lkml.org 
[lkml]   [2021]   [Jan]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH RFC x86/mce] Make mce_timed_out() identify holdout CPUs
The "Timeout: Not all CPUs entered broadcast exception handler" message
will appear from time to time given enough systems, but this message does
not identify which CPUs failed to enter the broadcast exception handler.
This information would be valuable if available, for example, in order to
correlated with other hardware-oriented error messages. This commit
therefore maintains a cpumask_t of CPUs that have entered this handler,
and prints out which ones failed to enter in the event of a timeout.

Build-tested only.

Cc: Tony Luck <tony.luck@intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <x86@kernel.org>
Cc: <linux-edac@vger.kernel.org>
Reported-by: Jonathan Lemon <bsd@fb.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 13d3f1c..44d2b99 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -878,6 +878,12 @@ static atomic_t mce_executing;
static atomic_t mce_callin;

/*
+ * Track which CPUs entered and not in order to print holdouts.
+ */
+static cpumask_t mce_present_cpus;
+static cpumask_t mce_missing_cpus;
+
+/*
* Check if a timeout waiting for other CPUs happened.
*/
static int mce_timed_out(u64 *t, const char *msg)
@@ -894,8 +900,12 @@ static int mce_timed_out(u64 *t, const char *msg)
if (!mca_cfg.monarch_timeout)
goto out;
if ((s64)*t < SPINUNIT) {
- if (mca_cfg.tolerant <= 1)
+ if (mca_cfg.tolerant <= 1) {
+ if (!cpumask_andnot(&mce_missing_cpus, cpu_online_mask, &mce_present_cpus))
+ pr_info("%s: MCE holdout CPUs: %*pbl\n",
+ __func__, cpumask_pr_args(&mce_missing_cpus));
mce_panic(msg, NULL, NULL);
+ }
cpu_missing = 1;
return 1;
}
@@ -1006,6 +1016,7 @@ static int mce_start(int *no_way_out)
* is updated before mce_callin.
*/
order = atomic_inc_return(&mce_callin);
+ cpumask_set_cpu(smp_processor_id(), &mce_present_cpus);

/*
* Wait for everyone.
@@ -1114,6 +1125,7 @@ static int mce_end(int order)
reset:
atomic_set(&global_nwo, 0);
atomic_set(&mce_callin, 0);
+ cpumask_clear(&mce_present_cpus);
barrier();

/*
@@ -2712,6 +2724,7 @@ static void mce_reset(void)
atomic_set(&mce_executing, 0);
atomic_set(&mce_callin, 0);
atomic_set(&global_nwo, 0);
+ cpumask_clear(&mce_present_cpus);
}

static int fake_panic_get(void *data, u64 *val)
\
 
 \ /
  Last update: 2021-01-06 18:42    [W:0.165 / U:1.704 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site