summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/mcheck/mce.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu/mcheck/mce.c')
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c80
1 files changed, 41 insertions, 39 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 25310d2b8609..07188a012492 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -139,6 +139,8 @@ void mce_setup(struct mce *m)
m->socketid = cpu_data(m->extcpu).phys_proc_id;
m->apicid = cpu_data(m->extcpu).initial_apicid;
rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);
+
+ m->microcode = boot_cpu_data.microcode;
}
DEFINE_PER_CPU(struct mce, injectm);
@@ -309,7 +311,7 @@ static void print_mce(struct mce *m)
*/
pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n",
m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
- cpu_data(m->extcpu).microcode);
+ m->microcode);
pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}
@@ -671,20 +673,50 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
barrier();
m.status = mce_rdmsrl(msr_ops.status(i));
+
+ /* If this entry is not valid, ignore it */
if (!(m.status & MCI_STATUS_VAL))
continue;
/*
- * Uncorrected or signalled events are handled by the exception
- * handler when it is enabled, so don't process those here.
- *
- * TBD do the same check for MCI_STATUS_EN here?
+ * If we are logging everything (at CPU online) or this
+ * is a corrected error, then we must log it.
*/
- if (!(flags & MCP_UC) &&
- (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
- continue;
+ if ((flags & MCP_UC) || !(m.status & MCI_STATUS_UC))
+ goto log_it;
+
+ /*
+ * Newer Intel systems that support software error
+ * recovery need to make additional checks. Other
+ * CPUs should skip over uncorrected errors, but log
+ * everything else.
+ */
+ if (!mca_cfg.ser) {
+ if (m.status & MCI_STATUS_UC)
+ continue;
+ goto log_it;
+ }
+
+ /* Log "not enabled" (speculative) errors */
+ if (!(m.status & MCI_STATUS_EN))
+ goto log_it;
+ /*
+ * Log UCNA (SDM: 15.6.3 "UCR Error Classification")
+ * UC == 1 && PCC == 0 && S == 0
+ */
+ if (!(m.status & MCI_STATUS_PCC) && !(m.status & MCI_STATUS_S))
+ goto log_it;
+
+ /*
+ * Skip anything else. Presumption is that our read of this
+ * bank is racing with a machine check. Leave the log alone
+ * for do_machine_check() to deal with it.
+ */
+ continue;
+
+log_it:
error_seen = true;
mce_read_aux(&m, i);
@@ -750,8 +782,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
if (quirk_no_way_out)
quirk_no_way_out(i, m, regs);
+ m->bank = i;
if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
- m->bank = i;
mce_read_aux(m, i);
*msg = tmp;
return 1;
@@ -1616,36 +1648,6 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
if (c->x86 == 0x15 && c->x86_model <= 0xf)
mce_flags.overflow_recov = 1;
- /*
- * Turn off MC4_MISC thresholding banks on those models since
- * they're not supported there.
- */
- if (c->x86 == 0x15 &&
- (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) {
- int i;
- u64 hwcr;
- bool need_toggle;
- u32 msrs[] = {
- 0x00000413, /* MC4_MISC0 */
- 0xc0000408, /* MC4_MISC1 */
- };
-
- rdmsrl(MSR_K7_HWCR, hwcr);
-
- /* McStatusWrEn has to be set */
- need_toggle = !(hwcr & BIT(18));
-
- if (need_toggle)
- wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
-
- /* Clear CntP bit safely */
- for (i = 0; i < ARRAY_SIZE(msrs); i++)
- msr_clear_bit(msrs[i], 62);
-
- /* restore old settings */
- if (need_toggle)
- wrmsrl(MSR_K7_HWCR, hwcr);
- }
}
if (c->x86_vendor == X86_VENDOR_INTEL) {