On Fri, Feb 28, 2014 at 04:33:40PM +0100, Jiri Olsa wrote:
> The trace_do_page_fault function trigger tracepoint
> and then handles the actual page fault.
>
> This could lead to error if the tracepoint caused page
> fault. The original cr2 value gets lost and the original
> page fault handler kill
Vince, can you test this patch instead. Seems that the bug you found was
found by others. You can remove all patches again, and modify this patch such
that the read of cr2 is before the exception_enter() call (in both locations)
On Fri, Feb 28, 2014 at 04:47:15PM +0100, Jiri Olsa wrote:
> On Fri,
On Fri, Feb 28, 2014 at 04:33:40PM +0100, Jiri Olsa wrote:
> The trace_do_page_fault function trigger tracepoint
> and then handles the actual page fault.
>
> This could lead to error if the tracepoint caused page
> fault. The original cr2 value gets lost and the original
> page fault handler kill
On Fri, Feb 28, 2014 at 04:33:40PM +0100, Jiri Olsa wrote:
While I like the idea of just pushing up the CR2 read; the below does
the read too late still, exception_enter() also has a tracepoint in.
> @@ -1267,9 +1269,18 @@ dotraplinkage void __kprobes
> trace_do_page_fault(struct pt_regs *regs,
The trace_do_page_fault function trigger tracepoint
and then handles the actual page fault.
This could lead to error if the tracepoint caused page
fault. The original cr2 value gets lost and the original
page fault handler kills current process with SIGSEGV.
This happens if you record page faults
5 matches
Mail list logo