RAS（三）IntelMCA-CMCI

C++
arch/x86/kernel/cpu/mce/intel.c
void intel_init_cmci(void)
{
        int banks;

        if (!cmci_supported(&banks))
                return;

        mce_threshold_vector = intel_threshold_interrupt;
        cmci_discover(banks);
        /*
         * For CPU #0 this runs with still disabled APIC, but that's
         * ok because only the vector is set up. We still do another
         * check for the banks later for CPU #0 just to make sure
         * to not miss any events.
         */
        apic_write(APIC_LVTCMCI, THRESHOLD_APIC_VECTOR|APIC_DM_FIXED);
        cmci_recheck();
}

C++
                rdmsrl(MSR_IA32_MCx_CTL2(i), val);
                ...
                
                val |= MCI_CTL2_CMCI_EN;
                wrmsrl(MSR_IA32_MCx_CTL2(i), val);
                rdmsrl(MSR_IA32_MCx_CTL2(i), val);

C++
#define CMCI_THRESHOLD          1

                if (!mca_cfg.bios_cmci_threshold) {
                        val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
                        val |= CMCI_THRESHOLD;
                } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) {
                        /*
                         * If bios_cmci_threshold boot option was specified
                         * but the threshold is zero, we'll try to initialize
                         * it to 1.
                         */
                        bios_zero_thresh = 1;
                        val |= CMCI_THRESHOLD;
                }

C++
/*
 * The interrupt handler. This is called on every event.
 * Just call the poller directly to log any events.
 * This could in theory increase the threshold under high load,
 * but doesn't for now.
 */
static void intel_threshold_interrupt(void)
{
        if (cmci_storm_detect())
                return;

        machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
}

C++
static bool cmci_storm_detect(void)
{
        unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
        unsigned long ts = __this_cpu_read(cmci_time_stamp);
        unsigned long now = jiffies;
        int r;

        if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE)
                return true;

        if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) {
                cnt++;
        } else {
                cnt = 1;
                __this_cpu_write(cmci_time_stamp, now);
        }
        __this_cpu_write(cmci_storm_cnt, cnt);

        if (cnt <= CMCI_STORM_THRESHOLD)
                return false;

        cmci_toggle_interrupt_mode(false);
        __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
        r = atomic_add_return(1, &cmci_storm_on_cpus);
        mce_timer_kick(CMCI_STORM_INTERVAL);
        this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL);

        if (r == 1)
                pr_notice("CMCI storm detected: switching to poll mode\n");
        return true;
}

C++
enum mcp_flags {
        MCP_TIMESTAMP   = BIT(0),       /* log time stamp */
        MCP_UC          = BIT(1),       /* log uncorrected errors */
        MCP_DONTLOG     = BIT(2),       /* only clear, don't log */
};

C++
bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{
        if (flags & MCP_TIMESTAMP)
                m.tsc = rdtsc(); // 记录当前TSC

/*CE Error记录*/
                /* If this entry is not valid, ignore it */
                if (!(m.status & MCI_STATUS_VAL))
                        continue;

                /*
                 * 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 & MCI_STATUS_UC))
                        goto log_it;
/*UCNA Error记录*/
                /*
                 * 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;
/*通过mce_log记录故障信息*/
log_it:         
                /*
                 * Don't get the IP here because it's unlikely to
                 * have anything to do with the actual error location.
                 */
                if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce)
                        mce_log(&m);
                else if (mce_usable_address(&m)) {
                        /*
                         * Although we skipped logging this, we still want
                         * to take action. Add to the pool so the registered
                         * notifiers will see it.
                         */
                        if (!mce_gen_pool_add(&m))
                                mce_schedule_work();
                }
        }