Re: [PATCH v3 10/10] x86/split_lock: Handle #AC exception for split lock

[Ingo Molnar]

* Fenghua Yu <fenghua.yu@xxxxxxxxx> wrote:

> --- a/arch/x86/kernel/traps.c
> +++ b/arch/x86/kernel/traps.c
> @@ -61,6 +61,7 @@
>  #include <asm/mpx.h>
>  #include <asm/vm86.h>
>  #include <asm/umip.h>
> +#include <asm/cpu.h>
>  
>  #ifdef CONFIG_X86_64
>  #include <asm/x86_init.h>
> @@ -292,9 +293,36 @@ DO_ERROR(X86_TRAP_OLD_MF, SIGFPE,           0, NULL, "coprocessor segment overru
>  DO_ERROR(X86_TRAP_TS,     SIGSEGV,          0, NULL, "invalid TSS",         invalid_TSS)
>  DO_ERROR(X86_TRAP_NP,     SIGBUS,           0, NULL, "segment not present", segment_not_present)
>  DO_ERROR(X86_TRAP_SS,     SIGBUS,           0, NULL, "stack segment",       stack_segment)
> -DO_ERROR(X86_TRAP_AC,     SIGBUS,  BUS_ADRALN, NULL, "alignment check",     alignment_check)
>  #undef IP
>  
> +dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code)
> +{
> +	unsigned int trapnr = X86_TRAP_AC;
> +	char str[] = "alignment check";
> +	int signr = SIGBUS;
> +	int ret;
> +
> +	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
> +
> +	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
> +			NOTIFY_STOP) {
> +		/* #AC exception could be handled by split lock handler. */
> +		ret = do_ac_split_lock(regs);
> +		if (ret) {
> +			cond_local_irq_enable(regs);
> +
> +			return;
> +		}
> +
> +		cond_local_irq_enable(regs);
> +		/*
> +		 * If not processed by split lock handler, go to generic
> +		 * #AC handler.
> +		 */
> +		do_trap(trapnr, signr, str, regs, error_code, BUS_ADRALN, NULL);
> +	}
> +}

Is there any experience with how frequently this signal is killing 
user-space processes on a modern distro? Any expectation of how frequent 
such SIGBUS task terminations are going to be in the field?

Thanks,

	Ingo