| From fead35c68926682c90c995f22b48f1c8d78865c1 Mon Sep 17 00:00:00 2001 |
| From: Yazen Ghannam <Yazen.Ghannam@amd.com> |
| Date: Sat, 30 Apr 2016 14:33:57 +0200 |
| Subject: x86/mce: Detect local MCEs properly |
| |
| From: Yazen Ghannam <Yazen.Ghannam@amd.com> |
| |
| commit fead35c68926682c90c995f22b48f1c8d78865c1 upstream. |
| |
| 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> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
| |
| --- |
| arch/x86/kernel/cpu/mcheck/mce.c | 33 ++++++++++++++++++++------------- |
| 1 file changed, 20 insertions(+), 13 deletions(-) |
| |
| --- a/arch/x86/kernel/cpu/mcheck/mce.c |
| +++ b/arch/x86/kernel/cpu/mcheck/mce.c |
| @@ -980,11 +980,12 @@ void do_machine_check(struct pt_regs *re |
| int i; |
| int worst = 0; |
| int severity; |
| + |
| /* |
| * Establish sequential order between the CPUs entering the machine |
| * check handler. |
| */ |
| - int order; |
| + int order = -1; |
| /* |
| * 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. |
| @@ -1000,7 +1001,12 @@ void do_machine_check(struct pt_regs *re |
| char *msg = "Unknown"; |
| u64 recover_paddr = ~0ull; |
| int flags = MF_ACTION_REQUIRED; |
| - 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 (cpu_is_offline(smp_processor_id())) { |
| @@ -1039,19 +1045,20 @@ void do_machine_check(struct pt_regs *re |
| 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) |
| - lmce = 1; |
| - else { |
| - /* |
| - * Go through all the banks in exclusion of the other CPUs. |
| - * This way we don't report duplicated events on shared banks |
| - * because the first one to see it will clear it. |
| - * If this is a Local MCE, then no need to perform rendezvous. |
| - */ |
| + if (m.cpuvendor == X86_VENDOR_INTEL) |
| + lmce = m.mcgstatus & MCG_STATUS_LMCES; |
| + |
| + /* |
| + * Go through all banks in exclusion of the other CPUs. This way we |
| + * don't report duplicated events on shared banks because the first one |
| + * to see it will clear it. If this is a Local MCE, then no need to |
| + * perform rendezvous. |
| + */ |
| + if (!lmce) |
| order = mce_start(&no_way_out); |
| - } |
| |
| for (i = 0; i < cfg->banks; i++) { |
| __clear_bit(i, toclear); |