x86/mce: Detect local MCEs properly
Check the MCG_STATUS_LMCES bit on Intel to verify that current MCE is local. It is always local on AMD. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> [ Massaged it a bit. Reflowed comments. Shut up -Wmaybe-uninitialized. ] Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/1462019637-16474-8-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Родитель
5541c93cdf
Коммит
fead35c689
|
@ -1038,11 +1038,12 @@ void do_machine_check(struct pt_regs *regs, long error_code)
|
||||||
int i;
|
int i;
|
||||||
int worst = 0;
|
int worst = 0;
|
||||||
int severity;
|
int severity;
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Establish sequential order between the CPUs entering the machine
|
* Establish sequential order between the CPUs entering the machine
|
||||||
* check handler.
|
* check handler.
|
||||||
*/
|
*/
|
||||||
int order;
|
int order = -1;
|
||||||
/*
|
/*
|
||||||
* If no_way_out gets set, there is no safe way to recover from this
|
* If no_way_out gets set, there is no safe way to recover from this
|
||||||
* MCE. If mca_cfg.tolerant is cranked up, we'll try anyway.
|
* MCE. If mca_cfg.tolerant is cranked up, we'll try anyway.
|
||||||
|
@ -1056,7 +1057,12 @@ void do_machine_check(struct pt_regs *regs, long error_code)
|
||||||
DECLARE_BITMAP(toclear, MAX_NR_BANKS);
|
DECLARE_BITMAP(toclear, MAX_NR_BANKS);
|
||||||
DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
|
DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
|
||||||
char *msg = "Unknown";
|
char *msg = "Unknown";
|
||||||
int lmce = 0;
|
|
||||||
|
/*
|
||||||
|
* MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
|
||||||
|
* on Intel.
|
||||||
|
*/
|
||||||
|
int lmce = 1;
|
||||||
|
|
||||||
/* If this CPU is offline, just bail out. */
|
/* If this CPU is offline, just bail out. */
|
||||||
if (cpu_is_offline(smp_processor_id())) {
|
if (cpu_is_offline(smp_processor_id())) {
|
||||||
|
@ -1095,19 +1101,20 @@ void do_machine_check(struct pt_regs *regs, long error_code)
|
||||||
kill_it = 1;
|
kill_it = 1;
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Check if this MCE is signaled to only this logical processor
|
* Check if this MCE is signaled to only this logical processor,
|
||||||
|
* on Intel only.
|
||||||
*/
|
*/
|
||||||
if (m.mcgstatus & MCG_STATUS_LMCES)
|
if (m.cpuvendor == X86_VENDOR_INTEL)
|
||||||
lmce = 1;
|
lmce = m.mcgstatus & MCG_STATUS_LMCES;
|
||||||
else {
|
|
||||||
/*
|
/*
|
||||||
* Go through all the banks in exclusion of the other CPUs.
|
* Go through all banks in exclusion of the other CPUs. This way we
|
||||||
* This way we don't report duplicated events on shared banks
|
* don't report duplicated events on shared banks because the first one
|
||||||
* because the first one to see it will clear it.
|
* to see it will clear it. If this is a Local MCE, then no need to
|
||||||
* If this is a Local MCE, then no need to perform rendezvous.
|
* perform rendezvous.
|
||||||
*/
|
*/
|
||||||
|
if (!lmce)
|
||||||
order = mce_start(&no_way_out);
|
order = mce_start(&no_way_out);
|
||||||
}
|
|
||||||
|
|
||||||
for (i = 0; i < cfg->banks; i++) {
|
for (i = 0; i < cfg->banks; i++) {
|
||||||
__clear_bit(i, toclear);
|
__clear_bit(i, toclear);
|
||||||
|
|
Загрузка…
Ссылка в новой задаче