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 correlate with other hardware-oriented error
messages.

Add a cpumask of CPUs which maintains which CPUs have entered this
handler, and print out which ones failed to enter in the event of a
timeout.

 [ bp: Massage. ]

Reported-by: Jonathan Lemon <bsd@fb.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20210106174102.GA23874@paulmck-ThinkPad-P72

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 13d3f1cbda176711069606c6dacbe2900579c208..6c81d0998e0a390cd7bdae4314cdc058adb4ef1f 100644 (file)
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -877,6 +877,12 @@ static atomic_t mce_executing;
  */
 static atomic_t mce_callin;
 
+/*
+ * Track which CPUs entered the MCA broadcast synchronization and which not in
+ * order to print holdouts.
+ */
+static cpumask_t mce_missing_cpus = CPU_MASK_ALL;
+
 /*
  * Check if a timeout waiting for other CPUs happened.
  */
@@ -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_and(&mce_missing_cpus, cpu_online_mask, &mce_missing_cpus))
+                               pr_emerg("CPUs not responding to MCE broadcast (may include false positives): %*pbl\n",
+                                        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_clear_cpu(smp_processor_id(), &mce_missing_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_setall(&mce_missing_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_setall(&mce_missing_cpus);
 }
 
 static int fake_panic_get(void *data, u64 *val)