Commit 5bc32950 authored by Xunlei Pang's avatar Xunlei Pang Committed by Thomas Gleixner
Browse files

x86/mce: Handle broadcasted MCE gracefully with kexec 



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.

[ Boris: rewrote commit message and comments. ]

Suggested-by: default avatarBorislav Petkov <bp@alien8.de>
Signed-off-by: default avatarXunlei Pang <xlpang@redhat.com>
Signed-off-by: default avatarBorislav Petkov <bp@suse.de>
Acked-by: default avatarTony Luck <tony.luck@intel.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: kexec@lists.infradead.org
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1487857012-9059-1-git-send-email-xlpang@redhat.com
Link: http://lkml.kernel.org/r/20170313095019.19351-1-bp@alien8.de


Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
parent 4495c08e

arch/x86/include/asm/reboot.h

+1 −0
Original line number Diff line number Diff line
@@ -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);

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

+16 −2
Original line number Diff line number Diff line
@@ -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);

arch/x86/kernel/reboot.c

+3 −2
Original line number Diff line number Diff line
@@ -765,10 +765,11 @@ 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;

CRA Git | Maintained and supported by SUSTech CRA and CCSE