Commit ea324444 authored by Borislav Petkov (AMD)'s avatar Borislav Petkov (AMD)
Browse files

x86/mce: Restore MCA polling interval halving 



RongQing reported that the MCA polling interval doesn't halve when an
error gets logged. It was traced down to the commit in Fixes:, because:

  mce_timer_fn()
  |-> mce_poll_banks()
  |-> machine_check_poll()
  |-> mce_log()

which will queue the work and return.

Now, back in mce_timer_fn():

        /*
         * Alert userspace if needed. If we logged an MCE, reduce the polling
         * interval, otherwise increase the polling interval.
         */
        if (mce_notify_irq())

<--- here we haven't ran the notifier chain yet so mce_need_notify is
not set yet so this won't hit and we won't halve the interval iv.

Now the notifier chain runs. mce_early_notifier() sets the bit, does
mce_notify_irq(), that clears the bit and then the notifier chain
a little later logs the error.

So this is a silly timing issue.

But, that's all unnecessary.

All it needs to happen here is, the "should we notify of a logged MCE"
mce_notify_irq() asks, should be simply a question to the mce gen pool:
"Are you empty?"

And that then turns into a simple yes or no answer and it all
JustWorks(tm).

So do that and also distribute the functionality where it belongs:
 - Print that MCE events have been logged in mce_log()
 - Trigger the mcelog tool specific work in the first notifier

As a result, mce_notify_irq() can go now.

Fixes: 011d8261 ("RAS: Add a Corrected Errors Collector")
Reported-by: default avatarLi RongQing <lirongqing@baidu.com>
Signed-off-by: default avatarBorislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: default avatarQiuxu Zhuo <qiuxu.zhuo@intel.com>
Tested-by: default avatarQiuxu Zhuo <qiuxu.zhuo@intel.com>
Link: https://lore.kernel.org/r/20260112082747.2842-1-lirongqing@baidu.com
parent 5d691905

arch/x86/kernel/cpu/mce/core.c

+5 −28
Original line number Diff line number Diff line
@@ -90,7 +90,6 @@ struct mca_config mca_cfg __read_mostly = { 
};



static DEFINE_PER_CPU(struct mce_hw_err, hw_errs_seen);

static unsigned long mce_need_notify;



/*

 * MCA banks polled by the period polling timer for corrected events.
@@ -152,9 +151,11 @@ EXPORT_PER_CPU_SYMBOL_GPL(injectm); 


void mce_log(struct mce_hw_err *err)

{

	if (mce_gen_pool_add(err))

	if (mce_gen_pool_add(err)) {

		pr_info(HW_ERR "Machine check events logged\n");

		irq_work_queue(&mce_irq_work);

	}

}

EXPORT_SYMBOL_GPL(mce_log);



void mce_register_decode_chain(struct notifier_block *nb)
@@ -585,28 +586,6 @@ bool mce_is_correctable(struct mce *m) 
}

EXPORT_SYMBOL_GPL(mce_is_correctable);



/*

 * Notify the user(s) about new machine check events.

 * Can be called from interrupt context, but not from machine check/NMI

 * context.

 */

static bool mce_notify_irq(void)

{

	/* Not more than two messages every minute */

	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);



	if (test_and_clear_bit(0, &mce_need_notify)) {

		mce_work_trigger();



		if (__ratelimit(&ratelimit))

			pr_info(HW_ERR "Machine check events logged\n");



		return true;

	}



	return false;

}



static int mce_early_notifier(struct notifier_block *nb, unsigned long val,

			      void *data)

{
@@ -618,9 +597,7 @@ static int mce_early_notifier(struct notifier_block *nb, unsigned long val, 
	/* Emit the trace record: */

	trace_mce_record(err);



	set_bit(0, &mce_need_notify);



	mce_notify_irq();

	mce_work_trigger();



	return NOTIFY_DONE;

}
@@ -1804,7 +1781,7 @@ static void mce_timer_fn(struct timer_list *t) 
	 * Alert userspace if needed. If we logged an MCE, reduce the polling

	 * interval, otherwise increase the polling interval.

	 */

	if (mce_notify_irq())

	if (!mce_gen_pool_empty())

		iv = max(iv / 2, (unsigned long) HZ/100);

	else

		iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));