Re: [PATCH -tip 4/5] kprobes/x86: Use text_poke_smp_batch

[Mathieu Desnoyers]

* Masami Hiramatsu (mhiramat@xxxxxxxxxx) wrote:
> Use text_poke_smp_batch() in optimization path for reducing
> the number of stop_machine() issues.
> 
> Signed-off-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
> Cc: Ananth N Mavinakayanahalli <ananth@xxxxxxxxxx>
> Cc: Ingo Molnar <mingo@xxxxxxx>
> Cc: Jim Keniston <jkenisto@xxxxxxxxxx>
> Cc: Jason Baron <jbaron@xxxxxxxxxx>
> Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
> ---
> 
>  arch/x86/kernel/kprobes.c |   37 ++++++++++++++++++++++++++++++-------
>  include/linux/kprobes.h   |    2 +-
>  kernel/kprobes.c          |   13 +------------
>  3 files changed, 32 insertions(+), 20 deletions(-)
> 
> diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
> index 345a4b1..63a5c24 100644
> --- a/arch/x86/kernel/kprobes.c
> +++ b/arch/x86/kernel/kprobes.c
> @@ -1385,10 +1385,14 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
>  	return 0;
>  }
>  
> -/* Replace a breakpoint (int3) with a relative jump.  */
> -int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
> +#define MAX_OPTIMIZE_PROBES 256

So what kind of interrupt latency does a 256-probes batch generate on the
system ?  Are we talking about a few milliseconds, a few seconds ?

Thanks,

Mathieu

> +static struct text_poke_param jump_params[MAX_OPTIMIZE_PROBES];
> +static char jump_code_buf[MAX_OPTIMIZE_PROBES][RELATIVEJUMP_SIZE];
> +
> +static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
> +					    char *insn_buf,
> +					    struct optimized_kprobe *op)
>  {
> -	unsigned char jmp_code[RELATIVEJUMP_SIZE];
>  	s32 rel = (s32)((long)op->optinsn.insn -
>  			((long)op->kp.addr + RELATIVEJUMP_SIZE));
>  
> @@ -1396,16 +1400,35 @@ int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
>  	memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
>  	       RELATIVE_ADDR_SIZE);
>  
> -	jmp_code[0] = RELATIVEJUMP_OPCODE;
> -	*(s32 *)(&jmp_code[1]) = rel;
> +	insn_buf[0] = RELATIVEJUMP_OPCODE;
> +	*(s32 *)(&insn_buf[1]) = rel;
> +
> +	tprm->addr = op->kp.addr;
> +	tprm->opcode = insn_buf;
> +	tprm->len = RELATIVEJUMP_SIZE;
> +}
> +
> +/* Replace a breakpoint (int3) with a relative jump.  */
> +void __kprobes arch_optimize_kprobes(struct list_head *oplist)
> +{
> +	struct optimized_kprobe *op, *tmp;
> +	int c = 0;
> +
> +	list_for_each_entry_safe(op, tmp, oplist, list) {
> +		WARN_ON(kprobe_disabled(&op->kp));
> +		/* Setup param */
> +		setup_optimize_kprobe(&jump_params[c], jump_code_buf[c], op);
> +		list_del_init(&op->list);
> +		if (++c >= MAX_OPTIMIZE_PROBES)
> +			break;
> +	}
>  
>  	/*
>  	 * text_poke_smp doesn't support NMI/MCE code modifying.
>  	 * However, since kprobes itself also doesn't support NMI/MCE
>  	 * code probing, it's not a problem.
>  	 */
> -	text_poke_smp(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE);
> -	return 0;
> +	text_poke_smp_batch(jump_params, c);
>  }
>  
>  /* Replace a relative jump with a breakpoint (int3).  */
> diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
> index e7d1b2e..fe157ba 100644
> --- a/include/linux/kprobes.h
> +++ b/include/linux/kprobes.h
> @@ -275,7 +275,7 @@ extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn);
>  extern int arch_check_optimized_kprobe(struct optimized_kprobe *op);
>  extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op);
>  extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op);
> -extern int  arch_optimize_kprobe(struct optimized_kprobe *op);
> +extern void arch_optimize_kprobes(struct list_head *oplist);
>  extern void arch_unoptimize_kprobe(struct optimized_kprobe *op);
>  extern kprobe_opcode_t *get_optinsn_slot(void);
>  extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty);
> diff --git a/kernel/kprobes.c b/kernel/kprobes.c
> index aae368a..c824c23 100644
> --- a/kernel/kprobes.c
> +++ b/kernel/kprobes.c
> @@ -424,14 +424,10 @@ static LIST_HEAD(optimizing_list);
>  static void kprobe_optimizer(struct work_struct *work);
>  static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
>  #define OPTIMIZE_DELAY 5
> -#define MAX_OPTIMIZE_PROBES 64
>  
>  /* Kprobe jump optimizer */
>  static __kprobes void kprobe_optimizer(struct work_struct *work)
>  {
> -	struct optimized_kprobe *op, *tmp;
> -	int c = 0;
> -
>  	/* Lock modules while optimizing kprobes */
>  	mutex_lock(&module_mutex);
>  	mutex_lock(&kprobe_mutex);
> @@ -459,14 +455,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
>  	 */
>  	get_online_cpus();
>  	mutex_lock(&text_mutex);
> -	list_for_each_entry_safe(op, tmp, &optimizing_list, list) {
> -		WARN_ON(kprobe_disabled(&op->kp));
> -		if (arch_optimize_kprobe(op) < 0)
> -			op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
> -		list_del_init(&op->list);
> -		if (++c >= MAX_OPTIMIZE_PROBES)
> -			break;
> -	}
> +	arch_optimize_kprobes(&optimizing_list);
>  	mutex_unlock(&text_mutex);
>  	put_online_cpus();
>  	if (!list_empty(&optimizing_list))
> 
> 
> -- 
> Masami Hiramatsu
> e-mail: mhiramat@xxxxxxxxxx

-- 
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
--
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/