Messages in this thread | | | Date | Fri, 10 Jan 2014 21:10:20 +0100 | From | Peter Zijlstra <> | Subject | Re: SIGSEGV when using "perf record -g" with 3.13-rc* kernel |
| |
On Fri, Jan 10, 2014 at 02:37:10PM -0500, Waiman Long wrote: > >@@ -641,7 +641,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, > > > > /* Are we prepared to handle this kernel fault? */ > > if (fixup_exception(regs)) { > >- if (current_thread_info()->sig_on_uaccess_error&& signal) { > >+ if (!in_nmi()&& current_thread_info()->sig_on_uaccess_error&& signal) { > > tsk->thread.trap_nr = X86_TRAP_PF; > > tsk->thread.error_code = error_code | PF_USER; > > tsk->thread.cr2 = address; > > Yes, this change fixed the error that I got. I no longer see SIGSEGV when I > run the test.
Awesome, just send a more elaborate version that should have the same effect.
> I did tried to back out your "perf: Fix arch_perf_out_copy_user default" > patch, but it didn't fix the problem.
The culprit was: e00b12e64be9 ("perf/x86: Further optimize copy_from_user_nmi()")
| |