Re: [PATCH RT 1/2 v3] x86: Do not disable preemption in int3 on32bit

[Masami Hiramatsu]

(2012/02/02 6:06), Steven Rostedt wrote:
> Preemption must be disabled before enabling interrupts in do_trap
> on x86_64 because the stack in use for int3 and debug is a per CPU
> stack set by th IST. But 32bit does not have an IST and the stack
> still belongs to the current task and there is no problem in scheduling
> out the task.
> 
> Keep preemption enabled on X86_32 when enabling interrupts for
> do_trap().
> 
> The name of the function is changed from preempt_conditional_sti/cli()
> to conditional_sti/cli_ist(), to annotate that this function is used
> when the stack is on the IST.
> 
> Signed-off-by: Steven Rostedt <rostedt@xxxxxxxxxxx

Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>

Thanks!

> 
> Index: linux-rt.git/arch/x86/kernel/traps.c
> ===================================================================
> --- linux-rt.git.orig/arch/x86/kernel/traps.c
> +++ linux-rt.git/arch/x86/kernel/traps.c
> @@ -87,9 +87,21 @@ static inline void conditional_sti(struc
>  		local_irq_enable();
>  }
>  
> -static inline void preempt_conditional_sti(struct pt_regs *regs)
> +static inline void conditional_sti_ist(struct pt_regs *regs)
>  {
> +#ifdef CONFIG_X86_64
> +	/*
> +	 * X86_64 uses a per CPU stack on the IST for certain traps
> +	 * like int3. The task can not be preempted when using one
> +	 * of these stacks, thus preemption must be disabled, otherwise
> +	 * the stack can be corrupted if the task is scheduled out,
> +	 * and another task comes in and uses this stack.
> +	 *
> +	 * On x86_32 the task keeps its own stack and it is OK if the
> +	 * task schedules out.
> +	 */
>  	inc_preempt_count();
> +#endif
>  	if (regs->flags & X86_EFLAGS_IF)
>  		local_irq_enable();
>  }
> @@ -100,11 +112,13 @@ static inline void conditional_cli(struc
>  		local_irq_disable();
>  }
>  
> -static inline void preempt_conditional_cli(struct pt_regs *regs)
> +static inline void conditional_cli_ist(struct pt_regs *regs)
>  {
>  	if (regs->flags & X86_EFLAGS_IF)
>  		local_irq_disable();
> +#ifdef CONFIG_X86_64
>  	dec_preempt_count();
> +#endif
>  }
>  
>  static void __kprobes
> @@ -222,9 +236,9 @@ dotraplinkage void do_stack_segment(stru
>  	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
>  			12, SIGBUS) == NOTIFY_STOP)
>  		return;
> -	preempt_conditional_sti(regs);
> +	conditional_sti_ist(regs);
>  	do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL);
> -	preempt_conditional_cli(regs);
> +	conditional_cli_ist(regs);
>  }
>  
>  dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
> @@ -316,9 +330,9 @@ dotraplinkage void __kprobes do_int3(str
>  		return;
>  #endif
>  
> -	preempt_conditional_sti(regs);
> +	conditional_sti_ist(regs);
>  	do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
> -	preempt_conditional_cli(regs);
> +	conditional_cli_ist(regs);
>  }
>  
>  #ifdef CONFIG_X86_64
> @@ -412,12 +426,12 @@ dotraplinkage void __kprobes do_debug(st
>  		return;
>  
>  	/* It's safe to allow irq's after DR6 has been saved */
> -	preempt_conditional_sti(regs);
> +	conditional_sti_ist(regs);
>  
>  	if (regs->flags & X86_VM_MASK) {
>  		handle_vm86_trap((struct kernel_vm86_regs *) regs,
>  				error_code, 1);
> -		preempt_conditional_cli(regs);
> +		conditional_cli_ist(regs);
>  		return;
>  	}
>  
> @@ -436,7 +450,7 @@ dotraplinkage void __kprobes do_debug(st
>  	si_code = get_si_code(tsk->thread.debugreg6);
>  	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
>  		send_sigtrap(tsk, regs, error_code, si_code);
> -	preempt_conditional_cli(regs);
> +	conditional_cli_ist(regs);
>  
>  	return;
>  }
> 


-- 
Masami HIRAMATSU
Software Platform Research Dept. Linux Technology Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: masami.hiramatsu.pt@xxxxxxxxxxx
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/