From 5a8da02ba59a9f978e2af4c5da9a029ea5f5ee3b Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 7 Jul 2006 16:54:05 -0700 Subject: [PATCH 01/11] [NET]: Fix network device interface printk message priority The printk's in the network device interface code should all be tagged with severity. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/core/dev.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 066a60a75280..0096349ee38b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1727,7 +1727,7 @@ static int ing_filter(struct sk_buff *skb) if (dev->qdisc_ingress) { __u32 ttl = (__u32) G_TC_RTTL(skb->tc_verd); if (MAX_RED_LOOP < ttl++) { - printk("Redir loop detected Dropping packet (%s->%s)\n", + printk(KERN_WARNING "Redir loop detected Dropping packet (%s->%s)\n", skb->input_dev->name, skb->dev->name); return TC_ACT_SHOT; } @@ -2922,7 +2922,7 @@ int register_netdevice(struct net_device *dev) /* Fix illegal SG+CSUM combinations. */ if ((dev->features & NETIF_F_SG) && !(dev->features & NETIF_F_ALL_CSUM)) { - printk("%s: Dropping NETIF_F_SG since no checksum feature.\n", + printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no checksum feature.\n", dev->name); dev->features &= ~NETIF_F_SG; } @@ -2930,7 +2930,7 @@ int register_netdevice(struct net_device *dev) /* TSO requires that SG is present as well. */ if ((dev->features & NETIF_F_TSO) && !(dev->features & NETIF_F_SG)) { - printk("%s: Dropping NETIF_F_TSO since no SG feature.\n", + printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no SG feature.\n", dev->name); dev->features &= ~NETIF_F_TSO; } From c165b0040502ef0d2b5751eef3cd96ea8210ae4c Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Sat, 8 Jul 2006 13:28:53 -0700 Subject: [PATCH 02/11] [TG3]: add amd8131 to "write reorder" chipsets Add the AMD 8131 bridge to the list of chipsets that reorder writes. Signed-off-by: John W. Linville Acked-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index f645921aff8b..ce6f3be86da0 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -10078,6 +10078,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) static struct pci_device_id write_reorder_chipsets[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_FE_GATE_700C) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, + PCI_DEVICE_ID_AMD_8131_BRIDGE) }, { PCI_DEVICE(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8385_0) }, { }, From 00181fc94648b4bb30d30ef95506055105316051 Mon Sep 17 00:00:00 2001 From: Matt LaPlante Date: Sat, 8 Jul 2006 13:30:09 -0700 Subject: [PATCH 03/11] [ATM]: Typo in drivers/atm/Kconfig... From: Matt LaPlante Signed-off-by: Charles Williams Signed-off-by: David S. Miller --- drivers/atm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/atm/Kconfig b/drivers/atm/Kconfig index 01a9f1cb7743..cfa5af883e13 100644 --- a/drivers/atm/Kconfig +++ b/drivers/atm/Kconfig @@ -398,7 +398,7 @@ config ATM_FORE200E_USE_TASKLET default n help This defers work to be done by the interrupt handler to a - tasklet instead of hanlding everything at interrupt time. This + tasklet instead of handling everything at interrupt time. This may improve the responsive of the host. config ATM_FORE200E_TX_RETRY From 1252ecf63f77ea147bd40f5462c7d9e3d3ae2815 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Sat, 8 Jul 2006 13:30:52 -0700 Subject: [PATCH 04/11] [ATM]: fix possible recursive locking in skb_migrate() ok this is a real potential deadlock in a way, it takes two locks of 2 skbuffs without doing any kind of lock ordering; I think the following patch should fix it. Just sort the lock taking order by address of the skb.. it's not pretty but it's the best this can do in a minimally invasive way. Signed-off-by: Arjan van de Ven Signed-off-by: Chas Williams Signed-off-by: David S. Miller --- net/atm/ipcommon.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/net/atm/ipcommon.c b/net/atm/ipcommon.c index 4b1faca5013f..1d3de42fada0 100644 --- a/net/atm/ipcommon.c +++ b/net/atm/ipcommon.c @@ -25,22 +25,27 @@ /* * skb_migrate appends the list at "from" to "to", emptying "from" in the * process. skb_migrate is atomic with respect to all other skb operations on - * "from" and "to". Note that it locks both lists at the same time, so beware - * of potential deadlocks. + * "from" and "to". Note that it locks both lists at the same time, so to deal + * with the lock ordering, the locks are taken in address order. * * This function should live in skbuff.c or skbuff.h. */ -void skb_migrate(struct sk_buff_head *from,struct sk_buff_head *to) +void skb_migrate(struct sk_buff_head *from, struct sk_buff_head *to) { unsigned long flags; struct sk_buff *skb_from = (struct sk_buff *) from; struct sk_buff *skb_to = (struct sk_buff *) to; struct sk_buff *prev; - spin_lock_irqsave(&from->lock,flags); - spin_lock(&to->lock); + if ((unsigned long) from < (unsigned long) to) { + spin_lock_irqsave(&from->lock, flags); + spin_lock_nested(&to->lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock_irqsave(&to->lock, flags); + spin_lock_nested(&from->lock, SINGLE_DEPTH_NESTING); + } prev = from->prev; from->next->prev = to->prev; prev->next = skb_to; @@ -51,7 +56,7 @@ void skb_migrate(struct sk_buff_head *from,struct sk_buff_head *to) from->prev = skb_from; from->next = skb_from; from->qlen = 0; - spin_unlock_irqrestore(&from->lock,flags); + spin_unlock_irqrestore(&from->lock, flags); } From 9c6c6795eda34e4dc38ecac912a16b6314082beb Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sat, 8 Jul 2006 13:33:28 -0700 Subject: [PATCH 05/11] [IRDA]: fix drivers/net/irda/ali-ircc.c:ali_ircc_init() The Coverity checker spotted, that from the changes from commit 898b1d16f8230fb912a0c2248df685735c6ceda3 the if (ret) platform_driver_unregister(&ali_ircc_driver); was dead code. This patch changes this function to what seems to have been the intention. Signed-off-by: Adrian Bunk Signed-off-by: David S. Miller --- drivers/net/irda/ali-ircc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/irda/ali-ircc.c b/drivers/net/irda/ali-ircc.c index bf1fca5a3fa0..e3c8cd5eca67 100644 --- a/drivers/net/irda/ali-ircc.c +++ b/drivers/net/irda/ali-ircc.c @@ -146,7 +146,7 @@ static int __init ali_ircc_init(void) { ali_chip_t *chip; chipio_t info; - int ret = -ENODEV; + int ret; int cfg, cfg_base; int reg, revision; int i = 0; @@ -160,6 +160,7 @@ static int __init ali_ircc_init(void) return ret; } + ret = -ENODEV; /* Probe for all the ALi chipsets we know about */ for (chip= chips; chip->name; chip++, i++) From 89114afd435a486deb8583e89f490fc274444d18 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 8 Jul 2006 13:34:32 -0700 Subject: [PATCH 06/11] [NET] gso: Add skb_is_gso This patch adds the wrapper function skb_is_gso which can be used instead of directly testing skb_shinfo(skb)->gso_size. This makes things a little nicer and allows us to change the primary key for indicating whether an skb is GSO (if we ever want to do that). Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- drivers/net/bnx2.c | 2 +- drivers/net/chelsio/sge.c | 2 +- drivers/net/e1000/e1000_main.c | 7 +++---- drivers/net/forcedeth.c | 2 +- drivers/net/ixgb/ixgb_main.c | 2 +- drivers/net/loopback.c | 2 +- drivers/net/myri10ge/myri10ge.c | 2 +- drivers/net/sky2.c | 2 +- drivers/net/typhoon.c | 4 ++-- drivers/s390/net/qeth_main.c | 2 +- include/linux/netdevice.h | 2 +- include/linux/skbuff.h | 5 +++++ net/bridge/br_forward.c | 2 +- net/bridge/br_netfilter.c | 2 +- net/ipv4/ip_output.c | 4 ++-- net/ipv4/xfrm4_output.c | 2 +- net/ipv6/ip6_output.c | 4 ++-- net/ipv6/xfrm6_output.c | 2 +- 18 files changed, 27 insertions(+), 23 deletions(-) diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 64b6a72b4f6a..db73de0d2511 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -1639,7 +1639,7 @@ bnx2_tx_int(struct bnx2 *bp) skb = tx_buf->skb; #ifdef BCM_TSO /* partial BD completions possible with TSO packets */ - if (skb_shinfo(skb)->gso_size) { + if (skb_is_gso(skb)) { u16 last_idx, last_ring_idx; last_idx = sw_cons + diff --git a/drivers/net/chelsio/sge.c b/drivers/net/chelsio/sge.c index 87f94d939ff8..61b3754f50ff 100644 --- a/drivers/net/chelsio/sge.c +++ b/drivers/net/chelsio/sge.c @@ -1417,7 +1417,7 @@ int t1_start_xmit(struct sk_buff *skb, struct net_device *dev) struct cpl_tx_pkt *cpl; #ifdef NETIF_F_TSO - if (skb_shinfo(skb)->gso_size) { + if (skb_is_gso(skb)) { int eth_type; struct cpl_tx_pkt_lso *hdr; diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index f77624f5f17b..1f34d06d01b0 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -2394,7 +2394,7 @@ e1000_tso(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring, uint8_t ipcss, ipcso, tucss, tucso, hdr_len; int err; - if (skb_shinfo(skb)->gso_size) { + if (skb_is_gso(skb)) { if (skb_header_cloned(skb)) { err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); if (err) @@ -2519,7 +2519,7 @@ e1000_tx_map(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring, * tso gets written back prematurely before the data is fully * DMA'd to the controller */ if (!skb->data_len && tx_ring->last_tx_tso && - !skb_shinfo(skb)->gso_size) { + !skb_is_gso(skb)) { tx_ring->last_tx_tso = 0; size -= 4; } @@ -2806,8 +2806,7 @@ e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev) #ifdef NETIF_F_TSO /* Controller Erratum workaround */ - if (!skb->data_len && tx_ring->last_tx_tso && - !skb_shinfo(skb)->gso_size) + if (!skb->data_len && tx_ring->last_tx_tso && !skb_is_gso(skb)) count++; #endif diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c index 037d870712ff..ad81ec68f887 100644 --- a/drivers/net/forcedeth.c +++ b/drivers/net/forcedeth.c @@ -1495,7 +1495,7 @@ static int nv_start_xmit(struct sk_buff *skb, struct net_device *dev) np->tx_skbuff[nr] = skb; #ifdef NETIF_F_TSO - if (skb_shinfo(skb)->gso_size) + if (skb_is_gso(skb)) tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->gso_size << NV_TX2_TSO_SHIFT); else #endif diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c index b91e082483f6..7eb08d929139 100644 --- a/drivers/net/ixgb/ixgb_main.c +++ b/drivers/net/ixgb/ixgb_main.c @@ -1173,7 +1173,7 @@ ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb) uint16_t ipcse, tucse, mss; int err; - if(likely(skb_shinfo(skb)->gso_size)) { + if (likely(skb_is_gso(skb))) { if (skb_header_cloned(skb)) { err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); if (err) diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 43fef7de8cb9..997cbce9af6e 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -139,7 +139,7 @@ static int loopback_xmit(struct sk_buff *skb, struct net_device *dev) #endif #ifdef LOOPBACK_TSO - if (skb_shinfo(skb)->gso_size) { + if (skb_is_gso(skb)) { BUG_ON(skb->protocol != htons(ETH_P_IP)); BUG_ON(skb->nh.iph->protocol != IPPROTO_TCP); diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index f4c8fd373b9b..ee1de971a712 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -2116,7 +2116,7 @@ abort_linearize: } idx = (idx + 1) & tx->mask; } while (idx != last_idx); - if (skb_shinfo(skb)->gso_size) { + if (skb_is_gso(skb)) { printk(KERN_ERR "myri10ge: %s: TSO but wanted to linearize?!?!?\n", mgp->dev->name); diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c index 418f169a6a31..31093760aa1e 100644 --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -1159,7 +1159,7 @@ static unsigned tx_le_req(const struct sk_buff *skb) count = sizeof(dma_addr_t) / sizeof(u32); count += skb_shinfo(skb)->nr_frags * count; - if (skb_shinfo(skb)->gso_size) + if (skb_is_gso(skb)) ++count; if (skb->ip_summed == CHECKSUM_HW) diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c index 063816f2b11e..4103c37172f9 100644 --- a/drivers/net/typhoon.c +++ b/drivers/net/typhoon.c @@ -805,7 +805,7 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev) * If problems develop with TSO, check this first. */ numDesc = skb_shinfo(skb)->nr_frags + 1; - if(skb_tso_size(skb)) + if (skb_is_gso(skb)) numDesc++; /* When checking for free space in the ring, we need to also @@ -845,7 +845,7 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev) TYPHOON_TX_PF_VLAN_TAG_SHIFT); } - if(skb_tso_size(skb)) { + if (skb_is_gso(skb)) { first_txd->processFlags |= TYPHOON_TX_PF_TCP_SEGMENT; first_txd->numDesc++; diff --git a/drivers/s390/net/qeth_main.c b/drivers/s390/net/qeth_main.c index 8e8963f15731..329e12c1fae4 100644 --- a/drivers/s390/net/qeth_main.c +++ b/drivers/s390/net/qeth_main.c @@ -4457,7 +4457,7 @@ qeth_send_packet(struct qeth_card *card, struct sk_buff *skb) queue = card->qdio.out_qs [qeth_get_priority_queue(card, skb, ipv, cast_type)]; - if (skb_shinfo(skb)->gso_size) + if (skb_is_gso(skb)) large_send = card->options.large_send; /*are we able to do TSO ? If so ,prepare and send it from here */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 85f99f60deea..0359a6430018 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1001,7 +1001,7 @@ static inline int net_gso_ok(int features, int gso_type) static inline int skb_gso_ok(struct sk_buff *skb, int features) { - return net_gso_ok(features, skb_shinfo(skb)->gso_size ? + return net_gso_ok(features, skb_is_gso(skb) ? skb_shinfo(skb)->gso_type : 0); } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3597b4f14389..0bf31b83578c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1455,5 +1455,10 @@ static inline void skb_init_secmark(struct sk_buff *skb) { } #endif +static inline int skb_is_gso(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->gso_size; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 8be9f2123e54..6ccd32b30809 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -35,7 +35,7 @@ static inline unsigned packet_length(const struct sk_buff *skb) int br_dev_queue_push_xmit(struct sk_buff *skb) { /* drop mtu oversized packets except gso */ - if (packet_length(skb) > skb->dev->mtu && !skb_shinfo(skb)->gso_size) + if (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb)) kfree_skb(skb); else { #ifdef CONFIG_BRIDGE_NETFILTER diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 8298a5179aef..cbc8a389a0a8 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -761,7 +761,7 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP) && skb->len > skb->dev->mtu && - !skb_shinfo(skb)->gso_size) + !skb_is_gso(skb)) return ip_fragment(skb, br_dev_queue_push_xmit); else return br_dev_queue_push_xmit(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index ca0e714613fb..7c9f9a6421b8 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -209,7 +209,7 @@ static inline int ip_finish_output(struct sk_buff *skb) return dst_output(skb); } #endif - if (skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size) + if (skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb)) return ip_fragment(skb, ip_finish_output2); else return ip_finish_output2(skb); @@ -1095,7 +1095,7 @@ ssize_t ip_append_page(struct sock *sk, struct page *page, while (size > 0) { int i; - if (skb_shinfo(skb)->gso_size) + if (skb_is_gso(skb)) len = size; else { diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 193363e22932..d16f863cf687 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -134,7 +134,7 @@ static int xfrm4_output_finish(struct sk_buff *skb) } #endif - if (!skb_shinfo(skb)->gso_size) + if (!skb_is_gso(skb)) return xfrm4_output_finish2(skb); skb->protocol = htons(ETH_P_IP); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2c5b44575af0..3bc74ce78800 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -147,7 +147,7 @@ static int ip6_output2(struct sk_buff *skb) int ip6_output(struct sk_buff *skb) { - if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size) || + if ((skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb)) || dst_allfrag(skb->dst)) return ip6_fragment(skb, ip6_output2); else @@ -229,7 +229,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, skb->priority = sk->sk_priority; mtu = dst_mtu(dst); - if ((skb->len <= mtu) || ipfragok || skb_shinfo(skb)->gso_size) { + if ((skb->len <= mtu) || ipfragok || skb_is_gso(skb)) { IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 48fccb1eca08..0eea60ea9ebc 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -122,7 +122,7 @@ static int xfrm6_output_finish(struct sk_buff *skb) { struct sk_buff *segs; - if (!skb_shinfo(skb)->gso_size) + if (!skb_is_gso(skb)) return xfrm6_output_finish2(skb); skb->protocol = htons(ETH_P_IP); From a430a43d087545c96542ee64573237919109d370 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 8 Jul 2006 13:34:56 -0700 Subject: [PATCH 07/11] [NET] gso: Fix up GSO packets with broken checksums Certain subsystems in the stack (e.g., netfilter) can break the partial checksum on GSO packets. Until they're fixed, this patch allows this to work by recomputing the partial checksums through the GSO mechanism. Once they've all been converted to update the partial checksum instead of clearing it, this workaround can be removed. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++-- include/net/protocol.h | 2 + include/net/tcp.h | 1 + net/core/dev.c | 36 ++++++++++++-- net/ipv4/af_inet.c | 36 ++++++++++++++ net/ipv4/tcp_ipv4.c | 18 +++++++ net/ipv6/ipv6_sockglue.c | 99 ++++++++++++++++++++++++++------------- net/ipv6/tcp_ipv6.c | 19 ++++++++ 8 files changed, 179 insertions(+), 40 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0359a6430018..76cc099c8580 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -549,6 +549,7 @@ struct packet_type { struct net_device *); struct sk_buff *(*gso_segment)(struct sk_buff *skb, int features); + int (*gso_send_check)(struct sk_buff *skb); void *af_packet_priv; struct list_head list; }; @@ -1001,13 +1002,14 @@ static inline int net_gso_ok(int features, int gso_type) static inline int skb_gso_ok(struct sk_buff *skb, int features) { - return net_gso_ok(features, skb_is_gso(skb) ? - skb_shinfo(skb)->gso_type : 0); + return net_gso_ok(features, skb_shinfo(skb)->gso_type); } static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb) { - return !skb_gso_ok(skb, dev->features); + return skb_is_gso(skb) && + (!skb_gso_ok(skb, dev->features) || + unlikely(skb->ip_summed != CHECKSUM_HW)); } #endif /* __KERNEL__ */ diff --git a/include/net/protocol.h b/include/net/protocol.h index a225d6371cb1..c643bce64e55 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -36,6 +36,7 @@ struct net_protocol { int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); + int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, int features); int no_policy; @@ -51,6 +52,7 @@ struct inet6_protocol int type, int code, int offset, __u32 info); + int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, int features); diff --git a/include/net/tcp.h b/include/net/tcp.h index 3cd803b0d7a5..0720bddff1e9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1086,6 +1086,7 @@ extern struct request_sock_ops tcp_request_sock_ops; extern int tcp_v4_destroy_sock(struct sock *sk); +extern int tcp_v4_gso_send_check(struct sk_buff *skb); extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features); #ifdef CONFIG_PROC_FS diff --git a/net/core/dev.c b/net/core/dev.c index 0096349ee38b..4d2b5167d7f5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1162,9 +1162,17 @@ int skb_checksum_help(struct sk_buff *skb, int inward) unsigned int csum; int ret = 0, offset = skb->h.raw - skb->data; - if (inward) { - skb->ip_summed = CHECKSUM_NONE; - goto out; + if (inward) + goto out_set_summed; + + if (unlikely(skb_shinfo(skb)->gso_size)) { + static int warned; + + WARN_ON(!warned); + warned = 1; + + /* Let GSO fix up the checksum. */ + goto out_set_summed; } if (skb_cloned(skb)) { @@ -1181,6 +1189,8 @@ int skb_checksum_help(struct sk_buff *skb, int inward) BUG_ON(skb->csum + 2 > offset); *(u16*)(skb->h.raw + skb->csum) = csum_fold(csum); + +out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: return ret; @@ -1201,17 +1211,35 @@ 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; + int err; 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); + if (unlikely(skb->ip_summed != CHECKSUM_HW)) { + static int warned; + + WARN_ON(!warned); + warned = 1; + + if (skb_header_cloned(skb) && + (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + return ERR_PTR(err); + } + rcu_read_lock(); list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) { if (ptype->type == type && !ptype->dev && ptype->gso_segment) { + if (unlikely(skb->ip_summed != CHECKSUM_HW)) { + err = ptype->gso_send_check(skb); + segs = ERR_PTR(err); + if (err || skb_gso_ok(skb, features)) + break; + __skb_push(skb, skb->data - skb->nh.raw); + } segs = ptype->gso_segment(skb, features); break; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 318d4674faa1..c84a32070f8d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1097,6 +1097,40 @@ int inet_sk_rebuild_header(struct sock *sk) EXPORT_SYMBOL(inet_sk_rebuild_header); +static int inet_gso_send_check(struct sk_buff *skb) +{ + struct iphdr *iph; + struct net_protocol *ops; + int proto; + int ihl; + int err = -EINVAL; + + if (unlikely(!pskb_may_pull(skb, sizeof(*iph)))) + goto out; + + iph = skb->nh.iph; + ihl = iph->ihl * 4; + if (ihl < sizeof(*iph)) + goto out; + + if (unlikely(!pskb_may_pull(skb, ihl))) + goto out; + + skb->h.raw = __skb_pull(skb, ihl); + iph = skb->nh.iph; + proto = iph->protocol & (MAX_INET_PROTOS - 1); + err = -EPROTONOSUPPORT; + + rcu_read_lock(); + ops = rcu_dereference(inet_protos[proto]); + if (likely(ops && ops->gso_send_check)) + err = ops->gso_send_check(skb); + rcu_read_unlock(); + +out: + return err; +} + static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features) { struct sk_buff *segs = ERR_PTR(-EINVAL); @@ -1162,6 +1196,7 @@ static struct net_protocol igmp_protocol = { static struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, + .gso_send_check = tcp_v4_gso_send_check, .gso_segment = tcp_tso_segment, .no_policy = 1, }; @@ -1208,6 +1243,7 @@ static int ipv4_proc_init(void); static struct packet_type ip_packet_type = { .type = __constant_htons(ETH_P_IP), .func = ip_rcv, + .gso_send_check = inet_gso_send_check, .gso_segment = inet_gso_segment, }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5a886e6efbbe..a891133f00e4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -496,6 +496,24 @@ void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) } } +int tcp_v4_gso_send_check(struct sk_buff *skb) +{ + struct iphdr *iph; + struct tcphdr *th; + + if (!pskb_may_pull(skb, sizeof(*th))) + return -EINVAL; + + iph = skb->nh.iph; + th = skb->h.th; + + th->check = 0; + th->check = ~tcp_v4_check(th, skb->len, iph->saddr, iph->daddr, 0); + skb->csum = offsetof(struct tcphdr, check); + skb->ip_summed = CHECKSUM_HW; + return 0; +} + /* * This routine will send an RST to the other tcp. * diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 0c17dec11c8d..43327264e69c 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -57,12 +57,71 @@ DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics) __read_mostly; +static struct inet6_protocol *ipv6_gso_pull_exthdrs(struct sk_buff *skb, + int proto) +{ + struct inet6_protocol *ops = NULL; + + for (;;) { + struct ipv6_opt_hdr *opth; + int len; + + if (proto != NEXTHDR_HOP) { + ops = rcu_dereference(inet6_protos[proto]); + + if (unlikely(!ops)) + break; + + if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) + break; + } + + if (unlikely(!pskb_may_pull(skb, 8))) + break; + + opth = (void *)skb->data; + len = opth->hdrlen * 8 + 8; + + if (unlikely(!pskb_may_pull(skb, len))) + break; + + proto = opth->nexthdr; + __skb_pull(skb, len); + } + + return ops; +} + +static int ipv6_gso_send_check(struct sk_buff *skb) +{ + struct ipv6hdr *ipv6h; + struct inet6_protocol *ops; + int err = -EINVAL; + + if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) + goto out; + + ipv6h = skb->nh.ipv6h; + __skb_pull(skb, sizeof(*ipv6h)); + err = -EPROTONOSUPPORT; + + rcu_read_lock(); + ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); + if (likely(ops && ops->gso_send_check)) { + skb->h.raw = skb->data; + err = ops->gso_send_check(skb); + } + rcu_read_unlock(); + +out: + return err; +} + static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; struct inet6_protocol *ops; - int proto; if (unlikely(skb_shinfo(skb)->gso_type & ~(SKB_GSO_UDP | @@ -76,42 +135,15 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) goto out; ipv6h = skb->nh.ipv6h; - proto = ipv6h->nexthdr; __skb_pull(skb, sizeof(*ipv6h)); + segs = ERR_PTR(-EPROTONOSUPPORT); rcu_read_lock(); - for (;;) { - struct ipv6_opt_hdr *opth; - int len; - - if (proto != NEXTHDR_HOP) { - ops = rcu_dereference(inet6_protos[proto]); - - if (unlikely(!ops)) - goto unlock; - - if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) - break; - } - - if (unlikely(!pskb_may_pull(skb, 8))) - goto unlock; - - opth = (void *)skb->data; - len = opth->hdrlen * 8 + 8; - - if (unlikely(!pskb_may_pull(skb, len))) - goto unlock; - - proto = opth->nexthdr; - __skb_pull(skb, len); - } - - skb->h.raw = skb->data; - if (likely(ops->gso_segment)) + ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); + if (likely(ops && ops->gso_segment)) { + skb->h.raw = skb->data; segs = ops->gso_segment(skb, features); - -unlock: + } rcu_read_unlock(); if (unlikely(IS_ERR(segs))) @@ -130,6 +162,7 @@ out: static struct packet_type ipv6_packet_type = { .type = __constant_htons(ETH_P_IPV6), .func = ipv6_rcv, + .gso_send_check = ipv6_gso_send_check, .gso_segment = ipv6_gso_segment, }; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5bdcb9002cf7..923989d0520d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -552,6 +552,24 @@ static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) } } +static int tcp_v6_gso_send_check(struct sk_buff *skb) +{ + struct ipv6hdr *ipv6h; + struct tcphdr *th; + + if (!pskb_may_pull(skb, sizeof(*th))) + return -EINVAL; + + ipv6h = skb->nh.ipv6h; + th = skb->h.th; + + th->check = 0; + th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, + IPPROTO_TCP, 0); + skb->csum = offsetof(struct tcphdr, check); + skb->ip_summed = CHECKSUM_HW; + return 0; +} static void tcp_v6_send_reset(struct sk_buff *skb) { @@ -1603,6 +1621,7 @@ struct proto tcpv6_prot = { static struct inet6_protocol tcpv6_protocol = { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, + .gso_send_check = tcp_v6_gso_send_check, .gso_segment = tcp_tso_segment, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; From 26e0fd1ce2418b10713b569a195bdb679233066b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 8 Jul 2006 13:38:55 -0700 Subject: [PATCH 08/11] [NET]: Fix IPv4/DECnet routing rule dumping When more rules are present than fit in a single skb, the remaining rules are incorrectly skipped. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/decnet/dn_rules.c | 3 ++- net/ipv4/fib_rules.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 06e785fe5757..22f321d9bf9d 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -399,9 +399,10 @@ int dn_fib_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); hlist_for_each_entry(r, node, &dn_fib_rules, r_hlist) { if (idx < s_idx) - continue; + goto next; if (dn_fib_fill_rule(skb, r, cb, NLM_F_MULTI) < 0) break; +next: idx++; } rcu_read_unlock(); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 6c642d11d4ca..773b12ba4e3c 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -457,13 +457,13 @@ int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); hlist_for_each_entry(r, node, &fib_rules, hlist) { - if (idx < s_idx) - continue; + goto next; if (inet_fill_rule(skb, r, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWRULE, NLM_F_MULTI) < 0) break; +next: idx++; } rcu_read_unlock(); From ebbaeab18b1c520054ea70e512ac0db7456ede01 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Sun, 9 Jul 2006 11:36:23 -0700 Subject: [PATCH 09/11] [PKT_SCHED]: act_api: Fix module leak while flushing actions Module reference needs to be given back if message header construction fails. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/sched/act_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 599423cc9d0d..0972247a839c 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -602,8 +602,8 @@ static int tca_action_flush(struct rtattr *rta, struct nlmsghdr *n, u32 pid) return err; rtattr_failure: - module_put(a->ops->owner); nlmsg_failure: + module_put(a->ops->owner); err_out: kfree_skb(skb); kfree(a); From 24781734643ea2e9fd864f58000e47793e2dcb04 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 9 Jul 2006 12:13:18 -0700 Subject: [PATCH 10/11] [ATM] net/atm/clip.c: fix PROC_FS=n compile MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixes the following compile error with CONFIG_PROC_FS=n by reverting commit dcdb02752ff13a64433c36f2937a58d93ae7a19e: <-- snip --> ... CC net/atm/clip.o net/atm/clip.c: In function ‘atm_clip_init’: net/atm/clip.c:975: error: ‘atm_proc_root’ undeclared (first use in this function) net/atm/clip.c:975: error: (Each undeclared identifier is reported only once net/atm/clip.c:975: error: for each function it appears in.) net/atm/clip.c:977: error: ‘arp_seq_fops’ undeclared (first use in this function) make[2]: *** [net/atm/clip.o] Error 1 <-- snip --> Signed-off-by: Adrian Bunk Signed-off-by: David S. Miller --- net/atm/clip.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/net/atm/clip.c b/net/atm/clip.c index 121bf6f49148..2e62105d91bd 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -962,7 +962,6 @@ static struct file_operations arp_seq_fops = { static int __init atm_clip_init(void) { - struct proc_dir_entry *p; neigh_table_init_no_netlink(&clip_tbl); clip_tbl_hook = &clip_tbl; @@ -972,9 +971,15 @@ static int __init atm_clip_init(void) setup_timer(&idle_timer, idle_timer_check, 0); - p = create_proc_entry("arp", S_IRUGO, atm_proc_root); - if (p) - p->proc_fops = &arp_seq_fops; +#ifdef CONFIG_PROC_FS + { + struct proc_dir_entry *p; + + p = create_proc_entry("arp", S_IRUGO, atm_proc_root); + if (p) + p->proc_fops = &arp_seq_fops; + } +#endif return 0; } From 1b30dd359ebec22d035e8b145751319f63772ca1 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Sun, 9 Jul 2006 12:14:22 -0700 Subject: [PATCH 11/11] [AX.25]: Use kzalloc Replace kzalloc instead of kmalloc + memset. Signed-off-by: Ralf Baechle Signed-off-by: David S. Miller --- net/ax25/af_ax25.c | 3 +-- net/ax25/ax25_dev.c | 4 +--- net/netrom/af_netrom.c | 4 +--- net/rose/af_rose.c | 3 +-- 4 files changed, 4 insertions(+), 10 deletions(-) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 10a3c0aa8398..f12be2acf9bc 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -486,10 +486,9 @@ ax25_cb *ax25_create_cb(void) { ax25_cb *ax25; - if ((ax25 = kmalloc(sizeof(*ax25), GFP_ATOMIC)) == NULL) + if ((ax25 = kzalloc(sizeof(*ax25), GFP_ATOMIC)) == NULL) return NULL; - memset(ax25, 0x00, sizeof(*ax25)); atomic_set(&ax25->refcount, 1); skb_queue_head_init(&ax25->write_queue); diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index 47e6e790bd67..b787678220ff 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -55,15 +55,13 @@ void ax25_dev_device_up(struct net_device *dev) { ax25_dev *ax25_dev; - if ((ax25_dev = kmalloc(sizeof(*ax25_dev), GFP_ATOMIC)) == NULL) { + if ((ax25_dev = kzalloc(sizeof(*ax25_dev), GFP_ATOMIC)) == NULL) { printk(KERN_ERR "AX.25: ax25_dev_device_up - out of memory\n"); return; } ax25_unregister_sysctl(); - memset(ax25_dev, 0x00, sizeof(*ax25_dev)); - dev->ax25_ptr = ax25_dev; ax25_dev->dev = dev; dev_hold(dev); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 389a4119e1b4..ecc796878f38 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1382,14 +1382,12 @@ static int __init nr_proto_init(void) return -1; } - dev_nr = kmalloc(nr_ndevs * sizeof(struct net_device *), GFP_KERNEL); + dev_nr = kzalloc(nr_ndevs * sizeof(struct net_device *), GFP_KERNEL); if (dev_nr == NULL) { printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device array\n"); return -1; } - memset(dev_nr, 0x00, nr_ndevs * sizeof(struct net_device *)); - for (i = 0; i < nr_ndevs; i++) { char name[IFNAMSIZ]; struct net_device *dev; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index d0a67bb31363..c115295ab431 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1490,14 +1490,13 @@ static int __init rose_proto_init(void) rose_callsign = null_ax25_address; - dev_rose = kmalloc(rose_ndevs * sizeof(struct net_device *), GFP_KERNEL); + dev_rose = kzalloc(rose_ndevs * sizeof(struct net_device *), GFP_KERNEL); if (dev_rose == NULL) { printk(KERN_ERR "ROSE: rose_proto_init - unable to allocate device structure\n"); rc = -ENOMEM; goto out_proto_unregister; } - memset(dev_rose, 0x00, rose_ndevs * sizeof(struct net_device*)); for (i = 0; i < rose_ndevs; i++) { struct net_device *dev; char name[IFNAMSIZ];