On Fri, Jul 17, 2020 at 02:35:00PM -0700, Fenghua Yu wrote:
> #DB for bus lock detect fixes all issues in #AC for split lock detect:
> 1) It's architectural ... just need to look at one CPUID bit to know it
> exists
> 2) The IA32_DEBUGCTL MSR, which reports bus lock in #DB, is per-thread.
> So each process or guest can have different behavior.
And it generates a whole new problem due to #DB being an IST, and
> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
> index b038695f36c5..58725567da39 100644
> --- a/arch/x86/kernel/traps.c
> +++ b/arch/x86/kernel/traps.c
> @@ -812,6 +812,16 @@ static void handle_debug(struct pt_regs *regs, unsigned
> long dr6, bool user)
> if (!user && !dr6)
> return;
>
> + /* Handle bus lock. */
> + if (!(dr6 & DR_BUS_LOCK)) {
> + cond_local_irq_enable(regs);
> + if (user)
> + handle_user_bus_lock(regs);
> + else
> + handle_kernel_bus_lock(regs);
> + goto out;
> + }
> +
> /*
> * If dr6 has no reason to give us about the origin of this trap,
> * then it's very likely the result of an icebp/int01 trap.
we very much rely on #DB never recursing, which we carefully crafted by
disallowing hardare breakpoints on noinstr code and clearing DR7 early.
But now it can... please keep the pieces.
