Merge branch 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

* 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: add IRQ context simulation in module mce-inject
  x86, mce, therm_throt: Don't report power limit and package level thermal throttle events in mcelog
  x86, MCE: Drain mcelog buffer
  x86, mce: Add wrappers for registering on the decode chain

3 files changed, 94 insertions, 33 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 319882e..fc4beb3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/fs.h>
+#include <linux/preempt.h>
 #include <linux/smp.h>
 #include <linux/notifier.h>
 #include <linux/kdebug.h>
@@ -92,6 +93,18 @@ static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
 	return NMI_HANDLED;
 }
 
+static void mce_irq_ipi(void *info)
+{
+	int cpu = smp_processor_id();
+	struct mce *m = &__get_cpu_var(injectm);
+
+	if (cpumask_test_cpu(cpu, mce_inject_cpumask) &&
+			m->inject_flags & MCJ_EXCEPTION) {
+		cpumask_clear_cpu(cpu, mce_inject_cpumask);
+		raise_exception(m, NULL);
+	}
+}
+
 /* Inject mce on current CPU */
 static int raise_local(void)
 {
@@ -139,9 +152,10 @@ static void raise_mce(struct mce *m)
 		return;
 
 #ifdef CONFIG_X86_LOCAL_APIC
-	if (m->inject_flags & MCJ_NMI_BROADCAST) {
+	if (m->inject_flags & (MCJ_IRQ_BRAODCAST | MCJ_NMI_BROADCAST)) {
 		unsigned long start;
 		int cpu;
+
 		get_online_cpus();
 		cpumask_copy(mce_inject_cpumask, cpu_online_mask);
 		cpumask_clear_cpu(get_cpu(), mce_inject_cpumask);
@@ -151,13 +165,25 @@ static void raise_mce(struct mce *m)
 			    MCJ_CTX(mcpu->inject_flags) != MCJ_CTX_RANDOM)
 				cpumask_clear_cpu(cpu, mce_inject_cpumask);
 		}
-		if (!cpumask_empty(mce_inject_cpumask))
-			apic->send_IPI_mask(mce_inject_cpumask, NMI_VECTOR);
+		if (!cpumask_empty(mce_inject_cpumask)) {
+			if (m->inject_flags & MCJ_IRQ_BRAODCAST) {
+				/*
+				 * don't wait because mce_irq_ipi is necessary
+				 * to be sync with following raise_local
+				 */
+				preempt_disable();
+				smp_call_function_many(mce_inject_cpumask,
+					mce_irq_ipi, NULL, 0);
+				preempt_enable();
+			} else if (m->inject_flags & MCJ_NMI_BROADCAST)
+				apic->send_IPI_mask(mce_inject_cpumask,
+						NMI_VECTOR);
+		}
 		start = jiffies;
 		while (!cpumask_empty(mce_inject_cpumask)) {
 			if (!time_before(jiffies, start + 2*HZ)) {
 				printk(KERN_ERR
-				"Timeout waiting for mce inject NMI %lx\n",
+				"Timeout waiting for mce inject %lx\n",
 					*cpumask_bits(mce_inject_cpumask));
 				break;
 			}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index e9c9d0a..cbe82b5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -95,13 +95,6 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int			cpu_missing;
 
-/*
- * CPU/chipset specific EDAC code can register a notifier call here to print
- * MCE errors in a human-readable form.
- */
-ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
-EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
-
 /* MCA banks polled by the period polling timer for corrected events */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
 	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
@@ -109,6 +102,12 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
 
 static DEFINE_PER_CPU(struct work_struct, mce_work);
 
+/*
+ * CPU/chipset specific EDAC code can register a notifier call here to print
+ * MCE errors in a human-readable form.
+ */
+ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+
 /* Do initial initialization of a struct mce */
 void mce_setup(struct mce *m)
 {
@@ -188,6 +187,57 @@ void mce_log(struct mce *mce)
 	set_bit(0, &mce_need_notify);
 }
 
+static void drain_mcelog_buffer(void)
+{
+	unsigned int next, i, prev = 0;
+
+	next = rcu_dereference_check_mce(mcelog.next);
+
+	do {
+		struct mce *m;
+
+		/* drain what was logged during boot */
+		for (i = prev; i < next; i++) {
+			unsigned long start = jiffies;
+			unsigned retries = 1;
+
+			m = &mcelog.entry[i];
+
+			while (!m->finished) {
+				if (time_after_eq(jiffies, start + 2*retries))
+					retries++;
+
+				cpu_relax();
+
+				if (!m->finished && retries >= 4) {
+					pr_err("MCE: skipping error being logged currently!\n");
+					break;
+				}
+			}
+			smp_rmb();
+			atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+		}
+
+		memset(mcelog.entry + prev, 0, (next - prev) * sizeof(*m));
+		prev = next;
+		next = cmpxchg(&mcelog.next, prev, 0);
+	} while (next != prev);
+}
+
+
+void mce_register_decode_chain(struct notifier_block *nb)
+{
+	atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
+	drain_mcelog_buffer();
+}
+EXPORT_SYMBOL_GPL(mce_register_decode_chain);
+
+void mce_unregister_decode_chain(struct notifier_block *nb)
+{
+	atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
+}
+EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
+
 static void print_mce(struct mce *m)
 {
 	int ret = 0;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index ce21561..39c6089 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -323,17 +323,6 @@ device_initcall(thermal_throttle_init_device);
 
 #endif /* CONFIG_SYSFS */
 
-/*
- * Set up the most two significant bit to notify mce log that this thermal
- * event type.
- * This is a temp solution. May be changed in the future with mce log
- * infrasture.
- */
-#define CORE_THROTTLED		(0)
-#define CORE_POWER_LIMIT	((__u64)1 << 62)
-#define PACKAGE_THROTTLED	((__u64)2 << 62)
-#define PACKAGE_POWER_LIMIT	((__u64)3 << 62)
-
 static void notify_thresholds(__u64 msr_val)
 {
 	/* check whether the interrupt handler is defined;
@@ -363,27 +352,23 @@ static void intel_thermal_interrupt(void)
 	if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
 				THERMAL_THROTTLING_EVENT,
 				CORE_LEVEL) != 0)
-		mce_log_therm_throt_event(CORE_THROTTLED | msr_val);
+		mce_log_therm_throt_event(msr_val);
 
 	if (this_cpu_has(X86_FEATURE_PLN))
-		if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
+		therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
 					POWER_LIMIT_EVENT,
-					CORE_LEVEL) != 0)
-			mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val);
+					CORE_LEVEL);
 
 	if (this_cpu_has(X86_FEATURE_PTS)) {
 		rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
-		if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
+		therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
 					THERMAL_THROTTLING_EVENT,
-					PACKAGE_LEVEL) != 0)
-			mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val);
+					PACKAGE_LEVEL);
 		if (this_cpu_has(X86_FEATURE_PLN))
-			if (therm_throt_process(msr_val &
+			therm_throt_process(msr_val &
 					PACKAGE_THERM_STATUS_POWER_LIMIT,
 					POWER_LIMIT_EVENT,
-					PACKAGE_LEVEL) != 0)
-				mce_log_therm_throt_event(PACKAGE_POWER_LIMIT
-							  | msr_val);
+					PACKAGE_LEVEL);
 	}
 }