1 files changed, 91 insertions, 17 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a8aacd4..18cc425 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -26,6 +26,7 @@
 #include <linux/sched.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/kmod.h>
 #include <linux/poll.h>
@@ -35,6 +36,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/debugfs.h>
+#include <linux/edac_mce.h>
 
 #include <asm/processor.h>
 #include <asm/hw_irq.h>
@@ -46,6 +48,13 @@
 
 #include "mce-internal.h"
 
+static DEFINE_MUTEX(mce_read_mutex);
+
+#define rcu_dereference_check_mce(p) \
+	rcu_dereference_check((p), \
+			      rcu_read_lock_sched_held() || \
+			      lockdep_is_held(&mce_read_mutex))
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
 
@@ -158,9 +167,18 @@ void mce_log(struct mce *mce)
 	mce->finished = 0;
 	wmb();
 	for (;;) {
-		entry = rcu_dereference(mcelog.next);
+		entry = rcu_dereference_check_mce(mcelog.next);
 		for (;;) {
 			/*
+			 * If edac_mce is enabled, it will check the error type
+			 * and will process it, if it is a known error.
+			 * Otherwise, the error will be sent through mcelog
+			 * interface
+			 */
+			if (edac_mce_parse(mce))
+				return;
+
+			/*
 			 * When the buffer fills up discard new entries.
 			 * Assume that the earlier errors are the more
 			 * interesting ones:
@@ -256,7 +274,7 @@ static void wait_for_panic(void)
 
 static void mce_panic(char *msg, struct mce *final, char *exp)
 {
-	int i;
+	int i, apei_err = 0;
 
 	if (!fake_panic) {
 		/*
@@ -279,8 +297,11 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
 		struct mce *m = &mcelog.entry[i];
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
-		if (!(m->status & MCI_STATUS_UC))
+		if (!(m->status & MCI_STATUS_UC)) {
 			print_mce(m);
+			if (!apei_err)
+				apei_err = apei_write_mce(m);
+		}
 	}
 	/* Now print uncorrected but with the final one last */
 	for (i = 0; i < MCE_LOG_LEN; i++) {
@@ -289,11 +310,17 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
 			continue;
 		if (!(m->status & MCI_STATUS_UC))
 			continue;
-		if (!final || memcmp(m, final, sizeof(struct mce)))
+		if (!final || memcmp(m, final, sizeof(struct mce))) {
 			print_mce(m);
+			if (!apei_err)
+				apei_err = apei_write_mce(m);
+		}
 	}
-	if (final)
+	if (final) {
 		print_mce(final);
+		if (!apei_err)
+			apei_err = apei_write_mce(final);
+	}
 	if (cpu_missing)
 		printk(KERN_EMERG "Some CPUs didn't answer in synchronization\n");
 	print_mce_tail();
@@ -531,7 +558,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 	struct mce m;
 	int i;
 
-	__get_cpu_var(mce_poll_count)++;
+	percpu_inc(mce_poll_count);
 
 	mce_setup(&m);
 
@@ -926,7 +953,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	atomic_inc(&mce_entry);
 
-	__get_cpu_var(mce_exception_count)++;
+	percpu_inc(mce_exception_count);
 
 	if (notify_die(DIE_NMI, "machine check", regs, error_code,
 			   18, SIGKILL) == NOTIFY_STOP)
@@ -1485,7 +1512,42 @@ static void collect_tscs(void *data)
 	rdtscll(cpu_tsc[smp_processor_id()]);
 }
 
-static DEFINE_MUTEX(mce_read_mutex);
+static int mce_apei_read_done;
+
+/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
+static int __mce_read_apei(char __user **ubuf, size_t usize)
+{
+	int rc;
+	u64 record_id;
+	struct mce m;
+
+	if (usize < sizeof(struct mce))
+		return -EINVAL;
+
+	rc = apei_read_mce(&m, &record_id);
+	/* Error or no more MCE record */
+	if (rc <= 0) {
+		mce_apei_read_done = 1;
+		return rc;
+	}
+	rc = -EFAULT;
+	if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
+		return rc;
+	/*
+	 * In fact, we should have cleared the record after that has
+	 * been flushed to the disk or sent to network in
+	 * /sbin/mcelog, but we have no interface to support that now,
+	 * so just clear it to avoid duplication.
+	 */
+	rc = apei_clear_mce(record_id);
+	if (rc) {
+		mce_apei_read_done = 1;
+		return rc;
+	}
+	*ubuf += sizeof(struct mce);
+
+	return 0;
+}
 
 static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
 			loff_t *off)
@@ -1500,16 +1562,20 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
 		return -ENOMEM;
 
 	mutex_lock(&mce_read_mutex);
-	next = rcu_dereference(mcelog.next);
 
-	/* Only supports full reads right now */
-	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) {
-		mutex_unlock(&mce_read_mutex);
-		kfree(cpu_tsc);
-
-		return -EINVAL;
+	if (!mce_apei_read_done) {
+		err = __mce_read_apei(&buf, usize);
+		if (err || buf != ubuf)
+			goto out;
 	}
 
+	next = rcu_dereference_check_mce(mcelog.next);
+
+	/* Only supports full reads right now */
+	err = -EINVAL;
+	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
+		goto out;
+
 	err = 0;
 	prev = 0;
 	do {
@@ -1556,16 +1622,23 @@ timeout:
 			memset(&mcelog.entry[i], 0, sizeof(struct mce));
 		}
 	}
+
+	if (err)
+		err = -EFAULT;
+
+out:
 	mutex_unlock(&mce_read_mutex);
 	kfree(cpu_tsc);
 
-	return err ? -EFAULT : buf - ubuf;
+	return err ? err : buf - ubuf;
 }
 
 static unsigned int mce_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &mce_wait, wait);
-	if (rcu_dereference(mcelog.next))
+	if (rcu_dereference_check_mce(mcelog.next))
+		return POLLIN | POLLRDNORM;
+	if (!mce_apei_read_done && apei_check_mce())
 		return POLLIN | POLLRDNORM;
 	return 0;
 }
@@ -2044,6 +2117,7 @@ static __init void mce_init_banks(void)
 		struct mce_bank *b = &mce_banks[i];
 		struct sysdev_attribute *a = &b->attr;
 
+		sysfs_attr_init(&a->attr);
 		a->attr.name	= b->attrname;
 		snprintf(b->attrname, ATTR_LEN, "bank%d", i);