Hi:
[NET]: Added GSO support
Imported GSO patch. This is a 2.6.16 backport for the GSO patch that was
merged in Linux.
Signed-off-by: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Cheers,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@xxxxxxxxxxxxxxxxxxx>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
--
diff -r 9ec0b4f10b4f -r b255efd0df72 linux-2.6-xen-sparse/include/linux/skbuff.h
--- a/linux-2.6-xen-sparse/include/linux/skbuff.h Sat Jun 24 23:44:18
2006 +0100
+++ b/linux-2.6-xen-sparse/include/linux/skbuff.h Tue Jun 27 21:27:13
2006 +1000
@@ -134,9 +134,10 @@ struct skb_shared_info {
struct skb_shared_info {
atomic_t dataref;
unsigned short nr_frags;
- unsigned short tso_size;
- unsigned short tso_segs;
- unsigned short ufo_size;
+ unsigned short gso_size;
+ /* Warning: this field is not always filled in (UFO)! */
+ unsigned short gso_segs;
+ unsigned short gso_type;
unsigned int ip6_frag_id;
struct sk_buff *frag_list;
skb_frag_t frags[MAX_SKB_FRAGS];
@@ -166,6 +167,11 @@ enum {
SKB_FCLONE_UNAVAILABLE,
SKB_FCLONE_ORIG,
SKB_FCLONE_CLONE,
+};
+
+enum {
+ SKB_GSO_TCPV4 = 1 << 0,
+ SKB_GSO_UDPV4 = 1 << 1,
};
/**
@@ -1157,18 +1163,34 @@ static inline int skb_can_coalesce(struc
return 0;
}
+static inline int __skb_linearize(struct sk_buff *skb)
+{
+ return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM;
+}
+
/**
* skb_linearize - convert paged skb to linear one
* @skb: buffer to linarize
- * @gfp: allocation mode
*
* If there is no free memory -ENOMEM is returned, otherwise zero
* is returned and the old skb data released.
*/
-extern int __skb_linearize(struct sk_buff *skb, gfp_t gfp);
-static inline int skb_linearize(struct sk_buff *skb, gfp_t gfp)
-{
- return __skb_linearize(skb, gfp);
+static inline int skb_linearize(struct sk_buff *skb)
+{
+ return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0;
+}
+
+/**
+ * skb_linearize_cow - make sure skb is linear and writable
+ * @skb: buffer to process
+ *
+ * If there is no free memory -ENOMEM is returned, otherwise zero
+ * is returned and the old skb data released.
+ */
+static inline int skb_linearize_cow(struct sk_buff *skb)
+{
+ return skb_is_nonlinear(skb) || skb_cloned(skb) ?
+ __skb_linearize(skb) : 0;
}
/**
@@ -1263,6 +1285,7 @@ extern void skb_split(struct sk_b
struct sk_buff *skb1, const u32 len);
extern void skb_release_data(struct sk_buff *skb);
+extern struct sk_buff *skb_segment(struct sk_buff *skb, int sg);
static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
int len, void *buffer)
diff -r 9ec0b4f10b4f -r b255efd0df72 linux-2.6-xen-sparse/net/core/dev.c
--- a/linux-2.6-xen-sparse/net/core/dev.c Sat Jun 24 23:44:18 2006 +0100
+++ b/linux-2.6-xen-sparse/net/core/dev.c Tue Jun 27 21:27:13 2006 +1000
@@ -115,6 +115,7 @@
#include <net/iw_handler.h>
#endif /* CONFIG_NET_RADIO */
#include <asm/current.h>
+#include <linux/err.h>
#ifdef CONFIG_XEN
#include <net/ip.h>
@@ -1038,7 +1039,7 @@ static inline void net_timestamp(struct
* taps currently in use.
*/
-void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
+static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
{
struct packet_type *ptype;
@@ -1112,6 +1113,40 @@ out:
return ret;
}
+/**
+ * skb_gso_segment - Perform segmentation on skb.
+ * @skb: buffer to segment
+ * @sg: whether scatter-gather is supported on the target.
+ *
+ * This function segments the given skb and returns a list of segments.
+ */
+struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg)
+{
+ struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
+ struct packet_type *ptype;
+ int type = skb->protocol;
+
+ BUG_ON(skb_shinfo(skb)->frag_list);
+ BUG_ON(skb->ip_summed != CHECKSUM_HW);
+
+ skb->mac.raw = skb->data;
+ skb->mac_len = skb->nh.raw - skb->data;
+ __skb_pull(skb, skb->mac_len);
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) {
+ if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
+ segs = ptype->gso_segment(skb, sg);
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return segs;
+}
+
+EXPORT_SYMBOL(skb_gso_segment);
+
/* Take action when hardware reception checksum errors are detected. */
#ifdef CONFIG_BUG
void netdev_rx_csum_fault(struct net_device *dev)
@@ -1148,75 +1183,98 @@ static inline int illegal_highdma(struct
#define illegal_highdma(dev, skb) (0)
#endif
-/* Keep head the same: replace data */
-int __skb_linearize(struct sk_buff *skb, gfp_t gfp_mask)
-{
- unsigned int size;
- u8 *data;
- long offset;
- struct skb_shared_info *ninfo;
- int headerlen = skb->data - skb->head;
- int expand = (skb->tail + skb->data_len) - skb->end;
-
- if (skb_shared(skb))
- BUG();
-
- if (expand <= 0)
- expand = 0;
-
- size = skb->end - skb->head + expand;
- size = SKB_DATA_ALIGN(size);
- data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
- if (!data)
- return -ENOMEM;
-
- /* Copy entire thing */
- if (skb_copy_bits(skb, -headerlen, data, headerlen + skb->len))
- BUG();
-
- /* Set up shinfo */
- ninfo = (struct skb_shared_info*)(data + size);
- atomic_set(&ninfo->dataref, 1);
- ninfo->tso_size = skb_shinfo(skb)->tso_size;
- ninfo->tso_segs = skb_shinfo(skb)->tso_segs;
- ninfo->nr_frags = 0;
- ninfo->frag_list = NULL;
-
- /* Offset between the two in bytes */
- offset = data - skb->head;
-
- /* Free old data. */
- skb_release_data(skb);
-
- skb->head = data;
- skb->end = data + size;
-
- /* Set up new pointers */
- skb->h.raw += offset;
- skb->nh.raw += offset;
- skb->mac.raw += offset;
- skb->tail += offset;
- skb->data += offset;
-
- /* We are no longer a clone, even if we were. */
- skb->cloned = 0;
-
- skb->tail += skb->data_len;
- skb->data_len = 0;
+struct dev_gso_cb {
+ void (*destructor)(struct sk_buff *skb);
+};
+
+#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb)
+
+static void dev_gso_skb_destructor(struct sk_buff *skb)
+{
+ struct dev_gso_cb *cb;
+
+ do {
+ struct sk_buff *nskb = skb->next;
+
+ skb->next = nskb->next;
+ nskb->next = NULL;
+ kfree_skb(nskb);
+ } while (skb->next);
+
+ cb = DEV_GSO_CB(skb);
+ if (cb->destructor)
+ cb->destructor(skb);
+}
+
+/**
+ * dev_gso_segment - Perform emulated hardware segmentation on skb.
+ * @skb: buffer to segment
+ *
+ * This function segments the given skb and stores the list of segments
+ * in skb->next.
+ */
+static int dev_gso_segment(struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+ struct sk_buff *segs;
+
+ segs = skb_gso_segment(skb, dev->features & NETIF_F_SG &&
+ !illegal_highdma(dev, skb));
+ if (unlikely(IS_ERR(segs)))
+ return PTR_ERR(segs);
+
+ skb->next = segs;
+ DEV_GSO_CB(skb)->destructor = skb->destructor;
+ skb->destructor = dev_gso_skb_destructor;
+
+ return 0;
+}
+
+int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ if (likely(!skb->next)) {
+ if (netdev_nit)
+ dev_queue_xmit_nit(skb, dev);
+
+ if (!netif_needs_gso(dev, skb))
+ return dev->hard_start_xmit(skb, dev);
+
+ if (unlikely(dev_gso_segment(skb)))
+ goto out_kfree_skb;
+ }
+
+ do {
+ struct sk_buff *nskb = skb->next;
+ int rc;
+
+ skb->next = nskb->next;
+ nskb->next = NULL;
+ rc = dev->hard_start_xmit(nskb, dev);
+ if (unlikely(rc)) {
+ nskb->next = skb->next;
+ skb->next = nskb;
+ return rc;
+ }
+ if (unlikely(netif_queue_stopped(dev) && skb->next))
+ return NETDEV_TX_BUSY;
+ } while (skb->next);
+
+ skb->destructor = DEV_GSO_CB(skb)->destructor;
+
+out_kfree_skb:
+ kfree_skb(skb);
return 0;
}
#define HARD_TX_LOCK(dev, cpu) { \
if ((dev->features & NETIF_F_LLTX) == 0) { \
- spin_lock(&dev->xmit_lock); \
- dev->xmit_lock_owner = cpu; \
+ netif_tx_lock(dev); \
} \
}
#define HARD_TX_UNLOCK(dev) { \
if ((dev->features & NETIF_F_LLTX) == 0) { \
- dev->xmit_lock_owner = -1; \
- spin_unlock(&dev->xmit_lock); \
+ netif_tx_unlock(dev); \
} \
}
@@ -1289,9 +1347,19 @@ int dev_queue_xmit(struct sk_buff *skb)
struct Qdisc *q;
int rc = -ENOMEM;
+ /* If a checksum-deferred packet is forwarded to a device that needs a
+ * checksum, correct the pointers and force checksumming.
+ */
+ if (skb_checksum_setup(skb))
+ goto out_kfree_skb;
+
+ /* GSO will handle the following emulations directly. */
+ if (netif_needs_gso(dev, skb))
+ goto gso;
+
if (skb_shinfo(skb)->frag_list &&
!(dev->features & NETIF_F_FRAGLIST) &&
- __skb_linearize(skb, GFP_ATOMIC))
+ __skb_linearize(skb))
goto out_kfree_skb;
/* Fragmented skb is linearized if device does not support SG,
@@ -1300,31 +1368,27 @@ int dev_queue_xmit(struct sk_buff *skb)
*/
if (skb_shinfo(skb)->nr_frags &&
(!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
+ __skb_linearize(skb))
__skb_linearize(skb, GFP_ATOMIC))
goto out_kfree_skb;
- /* If a checksum-deferred packet is forwarded to a device that needs a
- * checksum, correct the pointers and force checksumming.
- */
- if(skb_checksum_setup(skb))
- goto out_kfree_skb;
-
/* If packet is not checksummed and device does not support
* checksumming for this protocol, complete checksumming here.
*/
if (skb->ip_summed == CHECKSUM_HW &&
- (!(dev->features & (NETIF_F_HW_CSUM | NETIF_F_NO_CSUM)) &&
+ (!(dev->features & NETIF_F_GEN_CSUM) &&
(!(dev->features & NETIF_F_IP_CSUM) ||
skb->protocol != htons(ETH_P_IP))))
if (skb_checksum_help(skb, 0))
goto out_kfree_skb;
+gso:
spin_lock_prefetch(&dev->queue_lock);
/* Disable soft irqs for various locks below. Also
* stops preemption for RCU.
*/
- local_bh_disable();
+ rcu_read_lock_bh();
/* Updates of qdisc are serialized by queue_lock.
* The struct Qdisc which is pointed to by qdisc is now a
@@ -1358,8 +1422,8 @@ int dev_queue_xmit(struct sk_buff *skb)
/* The device has no queue. Common case for software devices:
loopback, all the sorts of tunnels...
- Really, it is unlikely that xmit_lock protection is necessary here.
- (f.e. loopback and IP tunnels are clean ignoring statistics
+ Really, it is unlikely that netif_tx_lock protection is necessary
+ here. (f.e. loopback and IP tunnels are clean ignoring statistics
counters.)
However, it is possible, that they rely on protection
made by us here.
@@ -1375,11 +1439,8 @@ int dev_queue_xmit(struct sk_buff *skb)
HARD_TX_LOCK(dev, cpu);
if (!netif_queue_stopped(dev)) {
- if (netdev_nit)
- dev_queue_xmit_nit(skb, dev);
-
rc = 0;
- if (!dev->hard_start_xmit(skb, dev)) {
+ if (!dev_hard_start_xmit(skb, dev)) {
HARD_TX_UNLOCK(dev);
goto out;
}
@@ -1398,13 +1459,13 @@ int dev_queue_xmit(struct sk_buff *skb)
}
rc = -ENETDOWN;
- local_bh_enable();
+ rcu_read_unlock_bh();
out_kfree_skb:
kfree_skb(skb);
return rc;
out:
- local_bh_enable();
+ rcu_read_unlock_bh();
return rc;
}
@@ -2732,7 +2793,7 @@ int register_netdevice(struct net_device
BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
spin_lock_init(&dev->queue_lock);
- spin_lock_init(&dev->xmit_lock);
+ spin_lock_init(&dev->_xmit_lock);
dev->xmit_lock_owner = -1;
#ifdef CONFIG_NET_CLS_ACT
spin_lock_init(&dev->ingress_lock);
@@ -2776,9 +2837,7 @@ int register_netdevice(struct net_device
/* Fix illegal SG+CSUM combinations. */
if ((dev->features & NETIF_F_SG) &&
- !(dev->features & (NETIF_F_IP_CSUM |
- NETIF_F_NO_CSUM |
- NETIF_F_HW_CSUM))) {
+ !(dev->features & NETIF_F_ALL_CSUM)) {
printk("%s: Dropping NETIF_F_SG since no checksum feature.\n",
dev->name);
dev->features &= ~NETIF_F_SG;
@@ -3330,7 +3389,6 @@ EXPORT_SYMBOL(__dev_get_by_index);
EXPORT_SYMBOL(__dev_get_by_index);
EXPORT_SYMBOL(__dev_get_by_name);
EXPORT_SYMBOL(__dev_remove_pack);
-EXPORT_SYMBOL(__skb_linearize);
EXPORT_SYMBOL(dev_valid_name);
EXPORT_SYMBOL(dev_add_pack);
EXPORT_SYMBOL(dev_alloc_name);
diff -r 9ec0b4f10b4f -r b255efd0df72 linux-2.6-xen-sparse/net/core/skbuff.c
--- a/linux-2.6-xen-sparse/net/core/skbuff.c Sat Jun 24 23:44:18 2006 +0100
+++ b/linux-2.6-xen-sparse/net/core/skbuff.c Tue Jun 27 21:27:13 2006 +1000
@@ -165,9 +165,9 @@ struct sk_buff *__alloc_skb(unsigned int
shinfo = skb_shinfo(skb);
atomic_set(&shinfo->dataref, 1);
shinfo->nr_frags = 0;
- shinfo->tso_size = 0;
- shinfo->tso_segs = 0;
- shinfo->ufo_size = 0;
+ shinfo->gso_size = 0;
+ shinfo->gso_segs = 0;
+ shinfo->gso_type = 0;
shinfo->ip6_frag_id = 0;
shinfo->frag_list = NULL;
@@ -237,9 +237,9 @@ struct sk_buff *alloc_skb_from_cache(kme
shinfo = skb_shinfo(skb);
atomic_set(&shinfo->dataref, 1);
shinfo->nr_frags = 0;
- shinfo->tso_size = 0;
- shinfo->tso_segs = 0;
- shinfo->ufo_size = 0;
+ skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_segs = 0;
+ skb_shinfo(skb)->gso_type = 0;
shinfo->ip6_frag_id = 0;
shinfo->frag_list = NULL;
@@ -524,8 +524,9 @@ static void copy_skb_header(struct sk_bu
new->tc_index = old->tc_index;
#endif
atomic_set(&new->users, 1);
- skb_shinfo(new)->tso_size = skb_shinfo(old)->tso_size;
- skb_shinfo(new)->tso_segs = skb_shinfo(old)->tso_segs;
+ skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
+ skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
+ skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
}
/**
@@ -1799,6 +1800,132 @@ int skb_append_datato_frags(struct sock
return 0;
}
+
+/**
+ * skb_segment - Perform protocol segmentation on skb.
+ * @skb: buffer to segment
+ * @sg: whether scatter-gather can be used for generated segments
+ *
+ * This function performs segmentation on the given skb. It returns
+ * the segment at the given position. It returns NULL if there are
+ * no more segments to generate, or when an error is encountered.
+ */
+struct sk_buff *skb_segment(struct sk_buff *skb, int sg)
+{
+ struct sk_buff *segs = NULL;
+ struct sk_buff *tail = NULL;
+ unsigned int mss = skb_shinfo(skb)->gso_size;
+ unsigned int doffset = skb->data - skb->mac.raw;
+ unsigned int offset = doffset;
+ unsigned int headroom;
+ unsigned int len;
+ int nfrags = skb_shinfo(skb)->nr_frags;
+ int err = -ENOMEM;
+ int i = 0;
+ int pos;
+
+ __skb_push(skb, doffset);
+ headroom = skb_headroom(skb);
+ pos = skb_headlen(skb);
+
+ do {
+ struct sk_buff *nskb;
+ skb_frag_t *frag;
+ int hsize, nsize;
+ int k;
+ int size;
+
+ len = skb->len - offset;
+ if (len > mss)
+ len = mss;
+
+ hsize = skb_headlen(skb) - offset;
+ if (hsize < 0)
+ hsize = 0;
+ nsize = hsize + doffset;
+ if (nsize > len + doffset || !sg)
+ nsize = len + doffset;
+
+ nskb = alloc_skb(nsize + headroom, GFP_ATOMIC);
+ if (unlikely(!nskb))
+ goto err;
+
+ if (segs)
+ tail->next = nskb;
+ else
+ segs = nskb;
+ tail = nskb;
+
+ nskb->dev = skb->dev;
+ nskb->priority = skb->priority;
+ nskb->protocol = skb->protocol;
+ nskb->dst = dst_clone(skb->dst);
+ memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
+ nskb->pkt_type = skb->pkt_type;
+ nskb->mac_len = skb->mac_len;
+
+ skb_reserve(nskb, headroom);
+ nskb->mac.raw = nskb->data;
+ nskb->nh.raw = nskb->data + skb->mac_len;
+ nskb->h.raw = nskb->nh.raw + (skb->h.raw - skb->nh.raw);
+ memcpy(skb_put(nskb, doffset), skb->data, doffset);
+
+ if (!sg) {
+ nskb->csum = skb_copy_and_csum_bits(skb, offset,
+ skb_put(nskb, len),
+ len, 0);
+ continue;
+ }
+
+ frag = skb_shinfo(nskb)->frags;
+ k = 0;
+
+ nskb->ip_summed = CHECKSUM_HW;
+ nskb->csum = skb->csum;
+ memcpy(skb_put(nskb, hsize), skb->data + offset, hsize);
+
+ while (pos < offset + len) {
+ BUG_ON(i >= nfrags);
+
+ *frag = skb_shinfo(skb)->frags[i];
+ get_page(frag->page);
+ size = frag->size;
+
+ if (pos < offset) {
+ frag->page_offset += offset - pos;
+ frag->size -= offset - pos;
+ }
+
+ k++;
+
+ if (pos + size <= offset + len) {
+ i++;
+ pos += size;
+ } else {
+ frag->size -= pos + size - (offset + len);
+ break;
+ }
+
+ frag++;
+ }
+
+ skb_shinfo(nskb)->nr_frags = k;
+ nskb->data_len = len - hsize;
+ nskb->len += nskb->data_len;
+ nskb->truesize += nskb->data_len;
+ } while ((offset += len) < skb->len);
+
+ return segs;
+
+err:
+ while ((skb = segs)) {
+ segs = skb->next;
+ kfree(skb);
+ }
+ return ERR_PTR(err);
+}
+
+EXPORT_SYMBOL_GPL(skb_segment);
void __init skb_init(void)
{
diff -r 9ec0b4f10b4f -r b255efd0df72 patches/linux-2.6.16.13/net-gso.patch
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/patches/linux-2.6.16.13/net-gso.patch Tue Jun 27 21:27:13 2006 +1000
@@ -0,0 +1,2285 @@
+diff --git a/Documentation/networking/netdevices.txt
b/Documentation/networking/netdevices.txt
+index 3c0a5ba..847cedb 100644
+--- a/Documentation/networking/netdevices.txt
++++ b/Documentation/networking/netdevices.txt
+@@ -42,9 +42,9 @@ dev->get_stats:
+ Context: nominally process, but don't sleep inside an rwlock
+
+ dev->hard_start_xmit:
+- Synchronization: dev->xmit_lock spinlock.
++ Synchronization: netif_tx_lock spinlock.
+ When the driver sets NETIF_F_LLTX in dev->features this will be
+- called without holding xmit_lock. In this case the driver
++ called without holding netif_tx_lock. In this case the driver
+ has to lock by itself when needed. It is recommended to use a try lock
+ for this and return -1 when the spin lock fails.
+ The locking there should also properly protect against
+@@ -62,12 +62,12 @@ dev->hard_start_xmit:
+ Only valid when NETIF_F_LLTX is set.
+
+ dev->tx_timeout:
+- Synchronization: dev->xmit_lock spinlock.
++ Synchronization: netif_tx_lock spinlock.
+ Context: BHs disabled
+ Notes: netif_queue_stopped() is guaranteed true
+
+ dev->set_multicast_list:
+- Synchronization: dev->xmit_lock spinlock.
++ Synchronization: netif_tx_lock spinlock.
+ Context: BHs disabled
+
+ dev->poll:
+diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c
+index 4be9769..2e7cac7 100644
+--- a/drivers/block/aoe/aoenet.c
++++ b/drivers/block/aoe/aoenet.c
+@@ -95,9 +95,8 @@ mac_addr(char addr[6])
+ static struct sk_buff *
+ skb_check(struct sk_buff *skb)
+ {
+- if (skb_is_nonlinear(skb))
+ if ((skb = skb_share_check(skb, GFP_ATOMIC)))
+- if (skb_linearize(skb, GFP_ATOMIC) < 0) {
++ if (skb_linearize(skb)) {
+ dev_kfree_skb(skb);
+ return NULL;
+ }
+diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+index a2408d7..c90e620 100644
+--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
++++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+@@ -821,7 +821,8 @@ void ipoib_mcast_restart_task(void *dev_
+
+ ipoib_mcast_stop_thread(dev, 0);
+
+- spin_lock_irqsave(&dev->xmit_lock, flags);
++ local_irq_save(flags);
++ netif_tx_lock(dev);
+ spin_lock(&priv->lock);
+
+ /*
+@@ -896,7 +897,8 @@ void ipoib_mcast_restart_task(void *dev_
+ }
+
+ spin_unlock(&priv->lock);
+- spin_unlock_irqrestore(&dev->xmit_lock, flags);
++ netif_tx_unlock(dev);
++ local_irq_restore(flags);
+
+ /* We have to cancel outside of the spinlock */
+ list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
+diff --git a/drivers/media/dvb/dvb-core/dvb_net.c
b/drivers/media/dvb/dvb-core/dvb_net.c
+index 6711eb6..8d2351f 100644
+--- a/drivers/media/dvb/dvb-core/dvb_net.c
++++ b/drivers/media/dvb/dvb-core/dvb_net.c
+@@ -1052,7 +1052,7 @@ static void wq_set_multicast_list (void
+
+ dvb_net_feed_stop(dev);
+ priv->rx_mode = RX_MODE_UNI;
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+
+ if (dev->flags & IFF_PROMISC) {
+ dprintk("%s: promiscuous mode\n", dev->name);
+@@ -1077,7 +1077,7 @@ static void wq_set_multicast_list (void
+ }
+ }
+
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ dvb_net_feed_start(dev);
+ }
+
+diff --git a/drivers/net/8139cp.c b/drivers/net/8139cp.c
+index dd41049..6615583 100644
+--- a/drivers/net/8139cp.c
++++ b/drivers/net/8139cp.c
+@@ -794,7 +794,7 @@ #endif
+ entry = cp->tx_head;
+ eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0;
+ if (dev->features & NETIF_F_TSO)
+- mss = skb_shinfo(skb)->tso_size;
++ mss = skb_shinfo(skb)->gso_size;
+
+ if (skb_shinfo(skb)->nr_frags == 0) {
+ struct cp_desc *txd = &cp->tx_ring[entry];
+diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c
+index a24200d..b5e39a1 100644
+--- a/drivers/net/bnx2.c
++++ b/drivers/net/bnx2.c
+@@ -1593,7 +1593,7 @@ bnx2_tx_int(struct bnx2 *bp)
+ skb = tx_buf->skb;
+ #ifdef BCM_TSO
+ /* partial BD completions possible with TSO packets */
+- if (skb_shinfo(skb)->tso_size) {
++ if (skb_shinfo(skb)->gso_size) {
+ u16 last_idx, last_ring_idx;
+
+ last_idx = sw_cons +
+@@ -1948,7 +1948,7 @@ bnx2_poll(struct net_device *dev, int *b
+ return 1;
+ }
+
+-/* Called with rtnl_lock from vlan functions and also dev->xmit_lock
++/* Called with rtnl_lock from vlan functions and also netif_tx_lock
+ * from set_multicast.
+ */
+ static void
+@@ -4403,7 +4403,7 @@ bnx2_vlan_rx_kill_vid(struct net_device
+ }
+ #endif
+
+-/* Called with dev->xmit_lock.
++/* Called with netif_tx_lock.
+ * hard_start_xmit is pseudo-lockless - a lock is only required when
+ * the tx queue is full. This way, we get the benefit of lockless
+ * operations most of the time without the complexities to handle
+@@ -4441,7 +4441,7 @@ bnx2_start_xmit(struct sk_buff *skb, str
+ (TX_BD_FLAGS_VLAN_TAG | (vlan_tx_tag_get(skb) << 16));
+ }
+ #ifdef BCM_TSO
+- if ((mss = skb_shinfo(skb)->tso_size) &&
++ if ((mss = skb_shinfo(skb)->gso_size) &&
+ (skb->len > (bp->dev->mtu + ETH_HLEN))) {
+ u32 tcp_opt_len, ip_tcp_len;
+
+diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
+index bcf9f17..e970921 100644
+--- a/drivers/net/bonding/bond_main.c
++++ b/drivers/net/bonding/bond_main.c
+@@ -1145,8 +1145,7 @@ int bond_sethwaddr(struct net_device *bo
+ }
+
+ #define BOND_INTERSECT_FEATURES \
+- (NETIF_F_SG|NETIF_F_IP_CSUM|NETIF_F_NO_CSUM|NETIF_F_HW_CSUM|\
+- NETIF_F_TSO|NETIF_F_UFO)
++ (NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_TSO | NETIF_F_UFO)
+
+ /*
+ * Compute the common dev->feature set available to all slaves. Some
+@@ -1164,9 +1163,7 @@ static int bond_compute_features(struct
+ features &= (slave->dev->features & BOND_INTERSECT_FEATURES);
+
+ if ((features & NETIF_F_SG) &&
+- !(features & (NETIF_F_IP_CSUM |
+- NETIF_F_NO_CSUM |
+- NETIF_F_HW_CSUM)))
++ !(features & NETIF_F_ALL_CSUM))
+ features &= ~NETIF_F_SG;
+
+ /*
+@@ -4147,7 +4144,7 @@ static int bond_init(struct net_device *
+ */
+ bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
+
+- /* don't acquire bond device's xmit_lock when
++ /* don't acquire bond device's netif_tx_lock when
+ * transmitting */
+ bond_dev->features |= NETIF_F_LLTX;
+
+diff --git a/drivers/net/chelsio/sge.c b/drivers/net/chelsio/sge.c
+index 30ff8ea..7b7d360 100644
+--- a/drivers/net/chelsio/sge.c
++++ b/drivers/net/chelsio/sge.c
+@@ -1419,7 +1419,7 @@ int t1_start_xmit(struct sk_buff *skb, s
+ struct cpl_tx_pkt *cpl;
+
+ #ifdef NETIF_F_TSO
+- if (skb_shinfo(skb)->tso_size) {
++ if (skb_shinfo(skb)->gso_size) {
+ int eth_type;
+ struct cpl_tx_pkt_lso *hdr;
+
+@@ -1434,7 +1434,7 @@ #ifdef NETIF_F_TSO
+ hdr->ip_hdr_words = skb->nh.iph->ihl;
+ hdr->tcp_hdr_words = skb->h.th->doff;
+ hdr->eth_type_mss = htons(MK_ETH_TYPE_MSS(eth_type,
+- skb_shinfo(skb)->tso_size));
++ skb_shinfo(skb)->gso_size));
+ hdr->len = htonl(skb->len - sizeof(*hdr));
+ cpl = (struct cpl_tx_pkt *)hdr;
+ sge->stats.tx_lso_pkts++;
+diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c
+index fa29402..681d284 100644
+--- a/drivers/net/e1000/e1000_main.c
++++ b/drivers/net/e1000/e1000_main.c
+@@ -2526,7 +2526,7 @@ #ifdef NETIF_F_TSO
+ uint8_t ipcss, ipcso, tucss, tucso, hdr_len;
+ int err;
+
+- if (skb_shinfo(skb)->tso_size) {
++ if (skb_shinfo(skb)->gso_size) {
+ if (skb_header_cloned(skb)) {
+ err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+ if (err)
+@@ -2534,7 +2534,7 @@ #ifdef NETIF_F_TSO
+ }
+
+ hdr_len = ((skb->h.raw - skb->data) + (skb->h.th->doff << 2));
+- mss = skb_shinfo(skb)->tso_size;
++ mss = skb_shinfo(skb)->gso_size;
+ if (skb->protocol == ntohs(ETH_P_IP)) {
+ skb->nh.iph->tot_len = 0;
+ skb->nh.iph->check = 0;
+@@ -2651,7 +2651,7 @@ #ifdef NETIF_F_TSO
+ * tso gets written back prematurely before the data is fully
+ * DMAd to the controller */
+ if (!skb->data_len && tx_ring->last_tx_tso &&
+- !skb_shinfo(skb)->tso_size) {
++ !skb_shinfo(skb)->gso_size) {
+ tx_ring->last_tx_tso = 0;
+ size -= 4;
+ }
+@@ -2893,7 +2893,7 @@ #endif
+ }
+
+ #ifdef NETIF_F_TSO
+- mss = skb_shinfo(skb)->tso_size;
++ mss = skb_shinfo(skb)->gso_size;
+ /* The controller does a simple calculation to
+ * make sure there is enough room in the FIFO before
+ * initiating the DMA for each buffer. The calc is:
+@@ -2935,7 +2935,7 @@ #endif
+ #ifdef NETIF_F_TSO
+ /* Controller Erratum workaround */
+ if (!skb->data_len && tx_ring->last_tx_tso &&
+- !skb_shinfo(skb)->tso_size)
++ !skb_shinfo(skb)->gso_size)
+ count++;
+ #endif
+
+diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c
+index 3682ec6..c35f16e 100644
+--- a/drivers/net/forcedeth.c
++++ b/drivers/net/forcedeth.c
+@@ -482,9 +482,9 @@ #define LPA_1000HALF 0x0400
+ * critical parts:
+ * - rx is (pseudo-) lockless: it relies on the single-threading provided
+ * by the arch code for interrupts.
+- * - tx setup is lockless: it relies on dev->xmit_lock. Actual submission
++ * - tx setup is lockless: it relies on netif_tx_lock. Actual submission
+ * needs dev->priv->lock :-(
+- * - set_multicast_list: preparation lockless, relies on dev->xmit_lock.
++ * - set_multicast_list: preparation lockless, relies on netif_tx_lock.
+ */
+
+ /* in dev: base, irq */
+@@ -1016,7 +1016,7 @@ static void drain_ring(struct net_device
+
+ /*
+ * nv_start_xmit: dev->hard_start_xmit function
+- * Called with dev->xmit_lock held.
++ * Called with netif_tx_lock held.
+ */
+ static int nv_start_xmit(struct sk_buff *skb, struct net_device *dev)
+ {
+@@ -1105,8 +1105,8 @@ static int nv_start_xmit(struct sk_buff
+ np->tx_skbuff[nr] = skb;
+
+ #ifdef NETIF_F_TSO
+- if (skb_shinfo(skb)->tso_size)
+- tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->tso_size <<
NV_TX2_TSO_SHIFT);
++ if (skb_shinfo(skb)->gso_size)
++ tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->gso_size <<
NV_TX2_TSO_SHIFT);
+ else
+ #endif
+ tx_flags_extra = (skb->ip_summed == CHECKSUM_HW ?
(NV_TX2_CHECKSUM_L3|NV_TX2_CHECKSUM_L4) : 0);
+@@ -1203,7 +1203,7 @@ static void nv_tx_done(struct net_device
+
+ /*
+ * nv_tx_timeout: dev->tx_timeout function
+- * Called with dev->xmit_lock held.
++ * Called with netif_tx_lock held.
+ */
+ static void nv_tx_timeout(struct net_device *dev)
+ {
+@@ -1524,7 +1524,7 @@ static int nv_change_mtu(struct net_devi
+ * Changing the MTU is a rare event, it shouldn't matter.
+ */
+ disable_irq(dev->irq);
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ spin_lock(&np->lock);
+ /* stop engines */
+ nv_stop_rx(dev);
+@@ -1559,7 +1559,7 @@ static int nv_change_mtu(struct net_devi
+ nv_start_rx(dev);
+ nv_start_tx(dev);
+ spin_unlock(&np->lock);
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ enable_irq(dev->irq);
+ }
+ return 0;
+@@ -1594,7 +1594,7 @@ static int nv_set_mac_address(struct net
+ memcpy(dev->dev_addr, macaddr->sa_data, ETH_ALEN);
+
+ if (netif_running(dev)) {
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ spin_lock_irq(&np->lock);
+
+ /* stop rx engine */
+@@ -1606,7 +1606,7 @@ static int nv_set_mac_address(struct net
+ /* restart rx engine */
+ nv_start_rx(dev);
+ spin_unlock_irq(&np->lock);
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ } else {
+ nv_copy_mac_to_hw(dev);
+ }
+@@ -1615,7 +1615,7 @@ static int nv_set_mac_address(struct net
+
+ /*
+ * nv_set_multicast: dev->set_multicast function
+- * Called with dev->xmit_lock held.
++ * Called with netif_tx_lock held.
+ */
+ static void nv_set_multicast(struct net_device *dev)
+ {
+diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
+index 102c1f0..d12605f 100644
+--- a/drivers/net/hamradio/6pack.c
++++ b/drivers/net/hamradio/6pack.c
+@@ -308,9 +308,9 @@ static int sp_set_mac_address(struct net
+ {
+ struct sockaddr_ax25 *sa = addr;
+
+- spin_lock_irq(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ memcpy(dev->dev_addr, &sa->sax25_call, AX25_ADDR_LEN);
+- spin_unlock_irq(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+
+ return 0;
+ }
+@@ -767,9 +767,9 @@ static int sixpack_ioctl(struct tty_stru
+ break;
+ }
+
+- spin_lock_irq(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ memcpy(dev->dev_addr, &addr, AX25_ADDR_LEN);
+- spin_unlock_irq(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+
+ err = 0;
+ break;
+diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
+index dc5e9d5..5c66f5a 100644
+--- a/drivers/net/hamradio/mkiss.c
++++ b/drivers/net/hamradio/mkiss.c
+@@ -357,9 +357,9 @@ static int ax_set_mac_address(struct net
+ {
+ struct sockaddr_ax25 *sa = addr;
+
+- spin_lock_irq(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ memcpy(dev->dev_addr, &sa->sax25_call, AX25_ADDR_LEN);
+- spin_unlock_irq(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+
+ return 0;
+ }
+@@ -886,9 +886,9 @@ static int mkiss_ioctl(struct tty_struct
+ break;
+ }
+
+- spin_lock_irq(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ memcpy(dev->dev_addr, addr, AX25_ADDR_LEN);
+- spin_unlock_irq(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+
+ err = 0;
+ break;
+diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
+index 31fb2d7..2e222ef 100644
+--- a/drivers/net/ifb.c
++++ b/drivers/net/ifb.c
+@@ -76,13 +76,13 @@ static void ri_tasklet(unsigned long dev
+ dp->st_task_enter++;
+ if ((skb = skb_peek(&dp->tq)) == NULL) {
+ dp->st_txq_refl_try++;
+- if (spin_trylock(&_dev->xmit_lock)) {
++ if (netif_tx_trylock(_dev)) {
+ dp->st_rxq_enter++;
+ while ((skb = skb_dequeue(&dp->rq)) != NULL) {
+ skb_queue_tail(&dp->tq, skb);
+ dp->st_rx2tx_tran++;
+ }
+- spin_unlock(&_dev->xmit_lock);
++ netif_tx_unlock(_dev);
+ } else {
+ /* reschedule */
+ dp->st_rxq_notenter++;
+@@ -110,7 +110,7 @@ static void ri_tasklet(unsigned long dev
+ }
+ }
+
+- if (spin_trylock(&_dev->xmit_lock)) {
++ if (netif_tx_trylock(_dev)) {
+ dp->st_rxq_check++;
+ if ((skb = skb_peek(&dp->rq)) == NULL) {
+ dp->tasklet_pending = 0;
+@@ -118,10 +118,10 @@ static void ri_tasklet(unsigned long dev
+ netif_wake_queue(_dev);
+ } else {
+ dp->st_rxq_rsch++;
+- spin_unlock(&_dev->xmit_lock);
++ netif_tx_unlock(_dev);
+ goto resched;
+ }
+- spin_unlock(&_dev->xmit_lock);
++ netif_tx_unlock(_dev);
+ } else {
+ resched:
+ dp->tasklet_pending = 1;
+diff --git a/drivers/net/irda/vlsi_ir.c b/drivers/net/irda/vlsi_ir.c
+index a9f49f0..339d4a7 100644
+--- a/drivers/net/irda/vlsi_ir.c
++++ b/drivers/net/irda/vlsi_ir.c
+@@ -959,7 +959,7 @@ static int vlsi_hard_start_xmit(struct s
+ || (now.tv_sec==ready.tv_sec &&
now.tv_usec>=ready.tv_usec))
+ break;
+ udelay(100);
+- /* must not sleep here - we are called under xmit_lock!
*/
++ /* must not sleep here - called under netif_tx_lock! */
+ }
+ }
+
+diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c
+index f9f77e4..bdab369 100644
+--- a/drivers/net/ixgb/ixgb_main.c
++++ b/drivers/net/ixgb/ixgb_main.c
+@@ -1163,7 +1163,7 @@ #ifdef NETIF_F_TSO
+ uint16_t ipcse, tucse, mss;
+ int err;
+
+- if(likely(skb_shinfo(skb)->tso_size)) {
++ if(likely(skb_shinfo(skb)->gso_size)) {
+ if (skb_header_cloned(skb)) {
+ err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+ if (err)
+@@ -1171,7 +1171,7 @@ #ifdef NETIF_F_TSO
+ }
+
+ hdr_len = ((skb->h.raw - skb->data) + (skb->h.th->doff << 2));
+- mss = skb_shinfo(skb)->tso_size;
++ mss = skb_shinfo(skb)->gso_size;
+ skb->nh.iph->tot_len = 0;
+ skb->nh.iph->check = 0;
+ skb->h.th->check = ~csum_tcpudp_magic(skb->nh.iph->saddr,
+diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
+index 690a1aa..9bcaa80 100644
+--- a/drivers/net/loopback.c
++++ b/drivers/net/loopback.c
+@@ -74,7 +74,7 @@ static void emulate_large_send_offload(s
+ struct iphdr *iph = skb->nh.iph;
+ struct tcphdr *th = (struct tcphdr*)(skb->nh.raw + (iph->ihl * 4));
+ unsigned int doffset = (iph->ihl + th->doff) * 4;
+- unsigned int mtu = skb_shinfo(skb)->tso_size + doffset;
++ unsigned int mtu = skb_shinfo(skb)->gso_size + doffset;
+ unsigned int offset = 0;
+ u32 seq = ntohl(th->seq);
+ u16 id = ntohs(iph->id);
+@@ -139,7 +139,7 @@ #ifndef LOOPBACK_MUST_CHECKSUM
+ #endif
+
+ #ifdef LOOPBACK_TSO
+- if (skb_shinfo(skb)->tso_size) {
++ if (skb_shinfo(skb)->gso_size) {
+ BUG_ON(skb->protocol != htons(ETH_P_IP));
+ BUG_ON(skb->nh.iph->protocol != IPPROTO_TCP);
+
+diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c
+index c0998ef..0fac9d5 100644
+--- a/drivers/net/mv643xx_eth.c
++++ b/drivers/net/mv643xx_eth.c
+@@ -1107,7 +1107,7 @@ static int mv643xx_eth_start_xmit(struct
+
+ #ifdef MV643XX_CHECKSUM_OFFLOAD_TX
+ if (has_tiny_unaligned_frags(skb)) {
+- if ((skb_linearize(skb, GFP_ATOMIC) != 0)) {
++ if (__skb_linearize(skb)) {
+ stats->tx_dropped++;
+ printk(KERN_DEBUG "%s: failed to linearize tiny "
+ "unaligned fragment\n", dev->name);
+diff --git a/drivers/net/natsemi.c b/drivers/net/natsemi.c
+index 9d6d254..c9ed624 100644
+--- a/drivers/net/natsemi.c
++++ b/drivers/net/natsemi.c
+@@ -323,12 +323,12 @@ performance critical codepaths:
+ The rx process only runs in the interrupt handler. Access from outside
+ the interrupt handler is only permitted after disable_irq().
+
+-The rx process usually runs under the dev->xmit_lock. If np->intr_tx_reap
++The rx process usually runs under the netif_tx_lock. If np->intr_tx_reap
+ is set, then access is permitted under spin_lock_irq(&np->lock).
+
+ Thus configuration functions that want to access everything must call
+ disable_irq(dev->irq);
+- spin_lock_bh(dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ spin_lock_irq(&np->lock);
+
+ IV. Notes
+diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
+index 8cc0d0b..e53b313 100644
+--- a/drivers/net/r8169.c
++++ b/drivers/net/r8169.c
+@@ -2171,7 +2171,7 @@ static int rtl8169_xmit_frags(struct rtl
+ static inline u32 rtl8169_tso_csum(struct sk_buff *skb, struct net_device
*dev)
+ {
+ if (dev->features & NETIF_F_TSO) {
+- u32 mss = skb_shinfo(skb)->tso_size;
++ u32 mss = skb_shinfo(skb)->gso_size;
+
+ if (mss)
+ return LargeSend | ((mss & MSSMask) << MSSShift);
+diff --git a/drivers/net/s2io.c b/drivers/net/s2io.c
+index b7f00d6..439f45f 100644
+--- a/drivers/net/s2io.c
++++ b/drivers/net/s2io.c
+@@ -3522,8 +3522,8 @@ #endif
+ txdp->Control_1 = 0;
+ txdp->Control_2 = 0;
+ #ifdef NETIF_F_TSO
+- mss = skb_shinfo(skb)->tso_size;
+- if (mss) {
++ mss = skb_shinfo(skb)->gso_size;
++ if (skb_shinfo(skb)->gso_type == SKB_GSO_TCPV4) {
+ txdp->Control_1 |= TXD_TCP_LSO_EN;
+ txdp->Control_1 |= TXD_TCP_LSO_MSS(mss);
+ }
+@@ -3543,10 +3543,10 @@ #endif
+ }
+
+ frg_len = skb->len - skb->data_len;
+- if (skb_shinfo(skb)->ufo_size) {
++ if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4) {
+ int ufo_size;
+
+- ufo_size = skb_shinfo(skb)->ufo_size;
++ ufo_size = skb_shinfo(skb)->gso_size;
+ ufo_size &= ~7;
+ txdp->Control_1 |= TXD_UFO_EN;
+ txdp->Control_1 |= TXD_UFO_MSS(ufo_size);
+@@ -3572,7 +3572,7 @@ #endif
+ txdp->Host_Control = (unsigned long) skb;
+ txdp->Control_1 |= TXD_BUFFER0_SIZE(frg_len);
+
+- if (skb_shinfo(skb)->ufo_size)
++ if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
+ txdp->Control_1 |= TXD_UFO_EN;
+
+ frg_cnt = skb_shinfo(skb)->nr_frags;
+@@ -3587,12 +3587,12 @@ #endif
+ (sp->pdev, frag->page, frag->page_offset,
+ frag->size, PCI_DMA_TODEVICE);
+ txdp->Control_1 = TXD_BUFFER0_SIZE(frag->size);
+- if (skb_shinfo(skb)->ufo_size)
++ if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
+ txdp->Control_1 |= TXD_UFO_EN;
+ }
+ txdp->Control_1 |= TXD_GATHER_CODE_LAST;
+
+- if (skb_shinfo(skb)->ufo_size)
++ if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
+ frg_cnt++; /* as Txd0 was used for inband header */
+
+ tx_fifo = mac_control->tx_FIFO_start[queue];
+@@ -3606,7 +3606,7 @@ #ifdef NETIF_F_TSO
+ if (mss)
+ val64 |= TX_FIFO_SPECIAL_FUNC;
+ #endif
+- if (skb_shinfo(skb)->ufo_size)
++ if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
+ val64 |= TX_FIFO_SPECIAL_FUNC;
+ writeq(val64, &tx_fifo->List_Control);
+
+diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c
+index 0618cd5..2a55eb3 100644
+--- a/drivers/net/sky2.c
++++ b/drivers/net/sky2.c
+@@ -1125,7 +1125,7 @@ static unsigned tx_le_req(const struct s
+ count = sizeof(dma_addr_t) / sizeof(u32);
+ count += skb_shinfo(skb)->nr_frags * count;
+
+- if (skb_shinfo(skb)->tso_size)
++ if (skb_shinfo(skb)->gso_size)
+ ++count;
+
+ if (skb->ip_summed == CHECKSUM_HW)
+@@ -1197,7 +1197,7 @@ static int sky2_xmit_frame(struct sk_buf
+ }
+
+ /* Check for TCP Segmentation Offload */
+- mss = skb_shinfo(skb)->tso_size;
++ mss = skb_shinfo(skb)->gso_size;
+ if (mss != 0) {
+ /* just drop the packet if non-linear expansion fails */
+ if (skb_header_cloned(skb) &&
+diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
+index caf4102..fc9164a 100644
+--- a/drivers/net/tg3.c
++++ b/drivers/net/tg3.c
+@@ -3664,7 +3664,7 @@ static int tg3_start_xmit(struct sk_buff
+ #if TG3_TSO_SUPPORT != 0
+ mss = 0;
+ if (skb->len > (tp->dev->mtu + ETH_HLEN) &&
+- (mss = skb_shinfo(skb)->tso_size) != 0) {
++ (mss = skb_shinfo(skb)->gso_size) != 0) {
+ int tcp_opt_len, ip_tcp_len;
+
+ if (skb_header_cloned(skb) &&
+diff --git a/drivers/net/tulip/winbond-840.c b/drivers/net/tulip/winbond-840.c
+index 5b1af39..11de5af 100644
+--- a/drivers/net/tulip/winbond-840.c
++++ b/drivers/net/tulip/winbond-840.c
+@@ -1605,11 +1605,11 @@ #ifdef CONFIG_PM
+ * - get_stats:
+ * spin_lock_irq(np->lock), doesn't touch hw if not present
+ * - hard_start_xmit:
+- * netif_stop_queue + spin_unlock_wait(&dev->xmit_lock);
++ * synchronize_irq + netif_tx_disable;
+ * - tx_timeout:
+- * netif_device_detach + spin_unlock_wait(&dev->xmit_lock);
++ * netif_device_detach + netif_tx_disable;
+ * - set_multicast_list
+- * netif_device_detach + spin_unlock_wait(&dev->xmit_lock);
++ * netif_device_detach + netif_tx_disable;
+ * - interrupt handler
+ * doesn't touch hw if not present, synchronize_irq waits for
+ * running instances of the interrupt handler.
+@@ -1635,11 +1635,10 @@ static int w840_suspend (struct pci_dev
+ netif_device_detach(dev);
+ update_csr6(dev, 0);
+ iowrite32(0, ioaddr + IntrEnable);
+- netif_stop_queue(dev);
+ spin_unlock_irq(&np->lock);
+
+- spin_unlock_wait(&dev->xmit_lock);
+ synchronize_irq(dev->irq);
++ netif_tx_disable(dev);
+
+ np->stats.rx_missed_errors += ioread32(ioaddr + RxMissed) &
0xffff;
+
+diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c
+index 4c76cb7..30c48c9 100644
+--- a/drivers/net/typhoon.c
++++ b/drivers/net/typhoon.c
+@@ -340,7 +340,7 @@ #define typhoon_synchronize_irq(x) synch
+ #endif
+
+ #if defined(NETIF_F_TSO)
+-#define skb_tso_size(x) (skb_shinfo(x)->tso_size)
++#define skb_tso_size(x) (skb_shinfo(x)->gso_size)
+ #define TSO_NUM_DESCRIPTORS 2
+ #define TSO_OFFLOAD_ON TYPHOON_OFFLOAD_TCP_SEGMENT
+ #else
+diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c
+index ed1f837..2eb6b5f 100644
+--- a/drivers/net/via-velocity.c
++++ b/drivers/net/via-velocity.c
+@@ -1899,6 +1899,13 @@ static int velocity_xmit(struct sk_buff
+
+ int pktlen = skb->len;
+
++#ifdef VELOCITY_ZERO_COPY_SUPPORT
++ if (skb_shinfo(skb)->nr_frags > 6 && __skb_linearize(skb)) {
++ kfree_skb(skb);
++ return 0;
++ }
++#endif
++
+ spin_lock_irqsave(&vptr->lock, flags);
+
+ index = vptr->td_curr[qnum];
+@@ -1914,8 +1921,6 @@ static int velocity_xmit(struct sk_buff
+ */
+ if (pktlen < ETH_ZLEN) {
+ /* Cannot occur until ZC support */
+- if(skb_linearize(skb, GFP_ATOMIC))
+- return 0;
+ pktlen = ETH_ZLEN;
+ memcpy(tdinfo->buf, skb->data, skb->len);
+ memset(tdinfo->buf + skb->len, 0, ETH_ZLEN - skb->len);
+@@ -1933,7 +1938,6 @@ #ifdef VELOCITY_ZERO_COPY_SUPPORT
+ int nfrags = skb_shinfo(skb)->nr_frags;
+ tdinfo->skb = skb;
+ if (nfrags > 6) {
+- skb_linearize(skb, GFP_ATOMIC);
+ memcpy(tdinfo->buf, skb->data, skb->len);
+ tdinfo->skb_dma[0] = tdinfo->buf_dma;
+ td_ptr->tdesc0.pktsize =
+diff --git a/drivers/net/wireless/orinoco.c b/drivers/net/wireless/orinoco.c
+index 6fd0bf7..75237c1 100644
+--- a/drivers/net/wireless/orinoco.c
++++ b/drivers/net/wireless/orinoco.c
+@@ -1835,7 +1835,9 @@ static int __orinoco_program_rids(struct
+ /* Set promiscuity / multicast*/
+ priv->promiscuous = 0;
+ priv->mc_count = 0;
+- __orinoco_set_multicast_list(dev); /* FIXME: what about the xmit_lock */
++
++ /* FIXME: what about netif_tx_lock */
++ __orinoco_set_multicast_list(dev);
+
+ return 0;
+ }
+diff --git a/drivers/s390/net/qeth_eddp.c b/drivers/s390/net/qeth_eddp.c
+index 82cb4af..57cec40 100644
+--- a/drivers/s390/net/qeth_eddp.c
++++ b/drivers/s390/net/qeth_eddp.c
+@@ -421,7 +421,7 @@ #endif /* CONFIG_QETH_VLAN */
+ }
+ tcph = eddp->skb->h.th;
+ while (eddp->skb_offset < eddp->skb->len) {
+- data_len = min((int)skb_shinfo(eddp->skb)->tso_size,
++ data_len = min((int)skb_shinfo(eddp->skb)->gso_size,
+ (int)(eddp->skb->len - eddp->skb_offset));
+ /* prepare qdio hdr */
+ if (eddp->qh.hdr.l2.id == QETH_HEADER_TYPE_LAYER2){
+@@ -516,20 +516,20 @@ qeth_eddp_calc_num_pages(struct qeth_edd
+
+ QETH_DBF_TEXT(trace, 5, "eddpcanp");
+ /* can we put multiple skbs in one page? */
+- skbs_per_page = PAGE_SIZE / (skb_shinfo(skb)->tso_size + hdr_len);
++ skbs_per_page = PAGE_SIZE / (skb_shinfo(skb)->gso_size + hdr_len);
+ if (skbs_per_page > 1){
+- ctx->num_pages = (skb_shinfo(skb)->tso_segs + 1) /
++ ctx->num_pages = (skb_shinfo(skb)->gso_segs + 1) /
+ skbs_per_page + 1;
+ ctx->elements_per_skb = 1;
+ } else {
+ /* no -> how many elements per skb? */
+- ctx->elements_per_skb = (skb_shinfo(skb)->tso_size + hdr_len +
++ ctx->elements_per_skb = (skb_shinfo(skb)->gso_size + hdr_len +
+ PAGE_SIZE) >> PAGE_SHIFT;
+ ctx->num_pages = ctx->elements_per_skb *
+- (skb_shinfo(skb)->tso_segs + 1);
++ (skb_shinfo(skb)->gso_segs + 1);
+ }
+ ctx->num_elements = ctx->elements_per_skb *
+- (skb_shinfo(skb)->tso_segs + 1);
++ (skb_shinfo(skb)->gso_segs + 1);
+ }
+
+ static inline struct qeth_eddp_context *
+diff --git a/drivers/s390/net/qeth_main.c b/drivers/s390/net/qeth_main.c
+index dba7f7f..d9cc997 100644
+--- a/drivers/s390/net/qeth_main.c
++++ b/drivers/s390/net/qeth_main.c
+@@ -4454,7 +4454,7 @@ qeth_send_packet(struct qeth_card *card,
+ queue = card->qdio.out_qs
+ [qeth_get_priority_queue(card, skb, ipv, cast_type)];
+
+- if (skb_shinfo(skb)->tso_size)
++ if (skb_shinfo(skb)->gso_size)
+ large_send = card->options.large_send;
+
+ /*are we able to do TSO ? If so ,prepare and send it from here */
+@@ -4501,7 +4501,7 @@ qeth_send_packet(struct qeth_card *card,
+ card->stats.tx_packets++;
+ card->stats.tx_bytes += skb->len;
+ #ifdef CONFIG_QETH_PERF_STATS
+- if (skb_shinfo(skb)->tso_size &&
++ if (skb_shinfo(skb)->gso_size &&
+ !(large_send == QETH_LARGE_SEND_NO)) {
+ card->perf_stats.large_send_bytes += skb->len;
+ card->perf_stats.large_send_cnt++;
+diff --git a/drivers/s390/net/qeth_tso.h b/drivers/s390/net/qeth_tso.h
+index 1286dde..89cbf34 100644
+--- a/drivers/s390/net/qeth_tso.h
++++ b/drivers/s390/net/qeth_tso.h
+@@ -51,7 +51,7 @@ qeth_tso_fill_header(struct qeth_card *c
+ hdr->ext.hdr_version = 1;
+ hdr->ext.hdr_len = 28;
+ /*insert non-fix values */
+- hdr->ext.mss = skb_shinfo(skb)->tso_size;
++ hdr->ext.mss = skb_shinfo(skb)->gso_size;
+ hdr->ext.dg_hdr_len = (__u16)(iph->ihl*4 + tcph->doff*4);
+ hdr->ext.payload_len = (__u16)(skb->len - hdr->ext.dg_hdr_len -
+ sizeof(struct qeth_hdr_tso));
+diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
+index 93535f0..9269df7 100644
+--- a/include/linux/ethtool.h
++++ b/include/linux/ethtool.h
+@@ -408,6 +408,8 @@ #define ETHTOOL_STSO 0x0000001f /* Set
+ #define ETHTOOL_GPERMADDR 0x00000020 /* Get permanent hardware address */
+ #define ETHTOOL_GUFO 0x00000021 /* Get UFO enable (ethtool_value) */
+ #define ETHTOOL_SUFO 0x00000022 /* Set UFO enable (ethtool_value) */
++#define ETHTOOL_GGSO 0x00000023 /* Get GSO enable (ethtool_value) */
++#define ETHTOOL_SGSO 0x00000024 /* Set GSO enable (ethtool_value) */
+
+ /* compatibility with older code */
+ #define SPARC_ETH_GSET ETHTOOL_GSET
+diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
+index 7fda03d..458b278 100644
+--- a/include/linux/netdevice.h
++++ b/include/linux/netdevice.h
+@@ -230,7 +230,8 @@ enum netdev_state_t
+ __LINK_STATE_SCHED,
+ __LINK_STATE_NOCARRIER,
+ __LINK_STATE_RX_SCHED,
+- __LINK_STATE_LINKWATCH_PENDING
++ __LINK_STATE_LINKWATCH_PENDING,
++ __LINK_STATE_QDISC_RUNNING,
+ };
+
+
+@@ -306,9 +307,16 @@ #define NETIF_F_HW_VLAN_TX 128 /* Transm
+ #define NETIF_F_HW_VLAN_RX 256 /* Receive VLAN hw acceleration */
+ #define NETIF_F_HW_VLAN_FILTER 512 /* Receive filtering on VLAN */
+ #define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN
packets */
+-#define NETIF_F_TSO 2048 /* Can offload TCP/IP segmentation */
++#define NETIF_F_GSO 2048 /* Enable software GSO. */
+ #define NETIF_F_LLTX 4096 /* LockLess TX */
+-#define NETIF_F_UFO 8192 /* Can offload UDP Large Send*/
++
++ /* Segmentation offload features */
++#define NETIF_F_GSO_SHIFT 16
++#define NETIF_F_TSO (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
++#define NETIF_F_UFO (SKB_GSO_UDPV4 << NETIF_F_GSO_SHIFT)
++
++#define NETIF_F_GEN_CSUM (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
++#define NETIF_F_ALL_CSUM (NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM)
+
+ struct net_device *next_sched;
+
+@@ -394,6 +402,9 @@ #define NETIF_F_UFO 8192
+ struct list_head qdisc_list;
+ unsigned long tx_queue_len; /* Max frames per queue allowed
*/
+
++ /* Partially transmitted GSO packet. */
++ struct sk_buff *gso_skb;
++
+ /* ingress path synchronizer */
+ spinlock_t ingress_lock;
+ struct Qdisc *qdisc_ingress;
+@@ -402,7 +413,7 @@ #define NETIF_F_UFO 8192
+ * One part is mostly used on xmit path (device)
+ */
+ /* hard_start_xmit synchronizer */
+- spinlock_t xmit_lock ____cacheline_aligned_in_smp;
++ spinlock_t _xmit_lock ____cacheline_aligned_in_smp;
+ /* cpu id of processor entered to hard_start_xmit or -1,
+ if nobody entered there.
+ */
+@@ -527,6 +538,7 @@ struct packet_type {
+ struct net_device *,
+ struct packet_type *,
+ struct net_device *);
++ struct sk_buff *(*gso_segment)(struct sk_buff *skb, int sg);
+ void *af_packet_priv;
+ struct list_head list;
+ };
+@@ -693,7 +705,8 @@ extern int dev_change_name(struct net_d
+ extern int dev_set_mtu(struct net_device *, int);
+ extern int dev_set_mac_address(struct net_device *,
+ struct sockaddr *);
+-extern void dev_queue_xmit_nit(struct sk_buff *skb, struct
net_device *dev);
++extern int dev_hard_start_xmit(struct sk_buff *skb,
++ struct net_device *dev);
+
+ extern void dev_init(void);
+
+@@ -900,11 +913,43 @@ static inline void __netif_rx_complete(s
+ clear_bit(__LINK_STATE_RX_SCHED, &dev->state);
+ }
+
++static inline void netif_tx_lock(struct net_device *dev)
++{
++ spin_lock(&dev->_xmit_lock);
++ dev->xmit_lock_owner = smp_processor_id();
++}
++
++static inline void netif_tx_lock_bh(struct net_device *dev)
++{
++ spin_lock_bh(&dev->_xmit_lock);
++ dev->xmit_lock_owner = smp_processor_id();
++}
++
++static inline int netif_tx_trylock(struct net_device *dev)
++{
++ int err = spin_trylock(&dev->_xmit_lock);
++ if (!err)
++ dev->xmit_lock_owner = smp_processor_id();
++ return err;
++}
++
++static inline void netif_tx_unlock(struct net_device *dev)
++{
++ dev->xmit_lock_owner = -1;
++ spin_unlock(&dev->_xmit_lock);
++}
++
++static inline void netif_tx_unlock_bh(struct net_device *dev)
++{
++ dev->xmit_lock_owner = -1;
++ spin_unlock_bh(&dev->_xmit_lock);
++}
++
+ static inline void netif_tx_disable(struct net_device *dev)
+ {
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ netif_stop_queue(dev);
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ }
+
+ /* These functions live elsewhere (drivers/net/net_init.c, but related) */
+@@ -932,6 +977,7 @@ extern int netdev_max_backlog;
+ extern int weight_p;
+ extern int netdev_set_master(struct net_device *dev, struct
net_device *master);
+ extern int skb_checksum_help(struct sk_buff *skb, int inward);
++extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg);
+ #ifdef CONFIG_BUG
+ extern void netdev_rx_csum_fault(struct net_device *dev);
+ #else
+@@ -951,6 +997,13 @@ #endif
+
+ extern void linkwatch_run_queue(void);
+
++static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb)
++{
++ int feature = skb_shinfo(skb)->gso_type << NETIF_F_GSO_SHIFT;
++ return skb_shinfo(skb)->gso_size &&
++ (dev->features & feature) != feature;
++}
++
+ #endif /* __KERNEL__ */
+
+ #endif /* _LINUX_DEV_H */
+diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
+index b94d1ad..75b5b93 100644
+--- a/include/net/pkt_sched.h
++++ b/include/net/pkt_sched.h
+@@ -218,12 +218,13 @@ extern struct qdisc_rate_table *qdisc_ge
+ struct rtattr *tab);
+ extern void qdisc_put_rtab(struct qdisc_rate_table *tab);
+
+-extern int qdisc_restart(struct net_device *dev);
++extern void __qdisc_run(struct net_device *dev);
+
+ static inline void qdisc_run(struct net_device *dev)
+ {
+- while (!netif_queue_stopped(dev) && qdisc_restart(dev) < 0)
+- /* NOTHING */;
++ if (!netif_queue_stopped(dev) &&
++ !test_and_set_bit(__LINK_STATE_QDISC_RUNNING, &dev->state))
++ __qdisc_run(dev);
+ }
+
+ extern int tc_classify(struct sk_buff *skb, struct tcf_proto *tp,
+diff --git a/include/net/protocol.h b/include/net/protocol.h
+index 6dc5970..650911d 100644
+--- a/include/net/protocol.h
++++ b/include/net/protocol.h
+@@ -37,6 +37,7 @@ #define MAX_INET_PROTOS 256 /* Must be
+ struct net_protocol {
+ int (*handler)(struct sk_buff *skb);
+ void (*err_handler)(struct sk_buff *skb, u32 info);
++ struct sk_buff *(*gso_segment)(struct sk_buff *skb, int sg);
+ int no_policy;
+ };
+
+diff --git a/include/net/sock.h b/include/net/sock.h
+index f63d0d5..a8e8d21 100644
+--- a/include/net/sock.h
++++ b/include/net/sock.h
+@@ -1064,9 +1064,13 @@ static inline void sk_setup_caps(struct
+ {
+ __sk_dst_set(sk, dst);
+ sk->sk_route_caps = dst->dev->features;
++ if (sk->sk_route_caps & NETIF_F_GSO)
++ sk->sk_route_caps |= NETIF_F_TSO;
+ if (sk->sk_route_caps & NETIF_F_TSO) {
+ if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len)
+ sk->sk_route_caps &= ~NETIF_F_TSO;
++ else
++ sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
+ }
+ }
+
+diff --git a/include/net/tcp.h b/include/net/tcp.h
+index 77f21c6..40e337c 100644
+--- a/include/net/tcp.h
++++ b/include/net/tcp.h
+@@ -552,13 +552,13 @@ #include <net/tcp_ecn.h>
+ */
+ static inline int tcp_skb_pcount(const struct sk_buff *skb)
+ {
+- return skb_shinfo(skb)->tso_segs;
++ return skb_shinfo(skb)->gso_segs;
+ }
+
+ /* This is valid iff tcp_skb_pcount() > 1. */
+ static inline int tcp_skb_mss(const struct sk_buff *skb)
+ {
+- return skb_shinfo(skb)->tso_size;
++ return skb_shinfo(skb)->gso_size;
+ }
+
+ static inline void tcp_dec_pcount_approx(__u32 *count,
+@@ -1063,6 +1063,8 @@ extern struct request_sock_ops tcp_reque
+
+ extern int tcp_v4_destroy_sock(struct sock *sk);
+
++extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg);
++
+ #ifdef CONFIG_PROC_FS
+ extern int tcp4_proc_init(void);
+ extern void tcp4_proc_exit(void);
+diff --git a/net/atm/clip.c b/net/atm/clip.c
+index 1842a4e..6dc21a7 100644
+--- a/net/atm/clip.c
++++ b/net/atm/clip.c
+@@ -101,7 +101,7 @@ static void unlink_clip_vcc(struct clip_
+ printk(KERN_CRIT "!clip_vcc->entry (clip_vcc %p)\n",clip_vcc);
+ return;
+ }
+- spin_lock_bh(&entry->neigh->dev->xmit_lock); /* block
clip_start_xmit() */
++ netif_tx_lock_bh(entry->neigh->dev); /* block clip_start_xmit() */
+ entry->neigh->used = jiffies;
+ for (walk = &entry->vccs; *walk; walk = &(*walk)->next)
+ if (*walk == clip_vcc) {
+@@ -125,7 +125,7 @@ static void unlink_clip_vcc(struct clip_
+ printk(KERN_CRIT "ATMARP: unlink_clip_vcc failed (entry %p, vcc "
+ "0x%p)\n",entry,clip_vcc);
+ out:
+- spin_unlock_bh(&entry->neigh->dev->xmit_lock);
++ netif_tx_unlock_bh(entry->neigh->dev);
+ }
+
+ /* The neighbour entry n->lock is held. */
+diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
+index 0b33a7b..b9e32b6 100644
+--- a/net/bridge/br_device.c
++++ b/net/bridge/br_device.c
+@@ -146,9 +146,9 @@ static int br_set_tx_csum(struct net_dev
+ struct net_bridge *br = netdev_priv(dev);
+
+ if (data)
+- br->feature_mask |= NETIF_F_IP_CSUM;
++ br->feature_mask |= NETIF_F_NO_CSUM;
+ else
+- br->feature_mask &= ~NETIF_F_IP_CSUM;
++ br->feature_mask &= ~NETIF_F_ALL_CSUM;
+
+ br_features_recompute(br);
+ return 0;
+@@ -186,5 +186,5 @@ void br_dev_setup(struct net_device *dev
+ dev->priv_flags = IFF_EBRIDGE;
+
+ dev->features = NETIF_F_SG | NETIF_F_FRAGLIST
+- | NETIF_F_HIGHDMA | NETIF_F_TSO | NETIF_F_IP_CSUM;
++ | NETIF_F_HIGHDMA | NETIF_F_TSO | NETIF_F_NO_CSUM;
+ }
+diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
+index 2d24fb4..00b1128 100644
+--- a/net/bridge/br_forward.c
++++ b/net/bridge/br_forward.c
+@@ -32,7 +32,7 @@ static inline int should_deliver(const s
+ int br_dev_queue_push_xmit(struct sk_buff *skb)
+ {
+ /* drop mtu oversized packets except tso */
+- if (skb->len > skb->dev->mtu && !skb_shinfo(skb)->tso_size)
++ if (skb->len > skb->dev->mtu && !skb_shinfo(skb)->gso_size)
+ kfree_skb(skb);
+ else {
+ #ifdef CONFIG_BRIDGE_NETFILTER
+diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
+index f36b35e..4e9743d 100644
+--- a/net/bridge/br_if.c
++++ b/net/bridge/br_if.c
+@@ -385,14 +385,24 @@ void br_features_recompute(struct net_br
+ struct net_bridge_port *p;
+ unsigned long features, checksum;
+
+- features = br->feature_mask &~ NETIF_F_IP_CSUM;
+- checksum = br->feature_mask & NETIF_F_IP_CSUM;
++ checksum = br->feature_mask & NETIF_F_ALL_CSUM ? NETIF_F_NO_CSUM : 0;
++ features = br->feature_mask & ~NETIF_F_ALL_CSUM;
+
+ list_for_each_entry(p, &br->port_list, list) {
+- if (!(p->dev->features
+- & (NETIF_F_IP_CSUM|NETIF_F_NO_CSUM|NETIF_F_HW_CSUM)))
++ unsigned long feature = p->dev->features;
++
++ if (checksum & NETIF_F_NO_CSUM && !(feature & NETIF_F_NO_CSUM))
++ checksum ^= NETIF_F_NO_CSUM | NETIF_F_HW_CSUM;
++ if (checksum & NETIF_F_HW_CSUM && !(feature & NETIF_F_HW_CSUM))
++ checksum ^= NETIF_F_HW_CSUM | NETIF_F_IP_CSUM;
++ if (!(feature & NETIF_F_IP_CSUM))
+ checksum = 0;
+- features &= p->dev->features;
++
++ if (feature & NETIF_F_GSO)
++ feature |= NETIF_F_TSO;
++ feature |= NETIF_F_GSO;
++
++ features &= feature;
+ }
+
+ br->dev->features = features | checksum | NETIF_F_LLTX;
+diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
+index 9e27373..588207f 100644
+--- a/net/bridge/br_netfilter.c
++++ b/net/bridge/br_netfilter.c
+@@ -743,7 +743,7 @@ static int br_nf_dev_queue_xmit(struct s
+ {
+ if (skb->protocol == htons(ETH_P_IP) &&
+ skb->len > skb->dev->mtu &&
+- !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size))
++ !skb_shinfo(skb)->gso_size)
+ return ip_fragment(skb, br_dev_queue_push_xmit);
+ else
+ return br_dev_queue_push_xmit(skb);
+diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c
+index 05d6085..c57d887 100644
+--- a/net/core/dev_mcast.c
++++ b/net/core/dev_mcast.c
+@@ -62,7 +62,7 @@ #include <net/arp.h>
+ * Device mc lists are changed by bh at least if IPv6 is enabled,
+ * so that it must be bh protected.
+ *
+- * We block accesses to device mc filters with dev->xmit_lock.
++ * We block accesses to device mc filters with netif_tx_lock.
+ */
+
+ /*
+@@ -93,9 +93,9 @@ static void __dev_mc_upload(struct net_d
+
+ void dev_mc_upload(struct net_device *dev)
+ {
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ __dev_mc_upload(dev);
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ }
+
+ /*
+@@ -107,7 +107,7 @@ int dev_mc_delete(struct net_device *dev
+ int err = 0;
+ struct dev_mc_list *dmi, **dmip;
+
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+
+ for (dmip = &dev->mc_list; (dmi = *dmip) != NULL; dmip = &dmi->next) {
+ /*
+@@ -139,13 +139,13 @@ int dev_mc_delete(struct net_device *dev
+ */
+ __dev_mc_upload(dev);
+
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ return 0;
+ }
+ }
+ err = -ENOENT;
+ done:
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ return err;
+ }
+
+@@ -160,7 +160,7 @@ int dev_mc_add(struct net_device *dev, v
+
+ dmi1 = kmalloc(sizeof(*dmi), GFP_ATOMIC);
+
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ for (dmi = dev->mc_list; dmi != NULL; dmi = dmi->next) {
+ if (memcmp(dmi->dmi_addr, addr, dmi->dmi_addrlen) == 0 &&
+ dmi->dmi_addrlen == alen) {
+@@ -176,7 +176,7 @@ int dev_mc_add(struct net_device *dev, v
+ }
+
+ if ((dmi = dmi1) == NULL) {
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ return -ENOMEM;
+ }
+ memcpy(dmi->dmi_addr, addr, alen);
+@@ -189,11 +189,11 @@ int dev_mc_add(struct net_device *dev, v
+
+ __dev_mc_upload(dev);
+
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ return 0;
+
+ done:
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ kfree(dmi1);
+ return err;
+ }
+@@ -204,7 +204,7 @@ done:
+
+ void dev_mc_discard(struct net_device *dev)
+ {
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+
+ while (dev->mc_list != NULL) {
+ struct dev_mc_list *tmp = dev->mc_list;
+@@ -215,7 +215,7 @@ void dev_mc_discard(struct net_device *d
+ }
+ dev->mc_count = 0;
+
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ }
+
+ #ifdef CONFIG_PROC_FS
+@@ -250,7 +250,7 @@ static int dev_mc_seq_show(struct seq_fi
+ struct dev_mc_list *m;
+ struct net_device *dev = v;
+
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ for (m = dev->mc_list; m; m = m->next) {
+ int i;
+
+@@ -262,7 +262,7 @@ static int dev_mc_seq_show(struct seq_fi
+
+ seq_putc(seq, '\n');
+ }
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ return 0;
+ }
+
+diff --git a/net/core/ethtool.c b/net/core/ethtool.c
+index e6f7610..27ce168 100644
+--- a/net/core/ethtool.c
++++ b/net/core/ethtool.c
+@@ -30,7 +30,7 @@ u32 ethtool_op_get_link(struct net_devic
+
+ u32 ethtool_op_get_tx_csum(struct net_device *dev)
+ {
+- return (dev->features & (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM)) != 0;
++ return (dev->features & NETIF_F_ALL_CSUM) != 0;
+ }
+
+ int ethtool_op_set_tx_csum(struct net_device *dev, u32 data)
+@@ -551,9 +551,7 @@ static int ethtool_set_sg(struct net_dev
+ return -EFAULT;
+
+ if (edata.data &&
+- !(dev->features & (NETIF_F_IP_CSUM |
+- NETIF_F_NO_CSUM |
+- NETIF_F_HW_CSUM)))
++ !(dev->features & NETIF_F_ALL_CSUM))
+ return -EINVAL;
+
+ return __ethtool_set_sg(dev, edata.data);
+@@ -591,7 +589,7 @@ static int ethtool_set_tso(struct net_de
+
+ static int ethtool_get_ufo(struct net_device *dev, char __user *useraddr)
+ {
+- struct ethtool_value edata = { ETHTOOL_GTSO };
++ struct ethtool_value edata = { ETHTOOL_GUFO };
+
+ if (!dev->ethtool_ops->get_ufo)
+ return -EOPNOTSUPP;
+@@ -600,6 +598,7 @@ static int ethtool_get_ufo(struct net_de
+ return -EFAULT;
+ return 0;
+ }
++
+ static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr)
+ {
+ struct ethtool_value edata;
+@@ -615,6 +614,29 @@ static int ethtool_set_ufo(struct net_de
+ return dev->ethtool_ops->set_ufo(dev, edata.data);
+ }
+
++static int ethtool_get_gso(struct net_device *dev, char __user *useraddr)
++{
++ struct ethtool_value edata = { ETHTOOL_GGSO };
++
++ edata.data = dev->features & NETIF_F_GSO;
++ if (copy_to_user(useraddr, &edata, sizeof(edata)))
++ return -EFAULT;
++ return 0;
++}
++
++static int ethtool_set_gso(struct net_device *dev, char __user *useraddr)
++{
++ struct ethtool_value edata;
++
++ if (copy_from_user(&edata, useraddr, sizeof(edata)))
++ return -EFAULT;
++ if (edata.data)
++ dev->features |= NETIF_F_GSO;
++ else
++ dev->features &= ~NETIF_F_GSO;
++ return 0;
++}
++
+ static int ethtool_self_test(struct net_device *dev, char __user *useraddr)
+ {
+ struct ethtool_test test;
+@@ -906,6 +928,12 @@ int dev_ethtool(struct ifreq *ifr)
+ case ETHTOOL_SUFO:
+ rc = ethtool_set_ufo(dev, useraddr);
+ break;
++ case ETHTOOL_GGSO:
++ rc = ethtool_get_gso(dev, useraddr);
++ break;
++ case ETHTOOL_SGSO:
++ rc = ethtool_set_gso(dev, useraddr);
++ break;
+ default:
+ rc = -EOPNOTSUPP;
+ }
+diff --git a/net/core/netpoll.c b/net/core/netpoll.c
+index ea51f8d..ec28d3b 100644
+--- a/net/core/netpoll.c
++++ b/net/core/netpoll.c
+@@ -273,24 +273,21 @@ static void netpoll_send_skb(struct netp
+
+ do {
+ npinfo->tries--;
+- spin_lock(&np->dev->xmit_lock);
+- np->dev->xmit_lock_owner = smp_processor_id();
++ netif_tx_lock(np->dev);
+
+ /*
+ * network drivers do not expect to be called if the queue is
+ * stopped.
+ */
+ if (netif_queue_stopped(np->dev)) {
+- np->dev->xmit_lock_owner = -1;
+- spin_unlock(&np->dev->xmit_lock);
++ netif_tx_unlock(np->dev);
+ netpoll_poll(np);
+ udelay(50);
+ continue;
+ }
+
+ status = np->dev->hard_start_xmit(skb, np->dev);
+- np->dev->xmit_lock_owner = -1;
+- spin_unlock(&np->dev->xmit_lock);
++ netif_tx_unlock(np->dev);
+
+ /* success */
+ if(!status) {
+diff --git a/net/core/pktgen.c b/net/core/pktgen.c
+index da16f8f..2380347 100644
+--- a/net/core/pktgen.c
++++ b/net/core/pktgen.c
+@@ -2582,7 +2582,7 @@ static __inline__ void pktgen_xmit(struc
+ }
+ }
+
+- spin_lock_bh(&odev->xmit_lock);
++ netif_tx_lock_bh(odev);
+ if (!netif_queue_stopped(odev)) {
+
+ atomic_inc(&(pkt_dev->skb->users));
+@@ -2627,7 +2627,7 @@ retry_now:
+ pkt_dev->next_tx_ns = 0;
+ }
+
+- spin_unlock_bh(&odev->xmit_lock);
++ netif_tx_unlock_bh(odev);
+
+ /* If pkt_dev->count is zero, then run forever */
+ if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) {
+diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
+index 44bda85..2e3323a 100644
+--- a/net/decnet/dn_nsp_in.c
++++ b/net/decnet/dn_nsp_in.c
+@@ -801,8 +801,7 @@ got_it:
+ * We linearize everything except data segments here.
+ */
+ if (cb->nsp_flags & ~0x60) {
+- if (unlikely(skb_is_nonlinear(skb)) &&
+- skb_linearize(skb, GFP_ATOMIC) != 0)
++ if (unlikely(skb_linearize(skb)))
+ goto free_out;
+ }
+
+diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
+index 3407f19..a0a25e0 100644
+--- a/net/decnet/dn_route.c
++++ b/net/decnet/dn_route.c
+@@ -629,8 +629,7 @@ int dn_route_rcv(struct sk_buff *skb, st
+ padlen);
+
+ if (flags & DN_RT_PKT_CNTL) {
+- if (unlikely(skb_is_nonlinear(skb)) &&
+- skb_linearize(skb, GFP_ATOMIC) != 0)
++ if (unlikely(skb_linearize(skb)))
+ goto dump_it;
+
+ switch(flags & DN_RT_CNTL_MSK) {
+diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
+index 97c276f..3692db5 100644
+--- a/net/ipv4/af_inet.c
++++ b/net/ipv4/af_inet.c
+@@ -68,6 +68,7 @@
+ */
+
+ #include <linux/config.h>
++#include <linux/err.h>
+ #include <linux/errno.h>
+ #include <linux/types.h>
+ #include <linux/socket.h>
+@@ -1084,6 +1085,54 @@ int inet_sk_rebuild_header(struct sock *
+
+ EXPORT_SYMBOL(inet_sk_rebuild_header);
+
++static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int sg)
++{
++ struct sk_buff *segs = ERR_PTR(-EINVAL);
++ struct iphdr *iph;
++ struct net_protocol *ops;
++ int proto;
++ int ihl;
++ int id;
++
++ if (!pskb_may_pull(skb, sizeof(*iph)))
++ goto out;
++
++ iph = skb->nh.iph;
++ ihl = iph->ihl * 4;
++ if (ihl < sizeof(*iph))
++ goto out;
++
++ if (!pskb_may_pull(skb, ihl))
++ goto out;
++
++ skb->h.raw = __skb_pull(skb, ihl);
++ iph = skb->nh.iph;
++ id = ntohs(iph->id);
++ proto = iph->protocol & (MAX_INET_PROTOS - 1);
++ segs = ERR_PTR(-EPROTONOSUPPORT);
++
++ rcu_read_lock();
++ ops = rcu_dereference(inet_protos[proto]);
++ if (ops && ops->gso_segment)
++ segs = ops->gso_segment(skb, sg);
++ rcu_read_unlock();
++
++ if (IS_ERR(segs))
++ goto out;
++
++ skb = segs;
++ do {
++ iph = skb->nh.iph;
++ iph->id = htons(id++);
++ iph->tot_len = htons(skb->len - skb->mac_len);
++ iph->check = 0;
++ iph->check = ip_fast_csum(skb->nh.raw, iph->ihl);
++ } while ((skb = skb->next));
++
++out:
++ return segs;
++}
++
+ #ifdef CONFIG_IP_MULTICAST
+ static struct net_protocol igmp_protocol = {
+ .handler = igmp_rcv,
+@@ -1093,6 +1142,7 @@ #endif
+ static struct net_protocol tcp_protocol = {
+ .handler = tcp_v4_rcv,
+ .err_handler = tcp_v4_err,
++ .gso_segment = tcp_tso_segment,
+ .no_policy = 1,
+ };
+
+@@ -1138,6 +1188,7 @@ static int ipv4_proc_init(void);
+ static struct packet_type ip_packet_type = {
+ .type = __constant_htons(ETH_P_IP),
+ .func = ip_rcv,
++ .gso_segment = inet_gso_segment,
+ };
+
+ static int __init inet_init(void)
+diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
+index 8dcba38..19c3c73 100644
+--- a/net/ipv4/ip_output.c
++++ b/net/ipv4/ip_output.c
+@@ -210,8 +210,7 @@ #if defined(CONFIG_NETFILTER) && defined
+ return dst_output(skb);
+ }
+ #endif
+- if (skb->len > dst_mtu(skb->dst) &&
+- !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size))
++ if (skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size)
+ return ip_fragment(skb, ip_finish_output2);
+ else
+ return ip_finish_output2(skb);
+@@ -362,7 +361,7 @@ packet_routed:
+ }
+
+ ip_select_ident_more(iph, &rt->u.dst, sk,
+- (skb_shinfo(skb)->tso_segs ?: 1) - 1);
++ (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+
+ /* Add an IP checksum. */
+ ip_send_check(iph);
+@@ -743,7 +742,8 @@ static inline int ip_ufo_append_data(str
+ (length - transhdrlen));
+ if (!err) {
+ /* specify the length of each IP datagram fragment*/
+- skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen);
++ skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
++ skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
+ __skb_queue_tail(&sk->sk_write_queue, skb);
+
+ return 0;
+@@ -839,7 +839,7 @@ int ip_append_data(struct sock *sk,
+ */
+ if (transhdrlen &&
+ length + fragheaderlen <= mtu &&
+-
rt->u.dst.dev->features&(NETIF_F_IP_CSUM|NETIF_F_NO_CSUM|NETIF_F_HW_CSUM) &&
++ rt->u.dst.dev->features & NETIF_F_ALL_CSUM &&
+ !exthdrlen)
+ csummode = CHECKSUM_HW;
+
+@@ -1086,14 +1086,16 @@ ssize_t ip_append_page(struct sock *sk,
+
+ inet->cork.length += size;
+ if ((sk->sk_protocol == IPPROTO_UDP) &&
+- (rt->u.dst.dev->features & NETIF_F_UFO))
+- skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen);
++ (rt->u.dst.dev->features & NETIF_F_UFO)) {
++ skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
++ skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
++ }
+
+
+ while (size > 0) {
+ int i;
+
+- if (skb_shinfo(skb)->ufo_size)
++ if (skb_shinfo(skb)->gso_size)
+ len = size;
+ else {
+
+diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
+index d64e2ec..7494823 100644
+--- a/net/ipv4/ipcomp.c
++++ b/net/ipv4/ipcomp.c
+@@ -84,7 +84,7 @@ static int ipcomp_input(struct xfrm_stat
+ struct xfrm_decap_state *decap, struct sk_buff *skb)
+ {
+ u8 nexthdr;
+- int err = 0;
++ int err = -ENOMEM;
+ struct iphdr *iph;
+ union {
+ struct iphdr iph;
+@@ -92,11 +92,8 @@ static int ipcomp_input(struct xfrm_stat
+ } tmp_iph;
+
+
+- if ((skb_is_nonlinear(skb) || skb_cloned(skb)) &&
+- skb_linearize(skb, GFP_ATOMIC) != 0) {
+- err = -ENOMEM;
++ if (skb_linearize_cow(skb))
+ goto out;
+- }
+
+ skb->ip_summed = CHECKSUM_NONE;
+
+@@ -171,10 +168,8 @@ static int ipcomp_output(struct xfrm_sta
+ goto out_ok;
+ }
+
+- if ((skb_is_nonlinear(skb) || skb_cloned(skb)) &&
+- skb_linearize(skb, GFP_ATOMIC) != 0) {
++ if (skb_linearize_cow(skb))
+ goto out_ok;
+- }
+
+ err = ipcomp_compress(x, skb);
+ iph = skb->nh.iph;
+diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
+index 00aa80e..de0753f 100644
+--- a/net/ipv4/tcp.c
++++ b/net/ipv4/tcp.c
+@@ -257,6 +257,7 @@ #include <linux/smp_lock.h>
+ #include <linux/fs.h>
+ #include <linux/random.h>
+ #include <linux/bootmem.h>
++#include <linux/err.h>
+
+ #include <net/icmp.h>
+ #include <net/tcp.h>
+@@ -570,7 +571,7 @@ new_segment:
+ skb->ip_summed = CHECKSUM_HW;
+ tp->write_seq += copy;
+ TCP_SKB_CB(skb)->end_seq += copy;
+- skb_shinfo(skb)->tso_segs = 0;
++ skb_shinfo(skb)->gso_segs = 0;
+
+ if (!copied)
+ TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH;
+@@ -621,14 +622,10 @@ ssize_t tcp_sendpage(struct socket *sock
+ ssize_t res;
+ struct sock *sk = sock->sk;
+
+-#define TCP_ZC_CSUM_FLAGS (NETIF_F_IP_CSUM | NETIF_F_NO_CSUM |
NETIF_F_HW_CSUM)
+-
+ if (!(sk->sk_route_caps & NETIF_F_SG) ||
+- !(sk->sk_route_caps & TCP_ZC_CSUM_FLAGS))
++ !(sk->sk_route_caps & NETIF_F_ALL_CSUM))
+ return sock_no_sendpage(sock, page, offset, size, flags);
+
+-#undef TCP_ZC_CSUM_FLAGS
+-
+ lock_sock(sk);
+ TCP_CHECK_TIMER(sk);
+ res = do_tcp_sendpages(sk, &page, offset, size, flags);
+@@ -725,9 +722,7 @@ new_segment:
+ /*
+ * Check whether we can use HW checksum.
+ */
+- if (sk->sk_route_caps &
+- (NETIF_F_IP_CSUM | NETIF_F_NO_CSUM |
+- NETIF_F_HW_CSUM))
++ if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
+ skb->ip_summed = CHECKSUM_HW;
+
+ skb_entail(sk, tp, skb);
+@@ -823,7 +818,7 @@ new_segment:
+
+ tp->write_seq += copy;
+ TCP_SKB_CB(skb)->end_seq += copy;
+- skb_shinfo(skb)->tso_segs = 0;
++ skb_shinfo(skb)->gso_segs = 0;
+
+ from += copy;
+ copied += copy;
+@@ -2026,6 +2021,67 @@ int tcp_getsockopt(struct sock *sk, int
+ }
+
+
++struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg)
++{
++ struct sk_buff *segs = ERR_PTR(-EINVAL);
++ struct tcphdr *th;
++ unsigned thlen;
++ unsigned int seq;
++ unsigned int delta;
++ unsigned int oldlen;
++ unsigned int len;
++
++ if (!pskb_may_pull(skb, sizeof(*th)))
++ goto out;
++
++ th = skb->h.th;
++ thlen = th->doff * 4;
++ if (thlen < sizeof(*th))
++ goto out;
++
++ if (!pskb_may_pull(skb, thlen))
++ goto out;
++
++ oldlen = (u16)~skb->len;
++ __skb_pull(skb, thlen);
++
++ segs = skb_segment(skb, sg);
++ if (IS_ERR(segs))
++ goto out;
++
++ len = skb_shinfo(skb)->gso_size;
++ delta = htonl(oldlen + (thlen + len));
++
++ skb = segs;
++ th = skb->h.th;
++ seq = ntohl(th->seq);
++
++ do {
++ th->fin = th->psh = 0;
++
++ th->check = ~csum_fold(th->check + delta);
++ if (skb->ip_summed != CHECKSUM_HW)
++ th->check = csum_fold(csum_partial(skb->h.raw, thlen,
++ skb->csum));
++
++ seq += len;
++ skb = skb->next;
++ th = skb->h.th;
++
++ th->seq = htonl(seq);
++ th->cwr = 0;
++ } while (skb->next);
++
++ delta = htonl(oldlen + (skb->tail - skb->h.raw) + skb->data_len);
++ th->check = ~csum_fold(th->check + delta);
++ if (skb->ip_summed != CHECKSUM_HW)
++ th->check = csum_fold(csum_partial(skb->h.raw, thlen,
++ skb->csum));
++
++out:
++ return segs;
++}
++
+ extern void __skb_cb_too_small_for_tcp(int, int);
+ extern struct tcp_congestion_ops tcp_reno;
+
+diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
+index e9a54ae..defe77a 100644
+--- a/net/ipv4/tcp_input.c
++++ b/net/ipv4/tcp_input.c
+@@ -1072,7 +1072,7 @@ tcp_sacktag_write_queue(struct sock *sk,
+ else
+ pkt_len = (end_seq -
+ TCP_SKB_CB(skb)->seq);
+- if (tcp_fragment(sk, skb, pkt_len,
skb_shinfo(skb)->tso_size))
++ if (tcp_fragment(sk, skb, pkt_len,
skb_shinfo(skb)->gso_size))
+ break;
+ pcount = tcp_skb_pcount(skb);
+ }
+diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
+index 310f2e6..ee01f69 100644
+--- a/net/ipv4/tcp_output.c
++++ b/net/ipv4/tcp_output.c
+@@ -497,15 +497,17 @@ static void tcp_set_skb_tso_segs(struct
+ /* Avoid the costly divide in the normal
+ * non-TSO case.
+ */
+- skb_shinfo(skb)->tso_segs = 1;
+- skb_shinfo(skb)->tso_size = 0;
++ skb_shinfo(skb)->gso_segs = 1;
++ skb_shinfo(skb)->gso_size = 0;
++ skb_shinfo(skb)->gso_type = 0;
+ } else {
+ unsigned int factor;
+
+ factor = skb->len + (mss_now - 1);
+ factor /= mss_now;
+- skb_shinfo(skb)->tso_segs = factor;
+- skb_shinfo(skb)->tso_size = mss_now;
++ skb_shinfo(skb)->gso_segs = factor;
++ skb_shinfo(skb)->gso_size = mss_now;
++ skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+ }
+ }
+
+@@ -850,7 +852,7 @@ static int tcp_init_tso_segs(struct sock
+
+ if (!tso_segs ||
+ (tso_segs > 1 &&
+- skb_shinfo(skb)->tso_size != mss_now)) {
++ tcp_skb_mss(skb) != mss_now)) {
+ tcp_set_skb_tso_segs(sk, skb, mss_now);
+ tso_segs = tcp_skb_pcount(skb);
+ }
+@@ -1510,8 +1512,9 @@ int tcp_retransmit_skb(struct sock *sk,
+ tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
+ if (!pskb_trim(skb, 0)) {
+ TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->end_seq - 1;
+- skb_shinfo(skb)->tso_segs = 1;
+- skb_shinfo(skb)->tso_size = 0;
++ skb_shinfo(skb)->gso_segs = 1;
++ skb_shinfo(skb)->gso_size = 0;
++ skb_shinfo(skb)->gso_type = 0;
+ skb->ip_summed = CHECKSUM_NONE;
+ skb->csum = 0;
+ }
+@@ -1716,8 +1719,9 @@ void tcp_send_fin(struct sock *sk)
+ skb->csum = 0;
+ TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_FIN);
+ TCP_SKB_CB(skb)->sacked = 0;
+- skb_shinfo(skb)->tso_segs = 1;
+- skb_shinfo(skb)->tso_size = 0;
++ skb_shinfo(skb)->gso_segs = 1;
++ skb_shinfo(skb)->gso_size = 0;
++ skb_shinfo(skb)->gso_type = 0;
+
+ /* FIN eats a sequence byte, write_seq advanced by
tcp_queue_skb(). */
+ TCP_SKB_CB(skb)->seq = tp->write_seq;
+@@ -1749,8 +1753,9 @@ void tcp_send_active_reset(struct sock *
+ skb->csum = 0;
+ TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_RST);
+ TCP_SKB_CB(skb)->sacked = 0;
+- skb_shinfo(skb)->tso_segs = 1;
+- skb_shinfo(skb)->tso_size = 0;
++ skb_shinfo(skb)->gso_segs = 1;
++ skb_shinfo(skb)->gso_size = 0;
++ skb_shinfo(skb)->gso_type = 0;
+
+ /* Send it off. */
+ TCP_SKB_CB(skb)->seq = tcp_acceptable_seq(sk, tp);
+@@ -1833,8 +1838,9 @@ struct sk_buff * tcp_make_synack(struct
+ TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn;
+ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
+ TCP_SKB_CB(skb)->sacked = 0;
+- skb_shinfo(skb)->tso_segs = 1;
+- skb_shinfo(skb)->tso_size = 0;
++ skb_shinfo(skb)->gso_segs = 1;
++ skb_shinfo(skb)->gso_size = 0;
++ skb_shinfo(skb)->gso_type = 0;
+ th->seq = htonl(TCP_SKB_CB(skb)->seq);
+ th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
+ if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
+@@ -1937,8 +1943,9 @@ int tcp_connect(struct sock *sk)
+ TCP_SKB_CB(buff)->flags = TCPCB_FLAG_SYN;
+ TCP_ECN_send_syn(sk, tp, buff);
+ TCP_SKB_CB(buff)->sacked = 0;
+- skb_shinfo(buff)->tso_segs = 1;
+- skb_shinfo(buff)->tso_size = 0;
++ skb_shinfo(buff)->gso_segs = 1;
++ skb_shinfo(buff)->gso_size = 0;
++ skb_shinfo(buff)->gso_type = 0;
+ buff->csum = 0;
+ TCP_SKB_CB(buff)->seq = tp->write_seq++;
+ TCP_SKB_CB(buff)->end_seq = tp->write_seq;
+@@ -2042,8 +2049,9 @@ void tcp_send_ack(struct sock *sk)
+ buff->csum = 0;
+ TCP_SKB_CB(buff)->flags = TCPCB_FLAG_ACK;
+ TCP_SKB_CB(buff)->sacked = 0;
+- skb_shinfo(buff)->tso_segs = 1;
+- skb_shinfo(buff)->tso_size = 0;
++ skb_shinfo(buff)->gso_segs = 1;
++ skb_shinfo(buff)->gso_size = 0;
++ skb_shinfo(buff)->gso_type = 0;
+
+ /* Send it off, this clears delayed acks for us. */
+ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(buff)->end_seq =
tcp_acceptable_seq(sk, tp);
+@@ -2078,8 +2086,9 @@ static int tcp_xmit_probe_skb(struct soc
+ skb->csum = 0;
+ TCP_SKB_CB(skb)->flags = TCPCB_FLAG_ACK;
+ TCP_SKB_CB(skb)->sacked = urgent;
+- skb_shinfo(skb)->tso_segs = 1;
+- skb_shinfo(skb)->tso_size = 0;
++ skb_shinfo(skb)->gso_segs = 1;
++ skb_shinfo(skb)->gso_size = 0;
++ skb_shinfo(skb)->gso_type = 0;
+
+ /* Use a previous sequence. This should cause the other
+ * end to send an ack. Don't queue or clone SKB, just
+diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
+index 32ad229..737c1db 100644
+--- a/net/ipv4/xfrm4_output.c
++++ b/net/ipv4/xfrm4_output.c
+@@ -9,6 +9,8 @@
+ */
+
+ #include <linux/compiler.h>
++#include <linux/if_ether.h>
++#include <linux/kernel.h>
+ #include <linux/skbuff.h>
+ #include <linux/spinlock.h>
+ #include <linux/netfilter_ipv4.h>
+@@ -152,16 +154,10 @@ error_nolock:
+ goto out_exit;
+ }
+
+-static int xfrm4_output_finish(struct sk_buff *skb)
++static int xfrm4_output_finish2(struct sk_buff *skb)
+ {
+ int err;
+
+-#ifdef CONFIG_NETFILTER
+- if (!skb->dst->xfrm) {
+- IPCB(skb)->flags |= IPSKB_REROUTED;
+- return dst_output(skb);
+- }
+-#endif
+ while (likely((err = xfrm4_output_one(skb)) == 0)) {
+ nf_reset(skb);
+
+@@ -174,7 +170,7 @@ #endif
+ return dst_output(skb);
+
+ err = nf_hook(PF_INET, NF_IP_POST_ROUTING, &skb, NULL,
+- skb->dst->dev, xfrm4_output_finish);
++ skb->dst->dev, xfrm4_output_finish2);
+ if (unlikely(err != 1))
+ break;
+ }
+@@ -182,6 +178,48 @@ #endif
+ return err;
+ }
+
++static int xfrm4_output_finish(struct sk_buff *skb)
++{
++ struct sk_buff *segs;
++
++#ifdef CONFIG_NETFILTER
++ if (!skb->dst->xfrm) {
++ IPCB(skb)->flags |= IPSKB_REROUTED;
++ return dst_output(skb);
++ }
++#endif
++
++ if (!skb_shinfo(skb)->gso_size)
++ return xfrm4_output_finish2(skb);
++
++ skb->protocol = htons(ETH_P_IP);
++ segs = skb_gso_segment(skb, 0);
++ kfree_skb(skb);
++ if (unlikely(IS_ERR(segs)))
++ return PTR_ERR(segs);
++
++ do {
++ struct sk_buff *nskb = segs->next;
++ int err;
++
++ segs->next = NULL;
++ err = xfrm4_output_finish2(segs);
++
++ if (unlikely(err)) {
++ while ((segs = nskb)) {
++ nskb = segs->next;
++ segs->next = NULL;
++ kfree_skb(segs);
++ }
++ return err;
++ }
++
++ segs = nskb;
++ } while (segs);
++
++ return 0;
++}
++
+ int xfrm4_output(struct sk_buff *skb)
+ {
+ return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL,
skb->dst->dev,
+diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
+index 5bf70b1..cf5d17e 100644
+--- a/net/ipv6/ip6_output.c
++++ b/net/ipv6/ip6_output.c
+@@ -147,7 +147,7 @@ static int ip6_output2(struct sk_buff *s
+
+ int ip6_output(struct sk_buff *skb)
+ {
+- if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->ufo_size) ||
++ if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size) ||
+ dst_allfrag(skb->dst))
+ return ip6_fragment(skb, ip6_output2);
+ else
+@@ -829,8 +829,9 @@ static inline int ip6_ufo_append_data(st
+ struct frag_hdr fhdr;
+
+ /* specify the length of each IP datagram fragment*/
+- skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen) -
+- sizeof(struct frag_hdr);
++ skb_shinfo(skb)->gso_size = mtu - fragheaderlen -
++ sizeof(struct frag_hdr);
++ skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
+ ipv6_select_ident(skb, &fhdr);
+ skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
+ __skb_queue_tail(&sk->sk_write_queue, skb);
+diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
+index d511a88..ef56d5d 100644
+--- a/net/ipv6/ipcomp6.c
++++ b/net/ipv6/ipcomp6.c
+@@ -64,7 +64,7 @@ static LIST_HEAD(ipcomp6_tfms_list);
+
+ static int ipcomp6_input(struct xfrm_state *x, struct xfrm_decap_state
*decap, struct sk_buff *skb)
+ {
+- int err = 0;
++ int err = -ENOMEM;
+ u8 nexthdr = 0;
+ int hdr_len = skb->h.raw - skb->nh.raw;
+ unsigned char *tmp_hdr = NULL;
+@@ -75,11 +75,8 @@ static int ipcomp6_input(struct xfrm_sta
+ struct crypto_tfm *tfm;
+ int cpu;
+
+- if ((skb_is_nonlinear(skb) || skb_cloned(skb)) &&
+- skb_linearize(skb, GFP_ATOMIC) != 0) {
+- err = -ENOMEM;
++ if (skb_linearize_cow(skb))
+ goto out;
+- }
+
+ skb->ip_summed = CHECKSUM_NONE;
+
+@@ -158,10 +155,8 @@ static int ipcomp6_output(struct xfrm_st
+ goto out_ok;
+ }
+
+- if ((skb_is_nonlinear(skb) || skb_cloned(skb)) &&
+- skb_linearize(skb, GFP_ATOMIC) != 0) {
++ if (skb_linearize_cow(skb))
+ goto out_ok;
+- }
+
+ /* compression */
+ plen = skb->len - hdr_len;
+diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
+index 8024217..39bdeec 100644
+--- a/net/ipv6/xfrm6_output.c
++++ b/net/ipv6/xfrm6_output.c
+@@ -151,7 +151,7 @@ error_nolock:
+ goto out_exit;
+ }
+
+-static int xfrm6_output_finish(struct sk_buff *skb)
++static int xfrm6_output_finish2(struct sk_buff *skb)
+ {
+ int err;
+
+@@ -167,7 +167,7 @@ static int xfrm6_output_finish(struct sk
+ return dst_output(skb);
+
+ err = nf_hook(PF_INET6, NF_IP6_POST_ROUTING, &skb, NULL,
+- skb->dst->dev, xfrm6_output_finish);
++ skb->dst->dev, xfrm6_output_finish2);
+ if (unlikely(err != 1))
+ break;
+ }
+@@ -175,6 +175,41 @@ static int xfrm6_output_finish(struct sk
+ return err;
+ }
+
++static int xfrm6_output_finish(struct sk_buff *skb)
++{
++ struct sk_buff *segs;
++
++ if (!skb_shinfo(skb)->gso_size)
++ return xfrm6_output_finish2(skb);
++
++ skb->protocol = htons(ETH_P_IP);
++ segs = skb_gso_segment(skb, 0);
++ kfree_skb(skb);
++ if (unlikely(IS_ERR(segs)))
++ return PTR_ERR(segs);
++
++ do {
++ struct sk_buff *nskb = segs->next;
++ int err;
++
++ segs->next = NULL;
++ err = xfrm6_output_finish2(segs);
++
++ if (unlikely(err)) {
++ while ((segs = nskb)) {
++ nskb = segs->next;
++ segs->next = NULL;
++ kfree_skb(segs);
++ }
++ return err;
++ }
++
++ segs = nskb;
++ } while (segs);
++
++ return 0;
++}
++
+ int xfrm6_output(struct sk_buff *skb)
+ {
+ return NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, skb, NULL, skb->dst->dev,
+diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
+index 99ceb91..28c9efd 100644
+--- a/net/sched/sch_generic.c
++++ b/net/sched/sch_generic.c
+@@ -72,9 +72,9 @@ void qdisc_unlock_tree(struct net_device
+ dev->queue_lock serializes queue accesses for this device
+ AND dev->qdisc pointer itself.
+
+- dev->xmit_lock serializes accesses to device driver.
++ netif_tx_lock serializes accesses to device driver.
+
+- dev->queue_lock and dev->xmit_lock are mutually exclusive,
++ dev->queue_lock and netif_tx_lock are mutually exclusive,
+ if one is grabbed, another must be free.
+ */
+
+@@ -90,14 +90,17 @@ void qdisc_unlock_tree(struct net_device
+ NOTE: Called under dev->queue_lock with locally disabled BH.
+ */
+
+-int qdisc_restart(struct net_device *dev)
++static inline int qdisc_restart(struct net_device *dev)
+ {
+ struct Qdisc *q = dev->qdisc;
+ struct sk_buff *skb;
+
+ /* Dequeue packet */
+- if ((skb = q->dequeue(q)) != NULL) {
++ if (((skb = dev->gso_skb)) || ((skb = q->dequeue(q)))) {
+ unsigned nolock = (dev->features & NETIF_F_LLTX);
++
++ dev->gso_skb = NULL;
++
+ /*
+ * When the driver has LLTX set it does its own locking
+ * in start_xmit. No need to add additional overhead by
+@@ -108,7 +111,7 @@ int qdisc_restart(struct net_device *dev
+ * will be requeued.
+ */
+ if (!nolock) {
+- if (!spin_trylock(&dev->xmit_lock)) {
++ if (!netif_tx_trylock(dev)) {
+ collision:
+ /* So, someone grabbed the driver. */
+
+@@ -126,8 +129,6 @@ int qdisc_restart(struct net_device *dev
+ __get_cpu_var(netdev_rx_stat).cpu_collision++;
+ goto requeue;
+ }
+- /* Remember that the driver is grabbed by us. */
+- dev->xmit_lock_owner = smp_processor_id();
+ }
+
+ {
+@@ -136,14 +137,11 @@ int qdisc_restart(struct net_device *dev
+
+ if (!netif_queue_stopped(dev)) {
+ int ret;
+- if (netdev_nit)
+- dev_queue_xmit_nit(skb, dev);
+
+- ret = dev->hard_start_xmit(skb, dev);
++ ret = dev_hard_start_xmit(skb, dev);
+ if (ret == NETDEV_TX_OK) {
+ if (!nolock) {
+- dev->xmit_lock_owner = -1;
+- spin_unlock(&dev->xmit_lock);
++ netif_tx_unlock(dev);
+ }
+ spin_lock(&dev->queue_lock);
+ return -1;
+@@ -157,8 +155,7 @@ int qdisc_restart(struct net_device *dev
+ /* NETDEV_TX_BUSY - we need to requeue */
+ /* Release the driver */
+ if (!nolock) {
+- dev->xmit_lock_owner = -1;
+- spin_unlock(&dev->xmit_lock);
++ netif_tx_unlock(dev);
+ }
+ spin_lock(&dev->queue_lock);
+ q = dev->qdisc;
+@@ -175,7 +172,10 @@ int qdisc_restart(struct net_device *dev
+ */
+
+ requeue:
+- q->ops->requeue(skb, q);
++ if (skb->next)
++ dev->gso_skb = skb;
++ else
++ q->ops->requeue(skb, q);
+ netif_schedule(dev);
+ return 1;
+ }
+@@ -183,11 +183,23 @@ requeue:
+ return q->q.qlen;
+ }
+
++void __qdisc_run(struct net_device *dev)
++{
++ if (unlikely(dev->qdisc == &noop_qdisc))
++ goto out;
++
++ while (qdisc_restart(dev) < 0 && !netif_queue_stopped(dev))
++ /* NOTHING */;
++
++out:
++ clear_bit(__LINK_STATE_QDISC_RUNNING, &dev->state);
++}
++
+ static void dev_watchdog(unsigned long arg)
+ {
+ struct net_device *dev = (struct net_device *)arg;
+
+- spin_lock(&dev->xmit_lock);
++ netif_tx_lock(dev);
+ if (dev->qdisc != &noop_qdisc) {
+ if (netif_device_present(dev) &&
+ netif_running(dev) &&
+@@ -201,7 +213,7 @@ static void dev_watchdog(unsigned long a
+ dev_hold(dev);
+ }
+ }
+- spin_unlock(&dev->xmit_lock);
++ netif_tx_unlock(dev);
+
+ dev_put(dev);
+ }
+@@ -225,17 +237,17 @@ void __netdev_watchdog_up(struct net_dev
+
+ static void dev_watchdog_up(struct net_device *dev)
+ {
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ __netdev_watchdog_up(dev);
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ }
+
+ static void dev_watchdog_down(struct net_device *dev)
+ {
+- spin_lock_bh(&dev->xmit_lock);
++ netif_tx_lock_bh(dev);
+ if (del_timer(&dev->watchdog_timer))
+ __dev_put(dev);
+- spin_unlock_bh(&dev->xmit_lock);
++ netif_tx_unlock_bh(dev);
+ }
+
+ void netif_carrier_on(struct net_device *dev)
+@@ -577,10 +589,17 @@ void dev_deactivate(struct net_device *d
+
+ dev_watchdog_down(dev);
+
+- while (test_bit(__LINK_STATE_SCHED, &dev->state))
++ /* Wait for outstanding dev_queue_xmit calls. */
++ synchronize_rcu();
++
++ /* Wait for outstanding qdisc_run calls. */
++ while (test_bit(__LINK_STATE_QDISC_RUNNING, &dev->state))
+ yield();
+
+- spin_unlock_wait(&dev->xmit_lock);
++ if (dev->gso_skb) {
++ kfree_skb(dev->gso_skb);
++ dev->gso_skb = NULL;
++ }
+ }
+
+ void dev_init_scheduler(struct net_device *dev)
+@@ -622,6 +641,5 @@ EXPORT_SYMBOL(qdisc_create_dflt);
+ EXPORT_SYMBOL(qdisc_alloc);
+ EXPORT_SYMBOL(qdisc_destroy);
+ EXPORT_SYMBOL(qdisc_reset);
+-EXPORT_SYMBOL(qdisc_restart);
+ EXPORT_SYMBOL(qdisc_lock_tree);
+ EXPORT_SYMBOL(qdisc_unlock_tree);
+diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
+index 79b8ef3..4c16ad5 100644
+--- a/net/sched/sch_teql.c
++++ b/net/sched/sch_teql.c
+@@ -302,20 +302,17 @@ restart:
+
+ switch (teql_resolve(skb, skb_res, slave)) {
+ case 0:
+- if (spin_trylock(&slave->xmit_lock)) {
+- slave->xmit_lock_owner = smp_processor_id();
++ if (netif_tx_trylock(slave)) {
+ if (!netif_queue_stopped(slave) &&
+ slave->hard_start_xmit(skb, slave) == 0) {
+- slave->xmit_lock_owner = -1;
+- spin_unlock(&slave->xmit_lock);
++ netif_tx_unlock(slave);
+ master->slaves = NEXT_SLAVE(q);
+ netif_wake_queue(dev);
+ master->stats.tx_packets++;
+ master->stats.tx_bytes += len;
+ return 0;
+ }
+- slave->xmit_lock_owner = -1;
+- spin_unlock(&slave->xmit_lock);
++ netif_tx_unlock(slave);
+ }
+ if (netif_queue_stopped(dev))
+ busy = 1;
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
Home