Messages in this thread | | | Date | Sat, 9 Aug 2008 21:31:38 +0800 | From | Herbert Xu <> | Subject | Re: Kernel oops with 2.6.26, padlock and ipsec: probably problem with fpu state changes |
| |
On Fri, Aug 08, 2008 at 04:11:21PM -0700, Suresh Siddha wrote: > > b) Looking deeper, do we need to disable interrupts in the kernel_fpu_begin()? > Is there a recursive case, where interrupt context also touches FPU/SSE > registers?
Even if there wasn't one before, there is going to be one now because as you pointed out yourself, if we get an inbound IPsec packet between any kernel_fpu_begin/kernel_fpu_end area, we could get a nested kernel_fpu_end which puts us back to square one wrt to the original race.
So clearly we need to think more about this issue.
Unless we can come up with a new solution quickly, I recommend that we back out the FPU changes.
Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
| |