[PATCH] x86/mce: Handle broadcasted MCE gracefully with kexec

[Borislav Petkov]

From: Xunlei Pang <***@redhat.com>

When we are about to kexec a crash kernel and right then and there a
broadcasted MCE fires while we're still in the first kernel and while
the other CPUs remain in a holding pattern, the #MC handler of the
first kernel will timeout and then panic due to never completing MCE
synchronization.

Handle this in a similar way as to when the CPUs are offlined when that
broadcasted MCE happens.

Suggested-by: Borislav Petkov <***@alien8.de>
Signed-off-by: Xunlei Pang <***@redhat.com>
Acked-by: Tony Luck <***@intel.com>
Cc: Naoya Horiguchi <n-***@ah.jp.nec.com>
Cc: ***@lists.infradead.org
Cc: linux-edac <linux-***@vger.kernel.org>
Cc: x86-ml <***@kernel.org>
Link: http://lkml.kernel.org/r/1487857012-9059-1-git-send-email-***@redhat.com
[ Boris: rewrote commit message and comments. ]
Signed-off-by: Borislav Petkov <***@suse.de>
---
arch/x86/include/asm/reboot.h | 1 +
arch/x86/kernel/cpu/mcheck/mce.c | 18 ++++++++++++++++--
arch/x86/kernel/reboot.c | 5 +++--
3 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 2cb1cc253d51..fc62ba8dce93 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -15,6 +15,7 @@ struct machine_ops {
};

extern struct machine_ops machine_ops;
+extern int crashing_cpu;

void native_machine_crash_shutdown(struct pt_regs *regs);
void native_machine_shutdown(void);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8e9725c607ea..177472ace838 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -49,6 +49,7 @@
#include <asm/tlbflush.h>
#include <asm/mce.h>
#include <asm/msr.h>
+#include <asm/reboot.h>

#include "mce-internal.h"

@@ -1127,9 +1128,22 @@ void do_machine_check(struct pt_regs *regs, long error_code)
* on Intel.
*/
int lmce = 1;
+ int cpu = smp_processor_id();

- /* If this CPU is offline, just bail out. */
- if (cpu_is_offline(smp_processor_id())) {
+ /*
+ * Cases where we avoid rendezvous handler timeout:
+ * 1) If this CPU is offline.
+ *
+ * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
+ * skip those CPUs which remain looping in the 1st kernel - see
+ * crash_nmi_callback().
+ *
+ * Note: there still is a small window between kexec-ing and the new,
+ * kdump kernel establishing a new #MC handler where a broadcasted MCE
+ * might not get handled properly.
+ */
+ if (cpu_is_offline(cpu) ||
+ (crashing_cpu != -1 && crashing_cpu != cpu)) {
u64 mcgstatus;

mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e244c19a2451..d3718cc5edbf 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -749,10 +749,11 @@ void machine_crash_shutdown(struct pt_regs *regs)
#endif


+/* This is the CPU performing the emergency shutdown work. */
+int crashing_cpu = -1;
+
#if defined(CONFIG_SMP)

-/* This keeps a track of which one is crashing cpu. */
-static int crashing_cpu;
static nmi_shootdown_cb shootdown_callback;

static atomic_t waiting_for_crash_ipi;