From 7a67e56fd362d3edfde1f19170893508c3940d3a Mon Sep 17 00:00:00 2001 From: Jarek Poplawski Date: Thu, 30 Apr 2009 05:41:19 -0700 Subject: net: Fix oops when splicing skbs from a frag_list. Lennert Buytenhek wrote: > Since 4fb669948116d928ae44262ab7743732c574630d ("net: Optimize memory > usage when splicing from sockets.") I'm seeing this oops (e.g. in > 2.6.30-rc3) when splicing from a TCP socket to /dev/null on a driver > (mv643xx_eth) that uses LRO in the skb mode (lro_receive_skb) rather > than the frag mode: My patch incorrectly assumed skb->sk was always valid, but for "frag_listed" skbs we can only use skb->sk of their parent. Reported-by: Lennert Buytenhek Debugged-by: Lennert Buytenhek Tested-by: Lennert Buytenhek Signed-off-by: Jarek Poplawski Signed-off-by: David S. Miller --- net/core/skbuff.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ce6356c..f091a5a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1365,9 +1365,8 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) static inline struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, - struct sk_buff *skb) + struct sk_buff *skb, struct sock *sk) { - struct sock *sk = skb->sk; struct page *p = sk->sk_sndmsg_page; unsigned int off; @@ -1405,13 +1404,14 @@ new_page: */ static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page, unsigned int *len, unsigned int offset, - struct sk_buff *skb, int linear) + struct sk_buff *skb, int linear, + struct sock *sk) { if (unlikely(spd->nr_pages == PIPE_BUFFERS)) return 1; if (linear) { - page = linear_to_page(page, len, &offset, skb); + page = linear_to_page(page, len, &offset, skb, sk); if (!page) return 1; } else @@ -1442,7 +1442,8 @@ static inline void __segment_seek(struct page **page, unsigned int *poff, static inline int __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, unsigned int *len, struct sk_buff *skb, - struct splice_pipe_desc *spd, int linear) + struct splice_pipe_desc *spd, int linear, + struct sock *sk) { if (!*len) return 1; @@ -1465,7 +1466,7 @@ static inline int __splice_segment(struct page *page, unsigned int poff, /* the linear region may spread across several pages */ flen = min_t(unsigned int, flen, PAGE_SIZE - poff); - if (spd_fill_page(spd, page, &flen, poff, skb, linear)) + if (spd_fill_page(spd, page, &flen, poff, skb, linear, sk)) return 1; __segment_seek(&page, &poff, &plen, flen); @@ -1481,8 +1482,8 @@ static inline int __splice_segment(struct page *page, unsigned int poff, * pipe is full or if we already spliced the requested length. */ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, - unsigned int *len, - struct splice_pipe_desc *spd) + unsigned int *len, struct splice_pipe_desc *spd, + struct sock *sk) { int seg; @@ -1492,7 +1493,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd, 1)) + offset, len, skb, spd, 1, sk)) return 1; /* @@ -1502,7 +1503,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; if (__splice_segment(f->page, f->page_offset, f->size, - offset, len, skb, spd, 0)) + offset, len, skb, spd, 0, sk)) return 1; } @@ -1528,12 +1529,13 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, .ops = &sock_pipe_buf_ops, .spd_release = sock_spd_release, }; + struct sock *sk = skb->sk; /* * __skb_splice_bits() only fails if the output has no room left, * so no point in going over the frag_list for the error case. */ - if (__skb_splice_bits(skb, &offset, &tlen, &spd)) + if (__skb_splice_bits(skb, &offset, &tlen, &spd, sk)) goto done; else if (!tlen) goto done; @@ -1545,14 +1547,13 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct sk_buff *list = skb_shinfo(skb)->frag_list; for (; list && tlen; list = list->next) { - if (__skb_splice_bits(list, &offset, &tlen, &spd)) + if (__skb_splice_bits(list, &offset, &tlen, &spd, sk)) break; } } done: if (spd.nr_pages) { - struct sock *sk = skb->sk; int ret; /* -- cgit v1.1 From ec581f6a42bbbea5271c66da9769a41b46c74e10 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 1 May 2009 09:05:06 -0700 Subject: net: Fix skb_tx_hash() for forwarding workloads. When skb_rx_queue_recorded() is true, we dont want to use jash distribution as the device driver exactly told us which queue was selected at RX time. jhash makes a statistical shuffle, but this wont work with 8 static inputs. Later improvements would be to compute reciprocal value of real_num_tx_queues to avoid a divide here. But this computation should be done once, when real_num_tx_queues is set. This needs a separate patch, and a new field in struct net_device. Reported-by: Andrew Dickinson Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index 308a7d0..e2e9e4a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1735,11 +1735,12 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) { u32 hash; - if (skb_rx_queue_recorded(skb)) { - hash = skb_get_rx_queue(skb); - } else if (skb->sk && skb->sk->sk_hash) { + if (skb_rx_queue_recorded(skb)) + return skb_get_rx_queue(skb) % dev->real_num_tx_queues; + + if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; - } else + else hash = skb->protocol; hash = jhash_1word(hash, skb_tx_hashrnd); -- cgit v1.1 From acda074390270ca9e28f2a9729f7b835e2ad6da4 Mon Sep 17 00:00:00 2001 From: Laszlo Attila Toth Date: Fri, 1 May 2009 15:23:10 -0700 Subject: xt_socket: checks for the state of nf_conntrack xt_socket can use connection tracking, and checks whether it is a module. Signed-off-by: Laszlo Attila Toth Signed-off-by: David S. Miller --- net/netfilter/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 881203c..cb3ad74 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -837,6 +837,7 @@ config NETFILTER_XT_MATCH_SOCKET depends on NETFILTER_TPROXY depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED + depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DEFRAG_IPV4 help This option adds a `socket' match, which can be used to match -- cgit v1.1