5 files changed, 326 insertions, 44 deletions

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 6ea7fdc82f3c..5167bd2bb6b1 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -583,7 +583,7 @@ bool amd_filter_mce(struct mce *m)
  * - Prevent possible spurious interrupts from the IF bank on Family 0x17
  *   Models 0x10-0x2F due to Erratum #1114.
  */
-void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
+static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 {
 	int i, num_msrs;
 	u64 hwcr;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 743370ee4983..5f42f25bac8f 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -488,8 +488,9 @@ int mce_usable_address(struct mce *m)
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
-	/* Checks after this one are Intel-specific: */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	/* Checks after this one are Intel/Zhaoxin-specific: */
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 1;
 
 	if (!(m->status & MCI_STATUS_MISCV))
@@ -507,10 +508,13 @@ EXPORT_SYMBOL_GPL(mce_usable_address);
 
 bool mce_is_memory_error(struct mce *m)
 {
-	if (m->cpuvendor == X86_VENDOR_AMD ||
-	    m->cpuvendor == X86_VENDOR_HYGON) {
+	switch (m->cpuvendor) {
+	case X86_VENDOR_AMD:
+	case X86_VENDOR_HYGON:
 		return amd_mce_is_memory_error(m);
-	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
+
+	case X86_VENDOR_INTEL:
+	case X86_VENDOR_ZHAOXIN:
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
 		 *
@@ -527,9 +531,10 @@ bool mce_is_memory_error(struct mce *m)
 		return (m->status & 0xef80) == BIT(7) ||
 		       (m->status & 0xef00) == BIT(8) ||
 		       (m->status & 0xeffc) == 0xc;
-	}
 
-	return false;
+	default:
+		return false;
+	}
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
@@ -1127,6 +1132,12 @@ static bool __mc_check_crashing_cpu(int cpu)
 		u64 mcgstatus;
 
 		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+
+		if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) {
+			if (mcgstatus & MCG_STATUS_LMCES)
+				return false;
+		}
+
 		if (mcgstatus & MCG_STATUS_RIPV) {
 			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
 			return true;
@@ -1277,9 +1288,10 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	/*
 	 * Check if this MCE is signaled to only this logical processor,
-	 * on Intel only.
+	 * on Intel, Zhaoxin only.
 	 */
-	if (m.cpuvendor == X86_VENDOR_INTEL)
+	if (m.cpuvendor == X86_VENDOR_INTEL ||
+	    m.cpuvendor == X86_VENDOR_ZHAOXIN)
 		lmce = m.mcgstatus & MCG_STATUS_LMCES;
 
 	/*
@@ -1697,6 +1709,18 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		if (c->x86 == 6 && c->x86_model == 45)
 			quirk_no_way_out = quirk_sandybridge_ifu;
 	}
+
+	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+		/*
+		 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+		 * synchronization with a one second timeout.
+		 */
+		if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+			if (cfg->monarch_timeout < 0)
+				cfg->monarch_timeout = USEC_PER_SEC;
+		}
+	}
+
 	if (cfg->monarch_timeout < 0)
 		cfg->monarch_timeout = 0;
 	if (cfg->bootlog != 0)
@@ -1760,6 +1784,35 @@ static void mce_centaur_feature_init(struct cpuinfo_x86 *c)
 	}
 }
 
+static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c)
+{
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+
+	/*
+	 * These CPUs have MCA bank 8 which reports only one error type called
+	 * SVAD (System View Address Decoder). The reporting of that error is
+	 * controlled by IA32_MC8.CTL.0.
+	 *
+	 * If enabled, prefetching on these CPUs will cause SVAD MCE when
+	 * virtual machines start and result in a system  panic. Always disable
+	 * bank 8 SVAD error by default.
+	 */
+	if ((c->x86 == 7 && c->x86_model == 0x1b) ||
+	    (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+		if (this_cpu_read(mce_num_banks) > 8)
+			mce_banks[8].ctl = 0;
+	}
+
+	intel_init_cmci();
+	intel_init_lmce();
+	mce_adjust_timer = cmci_intel_adjust_timer;
+}
+
+static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c)
+{
+	intel_clear_lmce();
+}
+
 static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 {
 	switch (c->x86_vendor) {
@@ -1781,6 +1834,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_centaur_feature_init(c);
 		break;
 
+	case X86_VENDOR_ZHAOXIN:
+		mce_zhaoxin_feature_init(c);
+		break;
+
 	default:
 		break;
 	}
@@ -1792,6 +1849,11 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
 	case X86_VENDOR_INTEL:
 		mce_intel_feature_clear(c);
 		break;
+
+	case X86_VENDOR_ZHAOXIN:
+		mce_zhaoxin_feature_clear(c);
+		break;
+
 	default:
 		break;
 	}
@@ -2014,15 +2076,16 @@ static void mce_disable_error_reporting(void)
 static void vendor_disable_error_reporting(void)
 {
 	/*
-	 * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs
-	 * are socket-wide.
-	 * Disabling them for just a single offlined CPU is bad, since it will
-	 * inhibit reporting for all shared resources on the socket like the
-	 * last level cache (LLC), the integrated memory controller (iMC), etc.
+	 * Don't clear on Intel or AMD or Hygon or Zhaoxin CPUs. Some of these
+	 * MSRs are socket-wide. Disabling them for just a single offlined CPU
+	 * is bad, since it will inhibit reporting for all shared resources on
+	 * the socket like the last level cache (LLC), the integrated memory
+	 * controller (iMC), etc.
 	 */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN)
 		return;
 
 	mce_disable_error_reporting();
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 88cd9598fa57..e270d0770134 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -85,8 +85,10 @@ static int cmci_supported(int *banks)
 	 * initialization is vendor keyed and this
 	 * makes sure none of the backdoors are entered otherwise.
 	 */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
 		return 0;
+
 	if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
 		return 0;
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
@@ -423,7 +425,7 @@ void cmci_disable_bank(int bank)
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
-static void intel_init_cmci(void)
+void intel_init_cmci(void)
 {
 	int banks;
 
@@ -442,7 +444,7 @@ static void intel_init_cmci(void)
 	cmci_recheck();
 }
 
-static void intel_init_lmce(void)
+void intel_init_lmce(void)
 {
 	u64 val;
 
@@ -455,7 +457,7 @@ static void intel_init_lmce(void)
 		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
 }
 
-static void intel_clear_lmce(void)
+void intel_clear_lmce(void)
 {
 	u64 val;
 
@@ -482,6 +484,7 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
 	case INTEL_FAM6_BROADWELL_D:
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_ICELAKE_X:
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
 
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 43031db429d2..842b273bce31 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -45,11 +45,17 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval);
 bool mce_intel_cmci_poll(void);
 void mce_intel_hcpu_update(unsigned long cpu);
 void cmci_disable_bank(int bank);
+void intel_init_cmci(void);
+void intel_init_lmce(void);
+void intel_clear_lmce(void);
 #else
 # define cmci_intel_adjust_timer mce_adjust_timer_default
 static inline bool mce_intel_cmci_poll(void) { return false; }
 static inline void mce_intel_hcpu_update(unsigned long cpu) { }
 static inline void cmci_disable_bank(int bank) { }
+static inline void intel_init_cmci(void) { }
+static inline void intel_init_lmce(void) { }
+static inline void intel_clear_lmce(void) { }
 #endif
 
 void mce_timer_kick(unsigned long interval);
diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c
index 6e2becf547c5..b38010b541d6 100644
--- a/arch/x86/kernel/cpu/mce/therm_throt.c
+++ b/arch/x86/kernel/cpu/mce/therm_throt.c
@@ -40,15 +40,58 @@
 #define THERMAL_THROTTLING_EVENT	0
 #define POWER_LIMIT_EVENT		1
 
-/*
- * Current thermal event state:
+/**
+ * struct _thermal_state - Represent the current thermal event state
+ * @next_check:			Stores the next timestamp, when it is allowed
+ *				to log the next warning message.
+ * @last_interrupt_time:	Stores the timestamp for the last threshold
+ *				high event.
+ * @therm_work:			Delayed workqueue structure
+ * @count:			Stores the current running count for thermal
+ *				or power threshold interrupts.
+ * @last_count:			Stores the previous running count for thermal
+ *				or power threshold interrupts.
+ * @max_time_ms:		This shows the maximum amount of time CPU was
+ *				in throttled state for a single thermal
+ *				threshold high to low state.
+ * @total_time_ms:		This is a cumulative time during which CPU was
+ *				in the throttled state.
+ * @rate_control_active:	Set when a throttling message is logged.
+ *				This is used for the purpose of rate-control.
+ * @new_event:			Stores the last high/low status of the
+ *				THERM_STATUS_PROCHOT or
+ *				THERM_STATUS_POWER_LIMIT.
+ * @level:			Stores whether this _thermal_state instance is
+ *				for a CORE level or for PACKAGE level.
+ * @sample_index:		Index for storing the next sample in the buffer
+ *				temp_samples[].
+ * @sample_count:		Total number of samples collected in the buffer
+ *				temp_samples[].
+ * @average:			The last moving average of temperature samples
+ * @baseline_temp:		Temperature at which thermal threshold high
+ *				interrupt was generated.
+ * @temp_samples:		Storage for temperature samples to calculate
+ *				moving average.
+ *
+ * This structure is used to represent data related to thermal state for a CPU.
+ * There is a separate storage for core and package level for each CPU.
  */
 struct _thermal_state {
-	bool			new_event;
-	int			event;
 	u64			next_check;
+	u64			last_interrupt_time;
+	struct delayed_work	therm_work;
 	unsigned long		count;
 	unsigned long		last_count;
+	unsigned long		max_time_ms;
+	unsigned long		total_time_ms;
+	bool			rate_control_active;
+	bool			new_event;
+	u8			level;
+	u8			sample_index;
+	u8			sample_count;
+	u8			average;
+	u8			baseline_temp;
+	u8			temp_samples[3];
 };
 
 struct thermal_state {
@@ -121,8 +164,22 @@ define_therm_throt_device_one_ro(package_throttle_count);
 define_therm_throt_device_show_func(package_power_limit, count);
 define_therm_throt_device_one_ro(package_power_limit_count);
 
+define_therm_throt_device_show_func(core_throttle, max_time_ms);
+define_therm_throt_device_one_ro(core_throttle_max_time_ms);
+
+define_therm_throt_device_show_func(package_throttle, max_time_ms);
+define_therm_throt_device_one_ro(package_throttle_max_time_ms);
+
+define_therm_throt_device_show_func(core_throttle, total_time_ms);
+define_therm_throt_device_one_ro(core_throttle_total_time_ms);
+
+define_therm_throt_device_show_func(package_throttle, total_time_ms);
+define_therm_throt_device_one_ro(package_throttle_total_time_ms);
+
 static struct attribute *thermal_throttle_attrs[] = {
 	&dev_attr_core_throttle_count.attr,
+	&dev_attr_core_throttle_max_time_ms.attr,
+	&dev_attr_core_throttle_total_time_ms.attr,
 	NULL
 };
 
@@ -135,6 +192,112 @@ static const struct attribute_group thermal_attr_group = {
 #define CORE_LEVEL	0
 #define PACKAGE_LEVEL	1
 
+#define THERM_THROT_POLL_INTERVAL	HZ
+#define THERM_STATUS_PROCHOT_LOG	BIT(1)
+
+#define THERM_STATUS_CLEAR_CORE_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11) | BIT(13) | BIT(15))
+#define THERM_STATUS_CLEAR_PKG_MASK  (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11))
+
+static void clear_therm_status_log(int level)
+{
+	int msr;
+	u64 mask, msr_val;
+
+	if (level == CORE_LEVEL) {
+		msr  = MSR_IA32_THERM_STATUS;
+		mask = THERM_STATUS_CLEAR_CORE_MASK;
+	} else {
+		msr  = MSR_IA32_PACKAGE_THERM_STATUS;
+		mask = THERM_STATUS_CLEAR_PKG_MASK;
+	}
+
+	rdmsrl(msr, msr_val);
+	msr_val &= mask;
+	wrmsrl(msr, msr_val & ~THERM_STATUS_PROCHOT_LOG);
+}
+
+static void get_therm_status(int level, bool *proc_hot, u8 *temp)
+{
+	int msr;
+	u64 msr_val;
+
+	if (level == CORE_LEVEL)
+		msr = MSR_IA32_THERM_STATUS;
+	else
+		msr = MSR_IA32_PACKAGE_THERM_STATUS;
+
+	rdmsrl(msr, msr_val);
+	if (msr_val & THERM_STATUS_PROCHOT_LOG)
+		*proc_hot = true;
+	else
+		*proc_hot = false;
+
+	*temp = (msr_val >> 16) & 0x7F;
+}
+
+static void throttle_active_work(struct work_struct *work)
+{
+	struct _thermal_state *state = container_of(to_delayed_work(work),
+						struct _thermal_state, therm_work);
+	unsigned int i, avg, this_cpu = smp_processor_id();
+	u64 now = get_jiffies_64();
+	bool hot;
+	u8 temp;
+
+	get_therm_status(state->level, &hot, &temp);
+	/* temperature value is offset from the max so lesser means hotter */
+	if (!hot && temp > state->baseline_temp) {
+		if (state->rate_control_active)
+			pr_info("CPU%d: %s temperature/speed normal (total events = %lu)\n",
+				this_cpu,
+				state->level == CORE_LEVEL ? "Core" : "Package",
+				state->count);
+
+		state->rate_control_active = false;
+		return;
+	}
+
+	if (time_before64(now, state->next_check) &&
+			  state->rate_control_active)
+		goto re_arm;
+
+	state->next_check = now + CHECK_INTERVAL;
+
+	if (state->count != state->last_count) {
+		/* There was one new thermal interrupt */
+		state->last_count = state->count;
+		state->average = 0;
+		state->sample_count = 0;
+		state->sample_index = 0;
+	}
+
+	state->temp_samples[state->sample_index] = temp;
+	state->sample_count++;
+	state->sample_index = (state->sample_index + 1) % ARRAY_SIZE(state->temp_samples);
+	if (state->sample_count < ARRAY_SIZE(state->temp_samples))
+		goto re_arm;
+
+	avg = 0;
+	for (i = 0; i < ARRAY_SIZE(state->temp_samples); ++i)
+		avg += state->temp_samples[i];
+
+	avg /= ARRAY_SIZE(state->temp_samples);
+
+	if (state->average > avg) {
+		pr_warn("CPU%d: %s temperature is above threshold, cpu clock is throttled (total events = %lu)\n",
+			this_cpu,
+			state->level == CORE_LEVEL ? "Core" : "Package",
+			state->count);
+		state->rate_control_active = true;
+	}
+
+	state->average = avg;
+
+re_arm:
+	clear_therm_status_log(state->level);
+	schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL);
+}
+
 /***
  * therm_throt_process - Process thermal throttling event from interrupt
  * @curr: Whether the condition is current or not (boolean), since the
@@ -178,27 +341,33 @@ static void therm_throt_process(bool new_event, int event, int level)
 	if (new_event)
 		state->count++;
 
-	if (time_before64(now, state->next_check) &&
-			state->count != state->last_count)
+	if (event != THERMAL_THROTTLING_EVENT)
 		return;
 
-	state->next_check = now + CHECK_INTERVAL;
-	state->last_count = state->count;
+	if (new_event && !state->last_interrupt_time) {
+		bool hot;
+		u8 temp;
+
+		get_therm_status(state->level, &hot, &temp);
+		/*
+		 * Ignore short temperature spike as the system is not close
+		 * to PROCHOT. 10C offset is large enough to ignore. It is
+		 * already dropped from the high threshold temperature.
+		 */
+		if (temp > 10)
+			return;
 
-	/* if we just entered the thermal event */
-	if (new_event) {
-		if (event == THERMAL_THROTTLING_EVENT)
-			pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
-				this_cpu,
-				level == CORE_LEVEL ? "Core" : "Package",
-				state->count);
-		return;
-	}
-	if (old_event) {
-		if (event == THERMAL_THROTTLING_EVENT)
-			pr_info("CPU%d: %s temperature/speed normal\n", this_cpu,
-				level == CORE_LEVEL ? "Core" : "Package");
-		return;
+		state->baseline_temp = temp;
+		state->last_interrupt_time = now;
+		schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL);
+	} else if (old_event && state->last_interrupt_time) {
+		unsigned long throttle_time;
+
+		throttle_time = jiffies_delta_to_msecs(now - state->last_interrupt_time);
+		if (throttle_time > state->max_time_ms)
+			state->max_time_ms = throttle_time;
+		state->total_time_ms += throttle_time;
+		state->last_interrupt_time = 0;
 	}
 }
 
@@ -244,20 +413,47 @@ static int thermal_throttle_add_dev(struct device *dev, unsigned int cpu)
 	if (err)
 		return err;
 
-	if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable)
+	if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) {
 		err = sysfs_add_file_to_group(&dev->kobj,
 					      &dev_attr_core_power_limit_count.attr,
 					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+	}
+
 	if (cpu_has(c, X86_FEATURE_PTS)) {
 		err = sysfs_add_file_to_group(&dev->kobj,
 					      &dev_attr_package_throttle_count.attr,
 					      thermal_attr_group.name);
-		if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable)
+		if (err)
+			goto del_group;
+
+		err = sysfs_add_file_to_group(&dev->kobj,
+					      &dev_attr_package_throttle_max_time_ms.attr,
+					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+
+		err = sysfs_add_file_to_group(&dev->kobj,
+					      &dev_attr_package_throttle_total_time_ms.attr,
+					      thermal_attr_group.name);
+		if (err)
+			goto del_group;
+
+		if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) {
 			err = sysfs_add_file_to_group(&dev->kobj,
 					&dev_attr_package_power_limit_count.attr,
 					thermal_attr_group.name);
+			if (err)
+				goto del_group;
+		}
 	}
 
+	return 0;
+
+del_group:
+	sysfs_remove_group(&dev->kobj, &thermal_attr_group);
+
 	return err;
 }
 
@@ -269,15 +465,29 @@ static void thermal_throttle_remove_dev(struct device *dev)
 /* Get notified when a cpu comes on/off. Be hotplug friendly. */
 static int thermal_throttle_online(unsigned int cpu)
 {
+	struct thermal_state *state = &per_cpu(thermal_state, cpu);
 	struct device *dev = get_cpu_device(cpu);
 
+	state->package_throttle.level = PACKAGE_LEVEL;
+	state->core_throttle.level = CORE_LEVEL;
+
+	INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work);
+	INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work);
+
 	return thermal_throttle_add_dev(dev, cpu);
 }
 
 static int thermal_throttle_offline(unsigned int cpu)
 {
+	struct thermal_state *state = &per_cpu(thermal_state, cpu);
 	struct device *dev = get_cpu_device(cpu);
 
+	cancel_delayed_work(&state->package_throttle.therm_work);
+	cancel_delayed_work(&state->core_throttle.therm_work);
+
+	state->package_throttle.rate_control_active = false;
+	state->core_throttle.rate_control_active = false;
+
 	thermal_throttle_remove_dev(dev);
 	return 0;
 }