diff --git a/MAINTAINERS b/MAINTAINERS
index 06d2087..35e0a64 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3177,8 +3177,8 @@
 S:	Supported
 
 SPIDERNET NETWORK DRIVER for CELL
-P:	Jim Lewis
-M:	jim@jklewis.com
+P:	Linas Vepstas
+M:	linas@austin.ibm.com
 L:	netdev@vger.kernel.org
 S:	Supported
 
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 38ac679..5ff0922 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2245,7 +2245,7 @@
 
 config SPIDER_NET
 	tristate "Spider Gigabit Ethernet driver"
-	depends on PCI && PPC_IBM_CELL_BLADE
+	depends on PCI && (PPC_IBM_CELL_BLADE || PPC_CELLEB)
 	select FW_LOADER
 	help
 	  This driver supports the Gigabit Ethernet chips present on the
diff --git a/drivers/net/chelsio/sge.c b/drivers/net/chelsio/sge.c
index 89a6827..326d4a6 100644
--- a/drivers/net/chelsio/sge.c
+++ b/drivers/net/chelsio/sge.c
@@ -1696,6 +1696,7 @@
 {
 	int work_done;
 	struct adapter *adapter = cookie;
+	struct respQ *Q = &adapter->sge->respQ;
 
 	spin_lock(&adapter->async_lock);
 
diff --git a/drivers/net/cxgb3/adapter.h b/drivers/net/cxgb3/adapter.h
index 5c97a64..80c3d8f 100644
--- a/drivers/net/cxgb3/adapter.h
+++ b/drivers/net/cxgb3/adapter.h
@@ -74,6 +74,11 @@
 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 */
@@ -81,11 +86,13 @@
 	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 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 */
 };
 
 /*
@@ -121,6 +128,8 @@
 	unsigned long empty;	/* # of times queue ran out of credits */
 	unsigned long nomem;	/* # of responses deferred due to no mem */
 	unsigned long unhandled_irqs;	/* # of spurious intrs */
+	unsigned long starved;
+	unsigned long restarted;
 };
 
 struct tx_desc;
diff --git a/drivers/net/cxgb3/cxgb3_ioctl.h b/drivers/net/cxgb3/cxgb3_ioctl.h
index a942818..0a82fcd 100644
--- a/drivers/net/cxgb3/cxgb3_ioctl.h
+++ b/drivers/net/cxgb3/cxgb3_ioctl.h
@@ -36,28 +36,17 @@
  * Ioctl commands specific to this driver.
  */
 enum {
-	CHELSIO_SETREG = 1024,
-	CHELSIO_GETREG,
-	CHELSIO_SETTPI,
-	CHELSIO_GETTPI,
-	CHELSIO_GETMTUTAB,
-	CHELSIO_SETMTUTAB,
-	CHELSIO_GETMTU,
-	CHELSIO_SET_PM,
-	CHELSIO_GET_PM,
-	CHELSIO_GET_TCAM,
-	CHELSIO_SET_TCAM,
-	CHELSIO_GET_TCB,
-	CHELSIO_GET_MEM,
-	CHELSIO_LOAD_FW,
-	CHELSIO_GET_PROTO,
-	CHELSIO_SET_PROTO,
-	CHELSIO_SET_TRACE_FILTER,
-	CHELSIO_SET_QSET_PARAMS,
-	CHELSIO_GET_QSET_PARAMS,
-	CHELSIO_SET_QSET_NUM,
-	CHELSIO_GET_QSET_NUM,
-	CHELSIO_SET_PKTSCHED,
+	CHELSIO_GETMTUTAB 		= 1029,
+	CHELSIO_SETMTUTAB 		= 1030,
+	CHELSIO_SET_PM 			= 1032,
+	CHELSIO_GET_PM			= 1033,
+	CHELSIO_GET_MEM			= 1038,
+	CHELSIO_LOAD_FW			= 1041,
+	CHELSIO_SET_TRACE_FILTER	= 1044,
+	CHELSIO_SET_QSET_PARAMS		= 1045,
+	CHELSIO_GET_QSET_PARAMS		= 1046,
+	CHELSIO_SET_QSET_NUM		= 1047,
+	CHELSIO_GET_QSET_NUM		= 1048,
 };
 
 struct ch_reg {
diff --git a/drivers/net/cxgb3/cxgb3_main.c b/drivers/net/cxgb3/cxgb3_main.c
index 43583ed..7ff834e 100644
--- a/drivers/net/cxgb3/cxgb3_main.c
+++ b/drivers/net/cxgb3/cxgb3_main.c
@@ -434,27 +434,25 @@
 
 static ssize_t attr_show(struct device *d, struct device_attribute *attr,
 			 char *buf,
-			 ssize_t(*format) (struct adapter *, char *))
+			 ssize_t(*format) (struct net_device *, char *))
 {
 	ssize_t len;
-	struct adapter *adap = to_net_dev(d)->priv;
 
 	/* Synchronize with ioctls that may shut down the device */
 	rtnl_lock();
-	len = (*format) (adap, buf);
+	len = (*format) (to_net_dev(d), buf);
 	rtnl_unlock();
 	return len;
 }
 
 static ssize_t attr_store(struct device *d, struct device_attribute *attr,
 			  const char *buf, size_t len,
-			  ssize_t(*set) (struct adapter *, unsigned int),
+			  ssize_t(*set) (struct net_device *, unsigned int),
 			  unsigned int min_val, unsigned int max_val)
 {
 	char *endp;
 	ssize_t ret;
 	unsigned int val;
-	struct adapter *adap = to_net_dev(d)->priv;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -464,7 +462,7 @@
 		return -EINVAL;
 
 	rtnl_lock();
-	ret = (*set) (adap, val);
+	ret = (*set) (to_net_dev(d), val);
 	if (!ret)
 		ret = len;
 	rtnl_unlock();
@@ -472,8 +470,9 @@
 }
 
 #define CXGB3_SHOW(name, val_expr) \
-static ssize_t format_##name(struct adapter *adap, char *buf) \
+static ssize_t format_##name(struct net_device *dev, char *buf) \
 { \
+	struct adapter *adap = dev->priv; \
 	return sprintf(buf, "%u\n", val_expr); \
 } \
 static ssize_t show_##name(struct device *d, struct device_attribute *attr, \
@@ -482,8 +481,10 @@
 	return attr_show(d, attr, buf, format_##name); \
 }
 
-static ssize_t set_nfilters(struct adapter *adap, unsigned int val)
+static ssize_t set_nfilters(struct net_device *dev, unsigned int val)
 {
+	struct adapter *adap = dev->priv;
+
 	if (adap->flags & FULL_INIT_DONE)
 		return -EBUSY;
 	if (val && adap->params.rev == 0)
@@ -500,8 +501,10 @@
 	return attr_store(d, attr, buf, len, set_nfilters, 0, ~0);
 }
 
-static ssize_t set_nservers(struct adapter *adap, unsigned int val)
+static ssize_t set_nservers(struct net_device *dev, unsigned int val)
 {
+	struct adapter *adap = dev->priv;
+
 	if (adap->flags & FULL_INIT_DONE)
 		return -EBUSY;
 	if (val > t3_mc5_size(&adap->mc5) - adap->params.mc5.nfilters)
@@ -1549,32 +1552,6 @@
 		return -EFAULT;
 
 	switch (cmd) {
-	case CHELSIO_SETREG:{
-		struct ch_reg edata;
-
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		if (copy_from_user(&edata, useraddr, sizeof(edata)))
-			return -EFAULT;
-		if ((edata.addr & 3) != 0
-			|| edata.addr >= adapter->mmio_len)
-			return -EINVAL;
-		writel(edata.val, adapter->regs + edata.addr);
-		break;
-	}
-	case CHELSIO_GETREG:{
-		struct ch_reg edata;
-
-		if (copy_from_user(&edata, useraddr, sizeof(edata)))
-			return -EFAULT;
-		if ((edata.addr & 3) != 0
-			|| edata.addr >= adapter->mmio_len)
-			return -EINVAL;
-		edata.val = readl(adapter->regs + edata.addr);
-		if (copy_to_user(useraddr, &edata, sizeof(edata)))
-			return -EFAULT;
-		break;
-	}
 	case CHELSIO_SET_QSET_PARAMS:{
 		int i;
 		struct qset_params *q;
@@ -1838,10 +1815,10 @@
 			return -EINVAL;
 
 		/*
-			* Version scheme:
-			* bits 0..9: chip version
-			* bits 10..15: chip revision
-			*/
+		 * Version scheme:
+		 * bits 0..9: chip version
+		 * bits 10..15: chip revision
+		 */
 		t.version = 3 | (adapter->params.rev << 10);
 		if (copy_to_user(useraddr, &t, sizeof(t)))
 			return -EFAULT;
@@ -1890,20 +1867,6 @@
 						t.trace_rx);
 		break;
 	}
-	case CHELSIO_SET_PKTSCHED:{
-		struct ch_pktsched_params p;
-
-		if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-		if (!adapter->open_device_map)
-				return -EAGAIN;	/* uP and SGE must be running */
-		if (copy_from_user(&p, useraddr, sizeof(p)))
-				return -EFAULT;
-		send_pktsched_cmd(adapter, p.sched, p.idx, p.min, p.max,
-				  p.binding);
-		break;
-			
-	}
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c
index 3f2cf8a..c237834 100644
--- a/drivers/net/cxgb3/sge.c
+++ b/drivers/net/cxgb3/sge.c
@@ -45,9 +45,25 @@
 #define USE_GTS 0
 
 #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_DROP_THRES 16
+/*
+ * Minimum number of freelist entries before we start dropping TUNNEL frames.
+ */
+#define SGE_RX_DROP_THRES 16
 
 /*
  * Period of the Tx buffer reclaim timer.  This timer does not need to run
@@ -85,7 +101,10 @@
 };
 
 struct rx_sw_desc {		/* SW state per Rx descriptor */
-	struct sk_buff *skb;
+	union {
+		struct sk_buff *skb;
+		struct sge_fl_page page;
+	} t;
 	 DECLARE_PCI_UNMAP_ADDR(dma_addr);
 };
 
@@ -105,6 +124,15 @@
 };
 
 /*
+ * Holds unmapping information for Tx packets that need deferred unmapping.
+ * This structure lives at skb->head and must be allocated by callers.
+ */
+struct deferred_unmap_info {
+	struct pci_dev *pdev;
+	dma_addr_t addr[MAX_SKB_FRAGS + 1];
+};
+
+/*
  * Maps a number of flits to the number of Tx descriptors that can hold them.
  * The formula is
  *
@@ -252,10 +280,13 @@
 	struct pci_dev *pdev = adapter->pdev;
 	unsigned int cidx = q->cidx;
 
+	const int need_unmap = need_skb_unmap() &&
+			       q->cntxt_id >= FW_TUNNEL_SGEEC_START;
+
 	d = &q->sdesc[cidx];
 	while (n--) {
 		if (d->skb) {	/* an SGL is present */
-			if (need_skb_unmap())
+			if (need_unmap)
 				unmap_skb(d->skb, q, cidx, pdev);
 			if (d->skb->priority == cidx)
 				kfree_skb(d->skb);
@@ -320,16 +351,27 @@
 
 		pci_unmap_single(pdev, pci_unmap_addr(d, dma_addr),
 				 q->buf_size, PCI_DMA_FROMDEVICE);
-		kfree_skb(d->skb);
-		d->skb = NULL;
+
+		if (q->buf_size != RX_PAGE_SIZE) {
+			kfree_skb(d->t.skb);
+			d->t.skb = NULL;
+		} else {
+			if (d->t.page.frag.page)
+				put_page(d->t.page.frag.page);
+			d->t.page.frag.page = NULL;
+		}
 		if (++cidx == q->size)
 			cidx = 0;
 	}
+
+	if (q->page.frag.page)
+		put_page(q->page.frag.page);
+	q->page.frag.page = NULL;
 }
 
 /**
  *	add_one_rx_buf - add a packet buffer to a free-buffer list
- *	@skb: the buffer to add
+ *	@va: va of the buffer to add
  *	@len: the buffer length
  *	@d: the HW Rx descriptor to write
  *	@sd: the SW Rx descriptor to write
@@ -339,14 +381,13 @@
  *	Add a buffer of the given length to the supplied HW and SW Rx
  *	descriptors.
  */
-static inline void add_one_rx_buf(struct sk_buff *skb, unsigned int len,
+static inline void add_one_rx_buf(unsigned char *va, unsigned int len,
 				  struct rx_desc *d, struct rx_sw_desc *sd,
 				  unsigned int gen, struct pci_dev *pdev)
 {
 	dma_addr_t mapping;
 
-	sd->skb = skb;
-	mapping = pci_map_single(pdev, skb->data, len, PCI_DMA_FROMDEVICE);
+	mapping = pci_map_single(pdev, va, len, PCI_DMA_FROMDEVICE);
 	pci_unmap_addr_set(sd, dma_addr, mapping);
 
 	d->addr_lo = cpu_to_be32(mapping);
@@ -371,14 +412,47 @@
 {
 	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--) {
-		struct sk_buff *skb = alloc_skb(q->buf_size, gfp);
+		unsigned char *va;
 
-		if (!skb)
-			break;
+		if (unlikely(q->buf_size != RX_PAGE_SIZE)) {
+			struct sk_buff *skb = alloc_skb(q->buf_size, gfp);
 
-		add_one_rx_buf(skb, q->buf_size, d, sd, q->gen, adap->pdev);
+			if (!skb) {
+				q->alloc_failed++;
+				break;
+			}
+			va = skb->data;
+			sd->t.skb = skb;
+		} 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);
+				}
+			}
+
+			memcpy(&sd->t, p, sizeof(*p));
+			va = p->va;
+
+			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);
+		}
+
+		add_one_rx_buf(va, q->buf_size, d, sd, q->gen, adap->pdev);
+
 		d++;
 		sd++;
 		if (++q->pidx == q->size) {
@@ -413,7 +487,7 @@
 	struct rx_desc *from = &q->desc[idx];
 	struct rx_desc *to = &q->desc[q->pidx];
 
-	q->sdesc[q->pidx] = q->sdesc[idx];
+	memcpy(&q->sdesc[q->pidx], &q->sdesc[idx], sizeof(struct rx_sw_desc));
 	to->addr_lo = from->addr_lo;	/* already big endian */
 	to->addr_hi = from->addr_hi;	/* likewise */
 	wmb();
@@ -446,7 +520,7 @@
  *	of the SW ring.
  */
 static void *alloc_ring(struct pci_dev *pdev, size_t nelem, size_t elem_size,
-			size_t sw_size, dma_addr_t *phys, void *metadata)
+			size_t sw_size, dma_addr_t * phys, void *metadata)
 {
 	size_t len = nelem * elem_size;
 	void *s = NULL;
@@ -576,61 +650,6 @@
 }
 
 /**
- *	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);
-
-	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_imm_packet - return the next ingress packet buffer from a response
  *	@resp: the response descriptor containing the packet data
  *
@@ -1227,6 +1246,50 @@
 }
 
 /**
+ *	deferred_unmap_destructor - unmap a packet when it is freed
+ *	@skb: the packet
+ *
+ *	This is the packet destructor used for Tx packets that need to remain
+ *	mapped until they are freed rather than until their Tx descriptors are
+ *	freed.
+ */
+static void deferred_unmap_destructor(struct sk_buff *skb)
+{
+	int i;
+	const dma_addr_t *p;
+	const struct skb_shared_info *si;
+	const struct deferred_unmap_info *dui;
+	const struct unmap_info *ui = (struct unmap_info *)skb->cb;
+
+	dui = (struct deferred_unmap_info *)skb->head;
+	p = dui->addr;
+
+	if (ui->len)
+		pci_unmap_single(dui->pdev, *p++, ui->len, PCI_DMA_TODEVICE);
+
+	si = skb_shinfo(skb);
+	for (i = 0; i < si->nr_frags; i++)
+		pci_unmap_page(dui->pdev, *p++, si->frags[i].size,
+			       PCI_DMA_TODEVICE);
+}
+
+static void setup_deferred_unmapping(struct sk_buff *skb, struct pci_dev *pdev,
+				     const struct sg_ent *sgl, int sgl_flits)
+{
+	dma_addr_t *p;
+	struct deferred_unmap_info *dui;
+
+	dui = (struct deferred_unmap_info *)skb->head;
+	dui->pdev = pdev;
+	for (p = dui->addr; sgl_flits >= 3; sgl++, sgl_flits -= 3) {
+		*p++ = be64_to_cpu(sgl->addr[0]);
+		*p++ = be64_to_cpu(sgl->addr[1]);
+	}
+	if (sgl_flits)
+		*p = be64_to_cpu(sgl->addr[0]);
+}
+
+/**
  *	write_ofld_wr - write an offload work request
  *	@adap: the adapter
  *	@skb: the packet to send
@@ -1262,8 +1325,11 @@
 	sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
 	sgl_flits = make_sgl(skb, sgp, skb->h.raw, skb->tail - skb->h.raw,
 			     adap->pdev);
-	if (need_skb_unmap())
+	if (need_skb_unmap()) {
+		setup_deferred_unmapping(skb, adap->pdev, sgp, sgl_flits);
+		skb->destructor = deferred_unmap_destructor;
 		((struct unmap_info *)skb->cb)->len = skb->tail - skb->h.raw;
+	}
 
 	write_wr_hdr_sgl(ndesc, skb, d, pidx, q, sgl, flits, sgl_flits,
 			 gen, from->wr_hi, from->wr_lo);
@@ -1617,7 +1683,6 @@
 	struct cpl_rx_pkt *p = (struct cpl_rx_pkt *)(skb->data + pad);
 	struct port_info *pi;
 
-	rq->eth_pkts++;
 	skb_pull(skb, sizeof(*p) + pad);
 	skb->dev = adap->port[p->iff];
 	skb->dev->last_rx = jiffies;
@@ -1645,6 +1710,85 @@
 		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) {
+		memcpy(skb->data, p->va, len);
+		skb->tail += len;
+		put_page(p->frag.page);
+	} else {
+		memcpy(skb->data, 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);
+			memcpy(skb->data, sd->t.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
@@ -1767,7 +1911,7 @@
 	q->next_holdoff = q->holdoff_tmr;
 
 	while (likely(budget_left && is_new_response(r, q))) {
-		int eth, ethpad = 0;
+		int eth, ethpad = 2;
 		struct sk_buff *skb = NULL;
 		u32 len, flags = ntohl(r->flags);
 		u32 rss_hi = *(const u32 *)r, rss_lo = r->rss_hdr.rss_hash_val;
@@ -1794,18 +1938,56 @@
 				break;
 			}
 			q->imm_data++;
+			ethpad = 0;
 		} else if ((len = ntohl(r->len_cq)) != 0) {
-			struct sge_fl *fl;
+			struct sge_fl *fl =
+			    (len & F_RSPD_FLQ) ? &qs->fl[1] : &qs->fl[0];
 
-			fl = (len & F_RSPD_FLQ) ? &qs->fl[1] : &qs->fl[0];
-			fl->credits--;
-			skb = get_packet(adap, fl, G_RSPD_LEN(len),
-					 eth ? SGE_RX_DROP_THRES : 0);
-			if (!skb)
-				q->rx_drops++;
-			else if (r->rss_hdr.opcode == CPL_TRACE_PKT)
-				__skb_pull(skb, 2);
-			ethpad = 2;
+			if (fl->buf_size == RX_PAGE_SIZE) {
+				struct rx_sw_desc *sd = &fl->sdesc[fl->cidx];
+				struct sge_fl_page *p = &sd->t.page;
+
+				prefetch(p->va);
+				prefetch(p->va + L1_CACHE_BYTES);
+
+				__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(adap, fl, G_RSPD_LEN(len),
+						 eth ? SGE_RX_DROP_THRES : 0);
+			}
+
 			if (++fl->cidx == fl->size)
 				fl->cidx = 0;
 		} else
@@ -1829,18 +2011,23 @@
 			q->credits = 0;
 		}
 
-		if (likely(skb != NULL)) {
+		if (skb) {
+			/* Preserve the RSS info in csum & priority */
+			skb->csum = rss_hi;
+			skb->priority = rss_lo;
+
 			if (eth)
 				rx_eth(adap, q, skb, ethpad);
 			else {
-				/* 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);
+				if (unlikely(r->rss_hdr.opcode ==
+					     CPL_TRACE_PKT))
+					__skb_pull(skb, ethpad);
+
+				ngathered = rx_offload(&adap->tdev, q,
+						       skb, offload_skbs,
+						       ngathered);
 			}
 		}
-
 		--budget_left;
 	}
 
@@ -2320,10 +2507,23 @@
 	    &adap->sge.qs[0].rspq.lock;
 	if (spin_trylock_irq(lock)) {
 		if (!napi_is_scheduled(qs->netdev)) {
+			u32 status = t3_read_reg(adap, A_SG_RSPQ_FL_STATUS);
+
 			if (qs->fl[0].credits < qs->fl[0].size)
 				__refill_fl(adap, &qs->fl[0]);
 			if (qs->fl[1].credits < qs->fl[1].size)
 				__refill_fl(adap, &qs->fl[1]);
+
+			if (status & (1 << qs->rspq.cntxt_id)) {
+				qs->rspq.starved++;
+				if (qs->rspq.credits) {
+					refill_rspq(adap, &qs->rspq, 1);
+					qs->rspq.credits--;
+					qs->rspq.restarted++;
+					t3_write_reg(adap, A_SG_RSPQ_FL_STATUS,
+						     1 << qs->rspq.cntxt_id);
+				}
+			}
 		}
 		spin_unlock_irq(lock);
 	}
@@ -2432,13 +2632,21 @@
 	    flits_to_desc(sgl_len(MAX_SKB_FRAGS + 1) + 3);
 
 	if (ntxq == 1) {
+#ifdef USE_RX_PAGE
+		q->fl[0].buf_size = RX_PAGE_SIZE;
+#else
 		q->fl[0].buf_size = SGE_RX_SM_BUF_SIZE + 2 +
 		    sizeof(struct cpl_rx_pkt);
+#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));
 	}
@@ -2632,7 +2840,7 @@
 		q->polling = adap->params.rev > 0;
 		q->coalesce_usecs = 5;
 		q->rspq_size = 1024;
-		q->fl_size = 4096;
+		q->fl_size = 1024;
 		q->jumbo_size = 512;
 		q->txq_size[TXQ_ETH] = 1024;
 		q->txq_size[TXQ_OFLD] = 1024;
diff --git a/drivers/net/cxgb3/t3_hw.c b/drivers/net/cxgb3/t3_hw.c
index 365a7f5..eaa7a2e 100644
--- a/drivers/net/cxgb3/t3_hw.c
+++ b/drivers/net/cxgb3/t3_hw.c
@@ -884,11 +884,13 @@
 	major = G_FW_VERSION_MAJOR(vers);
 	minor = G_FW_VERSION_MINOR(vers);
 
-	if (type == FW_VERSION_T3 && major == 3 && minor == 1)
+	if (type == FW_VERSION_T3 && major == FW_VERSION_MAJOR &&
+	    minor == FW_VERSION_MINOR)
 		return 0;
 
 	CH_ERR(adapter, "found wrong FW version(%u.%u), "
-	       "driver needs version 3.1\n", major, minor);
+	       "driver needs version %u.%u\n", major, minor,
+	       FW_VERSION_MAJOR, FW_VERSION_MINOR);
 	return -EINVAL;
 }
 
diff --git a/drivers/net/cxgb3/version.h b/drivers/net/cxgb3/version.h
index 2b67dd5..782a6cf 100644
--- a/drivers/net/cxgb3/version.h
+++ b/drivers/net/cxgb3/version.h
@@ -36,4 +36,6 @@
 #define DRV_NAME "cxgb3"
 /* Driver version */
 #define DRV_VERSION "1.0"
+#define FW_VERSION_MAJOR 3
+#define FW_VERSION_MINOR 2
 #endif				/* __CHELSIO_VERSION_H */
diff --git a/drivers/net/de600.c b/drivers/net/de600.c
index 8396e41..e547ce1 100644
--- a/drivers/net/de600.c
+++ b/drivers/net/de600.c
@@ -38,12 +38,6 @@
 /* Add more time here if your adapter won't work OK: */
 #define DE600_SLOW_DOWN	udelay(delay_time)
 
- /*
- * If you still have trouble reading/writing to the adapter,
- * modify the following "#define": (see <asm/io.h> for more info)
-#define REALLY_SLOW_IO
- */
-
 /* use 0 for production, 1 for verification, >2 for debug */
 #ifdef DE600_DEBUG
 #define PRINTK(x) if (de600_debug >= 2) printk x
diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c
index a363148..46e1697 100644
--- a/drivers/net/forcedeth.c
+++ b/drivers/net/forcedeth.c
@@ -839,7 +839,7 @@
 	NV_MSIX_INT_DISABLED,
 	NV_MSIX_INT_ENABLED
 };
-static int msix = NV_MSIX_INT_ENABLED;
+static int msix = NV_MSIX_INT_DISABLED;
 
 /*
  * DMA 64bit
@@ -3104,13 +3104,17 @@
 	struct fe_priv *np = netdev_priv(dev);
 	u8 __iomem *base = get_hwbase(dev);
 	unsigned long flags;
+	int retcode;
 
-	if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2)
+	if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) {
 		pkts = nv_rx_process(dev, limit);
-	else
+		retcode = nv_alloc_rx(dev);
+	} else {
 		pkts = nv_rx_process_optimized(dev, limit);
+		retcode = nv_alloc_rx_optimized(dev);
+	}
 
-	if (nv_alloc_rx(dev)) {
+	if (retcode) {
 		spin_lock_irqsave(&np->lock, flags);
 		if (!np->in_shutdown)
 			mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
@@ -5370,19 +5374,19 @@
 	},
 	{	/* MCP65 Ethernet Controller */
 		PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_20),
-		.driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+		.driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
 	},
 	{	/* MCP65 Ethernet Controller */
 		PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_21),
-		.driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+		.driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
 	},
 	{	/* MCP65 Ethernet Controller */
 		PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_22),
-		.driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+		.driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
 	},
 	{	/* MCP65 Ethernet Controller */
 		PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_23),
-		.driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_CHECKSUM|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
+		.driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_LARGEDESC|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT,
 	},
 	{	/* MCP67 Ethernet Controller */
 		PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_24),
diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c
index d98e53e..3e045a6 100644
--- a/drivers/net/mv643xx_eth.c
+++ b/drivers/net/mv643xx_eth.c
@@ -147,13 +147,13 @@
 	int unaligned;
 
 	while (mp->rx_desc_count < mp->rx_ring_size) {
-		skb = dev_alloc_skb(ETH_RX_SKB_SIZE + ETH_DMA_ALIGN);
+		skb = dev_alloc_skb(ETH_RX_SKB_SIZE + dma_get_cache_alignment());
 		if (!skb)
 			break;
 		mp->rx_desc_count++;
-		unaligned = (u32)skb->data & (ETH_DMA_ALIGN - 1);
+		unaligned = (u32)skb->data & (dma_get_cache_alignment() - 1);
 		if (unaligned)
-			skb_reserve(skb, ETH_DMA_ALIGN - unaligned);
+			skb_reserve(skb, dma_get_cache_alignment() - unaligned);
 		pkt_info.cmd_sts = ETH_RX_ENABLE_INTERRUPT;
 		pkt_info.byte_cnt = ETH_RX_SKB_SIZE;
 		pkt_info.buf_ptr = dma_map_single(NULL, skb->data,
diff --git a/drivers/net/mv643xx_eth.h b/drivers/net/mv643xx_eth.h
index 33c5faf..7cb0a41 100644
--- a/drivers/net/mv643xx_eth.h
+++ b/drivers/net/mv643xx_eth.h
@@ -42,17 +42,6 @@
 #define MAX_DESCS_PER_SKB	1
 #endif
 
-/*
- * The MV643XX HW requires 8-byte alignment.  However, when I/O
- * is non-cache-coherent, we need to ensure that the I/O buffers
- * we use don't share cache lines with other data.
- */
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_NOT_COHERENT_CACHE)
-#define ETH_DMA_ALIGN		L1_CACHE_BYTES
-#else
-#define ETH_DMA_ALIGN		8
-#endif
-
 #define ETH_VLAN_HLEN		4
 #define ETH_FCS_LEN		4
 #define ETH_HW_IP_ALIGN		2		/* hw aligns IP header */
diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c
index 030924f..954842e 100644
--- a/drivers/net/myri10ge/myri10ge.c
+++ b/drivers/net/myri10ge/myri10ge.c
@@ -195,6 +195,10 @@
 	char *fw_name;
 	char eeprom_strings[MYRI10GE_EEPROM_STRINGS_SIZE];
 	char fw_version[128];
+	int fw_ver_major;
+	int fw_ver_minor;
+	int fw_ver_tiny;
+	int adopted_rx_filter_bug;
 	u8 mac_addr[6];		/* eeprom mac address */
 	unsigned long serial_number;
 	int vendor_specific_offset;
@@ -447,7 +451,6 @@
 			   struct mcp_gen_header *hdr)
 {
 	struct device *dev = &mgp->pdev->dev;
-	int major, minor;
 
 	/* check firmware type */
 	if (ntohl(hdr->mcp_type) != MCP_TYPE_ETH) {
@@ -458,9 +461,11 @@
 	/* save firmware version for ethtool */
 	strncpy(mgp->fw_version, hdr->version, sizeof(mgp->fw_version));
 
-	sscanf(mgp->fw_version, "%d.%d", &major, &minor);
+	sscanf(mgp->fw_version, "%d.%d.%d", &mgp->fw_ver_major,
+	       &mgp->fw_ver_minor, &mgp->fw_ver_tiny);
 
-	if (!(major == MXGEFW_VERSION_MAJOR && minor == MXGEFW_VERSION_MINOR)) {
+	if (!(mgp->fw_ver_major == MXGEFW_VERSION_MAJOR
+	      && mgp->fw_ver_minor == MXGEFW_VERSION_MINOR)) {
 		dev_err(dev, "Found firmware version %s\n", mgp->fw_version);
 		dev_err(dev, "Driver needs %d.%d\n", MXGEFW_VERSION_MAJOR,
 			MXGEFW_VERSION_MINOR);
@@ -561,6 +566,18 @@
 	memcpy_fromio(hdr, mgp->sram + hdr_offset, bytes);
 	status = myri10ge_validate_firmware(mgp, hdr);
 	kfree(hdr);
+
+	/* check to see if adopted firmware has bug where adopting
+	 * it will cause broadcasts to be filtered unless the NIC
+	 * is kept in ALLMULTI mode */
+	if (mgp->fw_ver_major == 1 && mgp->fw_ver_minor == 4 &&
+	    mgp->fw_ver_tiny >= 4 && mgp->fw_ver_tiny <= 11) {
+		mgp->adopted_rx_filter_bug = 1;
+		dev_warn(dev, "Adopting fw %d.%d.%d: "
+			 "working around rx filter bug\n",
+			 mgp->fw_ver_major, mgp->fw_ver_minor,
+			 mgp->fw_ver_tiny);
+	}
 	return status;
 }
 
@@ -794,6 +811,8 @@
 	status = myri10ge_update_mac_address(mgp, mgp->dev->dev_addr);
 	myri10ge_change_promisc(mgp, 0, 0);
 	myri10ge_change_pause(mgp, mgp->pause);
+	if (mgp->adopted_rx_filter_bug)
+		(void)myri10ge_send_cmd(mgp, MXGEFW_ENABLE_ALLMULTI, &cmd, 1);
 	return status;
 }
 
@@ -2239,7 +2258,7 @@
 	myri10ge_change_promisc(mgp, dev->flags & IFF_PROMISC, 1);
 
 	/* This firmware is known to not support multicast */
-	if (!mgp->fw_multicast_support)
+	if (!mgp->fw_multicast_support || mgp->adopted_rx_filter_bug)
 		return;
 
 	/* Disable multicast filtering */
diff --git a/drivers/net/natsemi.c b/drivers/net/natsemi.c
index adf29dd..5c57433 100644
--- a/drivers/net/natsemi.c
+++ b/drivers/net/natsemi.c
@@ -260,7 +260,7 @@
 
 static const struct pci_device_id natsemi_pci_tbl[] __devinitdata = {
 	{ PCI_VENDOR_ID_NS, 0x0020, 0x12d9,     0x000c,     0, 0, 0 },
-	{ PCI_VENDOR_ID_NS, 0x0020, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
+	{ PCI_VENDOR_ID_NS, 0x0020, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 1 },
 	{ }	/* terminate list */
 };
 MODULE_DEVICE_TABLE(pci, natsemi_pci_tbl);
diff --git a/drivers/net/netxen/netxen_nic_hw.c b/drivers/net/netxen/netxen_nic_hw.c
index 7195af3..deec796 100644
--- a/drivers/net/netxen/netxen_nic_hw.c
+++ b/drivers/net/netxen/netxen_nic_hw.c
@@ -242,10 +242,11 @@
 	adapter->cmd_consumer = (uint32_t *) (((char *)addr) +
 					      sizeof(struct netxen_ring_ctx));
 
-	addr = pci_alloc_consistent(adapter->ahw.pdev,
-				    sizeof(struct cmd_desc_type0) *
-				    adapter->max_tx_desc_count,
-				    (dma_addr_t *) & hw->cmd_desc_phys_addr);
+	addr = netxen_alloc(adapter->ahw.pdev,
+			    sizeof(struct cmd_desc_type0) *
+			    adapter->max_tx_desc_count,
+			    (dma_addr_t *) & hw->cmd_desc_phys_addr,
+			    &adapter->ahw.cmd_desc_pdev);
 	printk("cmd_desc_phys_addr: 0x%llx\n", (u64) hw->cmd_desc_phys_addr);
 
 	if (addr == NULL) {
diff --git a/drivers/net/netxen/netxen_nic_init.c b/drivers/net/netxen/netxen_nic_init.c
index 2f32436..2f96570 100644
--- a/drivers/net/netxen/netxen_nic_init.c
+++ b/drivers/net/netxen/netxen_nic_init.c
@@ -499,7 +499,10 @@
 		while(1) {
 			int data1;
 
-			do_rom_fast_read(adapter, addridx, &data1);
+			ret = do_rom_fast_read(adapter, addridx, &data1);
+			if (ret < 0)
+				return ret;
+
 			if (data1 == data)
 				break;
 
diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c
index 225ff55..1bf3d49 100644
--- a/drivers/net/netxen/netxen_nic_main.c
+++ b/drivers/net/netxen/netxen_nic_main.c
@@ -525,6 +525,8 @@
 	if (adapter == NULL)
 		return;
 
+	if (adapter->irq)
+		free_irq(adapter->irq, adapter);
 	netxen_nic_stop_all_ports(adapter);
 	/* leave the hw in the same state as reboot */
 	netxen_pinit_from_rom(adapter, 0);
@@ -672,8 +674,6 @@
 
 	if (!adapter->active_ports) {
 		netxen_nic_disable_int(adapter);
-		if (adapter->irq)
-			free_irq(adapter->irq, adapter);
 		cmd_buff = adapter->cmd_buf_arr;
 		for (i = 0; i < adapter->max_tx_desc_count; i++) {
 			buffrag = cmd_buff->frag_array;
@@ -1155,8 +1155,8 @@
 	/*
 	 * Wait for some time to allow the dma to drain, if any.
 	 */
-	destroy_workqueue(netxen_workq);
 	pci_unregister_driver(&netxen_driver);
+	destroy_workqueue(netxen_workq);
 }
 
 module_exit(netxen_exit_module);
diff --git a/drivers/net/ni52.c b/drivers/net/ni52.c
index 196993a..a6f4b24 100644
--- a/drivers/net/ni52.c
+++ b/drivers/net/ni52.c
@@ -104,8 +104,6 @@
 static int rfdadd;	/* rfdadd=1 may be better for 8K MEM cards */
 static int fifo=0x8;	/* don't change */
 
-/* #define REALLY_SLOW_IO */
-
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/drivers/net/qla3xxx.c b/drivers/net/qla3xxx.c
index a142cdf..3a14d19 100755
--- a/drivers/net/qla3xxx.c
+++ b/drivers/net/qla3xxx.c
@@ -39,7 +39,7 @@
 
 #define DRV_NAME  	"qla3xxx"
 #define DRV_STRING 	"QLogic ISP3XXX Network Driver"
-#define DRV_VERSION	"v2.02.00-k36"
+#define DRV_VERSION	"v2.03.00-k3"
 #define PFX		DRV_NAME " "
 
 static const char ql3xxx_driver_name[] = DRV_NAME;
@@ -276,7 +276,8 @@
 static void ql_release_to_lrg_buf_free_list(struct ql3_adapter *qdev,
 					    struct ql_rcv_buf_cb *lrg_buf_cb)
 {
-	u64 map;
+	dma_addr_t map;
+	int err;
 	lrg_buf_cb->next = NULL;
 
 	if (qdev->lrg_buf_free_tail == NULL) {	/* The list is empty  */
@@ -287,9 +288,10 @@
 	}
 
 	if (!lrg_buf_cb->skb) {
-		lrg_buf_cb->skb = dev_alloc_skb(qdev->lrg_buffer_len);
+		lrg_buf_cb->skb = netdev_alloc_skb(qdev->ndev,
+						   qdev->lrg_buffer_len);
 		if (unlikely(!lrg_buf_cb->skb)) {
-			printk(KERN_ERR PFX "%s: failed dev_alloc_skb().\n",
+			printk(KERN_ERR PFX "%s: failed netdev_alloc_skb().\n",
 			       qdev->ndev->name);
 			qdev->lrg_buf_skb_check++;
 		} else {
@@ -303,6 +305,17 @@
 					     qdev->lrg_buffer_len -
 					     QL_HEADER_SPACE,
 					     PCI_DMA_FROMDEVICE);
+			err = pci_dma_mapping_error(map);
+			if(err) {
+				printk(KERN_ERR "%s: PCI mapping failed with error: %d\n", 
+				       qdev->ndev->name, err);
+				dev_kfree_skb(lrg_buf_cb->skb);
+				lrg_buf_cb->skb = NULL;
+
+				qdev->lrg_buf_skb_check++;
+				return;
+			}
+
 			lrg_buf_cb->buf_phy_addr_low =
 			    cpu_to_le32(LS_64BITS(map));
 			lrg_buf_cb->buf_phy_addr_high =
@@ -1387,6 +1400,8 @@
 			printk(KERN_INFO PFX
 			       "%s: Reset in progress, skip processing link "
 			       "state.\n", qdev->ndev->name);
+
+		spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);		
 		return;
 	}
 
@@ -1518,8 +1533,10 @@
 	spin_lock_irqsave(&qdev->hw_lock, hw_flags);
 	if(ql_sem_spinlock(qdev, QL_PHY_GIO_SEM_MASK,
 		(QL_RESOURCE_BITS_BASE_CODE | (qdev->mac_index) *
-			 2) << 7))
+			 2) << 7)) {
+		spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
 		return 0;
+	}
 	status = ql_is_auto_cfg(qdev);
 	ql_sem_unlock(qdev, QL_PHY_GIO_SEM_MASK);
 	spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
@@ -1533,8 +1550,10 @@
 	spin_lock_irqsave(&qdev->hw_lock, hw_flags);
 	if(ql_sem_spinlock(qdev, QL_PHY_GIO_SEM_MASK,
 		(QL_RESOURCE_BITS_BASE_CODE | (qdev->mac_index) *
-			 2) << 7))
+			 2) << 7)) {
+		spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
 		return 0;
+	}
 	status = ql_get_link_speed(qdev);
 	ql_sem_unlock(qdev, QL_PHY_GIO_SEM_MASK);
 	spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
@@ -1548,8 +1567,10 @@
 	spin_lock_irqsave(&qdev->hw_lock, hw_flags);
 	if(ql_sem_spinlock(qdev, QL_PHY_GIO_SEM_MASK,
 		(QL_RESOURCE_BITS_BASE_CODE | (qdev->mac_index) *
-			 2) << 7))
+			 2) << 7)) {
+		spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
 		return 0;
+	}
 	status = ql_is_link_full_dup(qdev);
 	ql_sem_unlock(qdev, QL_PHY_GIO_SEM_MASK);
 	spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
@@ -1615,14 +1636,16 @@
 static int ql_populate_free_queue(struct ql3_adapter *qdev)
 {
 	struct ql_rcv_buf_cb *lrg_buf_cb = qdev->lrg_buf_free_head;
-	u64 map;
+	dma_addr_t map;
+	int err;
 
 	while (lrg_buf_cb) {
 		if (!lrg_buf_cb->skb) {
-			lrg_buf_cb->skb = dev_alloc_skb(qdev->lrg_buffer_len);
+			lrg_buf_cb->skb = netdev_alloc_skb(qdev->ndev,
+							   qdev->lrg_buffer_len);
 			if (unlikely(!lrg_buf_cb->skb)) {
 				printk(KERN_DEBUG PFX
-				       "%s: Failed dev_alloc_skb().\n",
+				       "%s: Failed netdev_alloc_skb().\n",
 				       qdev->ndev->name);
 				break;
 			} else {
@@ -1636,6 +1659,17 @@
 						     qdev->lrg_buffer_len -
 						     QL_HEADER_SPACE,
 						     PCI_DMA_FROMDEVICE);
+
+				err = pci_dma_mapping_error(map);
+				if(err) {
+					printk(KERN_ERR "%s: PCI mapping failed with error: %d\n", 
+					       qdev->ndev->name, err);
+					dev_kfree_skb(lrg_buf_cb->skb);
+					lrg_buf_cb->skb = NULL;
+					break;
+				}
+
+
 				lrg_buf_cb->buf_phy_addr_low =
 				    cpu_to_le32(LS_64BITS(map));
 				lrg_buf_cb->buf_phy_addr_high =
@@ -1690,11 +1724,11 @@
 
 			qdev->lrg_buf_q_producer_index++;
 
-			if (qdev->lrg_buf_q_producer_index == NUM_LBUFQ_ENTRIES)
+			if (qdev->lrg_buf_q_producer_index == qdev->num_lbufq_entries)
 				qdev->lrg_buf_q_producer_index = 0;
 
 			if (qdev->lrg_buf_q_producer_index ==
-			    (NUM_LBUFQ_ENTRIES - 1)) {
+			    (qdev->num_lbufq_entries - 1)) {
 				lrg_buf_q_ele = qdev->lrg_buf_q_virt_addr;
 			}
 		}
@@ -1713,8 +1747,31 @@
 {
 	struct ql_tx_buf_cb *tx_cb;
 	int i;
+	int retval = 0;
 
+	if(mac_rsp->flags & OB_MAC_IOCB_RSP_S) {
+		printk(KERN_WARNING "Frame short but, frame was padded and sent.\n");
+	}
+	
 	tx_cb = &qdev->tx_buf[mac_rsp->transaction_id];
+
+	/*  Check the transmit response flags for any errors */
+	if(mac_rsp->flags & OB_MAC_IOCB_RSP_S) {
+		printk(KERN_ERR "Frame too short to be legal, frame not sent.\n");
+
+		qdev->stats.tx_errors++;
+		retval = -EIO;
+		goto frame_not_sent;
+	}
+
+	if(tx_cb->seg_count == 0) {
+		printk(KERN_ERR "tx_cb->seg_count == 0: %d\n", mac_rsp->transaction_id);
+
+		qdev->stats.tx_errors++;
+		retval = -EIO;
+		goto invalid_seg_count;
+	}
+
 	pci_unmap_single(qdev->pdev,
 			 pci_unmap_addr(&tx_cb->map[0], mapaddr),
 			 pci_unmap_len(&tx_cb->map[0], maplen),
@@ -1731,11 +1788,32 @@
 	}
 	qdev->stats.tx_packets++;
 	qdev->stats.tx_bytes += tx_cb->skb->len;
+
+frame_not_sent:
 	dev_kfree_skb_irq(tx_cb->skb);
 	tx_cb->skb = NULL;
+
+invalid_seg_count:
 	atomic_inc(&qdev->tx_count);
 }
 
+void ql_get_sbuf(struct ql3_adapter *qdev)
+{
+	if (++qdev->small_buf_index == NUM_SMALL_BUFFERS)
+		qdev->small_buf_index = 0;
+	qdev->small_buf_release_cnt++;
+}
+
+struct ql_rcv_buf_cb *ql_get_lbuf(struct ql3_adapter *qdev)
+{
+	struct ql_rcv_buf_cb *lrg_buf_cb = NULL;
+	lrg_buf_cb = &qdev->lrg_buf[qdev->lrg_buf_index];
+	qdev->lrg_buf_release_cnt++;
+	if (++qdev->lrg_buf_index == qdev->num_large_buffers)
+		qdev->lrg_buf_index = 0;
+	return(lrg_buf_cb);
+}
+
 /*
  * The difference between 3022 and 3032 for inbound completions:
  * 3022 uses two buffers per completion.  The first buffer contains 
@@ -1751,47 +1829,21 @@
 static void ql_process_mac_rx_intr(struct ql3_adapter *qdev,
 				   struct ib_mac_iocb_rsp *ib_mac_rsp_ptr)
 {
-	long int offset;
-	u32 lrg_buf_phy_addr_low = 0;
 	struct ql_rcv_buf_cb *lrg_buf_cb1 = NULL;
 	struct ql_rcv_buf_cb *lrg_buf_cb2 = NULL;
-	u32 *curr_ial_ptr;
 	struct sk_buff *skb;
 	u16 length = le16_to_cpu(ib_mac_rsp_ptr->length);
 
 	/*
 	 * Get the inbound address list (small buffer).
 	 */
-	offset = qdev->small_buf_index * QL_SMALL_BUFFER_SIZE;
-	if (++qdev->small_buf_index == NUM_SMALL_BUFFERS)
-		qdev->small_buf_index = 0;
+	ql_get_sbuf(qdev);
 
-	curr_ial_ptr = (u32 *) (qdev->small_buf_virt_addr + offset);
-	qdev->last_rsp_offset = qdev->small_buf_phy_addr_low + offset;
-	qdev->small_buf_release_cnt++;
-
-	if (qdev->device_id == QL3022_DEVICE_ID) {
-		/* start of first buffer (3022 only) */
-		lrg_buf_phy_addr_low = le32_to_cpu(*curr_ial_ptr);
-		lrg_buf_cb1 = &qdev->lrg_buf[qdev->lrg_buf_index];
-		qdev->lrg_buf_release_cnt++;
-		if (++qdev->lrg_buf_index == NUM_LARGE_BUFFERS) {
-			qdev->lrg_buf_index = 0;
-		}
-		curr_ial_ptr++;	/* 64-bit pointers require two incs. */
-		curr_ial_ptr++;
-	}
+	if (qdev->device_id == QL3022_DEVICE_ID)
+		lrg_buf_cb1 = ql_get_lbuf(qdev);
 
 	/* start of second buffer */
-	lrg_buf_phy_addr_low = le32_to_cpu(*curr_ial_ptr);
-	lrg_buf_cb2 = &qdev->lrg_buf[qdev->lrg_buf_index];
-
-	/*
-	 * Second buffer gets sent up the stack.
-	 */
-	qdev->lrg_buf_release_cnt++;
-	if (++qdev->lrg_buf_index == NUM_LARGE_BUFFERS)
-		qdev->lrg_buf_index = 0;
+	lrg_buf_cb2 = ql_get_lbuf(qdev);
 	skb = lrg_buf_cb2->skb;
 
 	qdev->stats.rx_packets++;
@@ -1819,11 +1871,8 @@
 static void ql_process_macip_rx_intr(struct ql3_adapter *qdev,
 				     struct ib_ip_iocb_rsp *ib_ip_rsp_ptr)
 {
-	long int offset;
-	u32 lrg_buf_phy_addr_low = 0;
 	struct ql_rcv_buf_cb *lrg_buf_cb1 = NULL;
 	struct ql_rcv_buf_cb *lrg_buf_cb2 = NULL;
-	u32 *curr_ial_ptr;
 	struct sk_buff *skb1 = NULL, *skb2;
 	struct net_device *ndev = qdev->ndev;
 	u16 length = le16_to_cpu(ib_ip_rsp_ptr->length);
@@ -1833,35 +1882,20 @@
 	 * Get the inbound address list (small buffer).
 	 */
 
-	offset = qdev->small_buf_index * QL_SMALL_BUFFER_SIZE;
-	if (++qdev->small_buf_index == NUM_SMALL_BUFFERS)
-		qdev->small_buf_index = 0;
-	curr_ial_ptr = (u32 *) (qdev->small_buf_virt_addr + offset);
-	qdev->last_rsp_offset = qdev->small_buf_phy_addr_low + offset;
-	qdev->small_buf_release_cnt++;
+	ql_get_sbuf(qdev);
 
 	if (qdev->device_id == QL3022_DEVICE_ID) {
 		/* start of first buffer on 3022 */
-		lrg_buf_phy_addr_low = le32_to_cpu(*curr_ial_ptr);
-		lrg_buf_cb1 = &qdev->lrg_buf[qdev->lrg_buf_index];
-		qdev->lrg_buf_release_cnt++;
-		if (++qdev->lrg_buf_index == NUM_LARGE_BUFFERS)
-			qdev->lrg_buf_index = 0;
+		lrg_buf_cb1 = ql_get_lbuf(qdev);
 		skb1 = lrg_buf_cb1->skb;
-		curr_ial_ptr++;	/* 64-bit pointers require two incs. */
-		curr_ial_ptr++;
 		size = ETH_HLEN;
 		if (*((u16 *) skb1->data) != 0xFFFF)
 			size += VLAN_ETH_HLEN - ETH_HLEN;
 	}
 
 	/* start of second buffer */
-	lrg_buf_phy_addr_low = le32_to_cpu(*curr_ial_ptr);
-	lrg_buf_cb2 = &qdev->lrg_buf[qdev->lrg_buf_index];
+	lrg_buf_cb2 = ql_get_lbuf(qdev);
 	skb2 = lrg_buf_cb2->skb;
-	qdev->lrg_buf_release_cnt++;
-	if (++qdev->lrg_buf_index == NUM_LARGE_BUFFERS)
-		qdev->lrg_buf_index = 0;
 
 	skb_put(skb2, length);	/* Just the second buffer length here. */
 	pci_unmap_single(qdev->pdev,
@@ -1914,10 +1948,13 @@
 	struct net_rsp_iocb *net_rsp;
 	struct net_device *ndev = qdev->ndev;
 	unsigned long hw_flags;
+	int work_done = 0;
+
+	u32 rsp_producer_index = le32_to_cpu(*(qdev->prsp_producer_index));
 
 	/* While there are entries in the completion queue. */
-	while ((cpu_to_le32(*(qdev->prsp_producer_index)) !=
-		qdev->rsp_consumer_index) && (*rx_cleaned < work_to_do)) {
+	while ((rsp_producer_index !=
+		qdev->rsp_consumer_index) && (work_done < work_to_do)) {
 
 		net_rsp = qdev->rsp_current;
 		switch (net_rsp->opcode) {
@@ -1968,37 +2005,34 @@
 		} else {
 			qdev->rsp_current++;
 		}
+
+		work_done = *tx_cleaned + *rx_cleaned;
 	}
 
-	spin_lock_irqsave(&qdev->hw_lock, hw_flags);
+	if(work_done) {
+		spin_lock_irqsave(&qdev->hw_lock, hw_flags);
 
-	ql_update_lrg_bufq_prod_index(qdev);
+		ql_update_lrg_bufq_prod_index(qdev);
 
-	if (qdev->small_buf_release_cnt >= 16) {
-		while (qdev->small_buf_release_cnt >= 16) {
-			qdev->small_buf_q_producer_index++;
+		if (qdev->small_buf_release_cnt >= 16) {
+			while (qdev->small_buf_release_cnt >= 16) {
+				qdev->small_buf_q_producer_index++;
 
-			if (qdev->small_buf_q_producer_index ==
-			    NUM_SBUFQ_ENTRIES)
-				qdev->small_buf_q_producer_index = 0;
-			qdev->small_buf_release_cnt -= 8;
+				if (qdev->small_buf_q_producer_index ==
+				    NUM_SBUFQ_ENTRIES)
+					qdev->small_buf_q_producer_index = 0;
+				qdev->small_buf_release_cnt -= 8;
+			}
+
+			wmb();
+			ql_write_common_reg(qdev,
+					    &port_regs->CommonRegs.
+					    rxSmallQProducerIndex,
+					    qdev->small_buf_q_producer_index);
+
 		}
 
-		ql_write_common_reg(qdev,
-				    &port_regs->CommonRegs.
-				    rxSmallQProducerIndex,
-				    qdev->small_buf_q_producer_index);
-	}
-
-	ql_write_common_reg(qdev,
-			    &port_regs->CommonRegs.rspQConsumerIndex,
-			    qdev->rsp_consumer_index);
-	spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
-
-	if (unlikely(netif_queue_stopped(qdev->ndev))) {
-		if (netif_queue_stopped(qdev->ndev) &&
-		    (atomic_read(&qdev->tx_count) > (NUM_REQ_Q_ENTRIES / 4)))
-			netif_wake_queue(qdev->ndev);
+		spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
 	}
 
 	return *tx_cleaned + *rx_cleaned;
@@ -2009,6 +2043,8 @@
 	struct ql3_adapter *qdev = netdev_priv(ndev);
 	int work_to_do = min(*budget, ndev->quota);
 	int rx_cleaned = 0, tx_cleaned = 0;
+	unsigned long hw_flags;
+	struct ql3xxx_port_registers __iomem *port_regs = qdev->mem_map_registers;
 
 	if (!netif_carrier_ok(ndev))
 		goto quit_polling;
@@ -2017,9 +2053,17 @@
 	*budget -= rx_cleaned;
 	ndev->quota -= rx_cleaned;
 
-	if ((!tx_cleaned && !rx_cleaned) || !netif_running(ndev)) {
+	if( tx_cleaned + rx_cleaned != work_to_do ||
+	    !netif_running(ndev)) {
 quit_polling:
 		netif_rx_complete(ndev);
+
+		spin_lock_irqsave(&qdev->hw_lock, hw_flags);
+		ql_write_common_reg(qdev,
+				    &port_regs->CommonRegs.rspQConsumerIndex,
+				    qdev->rsp_consumer_index);
+		spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
+
 		ql_enable_interrupts(qdev);
 		return 0;
 	}
@@ -2073,10 +2117,9 @@
 		spin_unlock(&qdev->adapter_lock);
 	} else if (value & ISP_IMR_DISABLE_CMPL_INT) {
 		ql_disable_interrupts(qdev);
-		if (likely(netif_rx_schedule_prep(ndev)))
+		if (likely(netif_rx_schedule_prep(ndev))) {
 			__netif_rx_schedule(ndev);
-		else
-			ql_enable_interrupts(qdev);
+		}
 	} else {
 		return IRQ_NONE;
 	}
@@ -2093,8 +2136,12 @@
  * the next AOL if more frags are coming.  
  * That is why the frags:segment count  ratio is not linear.
  */
-static int ql_get_seg_count(unsigned short frags)
+static int ql_get_seg_count(struct ql3_adapter *qdev,
+			    unsigned short frags)
 {
+	if (qdev->device_id == QL3022_DEVICE_ID)
+		return 1;
+
 	switch(frags) {
 	case 0:	return 1;	/* just the skb->data seg */
 	case 1:	return 2;	/* skb->data + 1 frag */
@@ -2139,11 +2186,13 @@
 
 	if (ip) {
 		if (ip->protocol == IPPROTO_TCP) {
-			mac_iocb_ptr->flags1 |= OB_3032MAC_IOCB_REQ_TC;
+			mac_iocb_ptr->flags1 |= OB_3032MAC_IOCB_REQ_TC | 
+			OB_3032MAC_IOCB_REQ_IC;
 			mac_iocb_ptr->ip_hdr_off = offset;
 			mac_iocb_ptr->ip_hdr_len = ip->ihl;
 		} else if (ip->protocol == IPPROTO_UDP) {
-			mac_iocb_ptr->flags1 |= OB_3032MAC_IOCB_REQ_UC;
+			mac_iocb_ptr->flags1 |= OB_3032MAC_IOCB_REQ_UC | 
+			OB_3032MAC_IOCB_REQ_IC;
 			mac_iocb_ptr->ip_hdr_off = offset;
 			mac_iocb_ptr->ip_hdr_len = ip->ihl;
 		}
@@ -2151,6 +2200,156 @@
 }
 
 /*
+ * Map the buffers for this transmit.  This will return
+ * NETDEV_TX_BUSY or NETDEV_TX_OK based on success.
+ */
+static int ql_send_map(struct ql3_adapter *qdev,
+				struct ob_mac_iocb_req *mac_iocb_ptr,
+				struct ql_tx_buf_cb *tx_cb,
+				struct sk_buff *skb)
+{
+	struct oal *oal;
+	struct oal_entry *oal_entry;
+	int len = skb->len;
+	dma_addr_t map;
+	int err;
+	int completed_segs, i;
+	int seg_cnt, seg = 0;
+	int frag_cnt = (int)skb_shinfo(skb)->nr_frags;
+
+	seg_cnt = tx_cb->seg_count = ql_get_seg_count(qdev,
+						      (skb_shinfo(skb)->nr_frags));
+	if(seg_cnt == -1) {
+		printk(KERN_ERR PFX"%s: invalid segment count!\n",__func__);
+		return NETDEV_TX_BUSY;
+	}
+	/*
+	 * Map the skb buffer first.
+	 */
+	map = pci_map_single(qdev->pdev, skb->data, len, PCI_DMA_TODEVICE);
+
+	err = pci_dma_mapping_error(map);
+	if(err) {
+		printk(KERN_ERR "%s: PCI mapping failed with error: %d\n", 
+		       qdev->ndev->name, err);
+
+		return NETDEV_TX_BUSY;
+	}
+	
+	oal_entry = (struct oal_entry *)&mac_iocb_ptr->buf_addr0_low;
+	oal_entry->dma_lo = cpu_to_le32(LS_64BITS(map));
+	oal_entry->dma_hi = cpu_to_le32(MS_64BITS(map));
+	oal_entry->len = cpu_to_le32(len);
+	pci_unmap_addr_set(&tx_cb->map[seg], mapaddr, map);
+	pci_unmap_len_set(&tx_cb->map[seg], maplen, len);
+	seg++;
+
+	if (seg_cnt == 1) {
+		/* Terminate the last segment. */
+		oal_entry->len =
+		    cpu_to_le32(le32_to_cpu(oal_entry->len) | OAL_LAST_ENTRY);
+	} else {
+		oal = tx_cb->oal;
+		for (completed_segs=0; completed_segs<frag_cnt; completed_segs++,seg++) {
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[completed_segs];
+			oal_entry++;
+			if ((seg == 2 && seg_cnt > 3) ||	/* Check for continuation */
+			    (seg == 7 && seg_cnt > 8) ||	/* requirements. It's strange */
+			    (seg == 12 && seg_cnt > 13) ||	/* but necessary. */
+			    (seg == 17 && seg_cnt > 18)) {
+				/* Continuation entry points to outbound address list. */
+				map = pci_map_single(qdev->pdev, oal,
+						     sizeof(struct oal),
+						     PCI_DMA_TODEVICE);
+
+				err = pci_dma_mapping_error(map);
+				if(err) {
+
+					printk(KERN_ERR "%s: PCI mapping outbound address list with error: %d\n", 
+					       qdev->ndev->name, err);
+					goto map_error;
+				}
+
+				oal_entry->dma_lo = cpu_to_le32(LS_64BITS(map));
+				oal_entry->dma_hi = cpu_to_le32(MS_64BITS(map));
+				oal_entry->len =
+				    cpu_to_le32(sizeof(struct oal) |
+						OAL_CONT_ENTRY);
+				pci_unmap_addr_set(&tx_cb->map[seg], mapaddr,
+						   map);
+				pci_unmap_len_set(&tx_cb->map[seg], maplen,
+						  len);
+				oal_entry = (struct oal_entry *)oal;
+				oal++;
+				seg++;
+			}
+
+			map =
+			    pci_map_page(qdev->pdev, frag->page,
+					 frag->page_offset, frag->size,
+					 PCI_DMA_TODEVICE);
+
+			err = pci_dma_mapping_error(map);
+			if(err) {
+				printk(KERN_ERR "%s: PCI mapping frags failed with error: %d\n", 
+				       qdev->ndev->name, err);
+				goto map_error;
+			}
+
+			oal_entry->dma_lo = cpu_to_le32(LS_64BITS(map));
+			oal_entry->dma_hi = cpu_to_le32(MS_64BITS(map));
+			oal_entry->len = cpu_to_le32(frag->size);
+			pci_unmap_addr_set(&tx_cb->map[seg], mapaddr, map);
+			pci_unmap_len_set(&tx_cb->map[seg], maplen,
+					  frag->size);
+		}
+		/* Terminate the last segment. */
+		oal_entry->len =
+		    cpu_to_le32(le32_to_cpu(oal_entry->len) | OAL_LAST_ENTRY);
+	}
+
+	return NETDEV_TX_OK;
+
+map_error:
+	/* A PCI mapping failed and now we will need to back out
+	 * We need to traverse through the oal's and associated pages which 
+	 * have been mapped and now we must unmap them to clean up properly
+	 */
+	
+	seg = 1;
+	oal_entry = (struct oal_entry *)&mac_iocb_ptr->buf_addr0_low;
+	oal = tx_cb->oal;
+	for (i=0; i<completed_segs; i++,seg++) {
+		oal_entry++;
+
+		if((seg == 2 && seg_cnt > 3) ||        /* Check for continuation */
+		   (seg == 7 && seg_cnt > 8) ||        /* requirements. It's strange */
+		   (seg == 12 && seg_cnt > 13) ||      /* but necessary. */
+		   (seg == 17 && seg_cnt > 18)) {
+			pci_unmap_single(qdev->pdev,
+				pci_unmap_addr(&tx_cb->map[seg], mapaddr),
+				pci_unmap_len(&tx_cb->map[seg], maplen),
+				 PCI_DMA_TODEVICE);
+			oal++;
+			seg++;
+		}
+
+		pci_unmap_page(qdev->pdev,
+			       pci_unmap_addr(&tx_cb->map[seg], mapaddr),
+			       pci_unmap_len(&tx_cb->map[seg], maplen),
+			       PCI_DMA_TODEVICE);
+	}
+
+	pci_unmap_single(qdev->pdev,
+			 pci_unmap_addr(&tx_cb->map[0], mapaddr),
+			 pci_unmap_addr(&tx_cb->map[0], maplen),
+			 PCI_DMA_TODEVICE);
+
+	return NETDEV_TX_BUSY;
+
+}
+
+/*
  * The difference between 3022 and 3032 sends:
  * 3022 only supports a simple single segment transmission.
  * 3032 supports checksumming and scatter/gather lists (fragments).
@@ -2167,92 +2366,35 @@
 	struct ql3xxx_port_registers __iomem *port_regs = qdev->mem_map_registers;
 	struct ql_tx_buf_cb *tx_cb;
 	u32 tot_len = skb->len;
-	struct oal *oal;
-	struct oal_entry *oal_entry;
-	int len;
 	struct ob_mac_iocb_req *mac_iocb_ptr;
-	u64 map;
-	int seg_cnt, seg = 0;
-	int frag_cnt = (int)skb_shinfo(skb)->nr_frags;
 
 	if (unlikely(atomic_read(&qdev->tx_count) < 2)) {
-		if (!netif_queue_stopped(ndev))
-			netif_stop_queue(ndev);
 		return NETDEV_TX_BUSY;
 	}
+	
 	tx_cb = &qdev->tx_buf[qdev->req_producer_index] ;
-	seg_cnt = tx_cb->seg_count = ql_get_seg_count((skb_shinfo(skb)->nr_frags));
-	if(seg_cnt == -1) {
+	if((tx_cb->seg_count = ql_get_seg_count(qdev,
+						(skb_shinfo(skb)->nr_frags))) == -1) {
 		printk(KERN_ERR PFX"%s: invalid segment count!\n",__func__);
 		return NETDEV_TX_OK;
-
 	}
+	
 	mac_iocb_ptr = tx_cb->queue_entry;
-	memset((void *)mac_iocb_ptr, 0, sizeof(struct ob_mac_iocb_req));
 	mac_iocb_ptr->opcode = qdev->mac_ob_opcode;
+	mac_iocb_ptr->flags = OB_MAC_IOCB_REQ_X;
 	mac_iocb_ptr->flags |= qdev->mb_bit_mask;
 	mac_iocb_ptr->transaction_id = qdev->req_producer_index;
 	mac_iocb_ptr->data_len = cpu_to_le16((u16) tot_len);
 	tx_cb->skb = skb;
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
+	if (qdev->device_id == QL3032_DEVICE_ID &&
+	    skb->ip_summed == CHECKSUM_PARTIAL)
 		ql_hw_csum_setup(skb, mac_iocb_ptr);
-	len = skb_headlen(skb);
-	map = pci_map_single(qdev->pdev, skb->data, len, PCI_DMA_TODEVICE);
-	oal_entry = (struct oal_entry *)&mac_iocb_ptr->buf_addr0_low;
-	oal_entry->dma_lo = cpu_to_le32(LS_64BITS(map));
-	oal_entry->dma_hi = cpu_to_le32(MS_64BITS(map));
-	oal_entry->len = cpu_to_le32(len);
-	pci_unmap_addr_set(&tx_cb->map[seg], mapaddr, map);
-	pci_unmap_len_set(&tx_cb->map[seg], maplen, len);
-	seg++;
-
-	if (!skb_shinfo(skb)->nr_frags) {
-		/* Terminate the last segment. */
-		oal_entry->len =
-		    cpu_to_le32(le32_to_cpu(oal_entry->len) | OAL_LAST_ENTRY);
-	} else {
-		int i;
-		oal = tx_cb->oal;
-		for (i=0; i<frag_cnt; i++,seg++) {
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-			oal_entry++;
-			if ((seg == 2 && seg_cnt > 3) ||	/* Check for continuation */
-			    (seg == 7 && seg_cnt > 8) ||	/* requirements. It's strange */
-			    (seg == 12 && seg_cnt > 13) ||	/* but necessary. */
-			    (seg == 17 && seg_cnt > 18)) {
-				/* Continuation entry points to outbound address list. */
-				map = pci_map_single(qdev->pdev, oal,
-						     sizeof(struct oal),
-						     PCI_DMA_TODEVICE);
-				oal_entry->dma_lo = cpu_to_le32(LS_64BITS(map));
-				oal_entry->dma_hi = cpu_to_le32(MS_64BITS(map));
-				oal_entry->len =
-				    cpu_to_le32(sizeof(struct oal) |
-						OAL_CONT_ENTRY);
-				pci_unmap_addr_set(&tx_cb->map[seg], mapaddr,
-						   map);
-				pci_unmap_len_set(&tx_cb->map[seg], maplen,
-						  len);
-				oal_entry = (struct oal_entry *)oal;
-				oal++;
-				seg++;
-			}
-
-			map =
-			    pci_map_page(qdev->pdev, frag->page,
-					 frag->page_offset, frag->size,
-					 PCI_DMA_TODEVICE);
-			oal_entry->dma_lo = cpu_to_le32(LS_64BITS(map));
-			oal_entry->dma_hi = cpu_to_le32(MS_64BITS(map));
-			oal_entry->len = cpu_to_le32(frag->size);
-			pci_unmap_addr_set(&tx_cb->map[seg], mapaddr, map);
-			pci_unmap_len_set(&tx_cb->map[seg], maplen,
-					  frag->size);
-		}
-		/* Terminate the last segment. */
-		oal_entry->len =
-		    cpu_to_le32(le32_to_cpu(oal_entry->len) | OAL_LAST_ENTRY);
+	
+	if(ql_send_map(qdev,mac_iocb_ptr,tx_cb,skb) != NETDEV_TX_OK) {
+		printk(KERN_ERR PFX"%s: Could not map the segments!\n",__func__);
+		return NETDEV_TX_BUSY;
 	}
+	
 	wmb();
 	qdev->req_producer_index++;
 	if (qdev->req_producer_index == NUM_REQ_Q_ENTRIES)
@@ -2338,12 +2480,19 @@
 {
 	/* Create Large Buffer Queue */
 	qdev->lrg_buf_q_size =
-	    NUM_LBUFQ_ENTRIES * sizeof(struct lrg_buf_q_entry);
+	    qdev->num_lbufq_entries * sizeof(struct lrg_buf_q_entry);
 	if (qdev->lrg_buf_q_size < PAGE_SIZE)
 		qdev->lrg_buf_q_alloc_size = PAGE_SIZE;
 	else
 		qdev->lrg_buf_q_alloc_size = qdev->lrg_buf_q_size * 2;
 
+	qdev->lrg_buf = kmalloc(qdev->num_large_buffers * sizeof(struct ql_rcv_buf_cb),GFP_KERNEL);
+	if (qdev->lrg_buf == NULL) {
+		printk(KERN_ERR PFX
+		       "%s: qdev->lrg_buf alloc failed.\n", qdev->ndev->name);
+		return -ENOMEM;
+	}
+	
 	qdev->lrg_buf_q_alloc_virt_addr =
 	    pci_alloc_consistent(qdev->pdev,
 				 qdev->lrg_buf_q_alloc_size,
@@ -2393,7 +2542,7 @@
 		       "%s: Already done.\n", qdev->ndev->name);
 		return;
 	}
-
+	if(qdev->lrg_buf) kfree(qdev->lrg_buf);
 	pci_free_consistent(qdev->pdev,
 			    qdev->lrg_buf_q_alloc_size,
 			    qdev->lrg_buf_q_alloc_virt_addr,
@@ -2438,8 +2587,6 @@
 
 	small_buf_q_entry = qdev->small_buf_q_virt_addr;
 
-	qdev->last_rsp_offset = qdev->small_buf_phy_addr_low;
-
 	/* Initialize the small buffer queue. */
 	for (i = 0; i < (QL_ADDR_ELE_PER_BUFQ_ENTRY * NUM_SBUFQ_ENTRIES); i++) {
 		small_buf_q_entry->addr_high =
@@ -2476,7 +2623,7 @@
 	int i = 0;
 	struct ql_rcv_buf_cb *lrg_buf_cb;
 
-	for (i = 0; i < NUM_LARGE_BUFFERS; i++) {
+	for (i = 0; i < qdev->num_large_buffers; i++) {
 		lrg_buf_cb = &qdev->lrg_buf[i];
 		if (lrg_buf_cb->skb) {
 			dev_kfree_skb(lrg_buf_cb->skb);
@@ -2497,7 +2644,7 @@
 	struct ql_rcv_buf_cb *lrg_buf_cb;
 	struct bufq_addr_element *buf_addr_ele = qdev->lrg_buf_q_virt_addr;
 
-	for (i = 0; i < NUM_LARGE_BUFFERS; i++) {
+	for (i = 0; i < qdev->num_large_buffers; i++) {
 		lrg_buf_cb = &qdev->lrg_buf[i];
 		buf_addr_ele->addr_high = lrg_buf_cb->buf_phy_addr_high;
 		buf_addr_ele->addr_low = lrg_buf_cb->buf_phy_addr_low;
@@ -2512,10 +2659,12 @@
 	int i;
 	struct ql_rcv_buf_cb *lrg_buf_cb;
 	struct sk_buff *skb;
-	u64 map;
+	dma_addr_t map;
+	int err;
 
-	for (i = 0; i < NUM_LARGE_BUFFERS; i++) {
-		skb = dev_alloc_skb(qdev->lrg_buffer_len);
+	for (i = 0; i < qdev->num_large_buffers; i++) {
+		skb = netdev_alloc_skb(qdev->ndev,
+				       qdev->lrg_buffer_len);
 		if (unlikely(!skb)) {
 			/* Better luck next round */
 			printk(KERN_ERR PFX
@@ -2541,6 +2690,15 @@
 					     qdev->lrg_buffer_len -
 					     QL_HEADER_SPACE,
 					     PCI_DMA_FROMDEVICE);
+
+			err = pci_dma_mapping_error(map);
+			if(err) {
+				printk(KERN_ERR "%s: PCI mapping failed with error: %d\n",
+				       qdev->ndev->name, err);
+				ql_free_large_buffers(qdev);
+				return -ENOMEM;
+			}
+
 			pci_unmap_addr_set(lrg_buf_cb, mapaddr, map);
 			pci_unmap_len_set(lrg_buf_cb, maplen,
 					  qdev->lrg_buffer_len -
@@ -2592,9 +2750,15 @@
 
 static int ql_alloc_mem_resources(struct ql3_adapter *qdev)
 {
-	if (qdev->ndev->mtu == NORMAL_MTU_SIZE)
+	if (qdev->ndev->mtu == NORMAL_MTU_SIZE) {
+		qdev->num_lbufq_entries = NUM_LBUFQ_ENTRIES;
 		qdev->lrg_buffer_len = NORMAL_MTU_SIZE;
+	}
 	else if (qdev->ndev->mtu == JUMBO_MTU_SIZE) {
+		/*
+		 * Bigger buffers, so less of them.
+		 */
+		qdev->num_lbufq_entries = JUMBO_NUM_LBUFQ_ENTRIES;
 		qdev->lrg_buffer_len = JUMBO_MTU_SIZE;
 	} else {
 		printk(KERN_ERR PFX
@@ -2602,6 +2766,7 @@
 		       qdev->ndev->name);
 		return -ENOMEM;
 	}
+	qdev->num_large_buffers = qdev->num_lbufq_entries * QL_ADDR_ELE_PER_BUFQ_ENTRY;
 	qdev->lrg_buffer_len += VLAN_ETH_HLEN + VLAN_ID_LEN + QL_HEADER_SPACE;
 	qdev->max_frame_size =
 	    (qdev->lrg_buffer_len - QL_HEADER_SPACE) + ETHERNET_CRC_SIZE;
@@ -2834,7 +2999,7 @@
 			   &hmem_regs->rxLargeQBaseAddrLow,
 			   LS_64BITS(qdev->lrg_buf_q_phy_addr));
 
-	ql_write_page1_reg(qdev, &hmem_regs->rxLargeQLength, NUM_LBUFQ_ENTRIES);
+	ql_write_page1_reg(qdev, &hmem_regs->rxLargeQLength, qdev->num_lbufq_entries);
 
 	ql_write_page1_reg(qdev,
 			   &hmem_regs->rxLargeBufferLength,
@@ -2856,7 +3021,7 @@
 
 	qdev->small_buf_q_producer_index = NUM_SBUFQ_ENTRIES - 1;
 	qdev->small_buf_release_cnt = 8;
-	qdev->lrg_buf_q_producer_index = NUM_LBUFQ_ENTRIES - 1;
+	qdev->lrg_buf_q_producer_index = qdev->num_lbufq_entries - 1;
 	qdev->lrg_buf_release_cnt = 8;
 	qdev->lrg_buf_next_free =
 	    (struct bufq_addr_element *)qdev->lrg_buf_q_virt_addr;
@@ -3292,6 +3457,7 @@
 err_init:
 	ql_sem_unlock(qdev, QL_DRVR_SEM_MASK);
 err_lock:
+	spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
 	free_irq(qdev->pdev->irq, ndev);
 err_irq:
 	if (qdev->msi && test_bit(QL_MSI_ENABLED,&qdev->flags)) {
@@ -3343,27 +3509,6 @@
 	return &qdev->stats;
 }
 
-static int ql3xxx_change_mtu(struct net_device *ndev, int new_mtu)
-{
-	struct ql3_adapter *qdev = netdev_priv(ndev);
-	printk(KERN_ERR PFX "%s:  new mtu size = %d.\n", ndev->name, new_mtu);
-	if (new_mtu != NORMAL_MTU_SIZE && new_mtu != JUMBO_MTU_SIZE) {
-		printk(KERN_ERR PFX
-		       "%s: mtu size of %d is not valid.  Use exactly %d or "
-		       "%d.\n", ndev->name, new_mtu, NORMAL_MTU_SIZE,
-		       JUMBO_MTU_SIZE);
-		return -EINVAL;
-	}
-
-	if (!netif_running(ndev)) {
-		ndev->mtu = new_mtu;
-		return 0;
-	}
-
-	ndev->mtu = new_mtu;
-	return ql_cycle_adapter(qdev,QL_DO_RESET);
-}
-
 static void ql3xxx_set_multicast_list(struct net_device *ndev)
 {
 	/*
@@ -3609,8 +3754,12 @@
 	}
 
 	ndev = alloc_etherdev(sizeof(struct ql3_adapter));
-	if (!ndev)
+	if (!ndev) {
+		printk(KERN_ERR PFX "%s could not alloc etherdev\n",
+		       pci_name(pdev));
+		err = -ENOMEM;
 		goto err_out_free_regions;
+	}
 
 	SET_MODULE_OWNER(ndev);
 	SET_NETDEV_DEV(ndev, &pdev->dev);
@@ -3639,6 +3788,7 @@
 	if (!qdev->mem_map_registers) {
 		printk(KERN_ERR PFX "%s: cannot map device registers\n",
 		       pci_name(pdev));
+		err = -EIO;
 		goto err_out_free_ndev;
 	}
 
@@ -3650,7 +3800,6 @@
 	ndev->hard_start_xmit = ql3xxx_send;
 	ndev->stop = ql3xxx_close;
 	ndev->get_stats = ql3xxx_get_stats;
-	ndev->change_mtu = ql3xxx_change_mtu;
 	ndev->set_multicast_list = ql3xxx_set_multicast_list;
 	SET_ETHTOOL_OPS(ndev, &ql3xxx_ethtool_ops);
 	ndev->set_mac_address = ql3xxx_set_mac_address;
@@ -3667,6 +3816,7 @@
 		printk(KERN_ALERT PFX
 		       "ql3xxx_probe: Adapter #%d, Invalid NVRAM parameters.\n",
 		       qdev->index);
+		err = -EIO;
 		goto err_out_iounmap;
 	}
 
@@ -3674,9 +3824,11 @@
 
 	/* Validate and set parameters */
 	if (qdev->mac_index) {
+		ndev->mtu = qdev->nvram_data.macCfg_port1.etherMtu_mac ;
 		memcpy(ndev->dev_addr, &qdev->nvram_data.funcCfg_fn2.macAddress,
 		       ETH_ALEN);
 	} else {
+		ndev->mtu = qdev->nvram_data.macCfg_port0.etherMtu_mac ;
 		memcpy(ndev->dev_addr, &qdev->nvram_data.funcCfg_fn0.macAddress,
 		       ETH_ALEN);
 	}
diff --git a/drivers/net/qla3xxx.h b/drivers/net/qla3xxx.h
index b2d76ea..34cd658 100755
--- a/drivers/net/qla3xxx.h
+++ b/drivers/net/qla3xxx.h
@@ -1014,13 +1014,15 @@
 
 /* Transmit and Receive Buffers */
 #define NUM_LBUFQ_ENTRIES   	128
+#define JUMBO_NUM_LBUFQ_ENTRIES   	\
+(NUM_LBUFQ_ENTRIES/(JUMBO_MTU_SIZE/NORMAL_MTU_SIZE))
 #define NUM_SBUFQ_ENTRIES   	64
 #define QL_SMALL_BUFFER_SIZE    32
 #define QL_ADDR_ELE_PER_BUFQ_ENTRY \
 (sizeof(struct lrg_buf_q_entry) / sizeof(struct bufq_addr_element))
     /* Each send has at least control block.  This is how many we keep. */
 #define NUM_SMALL_BUFFERS     	NUM_SBUFQ_ENTRIES * QL_ADDR_ELE_PER_BUFQ_ENTRY
-#define NUM_LARGE_BUFFERS     	NUM_LBUFQ_ENTRIES * QL_ADDR_ELE_PER_BUFQ_ENTRY
+
 #define QL_HEADER_SPACE 32	/* make header space at top of skb. */
 /*
  * Large & Small Buffers for Receives
@@ -1092,7 +1094,6 @@
 	u32 len;
 #define OAL_LAST_ENTRY   0x80000000	/* Last valid buffer in list. */
 #define OAL_CONT_ENTRY   0x40000000	/* points to an OAL. (continuation) */
-	u32 reserved;
 };
 
 struct oal {
@@ -1193,7 +1194,7 @@
 	struct net_rsp_iocb *rsp_current;
 	u16 rsp_consumer_index;
 	u16 reserved_06;
-	u32 *prsp_producer_index;
+	volatile u32 *prsp_producer_index;
 	u32 rsp_producer_index_phy_addr_high;
 	u32 rsp_producer_index_phy_addr_low;
 
@@ -1207,9 +1208,11 @@
 	u32 lrg_buf_q_producer_index;
 	u32 lrg_buf_release_cnt;
 	struct bufq_addr_element *lrg_buf_next_free;
+	u32 num_large_buffers;
+	u32 num_lbufq_entries;
 
 	/* Large (Receive) Buffers */
-	struct ql_rcv_buf_cb lrg_buf[NUM_LARGE_BUFFERS];
+	struct ql_rcv_buf_cb *lrg_buf;
 	struct ql_rcv_buf_cb *lrg_buf_free_head;
 	struct ql_rcv_buf_cb *lrg_buf_free_tail;
 	u32 lrg_buf_free_count;
diff --git a/drivers/net/s2io-regs.h b/drivers/net/s2io-regs.h
index 0e345cb..33fb7f3 100644
--- a/drivers/net/s2io-regs.h
+++ b/drivers/net/s2io-regs.h
@@ -430,6 +430,7 @@
 #define TX_PA_CFG_IGNORE_SNAP_OUI          BIT(2)
 #define TX_PA_CFG_IGNORE_LLC_CTRL          BIT(3)
 #define	TX_PA_CFG_IGNORE_L2_ERR			   BIT(6)
+#define RX_PA_CFG_STRIP_VLAN_TAG		BIT(15)
 
 /* Recent add, used only debug purposes. */
 	u64 pcc_enable;
diff --git a/drivers/net/s2io.c b/drivers/net/s2io.c
index fd85648..44bb239 100644
--- a/drivers/net/s2io.c
+++ b/drivers/net/s2io.c
@@ -42,6 +42,14 @@
  *     Possible values '1' for enable '0' for disable. Default is '0'
  * lro_max_pkts: This parameter defines maximum number of packets can be
  *     aggregated as a single large packet
+ * napi: This parameter used to enable/disable NAPI (polling Rx)
+ *     Possible values '1' for enable and '0' for disable. Default is '1'
+ * ufo: This parameter used to enable/disable UDP Fragmentation Offload(UFO)
+ *      Possible values '1' for enable and '0' for disable. Default is '0'
+ * vlan_tag_strip: This can be used to enable or disable vlan stripping.
+ *                 Possible values '1' for enable , '0' for disable.
+ *                 Default is '2' - which means disable in promisc mode
+ *                 and enable in non-promiscuous mode.
  ************************************************************************/
 
 #include <linux/module.h>
@@ -76,7 +84,7 @@
 #include "s2io.h"
 #include "s2io-regs.h"
 
-#define DRV_VERSION "2.0.16.1"
+#define DRV_VERSION "2.0.17.1"
 
 /* S2io Driver name & version. */
 static char s2io_driver_name[] = "Neterion";
@@ -131,7 +139,7 @@
 	"BIST Test\t(offline)"
 };
 
-static char ethtool_stats_keys[][ETH_GSTRING_LEN] = {
+static char ethtool_xena_stats_keys[][ETH_GSTRING_LEN] = {
 	{"tmac_frms"},
 	{"tmac_data_octets"},
 	{"tmac_drop_frms"},
@@ -225,7 +233,10 @@
 	{"rxd_rd_cnt"},
 	{"rxd_wr_cnt"},
 	{"txf_rd_cnt"},
-	{"rxf_wr_cnt"},
+	{"rxf_wr_cnt"}
+};
+
+static char ethtool_enhanced_stats_keys[][ETH_GSTRING_LEN] = {
 	{"rmac_ttl_1519_4095_frms"},
 	{"rmac_ttl_4096_8191_frms"},
 	{"rmac_ttl_8192_max_frms"},
@@ -241,7 +252,10 @@
 	{"rmac_red_discard"},
 	{"rmac_rts_discard"},
 	{"rmac_ingm_full_discard"},
-	{"link_fault_cnt"},
+	{"link_fault_cnt"}
+};
+
+static char ethtool_driver_stats_keys[][ETH_GSTRING_LEN] = {
 	{"\n DRIVER STATISTICS"},
 	{"single_bit_ecc_errs"},
 	{"double_bit_ecc_errs"},
@@ -269,8 +283,16 @@
 	("lro_avg_aggr_pkts"),
 };
 
-#define S2IO_STAT_LEN sizeof(ethtool_stats_keys)/ ETH_GSTRING_LEN
-#define S2IO_STAT_STRINGS_LEN S2IO_STAT_LEN * ETH_GSTRING_LEN
+#define S2IO_XENA_STAT_LEN sizeof(ethtool_xena_stats_keys)/ ETH_GSTRING_LEN
+#define S2IO_ENHANCED_STAT_LEN sizeof(ethtool_enhanced_stats_keys)/ \
+					ETH_GSTRING_LEN
+#define S2IO_DRIVER_STAT_LEN sizeof(ethtool_driver_stats_keys)/ ETH_GSTRING_LEN
+
+#define XFRAME_I_STAT_LEN (S2IO_XENA_STAT_LEN + S2IO_DRIVER_STAT_LEN )
+#define XFRAME_II_STAT_LEN (XFRAME_I_STAT_LEN + S2IO_ENHANCED_STAT_LEN )
+
+#define XFRAME_I_STAT_STRINGS_LEN ( XFRAME_I_STAT_LEN * ETH_GSTRING_LEN )
+#define XFRAME_II_STAT_STRINGS_LEN ( XFRAME_II_STAT_LEN * ETH_GSTRING_LEN )
 
 #define S2IO_TEST_LEN	sizeof(s2io_gstrings) / ETH_GSTRING_LEN
 #define S2IO_STRINGS_LEN	S2IO_TEST_LEN * ETH_GSTRING_LEN
@@ -293,6 +315,9 @@
 	spin_unlock_irqrestore(&nic->tx_lock, flags);
 }
 
+/* A flag indicating whether 'RX_PA_CFG_STRIP_VLAN_TAG' bit is set or not */
+int vlan_strip_flag;
+
 /* Unregister the vlan */
 static void s2io_vlan_rx_kill_vid(struct net_device *dev, unsigned long vid)
 {
@@ -404,6 +429,7 @@
 
 S2IO_PARM_INT(napi, 1);
 S2IO_PARM_INT(ufo, 0);
+S2IO_PARM_INT(vlan_tag_strip, NO_STRIP_IN_PROMISC);
 
 static unsigned int tx_fifo_len[MAX_TX_FIFOS] =
     {DEFAULT_FIFO_0_LEN, [1 ...(MAX_TX_FIFOS - 1)] = DEFAULT_FIFO_1_7_LEN};
@@ -1371,6 +1397,16 @@
 				&bar0->rts_frm_len_n[i]);
 		}
 	}
+	
+	/* Disable differentiated services steering logic */
+	for (i = 0; i < 64; i++) {
+		if (rts_ds_steer(nic, i, 0) == FAILURE) {
+			DBG_PRINT(ERR_DBG, "%s: failed rts ds steering",
+				dev->name);
+			DBG_PRINT(ERR_DBG, "set on codepoint %d\n", i);
+			return FAILURE;
+		}
+	}
 
 	/* Program statistics memory */
 	writeq(mac_control->stats_mem_phy, &bar0->stat_addr);
@@ -1943,6 +1979,13 @@
 		writeq(val64, &bar0->rx_pa_cfg);
 	}
 
+	if (vlan_tag_strip == 0) {
+		val64 = readq(&bar0->rx_pa_cfg);
+		val64 &= ~RX_PA_CFG_STRIP_VLAN_TAG;
+		writeq(val64, &bar0->rx_pa_cfg);
+		vlan_strip_flag = 0;
+	}
+
 	/*
 	 * Enabling MC-RLDRAM. After enabling the device, we timeout
 	 * for around 100ms, which is approximately the time required
@@ -3195,26 +3238,37 @@
  *   SUCCESS on success and FAILURE on failure.
  */
 
-static int wait_for_cmd_complete(void __iomem *addr, u64 busy_bit)
+static int wait_for_cmd_complete(void __iomem *addr, u64 busy_bit,
+				int bit_state)
 {
-	int ret = FAILURE, cnt = 0;
+	int ret = FAILURE, cnt = 0, delay = 1;
 	u64 val64;
 
-	while (TRUE) {
+	if ((bit_state != S2IO_BIT_RESET) && (bit_state != S2IO_BIT_SET))
+		return FAILURE;
+
+	do {
 		val64 = readq(addr);
-		if (!(val64 & busy_bit)) {
-			ret = SUCCESS;
-			break;
+		if (bit_state == S2IO_BIT_RESET) {
+			if (!(val64 & busy_bit)) {
+				ret = SUCCESS;
+				break;
+			}
+		} else {
+			if (!(val64 & busy_bit)) {
+				ret = SUCCESS;
+				break;
+			}
 		}
 
 		if(in_interrupt())
-			mdelay(50);
+			mdelay(delay);
 		else
-			msleep(50);
+			msleep(delay);
 
-		if (cnt++ > 10)
-			break;
-	}
+		if (++cnt >= 10)
+			delay = 50;
+	} while (cnt < 20);
 	return ret;
 }
 /*
@@ -3340,6 +3394,9 @@
 		writeq(val64, &bar0->pcc_err_reg);
 	}
 
+	/* restore the previously assigned mac address */
+	s2io_set_mac_addr(sp->dev, (u8 *)&sp->def_mac_addr[0].mac_addr);
+
 	sp->device_enabled_once = FALSE;
 }
 
@@ -4087,6 +4144,11 @@
 			val64 &= ~GPIO_INT_MASK_LINK_UP;
 			val64 |= GPIO_INT_MASK_LINK_DOWN;
 			writeq(val64, &bar0->gpio_int_mask);
+
+			/* turn off LED */
+			val64 = readq(&bar0->adapter_control);
+			val64 = val64 &(~ADAPTER_LED_ON);
+			writeq(val64, &bar0->adapter_control);
 		}
 	}
 	val64 = readq(&bar0->gpio_int_mask);
@@ -4296,7 +4358,8 @@
 		writeq(val64, &bar0->rmac_addr_cmd_mem);
 		/* Wait till command completes */
 		wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
-				      RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING);
+					RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
+					S2IO_BIT_RESET);
 
 		sp->m_cast_flg = 1;
 		sp->all_multi_pos = MAC_MC_ALL_MC_ADDR_OFFSET;
@@ -4312,7 +4375,8 @@
 		writeq(val64, &bar0->rmac_addr_cmd_mem);
 		/* Wait till command completes */
 		wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
-				      RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING);
+					RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
+					S2IO_BIT_RESET);
 
 		sp->m_cast_flg = 0;
 		sp->all_multi_pos = 0;
@@ -4329,6 +4393,13 @@
 		writeq(RMAC_CFG_KEY(0x4C0D), &bar0->rmac_cfg_key);
 		writel((u32) (val64 >> 32), (add + 4));
 
+		if (vlan_tag_strip != 1) {
+			val64 = readq(&bar0->rx_pa_cfg);
+			val64 &= ~RX_PA_CFG_STRIP_VLAN_TAG;
+			writeq(val64, &bar0->rx_pa_cfg);
+			vlan_strip_flag = 0;
+		}
+
 		val64 = readq(&bar0->mac_cfg);
 		sp->promisc_flg = 1;
 		DBG_PRINT(INFO_DBG, "%s: entered promiscuous mode\n",
@@ -4344,6 +4415,13 @@
 		writeq(RMAC_CFG_KEY(0x4C0D), &bar0->rmac_cfg_key);
 		writel((u32) (val64 >> 32), (add + 4));
 
+		if (vlan_tag_strip != 0) {
+			val64 = readq(&bar0->rx_pa_cfg);
+			val64 |= RX_PA_CFG_STRIP_VLAN_TAG;
+			writeq(val64, &bar0->rx_pa_cfg);
+			vlan_strip_flag = 1;
+		}
+
 		val64 = readq(&bar0->mac_cfg);
 		sp->promisc_flg = 0;
 		DBG_PRINT(INFO_DBG, "%s: left promiscuous mode\n",
@@ -4378,7 +4456,8 @@
 
 			/* Wait for command completes */
 			if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
-				      RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING)) {
+					RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
+					S2IO_BIT_RESET)) {
 				DBG_PRINT(ERR_DBG, "%s: Adding ",
 					  dev->name);
 				DBG_PRINT(ERR_DBG, "Multicasts failed\n");
@@ -4409,7 +4488,8 @@
 
 			/* Wait for command completes */
 			if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
-				      RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING)) {
+					RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING,
+					S2IO_BIT_RESET)) {
 				DBG_PRINT(ERR_DBG, "%s: Adding ",
 					  dev->name);
 				DBG_PRINT(ERR_DBG, "Multicasts failed\n");
@@ -4435,6 +4515,7 @@
 	struct XENA_dev_config __iomem *bar0 = sp->bar0;
 	register u64 val64, mac_addr = 0;
 	int i;
+	u64 old_mac_addr = 0;
 
 	/*
 	 * Set the new MAC address as the new unicast filter and reflect this
@@ -4444,6 +4525,22 @@
 	for (i = 0; i < ETH_ALEN; i++) {
 		mac_addr <<= 8;
 		mac_addr |= addr[i];
+		old_mac_addr <<= 8;
+		old_mac_addr |= sp->def_mac_addr[0].mac_addr[i];
+	}
+
+	if(0 == mac_addr)
+		return SUCCESS;
+
+	/* Update the internal structure with this new mac address */
+	if(mac_addr != old_mac_addr) {
+		memset(sp->def_mac_addr[0].mac_addr, 0, sizeof(ETH_ALEN));
+		sp->def_mac_addr[0].mac_addr[5] = (u8) (mac_addr);
+		sp->def_mac_addr[0].mac_addr[4] = (u8) (mac_addr >> 8);
+		sp->def_mac_addr[0].mac_addr[3] = (u8) (mac_addr >> 16);
+		sp->def_mac_addr[0].mac_addr[2] = (u8) (mac_addr >> 24);
+		sp->def_mac_addr[0].mac_addr[1] = (u8) (mac_addr >> 32);
+		sp->def_mac_addr[0].mac_addr[0] = (u8) (mac_addr >> 40);
 	}
 
 	writeq(RMAC_ADDR_DATA0_MEM_ADDR(mac_addr),
@@ -4455,7 +4552,7 @@
 	writeq(val64, &bar0->rmac_addr_cmd_mem);
 	/* Wait till command completes */
 	if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
-		      RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING)) {
+		      RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING, S2IO_BIT_RESET)) {
 		DBG_PRINT(ERR_DBG, "%s: set_mac_addr failed\n", dev->name);
 		return FAILURE;
 	}
@@ -4546,7 +4643,11 @@
 	info->regdump_len = XENA_REG_SPACE;
 	info->eedump_len = XENA_EEPROM_SPACE;
 	info->testinfo_len = S2IO_TEST_LEN;
-	info->n_stats = S2IO_STAT_LEN;
+
+	if (sp->device_type == XFRAME_I_DEVICE)
+		info->n_stats = XFRAME_I_STAT_LEN;
+	else
+		info->n_stats = XFRAME_II_STAT_LEN;
 }
 
 /**
@@ -5568,22 +5669,30 @@
 	tmp_stats[i++] = le32_to_cpu(stat_info->rxd_wr_cnt);
 	tmp_stats[i++] = le32_to_cpu(stat_info->txf_rd_cnt);
 	tmp_stats[i++] = le32_to_cpu(stat_info->rxf_wr_cnt);
-	tmp_stats[i++] = le64_to_cpu(stat_info->rmac_ttl_1519_4095_frms);
-        tmp_stats[i++] = le64_to_cpu(stat_info->rmac_ttl_4096_8191_frms);
-        tmp_stats[i++] = le64_to_cpu(stat_info->rmac_ttl_8192_max_frms);
-        tmp_stats[i++] = le64_to_cpu(stat_info->rmac_ttl_gt_max_frms);
-        tmp_stats[i++] = le64_to_cpu(stat_info->rmac_osized_alt_frms);
-        tmp_stats[i++] = le64_to_cpu(stat_info->rmac_jabber_alt_frms);
-        tmp_stats[i++] = le64_to_cpu(stat_info->rmac_gt_max_alt_frms);
-        tmp_stats[i++] = le64_to_cpu(stat_info->rmac_vlan_frms);
-        tmp_stats[i++] = le32_to_cpu(stat_info->rmac_len_discard);
-        tmp_stats[i++] = le32_to_cpu(stat_info->rmac_fcs_discard);
-        tmp_stats[i++] = le32_to_cpu(stat_info->rmac_pf_discard);
-        tmp_stats[i++] = le32_to_cpu(stat_info->rmac_da_discard);
-        tmp_stats[i++] = le32_to_cpu(stat_info->rmac_red_discard);
-        tmp_stats[i++] = le32_to_cpu(stat_info->rmac_rts_discard);
-        tmp_stats[i++] = le32_to_cpu(stat_info->rmac_ingm_full_discard);
-        tmp_stats[i++] = le32_to_cpu(stat_info->link_fault_cnt);
+
+	/* Enhanced statistics exist only for Hercules */
+	if(sp->device_type == XFRAME_II_DEVICE) {
+		tmp_stats[i++] =
+				le64_to_cpu(stat_info->rmac_ttl_1519_4095_frms);
+		tmp_stats[i++] =
+				le64_to_cpu(stat_info->rmac_ttl_4096_8191_frms);
+		tmp_stats[i++] =
+				le64_to_cpu(stat_info->rmac_ttl_8192_max_frms);
+		tmp_stats[i++] = le64_to_cpu(stat_info->rmac_ttl_gt_max_frms);
+		tmp_stats[i++] = le64_to_cpu(stat_info->rmac_osized_alt_frms);
+		tmp_stats[i++] = le64_to_cpu(stat_info->rmac_jabber_alt_frms);
+		tmp_stats[i++] = le64_to_cpu(stat_info->rmac_gt_max_alt_frms);
+		tmp_stats[i++] = le64_to_cpu(stat_info->rmac_vlan_frms);
+		tmp_stats[i++] = le32_to_cpu(stat_info->rmac_len_discard);
+		tmp_stats[i++] = le32_to_cpu(stat_info->rmac_fcs_discard);
+		tmp_stats[i++] = le32_to_cpu(stat_info->rmac_pf_discard);
+		tmp_stats[i++] = le32_to_cpu(stat_info->rmac_da_discard);
+		tmp_stats[i++] = le32_to_cpu(stat_info->rmac_red_discard);
+		tmp_stats[i++] = le32_to_cpu(stat_info->rmac_rts_discard);
+		tmp_stats[i++] = le32_to_cpu(stat_info->rmac_ingm_full_discard);
+		tmp_stats[i++] = le32_to_cpu(stat_info->link_fault_cnt);
+	}
+
 	tmp_stats[i++] = 0;
 	tmp_stats[i++] = stat_info->sw_stat.single_ecc_errs;
 	tmp_stats[i++] = stat_info->sw_stat.double_ecc_errs;
@@ -5663,18 +5772,42 @@
 static void s2io_ethtool_get_strings(struct net_device *dev,
 				     u32 stringset, u8 * data)
 {
+	int stat_size = 0;
+	struct s2io_nic *sp = dev->priv;
+
 	switch (stringset) {
 	case ETH_SS_TEST:
 		memcpy(data, s2io_gstrings, S2IO_STRINGS_LEN);
 		break;
 	case ETH_SS_STATS:
-		memcpy(data, &ethtool_stats_keys,
-		       sizeof(ethtool_stats_keys));
+		stat_size = sizeof(ethtool_xena_stats_keys);
+		memcpy(data, &ethtool_xena_stats_keys,stat_size);
+		if(sp->device_type == XFRAME_II_DEVICE) {
+			memcpy(data + stat_size,
+				&ethtool_enhanced_stats_keys,
+				sizeof(ethtool_enhanced_stats_keys));
+			stat_size += sizeof(ethtool_enhanced_stats_keys);
+		}
+
+		memcpy(data + stat_size, &ethtool_driver_stats_keys,
+			sizeof(ethtool_driver_stats_keys));
 	}
 }
 static int s2io_ethtool_get_stats_count(struct net_device *dev)
 {
-	return (S2IO_STAT_LEN);
+	struct s2io_nic *sp = dev->priv;
+	int stat_count = 0;
+	switch(sp->device_type) {
+	case XFRAME_I_DEVICE:
+		stat_count = XFRAME_I_STAT_LEN;
+	break;
+
+	case XFRAME_II_DEVICE:
+		stat_count = XFRAME_II_STAT_LEN;
+	break;
+	}
+
+	return stat_count;
 }
 
 static int s2io_ethtool_op_set_tx_csum(struct net_device *dev, u32 data)
@@ -5909,7 +6042,7 @@
 	clear_bit(0, &(nic->link_state));
 
 out_unlock:
-	rtnl_lock();
+	rtnl_unlock();
 }
 
 static int set_rxd_buffer_pointer(struct s2io_nic *sp, struct RxD_t *rxdp,
@@ -6066,10 +6199,13 @@
 					rx_blocks[j].rxds[k].virt_addr;
 				if(sp->rxd_mode >= RXD_MODE_3A)
 					ba = &mac_control->rings[i].ba[j][k];
-				set_rxd_buffer_pointer(sp, rxdp, ba,
+				if (set_rxd_buffer_pointer(sp, rxdp, ba,
 						       &skb,(u64 *)&temp0_64,
 						       (u64 *)&temp1_64,
-						       (u64 *)&temp2_64, size);
+						       (u64 *)&temp2_64,
+							size) == ENOMEM) {
+					return 0;
+				}
 
 				set_rxd_buffer_size(sp, rxdp, size);
 				wmb();
@@ -6112,7 +6248,7 @@
 		}
 	}
 	if (sp->intr_type == MSI_X) {
-		int i;
+		int i, msix_tx_cnt=0,msix_rx_cnt=0;
 
 		for (i=1; (sp->s2io_entries[i].in_use == MSIX_FLG); i++) {
 			if (sp->s2io_entries[i].type == MSIX_FIFO_TYPE) {
@@ -6121,16 +6257,36 @@
 				err = request_irq(sp->entries[i].vector,
 					  s2io_msix_fifo_handle, 0, sp->desc[i],
 						  sp->s2io_entries[i].arg);
-				DBG_PRINT(ERR_DBG, "%s @ 0x%llx\n", sp->desc[i],
-				(unsigned long long)sp->msix_info[i].addr);
+				/* If either data or addr is zero print it */
+				if(!(sp->msix_info[i].addr &&
+					sp->msix_info[i].data)) {
+					DBG_PRINT(ERR_DBG, "%s @ Addr:0x%llx"
+						"Data:0x%lx\n",sp->desc[i],
+						(unsigned long long)
+						sp->msix_info[i].addr,
+						(unsigned long)
+						ntohl(sp->msix_info[i].data));
+				} else {
+					msix_tx_cnt++;
+				}
 			} else {
 				sprintf(sp->desc[i], "%s:MSI-X-%d-RX",
 					dev->name, i);
 				err = request_irq(sp->entries[i].vector,
 					  s2io_msix_ring_handle, 0, sp->desc[i],
 						  sp->s2io_entries[i].arg);
-				DBG_PRINT(ERR_DBG, "%s @ 0x%llx\n", sp->desc[i],
-				(unsigned long long)sp->msix_info[i].addr);
+				/* If either data or addr is zero print it */
+				if(!(sp->msix_info[i].addr &&
+					sp->msix_info[i].data)) {
+					DBG_PRINT(ERR_DBG, "%s @ Addr:0x%llx"
+						"Data:0x%lx\n",sp->desc[i],
+						(unsigned long long)
+						sp->msix_info[i].addr,
+						(unsigned long)
+						ntohl(sp->msix_info[i].data));
+				} else {
+					msix_rx_cnt++;
+				}
 			}
 			if (err) {
 				DBG_PRINT(ERR_DBG,"%s:MSI-X-%d registration "
@@ -6140,6 +6296,8 @@
 			}
 			sp->s2io_entries[i].in_use = MSIX_REGISTERED_SUCCESS;
 		}
+		printk("MSI-X-TX %d entries enabled\n",msix_tx_cnt);
+		printk("MSI-X-RX %d entries enabled\n",msix_rx_cnt);
 	}
 	if (sp->intr_type == INTA) {
 		err = request_irq((int) sp->pdev->irq, s2io_isr, IRQF_SHARED,
@@ -6567,7 +6725,8 @@
 
 	if (!sp->lro) {
 		skb->protocol = eth_type_trans(skb, dev);
-		if (sp->vlgrp && RXD_GET_VLAN_TAG(rxdp->Control_2)) {
+		if ((sp->vlgrp && RXD_GET_VLAN_TAG(rxdp->Control_2) &&
+			vlan_strip_flag)) {
 			/* Queueing the vlan frame to the upper layer */
 			if (napi)
 				vlan_hwaccel_receive_skb(skb, sp->vlgrp,
@@ -6704,8 +6863,7 @@
 					"Defaulting to INTA\n");
 		*dev_intr_type = INTA;
 	}
-	if ( (rx_ring_num > 1) && (*dev_intr_type != INTA) )
-		napi = 0;
+
 	if (rx_ring_mode > 3) {
 		DBG_PRINT(ERR_DBG, "s2io: Requested ring mode not supported\n");
 		DBG_PRINT(ERR_DBG, "s2io: Defaulting to 3-buffer mode\n");
@@ -6715,6 +6873,37 @@
 }
 
 /**
+ * rts_ds_steer - Receive traffic steering based on IPv4 or IPv6 TOS
+ * or Traffic class respectively.
+ * @nic: device peivate variable
+ * Description: The function configures the receive steering to
+ * desired receive ring.
+ * Return Value:  SUCCESS on success and
+ * '-1' on failure (endian settings incorrect).
+ */
+static int rts_ds_steer(struct s2io_nic *nic, u8 ds_codepoint, u8 ring)
+{
+	struct XENA_dev_config __iomem *bar0 = nic->bar0;
+	register u64 val64 = 0;
+
+	if (ds_codepoint > 63)
+		return FAILURE;
+
+	val64 = RTS_DS_MEM_DATA(ring);
+	writeq(val64, &bar0->rts_ds_mem_data);
+
+	val64 = RTS_DS_MEM_CTRL_WE |
+		RTS_DS_MEM_CTRL_STROBE_NEW_CMD |
+		RTS_DS_MEM_CTRL_OFFSET(ds_codepoint);
+
+	writeq(val64, &bar0->rts_ds_mem_ctrl);
+
+	return wait_for_cmd_complete(&bar0->rts_ds_mem_ctrl,
+				RTS_DS_MEM_CTRL_STROBE_CMD_BEING_EXECUTED,
+				S2IO_BIT_RESET);
+}
+
+/**
  *  s2io_init_nic - Initialization of the adapter .
  *  @pdev : structure containing the PCI related information of the device.
  *  @pre: List of PCI devices supported by the driver listed in s2io_tbl.
@@ -7008,13 +7197,11 @@
 	    RMAC_ADDR_CMD_MEM_OFFSET(0 + MAC_MAC_ADDR_START_OFFSET);
 	writeq(val64, &bar0->rmac_addr_cmd_mem);
 	wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem,
-		      RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING);
+		      RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING, S2IO_BIT_RESET);
 	tmp64 = readq(&bar0->rmac_addr_data0_mem);
 	mac_down = (u32) tmp64;
 	mac_up = (u32) (tmp64 >> 32);
 
-	memset(sp->def_mac_addr[0].mac_addr, 0, sizeof(ETH_ALEN));
-
 	sp->def_mac_addr[0].mac_addr[3] = (u8) (mac_up);
 	sp->def_mac_addr[0].mac_addr[2] = (u8) (mac_up >> 8);
 	sp->def_mac_addr[0].mac_addr[1] = (u8) (mac_up >> 16);
diff --git a/drivers/net/s2io.h b/drivers/net/s2io.h
index 0de0c65..803137c 100644
--- a/drivers/net/s2io.h
+++ b/drivers/net/s2io.h
@@ -32,7 +32,8 @@
 #define FAILURE -1
 #define S2IO_MINUS_ONE 0xFFFFFFFFFFFFFFFFULL
 #define S2IO_MAX_PCI_CONFIG_SPACE_REINIT 100
-
+#define S2IO_BIT_RESET 1
+#define S2IO_BIT_SET 2
 #define CHECKBIT(value, nbit) (value & (1 << nbit))
 
 /* Maximum time to flicker LED when asked to identify NIC using ethtool */
@@ -296,6 +297,9 @@
 	struct xpakStat xpak_stat;
 };
 
+/* Default value for 'vlan_strip_tag' configuration parameter */
+#define NO_STRIP_IN_PROMISC 2
+
 /*
  * Structures representing different init time configuration
  * parameters of the NIC.
@@ -1005,7 +1009,8 @@
 static void s2io_card_down(struct s2io_nic *nic);
 static int s2io_card_up(struct s2io_nic *nic);
 static int get_xena_rev_id(struct pci_dev *pdev);
-static int wait_for_cmd_complete(void __iomem *addr, u64 busy_bit);
+static int wait_for_cmd_complete(void __iomem *addr, u64 busy_bit,
+					int bit_state);
 static int s2io_add_isr(struct s2io_nic * sp);
 static void s2io_rem_isr(struct s2io_nic * sp);
 
@@ -1019,6 +1024,7 @@
 static void update_L3L4_header(struct s2io_nic *sp, struct lro *lro);
 static void lro_append_pkt(struct s2io_nic *sp, struct lro *lro,
 			   struct sk_buff *skb, u32 tcp_len);
+static int rts_ds_steer(struct s2io_nic *nic, u8 ds_codepoint, u8 ring);
 
 #define s2io_tcp_mss(skb) skb_shinfo(skb)->gso_size
 #define s2io_udp_mss(skb) skb_shinfo(skb)->gso_size
diff --git a/drivers/net/sgiseeq.c b/drivers/net/sgiseeq.c
index a833e7f..52ed522 100644
--- a/drivers/net/sgiseeq.c
+++ b/drivers/net/sgiseeq.c
@@ -12,26 +12,15 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/socket.h>
-#include <linux/in.h>
-#include <linux/route.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/delay.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
-#include <linux/bitops.h>
 
-#include <asm/byteorder.h>
-#include <asm/io.h>
-#include <asm/system.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/sgi/hpc3.h>
 #include <asm/sgi/ip22.h>
-#include <asm/sgialib.h>
 
 #include "sgiseeq.h"
 
diff --git a/drivers/net/skfp/cfm.c b/drivers/net/skfp/cfm.c
index 4c8aaa7..5310d39 100644
--- a/drivers/net/skfp/cfm.c
+++ b/drivers/net/skfp/cfm.c
@@ -73,7 +73,7 @@
 /*
  * map from state to downstream port type
  */
-static const u_char cf_to_ptype[] = {
+static const unsigned char cf_to_ptype[] = {
 	TNONE,TNONE,TNONE,TNONE,TNONE,
 	TNONE,TB,TB,TS,
 	TA,TB,TS,TB
diff --git a/drivers/net/skge.c b/drivers/net/skge.c
index c3d2e0a..eea75a4 100644
--- a/drivers/net/skge.c
+++ b/drivers/net/skge.c
@@ -77,13 +77,13 @@
 	{ PCI_DEVICE(PCI_VENDOR_ID_3COM, PCI_DEVICE_ID_3COM_3C940B) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, PCI_DEVICE_ID_SYSKONNECT_GE) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, PCI_DEVICE_ID_SYSKONNECT_YU) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK, PCI_DEVICE_ID_DLINK_DGE510T), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK, PCI_DEVICE_ID_DLINK_DGE510T) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK, 0x4b01) },	/* DGE-530T */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4320) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x5005) }, /* Belkin */
 	{ PCI_DEVICE(PCI_VENDOR_ID_CNET, PCI_DEVICE_ID_CNET_GIGACARD) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_LINKSYS, PCI_DEVICE_ID_LINKSYS_EG1064) },
-	{ PCI_VENDOR_ID_LINKSYS, 0x1032, PCI_ANY_ID, 0x0015, },
+	{ PCI_VENDOR_ID_LINKSYS, 0x1032, PCI_ANY_ID, 0x0015 },
 	{ 0 }
 };
 MODULE_DEVICE_TABLE(pci, skge_id_table);
@@ -2767,6 +2767,17 @@
 	return err;
 }
 
+static const u8 pause_mc_addr[ETH_ALEN] = { 0x1, 0x80, 0xc2, 0x0, 0x0, 0x1 };
+
+static void genesis_add_filter(u8 filter[8], const u8 *addr)
+{
+	u32 crc, bit;
+
+	crc = ether_crc_le(ETH_ALEN, addr);
+	bit = ~crc & 0x3f;
+	filter[bit/8] |= 1 << (bit%8);
+}
+
 static void genesis_set_multicast(struct net_device *dev)
 {
 	struct skge_port *skge = netdev_priv(dev);
@@ -2788,24 +2799,33 @@
 		memset(filter, 0xff, sizeof(filter));
 	else {
 		memset(filter, 0, sizeof(filter));
-		for (i = 0; list && i < count; i++, list = list->next) {
-			u32 crc, bit;
-			crc = ether_crc_le(ETH_ALEN, list->dmi_addr);
-			bit = ~crc & 0x3f;
-			filter[bit/8] |= 1 << (bit%8);
-		}
+
+		if (skge->flow_status == FLOW_STAT_REM_SEND
+		    || skge->flow_status == FLOW_STAT_SYMMETRIC)
+			genesis_add_filter(filter, pause_mc_addr);
+
+		for (i = 0; list && i < count; i++, list = list->next)
+			genesis_add_filter(filter, list->dmi_addr);
 	}
 
 	xm_write32(hw, port, XM_MODE, mode);
 	xm_outhash(hw, port, XM_HSM, filter);
 }
 
+static void yukon_add_filter(u8 filter[8], const u8 *addr)
+{
+	 u32 bit = ether_crc(ETH_ALEN, addr) & 0x3f;
+	 filter[bit/8] |= 1 << (bit%8);
+}
+
 static void yukon_set_multicast(struct net_device *dev)
 {
 	struct skge_port *skge = netdev_priv(dev);
 	struct skge_hw *hw = skge->hw;
 	int port = skge->port;
 	struct dev_mc_list *list = dev->mc_list;
+	int rx_pause = (skge->flow_status == FLOW_STAT_REM_SEND
+			|| skge->flow_status == FLOW_STAT_SYMMETRIC);
 	u16 reg;
 	u8 filter[8];
 
@@ -2818,16 +2838,17 @@
 		reg &= ~(GM_RXCR_UCF_ENA | GM_RXCR_MCF_ENA);
 	else if (dev->flags & IFF_ALLMULTI)	/* all multicast */
 		memset(filter, 0xff, sizeof(filter));
-	else if (dev->mc_count == 0)		/* no multicast */
+	else if (dev->mc_count == 0 && !rx_pause)/* no multicast */
 		reg &= ~GM_RXCR_MCF_ENA;
 	else {
 		int i;
 		reg |= GM_RXCR_MCF_ENA;
 
-		for (i = 0; list && i < dev->mc_count; i++, list = list->next) {
-			u32 bit = ether_crc(ETH_ALEN, list->dmi_addr) & 0x3f;
-			filter[bit/8] |= 1 << (bit%8);
-		}
+		if (rx_pause)
+			yukon_add_filter(filter, pause_mc_addr);
+
+		for (i = 0; list && i < dev->mc_count; i++, list = list->next)
+			yukon_add_filter(filter, list->dmi_addr);
 	}
 
 
diff --git a/drivers/net/skge.h b/drivers/net/skge.h
index 17b1b47..e9354df 100644
--- a/drivers/net/skge.h
+++ b/drivers/net/skge.h
@@ -1849,8 +1849,7 @@
 			  GMR_FS_JABBER,
 /* Rx GMAC FIFO Flush Mask (default) */
 	RX_FF_FL_DEF_MSK = GMR_FS_CRC_ERR | GMR_FS_RX_FF_OV |GMR_FS_MII_ERR |
-			   GMR_FS_BAD_FC | GMR_FS_GOOD_FC | GMR_FS_UN_SIZE |
-			   GMR_FS_JABBER,
+			   GMR_FS_BAD_FC |  GMR_FS_UN_SIZE | GMR_FS_JABBER,
 };
 
 /*	RX_GMF_CTRL_T	32 bit	Rx GMAC FIFO Control/Test */
diff --git a/drivers/net/spider_net.c b/drivers/net/spider_net.c
index 64ed8ff..3b91af8 100644
--- a/drivers/net/spider_net.c
+++ b/drivers/net/spider_net.c
@@ -1,7 +1,8 @@
 /*
- * Network device driver for Cell Processor-Based Blade
+ * Network device driver for Cell Processor-Based Blade and Celleb platform
  *
  * (C) Copyright IBM Corp. 2005
+ * (C) Copyright 2006 TOSHIBA CORPORATION
  *
  * Authors : Utz Bacher <utz.bacher@de.ibm.com>
  *           Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
@@ -166,6 +167,41 @@
 }
 
 /**
+ * spider_net_setup_aneg - initial auto-negotiation setup
+ * @card: device structure
+ **/
+static void
+spider_net_setup_aneg(struct spider_net_card *card)
+{
+	struct mii_phy *phy = &card->phy;
+	u32 advertise = 0;
+	u16 bmcr, bmsr, stat1000, estat;
+
+	bmcr     = spider_net_read_phy(card->netdev, phy->mii_id, MII_BMCR);
+	bmsr     = spider_net_read_phy(card->netdev, phy->mii_id, MII_BMSR);
+	stat1000 = spider_net_read_phy(card->netdev, phy->mii_id, MII_STAT1000);
+	estat    = spider_net_read_phy(card->netdev, phy->mii_id, MII_ESTATUS);
+
+	if (bmsr & BMSR_10HALF)
+		advertise |= ADVERTISED_10baseT_Half;
+	if (bmsr & BMSR_10FULL)
+		advertise |= ADVERTISED_10baseT_Full;
+	if (bmsr & BMSR_100HALF)
+		advertise |= ADVERTISED_100baseT_Half;
+	if (bmsr & BMSR_100FULL)
+		advertise |= ADVERTISED_100baseT_Full;
+
+	if ((bmsr & BMSR_ESTATEN) && (estat & ESTATUS_1000_TFULL))
+		advertise |= SUPPORTED_1000baseT_Full;
+	if ((bmsr & BMSR_ESTATEN) && (estat & ESTATUS_1000_THALF))
+		advertise |= SUPPORTED_1000baseT_Half;
+
+	mii_phy_probe(phy, phy->mii_id);
+	phy->def->ops->setup_aneg(phy, advertise);
+
+}
+
+/**
  * spider_net_rx_irq_off - switch off rx irq on this spider card
  * @card: device structure
  *
@@ -263,9 +299,9 @@
  * returns the status as in the dmac_cmd_status field of the descriptor
  */
 static inline int
-spider_net_get_descr_status(struct spider_net_descr *descr)
+spider_net_get_descr_status(struct spider_net_hw_descr *hwdescr)
 {
-	return descr->dmac_cmd_status & SPIDER_NET_DESCR_IND_PROC_MASK;
+	return hwdescr->dmac_cmd_status & SPIDER_NET_DESCR_IND_PROC_MASK;
 }
 
 /**
@@ -283,12 +319,12 @@
 	descr = chain->ring;
 	do {
 		descr->bus_addr = 0;
-		descr->next_descr_addr = 0;
+		descr->hwdescr->next_descr_addr = 0;
 		descr = descr->next;
 	} while (descr != chain->ring);
 
 	dma_free_coherent(&card->pdev->dev, chain->num_desc,
-	    chain->ring, chain->dma_addr);
+	    chain->hwring, chain->dma_addr);
 }
 
 /**
@@ -307,31 +343,34 @@
 {
 	int i;
 	struct spider_net_descr *descr;
+	struct spider_net_hw_descr *hwdescr;
 	dma_addr_t buf;
 	size_t alloc_size;
 
-	alloc_size = chain->num_desc * sizeof (struct spider_net_descr);
+	alloc_size = chain->num_desc * sizeof(struct spider_net_hw_descr);
 
-	chain->ring = dma_alloc_coherent(&card->pdev->dev, alloc_size,
+	chain->hwring = dma_alloc_coherent(&card->pdev->dev, alloc_size,
 		&chain->dma_addr, GFP_KERNEL);
 
-	if (!chain->ring)
+	if (!chain->hwring)
 		return -ENOMEM;
 
-	descr = chain->ring;
-	memset(descr, 0, alloc_size);
+	memset(chain->ring, 0, chain->num_desc * sizeof(struct spider_net_descr));
 
 	/* Set up the hardware pointers in each descriptor */
+	descr = chain->ring;
+	hwdescr = chain->hwring;
 	buf = chain->dma_addr;
-	for (i=0; i < chain->num_desc; i++, descr++) {
-		descr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
+	for (i=0; i < chain->num_desc; i++, descr++, hwdescr++) {
+		hwdescr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
+		hwdescr->next_descr_addr = 0;
 
+		descr->hwdescr = hwdescr;
 		descr->bus_addr = buf;
-		descr->next_descr_addr = 0;
 		descr->next = descr + 1;
 		descr->prev = descr - 1;
 
-		buf += sizeof(struct spider_net_descr);
+		buf += sizeof(struct spider_net_hw_descr);
 	}
 	/* do actual circular list */
 	(descr-1)->next = chain->ring;
@@ -357,10 +396,11 @@
 	descr = card->rx_chain.head;
 	do {
 		if (descr->skb) {
-			dev_kfree_skb(descr->skb);
-			pci_unmap_single(card->pdev, descr->buf_addr,
+			pci_unmap_single(card->pdev, descr->hwdescr->buf_addr,
 					 SPIDER_NET_MAX_FRAME,
 					 PCI_DMA_BIDIRECTIONAL);
+			dev_kfree_skb(descr->skb);
+			descr->skb = NULL;
 		}
 		descr = descr->next;
 	} while (descr != card->rx_chain.head);
@@ -380,6 +420,7 @@
 spider_net_prepare_rx_descr(struct spider_net_card *card,
 			    struct spider_net_descr *descr)
 {
+	struct spider_net_hw_descr *hwdescr = descr->hwdescr;
 	dma_addr_t buf;
 	int offset;
 	int bufsize;
@@ -398,11 +439,11 @@
 		card->spider_stats.alloc_rx_skb_error++;
 		return -ENOMEM;
 	}
-	descr->buf_size = bufsize;
-	descr->result_size = 0;
-	descr->valid_size = 0;
-	descr->data_status = 0;
-	descr->data_error = 0;
+	hwdescr->buf_size = bufsize;
+	hwdescr->result_size = 0;
+	hwdescr->valid_size = 0;
+	hwdescr->data_status = 0;
+	hwdescr->data_error = 0;
 
 	offset = ((unsigned long)descr->skb->data) &
 		(SPIDER_NET_RXBUF_ALIGN - 1);
@@ -411,21 +452,22 @@
 	/* iommu-map the skb */
 	buf = pci_map_single(card->pdev, descr->skb->data,
 			SPIDER_NET_MAX_FRAME, PCI_DMA_FROMDEVICE);
-	descr->buf_addr = buf;
 	if (pci_dma_mapping_error(buf)) {
 		dev_kfree_skb_any(descr->skb);
+		descr->skb = NULL;
 		if (netif_msg_rx_err(card) && net_ratelimit())
 			pr_err("Could not iommu-map rx buffer\n");
 		card->spider_stats.rx_iommu_map_error++;
-		descr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
+		hwdescr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
 	} else {
-		descr->next_descr_addr = 0;
+		hwdescr->buf_addr = buf;
+		hwdescr->next_descr_addr = 0;
 		wmb();
-		descr->dmac_cmd_status = SPIDER_NET_DESCR_CARDOWNED |
+		hwdescr->dmac_cmd_status = SPIDER_NET_DESCR_CARDOWNED |
 					 SPIDER_NET_DMAC_NOINTR_COMPLETE;
 
 		wmb();
-		descr->prev->next_descr_addr = descr->bus_addr;
+		descr->prev->hwdescr->next_descr_addr = descr->bus_addr;
 	}
 
 	return 0;
@@ -481,7 +523,7 @@
 	if (!spin_trylock_irqsave(&chain->lock, flags))
 		return;
 
-	while (spider_net_get_descr_status(chain->head) ==
+	while (spider_net_get_descr_status(chain->head->hwdescr) ==
 			SPIDER_NET_DESCR_NOT_IN_USE) {
 		if (spider_net_prepare_rx_descr(card, chain->head))
 			break;
@@ -642,7 +684,9 @@
 spider_net_prepare_tx_descr(struct spider_net_card *card,
 			    struct sk_buff *skb)
 {
+	struct spider_net_descr_chain *chain = &card->tx_chain;
 	struct spider_net_descr *descr;
+	struct spider_net_hw_descr *hwdescr;
 	dma_addr_t buf;
 	unsigned long flags;
 
@@ -655,32 +699,39 @@
 		return -ENOMEM;
 	}
 
-	spin_lock_irqsave(&card->tx_chain.lock, flags);
+	spin_lock_irqsave(&chain->lock, flags);
 	descr = card->tx_chain.head;
-	card->tx_chain.head = descr->next;
+	if (descr->next == chain->tail->prev) {
+		spin_unlock_irqrestore(&chain->lock, flags);
+		pci_unmap_single(card->pdev, buf, skb->len, PCI_DMA_TODEVICE);
+		return -ENOMEM;
+	}
+	hwdescr = descr->hwdescr;
+	chain->head = descr->next;
 
-	descr->buf_addr = buf;
-	descr->buf_size = skb->len;
-	descr->next_descr_addr = 0;
 	descr->skb = skb;
-	descr->data_status = 0;
+	hwdescr->buf_addr = buf;
+	hwdescr->buf_size = skb->len;
+	hwdescr->next_descr_addr = 0;
+	hwdescr->data_status = 0;
 
-	descr->dmac_cmd_status =
+	hwdescr->dmac_cmd_status =
 			SPIDER_NET_DESCR_CARDOWNED | SPIDER_NET_DMAC_NOCS;
-	spin_unlock_irqrestore(&card->tx_chain.lock, flags);
+	spin_unlock_irqrestore(&chain->lock, flags);
 
 	if (skb->protocol == htons(ETH_P_IP))
 		switch (skb->nh.iph->protocol) {
 		case IPPROTO_TCP:
-			descr->dmac_cmd_status |= SPIDER_NET_DMAC_TCP;
+			hwdescr->dmac_cmd_status |= SPIDER_NET_DMAC_TCP;
 			break;
 		case IPPROTO_UDP:
-			descr->dmac_cmd_status |= SPIDER_NET_DMAC_UDP;
+			hwdescr->dmac_cmd_status |= SPIDER_NET_DMAC_UDP;
 			break;
 		}
 
 	/* Chain the bus address, so that the DMA engine finds this descr. */
-	descr->prev->next_descr_addr = descr->bus_addr;
+	wmb();
+	descr->prev->hwdescr->next_descr_addr = descr->bus_addr;
 
 	card->netdev->trans_start = jiffies; /* set netdev watchdog timer */
 	return 0;
@@ -689,16 +740,17 @@
 static int
 spider_net_set_low_watermark(struct spider_net_card *card)
 {
+	struct spider_net_descr *descr = card->tx_chain.tail;
+	struct spider_net_hw_descr *hwdescr;
 	unsigned long flags;
 	int status;
 	int cnt=0;
 	int i;
-	struct spider_net_descr *descr = card->tx_chain.tail;
 
 	/* Measure the length of the queue. Measurement does not
 	 * need to be precise -- does not need a lock. */
 	while (descr != card->tx_chain.head) {
-		status = descr->dmac_cmd_status & SPIDER_NET_DESCR_NOT_IN_USE;
+		status = descr->hwdescr->dmac_cmd_status & SPIDER_NET_DESCR_NOT_IN_USE;
 		if (status == SPIDER_NET_DESCR_NOT_IN_USE)
 			break;
 		descr = descr->next;
@@ -717,10 +769,12 @@
 
 	/* Set the new watermark, clear the old watermark */
 	spin_lock_irqsave(&card->tx_chain.lock, flags);
-	descr->dmac_cmd_status |= SPIDER_NET_DESCR_TXDESFLG;
-	if (card->low_watermark && card->low_watermark != descr)
-		card->low_watermark->dmac_cmd_status =
-		     card->low_watermark->dmac_cmd_status & ~SPIDER_NET_DESCR_TXDESFLG;
+	descr->hwdescr->dmac_cmd_status |= SPIDER_NET_DESCR_TXDESFLG;
+	if (card->low_watermark && card->low_watermark != descr) {
+		hwdescr = card->low_watermark->hwdescr;
+		hwdescr->dmac_cmd_status =
+		     hwdescr->dmac_cmd_status & ~SPIDER_NET_DESCR_TXDESFLG;
+	}
 	card->low_watermark = descr;
 	spin_unlock_irqrestore(&card->tx_chain.lock, flags);
 	return cnt;
@@ -743,16 +797,22 @@
 {
 	struct spider_net_descr_chain *chain = &card->tx_chain;
 	struct spider_net_descr *descr;
+	struct spider_net_hw_descr *hwdescr;
 	struct sk_buff *skb;
 	u32 buf_addr;
 	unsigned long flags;
 	int status;
 
-	while (chain->tail != chain->head) {
+	while (1) {
 		spin_lock_irqsave(&chain->lock, flags);
+		if (chain->tail == chain->head) {
+			spin_unlock_irqrestore(&chain->lock, flags);
+			return 0;
+		}
 		descr = chain->tail;
+		hwdescr = descr->hwdescr;
 
-		status = spider_net_get_descr_status(descr);
+		status = spider_net_get_descr_status(hwdescr);
 		switch (status) {
 		case SPIDER_NET_DESCR_COMPLETE:
 			card->netdev_stats.tx_packets++;
@@ -788,9 +848,10 @@
 		}
 
 		chain->tail = descr->next;
-		descr->dmac_cmd_status |= SPIDER_NET_DESCR_NOT_IN_USE;
+		hwdescr->dmac_cmd_status |= SPIDER_NET_DESCR_NOT_IN_USE;
 		skb = descr->skb;
-		buf_addr = descr->buf_addr;
+		descr->skb = NULL;
+		buf_addr = hwdescr->buf_addr;
 		spin_unlock_irqrestore(&chain->lock, flags);
 
 		/* unmap the skb */
@@ -826,7 +887,7 @@
 
 	descr = card->tx_chain.tail;
 	for (;;) {
-		if (spider_net_get_descr_status(descr) ==
+		if (spider_net_get_descr_status(descr->hwdescr) ==
 				SPIDER_NET_DESCR_CARDOWNED) {
 			spider_net_write_reg(card, SPIDER_NET_GDTDCHA,
 					descr->bus_addr);
@@ -855,13 +916,10 @@
 {
 	int cnt;
 	struct spider_net_card *card = netdev_priv(netdev);
-	struct spider_net_descr_chain *chain = &card->tx_chain;
 
 	spider_net_release_tx_chain(card, 0);
 
-	if ((chain->head->next == chain->tail->prev) ||
-	   (spider_net_prepare_tx_descr(card, skb) != 0)) {
-
+	if (spider_net_prepare_tx_descr(card, skb) != 0) {
 		card->netdev_stats.tx_dropped++;
 		netif_stop_queue(netdev);
 		return NETDEV_TX_BUSY;
@@ -922,17 +980,18 @@
 spider_net_pass_skb_up(struct spider_net_descr *descr,
 		       struct spider_net_card *card)
 {
+	struct spider_net_hw_descr *hwdescr= descr->hwdescr;
 	struct sk_buff *skb;
 	struct net_device *netdev;
 	u32 data_status, data_error;
 
-	data_status = descr->data_status;
-	data_error = descr->data_error;
+	data_status = hwdescr->data_status;
+	data_error = hwdescr->data_error;
 	netdev = card->netdev;
 
 	skb = descr->skb;
 	skb->dev = netdev;
-	skb_put(skb, descr->valid_size);
+	skb_put(skb, hwdescr->valid_size);
 
 	/* the card seems to add 2 bytes of junk in front
 	 * of the ethernet frame */
@@ -994,23 +1053,25 @@
 #endif
 
 /**
- * spider_net_decode_one_descr - processes an rx descriptor
+ * spider_net_decode_one_descr - processes an RX descriptor
  * @card: card structure
  *
- * Returns 1 if a packet has been sent to the stack, otherwise 0
+ * Returns 1 if a packet has been sent to the stack, otherwise 0.
  *
- * Processes an rx descriptor by iommu-unmapping the data buffer and passing
- * the packet up to the stack. This function is called in softirq
- * context, e.g. either bottom half from interrupt or NAPI polling context
+ * Processes an RX descriptor by iommu-unmapping the data buffer
+ * and passing the packet up to the stack. This function is called
+ * in softirq context, e.g. either bottom half from interrupt or
+ * NAPI polling context.
  */
 static int
 spider_net_decode_one_descr(struct spider_net_card *card)
 {
 	struct spider_net_descr_chain *chain = &card->rx_chain;
 	struct spider_net_descr *descr = chain->tail;
+	struct spider_net_hw_descr *hwdescr = descr->hwdescr;
 	int status;
 
-	status = spider_net_get_descr_status(descr);
+	status = spider_net_get_descr_status(hwdescr);
 
 	/* Nothing in the descriptor, or ring must be empty */
 	if ((status == SPIDER_NET_DESCR_CARDOWNED) ||
@@ -1021,7 +1082,7 @@
 	chain->tail = descr->next;
 
 	/* unmap descriptor */
-	pci_unmap_single(card->pdev, descr->buf_addr,
+	pci_unmap_single(card->pdev, hwdescr->buf_addr,
 			SPIDER_NET_MAX_FRAME, PCI_DMA_FROMDEVICE);
 
 	if ( (status == SPIDER_NET_DESCR_RESPONSE_ERROR) ||
@@ -1037,34 +1098,33 @@
 	if ( (status != SPIDER_NET_DESCR_COMPLETE) &&
 	     (status != SPIDER_NET_DESCR_FRAME_END) ) {
 		if (netif_msg_rx_err(card))
-			pr_err("%s: RX descriptor with unkown state %d\n",
+			pr_err("%s: RX descriptor with unknown state %d\n",
 			       card->netdev->name, status);
 		card->spider_stats.rx_desc_unk_state++;
 		goto bad_desc;
 	}
 
 	/* The cases we'll throw away the packet immediately */
-	if (descr->data_error & SPIDER_NET_DESTROY_RX_FLAGS) {
+	if (hwdescr->data_error & SPIDER_NET_DESTROY_RX_FLAGS) {
 		if (netif_msg_rx_err(card))
 			pr_err("%s: error in received descriptor found, "
 			       "data_status=x%08x, data_error=x%08x\n",
 			       card->netdev->name,
-			       descr->data_status, descr->data_error);
+			       hwdescr->data_status, hwdescr->data_error);
 		goto bad_desc;
 	}
 
-	if (descr->dmac_cmd_status & 0xfefe) {
+	if (hwdescr->dmac_cmd_status & 0xfefe) {
 		pr_err("%s: bad status, cmd_status=x%08x\n",
 			       card->netdev->name,
-			       descr->dmac_cmd_status);
-		pr_err("buf_addr=x%08x\n", descr->buf_addr);
-		pr_err("buf_size=x%08x\n", descr->buf_size);
-		pr_err("next_descr_addr=x%08x\n", descr->next_descr_addr);
-		pr_err("result_size=x%08x\n", descr->result_size);
-		pr_err("valid_size=x%08x\n", descr->valid_size);
-		pr_err("data_status=x%08x\n", descr->data_status);
-		pr_err("data_error=x%08x\n", descr->data_error);
-		pr_err("bus_addr=x%08x\n", descr->bus_addr);
+			       hwdescr->dmac_cmd_status);
+		pr_err("buf_addr=x%08x\n", hwdescr->buf_addr);
+		pr_err("buf_size=x%08x\n", hwdescr->buf_size);
+		pr_err("next_descr_addr=x%08x\n", hwdescr->next_descr_addr);
+		pr_err("result_size=x%08x\n", hwdescr->result_size);
+		pr_err("valid_size=x%08x\n", hwdescr->valid_size);
+		pr_err("data_status=x%08x\n", hwdescr->data_status);
+		pr_err("data_error=x%08x\n", hwdescr->data_error);
 		pr_err("which=%ld\n", descr - card->rx_chain.ring);
 
 		card->spider_stats.rx_desc_error++;
@@ -1073,12 +1133,13 @@
 
 	/* Ok, we've got a packet in descr */
 	spider_net_pass_skb_up(descr, card);
-	descr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
+	hwdescr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
 	return 1;
 
 bad_desc:
 	dev_kfree_skb_irq(descr->skb);
-	descr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
+	descr->skb = NULL;
+	hwdescr->dmac_cmd_status = SPIDER_NET_DESCR_NOT_IN_USE;
 	return 0;
 }
 
@@ -1248,6 +1309,33 @@
 }
 
 /**
+ * spider_net_link_reset
+ * @netdev: net device structure
+ *
+ * This is called when the PHY_LINK signal is asserted. For the blade this is
+ * not connected so we should never get here.
+ *
+ */
+static void
+spider_net_link_reset(struct net_device *netdev)
+{
+
+	struct spider_net_card *card = netdev_priv(netdev);
+
+	del_timer_sync(&card->aneg_timer);
+
+	/* clear interrupt, block further interrupts */
+	spider_net_write_reg(card, SPIDER_NET_GMACST,
+			     spider_net_read_reg(card, SPIDER_NET_GMACST));
+	spider_net_write_reg(card, SPIDER_NET_GMACINTEN, 0);
+
+	/* reset phy and setup aneg */
+	spider_net_setup_aneg(card);
+	mod_timer(&card->aneg_timer, jiffies + SPIDER_NET_ANEG_TIMER);
+
+}
+
+/**
  * spider_net_handle_error_irq - handles errors raised by an interrupt
  * @card: card structure
  * @status_reg: interrupt status register 0 (GHIINT0STS)
@@ -1359,8 +1447,8 @@
 				switch (i)
 	{
 	case SPIDER_NET_GTMFLLINT:
-		if (netif_msg_intr(card) && net_ratelimit())
-			pr_err("Spider TX RAM full\n");
+		/* TX RAM full may happen on a usual case.
+		 * Logging is not needed. */
 		show_error = 0;
 		break;
 	case SPIDER_NET_GRFDFLLINT: /* fallthrough */
@@ -1500,6 +1588,9 @@
 	if (status_reg & SPIDER_NET_TXINT)
 		netif_rx_schedule(netdev);
 
+	if (status_reg & SPIDER_NET_LINKINT)
+		spider_net_link_reset(netdev);
+
 	if (status_reg & SPIDER_NET_ERRINT )
 		spider_net_handle_error_irq(card, status_reg);
 
@@ -1540,6 +1631,11 @@
 
 	spider_net_write_reg(card, SPIDER_NET_CKRCTRL,
 			     SPIDER_NET_CKRCTRL_RUN_VALUE);
+
+	/* trigger ETOMOD signal */
+	spider_net_write_reg(card, SPIDER_NET_GMACOPEMD,
+		spider_net_read_reg(card, SPIDER_NET_GMACOPEMD) | 0x4);
+
 }
 
 /**
@@ -1624,8 +1720,6 @@
 
 	spider_net_write_reg(card, SPIDER_NET_GMACLENLMT,
 			     SPIDER_NET_LENLMT_VALUE);
-	spider_net_write_reg(card, SPIDER_NET_GMACMODE,
-			     SPIDER_NET_MACMODE_VALUE);
 	spider_net_write_reg(card, SPIDER_NET_GMACOPEMD,
 			     SPIDER_NET_OPMODE_VALUE);
 
@@ -1642,98 +1736,6 @@
 }
 
 /**
- * spider_net_open - called upon ifonfig up
- * @netdev: interface device structure
- *
- * returns 0 on success, <0 on failure
- *
- * spider_net_open allocates all the descriptors and memory needed for
- * operation, sets up multicast list and enables interrupts
- */
-int
-spider_net_open(struct net_device *netdev)
-{
-	struct spider_net_card *card = netdev_priv(netdev);
-	int result;
-
-	result = spider_net_init_chain(card, &card->tx_chain);
-	if (result)
-		goto alloc_tx_failed;
-	card->low_watermark = NULL;
-
-	result = spider_net_init_chain(card, &card->rx_chain);
-	if (result)
-		goto alloc_rx_failed;
-
-	/* Allocate rx skbs */
-	if (spider_net_alloc_rx_skbs(card))
-		goto alloc_skbs_failed;
-
-	spider_net_set_multi(netdev);
-
-	/* further enhancement: setup hw vlan, if needed */
-
-	result = -EBUSY;
-	if (request_irq(netdev->irq, spider_net_interrupt,
-			     IRQF_SHARED, netdev->name, netdev))
-		goto register_int_failed;
-
-	spider_net_enable_card(card);
-
-	netif_start_queue(netdev);
-	netif_carrier_on(netdev);
-	netif_poll_enable(netdev);
-
-	return 0;
-
-register_int_failed:
-	spider_net_free_rx_chain_contents(card);
-alloc_skbs_failed:
-	spider_net_free_chain(card, &card->rx_chain);
-alloc_rx_failed:
-	spider_net_free_chain(card, &card->tx_chain);
-alloc_tx_failed:
-	return result;
-}
-
-/**
- * spider_net_setup_phy - setup PHY
- * @card: card structure
- *
- * returns 0 on success, <0 on failure
- *
- * spider_net_setup_phy is used as part of spider_net_probe. Sets
- * the PHY to 1000 Mbps
- **/
-static int
-spider_net_setup_phy(struct spider_net_card *card)
-{
-	struct mii_phy *phy = &card->phy;
-
-	spider_net_write_reg(card, SPIDER_NET_GDTDMASEL,
-			     SPIDER_NET_DMASEL_VALUE);
-	spider_net_write_reg(card, SPIDER_NET_GPCCTRL,
-			     SPIDER_NET_PHY_CTRL_VALUE);
-	phy->mii_id = 1;
-	phy->dev = card->netdev;
-	phy->mdio_read = spider_net_read_phy;
-	phy->mdio_write = spider_net_write_phy;
-
-	mii_phy_probe(phy, phy->mii_id);
-
-	if (phy->def->ops->setup_forced)
-		phy->def->ops->setup_forced(phy, SPEED_1000, DUPLEX_FULL);
-
-	phy->def->ops->enable_fiber(phy);
-
-	phy->def->ops->read_link(phy);
-	pr_info("Found %s with %i Mbps, %s-duplex.\n", phy->def->name,
-		phy->speed, phy->duplex==1 ? "Full" : "Half");
-
-	return 0;
-}
-
-/**
  * spider_net_download_firmware - loads firmware into the adapter
  * @card: card structure
  * @firmware_ptr: pointer to firmware data
@@ -1852,6 +1854,179 @@
 }
 
 /**
+ * spider_net_open - called upon ifonfig up
+ * @netdev: interface device structure
+ *
+ * returns 0 on success, <0 on failure
+ *
+ * spider_net_open allocates all the descriptors and memory needed for
+ * operation, sets up multicast list and enables interrupts
+ */
+int
+spider_net_open(struct net_device *netdev)
+{
+	struct spider_net_card *card = netdev_priv(netdev);
+	int result;
+
+	result = spider_net_init_firmware(card);
+	if (result)
+		goto init_firmware_failed;
+
+	/* start probing with copper */
+	spider_net_setup_aneg(card);
+	if (card->phy.def->phy_id)
+		mod_timer(&card->aneg_timer, jiffies + SPIDER_NET_ANEG_TIMER);
+
+	result = spider_net_init_chain(card, &card->tx_chain);
+	if (result)
+		goto alloc_tx_failed;
+	card->low_watermark = NULL;
+
+	result = spider_net_init_chain(card, &card->rx_chain);
+	if (result)
+		goto alloc_rx_failed;
+
+	/* Allocate rx skbs */
+	if (spider_net_alloc_rx_skbs(card))
+		goto alloc_skbs_failed;
+
+	spider_net_set_multi(netdev);
+
+	/* further enhancement: setup hw vlan, if needed */
+
+	result = -EBUSY;
+	if (request_irq(netdev->irq, spider_net_interrupt,
+			     IRQF_SHARED, netdev->name, netdev))
+		goto register_int_failed;
+
+	spider_net_enable_card(card);
+
+	netif_start_queue(netdev);
+	netif_carrier_on(netdev);
+	netif_poll_enable(netdev);
+
+	return 0;
+
+register_int_failed:
+	spider_net_free_rx_chain_contents(card);
+alloc_skbs_failed:
+	spider_net_free_chain(card, &card->rx_chain);
+alloc_rx_failed:
+	spider_net_free_chain(card, &card->tx_chain);
+alloc_tx_failed:
+	del_timer_sync(&card->aneg_timer);
+init_firmware_failed:
+	return result;
+}
+
+/**
+ * spider_net_link_phy
+ * @data: used for pointer to card structure
+ *
+ */
+static void spider_net_link_phy(unsigned long data)
+{
+	struct spider_net_card *card = (struct spider_net_card *)data;
+	struct mii_phy *phy = &card->phy;
+
+	/* if link didn't come up after SPIDER_NET_ANEG_TIMEOUT tries, setup phy again */
+	if (card->aneg_count > SPIDER_NET_ANEG_TIMEOUT) {
+
+		pr_info("%s: link is down trying to bring it up\n", card->netdev->name);
+
+		switch (card->medium) {
+		case BCM54XX_COPPER:
+			/* enable fiber with autonegotiation first */
+			if (phy->def->ops->enable_fiber)
+				phy->def->ops->enable_fiber(phy, 1);
+			card->medium = BCM54XX_FIBER;
+			break;
+
+		case BCM54XX_FIBER:
+			/* fiber didn't come up, try to disable fiber autoneg */
+			if (phy->def->ops->enable_fiber)
+				phy->def->ops->enable_fiber(phy, 0);
+			card->medium = BCM54XX_UNKNOWN;
+			break;
+
+		case BCM54XX_UNKNOWN:
+			/* copper, fiber with and without failed,
+			 * retry from beginning */
+			spider_net_setup_aneg(card);
+			card->medium = BCM54XX_COPPER;
+			break;
+		}
+
+		card->aneg_count = 0;
+		mod_timer(&card->aneg_timer, jiffies + SPIDER_NET_ANEG_TIMER);
+		return;
+	}
+
+	/* link still not up, try again later */
+	if (!(phy->def->ops->poll_link(phy))) {
+		card->aneg_count++;
+		mod_timer(&card->aneg_timer, jiffies + SPIDER_NET_ANEG_TIMER);
+		return;
+	}
+
+	/* link came up, get abilities */
+	phy->def->ops->read_link(phy);
+
+	spider_net_write_reg(card, SPIDER_NET_GMACST,
+			     spider_net_read_reg(card, SPIDER_NET_GMACST));
+	spider_net_write_reg(card, SPIDER_NET_GMACINTEN, 0x4);
+
+	if (phy->speed == 1000)
+		spider_net_write_reg(card, SPIDER_NET_GMACMODE, 0x00000001);
+	else
+		spider_net_write_reg(card, SPIDER_NET_GMACMODE, 0);
+
+	card->aneg_count = 0;
+
+	pr_debug("Found %s with %i Mbps, %s-duplex %sautoneg.\n",
+		phy->def->name, phy->speed, phy->duplex==1 ? "Full" : "Half",
+		phy->autoneg==1 ? "" : "no ");
+
+	return;
+}
+
+/**
+ * spider_net_setup_phy - setup PHY
+ * @card: card structure
+ *
+ * returns 0 on success, <0 on failure
+ *
+ * spider_net_setup_phy is used as part of spider_net_probe.
+ **/
+static int
+spider_net_setup_phy(struct spider_net_card *card)
+{
+	struct mii_phy *phy = &card->phy;
+
+	spider_net_write_reg(card, SPIDER_NET_GDTDMASEL,
+			     SPIDER_NET_DMASEL_VALUE);
+	spider_net_write_reg(card, SPIDER_NET_GPCCTRL,
+			     SPIDER_NET_PHY_CTRL_VALUE);
+
+	phy->dev = card->netdev;
+	phy->mdio_read = spider_net_read_phy;
+	phy->mdio_write = spider_net_write_phy;
+
+	for (phy->mii_id = 1; phy->mii_id <= 31; phy->mii_id++) {
+		unsigned short id;
+		id = spider_net_read_phy(card->netdev, phy->mii_id, MII_BMSR);
+		if (id != 0x0000 && id != 0xffff) {
+			if (!mii_phy_probe(phy, phy->mii_id)) {
+				pr_info("Found %s.\n", phy->def->name);
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/**
  * spider_net_workaround_rxramfull - work around firmware bug
  * @card: card structure
  *
@@ -1900,14 +2075,15 @@
 	netif_carrier_off(netdev);
 	netif_stop_queue(netdev);
 	del_timer_sync(&card->tx_timer);
+	del_timer_sync(&card->aneg_timer);
 
 	/* disable/mask all interrupts */
 	spider_net_write_reg(card, SPIDER_NET_GHIINT0MSK, 0);
 	spider_net_write_reg(card, SPIDER_NET_GHIINT1MSK, 0);
 	spider_net_write_reg(card, SPIDER_NET_GHIINT2MSK, 0);
+	spider_net_write_reg(card, SPIDER_NET_GMACINTEN, 0);
 
-	/* free_irq(netdev->irq, netdev);*/
-	free_irq(to_pci_dev(netdev->dev.parent)->irq, netdev);
+	free_irq(netdev->irq, netdev);
 
 	spider_net_write_reg(card, SPIDER_NET_GDTDMACCNTR,
 			     SPIDER_NET_DMA_TX_FEND_VALUE);
@@ -1919,8 +2095,6 @@
 	spider_net_release_tx_chain(card, 1);
 	spider_net_free_rx_chain_contents(card);
 
-	spider_net_free_rx_chain_contents(card);
-
 	spider_net_free_chain(card, &card->tx_chain);
 	spider_net_free_chain(card, &card->rx_chain);
 
@@ -1952,8 +2126,6 @@
 
 	if (spider_net_setup_phy(card))
 		goto out;
-	if (spider_net_init_firmware(card))
-		goto out;
 
 	spider_net_open(netdev);
 	spider_net_kick_tx_dma(card);
@@ -2046,10 +2218,12 @@
 	card->tx_timer.data = (unsigned long) card;
 	netdev->irq = card->pdev->irq;
 
-	card->options.rx_csum = SPIDER_NET_RX_CSUM_DEFAULT;
+	card->aneg_count = 0;
+	init_timer(&card->aneg_timer);
+	card->aneg_timer.function = spider_net_link_phy;
+	card->aneg_timer.data = (unsigned long) card;
 
-	card->tx_chain.num_desc = tx_descriptors;
-	card->rx_chain.num_desc = rx_descriptors;
+	card->options.rx_csum = SPIDER_NET_RX_CSUM_DEFAULT;
 
 	spider_net_setup_netdev_ops(netdev);
 
@@ -2098,8 +2272,11 @@
 {
 	struct net_device *netdev;
 	struct spider_net_card *card;
+	size_t alloc_size;
 
-	netdev = alloc_etherdev(sizeof(struct spider_net_card));
+	alloc_size = sizeof(struct spider_net_card) +
+	   (tx_descriptors + rx_descriptors) * sizeof(struct spider_net_descr);
+	netdev = alloc_etherdev(alloc_size);
 	if (!netdev)
 		return NULL;
 
@@ -2110,6 +2287,11 @@
 	init_waitqueue_head(&card->waitq);
 	atomic_set(&card->tx_timeout_task_counter, 0);
 
+	card->rx_chain.num_desc = rx_descriptors;
+	card->rx_chain.ring = card->darray;
+	card->tx_chain.num_desc = tx_descriptors;
+	card->tx_chain.ring = card->darray + rx_descriptors;
+
 	return card;
 }
 
@@ -2220,10 +2402,6 @@
 	if (err)
 		goto out_undo_pci;
 
-	err = spider_net_init_firmware(card);
-	if (err)
-		goto out_undo_pci;
-
 	err = spider_net_setup_netdev(card);
 	if (err)
 		goto out_undo_pci;
diff --git a/drivers/net/spider_net.h b/drivers/net/spider_net.h
index 2fec5cf..4a1e0d2 100644
--- a/drivers/net/spider_net.h
+++ b/drivers/net/spider_net.h
@@ -1,7 +1,8 @@
 /*
- * Network device driver for Cell Processor-Based Blade
+ * Network device driver for Cell Processor-Based Blade and Celleb platform
  *
  * (C) Copyright IBM Corp. 2005
+ * (C) Copyright 2006 TOSHIBA CORPORATION
  *
  * Authors : Utz Bacher <utz.bacher@de.ibm.com>
  *           Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
@@ -24,7 +25,7 @@
 #ifndef _SPIDER_NET_H
 #define _SPIDER_NET_H
 
-#define VERSION "1.6 B"
+#define VERSION "2.0 A"
 
 #include "sungem_phy.h"
 
@@ -50,6 +51,8 @@
 #define SPIDER_NET_TX_DESCRIPTORS_MAX		512
 
 #define SPIDER_NET_TX_TIMER			(HZ/5)
+#define SPIDER_NET_ANEG_TIMER			(HZ)
+#define SPIDER_NET_ANEG_TIMEOUT			2
 
 #define SPIDER_NET_RX_CSUM_DEFAULT		1
 
@@ -104,6 +107,7 @@
 
 #define SPIDER_NET_GMACOPEMD		0x00000100
 #define SPIDER_NET_GMACLENLMT		0x00000108
+#define SPIDER_NET_GMACST		0x00000110
 #define SPIDER_NET_GMACINTEN		0x00000118
 #define SPIDER_NET_GMACPHYCTRL		0x00000120
 
@@ -181,7 +185,8 @@
 
 /* pause frames: automatic, no upper retransmission count */
 /* outside loopback mode: ETOMOD signal dont matter, not connected */
-#define SPIDER_NET_OPMODE_VALUE		0x00000063
+/* ETOMOD signal is brought to PHY reset. bit 2 must be 1 in Celleb */
+#define SPIDER_NET_OPMODE_VALUE		0x00000067
 /*#define SPIDER_NET_OPMODE_VALUE		0x001b0062*/
 #define SPIDER_NET_LENLMT_VALUE		0x00000908
 
@@ -333,9 +338,12 @@
 /* We rely on flagged descriptor interrupts */
 #define SPIDER_NET_RXINT	( (1 << SPIDER_NET_GDAFDCINT) )
 
+#define SPIDER_NET_LINKINT	( 1 << SPIDER_NET_GMAC2INT )
+
 #define SPIDER_NET_ERRINT	( 0xffffffff & \
 				  (~SPIDER_NET_TXINT) & \
-				  (~SPIDER_NET_RXINT) )
+				  (~SPIDER_NET_RXINT) & \
+				  (~SPIDER_NET_LINKINT) )
 
 #define SPIDER_NET_GPREXEC			0x80000000
 #define SPIDER_NET_GPRDAT_MASK			0x0000ffff
@@ -356,8 +364,8 @@
 #define SPIDER_NET_DESCR_NOT_IN_USE		0xF0000000
 #define SPIDER_NET_DESCR_TXDESFLG		0x00800000
 
-struct spider_net_descr {
-	/* as defined by the hardware */
+/* Descriptor, as defined by the hardware */
+struct spider_net_hw_descr {
 	u32 buf_addr;
 	u32 buf_size;
 	u32 next_descr_addr;
@@ -366,13 +374,15 @@
 	u32 valid_size;	/* all zeroes for tx */
 	u32 data_status;
 	u32 data_error;	/* all zeroes for tx */
+} __attribute__((aligned(32)));
 
-	/* used in the driver */
+struct spider_net_descr {
+	struct spider_net_hw_descr *hwdescr;
 	struct sk_buff *skb;
 	u32 bus_addr;
 	struct spider_net_descr *next;
 	struct spider_net_descr *prev;
-} __attribute__((aligned(32)));
+};
 
 struct spider_net_descr_chain {
 	spinlock_t lock;
@@ -380,6 +390,7 @@
 	struct spider_net_descr *tail;
 	struct spider_net_descr *ring;
 	int num_desc;
+	struct spider_net_hw_descr *hwring;
 	dma_addr_t dma_addr;
 };
 
@@ -436,12 +447,16 @@
 	struct pci_dev *pdev;
 	struct mii_phy phy;
 
+	int medium;
+
 	void __iomem *regs;
 
 	struct spider_net_descr_chain tx_chain;
 	struct spider_net_descr_chain rx_chain;
 	struct spider_net_descr *low_watermark;
 
+	int aneg_count;
+	struct timer_list aneg_timer;
 	struct timer_list tx_timer;
 	struct work_struct tx_timeout_task;
 	atomic_t tx_timeout_task_counter;
@@ -452,6 +467,9 @@
 	struct net_device_stats netdev_stats;
 	struct spider_net_extra_stats spider_stats;
 	struct spider_net_options options;
+
+	/* Must be last item in struct */
+	struct spider_net_descr darray[0];
 };
 
 #define pr_err(fmt,arg...) \
diff --git a/drivers/net/sun3_82586.c b/drivers/net/sun3_82586.c
index a3220a9..4757aa6 100644
--- a/drivers/net/sun3_82586.c
+++ b/drivers/net/sun3_82586.c
@@ -28,8 +28,6 @@
 static int rfdadd = 0; /* rfdadd=1 may be better for 8K MEM cards */
 static int fifo=0x8;	/* don't change */
 
-/* #define REALLY_SLOW_IO */
-
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c
index 701ba4f..56a110c 100644
--- a/drivers/net/sungem_phy.c
+++ b/drivers/net/sungem_phy.c
@@ -310,6 +310,107 @@
 	return 0;
 }
 
+static int genmii_setup_aneg(struct mii_phy *phy, u32 advertise)
+{
+	u16 ctl, adv;
+
+	phy->autoneg = 1;
+	phy->speed = SPEED_10;
+	phy->duplex = DUPLEX_HALF;
+	phy->pause = 0;
+	phy->advertising = advertise;
+
+	/* Setup standard advertise */
+	adv = phy_read(phy, MII_ADVERTISE);
+	adv &= ~(ADVERTISE_ALL | ADVERTISE_100BASE4);
+	if (advertise & ADVERTISED_10baseT_Half)
+		adv |= ADVERTISE_10HALF;
+	if (advertise & ADVERTISED_10baseT_Full)
+		adv |= ADVERTISE_10FULL;
+	if (advertise & ADVERTISED_100baseT_Half)
+		adv |= ADVERTISE_100HALF;
+	if (advertise & ADVERTISED_100baseT_Full)
+		adv |= ADVERTISE_100FULL;
+	phy_write(phy, MII_ADVERTISE, adv);
+
+	/* Start/Restart aneg */
+	ctl = phy_read(phy, MII_BMCR);
+	ctl |= (BMCR_ANENABLE | BMCR_ANRESTART);
+	phy_write(phy, MII_BMCR, ctl);
+
+	return 0;
+}
+
+static int genmii_setup_forced(struct mii_phy *phy, int speed, int fd)
+{
+	u16 ctl;
+
+	phy->autoneg = 0;
+	phy->speed = speed;
+	phy->duplex = fd;
+	phy->pause = 0;
+
+	ctl = phy_read(phy, MII_BMCR);
+	ctl &= ~(BMCR_FULLDPLX|BMCR_SPEED100|BMCR_ANENABLE);
+
+	/* First reset the PHY */
+	phy_write(phy, MII_BMCR, ctl | BMCR_RESET);
+
+	/* Select speed & duplex */
+	switch(speed) {
+	case SPEED_10:
+		break;
+	case SPEED_100:
+		ctl |= BMCR_SPEED100;
+		break;
+	case SPEED_1000:
+	default:
+		return -EINVAL;
+	}
+	if (fd == DUPLEX_FULL)
+		ctl |= BMCR_FULLDPLX;
+	phy_write(phy, MII_BMCR, ctl);
+
+	return 0;
+}
+
+static int genmii_poll_link(struct mii_phy *phy)
+{
+	u16 status;
+
+	(void)phy_read(phy, MII_BMSR);
+	status = phy_read(phy, MII_BMSR);
+	if ((status & BMSR_LSTATUS) == 0)
+		return 0;
+	if (phy->autoneg && !(status & BMSR_ANEGCOMPLETE))
+		return 0;
+	return 1;
+}
+
+static int genmii_read_link(struct mii_phy *phy)
+{
+	u16 lpa;
+
+	if (phy->autoneg) {
+		lpa = phy_read(phy, MII_LPA);
+
+		if (lpa & (LPA_10FULL | LPA_100FULL))
+			phy->duplex = DUPLEX_FULL;
+		else
+			phy->duplex = DUPLEX_HALF;
+		if (lpa & (LPA_100FULL | LPA_100HALF))
+			phy->speed = SPEED_100;
+		else
+			phy->speed = SPEED_10;
+		phy->pause = 0;
+	}
+	/* On non-aneg, we assume what we put in BMCR is the speed,
+	 * though magic-aneg shouldn't prevent this case from occurring
+	 */
+
+	 return 0;
+}
+
 static int generic_suspend(struct mii_phy* phy)
 {
 	phy_write(phy, MII_BMCR, BMCR_PDOWN);
@@ -364,30 +465,6 @@
 	return 0;
 }
 
-static int bcm5421_enable_fiber(struct mii_phy* phy)
-{
-	/* enable fiber mode */
-	phy_write(phy, MII_NCONFIG, 0x9020);
-	/* LEDs active in both modes, autosense prio = fiber */
-	phy_write(phy, MII_NCONFIG, 0x945f);
-
-	/* switch off fibre autoneg */
-	phy_write(phy, MII_NCONFIG, 0xfc01);
-	phy_write(phy, 0x0b, 0x0004);
-
-	return 0;
-}
-
-static int bcm5461_enable_fiber(struct mii_phy* phy)
-{
-	phy_write(phy, MII_NCONFIG, 0xfc0c);
-	phy_write(phy, MII_BMCR, 0x4140);
-	phy_write(phy, MII_NCONFIG, 0xfc0b);
-	phy_write(phy, MII_BMCR, 0x0140);
-
-	return 0;
-}
-
 static int bcm54xx_setup_aneg(struct mii_phy *phy, u32 advertise)
 {
 	u16 ctl, adv;
@@ -515,6 +592,155 @@
 	return 0;
 }
 
+#define BCM5421_MODE_MASK	(1 << 5)
+
+static int bcm5421_poll_link(struct mii_phy* phy)
+{
+	u32 phy_reg;
+	int mode;
+
+	/* find out in what mode we are */
+	phy_write(phy, MII_NCONFIG, 0x1000);
+	phy_reg = phy_read(phy, MII_NCONFIG);
+
+	mode = (phy_reg & BCM5421_MODE_MASK) >> 5;
+
+	if ( mode == BCM54XX_COPPER)
+		return genmii_poll_link(phy);
+
+	/* try to find out wether we have a link */
+	phy_write(phy, MII_NCONFIG, 0x2000);
+	phy_reg = phy_read(phy, MII_NCONFIG);
+
+	if (phy_reg & 0x0020)
+		return 0;
+	else
+		return 1;
+}
+
+static int bcm5421_read_link(struct mii_phy* phy)
+{
+	u32 phy_reg;
+	int mode;
+
+	/* find out in what mode we are */
+	phy_write(phy, MII_NCONFIG, 0x1000);
+	phy_reg = phy_read(phy, MII_NCONFIG);
+
+	mode = (phy_reg & BCM5421_MODE_MASK ) >> 5;
+
+	if ( mode == BCM54XX_COPPER)
+		return bcm54xx_read_link(phy);
+
+	phy->speed = SPEED_1000;
+
+	/* find out wether we are running half- or full duplex */
+	phy_write(phy, MII_NCONFIG, 0x2000);
+	phy_reg = phy_read(phy, MII_NCONFIG);
+
+	if ( (phy_reg & 0x0080) >> 7)
+		phy->duplex |=  DUPLEX_HALF;
+	else
+		phy->duplex |=  DUPLEX_FULL;
+
+	return 0;
+}
+
+static int bcm5421_enable_fiber(struct mii_phy* phy, int autoneg)
+{
+	/* enable fiber mode */
+	phy_write(phy, MII_NCONFIG, 0x9020);
+	/* LEDs active in both modes, autosense prio = fiber */
+	phy_write(phy, MII_NCONFIG, 0x945f);
+
+	if (!autoneg) {
+		/* switch off fibre autoneg */
+		phy_write(phy, MII_NCONFIG, 0xfc01);
+		phy_write(phy, 0x0b, 0x0004);
+	}
+
+	phy->autoneg = autoneg;
+
+	return 0;
+}
+
+#define BCM5461_FIBER_LINK	(1 << 2)
+#define BCM5461_MODE_MASK	(3 << 1)
+
+static int bcm5461_poll_link(struct mii_phy* phy)
+{
+	u32 phy_reg;
+	int mode;
+
+	/* find out in what mode we are */
+	phy_write(phy, MII_NCONFIG, 0x7c00);
+	phy_reg = phy_read(phy, MII_NCONFIG);
+
+	mode = (phy_reg & BCM5461_MODE_MASK ) >> 1;
+
+	if ( mode == BCM54XX_COPPER)
+		return genmii_poll_link(phy);
+
+	/* find out wether we have a link */
+	phy_write(phy, MII_NCONFIG, 0x7000);
+	phy_reg = phy_read(phy, MII_NCONFIG);
+
+	if (phy_reg & BCM5461_FIBER_LINK)
+		return 1;
+	else
+		return 0;
+}
+
+#define BCM5461_FIBER_DUPLEX	(1 << 3)
+
+static int bcm5461_read_link(struct mii_phy* phy)
+{
+	u32 phy_reg;
+	int mode;
+
+	/* find out in what mode we are */
+	phy_write(phy, MII_NCONFIG, 0x7c00);
+	phy_reg = phy_read(phy, MII_NCONFIG);
+
+	mode = (phy_reg & BCM5461_MODE_MASK ) >> 1;
+
+	if ( mode == BCM54XX_COPPER) {
+		return bcm54xx_read_link(phy);
+	}
+
+	phy->speed = SPEED_1000;
+
+	/* find out wether we are running half- or full duplex */
+	phy_write(phy, MII_NCONFIG, 0x7000);
+	phy_reg = phy_read(phy, MII_NCONFIG);
+
+	if (phy_reg & BCM5461_FIBER_DUPLEX)
+		phy->duplex |=  DUPLEX_FULL;
+	else
+		phy->duplex |=  DUPLEX_HALF;
+
+	return 0;
+}
+
+static int bcm5461_enable_fiber(struct mii_phy* phy, int autoneg)
+{
+	/* select fiber mode, enable 1000 base-X registers */
+	phy_write(phy, MII_NCONFIG, 0xfc0b);
+
+	if (autoneg) {
+		/* enable fiber with no autonegotiation */
+		phy_write(phy, MII_ADVERTISE, 0x01e0);
+		phy_write(phy, MII_BMCR, 0x1140);
+	} else {
+		/* enable fiber with autonegotiation */
+		phy_write(phy, MII_BMCR, 0x0140);
+	}
+
+	phy->autoneg = autoneg;
+
+	return 0;
+}
+
 static int marvell_setup_aneg(struct mii_phy *phy, u32 advertise)
 {
 	u16 ctl, adv;
@@ -645,113 +871,6 @@
 	return 0;
 }
 
-static int genmii_setup_aneg(struct mii_phy *phy, u32 advertise)
-{
-	u16 ctl, adv;
-
-	phy->autoneg = 1;
-	phy->speed = SPEED_10;
-	phy->duplex = DUPLEX_HALF;
-	phy->pause = 0;
-	phy->advertising = advertise;
-
-	/* Setup standard advertise */
-	adv = phy_read(phy, MII_ADVERTISE);
-	adv &= ~(ADVERTISE_ALL | ADVERTISE_100BASE4);
-	if (advertise & ADVERTISED_10baseT_Half)
-		adv |= ADVERTISE_10HALF;
-	if (advertise & ADVERTISED_10baseT_Full)
-		adv |= ADVERTISE_10FULL;
-	if (advertise & ADVERTISED_100baseT_Half)
-		adv |= ADVERTISE_100HALF;
-	if (advertise & ADVERTISED_100baseT_Full)
-		adv |= ADVERTISE_100FULL;
-	if (advertise & ADVERTISED_Pause)
-		adv |= ADVERTISE_PAUSE_CAP;
-	if (advertise & ADVERTISED_Asym_Pause)
-		adv |= ADVERTISE_PAUSE_ASYM;
-	phy_write(phy, MII_ADVERTISE, adv);
-
-	/* Start/Restart aneg */
-	ctl = phy_read(phy, MII_BMCR);
-	ctl |= (BMCR_ANENABLE | BMCR_ANRESTART);
-	phy_write(phy, MII_BMCR, ctl);
-
-	return 0;
-}
-
-static int genmii_setup_forced(struct mii_phy *phy, int speed, int fd)
-{
-	u16 ctl;
-
-	phy->autoneg = 0;
-	phy->speed = speed;
-	phy->duplex = fd;
-	phy->pause = 0;
-
-	ctl = phy_read(phy, MII_BMCR);
-	ctl &= ~(BMCR_FULLDPLX|BMCR_SPEED100|BMCR_ANENABLE);
-
-	/* First reset the PHY */
-	phy_write(phy, MII_BMCR, ctl | BMCR_RESET);
-
-	/* Select speed & duplex */
-	switch(speed) {
-	case SPEED_10:
-		break;
-	case SPEED_100:
-		ctl |= BMCR_SPEED100;
-		break;
-	case SPEED_1000:
-	default:
-		return -EINVAL;
-	}
-	if (fd == DUPLEX_FULL)
-		ctl |= BMCR_FULLDPLX;
-	phy_write(phy, MII_BMCR, ctl);
-
-	return 0;
-}
-
-static int genmii_poll_link(struct mii_phy *phy)
-{
-	u16 status;
-
-	(void)phy_read(phy, MII_BMSR);
-	status = phy_read(phy, MII_BMSR);
-	if ((status & BMSR_LSTATUS) == 0)
-		return 0;
-	if (phy->autoneg && !(status & BMSR_ANEGCOMPLETE))
-		return 0;
-	return 1;
-}
-
-static int genmii_read_link(struct mii_phy *phy)
-{
-	u16 lpa;
-
-	if (phy->autoneg) {
-		lpa = phy_read(phy, MII_LPA);
-
-		if (lpa & (LPA_10FULL | LPA_100FULL))
-			phy->duplex = DUPLEX_FULL;
-		else
-			phy->duplex = DUPLEX_HALF;
-		if (lpa & (LPA_100FULL | LPA_100HALF))
-			phy->speed = SPEED_100;
-		else
-			phy->speed = SPEED_10;
-		phy->pause = (phy->duplex == DUPLEX_FULL) &&
-			((lpa & LPA_PAUSE) != 0);
-	}
-	/* On non-aneg, we assume what we put in BMCR is the speed,
-	 * though magic-aneg shouldn't prevent this case from occurring
-	 */
-
-	 return 0;
-}
-
-
 #define MII_BASIC_FEATURES \
 	(SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |	\
 	 SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |	\
@@ -885,8 +1004,8 @@
 	.suspend	= generic_suspend,
 	.setup_aneg	= bcm54xx_setup_aneg,
 	.setup_forced	= bcm54xx_setup_forced,
-	.poll_link	= genmii_poll_link,
-	.read_link	= bcm54xx_read_link,
+	.poll_link	= bcm5421_poll_link,
+	.read_link	= bcm5421_read_link,
 	.enable_fiber   = bcm5421_enable_fiber,
 };
 
@@ -923,8 +1042,8 @@
 	.suspend	= generic_suspend,
 	.setup_aneg	= bcm54xx_setup_aneg,
 	.setup_forced	= bcm54xx_setup_forced,
-	.poll_link	= genmii_poll_link,
-	.read_link	= bcm54xx_read_link,
+	.poll_link	= bcm5461_poll_link,
+	.read_link	= bcm5461_read_link,
 	.enable_fiber   = bcm5461_enable_fiber,
 };
 
diff --git a/drivers/net/sungem_phy.h b/drivers/net/sungem_phy.h
index 1d70ba6..af02f94 100644
--- a/drivers/net/sungem_phy.h
+++ b/drivers/net/sungem_phy.h
@@ -12,7 +12,7 @@
 	int		(*setup_forced)(struct mii_phy *phy, int speed, int fd);
 	int		(*poll_link)(struct mii_phy *phy);
 	int		(*read_link)(struct mii_phy *phy);
-	int		(*enable_fiber)(struct mii_phy *phy);
+	int		(*enable_fiber)(struct mii_phy *phy, int autoneg);
 };
 
 /* Structure used to statically define an mii/gii based PHY */
@@ -26,6 +26,14 @@
 	const struct mii_phy_ops*	ops;
 };
 
+enum {
+	BCM54XX_COPPER,
+	BCM54XX_FIBER,
+	BCM54XX_GBIC,
+	BCM54XX_SGMII,
+	BCM54XX_UNKNOWN,
+};
+
 /* An instance of a PHY, partially borrowed from mii_if_info */
 struct mii_phy
 {
diff --git a/drivers/net/tc35815.c b/drivers/net/tc35815.c
index 81ed82f0..eae2b63 100644
--- a/drivers/net/tc35815.c
+++ b/drivers/net/tc35815.c
@@ -657,7 +657,7 @@
 		dma_cache_wback_inv((unsigned long)lp->fd_buf, PAGE_SIZE * FD_PAGE_NUM);
 #endif
 	} else {
-		clear_page(lp->fd_buf);
+		memset(lp->fd_buf, 0, PAGE_SIZE * FD_PAGE_NUM);
 #ifdef __mips__
 		dma_cache_wback_inv((unsigned long)lp->fd_buf, PAGE_SIZE * FD_PAGE_NUM);
 #endif
@@ -1732,6 +1732,11 @@
 {
 	struct net_device *next_dev;
 
+	/*
+	 * TODO: implement a tc35815_driver.remove hook, and
+	 * move this code into that function.  Then, delete
+	 * all root_tc35815_dev list handling code.
+	 */
 	while (root_tc35815_dev) {
 		struct net_device *dev = root_tc35815_dev;
 		next_dev = ((struct tc35815_local *)dev->priv)->next_module;
@@ -1740,6 +1745,9 @@
 		free_netdev(dev);
 		root_tc35815_dev = next_dev;
 	}
+
+	pci_unregister_driver(&tc35815_driver);
 }
+
 module_init(tc35815_init_module);
 module_exit(tc35815_cleanup_module);
diff --git a/drivers/net/ucc_geth.c b/drivers/net/ucc_geth.c
index a2fc2bb..885e73d 100644
--- a/drivers/net/ucc_geth.c
+++ b/drivers/net/ucc_geth.c
@@ -4199,9 +4199,7 @@
 	ugeth->ug_info = ug_info;
 	ugeth->dev = dev;
 
-	mac_addr = get_property(np, "mac-address", NULL);
-	if (mac_addr == NULL)
-		mac_addr = get_property(np, "local-mac-address", NULL);
+	mac_addr = of_get_mac_address(np);
 	if (mac_addr)
 		memcpy(dev->dev_addr, mac_addr, 6);
 
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index e91b5a8..5b82e4f 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -94,7 +94,6 @@
 #include <linux/device.h>
 
 #undef COSA_SLOW_IO	/* for testing purposes only */
-#undef REALLY_SLOW_IO
 
 #include <asm/io.h>
 #include <asm/dma.h>
diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c
index c250f08..ce9230b 100644
--- a/drivers/net/wireless/wl3501_cs.c
+++ b/drivers/net/wireless/wl3501_cs.c
@@ -26,7 +26,6 @@
  * Tested with Planet AP in 2.5.73-bk, 216 Kbytes/s in Infrastructure mode
  * with a SMP machine (dual pentium 100), using pktgen, 432 pps (pkt_size = 60)
  */
-#undef REALLY_SLOW_IO	/* most systems can safely undef this */
 
 #include <linux/delay.h>
 #include <linux/types.h>