On Mon, 15 Jun 2009, Ingo Molnar wrote: > > Note that Oprofile uses the same method of __copy_user_inatomic() in > arch/x86/oprofile/backtrace.c, but i believe that code is broken - i > doubt the call-chain support for user-space stacks ever worked in > oprofile - with perfcounters i can make this method crash under > load. (we re-enter the NMI which due to IST executes over the exact > same, still pending NMI frame. Kaboom.) > > I saw you being involved with the Oprofile code 3 years ago: > > | commit c34d1b4d165c67b966bca4aba026443d7ff161eb > | Author: Hugh Dickins <hugh@xxxxxxxxxxx> > | Date: Sat Oct 29 18:16:32 2005 -0700 > | > | [PATCH] mm: kill check_user_page_readable > > That method of __copy_user_inatomic(), while elegant, is subtly > wrong in an NMI context. We really must avoid taking faults there. Yes, I'm afraid that subtlety escaped me - thanks for explaining. Hugh -- To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
|