summaryrefslogtreecommitdiff
path: root/net/core/sock.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-10-08 21:40:54 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2014-10-08 21:40:54 -0400
commit35a9ad8af0bb0fa3525e6d0d20e32551d226f38e (patch)
tree15b4b33206818886d9cff371fd2163e073b70568 /net/core/sock.c
parentd5935b07da53f74726e2a65dd4281d0f2c70e5d4 (diff)
parent64b1f00a0830e1c53874067273a096b228d83d36 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Most notable changes in here: 1) By far the biggest accomplishment, thanks to a large range of contributors, is the addition of multi-send for transmit. This is the result of discussions back in Chicago, and the hard work of several individuals. Now, when the ->ndo_start_xmit() method of a driver sees skb->xmit_more as true, it can choose to defer the doorbell telling the driver to start processing the new TX queue entires. skb->xmit_more means that the generic networking is guaranteed to call the driver immediately with another SKB to send. There is logic added to the qdisc layer to dequeue multiple packets at a time, and the handling mis-predicted offloads in software is now done with no locks held. Finally, pktgen is extended to have a "burst" parameter that can be used to test a multi-send implementation. Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4, virtio_net Adding support is almost trivial, so export more drivers to support this optimization soon. I want to thank, in no particular or implied order, Jesper Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann, David Tat, Hannes Frederic Sowa, and Rusty Russell. 2) PTP and timestamping support in bnx2x, from Michal Kalderon. 3) Allow adjusting the rx_copybreak threshold for a driver via ethtool, and add rx_copybreak support to enic driver. From Govindarajulu Varadarajan. 4) Significant enhancements to the generic PHY layer and the bcm7xxx driver in particular (EEE support, auto power down, etc.) from Florian Fainelli. 5) Allow raw buffers to be used for flow dissection, allowing drivers to determine the optimal "linear pull" size for devices that DMA into pools of pages. The objective is to get exactly the necessary amount of headers into the linear SKB area pre-pulled, but no more. The new interface drivers use is eth_get_headlen(). From WANG Cong, with driver conversions (several had their own by-hand duplicated implementations) by Alexander Duyck and Eric Dumazet. 6) Support checksumming more smoothly and efficiently for encapsulations, and add "foo over UDP" facility. From Tom Herbert. 7) Add Broadcom SF2 switch driver to DSA layer, from Florian Fainelli. 8) eBPF now can load programs via a system call and has an extensive testsuite. Alexei Starovoitov and Daniel Borkmann. 9) Major overhaul of the packet scheduler to use RCU in several major areas such as the classifiers and rate estimators. From John Fastabend. 10) Add driver for Intel FM10000 Ethernet Switch, from Alexander Duyck. 11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric Dumazet. 12) Add Datacenter TCP congestion control algorithm support, From Florian Westphal. 13) Reorganize sk_buff so that __copy_skb_header() is significantly faster. From Eric Dumazet" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits) netlabel: directly return netlbl_unlabel_genl_init() net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers net: description of dma_cookie cause make xmldocs warning cxgb4: clean up a type issue cxgb4: potential shift wrapping bug i40e: skb->xmit_more support net: fs_enet: Add NAPI TX net: fs_enet: Remove non NAPI RX r8169:add support for RTL8168EP net_sched: copy exts->type in tcf_exts_change() wimax: convert printk to pr_foo() af_unix: remove 0 assignment on static ipv6: Do not warn for informational ICMP messages, regardless of type. Update Intel Ethernet Driver maintainers list bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING tipc: fix bug in multicast congestion handling net: better IFF_XMIT_DST_RELEASE support net/mlx4_en: remove NETDEV_TX_BUSY 3c59x: fix bad split of cpu_to_le32(pci_map_single()) net: bcmgenet: fix Tx ring priority programming ...
Diffstat (limited to 'net/core/sock.c')
-rw-r--r--net/core/sock.c110
1 files changed, 25 insertions, 85 deletions
diff --git a/net/core/sock.c b/net/core/sock.c
index 611f424fb76b..b4f3ea2fce60 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -437,7 +437,6 @@ static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int err;
- int skb_len;
unsigned long flags;
struct sk_buff_head *list = &sk->sk_receive_queue;
@@ -459,13 +458,6 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
skb->dev = NULL;
skb_set_owner_r(skb, sk);
- /* Cache the SKB length before we tack it onto the receive
- * queue. Once it is added it no longer belongs to us and
- * may be freed by other threads of control pulling packets
- * from the queue.
- */
- skb_len = skb->len;
-
/* we escape from rcu protected region, make sure we dont leak
* a norefcounted dst
*/
@@ -1642,18 +1634,24 @@ void sock_rfree(struct sk_buff *skb)
}
EXPORT_SYMBOL(sock_rfree);
+void sock_efree(struct sk_buff *skb)
+{
+ sock_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_efree);
+
+#ifdef CONFIG_INET
void sock_edemux(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
-#ifdef CONFIG_INET
if (sk->sk_state == TCP_TIME_WAIT)
inet_twsk_put(inet_twsk(sk));
else
-#endif
sock_put(sk);
}
EXPORT_SYMBOL(sock_edemux);
+#endif
kuid_t sock_i_uid(struct sock *sk)
{
@@ -1761,21 +1759,12 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
unsigned long data_len, int noblock,
int *errcode, int max_page_order)
{
- struct sk_buff *skb = NULL;
- unsigned long chunk;
- gfp_t gfp_mask;
+ struct sk_buff *skb;
long timeo;
int err;
- int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
- struct page *page;
- int i;
-
- err = -EMSGSIZE;
- if (npages > MAX_SKB_FRAGS)
- goto failure;
timeo = sock_sndtimeo(sk, noblock);
- while (!skb) {
+ for (;;) {
err = sock_error(sk);
if (err != 0)
goto failure;
@@ -1784,66 +1773,27 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
if (sk->sk_shutdown & SEND_SHUTDOWN)
goto failure;
- if (atomic_read(&sk->sk_wmem_alloc) >= sk->sk_sndbuf) {
- set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
- err = -EAGAIN;
- if (!timeo)
- goto failure;
- if (signal_pending(current))
- goto interrupted;
- timeo = sock_wait_for_wmem(sk, timeo);
- continue;
- }
-
- err = -ENOBUFS;
- gfp_mask = sk->sk_allocation;
- if (gfp_mask & __GFP_WAIT)
- gfp_mask |= __GFP_REPEAT;
+ if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
+ break;
- skb = alloc_skb(header_len, gfp_mask);
- if (!skb)
+ set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ err = -EAGAIN;
+ if (!timeo)
goto failure;
-
- skb->truesize += data_len;
-
- for (i = 0; npages > 0; i++) {
- int order = max_page_order;
-
- while (order) {
- if (npages >= 1 << order) {
- page = alloc_pages(sk->sk_allocation |
- __GFP_COMP |
- __GFP_NOWARN |
- __GFP_NORETRY,
- order);
- if (page)
- goto fill_page;
- /* Do not retry other high order allocations */
- order = 1;
- max_page_order = 0;
- }
- order--;
- }
- page = alloc_page(sk->sk_allocation);
- if (!page)
- goto failure;
-fill_page:
- chunk = min_t(unsigned long, data_len,
- PAGE_SIZE << order);
- skb_fill_page_desc(skb, i, page, 0, chunk);
- data_len -= chunk;
- npages -= 1 << order;
- }
+ if (signal_pending(current))
+ goto interrupted;
+ timeo = sock_wait_for_wmem(sk, timeo);
}
-
- skb_set_owner_w(skb, sk);
+ skb = alloc_skb_with_frags(header_len, data_len, max_page_order,
+ errcode, sk->sk_allocation);
+ if (skb)
+ skb_set_owner_w(skb, sk);
return skb;
interrupted:
err = sock_intr_errno(timeo);
failure:
- kfree_skb(skb);
*errcode = err;
return NULL;
}
@@ -2492,11 +2442,11 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
int level, int type)
{
struct sock_exterr_skb *serr;
- struct sk_buff *skb, *skb2;
+ struct sk_buff *skb;
int copied, err;
err = -EAGAIN;
- skb = skb_dequeue(&sk->sk_error_queue);
+ skb = sock_dequeue_err_skb(sk);
if (skb == NULL)
goto out;
@@ -2517,16 +2467,6 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
msg->msg_flags |= MSG_ERRQUEUE;
err = copied;
- /* Reset and regenerate socket error */
- spin_lock_bh(&sk->sk_error_queue.lock);
- sk->sk_err = 0;
- if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
- sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
- spin_unlock_bh(&sk->sk_error_queue.lock);
- sk->sk_error_report(sk);
- } else
- spin_unlock_bh(&sk->sk_error_queue.lock);
-
out_free_skb:
kfree_skb(skb);
out: