aboutsummaryrefslogtreecommitdiff
path: root/net/core/dev.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/dev.c')
-rw-r--r--net/core/dev.c170
1 files changed, 151 insertions, 19 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index ab39fe17cb5..066a60a7528 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -76,7 +76,6 @@
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/capability.h>
-#include <linux/config.h>
#include <linux/cpu.h>
#include <linux/types.h>
#include <linux/kernel.h>
@@ -116,6 +115,7 @@
#include <asm/current.h>
#include <linux/audit.h>
#include <linux/dmaengine.h>
+#include <linux/err.h>
/*
* The list of packet types we will receive (as opposed to discard)
@@ -229,7 +229,7 @@ extern void netdev_unregister_sysfs(struct net_device *);
* For efficiency
*/
-int netdev_nit;
+static int netdev_nit;
/*
* Add a protocol ID to the list. Now that the input handler is
@@ -1048,7 +1048,7 @@ static inline void net_timestamp(struct sk_buff *skb)
* 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;
@@ -1186,6 +1186,45 @@ out:
return ret;
}
+/**
+ * skb_gso_segment - Perform segmentation on skb.
+ * @skb: buffer to segment
+ * @features: features for the output path (see dev->features)
+ *
+ * This function segments the given skb and returns a list of segments.
+ *
+ * It may return NULL if the skb requires no segmentation. This is
+ * only possible when GSO is used for verifying header integrity.
+ */
+struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features)
+{
+ 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, features);
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ __skb_push(skb, skb->data - skb->mac.raw);
+
+ 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)
@@ -1199,7 +1238,6 @@ void netdev_rx_csum_fault(struct net_device *dev)
EXPORT_SYMBOL(netdev_rx_csum_fault);
#endif
-#ifdef CONFIG_HIGHMEM
/* Actually, we should eliminate this check as soon as we know, that:
* 1. IOMMU is present and allows to map all the memory.
* 2. No high memory really exists on this machine.
@@ -1207,6 +1245,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault);
static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
{
+#ifdef CONFIG_HIGHMEM
int i;
if (dev->features & NETIF_F_HIGHDMA)
@@ -1216,11 +1255,102 @@ static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
if (PageHighMem(skb_shinfo(skb)->frags[i].page))
return 1;
+#endif
+ return 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;
+ int features = dev->features & ~(illegal_highdma(dev, skb) ?
+ NETIF_F_SG : 0);
+
+ segs = skb_gso_segment(skb, features);
+
+ /* Verifying header integrity only. */
+ if (!segs)
+ return 0;
+
+ 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)) {
+ if (unlikely(dev_gso_segment(skb)))
+ goto out_kfree_skb;
+ if (skb->next)
+ goto gso;
+ }
+
+ return dev->hard_start_xmit(skb, dev);
+ }
+
+gso:
+ 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;
}
-#else
-#define illegal_highdma(dev, skb) (0)
-#endif
#define HARD_TX_LOCK(dev, cpu) { \
if ((dev->features & NETIF_F_LLTX) == 0) { \
@@ -1266,6 +1396,10 @@ int dev_queue_xmit(struct sk_buff *skb)
struct Qdisc *q;
int rc = -ENOMEM;
+ /* 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))
@@ -1290,12 +1424,13 @@ int dev_queue_xmit(struct sk_buff *skb)
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
@@ -1346,11 +1481,8 @@ 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;
}
@@ -1369,13 +1501,13 @@ 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;
}
@@ -2980,7 +3112,7 @@ static void netdev_wait_allrefs(struct net_device *dev)
static DEFINE_MUTEX(net_todo_run_mutex);
void netdev_run_todo(void)
{
- struct list_head list = LIST_HEAD_INIT(list);
+ struct list_head list;
/* Need to guard against multiple cpu's getting out of order. */
mutex_lock(&net_todo_run_mutex);
@@ -2995,9 +3127,9 @@ void netdev_run_todo(void)
/* Snapshot list, allow later requests */
spin_lock(&net_todo_list_lock);
- list_splice_init(&net_todo_list, &list);
+ list_replace_init(&net_todo_list, &list);
spin_unlock(&net_todo_list_lock);
-
+
while (!list_empty(&list)) {
struct net_device *dev
= list_entry(list.next, struct net_device, todo_list);
@@ -3301,8 +3433,8 @@ static void net_dma_rebalance(void)
/**
* netdev_dma_event - event callback for the net_dma_client
* @client: should always be net_dma_client
- * @chan:
- * @event:
+ * @chan: DMA channel for the event
+ * @event: event type
*/
static void netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
enum dma_event event)
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2025-01-03 16:42:34 +0000