From b634f87522dff87712df8bda2a6c9061954d552a Mon Sep 17 00:00:00 2001 From: Alexandra Kossovsky Date: Thu, 18 Mar 2010 20:29:24 -0700 Subject: tcp: Fix OOB POLLIN avoidance. From: Alexandra.Kossovsky@oktetlabs.ru Fixes kernel bugzilla #15541 Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5901010fad55..ae16f809e716 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -429,7 +429,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tp->urg_seq == tp->copied_seq && !sock_flag(sk, SOCK_URGINLINE) && tp->urg_data) - target--; + target++; /* Potential race condition. If read of tp below will * escape above sk->sk_state, we can be illegally awaken -- cgit v1.2.2 From 73852e8151b7d7a529fbe019ab6d2d0c02d8f3f2 Mon Sep 17 00:00:00 2001 From: "Steven J. Magnani" Date: Tue, 16 Mar 2010 05:22:44 +0000 Subject: NET_DMA: free skbs periodically Under NET_DMA, data transfer can grind to a halt when userland issues a large read on a socket with a high RCVLOWAT (i.e., 512 KB for both). This appears to be because the NET_DMA design queues up lots of memcpy operations, but doesn't issue or wait for them (and thus free the associated skbs) until it is time for tcp_recvmesg() to return. The socket hangs when its TCP window goes to zero before enough data is available to satisfy the read. Periodically issue asynchronous memcpy operations, and free skbs for ones that have completed, to prevent sockets from going into zero-window mode. Signed-off-by: Steven J. Magnani Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 63 +++++++++++++++++++++++++++++++++++++++------------------- 1 file changed, 43 insertions(+), 20 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ae16f809e716..6afb6d8662b2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1254,6 +1254,39 @@ static void tcp_prequeue_process(struct sock *sk) tp->ucopy.memory = 0; } +#ifdef CONFIG_NET_DMA +static void tcp_service_net_dma(struct sock *sk, bool wait) +{ + dma_cookie_t done, used; + dma_cookie_t last_issued; + struct tcp_sock *tp = tcp_sk(sk); + + if (!tp->ucopy.dma_chan) + return; + + last_issued = tp->ucopy.dma_cookie; + dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + + do { + if (dma_async_memcpy_complete(tp->ucopy.dma_chan, + last_issued, &done, + &used) == DMA_SUCCESS) { + /* Safe to free early-copied skbs now */ + __skb_queue_purge(&sk->sk_async_wait_queue); + break; + } else { + struct sk_buff *skb; + while ((skb = skb_peek(&sk->sk_async_wait_queue)) && + (dma_async_is_complete(skb->dma_cookie, done, + used) == DMA_SUCCESS)) { + __skb_dequeue(&sk->sk_async_wait_queue); + kfree_skb(skb); + } + } + } while (wait); +} +#endif + static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; @@ -1546,6 +1579,10 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, /* __ Set realtime policy in scheduler __ */ } +#ifdef CONFIG_NET_DMA + if (tp->ucopy.dma_chan) + dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); +#endif if (copied >= target) { /* Do not sleep, just process backlog. */ release_sock(sk); @@ -1554,6 +1591,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sk_wait_data(sk, &timeo); #ifdef CONFIG_NET_DMA + tcp_service_net_dma(sk, false); /* Don't block */ tp->ucopy.wakeup = 0; #endif @@ -1633,6 +1671,9 @@ do_prequeue: copied = -EFAULT; break; } + + dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + if ((offset + used) == skb->len) copied_early = 1; @@ -1702,27 +1743,9 @@ skip_copy: } #ifdef CONFIG_NET_DMA - if (tp->ucopy.dma_chan) { - dma_cookie_t done, used; - - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); - - while (dma_async_memcpy_complete(tp->ucopy.dma_chan, - tp->ucopy.dma_cookie, &done, - &used) == DMA_IN_PROGRESS) { - /* do partial cleanup of sk_async_wait_queue */ - while ((skb = skb_peek(&sk->sk_async_wait_queue)) && - (dma_async_is_complete(skb->dma_cookie, done, - used) == DMA_SUCCESS)) { - __skb_dequeue(&sk->sk_async_wait_queue); - kfree_skb(skb); - } - } + tcp_service_net_dma(sk, true); /* Wait for queue to drain */ + tp->ucopy.dma_chan = NULL; - /* Safe to free early-copied skbs now */ - __skb_queue_purge(&sk->sk_async_wait_queue); - tp->ucopy.dma_chan = NULL; - } if (tp->ucopy.pinned_list) { dma_unpin_iovec_pages(tp->ucopy.pinned_list); tp->ucopy.pinned_list = NULL; -- cgit v1.2.2 From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- net/ipv4/tcp.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6afb6d8662b2..7a1f1d78893f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -265,6 +265,7 @@ #include #include #include +#include #include #include -- cgit v1.2.2 From baff42ab1494528907bf4d5870359e31711746ae Mon Sep 17 00:00:00 2001 From: "Steven J. Magnani" Date: Tue, 30 Mar 2010 13:56:01 -0700 Subject: net: Fix oops from tcp_collapse() when using splice() tcp_read_sock() can have a eat skbs without immediately advancing copied_seq. This can cause a panic in tcp_collapse() if it is called as a result of the recv_actor dropping the socket lock. A userspace program that splices data from a socket to either another socket or to a file can trigger this bug. Signed-off-by: Steven J. Magnani Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6afb6d8662b2..2c75f891914e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1368,6 +1368,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_eat_skb(sk, skb, 0); if (!desc->count) break; + tp->copied_seq = seq; } tp->copied_seq = seq; -- cgit v1.2.2