diff options
Diffstat (limited to 'arch/x86/kernel/cpu/mcheck/mce_intel.c')
-rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce_intel.c | 63 |
1 files changed, 42 insertions, 21 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index b3c97bafc123..b4a41cf030ed 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -39,6 +39,15 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); /* + * CMCI storm detection backoff counter + * + * During storm, we reset this counter to INITIAL_CHECK_INTERVAL in case we've + * encountered an error. If not, we decrement it by one. We signal the end of + * the CMCI storm when it reaches 0. + */ +static DEFINE_PER_CPU(int, cmci_backoff_cnt); + +/* * cmci_discover_lock protects against parallel discovery attempts * which could race against each other. */ @@ -46,7 +55,7 @@ static DEFINE_RAW_SPINLOCK(cmci_discover_lock); #define CMCI_THRESHOLD 1 #define CMCI_POLL_INTERVAL (30 * HZ) -#define CMCI_STORM_INTERVAL (1 * HZ) +#define CMCI_STORM_INTERVAL (HZ) #define CMCI_STORM_THRESHOLD 15 static DEFINE_PER_CPU(unsigned long, cmci_time_stamp); @@ -82,11 +91,21 @@ static int cmci_supported(int *banks) return !!(cap & MCG_CMCI_P); } -void mce_intel_cmci_poll(void) +bool mce_intel_cmci_poll(void) { if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) - return; - machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); + return false; + + /* + * Reset the counter if we've logged an error in the last poll + * during the storm. + */ + if (machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned))) + this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); + else + this_cpu_dec(cmci_backoff_cnt); + + return true; } void mce_intel_hcpu_update(unsigned long cpu) @@ -97,31 +116,32 @@ void mce_intel_hcpu_update(unsigned long cpu) per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; } -unsigned long mce_intel_adjust_timer(unsigned long interval) +unsigned long cmci_intel_adjust_timer(unsigned long interval) { - int r; - - if (interval < CMCI_POLL_INTERVAL) - return interval; + if ((this_cpu_read(cmci_backoff_cnt) > 0) && + (__this_cpu_read(cmci_storm_state) == CMCI_STORM_ACTIVE)) { + mce_notify_irq(); + return CMCI_STORM_INTERVAL; + } switch (__this_cpu_read(cmci_storm_state)) { case CMCI_STORM_ACTIVE: + /* * We switch back to interrupt mode once the poll timer has - * silenced itself. That means no events recorded and the - * timer interval is back to our poll interval. + * silenced itself. That means no events recorded and the timer + * interval is back to our poll interval. */ __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED); - r = atomic_sub_return(1, &cmci_storm_on_cpus); - if (r == 0) + if (!atomic_sub_return(1, &cmci_storm_on_cpus)) pr_notice("CMCI storm subsided: switching to interrupt mode\n"); + /* FALLTHROUGH */ case CMCI_STORM_SUBSIDED: /* - * We wait for all cpus to go back to SUBSIDED - * state. When that happens we switch back to - * interrupt mode. + * We wait for all CPUs to go back to SUBSIDED state. When that + * happens we switch back to interrupt mode. */ if (!atomic_read(&cmci_storm_on_cpus)) { __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); @@ -130,10 +150,8 @@ unsigned long mce_intel_adjust_timer(unsigned long interval) } return CMCI_POLL_INTERVAL; default: - /* - * We have shiny weather. Let the poll do whatever it - * thinks. - */ + + /* We have shiny weather. Let the poll do whatever it thinks. */ return interval; } } @@ -178,7 +196,8 @@ static bool cmci_storm_detect(void) cmci_storm_disable_banks(); __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); r = atomic_add_return(1, &cmci_storm_on_cpus); - mce_timer_kick(CMCI_POLL_INTERVAL); + 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"); @@ -195,6 +214,7 @@ static void intel_threshold_interrupt(void) { if (cmci_storm_detect()) return; + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); mce_notify_irq(); } @@ -286,6 +306,7 @@ void cmci_recheck(void) if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks)) return; + local_irq_save(flags); machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); local_irq_restore(flags); |