Update the i.MX31 Kernel to 2.6.232.6.23-mx31ads-2008022618072.6.23-mx31-200802261807

This is the result of a brute-force attempt to update the kernel to 2.6.23.
Now that we have a git tree, our effort will be a little nicer in the future.

Signed-off-by: Justin Waters <justin.waters@timesys.com>

10 files changed, 606 insertions, 324 deletions

diff --git a/drivers/net/cxgb3/adapter.h b/drivers/net/cxgb3/adapter.h
index 80c3d8f268a7..20e887de2545 100644
--- a/drivers/net/cxgb3/adapter.h
+++ b/drivers/net/cxgb3/adapter.h
@@ -50,7 +50,9 @@ typedef irqreturn_t(*intr_handler_t) (int, void *);
 
 struct vlan_group;
 
+struct adapter;
 struct port_info {
+	struct adapter *adapter;
 	struct vlan_group *vlan_grp;
 	const struct port_type_info *port_type;
 	u8 port_id;
@@ -71,27 +73,29 @@ enum {				/* adapter flags */
 	QUEUES_BOUND = (1 << 3),
 };
 
+struct fl_pg_chunk {
+	struct page *page;
+	void *va;
+	unsigned int offset;
+};
+
 struct rx_desc;
 struct rx_sw_desc;
 
-struct sge_fl_page {
-	struct skb_frag_struct frag;
-	unsigned char *va;
-};
-
-struct sge_fl {			/* SGE per free-buffer list state */
-	unsigned int buf_size;	/* size of each Rx buffer */
-	unsigned int credits;	/* # of available Rx buffers */
-	unsigned int size;	/* capacity of free list */
-	unsigned int cidx;	/* consumer index */
-	unsigned int pidx;	/* producer index */
-	unsigned int gen;	/* free list generation */
-	unsigned int cntxt_id;	/* SGE context id for the free list */
-	struct sge_fl_page page;
-	struct rx_desc *desc;	/* address of HW Rx descriptor ring */
-	struct rx_sw_desc *sdesc;	/* address of SW Rx descriptor ring */
-	dma_addr_t phys_addr;	/* physical address of HW ring start */
-	unsigned long empty;	/* # of times queue ran out of buffers */
+struct sge_fl {                     /* SGE per free-buffer list state */
+	unsigned int buf_size;      /* size of each Rx buffer */
+	unsigned int credits;       /* # of available Rx buffers */
+	unsigned int size;          /* capacity of free list */
+	unsigned int cidx;          /* consumer index */
+	unsigned int pidx;          /* producer index */
+	unsigned int gen;           /* free list generation */
+	struct fl_pg_chunk pg_chunk;/* page chunk cache */
+	unsigned int use_pages;     /* whether FL uses pages or sk_buffs */
+	struct rx_desc *desc;       /* address of HW Rx descriptor ring */
+	struct rx_sw_desc *sdesc;   /* address of SW Rx descriptor ring */
+	dma_addr_t   phys_addr;     /* physical address of HW ring start */
+	unsigned int cntxt_id;      /* SGE context id for the free list */
+	unsigned long empty;        /* # of times queue ran out of buffers */
 	unsigned long alloc_failed; /* # of times buffer allocation failed */
 };
 
diff --git a/drivers/net/cxgb3/common.h b/drivers/net/cxgb3/common.h
index 8d1379633698..2129210a67c1 100644
--- a/drivers/net/cxgb3/common.h
+++ b/drivers/net/cxgb3/common.h
@@ -101,6 +101,7 @@ enum {
 	TCB_SIZE = 128,		/* TCB size */
 	NMTUS = 16,		/* size of MTU table */
 	NCCTRL_WIN = 32,	/* # of congestion control windows */
+	PROTO_SRAM_LINES = 128, /* size of TP sram */
 };
 
 #define MAX_RX_COALESCING_LEN 16224U
@@ -124,6 +125,30 @@ enum {				/* adapter interrupt-maintained statistics */
 };
 
 enum {
+	TP_VERSION_MAJOR	= 1,
+	TP_VERSION_MINOR	= 0,
+	TP_VERSION_MICRO	= 44
+};
+
+#define S_TP_VERSION_MAJOR		16
+#define M_TP_VERSION_MAJOR		0xFF
+#define V_TP_VERSION_MAJOR(x)		((x) << S_TP_VERSION_MAJOR)
+#define G_TP_VERSION_MAJOR(x)		\
+	    (((x) >> S_TP_VERSION_MAJOR) & M_TP_VERSION_MAJOR)
+
+#define S_TP_VERSION_MINOR		8
+#define M_TP_VERSION_MINOR		0xFF
+#define V_TP_VERSION_MINOR(x)		((x) << S_TP_VERSION_MINOR)
+#define G_TP_VERSION_MINOR(x)		\
+	    (((x) >> S_TP_VERSION_MINOR) & M_TP_VERSION_MINOR)
+
+#define S_TP_VERSION_MICRO		0
+#define M_TP_VERSION_MICRO		0xFF
+#define V_TP_VERSION_MICRO(x)		((x) << S_TP_VERSION_MICRO)
+#define G_TP_VERSION_MICRO(x)		\
+	    (((x) >> S_TP_VERSION_MICRO) & M_TP_VERSION_MICRO)
+
+enum {
 	SGE_QSETS = 8,		/* # of SGE Tx/Rx/RspQ sets */
 	SGE_RXQ_PER_SET = 2,	/* # of Rx queues per set */
 	SGE_TXQ_PER_SET = 3	/* # of Tx queues per set */
@@ -654,6 +679,10 @@ const struct adapter_info *t3_get_adapter_info(unsigned int board_id);
 int t3_seeprom_read(struct adapter *adapter, u32 addr, u32 *data);
 int t3_seeprom_write(struct adapter *adapter, u32 addr, u32 data);
 int t3_seeprom_wp(struct adapter *adapter, int enable);
+int t3_get_tp_version(struct adapter *adapter, u32 *vers);
+int t3_check_tpsram_version(struct adapter *adapter, int *must_load);
+int t3_check_tpsram(struct adapter *adapter, u8 *tp_ram, unsigned int size);
+int t3_set_proto_sram(struct adapter *adap, u8 *data);
 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);
diff --git a/drivers/net/cxgb3/cxgb3_main.c b/drivers/net/cxgb3/cxgb3_main.c
index d8a1f5452c51..5ab319cfe5de 100644
--- a/drivers/net/cxgb3/cxgb3_main.c
+++ b/drivers/net/cxgb3/cxgb3_main.c
@@ -43,6 +43,7 @@
 #include <linux/proc_fs.h>
 #include <linux/rtnetlink.h>
 #include <linux/firmware.h>
+#include <linux/log2.h>
 #include <asm/uaccess.h>
 
 #include "common.h"
@@ -357,11 +358,14 @@ static int init_dummy_netdevs(struct adapter *adap)
 
 		for (j = 0; j < pi->nqsets - 1; j++) {
 			if (!adap->dummy_netdev[dummy_idx]) {
-				nd = alloc_netdev(0, "", ether_setup);
+				struct port_info *p;
+
+				nd = alloc_netdev(sizeof(*p), "", ether_setup);
 				if (!nd)
 					goto free_all;
 
-				nd->priv = adap;
+				p = netdev_priv(nd);
+				p->adapter = adap;
 				nd->weight = 64;
 				set_bit(__LINK_STATE_START, &nd->state);
 				adap->dummy_netdev[dummy_idx] = nd;
@@ -481,7 +485,8 @@ static ssize_t attr_store(struct device *d, struct device_attribute *attr,
 #define CXGB3_SHOW(name, val_expr) \
 static ssize_t format_##name(struct net_device *dev, char *buf) \
 { \
-	struct adapter *adap = dev->priv; \
+	struct port_info *pi = netdev_priv(dev); \
+	struct adapter *adap = pi->adapter; \
 	return sprintf(buf, "%u\n", val_expr); \
 } \
 static ssize_t show_##name(struct device *d, struct device_attribute *attr, \
@@ -492,7 +497,8 @@ static ssize_t show_##name(struct device *d, struct device_attribute *attr, \
 
 static ssize_t set_nfilters(struct net_device *dev, unsigned int val)
 {
-	struct adapter *adap = dev->priv;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
 	int min_tids = is_offload(adap) ? MC5_MIN_TIDS : 0;
 
 	if (adap->flags & FULL_INIT_DONE)
@@ -514,7 +520,8 @@ static ssize_t store_nfilters(struct device *d, struct device_attribute *attr,
 
 static ssize_t set_nservers(struct net_device *dev, unsigned int val)
 {
-	struct adapter *adap = dev->priv;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
 
 	if (adap->flags & FULL_INIT_DONE)
 		return -EBUSY;
@@ -555,9 +562,10 @@ static struct attribute_group cxgb3_attr_group = {.attrs = cxgb3_attrs };
 static ssize_t tm_attr_show(struct device *d, struct device_attribute *attr,
 			    char *buf, int sched)
 {
-	ssize_t len;
+	struct port_info *pi = netdev_priv(to_net_dev(d));
+	struct adapter *adap = pi->adapter;
 	unsigned int v, addr, bpt, cpt;
-	struct adapter *adap = to_net_dev(d)->priv;
+	ssize_t len;
 
 	addr = A_TP_TX_MOD_Q1_Q0_RATE_LIMIT - sched / 2;
 	rtnl_lock();
@@ -580,10 +588,11 @@ static ssize_t tm_attr_show(struct device *d, struct device_attribute *attr,
 static ssize_t tm_attr_store(struct device *d, struct device_attribute *attr,
 			     const char *buf, size_t len, int sched)
 {
+	struct port_info *pi = netdev_priv(to_net_dev(d));
+	struct adapter *adap = pi->adapter;
+	unsigned int val;
 	char *endp;
 	ssize_t ret;
-	unsigned int val;
-	struct adapter *adap = to_net_dev(d)->priv;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -720,6 +729,7 @@ static void bind_qsets(struct adapter *adap)
 }
 
 #define FW_FNAME "t3fw-%d.%d.%d.bin"
+#define TPSRAM_NAME "t3%c_protocol_sram-%d.%d.%d.bin"
 
 static int upgrade_fw(struct adapter *adap)
 {
@@ -738,6 +748,71 @@ static int upgrade_fw(struct adapter *adap)
 	}
 	ret = t3_load_fw(adap, fw->data, fw->size);
 	release_firmware(fw);
+
+	if (ret == 0)
+		dev_info(dev, "successful upgrade to firmware %d.%d.%d\n",
+			 FW_VERSION_MAJOR, FW_VERSION_MINOR, FW_VERSION_MICRO);
+	else
+		dev_err(dev, "failed to upgrade to firmware %d.%d.%d\n",
+			FW_VERSION_MAJOR, FW_VERSION_MINOR, FW_VERSION_MICRO);
+	
+	return ret;
+}
+
+static inline char t3rev2char(struct adapter *adapter)
+{
+	char rev = 0;
+
+	switch(adapter->params.rev) {
+	case T3_REV_B:
+	case T3_REV_B2:
+		rev = 'b';
+		break;
+	}
+	return rev;
+}
+
+int update_tpsram(struct adapter *adap)
+{
+	const struct firmware *tpsram;
+	char buf[64];
+	struct device *dev = &adap->pdev->dev;
+	int ret;
+	char rev;
+	
+	rev = t3rev2char(adap);
+	if (!rev)
+		return 0;
+
+	snprintf(buf, sizeof(buf), TPSRAM_NAME, rev,
+		 TP_VERSION_MAJOR, TP_VERSION_MINOR, TP_VERSION_MICRO);
+
+	ret = request_firmware(&tpsram, buf, dev);
+	if (ret < 0) {
+		dev_err(dev, "could not load TP SRAM: unable to load %s\n",
+			buf);
+		return ret;
+	}
+	
+	ret = t3_check_tpsram(adap, tpsram->data, tpsram->size);
+	if (ret)
+		goto release_tpsram;	
+
+	ret = t3_set_proto_sram(adap, tpsram->data);
+	if (ret == 0)
+		dev_info(dev,
+			 "successful update of protocol engine "
+			 "to %d.%d.%d\n",
+			 TP_VERSION_MAJOR, TP_VERSION_MINOR, TP_VERSION_MICRO);
+	else
+		dev_err(dev, "failed to update of protocol engine %d.%d.%d\n",
+			TP_VERSION_MAJOR, TP_VERSION_MINOR, TP_VERSION_MICRO);
+	if (ret)
+		dev_err(dev, "loading protocol SRAM failed\n");
+
+release_tpsram:
+	release_firmware(tpsram);
+	
 	return ret;
 }
 
@@ -754,6 +829,7 @@ static int upgrade_fw(struct adapter *adap)
 static int cxgb_up(struct adapter *adap)
 {
 	int err = 0;
+	int must_load;
 
 	if (!(adap->flags & FULL_INIT_DONE)) {
 		err = t3_check_fw_version(adap);
@@ -762,6 +838,13 @@ static int cxgb_up(struct adapter *adap)
 		if (err)
 			goto out;
 
+		err = t3_check_tpsram_version(adap, &must_load);
+		if (err == -EINVAL) {
+			err = update_tpsram(adap);
+			if (err && must_load)
+				goto out;
+		}
+
 		err = init_dummy_netdevs(adap);
 		if (err)
 			goto out;
@@ -857,8 +940,9 @@ static void schedule_chk_task(struct adapter *adap)
 
 static int offload_open(struct net_device *dev)
 {
-	struct adapter *adapter = dev->priv;
-	struct t3cdev *tdev = T3CDEV(dev);
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
+	struct t3cdev *tdev = dev2t3cdev(dev);
 	int adap_up = adapter->open_device_map & PORT_MASK;
 	int err = 0;
 
@@ -923,10 +1007,10 @@ static int offload_close(struct t3cdev *tdev)
 
 static int cxgb_open(struct net_device *dev)
 {
-	int err;
-	struct adapter *adapter = dev->priv;
 	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	int other_ports = adapter->open_device_map & PORT_MASK;
+	int err;
 
 	if (!adapter->open_device_map && (err = cxgb_up(adapter)) < 0)
 		return err;
@@ -950,17 +1034,17 @@ static int cxgb_open(struct net_device *dev)
 
 static int cxgb_close(struct net_device *dev)
 {
-	struct adapter *adapter = dev->priv;
-	struct port_info *p = netdev_priv(dev);
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 
-	t3_port_intr_disable(adapter, p->port_id);
+	t3_port_intr_disable(adapter, pi->port_id);
 	netif_stop_queue(dev);
-	p->phy.ops->power_down(&p->phy, 1);
+	pi->phy.ops->power_down(&pi->phy, 1);
 	netif_carrier_off(dev);
-	t3_mac_disable(&p->mac, MAC_DIRECTION_TX | MAC_DIRECTION_RX);
+	t3_mac_disable(&pi->mac, MAC_DIRECTION_TX | MAC_DIRECTION_RX);
 
 	spin_lock(&adapter->work_lock);	/* sync with update task */
-	clear_bit(p->port_id, &adapter->open_device_map);
+	clear_bit(pi->port_id, &adapter->open_device_map);
 	spin_unlock(&adapter->work_lock);
 
 	if (!(adapter->open_device_map & PORT_MASK))
@@ -975,13 +1059,13 @@ static int cxgb_close(struct net_device *dev)
 
 static struct net_device_stats *cxgb_get_stats(struct net_device *dev)
 {
-	struct adapter *adapter = dev->priv;
-	struct port_info *p = netdev_priv(dev);
-	struct net_device_stats *ns = &p->netstats;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
+	struct net_device_stats *ns = &pi->netstats;
 	const struct mac_stats *pstats;
 
 	spin_lock(&adapter->stats_lock);
-	pstats = t3_mac_update_stats(&p->mac);
+	pstats = t3_mac_update_stats(&pi->mac);
 	spin_unlock(&adapter->stats_lock);
 
 	ns->tx_bytes = pstats->tx_octets;
@@ -1014,14 +1098,16 @@ static struct net_device_stats *cxgb_get_stats(struct net_device *dev)
 
 static u32 get_msglevel(struct net_device *dev)
 {
-	struct adapter *adapter = dev->priv;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 
 	return adapter->msg_enable;
 }
 
 static void set_msglevel(struct net_device *dev, u32 val)
 {
-	struct adapter *adapter = dev->priv;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 
 	adapter->msg_enable = val;
 }
@@ -1095,10 +1181,13 @@ static int get_eeprom_len(struct net_device *dev)
 
 static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	u32 fw_vers = 0;
-	struct adapter *adapter = dev->priv;
+	u32 tp_vers = 0;
 
 	t3_get_fw_version(adapter, &fw_vers);
+	t3_get_tp_version(adapter, &tp_vers);
 
 	strcpy(info->driver, DRV_NAME);
 	strcpy(info->version, DRV_VERSION);
@@ -1107,11 +1196,14 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 		strcpy(info->fw_version, "N/A");
 	else {
 		snprintf(info->fw_version, sizeof(info->fw_version),
-			 "%s %u.%u.%u",
+			 "%s %u.%u.%u TP %u.%u.%u",
 			 G_FW_VERSION_TYPE(fw_vers) ? "T" : "N",
 			 G_FW_VERSION_MAJOR(fw_vers),
 			 G_FW_VERSION_MINOR(fw_vers),
-			 G_FW_VERSION_MICRO(fw_vers));
+			 G_FW_VERSION_MICRO(fw_vers),
+			 G_TP_VERSION_MAJOR(tp_vers),
+			 G_TP_VERSION_MINOR(tp_vers),
+			 G_TP_VERSION_MICRO(tp_vers));
 	}
 }
 
@@ -1135,8 +1227,8 @@ static unsigned long collect_sge_port_stats(struct adapter *adapter,
 static void get_stats(struct net_device *dev, struct ethtool_stats *stats,
 		      u64 *data)
 {
-	struct adapter *adapter = dev->priv;
 	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	const struct mac_stats *s;
 
 	spin_lock(&adapter->stats_lock);
@@ -1204,7 +1296,8 @@ static inline void reg_block_dump(struct adapter *ap, void *buf,
 static void get_regs(struct net_device *dev, struct ethtool_regs *regs,
 		     void *buf)
 {
-	struct adapter *ap = dev->priv;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *ap = pi->adapter;
 
 	/*
 	 * Version scheme:
@@ -1245,8 +1338,9 @@ static int restart_autoneg(struct net_device *dev)
 
 static int cxgb3_phys_id(struct net_device *dev, u32 data)
 {
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	int i;
-	struct adapter *adapter = dev->priv;
 
 	if (data == 0)
 		data = 2;
@@ -1407,8 +1501,8 @@ static int set_rx_csum(struct net_device *dev, u32 data)
 
 static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e)
 {
-	const struct adapter *adapter = dev->priv;
-	const struct port_info *pi = netdev_priv(dev);
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	const struct qset_params *q = &adapter->params.sge.qset[pi->first_qset];
 
 	e->rx_max_pending = MAX_RX_BUFFERS;
@@ -1424,10 +1518,10 @@ static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e)
 
 static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e)
 {
-	int i;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	struct qset_params *q;
-	struct adapter *adapter = dev->priv;
-	const struct port_info *pi = netdev_priv(dev);
+	int i;
 
 	if (e->rx_pending > MAX_RX_BUFFERS ||
 	    e->rx_jumbo_pending > MAX_RX_JUMBO_BUFFERS ||
@@ -1456,7 +1550,8 @@ static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e)
 
 static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
 {
-	struct adapter *adapter = dev->priv;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	struct qset_params *qsp = &adapter->params.sge.qset[0];
 	struct sge_qset *qs = &adapter->sge.qs[0];
 
@@ -1470,7 +1565,8 @@ static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
 
 static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
 {
-	struct adapter *adapter = dev->priv;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	struct qset_params *q = adapter->params.sge.qset;
 
 	c->rx_coalesce_usecs = q->coalesce_usecs;
@@ -1480,8 +1576,9 @@ static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
 static int get_eeprom(struct net_device *dev, struct ethtool_eeprom *e,
 		      u8 * data)
 {
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	int i, err = 0;
-	struct adapter *adapter = dev->priv;
 
 	u8 *buf = kmalloc(EEPROMSIZE, GFP_KERNEL);
 	if (!buf)
@@ -1500,10 +1597,11 @@ static int get_eeprom(struct net_device *dev, struct ethtool_eeprom *e,
 static int set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 		      u8 * data)
 {
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
+	u32 aligned_offset, aligned_len, *p;
 	u8 *buf;
 	int err = 0;
-	u32 aligned_offset, aligned_len, *p;
-	struct adapter *adapter = dev->priv;
 
 	if (eeprom->magic != EEPROM_MAGIC)
 		return -EINVAL;
@@ -1582,7 +1680,6 @@ static const struct ethtool_ops cxgb_ethtool_ops = {
 	.get_wol = get_wol,
 	.get_tso = ethtool_op_get_tso,
 	.set_tso = ethtool_op_set_tso,
-	.get_perm_addr = ethtool_op_get_perm_addr
 };
 
 static int in_range(int val, int lo, int hi)
@@ -1592,9 +1689,10 @@ static int in_range(int val, int lo, int hi)
 
 static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 {
-	int ret;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	u32 cmd;
-	struct adapter *adapter = dev->priv;
+	int ret;
 
 	if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
 		return -EFAULT;
@@ -1818,8 +1916,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 			return -EBUSY;
 		if (copy_from_user(&m, useraddr, sizeof(m)))
 			return -EFAULT;
-		if (!m.rx_pg_sz || (m.rx_pg_sz & (m.rx_pg_sz - 1)) ||
-			!m.tx_pg_sz || (m.tx_pg_sz & (m.tx_pg_sz - 1)))
+		if (!is_power_of_2(m.rx_pg_sz) ||
+			!is_power_of_2(m.tx_pg_sz))
 			return -EINVAL;	/* not power of 2 */
 		if (!(m.rx_pg_sz & 0x14000))
 			return -EINVAL;	/* not 16KB or 64KB */
@@ -1923,10 +2021,10 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 
 static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 {
-	int ret, mmd;
-	struct adapter *adapter = dev->priv;
-	struct port_info *pi = netdev_priv(dev);
 	struct mii_ioctl_data *data = if_mii(req);
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
+	int ret, mmd;
 
 	switch (cmd) {
 	case SIOCGMIIPHY:
@@ -1994,9 +2092,9 @@ static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 
 static int cxgb_change_mtu(struct net_device *dev, int new_mtu)
 {
-	int ret;
-	struct adapter *adapter = dev->priv;
 	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
+	int ret;
 
 	if (new_mtu < 81)	/* accommodate SACK */
 		return -EINVAL;
@@ -2013,8 +2111,8 @@ static int cxgb_change_mtu(struct net_device *dev, int new_mtu)
 
 static int cxgb_set_mac_addr(struct net_device *dev, void *p)
 {
-	struct adapter *adapter = dev->priv;
 	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	struct sockaddr *addr = p;
 
 	if (!is_valid_ether_addr(addr->sa_data))
@@ -2050,8 +2148,8 @@ static void t3_synchronize_rx(struct adapter *adap, const struct port_info *p)
 
 static void vlan_rx_register(struct net_device *dev, struct vlan_group *grp)
 {
-	struct adapter *adapter = dev->priv;
 	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 
 	pi->vlan_grp = grp;
 	if (adapter->params.rev > 0)
@@ -2070,8 +2168,8 @@ static void vlan_rx_register(struct net_device *dev, struct vlan_group *grp)
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void cxgb_netpoll(struct net_device *dev)
 {
-	struct adapter *adapter = dev->priv;
 	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	int qidx;
 
 	for (qidx = pi->first_qset; qidx < pi->first_qset + pi->nqsets; qidx++) {
@@ -2397,6 +2495,7 @@ static int __devinit init_one(struct pci_dev *pdev,
 
 		adapter->port[i] = netdev;
 		pi = netdev_priv(netdev);
+		pi->adapter = adapter;
 		pi->rx_csum_offload = 1;
 		pi->nqsets = 1;
 		pi->first_qset = i;
@@ -2406,7 +2505,6 @@ static int __devinit init_one(struct pci_dev *pdev,
 		netdev->irq = pdev->irq;
 		netdev->mem_start = mmio_start;
 		netdev->mem_end = mmio_start + mmio_len - 1;
-		netdev->priv = adapter;
 		netdev->features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
 		netdev->features |= NETIF_F_LLTX;
 		if (pci_using_dac)
@@ -2431,12 +2529,12 @@ static int __devinit init_one(struct pci_dev *pdev,
 		SET_ETHTOOL_OPS(netdev, &cxgb_ethtool_ops);
 	}
 
-	pci_set_drvdata(pdev, adapter->port[0]);
+	pci_set_drvdata(pdev, adapter);
 	if (t3_prep_adapter(adapter, ai, 1) < 0) {
 		err = -ENODEV;
 		goto out_free_dev;
 	}
-
+		
 	/*
 	 * The card is now ready to go.  If any errors occur during device
 	 * registration we do not fail the whole card but rather proceed only
@@ -2504,11 +2602,10 @@ out_release_regions:
 
 static void __devexit remove_one(struct pci_dev *pdev)
 {
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct adapter *adapter = pci_get_drvdata(pdev);
 
-	if (dev) {
+	if (adapter) {
 		int i;
-		struct adapter *adapter = dev->priv;
 
 		t3_sge_stop(adapter);
 		sysfs_remove_group(&adapter->port[0]->dev.kobj,
diff --git a/drivers/net/cxgb3/cxgb3_offload.c b/drivers/net/cxgb3/cxgb3_offload.c
index ebcf35e4cf5b..bdff7baeb59d 100644
--- a/drivers/net/cxgb3/cxgb3_offload.c
+++ b/drivers/net/cxgb3/cxgb3_offload.c
@@ -593,6 +593,16 @@ int cxgb3_alloc_stid(struct t3cdev *tdev, struct cxgb3_client *client,
 
 EXPORT_SYMBOL(cxgb3_alloc_stid);
 
+/* Get the t3cdev associated with a net_device */
+struct t3cdev *dev2t3cdev(struct net_device *dev)
+{
+	const struct port_info *pi = netdev_priv(dev);
+
+	return (struct t3cdev *)pi->adapter;
+}
+
+EXPORT_SYMBOL(dev2t3cdev);
+
 static int do_smt_write_rpl(struct t3cdev *dev, struct sk_buff *skb)
 {
 	struct cpl_smt_write_rpl *rpl = cplhdr(skb);
@@ -699,7 +709,7 @@ static int do_cr(struct t3cdev *dev, struct sk_buff *skb)
  * the buffer.
  */
 static struct sk_buff *cxgb3_get_cpl_reply_skb(struct sk_buff *skb, size_t len,
-					       int gfp)
+					       gfp_t gfp)
 {
 	if (likely(!skb_cloned(skb))) {
 		BUG_ON(skb->len < len);
@@ -925,7 +935,7 @@ void cxgb_neigh_update(struct neighbour *neigh)
 	struct net_device *dev = neigh->dev;
 
 	if (dev && (is_offloading(dev))) {
-		struct t3cdev *tdev = T3CDEV(dev);
+		struct t3cdev *tdev = dev2t3cdev(dev);
 
 		BUG_ON(!tdev);
 		t3_l2t_update(tdev, neigh);
@@ -973,9 +983,9 @@ void cxgb_redirect(struct dst_entry *old, struct dst_entry *new)
 		       "device ignored.\n", __FUNCTION__);
 		return;
 	}
-	tdev = T3CDEV(olddev);
+	tdev = dev2t3cdev(olddev);
 	BUG_ON(!tdev);
-	if (tdev != T3CDEV(newdev)) {
+	if (tdev != dev2t3cdev(newdev)) {
 		printk(KERN_WARNING "%s: Redirect to different "
 		       "offload device ignored.\n", __FUNCTION__);
 		return;
diff --git a/drivers/net/cxgb3/cxgb3_offload.h b/drivers/net/cxgb3/cxgb3_offload.h
index f15446a32efc..7a379138b5a6 100644
--- a/drivers/net/cxgb3/cxgb3_offload.h
+++ b/drivers/net/cxgb3/cxgb3_offload.h
@@ -51,6 +51,8 @@ void cxgb3_offload_deactivate(struct adapter *adapter);
 
 void cxgb3_set_dummy_ops(struct t3cdev *dev);
 
+struct t3cdev *dev2t3cdev(struct net_device *dev);
+
 /*
  * Client registration.  Users of T3 driver must register themselves.
  * The T3 driver will call the add function of every client for each T3
diff --git a/drivers/net/cxgb3/regs.h b/drivers/net/cxgb3/regs.h
index 020859c855d7..aa80313c922e 100644
--- a/drivers/net/cxgb3/regs.h
+++ b/drivers/net/cxgb3/regs.h
@@ -1160,6 +1160,8 @@
 
 #define A_TP_MOD_CHANNEL_WEIGHT 0x434
 
+#define A_TP_MOD_RATE_LIMIT 0x438
+
 #define A_TP_PIO_ADDR 0x440
 
 #define A_TP_PIO_DATA 0x444
@@ -1214,6 +1216,15 @@
 #define G_TXDROPCNTCH0RCVD(x) (((x) >> S_TXDROPCNTCH0RCVD) & \
 			       M_TXDROPCNTCH0RCVD)
 
+#define A_TP_PROXY_FLOW_CNTL 0x4b0
+
+#define A_TP_EMBED_OP_FIELD0 0x4e8
+#define A_TP_EMBED_OP_FIELD1 0x4ec
+#define A_TP_EMBED_OP_FIELD2 0x4f0
+#define A_TP_EMBED_OP_FIELD3 0x4f4
+#define A_TP_EMBED_OP_FIELD4 0x4f8
+#define A_TP_EMBED_OP_FIELD5 0x4fc
+
 #define A_ULPRX_CTL 0x500
 
 #define S_ROUND_ROBIN    4
diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c
index a60ec4d4707c..58a5f60521ed 100644
--- a/drivers/net/cxgb3/sge.c
+++ b/drivers/net/cxgb3/sge.c
@@ -46,23 +46,16 @@
 
 #define SGE_RX_SM_BUF_SIZE 1536
 
-/*
- * If USE_RX_PAGE is defined, the small freelist populated with (partial)
- * pages instead of skbs. Pages are carved up into RX_PAGE_SIZE chunks (must
- * be a multiple of the host page size).
- */
-#define USE_RX_PAGE
-#define RX_PAGE_SIZE 2048
-
-/*
- * skb freelist packets are copied into a new skb (and the freelist one is 
- * reused) if their len is <= 
- */
 #define SGE_RX_COPY_THRES  256
+#define SGE_RX_PULL_LEN    128
 
 /*
- * Minimum number of freelist entries before we start dropping TUNNEL frames.
+ * Page chunk size for FL0 buffers if FL0 is to be populated with page chunks.
+ * It must be a divisor of PAGE_SIZE.  If set to 0 FL0 will use sk_buffs
+ * directly.
  */
+#define FL0_PG_CHUNK_SIZE  2048
+
 #define SGE_RX_DROP_THRES 16
 
 /*
@@ -100,12 +93,12 @@ struct tx_sw_desc {		/* SW state per Tx descriptor */
 	struct sk_buff *skb;
 };
 
-struct rx_sw_desc {		/* SW state per Rx descriptor */
+struct rx_sw_desc {                /* SW state per Rx descriptor */
 	union {
 		struct sk_buff *skb;
-		struct sge_fl_page page;
-	} t;
-	 DECLARE_PCI_UNMAP_ADDR(dma_addr);
+		struct fl_pg_chunk pg_chunk;
+	};
+	DECLARE_PCI_UNMAP_ADDR(dma_addr);
 };
 
 struct rsp_desc {		/* response queue descriptor */
@@ -351,27 +344,26 @@ static void free_rx_bufs(struct pci_dev *pdev, struct sge_fl *q)
 
 		pci_unmap_single(pdev, pci_unmap_addr(d, dma_addr),
 				 q->buf_size, PCI_DMA_FROMDEVICE);
-
-		if (q->buf_size != RX_PAGE_SIZE) {
-			kfree_skb(d->t.skb);
-			d->t.skb = NULL;
+		if (q->use_pages) {
+			put_page(d->pg_chunk.page);
+			d->pg_chunk.page = NULL;
 		} else {
-			if (d->t.page.frag.page)
-				put_page(d->t.page.frag.page);
-			d->t.page.frag.page = NULL;
+			kfree_skb(d->skb);
+			d->skb = NULL;
 		}
 		if (++cidx == q->size)
 			cidx = 0;
 	}
 
-	if (q->page.frag.page)
-		put_page(q->page.frag.page);
-	q->page.frag.page = NULL;
+	if (q->pg_chunk.page) {
+		__free_page(q->pg_chunk.page);
+		q->pg_chunk.page = NULL;
+	}
 }
 
 /**
  *	add_one_rx_buf - add a packet buffer to a free-buffer list
- *	@va: va of the buffer to add
+ *	@va:  buffer start VA
  *	@len: the buffer length
  *	@d: the HW Rx descriptor to write
  *	@sd: the SW Rx descriptor to write
@@ -381,7 +373,7 @@ static void free_rx_bufs(struct pci_dev *pdev, struct sge_fl *q)
  *	Add a buffer of the given length to the supplied HW and SW Rx
  *	descriptors.
  */
-static inline void add_one_rx_buf(unsigned char *va, unsigned int len,
+static inline void add_one_rx_buf(void *va, unsigned int len,
 				  struct rx_desc *d, struct rx_sw_desc *sd,
 				  unsigned int gen, struct pci_dev *pdev)
 {
@@ -397,6 +389,27 @@ static inline void add_one_rx_buf(unsigned char *va, unsigned int len,
 	d->gen2 = cpu_to_be32(V_FLD_GEN2(gen));
 }
 
+static int alloc_pg_chunk(struct sge_fl *q, struct rx_sw_desc *sd, gfp_t gfp)
+{
+	if (!q->pg_chunk.page) {
+		q->pg_chunk.page = alloc_page(gfp);
+		if (unlikely(!q->pg_chunk.page))
+			return -ENOMEM;
+		q->pg_chunk.va = page_address(q->pg_chunk.page);
+		q->pg_chunk.offset = 0;
+	}
+	sd->pg_chunk = q->pg_chunk;
+
+	q->pg_chunk.offset += q->buf_size;
+	if (q->pg_chunk.offset == PAGE_SIZE)
+		q->pg_chunk.page = NULL;
+	else {
+		q->pg_chunk.va += q->buf_size;
+		get_page(q->pg_chunk.page);
+	}
+	return 0;
+}
+
 /**
  *	refill_fl - refill an SGE free-buffer list
  *	@adapter: the adapter
@@ -410,49 +423,29 @@ static inline void add_one_rx_buf(unsigned char *va, unsigned int len,
  */
 static void refill_fl(struct adapter *adap, struct sge_fl *q, int n, gfp_t gfp)
 {
+	void *buf_start;
 	struct rx_sw_desc *sd = &q->sdesc[q->pidx];
 	struct rx_desc *d = &q->desc[q->pidx];
-	struct sge_fl_page *p = &q->page;
 
 	while (n--) {
-		unsigned char *va;
-
-		if (unlikely(q->buf_size != RX_PAGE_SIZE)) {
-			struct sk_buff *skb = alloc_skb(q->buf_size, gfp);
-
-			if (!skb) {
-				q->alloc_failed++;
+		if (q->use_pages) {
+			if (unlikely(alloc_pg_chunk(q, sd, gfp))) {
+nomem:				q->alloc_failed++;
 				break;
 			}
-			va = skb->data;
-			sd->t.skb = skb;
+			buf_start = sd->pg_chunk.va;
 		} else {
-			if (!p->frag.page) {
-				p->frag.page = alloc_pages(gfp, 0);
-				if (unlikely(!p->frag.page)) {
-					q->alloc_failed++;
-					break;
-				} else {
-					p->frag.size = RX_PAGE_SIZE;
-					p->frag.page_offset = 0;
-					p->va = page_address(p->frag.page);
-				}
-			}
+			struct sk_buff *skb = alloc_skb(q->buf_size, gfp);
 
-			memcpy(&sd->t, p, sizeof(*p));
-			va = p->va;
+			if (!skb)
+				goto nomem;
 
-			p->frag.page_offset += RX_PAGE_SIZE;
-			BUG_ON(p->frag.page_offset > PAGE_SIZE);
-			p->va += RX_PAGE_SIZE;
-			if (p->frag.page_offset == PAGE_SIZE)
-				p->frag.page = NULL;
-			else
-				get_page(p->frag.page);
+			sd->skb = skb;
+			buf_start = skb->data;
 		}
 
-		add_one_rx_buf(va, q->buf_size, d, sd, q->gen, adap->pdev);
-
+		add_one_rx_buf(buf_start, q->buf_size, d, sd, q->gen,
+			       adap->pdev);
 		d++;
 		sd++;
 		if (++q->pidx == q->size) {
@@ -487,7 +480,7 @@ static void recycle_rx_buf(struct adapter *adap, struct sge_fl *q,
 	struct rx_desc *from = &q->desc[idx];
 	struct rx_desc *to = &q->desc[q->pidx];
 
-	memcpy(&q->sdesc[q->pidx], &q->sdesc[idx], sizeof(struct rx_sw_desc));
+	q->sdesc[q->pidx] = q->sdesc[idx];
 	to->addr_lo = from->addr_lo;	/* already big endian */
 	to->addr_hi = from->addr_hi;	/* likewise */
 	wmb();
@@ -650,6 +643,132 @@ static inline unsigned int flits_to_desc(unsigned int n)
 }
 
 /**
+ *	get_packet - return the next ingress packet buffer from a free list
+ *	@adap: the adapter that received the packet
+ *	@fl: the SGE free list holding the packet
+ *	@len: the packet length including any SGE padding
+ *	@drop_thres: # of remaining buffers before we start dropping packets
+ *
+ *	Get the next packet from a free list and complete setup of the
+ *	sk_buff.  If the packet is small we make a copy and recycle the
+ *	original buffer, otherwise we use the original buffer itself.  If a
+ *	positive drop threshold is supplied packets are dropped and their
+ *	buffers recycled if (a) the number of remaining buffers is under the
+ *	threshold and the packet is too big to copy, or (b) the packet should
+ *	be copied but there is no memory for the copy.
+ */
+static struct sk_buff *get_packet(struct adapter *adap, struct sge_fl *fl,
+				  unsigned int len, unsigned int drop_thres)
+{
+	struct sk_buff *skb = NULL;
+	struct rx_sw_desc *sd = &fl->sdesc[fl->cidx];
+
+	prefetch(sd->skb->data);
+	fl->credits--;
+
+	if (len <= SGE_RX_COPY_THRES) {
+		skb = alloc_skb(len, GFP_ATOMIC);
+		if (likely(skb != NULL)) {
+			__skb_put(skb, len);
+			pci_dma_sync_single_for_cpu(adap->pdev,
+					    pci_unmap_addr(sd, dma_addr), len,
+					    PCI_DMA_FROMDEVICE);
+			memcpy(skb->data, sd->skb->data, len);
+			pci_dma_sync_single_for_device(adap->pdev,
+					    pci_unmap_addr(sd, dma_addr), len,
+					    PCI_DMA_FROMDEVICE);
+		} else if (!drop_thres)
+			goto use_orig_buf;
+recycle:
+		recycle_rx_buf(adap, fl, fl->cidx);
+		return skb;
+	}
+
+	if (unlikely(fl->credits < drop_thres))
+		goto recycle;
+
+use_orig_buf:
+	pci_unmap_single(adap->pdev, pci_unmap_addr(sd, dma_addr),
+			 fl->buf_size, PCI_DMA_FROMDEVICE);
+	skb = sd->skb;
+	skb_put(skb, len);
+	__refill_fl(adap, fl);
+	return skb;
+}
+
+/**
+ *	get_packet_pg - return the next ingress packet buffer from a free list
+ *	@adap: the adapter that received the packet
+ *	@fl: the SGE free list holding the packet
+ *	@len: the packet length including any SGE padding
+ *	@drop_thres: # of remaining buffers before we start dropping packets
+ *
+ *	Get the next packet from a free list populated with page chunks.
+ *	If the packet is small we make a copy and recycle the original buffer,
+ *	otherwise we attach the original buffer as a page fragment to a fresh
+ *	sk_buff.  If a positive drop threshold is supplied packets are dropped
+ *	and their buffers recycled if (a) the number of remaining buffers is
+ *	under the threshold and the packet is too big to copy, or (b) there's
+ *	no system memory.
+ *
+ * 	Note: this function is similar to @get_packet but deals with Rx buffers
+ * 	that are page chunks rather than sk_buffs.
+ */
+static struct sk_buff *get_packet_pg(struct adapter *adap, struct sge_fl *fl,
+				     unsigned int len, unsigned int drop_thres)
+{
+	struct sk_buff *skb = NULL;
+	struct rx_sw_desc *sd = &fl->sdesc[fl->cidx];
+
+	if (len <= SGE_RX_COPY_THRES) {
+		skb = alloc_skb(len, GFP_ATOMIC);
+		if (likely(skb != NULL)) {
+			__skb_put(skb, len);
+			pci_dma_sync_single_for_cpu(adap->pdev,
+					    pci_unmap_addr(sd, dma_addr), len,
+					    PCI_DMA_FROMDEVICE);
+			memcpy(skb->data, sd->pg_chunk.va, len);
+			pci_dma_sync_single_for_device(adap->pdev,
+					    pci_unmap_addr(sd, dma_addr), len,
+					    PCI_DMA_FROMDEVICE);
+		} else if (!drop_thres)
+			return NULL;
+recycle:
+		fl->credits--;
+		recycle_rx_buf(adap, fl, fl->cidx);
+		return skb;
+	}
+
+	if (unlikely(fl->credits <= drop_thres))
+		goto recycle;
+
+	skb = alloc_skb(SGE_RX_PULL_LEN, GFP_ATOMIC);
+	if (unlikely(!skb)) {
+		if (!drop_thres)
+			return NULL;
+		goto recycle;
+	}
+
+	pci_unmap_single(adap->pdev, pci_unmap_addr(sd, dma_addr),
+			 fl->buf_size, PCI_DMA_FROMDEVICE);
+	__skb_put(skb, SGE_RX_PULL_LEN);
+	memcpy(skb->data, sd->pg_chunk.va, SGE_RX_PULL_LEN);
+	skb_fill_page_desc(skb, 0, sd->pg_chunk.page,
+			   sd->pg_chunk.offset + SGE_RX_PULL_LEN,
+			   len - SGE_RX_PULL_LEN);
+	skb->len = len;
+	skb->data_len = len - SGE_RX_PULL_LEN;
+	skb->truesize += skb->data_len;
+
+	fl->credits--;
+	/*
+	 * We do not refill FLs here, we let the caller do it to overlap a
+	 * prefetch.
+	 */
+	return skb;
+}
+
+/**
  *	get_imm_packet - return the next ingress packet buffer from a response
  *	@resp: the response descriptor containing the packet data
  *
@@ -954,7 +1073,7 @@ 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 = dev->priv;
+	struct adapter *adap = pi->adapter;
 	struct sge_qset *qs = dev2qset(dev);
 	struct sge_txq *q = &qs->txq[TXQ_ETH];
 
@@ -1207,7 +1326,8 @@ 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];
-	struct adapter *adap = qs->netdev->priv;
+	const struct port_info *pi = netdev_priv(qs->netdev);
+	struct adapter *adap = pi->adapter;
 
 	spin_lock(&q->lock);
       again:reclaim_completed_tx_imm(q);
@@ -1412,7 +1532,8 @@ static void restart_offloadq(unsigned long data)
 	struct sk_buff *skb;
 	struct sge_qset *qs = (struct sge_qset *)data;
 	struct sge_txq *q = &qs->txq[TXQ_OFLD];
-	struct adapter *adap = qs->netdev->priv;
+	const struct port_info *pi = netdev_priv(qs->netdev);
+	struct adapter *adap = pi->adapter;
 
 	spin_lock(&q->lock);
       again:reclaim_completed_tx(adap, q);
@@ -1556,7 +1677,8 @@ static inline void deliver_partial_bundle(struct t3cdev *tdev,
  */
 static int ofld_poll(struct net_device *dev, int *budget)
 {
-	struct adapter *adapter = dev->priv;
+	const struct port_info *pi = netdev_priv(dev);
+	struct adapter *adapter = pi->adapter;
 	struct sge_qset *qs = dev2qset(dev);
 	struct sge_rspq *q = &qs->rspq;
 	int work_done, limit = min(*budget, dev->quota), avail = limit;
@@ -1715,85 +1837,6 @@ static void rx_eth(struct adapter *adap, struct sge_rspq *rq,
 		netif_rx(skb);
 }
 
-#define SKB_DATA_SIZE 128
-
-static void skb_data_init(struct sk_buff *skb, struct sge_fl_page *p,
-			  unsigned int len)
-{
-	skb->len = len;
-	if (len <= SKB_DATA_SIZE) {
-		skb_copy_to_linear_data(skb, p->va, len);
-		skb->tail += len;
-		put_page(p->frag.page);
-	} else {
-		skb_copy_to_linear_data(skb, p->va, SKB_DATA_SIZE);
-		skb_shinfo(skb)->frags[0].page = p->frag.page;
-		skb_shinfo(skb)->frags[0].page_offset =
-		    p->frag.page_offset + SKB_DATA_SIZE;
-		skb_shinfo(skb)->frags[0].size = len - SKB_DATA_SIZE;
-		skb_shinfo(skb)->nr_frags = 1;
-		skb->data_len = len - SKB_DATA_SIZE;
-		skb->tail += SKB_DATA_SIZE;
-		skb->truesize += skb->data_len;
-	}
-}
-
-/**
-*      get_packet - return the next ingress packet buffer from a free list
-*      @adap: the adapter that received the packet
-*      @fl: the SGE free list holding the packet
-*      @len: the packet length including any SGE padding
-*      @drop_thres: # of remaining buffers before we start dropping packets
-*
-*      Get the next packet from a free list and complete setup of the
-*      sk_buff.  If the packet is small we make a copy and recycle the
-*      original buffer, otherwise we use the original buffer itself.  If a
-*      positive drop threshold is supplied packets are dropped and their
-*      buffers recycled if (a) the number of remaining buffers is under the
-*      threshold and the packet is too big to copy, or (b) the packet should
-*      be copied but there is no memory for the copy.
-*/
-static struct sk_buff *get_packet(struct adapter *adap, struct sge_fl *fl,
-				  unsigned int len, unsigned int drop_thres)
-{
-	struct sk_buff *skb = NULL;
-	struct rx_sw_desc *sd = &fl->sdesc[fl->cidx];
-
-	prefetch(sd->t.skb->data);
-
-	if (len <= SGE_RX_COPY_THRES) {
-		skb = alloc_skb(len, GFP_ATOMIC);
-		if (likely(skb != NULL)) {
-			struct rx_desc *d = &fl->desc[fl->cidx];
-			dma_addr_t mapping =
-			    (dma_addr_t)((u64) be32_to_cpu(d->addr_hi) << 32 |
-					 be32_to_cpu(d->addr_lo));
-
-			__skb_put(skb, len);
-			pci_dma_sync_single_for_cpu(adap->pdev, mapping, len,
-						    PCI_DMA_FROMDEVICE);
-			skb_copy_from_linear_data(sd->t.skb, skb->data, len);
-			pci_dma_sync_single_for_device(adap->pdev, mapping, len,
-						       PCI_DMA_FROMDEVICE);
-		} else if (!drop_thres)
-			goto use_orig_buf;
-recycle:
-		recycle_rx_buf(adap, fl, fl->cidx);
-		return skb;
-	}
-
-	if (unlikely(fl->credits < drop_thres))
-		goto recycle;
-
-use_orig_buf:
-	pci_unmap_single(adap->pdev, pci_unmap_addr(sd, dma_addr),
-			 fl->buf_size, PCI_DMA_FROMDEVICE);
-	skb = sd->t.skb;
-	skb_put(skb, len);
-	__refill_fl(adap, fl);
-	return skb;
-}
-
 /**
  *	handle_rsp_cntrl_info - handles control information in a response
  *	@qs: the queue set corresponding to the response
@@ -1935,7 +1978,7 @@ static int process_responses(struct adapter *adap, struct sge_qset *qs,
 		} else if (flags & F_RSPD_IMM_DATA_VALID) {
 			skb = get_imm_packet(r);
 			if (unlikely(!skb)) {
-			      no_mem:
+no_mem:
 				q->next_holdoff = NOMEM_INTR_DELAY;
 				q->nomem++;
 				/* consume one credit since we tried */
@@ -1945,53 +1988,29 @@ static int process_responses(struct adapter *adap, struct sge_qset *qs,
 			q->imm_data++;
 			ethpad = 0;
 		} else if ((len = ntohl(r->len_cq)) != 0) {
-			struct sge_fl *fl =
-			    (len & F_RSPD_FLQ) ? &qs->fl[1] : &qs->fl[0];
-
-			if (fl->buf_size == RX_PAGE_SIZE) {
-				struct rx_sw_desc *sd = &fl->sdesc[fl->cidx];
-				struct sge_fl_page *p = &sd->t.page;
+			struct sge_fl *fl;
 
-				prefetch(p->va);
-				prefetch(p->va + L1_CACHE_BYTES);
+			fl = (len & F_RSPD_FLQ) ? &qs->fl[1] : &qs->fl[0];
+			if (fl->use_pages) {
+				void *addr = fl->sdesc[fl->cidx].pg_chunk.va;
 
+				prefetch(addr);
+#if L1_CACHE_BYTES < 128
+				prefetch(addr + L1_CACHE_BYTES);
+#endif
 				__refill_fl(adap, fl);
 
-				pci_unmap_single(adap->pdev,
-						 pci_unmap_addr(sd, dma_addr),
-						 fl->buf_size,
-						 PCI_DMA_FROMDEVICE);
-
-				if (eth) {
-					if (unlikely(fl->credits <
-						     SGE_RX_DROP_THRES))
-						goto eth_recycle;
-
-					skb = alloc_skb(SKB_DATA_SIZE,
-							GFP_ATOMIC);
-					if (unlikely(!skb)) {
-eth_recycle:
-						q->rx_drops++;
-						recycle_rx_buf(adap, fl,
-							       fl->cidx);
-						goto eth_done;
-					}
-				} else {
-					skb = alloc_skb(SKB_DATA_SIZE,
-							GFP_ATOMIC);
-					if (unlikely(!skb))
-						goto no_mem;
-				}
-
-				skb_data_init(skb, p, G_RSPD_LEN(len));
-eth_done:
-				fl->credits--;
-				q->eth_pkts++;
-			} else {
-				fl->credits--;
+				skb = get_packet_pg(adap, fl, G_RSPD_LEN(len),
+						 eth ? SGE_RX_DROP_THRES : 0);
+			} else
 				skb = get_packet(adap, fl, G_RSPD_LEN(len),
 						 eth ? SGE_RX_DROP_THRES : 0);
-			}
+			if (unlikely(!skb)) {
+				if (!eth)
+					goto no_mem;
+				q->rx_drops++;
+			} else if (unlikely(r->rss_hdr.opcode == CPL_TRACE_PKT))
+				__skb_pull(skb, 2);
 
 			if (++fl->cidx == fl->size)
 				fl->cidx = 0;
@@ -2016,20 +2035,15 @@ eth_done:
 			q->credits = 0;
 		}
 
-		if (skb) {
-			/* Preserve the RSS info in csum & priority */
-			skb->csum = rss_hi;
-			skb->priority = rss_lo;
-
+		if (likely(skb != NULL)) {
 			if (eth)
 				rx_eth(adap, q, skb, ethpad);
 			else {
-				if (unlikely(r->rss_hdr.opcode ==
-					     CPL_TRACE_PKT))
-					__skb_pull(skb, ethpad);
-
-				ngathered = rx_offload(&adap->tdev, q,
-						       skb, offload_skbs,
+				/* Preserve the RSS info in csum & priority */
+				skb->csum = rss_hi;
+				skb->priority = rss_lo;
+				ngathered = rx_offload(&adap->tdev, q, skb,
+						       offload_skbs,
 						       ngathered);
 			}
 		}
@@ -2064,7 +2078,8 @@ static inline int is_pure_response(const struct rsp_desc *r)
  */
 static int napi_rx_handler(struct net_device *dev, int *budget)
 {
-	struct adapter *adap = dev->priv;
+	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);
 
@@ -2194,7 +2209,8 @@ 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;
-	struct adapter *adap = qs->netdev->priv;
+	const struct port_info *pi = netdev_priv(qs->netdev);
+	struct adapter *adap = pi->adapter;
 	struct sge_rspq *q = &qs->rspq;
 
 	spin_lock(&q->lock);
@@ -2213,7 +2229,8 @@ irqreturn_t t3_sge_intr_msix(int irq, void *cookie)
 irqreturn_t t3_sge_intr_msix_napi(int irq, void *cookie)
 {
 	struct sge_qset *qs = cookie;
-	struct adapter *adap = qs->netdev->priv;
+	const struct port_info *pi = netdev_priv(qs->netdev);
+	struct adapter *adap = pi->adapter;
 	struct sge_rspq *q = &qs->rspq;
 
 	spin_lock(&q->lock);
@@ -2497,7 +2514,8 @@ static void sge_timer_cb(unsigned long data)
 {
 	spinlock_t *lock;
 	struct sge_qset *qs = (struct sge_qset *)data;
-	struct adapter *adap = qs->netdev->priv;
+	const struct port_info *pi = netdev_priv(qs->netdev);
+	struct adapter *adap = pi->adapter;
 
 	if (spin_trylock(&qs->txq[TXQ_ETH].lock)) {
 		reclaim_completed_tx(adap, &qs->txq[TXQ_ETH]);
@@ -2635,25 +2653,15 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 	q->txq[TXQ_ETH].stop_thres = nports *
 	    flits_to_desc(sgl_len(MAX_SKB_FRAGS + 1) + 3);
 
-	if (!is_offload(adapter)) {
-#ifdef USE_RX_PAGE
-		q->fl[0].buf_size = RX_PAGE_SIZE;
+#if FL0_PG_CHUNK_SIZE > 0
+	q->fl[0].buf_size = FL0_PG_CHUNK_SIZE;
 #else
-		q->fl[0].buf_size = SGE_RX_SM_BUF_SIZE + 2 +
-		    sizeof(struct cpl_rx_pkt);
+	q->fl[0].buf_size = SGE_RX_SM_BUF_SIZE + sizeof(struct cpl_rx_data);
 #endif
-		q->fl[1].buf_size = MAX_FRAME_SIZE + 2 +
-		    sizeof(struct cpl_rx_pkt);
-	} else {
-#ifdef USE_RX_PAGE
-		q->fl[0].buf_size = RX_PAGE_SIZE;
-#else
-		q->fl[0].buf_size = SGE_RX_SM_BUF_SIZE +
-		    sizeof(struct cpl_rx_data);
-#endif
-		q->fl[1].buf_size = (16 * 1024) -
-		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	}
+	q->fl[0].use_pages = FL0_PG_CHUNK_SIZE > 0;
+	q->fl[1].buf_size = is_offload(adapter) ?
+		(16 * 1024) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
+		MAX_FRAME_SIZE + 2 + sizeof(struct cpl_rx_pkt);
 
 	spin_lock(&adapter->sge.reg_lock);
 
diff --git a/drivers/net/cxgb3/t3_hw.c b/drivers/net/cxgb3/t3_hw.c
index fb485d0a43d8..b02d15daf5d9 100644
--- a/drivers/net/cxgb3/t3_hw.c
+++ b/drivers/net/cxgb3/t3_hw.c
@@ -847,6 +847,98 @@ static int t3_write_flash(struct adapter *adapter, unsigned int addr,
 	return 0;
 }
 
+/**
+ *	t3_get_tp_version - read the tp sram version
+ *	@adapter: the adapter
+ *	@vers: where to place the version
+ *
+ *	Reads the protocol sram version from sram.
+ */
+int t3_get_tp_version(struct adapter *adapter, u32 *vers)
+{
+	int ret;
+
+	/* Get version loaded in SRAM */
+	t3_write_reg(adapter, A_TP_EMBED_OP_FIELD0, 0);
+	ret = t3_wait_op_done(adapter, A_TP_EMBED_OP_FIELD0,
+			      1, 1, 5, 1);
+	if (ret)
+		return ret;
+	
+	*vers = t3_read_reg(adapter, A_TP_EMBED_OP_FIELD1);
+
+	return 0;
+}
+
+/**
+ *	t3_check_tpsram_version - read the tp sram version
+ *	@adapter: the adapter
+ *	@must_load: set to 1 if loading a new microcode image is required
+ *
+ *	Reads the protocol sram version from flash.
+ */
+int t3_check_tpsram_version(struct adapter *adapter, int *must_load)
+{
+	int ret;
+	u32 vers;
+	unsigned int major, minor;
+
+	if (adapter->params.rev == T3_REV_A)
+		return 0;
+
+	*must_load = 1;
+
+	ret = t3_get_tp_version(adapter, &vers);
+	if (ret)
+		return ret;
+
+	major = G_TP_VERSION_MAJOR(vers);
+	minor = G_TP_VERSION_MINOR(vers);
+
+	if (major == TP_VERSION_MAJOR && minor == TP_VERSION_MINOR) 
+		return 0;
+
+	if (major != TP_VERSION_MAJOR)
+		CH_ERR(adapter, "found wrong TP version (%u.%u), "
+		       "driver needs version %d.%d\n", major, minor,
+		       TP_VERSION_MAJOR, TP_VERSION_MINOR);
+	else {
+		*must_load = 0;
+		CH_ERR(adapter, "found wrong TP version (%u.%u), "
+		       "driver compiled for version %d.%d\n", major, minor,
+		       TP_VERSION_MAJOR, TP_VERSION_MINOR);
+	}
+	return -EINVAL;
+}
+
+/**
+ *	t3_check_tpsram - check if provided protocol SRAM 
+ *			  is compatible with this driver
+ *	@adapter: the adapter
+ *	@tp_sram: the firmware image to write
+ *	@size: image size
+ *
+ *	Checks if an adapter's tp sram is compatible with the driver.
+ *	Returns 0 if the versions are compatible, a negative error otherwise.
+ */
+int t3_check_tpsram(struct adapter *adapter, u8 *tp_sram, unsigned int size)
+{
+	u32 csum;
+	unsigned int i;
+	const u32 *p = (const u32 *)tp_sram;
+
+	/* Verify checksum */
+	for (csum = 0, i = 0; i < size / sizeof(csum); i++)
+		csum += ntohl(p[i]);
+	if (csum != 0xffffffff) {
+		CH_ERR(adapter, "corrupted protocol SRAM image, checksum %u\n",
+		       csum);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 enum fw_version_type {
 	FW_VERSION_N3,
 	FW_VERSION_T3
@@ -921,7 +1013,7 @@ static int t3_flash_erase_sectors(struct adapter *adapter, int start, int end)
 /*
  *	t3_load_fw - download firmware
  *	@adapter: the adapter
- *	@fw_data: the firrware image to write
+ *	@fw_data: the firmware image to write
  *	@size: image size
  *
  *	Write the supplied firmware image to the card's serial flash.
@@ -2362,7 +2454,7 @@ static void tp_config(struct adapter *adap, const struct tp_params *p)
 		     F_TCPCHECKSUMOFFLOAD | V_IPTTL(64));
 	t3_write_reg(adap, A_TP_TCP_OPTIONS, V_MTUDEFAULT(576) |
 		     F_MTUENABLE | V_WINDOWSCALEMODE(1) |
-		     V_TIMESTAMPSMODE(1) | V_SACKMODE(1) | V_SACKRX(1));
+		     V_TIMESTAMPSMODE(0) | V_SACKMODE(1) | V_SACKRX(1));
 	t3_write_reg(adap, A_TP_DACK_CONFIG, V_AUTOSTATE3(1) |
 		     V_AUTOSTATE2(1) | V_AUTOSTATE1(0) |
 		     V_BYTETHRESHOLD(16384) | V_MSSTHRESHOLD(2) |
@@ -2371,16 +2463,18 @@ static void tp_config(struct adapter *adap, const struct tp_params *p)
 			 F_IPV6ENABLE | F_NICMODE);
 	t3_write_reg(adap, A_TP_TX_RESOURCE_LIMIT, 0x18141814);
 	t3_write_reg(adap, A_TP_PARA_REG4, 0x5050105);
-	t3_set_reg_field(adap, A_TP_PARA_REG6,
-			 adap->params.rev > 0 ? F_ENABLEESND : F_T3A_ENABLEESND,
-			 0);
+	t3_set_reg_field(adap, A_TP_PARA_REG6, 0,
+			 adap->params.rev > 0 ? F_ENABLEESND :
+			 F_T3A_ENABLEESND);
 
 	t3_set_reg_field(adap, A_TP_PC_CONFIG,
-			 F_ENABLEEPCMDAFULL | F_ENABLEOCSPIFULL,
-			 F_TXDEFERENABLE | F_HEARBEATDACK | F_TXCONGESTIONMODE |
-			 F_RXCONGESTIONMODE);
+			 F_ENABLEEPCMDAFULL,
+			 F_ENABLEOCSPIFULL |F_TXDEFERENABLE | F_HEARBEATDACK |
+			 F_TXCONGESTIONMODE | F_RXCONGESTIONMODE);
 	t3_set_reg_field(adap, A_TP_PC_CONFIG2, F_CHDRAFULL, 0);
-
+	t3_write_reg(adap, A_TP_PROXY_FLOW_CNTL, 1080);
+	t3_write_reg(adap, A_TP_PROXY_FLOW_CNTL, 1000);
+	
 	if (adap->params.rev > 0) {
 		tp_wr_indirect(adap, A_TP_EGRESS_CONFIG, F_REWRITEFORCETOSIZE);
 		t3_set_reg_field(adap, A_TP_PARA_REG3, F_TXPACEAUTO,
@@ -2390,9 +2484,10 @@ static void tp_config(struct adapter *adap, const struct tp_params *p)
 	} else
 		t3_set_reg_field(adap, A_TP_PARA_REG3, 0, F_TXPACEFIXED);
 
-	t3_write_reg(adap, A_TP_TX_MOD_QUEUE_WEIGHT1, 0x12121212);
-	t3_write_reg(adap, A_TP_TX_MOD_QUEUE_WEIGHT0, 0x12121212);
-	t3_write_reg(adap, A_TP_MOD_CHANNEL_WEIGHT, 0x1212);
+	t3_write_reg(adap, A_TP_TX_MOD_QUEUE_WEIGHT1, 0);
+	t3_write_reg(adap, A_TP_TX_MOD_QUEUE_WEIGHT0, 0);
+	t3_write_reg(adap, A_TP_MOD_CHANNEL_WEIGHT, 0);
+	t3_write_reg(adap, A_TP_MOD_RATE_LIMIT, 0xf2200000);
 }
 
 /* Desired TP timer resolution in usec */
@@ -2468,6 +2563,7 @@ int t3_tp_set_coalescing_size(struct adapter *adap, unsigned int size, int psh)
 		val |= F_RXCOALESCEENABLE;
 		if (psh)
 			val |= F_RXCOALESCEPSHEN;
+		size = min(MAX_RX_COALESCING_LEN, size);
 		t3_write_reg(adap, A_TP_PARA_REG2, V_RXCOALESCESIZE(size) |
 			     V_MAXRXDATA(MAX_RX_COALESCING_LEN));
 	}
@@ -2496,11 +2592,11 @@ static void __devinit init_mtus(unsigned short mtus[])
 	 * it can accomodate max size TCP/IP headers when SACK and timestamps
 	 * are enabled and still have at least 8 bytes of payload.
 	 */
-	mtus[0] = 88;
-	mtus[1] = 256;
-	mtus[2] = 512;
-	mtus[3] = 576;
-	mtus[4] = 808;
+	mtus[1] = 88;
+	mtus[1] = 88;
+	mtus[2] = 256;
+	mtus[3] = 512;
+	mtus[4] = 576;
 	mtus[5] = 1024;
 	mtus[6] = 1280;
 	mtus[7] = 1492;
@@ -2682,6 +2778,34 @@ static void ulp_config(struct adapter *adap, const struct tp_params *p)
 	t3_write_reg(adap, A_ULPRX_TDDP_TAGMASK, 0xffffffff);
 }
 
+/**
+ *	t3_set_proto_sram - set the contents of the protocol sram
+ *	@adapter: the adapter
+ *	@data: the protocol image
+ *
+ *	Write the contents of the protocol SRAM.
+ */
+int t3_set_proto_sram(struct adapter *adap, u8 *data)
+{
+	int i;
+	u32 *buf = (u32 *)data;
+
+	for (i = 0; i < PROTO_SRAM_LINES; i++) {
+		t3_write_reg(adap, A_TP_EMBED_OP_FIELD5, cpu_to_be32(*buf++));
+		t3_write_reg(adap, A_TP_EMBED_OP_FIELD4, cpu_to_be32(*buf++));
+		t3_write_reg(adap, A_TP_EMBED_OP_FIELD3, cpu_to_be32(*buf++));
+		t3_write_reg(adap, A_TP_EMBED_OP_FIELD2, cpu_to_be32(*buf++));
+		t3_write_reg(adap, A_TP_EMBED_OP_FIELD1, cpu_to_be32(*buf++));
+		
+		t3_write_reg(adap, A_TP_EMBED_OP_FIELD0, i << 1 | 1 << 31);
+		if (t3_wait_op_done(adap, A_TP_EMBED_OP_FIELD0, 1, 1, 5, 1))
+			return -EIO;
+	}
+	t3_write_reg(adap, A_TP_EMBED_OP_FIELD0, 0);
+
+	return 0;
+}
+
 void t3_config_trace_filter(struct adapter *adapter,
 			    const struct trace_params *tp, int filter_index,
 			    int invert, int enable)
@@ -2802,7 +2926,7 @@ static void init_hw_for_avail_ports(struct adapter *adap, int nports)
 		t3_set_reg_field(adap, A_ULPTX_CONFIG, F_CFG_RR_ARB, 0);
 		t3_write_reg(adap, A_MPS_CFG, F_TPRXPORTEN | F_TPTXPORT0EN |
 			     F_PORT0ACTIVE | F_ENFORCEPKT);
-		t3_write_reg(adap, A_PM1_TX_CFG, 0xc000c000);
+		t3_write_reg(adap, A_PM1_TX_CFG, 0xffffffff);
 	} else {
 		t3_set_reg_field(adap, A_ULPRX_CTL, 0, F_ROUND_ROBIN);
 		t3_set_reg_field(adap, A_ULPTX_CONFIG, 0, F_CFG_RR_ARB);
@@ -3097,7 +3221,7 @@ int t3_init_hw(struct adapter *adapter, u32 fw_params)
 	else
 		t3_set_reg_field(adapter, A_PCIX_CFG, 0, F_CLIDECEN);
 
-	t3_write_reg(adapter, A_PM1_RX_CFG, 0xf000f000);
+	t3_write_reg(adapter, A_PM1_RX_CFG, 0xffffffff);
 	init_hw_for_avail_ports(adapter, adapter->params.nports);
 	t3_sge_init(adapter, &adapter->params.sge);
 
diff --git a/drivers/net/cxgb3/t3cdev.h b/drivers/net/cxgb3/t3cdev.h
index fa4099bc0416..77fcc1a4984e 100644
--- a/drivers/net/cxgb3/t3cdev.h
+++ b/drivers/net/cxgb3/t3cdev.h
@@ -42,9 +42,6 @@
 
 #define T3CNAMSIZ 16
 
-/* Get the t3cdev associated with a net_device */
-#define T3CDEV(netdev) (struct t3cdev *)(netdev->priv)
-
 struct cxgb3_client;
 
 enum t3ctype {
diff --git a/drivers/net/cxgb3/version.h b/drivers/net/cxgb3/version.h
index b112317f033e..eb508bf8022a 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 0
+#define FW_VERSION_MINOR 3
 #define FW_VERSION_MICRO 0
 #endif				/* __CHELSIO_VERSION_H */