Re: [PATCH -v3] x86, MCE: Drop the default decoding notifier

[Prarit Bhargava]

On 04/14/2011 11:00 AM, Borislav Petkov wrote:
> On Wed, Apr 13, 2011 at 01:37:05PM -0400, Borislav Petkov wrote:
>   
>> In the worst case, we will report 32 CEs before panicking. For that case
>> we either do printk_once as Tony suggested or we ratelimit it. I'll
>> update the patch.
>>     
> Ok, how about the following, I ratelimit the printk to the default of 10
> messages per 5 seconds. I've also got the hardware MCE injection patches
> ready and will do some testing with them.
>   

See my previous email ;)  I think just putting in a printk_once after
the CE call to print_mce() in mce_panic() might be better?  At least
that way we get the --ascii message for *EVERY* UC which IMO would be
nice...

P.

> --
> From: Borislav Petkov <borislav.petkov@xxxxxxx>
> Date: Wed, 13 Apr 2011 14:32:06 +0200
> Subject: [PATCH -v3] x86, MCE: Drop the default decoding notifier
>
> The default notifier doesn't make a lot of sense to call in the
> correctable errors case. Drop it and emit the mcelog decoding hint only
> in the uncorrectable errors case and when no notifier is registered.
> Also, limit the issual of the "mcelog" message in the remote case when
> we dump unreported CEs before panicking.
>
> While at it, remove unused old x86_mce_decode_callback from the header.
>
> Signed-off-by: Prarit Bhargava <prarit@xxxxxxxxxx>
> Signed-off-by: Borislav Petkov <borislav.petkov@xxxxxxx>
> ---
>  arch/x86/include/asm/mce.h       |    2 --
>  arch/x86/kernel/cpu/mcheck/mce.c |   23 ++++++-----------------
>  2 files changed, 6 insertions(+), 19 deletions(-)
>
> diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
> index eb16e94..021979a 100644
> --- a/arch/x86/include/asm/mce.h
> +++ b/arch/x86/include/asm/mce.h
> @@ -142,8 +142,6 @@ static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
>  static inline void enable_p5_mce(void) {}
>  #endif
>  
> -extern void (*x86_mce_decode_callback)(struct mce *m);
> -
>  void mce_setup(struct mce *m);
>  void mce_log(struct mce *m);
>  DECLARE_PER_CPU(struct sys_device, mce_dev);
> diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
> index 68e2303..679bd9e 100644
> --- a/arch/x86/kernel/cpu/mcheck/mce.c
> +++ b/arch/x86/kernel/cpu/mcheck/mce.c
> @@ -105,20 +105,6 @@ static int			cpu_missing;
>  ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
>  EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
>  
> -static int default_decode_mce(struct notifier_block *nb, unsigned long val,
> -			       void *data)
> -{
> -	pr_emerg(HW_ERR "No human readable MCE decoding support on this CPU type.\n");
> -	pr_emerg(HW_ERR "Run the message through 'mcelog --ascii' to decode.\n");
> -
> -	return NOTIFY_STOP;
> -}
> -
> -static struct notifier_block mce_dec_nb = {
> -	.notifier_call = default_decode_mce,
> -	.priority      = -1,
> -};
> -
>  /* MCA banks polled by the period polling timer for corrected events */
>  DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
>  	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
> @@ -212,6 +198,8 @@ void mce_log(struct mce *mce)
>  
>  static void print_mce(struct mce *m)
>  {
> +	int ret = 0;
> +
>  	pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
>  	       m->extcpu, m->mcgstatus, m->bank, m->status);
>  
> @@ -239,7 +227,10 @@ static void print_mce(struct mce *m)
>  	 * Print out human-readable details about the MCE error,
>  	 * (if the CPU has an implementation for that)
>  	 */
> -	atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
> +	ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
> +	if (ret != NOTIFY_STOP)
> +		printk_ratelimited(KERN_EMERG HW_ERR
> +				   "Run the above through 'mcelog --ascii'\n");
>  }
>  
>  #define PANIC_TIMEOUT 5 /* 5 seconds */
> @@ -1721,8 +1712,6 @@ __setup("mce", mcheck_enable);
>  
>  int __init mcheck_init(void)
>  {
> -	atomic_notifier_chain_register(&x86_mce_decoder_chain, &mce_dec_nb);
> -
>  	mcheck_intel_therm_init();
>  
>  	return 0;
>   
--
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/