) && (mac->tx_xcnt == 0)) ||
-	    ((mac->tx_mcnt == tx_mcnt) &&
-	     (tx_xcnt != 0) && (mac->tx_xcnt != 0))) {
+	if ((tx_tcnt != mac->tx_tcnt) && (mac->tx_xcnt == 0))  {
 		if (mac->toggle_cnt > 4) {
 			status = 2;
 			goto out;
@@ -541,11 +536,14 @@ int t3b2_mac_watchdog_task(struct cmac *mac)
 	}
 
 rxcheck:
-	if (rx_mcnt != mac->rx_mcnt)
+	if (rx_mcnt != mac->rx_mcnt) {
 		rx_xcnt = (G_TXSPI4SOPCNT(t3_read_reg(adap,
 						A_XGM_RX_SPI4_SOP_EOP_CNT +
-						mac->offset)));
-	else
+						mac->offset))) +
+						(s->rx_fifo_ovfl -
+						 mac->rx_ocnt);
+		mac->rx_ocnt = s->rx_fifo_ovfl;
+	} else
 		goto out;
 
 	if (mac->rx_mcnt != s->rx_frames && rx_xcnt == 0 &&
@@ -560,6 +558,7 @@ out:
 	mac->tx_mcnt = s->tx_frames;
 	mac->rx_xcnt = rx_xcnt;
 	mac->rx_mcnt = s->rx_frames;
+	mac->rx_pause = s->rx_pause;
 	if (status == 1) {
 		t3_write_reg(adap, A_XGM_TX_CTRL + mac->offset, 0);
 		t3_read_reg(adap, A_XGM_TX_CTRL + mac->offset);  /* flush */