This should fix the following bugs: * Connections with MD5 signatures produce invalid packets whenever SACK options are included * MD5 signatures are counted twice in the MSS calculations Behaviour changes: * A SYN with MD5 + SACK + TS elicits a SYNACK with MD5 + SACK This is because we can't fit any SACK blocks in a packet with MD5 + TS options. There was discussion about disabling SACK rather than TS in order to fit in better with old, buggy kernels, but that was deemed t...

Currently, the MD5 code assumes that the SKBs are linear and, in the case that they aren't, happily goes off and hashes off the end of the SKB and into random memory. Reported by Stephen Hemminger in [1]. Advice thanks to Stephen and Evgeniy Polyakov. Also includes a couple of missed route_caps from Stephen's patch in [2]. [1] http://marc.info/?l=linux-netdev&m=121445989106145&w=2 [2] http://marc.info/?l=linux-netdev&m=121459157816964&w=2 Signed-off-by: Adam Langley <agl@imp...

A regression to v2.6.26: I started getting this skb-head corruption message today, on a T60 laptop with e1000: PM: Removing info for No Bus:vcs11 device: 'vcs11': device_create_release ============================================================================= BUG skbuff_head_cache: Poison overwritten ----------------------------------------------------------------------------- INFO: 0xf658ae9c-0xf658ae9c. First byte 0x6a instead of 0x6b INFO: Allocated in __alloc_skb+0x2c/0x110 age=0 cp...

that's ok - i've got some local qa helpers that have config options. Things like making SMP bootups more likely in randconfig, adding various boot parameters to the bootup via .config methods (so that boot parameters can be randomized via make randconfig), etc. these: CONFIG_BOOTPARAM_SUPPORT=y CONFIG_BOOTPARAM_NO_HZ_OFF=y CONFIG_BOOTPARAM_NMI_WATCHDOG_BIT_0=y CONFIG_BOOTPARAM_LAPIC=y CONFIG_BOOTPARAM_IDLE_MWAIT=y CONFIG_BOOTPARAM_NOPAT=y CONFIG_BOOTPARAM_NOTSC=y are...

hmm ... your analysis gave me a wonderful albeit admittedly remote idea: If only we had some kernel technology that could track and validate memory accesses, and point out the cases where we access uninitialized memory, just like Valgrind? ... something like kmemcheck? ;-) So i booted that box with tip/master and kmemcheck enabled. (plus a few fixlets to make networking allocations be properly tracked by kmemcheck.) It was a slow bootup and long wait, but it gave a few hits here: ...

From: Ingo Molnar <mingo@elte.hu> This is very unlikely to be added by us networking folks, no networking merges have happened for the 2.6.27 merge window yet :-) --

hm, but it was not reproducible on the third and fourth attempt :-( I tried hard to provoke it by generating artificial parallel network and netconsole output - but it didnt want to trigger. Heisenbug ... Maybe the debug output gives someone an idea about the nature of the bug? Ingo --

Cheers, Harvey --

Do you mean the problem with IPSEC and icmp packets generated on the router? Couldn't check yet. I started testing 2.6.26 but I get a kernel oops, so I switched back to 2.6.25.11. Here is the output of dmesg (no logging was switched on so I don't have the complete oops). But it happened on several of our routers within one day: xe [<c01c8c4f>] update+0x0/0x46 [<c01c8a4d>] final+0x0/0x54 [<c01c8be4>] digest+0x0/0x6b [<c01c8c95>] nosetkey+0x0/0xf [<c01c89cc&g...

could I have your ack for this?

I am probably missing some usecases here, but usually if you want to use non-blocking I/O you need to use special approach anyway (e.g. code the I don't know... the man page explicitly says that even when you use SPLICE_F_NONBLOCK splice may block because of the underlying fd blocking. But more importantly, how can we solve the deadlock issue described in the patch? Do we need all of the complications of async I/O for such a simple and common usecase? Maybe we can solve both usecases by ...

You lost me here :) The way I interpret the man page text is that it is ok for splice to block, even if SPLICE_F_NONBLOCK is set. The comments near SPLICE_F_NONBLOCK says the same thing: #define SPLICE_F_NONBLOCK (0x02) /* don't block on the pipe splicing (but */ /* we may still block on the fd we splice */ /* from/to, of course */ For this "program": x=splice(socket, pipe, size, flags=0); if (x > 0) splice(pipe, ...

They are symmetrical to single_open ones :) Signed-off-by: Pavel Emelyanov <xemul@openvz.org> --- fs/proc/proc_net.c | 8 ++++++++ include/linux/seq_file_net.h | 1 + net/ipv4/fib_trie.c | 9 +-------- net/ipv4/proc.c | 30 +++--------------------------- net/ipv6/proc.c | 10 +--------- net/ipv6/route.c | 20 ++------------------ 6 files changed, 16 insertions(+), 62 deletions(-) diff --git a/fs/proc/proc_net.c b/fs...

After all this stuff is moved outside, this function can look better. Besides, I tuned the error path in ip_proc_init_net to make it have only 2 exit points, not 3. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> --- net/ipv4/proc.c | 15 +++------------ 1 files changed, 3 insertions(+), 12 deletions(-) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 120e1f7..5543904 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -508,7 +508,7 @@ static const struct file_operations ne...

All the statistics show in this file is also made per-net already. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> --- net/ipv4/proc.c | 70 +++++++++++++++++++++++++++++++++++++++--------------- 1 files changed, 50 insertions(+), 20 deletions(-) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index df8c4af..367b81f 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -266,11 +266,12 @@ static void icmpmsg_put(struct seq_file *seq) int j, i, count; static int out[PERLINE]; ...

After moving all the stuff outside this function it looks a bit ugly - make it look better. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> --- net/ipv4/af_inet.c | 8 +------- 1 files changed, 1 insertions(+), 7 deletions(-) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 36ff6dc..dd919d8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1399,13 +1399,7 @@ static __net_initdata struct pernet_operations ipv4_mib_ops = { static int __init init_ipv4_mibs(vo...

Signed-off-by: Pavel Emelyanov <xemul@openvz.org> --- include/net/icmp.h | 5 ++--- include/net/netns/mib.h | 1 + net/ipv4/af_inet.c | 11 ++++++----- net/ipv4/icmp.c | 2 -- net/ipv4/proc.c | 8 ++++---- 5 files changed, 13 insertions(+), 14 deletions(-) diff --git a/include/net/icmp.h b/include/net/icmp.h index 03b9972..e14f2c0 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -29,10 +29,9 @@ struct icmp_err { }; extern struct ...

Similar to... ouch, I repeat myself. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> --- include/net/netns/mib.h | 1 + include/net/udp.h | 9 ++++----- net/ipv4/af_inet.c | 11 ++++++----- net/ipv4/proc.c | 2 +- net/ipv4/udp.c | 3 --- 5 files changed, 12 insertions(+), 14 deletions(-) diff --git a/include/net/netns/mib.h b/include/net/netns/mib.h index b5b1115..738c87c 100644 --- a/include/net/netns/mib.h +++ b/include/net/netns/mib.h @@...

Similar to tcp one. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> --- include/net/ip.h | 7 +++---- include/net/netns/mib.h | 1 + net/ipv4/af_inet.c | 11 ++++++----- net/ipv4/ip_input.c | 8 -------- net/ipv4/proc.c | 4 ++-- 5 files changed, 12 insertions(+), 19 deletions(-) diff --git a/include/net/ip.h b/include/net/ip.h index 02924fb..ff2535a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -156,10 +156,9 @@ struct ipv4_config ...

These ones are currently empty, but stuff from init_ipv4_mibs will sequentially migrate there. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> --- net/ipv4/af_inet.c | 20 ++++++++++++++++++++ 1 files changed, 20 insertions(+), 0 deletions(-) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 95a966d..b4b77aa 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -110,6 +110,7 @@ #include <net/ipip.h> #include <net/inet_common.h> #include <net/xfrm....

Signed-off-by: Denis V. Lunev <den@openvz.org> --- include/net/ipv6.h | 4 +--- net/ipv6/ipv6_sockglue.c | 7 ++----- net/ipv6/raw.c | 2 +- 3 files changed, 4 insertions(+), 9 deletions(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index c2c3649..2d5c185 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -221,9 +221,7 @@ static inline void fl6_sock_release(struct ip6_flowlabel *fl) atomic_dec(&fl->users); } -extern int ip6_r...

Instead of 'pfifo_fast' we have just plain 'fifo_fast'. No priority queues, just a straight FIFO. This is necessary in order to legally have a seperate qdisc per queue in multi-TX-queue setups, and thus get full parallelization. Signed-off-by: David S. Miller <davem@davemloft.net> --- net/sched/sch_generic.c | 99 ++++++++++------------------------------------ 1 files changed, 22 insertions(+), 77 deletions(-) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 8f...

We can simply use the qdisc->q.lock for all of the qdisc tree synchronization. Signed-off-by: David S. Miller <davem@davemloft.net> --- drivers/net/ifb.c | 20 -------------------- include/linux/netdevice.h | 1 - include/net/sch_generic.h | 7 ++++++- net/core/dev.c | 9 +++++---- net/mac80211/wme.c | 19 ++++++++++++------- net/sched/sch_generic.c | 32 +++++++++++++++----------------- net/sched/sch_teql.c | 7 +++++-- 7 files cha...

Make sch_tree_lock() lock the qdisc's root. All of the users hold the RTNL semaphore and the root qdisc is not changing. Implement tbf_tree_{lock,unlock}() simply in terms of sch_tree_{lock,unlock}(). Signed-off-by: David S. Miller <davem@davemloft.net> --- include/net/sch_generic.h | 16 ++++++++++++---- 1 files changed, 12 insertions(+), 4 deletions(-) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 3cc4b5c..60e1e9f 100644 --- a/include/net/sch_generic...