RAS changes for v3.14

index de8b60a..a1aef95 100644
@@ -33,22 +33,28 @@
 #include <linux/acpi.h>
 #include <linux/cper.h>
 #include <acpi/apei.h>
+#include <acpi/ghes.h>
 #include <asm/mce.h>
 
 #include "mce-internal.h"
 
-void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
+void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 {
 	struct mce m;
 
-	/* Only corrected MC is reported */
-	if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA))
+	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
 
 	mce_setup(&m);
 	m.bank = 1;
-	/* Fake a memory read corrected error with unknown channel */
+	/* Fake a memory read error with unknown channel */
 	m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | 0x9f;
+
+	if (severity >= GHES_SEV_RECOVERABLE)
+		m.status |= MCI_STATUS_UC;
+	if (severity >= GHES_SEV_PANIC)
+		m.status |= MCI_STATUS_PCC;
+
 	m.addr = mem_err->physical_addr;
 	mce_log(&m);
 	mce_notify_irq();

index b3218cd..4d5419b 100644
@@ -1638,15 +1638,15 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 
 static void mce_start_timer(unsigned int cpu, struct timer_list *t)
 {
-	unsigned long iv = mce_adjust_timer(check_interval * HZ);
-
-	__this_cpu_write(mce_next_interval, iv);
+	unsigned long iv = check_interval * HZ;
 
 	if (mca_cfg.ignore_ce || !iv)
 		return;
 
+	per_cpu(mce_next_interval, cpu) = iv;
+
 	t->expires = round_jiffies(jiffies + iv);
-	add_timer_on(t, smp_processor_id());
+	add_timer_on(t, cpu);
 }
 
 static void __mcheck_cpu_init_timer(void)

@@ -2272,8 +2272,10 @@ static int mce_device_create(unsigned int cpu)
 	dev->release = &mce_device_release;
 
 	err = device_register(dev);
-	if (err)
+	if (err) {
+		put_device(dev);
 		return err;
+	}
 
 	for (i = 0; mce_device_attrs[i]; i++) {
 		err = device_create_file(dev, mce_device_attrs[i]);

index a6869e1..5d33c54 100644
@@ -12,6 +12,7 @@
 #include <acpi/acpi_bus.h>
 #include <linux/cper.h>
 #include <linux/ratelimit.h>
+#include <linux/edac.h>
 #include <asm/cpu.h>
 #include <asm/mce.h>
 

@@ -43,6 +44,8 @@ struct extlog_l1_head {
 	u8  rev1[12];
 };
 
+static int old_edac_report_status;
+
 static u8 extlog_dsm_uuid[] = "663E35AF-CC10-41A4-88EA-5470AF055295";
 
 /* L1 table related physical address */

@@ -150,7 +153,7 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 
 	rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu);
 
-	return NOTIFY_DONE;
+	return NOTIFY_STOP;
 }
 
 static int extlog_get_dsm(acpi_handle handle, int rev, int func, u64 *ret)

@@ -231,8 +234,12 @@ static int __init extlog_init(void)
 	u64 cap;
 	int rc;
 
-	rc = -ENODEV;
+	if (get_edac_report_status() == EDAC_REPORTING_FORCE) {
+		pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n");
+		return -EPERM;
+	}
 
+	rc = -ENODEV;
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	if (!(cap & MCG_ELOG_P))
 		return rc;

@@ -287,6 +294,12 @@ static int __init extlog_init(void)
 	if (elog_buf == NULL)
 		goto err_release_elog;
 
+	/*
+	 * eMCA event report method has higher priority than EDAC method,
+	 * unless EDAC event report method is mandatory.
+	 */
+	old_edac_report_status = get_edac_report_status();
+	set_edac_report_status(EDAC_REPORTING_DISABLED);
 	mce_register_decode_chain(&extlog_mce_dec);
 	/* enable OS to be involved to take over management from BIOS */
 	((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN;

@@ -308,6 +321,7 @@ err:
 
 static void __exit extlog_exit(void)
 {
+	set_edac_report_status(old_edac_report_status);
 	mce_unregister_decode_chain(&extlog_mce_dec);
 	((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
 	if (extlog_l1_addr)

index 6d2c49b..e55584a 100644
@@ -41,6 +41,7 @@
 #include <linux/rculist.h>
 #include <linux/interrupt.h>
 #include <linux/debugfs.h>
+#include <asm/unaligned.h>
 
 #include "apei-internal.h"
 

@@ -567,8 +568,7 @@ static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr,
 	bit_offset = reg->bit_offset;
 	access_size_code = reg->access_width;
 	space_id = reg->space_id;
-	/* Handle possible alignment issues */
-	memcpy(paddr, &reg->address, sizeof(*paddr));
+	*paddr = get_unaligned(&reg->address);
 	if (!*paddr) {
 		pr_warning(FW_BUG APEI_PFX
 			   "Invalid physical address in GAR [0x%llx/%u/%u/%u/%u]\n",

151 lines not on this page · raw message

index cb1d557..ed65e9c 100644
@@ -611,7 +611,7 @@ static void __erst_record_id_cache_compact(void)
 		if (entries[i] == APEI_ERST_INVALID_RECORD_ID)
 			continue;
 		if (wpos != i)
-			memcpy(&entries[wpos], &entries[i], sizeof(entries[i]));
+			entries[wpos] = entries[i];
 		wpos++;
 	}
 	erst_record_id_cache.len = wpos;

index a30bc31..46766ef 100644
@@ -413,27 +413,31 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 {
 #ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
 	unsigned long pfn;
+	int flags = -1;
 	int sec_sev = ghes_severity(gdata->error_severity);
 	struct cper_sec_mem_err *mem_err;
 	mem_err = (struct cper_sec_mem_err *)(gdata + 1);
 
-	if (sec_sev == GHES_SEV_CORRECTED &&
-	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) &&
-	    (mem_err->validation_bits & CPER_MEM_VALID_PA)) {
-		pfn = mem_err->physical_addr >> PAGE_SHIFT;
-		if (pfn_valid(pfn))
-			memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);
-		else if (printk_ratelimit())
-			pr_warn(FW_WARN GHES_PFX
-			"Invalid address in generic error data: %#llx\n",
-			mem_err->physical_addr);
-	}
-	if (sev == GHES_SEV_RECOVERABLE &&
-	    sec_sev == GHES_SEV_RECOVERABLE &&
-	    mem_err->validation_bits & CPER_MEM_VALID_PA) {
-		pfn = mem_err->physical_addr >> PAGE_SHIFT;
-		memory_failure_queue(pfn, 0, 0);
+	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
+		return;
+
+	pfn = mem_err->physical_addr >> PAGE_SHIFT;
+	if (!pfn_valid(pfn)) {
+		pr_warn_ratelimited(FW_WARN GHES_PFX
+		"Invalid address in generic error data: %#llx\n",
+		mem_err->physical_addr);
+		return;
 	}
+
+	/* iff following two events can be handled properly by now */
+	if (sec_sev == GHES_SEV_CORRECTED &&
+	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
+		flags = MF_SOFT_OFFLINE;
+	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
+		flags = 0;
+
+	if (flags != -1)
+		memory_failure_queue(pfn, 0, flags);
 #endif
 }
 

@@ -453,8 +457,7 @@ static void ghes_do_proc(struct ghes *ghes,
 			ghes_edac_report_mem_error(ghes, sev, mem_err);
 
 #ifdef CONFIG_X86_MCE
-			apei_mce_report_mem_error(sev == GHES_SEV_CORRECTED,
-						  mem_err);
+			apei_mce_report_mem_error(sev, mem_err);
 #endif
 			ghes_handle_memory_failure(gdata, sev);
 		}

index 351945f..9d9e18a 100644
@@ -29,6 +29,25 @@ EXPORT_SYMBOL_GPL(edac_err_assert);
 
 static atomic_t edac_subsys_valid = ATOMIC_INIT(0);
 
+int edac_report_status = EDAC_REPORTING_ENABLED;
+EXPORT_SYMBOL_GPL(edac_report_status);
+
+static int __init edac_report_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strncmp(str, "on", 2))
+		set_edac_report_status(EDAC_REPORTING_ENABLED);
+	else if (!strncmp(str, "off", 3))
+		set_edac_report_status(EDAC_REPORTING_DISABLED);
+	else if (!strncmp(str, "force", 5))
+		set_edac_report_status(EDAC_REPORTING_FORCE);
+
+	return 0;
+}
+__setup("edac_report=", edac_report_setup);
+
 /*
  * called to determine if there is an EDAC driver interested in
  * knowing an event (such as NMI) occurred

index d7f1b57..1229123 100644
@@ -1829,6 +1829,9 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 	struct mem_ctl_info *mci;
 	struct sbridge_pvt *pvt;
 
+	if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+		return NOTIFY_DONE;
+
 	mci = get_mci_for_node_id(mce->socketid);
 	if (!mci)
 		return NOTIFY_BAD;

@@ -2142,9 +2145,10 @@ static int __init sbridge_init(void)
 	opstate_init();
 
 	pci_rc = pci_register_driver(&sbridge_driver);
-
 	if (pci_rc >= 0) {
 		mce_register_decode_chain(&sbridge_mce_dec);
+		if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+			sbridge_printk(KERN_WARNING, "Loading driver, error reporting disabled.\n");
 		return 0;
 	}
 

index dbdffe8..8e6c20a 100644
@@ -35,6 +35,34 @@ extern void edac_atomic_assert_error(void);
 extern struct bus_type *edac_get_sysfs_subsys(void);
 extern void edac_put_sysfs_subsys(void);
 
+enum {
+	EDAC_REPORTING_ENABLED,
+	EDAC_REPORTING_DISABLED,
+	EDAC_REPORTING_FORCE
+};
+
+extern int edac_report_status;
+#ifdef CONFIG_EDAC
+static inline int get_edac_report_status(void)
+{
+	return edac_report_status;
+}
+
+static inline void set_edac_report_status(int new)
+{
+	edac_report_status = new;
+}
+#else
+static inline int get_edac_report_status(void)
+{
+	return EDAC_REPORTING_DISABLED;
+}
+
+static inline void set_edac_report_status(int new)
+{
+}
+#endif
+
 static inline void opstate_init(void)
 {
 	switch (edac_op_state) {

index 88b8783..1c875ad 100644
@@ -5,7 +5,7 @@
 #define _TRACE_AER_H
 
 #include <linux/tracepoint.h>
-#include <linux/edac.h>
+#include <linux/aer.h>
 
 
 /*

@@ -63,10 +63,10 @@ TRACE_EVENT(aer_event,
 
 	TP_printk("%s PCIe Bus Error: severity=%s, %s\n",
 		__get_str(dev_name),
-		__entry->severity == HW_EVENT_ERR_CORRECTED ? "Corrected" :
-			__entry->severity == HW_EVENT_ERR_FATAL ?
-			"Fatal" : "Uncorrected",
-		__entry->severity == HW_EVENT_ERR_CORRECTED ?
+		__entry->severity == AER_CORRECTABLE ? "Corrected" :
+			__entry->severity == AER_FATAL ?
+			"Fatal" : "Uncorrected, non-fatal",
+		__entry->severity == AER_CORRECTABLE ?
 		__print_flags(__entry->status, "|", aer_correctable_errors) :
 		__print_flags(__entry->status, "|", aer_uncorrectable_errors))
 );