| To: | Andi Kleen <ak@xxxxxx> |
|---|---|
| Subject: | Re: Network oops |
| From: | george anzinger <george@xxxxxxxxxx> |
| Date: | Fri, 28 Jun 2002 12:56:31 -0700 |
| Cc: | "David S. Miller" <davem@xxxxxxxxxx>, kuznet@xxxxxxxxxxxxx, netdev@xxxxxxxxxxx, linux-net@xxxxxxxxxxxxxxx, pekkas@xxxxxxxxxx, andrew.r.cress@xxxxxxxxx |
| Organization: | Monta Vista Software |
| References: | <20020609.213150.32126725.davem@xxxxxxxxxx> <3D042F8F.72764243@xxxxxxxxxx> <3D120EAE.5A0D365E@xxxxxxxxxx> <20020620.173805.55219901.davem@xxxxxxxxxx> <3D133538.60B6810C@xxxxxxxxxx> <20020622025551.A1919@averell> |
| Sender: | owner-netdev@xxxxxxxxxxx |
We finally found the problem. I want to thank the folks who gave any thought and/or feedback to us, particularly Alexey and David. For what its worth we tracked it down to the kernel memory allocation routines allocating the same buffer to two different network requesters. This in turn was caused by a basic flaw in the preemption code that preempted on spin_unlock, REGARDLESS OF THE STATE OF THE INTERRUPT SYSTEM. -- George Anzinger george@xxxxxxxxxx High-res-timers: http://sourceforge.net/projects/high-res-timers/ Real time sched: http://sourceforge.net/projects/rtsched/ Preemption patch: http://www.kernel.org/pub/linux/kernel/people/rml |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | skb_copy() for private linear skb->data, Memon, Mazhar I |
|---|---|
| Next by Date: | IPv6 ND on PPC hardware, Marco d'Itri |
| Previous by Thread: | Re: Network oops, Andi Kleen |
| Next by Thread: | Re: Network oops, David S. Miller |
| Indexes: | [Date] [Thread] [Top] [All Lists] |