MCE changes for v3.4

index 6aefb14..441520e 100644
@@ -151,7 +151,7 @@ static inline void enable_p5_mce(void) {}
 
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
-extern struct device *mce_device[CONFIG_NR_CPUS];
+DECLARE_PER_CPU(struct device *, mce_device);
 
 /*
  * Maximum banks number.

index 7395d5f..0c82091 100644
@@ -54,7 +54,14 @@ static struct severity {
 #define  MASK(x, y)	.mask = x, .result = y
 #define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S)
 #define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR)
+#define	MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV)
 #define MCACOD 0xffff
+/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
+#define MCACOD_SCRUB	0x00C0	/* 0xC0-0xCF Memory Scrubbing */
+#define MCACOD_SCRUBMSK	0xfff0
+#define MCACOD_L3WB	0x017A	/* L3 Explicit Writeback */
+#define MCACOD_DATA	0x0134	/* Data Load */
+#define MCACOD_INSTR	0x0150	/* Instruction Fetch */
 
 	MCESEV(
 		NO, "Invalid",

@@ -102,11 +109,24 @@ static struct severity {
 		SER, BITCLR(MCI_STATUS_S)
 		),
 
-	/* AR add known MCACODs here */
 	MCESEV(
 		PANIC, "Action required with lost events",
 		SER, BITSET(MCI_STATUS_OVER|MCI_UC_SAR)
 		),
+
+	/* known AR MCACODs: */
+#ifdef	CONFIG_MEMORY_FAILURE
+	MCESEV(
+		KEEP, "HT thread notices Action required: data load error",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+		MCGMASK(MCG_STATUS_EIPV, 0)
+		),
+	MCESEV(
+		AR, "Action required: data load error",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+		USER
+		),
+#endif
 	MCESEV(
 		PANIC, "Action required: unknown MCACOD",
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_SAR)

@@ -115,11 +135,11 @@ static struct severity {
 	/* known AO MCACODs: */
 	MCESEV(
 		AO, "Action optional: memory scrubbing error",
-		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|0xfff0, MCI_UC_S|0x00c0)
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD_SCRUBMSK, MCI_UC_S|MCACOD_SCRUB)
 		),
 	MCESEV(
 		AO, "Action optional: last level cache writeback error",
-		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|0x017a)
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|MCACOD_L3WB)
 		),
 	MCESEV(
 		SOME, "Action optional: unknown MCACOD",

290 lines not on this page · raw message

index e4eeaaf..99b5717 100644
@@ -523,7 +523,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 {
 	int i, err = 0;
 	struct threshold_bank *b = NULL;
-	struct device *dev = mce_device[cpu];
+	struct device *dev = per_cpu(mce_device, cpu);
 	char name[32];
 
 	sprintf(name, "threshold_bank%i", bank);

@@ -587,7 +587,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (i == cpu)
 			continue;
 
-		dev = mce_device[i];
+		dev = per_cpu(mce_device, i);
 		if (dev)
 			err = sysfs_create_link(&dev->kobj,b->kobj, name);
 		if (err)

@@ -667,7 +667,8 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
 #ifdef CONFIG_SMP
 	/* sibling symlink */
 	if (shared_bank[bank] && b->blocks->cpu != cpu) {
-		sysfs_remove_link(&mce_device[cpu]->kobj, name);
+		dev = per_cpu(mce_device, cpu);
+		sysfs_remove_link(&dev->kobj, name);
 		per_cpu(threshold_banks, cpu)[bank] = NULL;
 
 		return;

@@ -679,7 +680,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
 		if (i == cpu)
 			continue;
 
-		dev = mce_device[i];
+		dev = per_cpu(mce_device, i);
 		if (dev)
 			sysfs_remove_link(&dev->kobj, name);
 		per_cpu(threshold_banks, i)[bank] = NULL;

index 9e60dbe..7dda4f7 100644
@@ -466,7 +466,7 @@ store_hard_offline_page(struct device *dev,
 	if (strict_strtoull(buf, 0, &pfn) < 0)
 		return -EINVAL;
 	pfn >>= PAGE_SHIFT;
-	ret = __memory_failure(pfn, 0, 0);
+	ret = memory_failure(pfn, 0, 0);
 	return ret ? ret : count;
 }
 

index 17b27cd..3dc8f6b 100644
@@ -1598,9 +1598,9 @@ void vmemmap_populate_print_last(void);
 
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,
+	MF_ACTION_REQUIRED = 1 << 1,
 };
-extern void memory_failure(unsigned long pfn, int trapno);
-extern int __memory_failure(unsigned long pfn, int trapno, int flags);
+extern int memory_failure(unsigned long pfn, int trapno, int flags);
 extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);
 extern int unpoison_memory(unsigned long pfn);
 extern int sysctl_memory_failure_early_kill;

index c7fc7fd..cc448bb 100644
@@ -45,7 +45,7 @@ static int hwpoison_inject(void *data, u64 val)
 	 * do a racy check with elevated page count, to make sure PG_hwpoison
 	 * will only be set for the targeted owner (or on a free page).
 	 * We temporarily take page lock for try_get_mem_cgroup_from_page().
-	 * __memory_failure() will redo the check reliably inside page lock.
+	 * memory_failure() will redo the check reliably inside page lock.
 	 */
 	lock_page(hpage);
 	err = hwpoison_filter(hpage);

@@ -55,7 +55,7 @@ static int hwpoison_inject(void *data, u64 val)
 
 inject:
 	printk(KERN_INFO "Injecting memory failure at pfn %lx\n", pfn);
-	return __memory_failure(pfn, 18, MF_COUNT_INCREASED);
+	return memory_failure(pfn, 18, MF_COUNT_INCREASED);
 }
 
 static int hwpoison_unpoison(void *data, u64 val)

index 74bf193..f5ab745 100644
@@ -251,7 +251,7 @@ static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
 		printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n",
 		       page_to_pfn(p), start);
 		/* Ignore return value for now */
-		__memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
+		memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
 	}
 	return ret;
 }

164 lines not on this page · raw message