x86/ras changes for v3.17

62 lines not on this page · raw message

index bb92f38..4fc5797 100644
@@ -2385,6 +2385,10 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 			threshold_cpu_callback(action, cpu);
 		mce_device_remove(cpu);
 		mce_intel_hcpu_update(cpu);
+
+		/* intentionally ignoring frozen here */
+		if (!(action & CPU_TASKS_FROZEN))
+			cmci_rediscover();
 		break;
 	case CPU_DOWN_PREPARE:
 		smp_call_function_single(cpu, mce_disable_cpu, &action, 1);

@@ -2396,11 +2400,6 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 	}
 
-	if (action == CPU_POST_DEAD) {
-		/* intentionally ignoring frozen here */
-		cmci_rediscover();
-	}
-
 	return NOTIFY_OK;
 }
 

@@ -2451,6 +2450,12 @@ static __init int mcheck_init_device(void)
 	for_each_online_cpu(i) {
 		err = mce_device_create(i);
 		if (err) {
+			/*
+			 * Register notifier anyway (and do not unreg it) so
+			 * that we don't leave undeleted timers, see notifier
+			 * callback above.
+			 */
+			__register_hotcpu_notifier(&mce_cpu_notifier);
 			cpu_notifier_register_done();
 			goto err_device_create;
 		}

@@ -2471,10 +2476,6 @@ static __init int mcheck_init_device(void)
 err_register:
 	unregister_syscore_ops(&mce_syscore_ops);
 
-	cpu_notifier_register_begin();
-	__unregister_hotcpu_notifier(&mce_cpu_notifier);
-	cpu_notifier_register_done();
-
 err_device_create:
 	/*
 	 * We didn't keep track of which devices were created above, but

80 lines not on this page · raw message

index 8678dfe..2cd7bdd 100644
@@ -745,6 +745,19 @@ struct dentry *apei_get_debugfs_dir(void)
 }
 EXPORT_SYMBOL_GPL(apei_get_debugfs_dir);
 
+int __weak arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr,
+				  void *data)
+{
+	return 1;
+}
+EXPORT_SYMBOL_GPL(arch_apei_enable_cmcff);
+
+void __weak arch_apei_report_mem_error(int sev,
+				       struct cper_sec_mem_err *mem_err)
+{
+}
+EXPORT_SYMBOL_GPL(arch_apei_report_mem_error);
+
 int apei_osc_setup(void)
 {
 	static u8 whea_uuid_str[] = "ed855e0c-6c90-47bf-a62a-26de0fc5ad5c";

289 lines not on this page · raw message

index f5e37f3..06e9b41 100644
@@ -36,7 +36,6 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <acpi/apei.h>
-#include <asm/mce.h>
 
 #include "apei-internal.h"
 

@@ -128,33 +127,7 @@ EXPORT_SYMBOL_GPL(apei_hest_parse);
  */
 static int __init hest_parse_cmc(struct acpi_hest_header *hest_hdr, void *data)
 {
-#ifdef CONFIG_X86_MCE
-	int i;
-	struct acpi_hest_ia_corrected *cmc;
-	struct acpi_hest_ia_error_bank *mc_bank;
-
-	if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK)
-		return 0;
-
-	cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
-	if (!cmc->enabled)
-		return 0;
-
-	/*
-	 * We expect HEST to provide a list of MC banks that report errors
-	 * in firmware first mode. Otherwise, return non-zero value to
-	 * indicate that we are done parsing HEST.
-	 */
-	if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) || !cmc->num_hardware_banks)
-		return 1;
-
-	pr_info(HEST_PFX "Enabling Firmware First mode for corrected errors.\n");
-
-	mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1);
-	for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++)
-		mce_disable_bank(mc_bank->bank_number);
-#endif
-	return 1;
+	return arch_apei_enable_cmcff(hest_hdr, data);
 }
 
 struct ghes_arr {

index 2c694b5..9f134823 100644
@@ -33,9 +33,6 @@
 #include <asm/edac.h>
 #include "edac_core.h"
 #include "edac_module.h"
-
-#define CREATE_TRACE_POINTS
-#define TRACE_INCLUDE_PATH ../../include/ras
 #include <ras/ras_event.h>
 
 /* lock to memory controller's control array */

292 lines not on this page · raw message

index 36ed31b5..35d06e1 100644
@@ -22,9 +22,7 @@
 #include <linux/cper.h>
 
 #include "aerdrv.h"
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/ras.h>
+#include <ras/ras_event.h>
 
 #define AER_AGENT_RECEIVER		0
 #define AER_AGENT_REQUESTER		1

56 lines not on this page · raw message

new file mode 100644
index 0000000..b67dd36
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2014 Intel Corporation
+ *
+ * Authors:
+ *	Chen, Gong <[email protected]>
+ */
+
+#include <linux/init.h>
+#include <linux/ras.h>
+
+#define CREATE_TRACE_POINTS
+#define TRACE_INCLUDE_PATH ../../include/ras
+#include <ras/ras_event.h>
+
+static int __init ras_init(void)
+{
+	int rc = 0;
+
+	ras_debugfs_init();
+	rc = ras_add_daemon_trace();
+
+	return rc;
+}
+subsys_initcall(ras_init);
+
+#if defined(CONFIG_ACPI_EXTLOG) || defined(CONFIG_ACPI_EXTLOG_MODULE)
+EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
+#endif
+EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);

index 04f349d..76284bb 100644
@@ -42,5 +42,9 @@ ssize_t erst_read(u64 record_id, struct cper_record_header *record,
 		  size_t buflen);
 int erst_clear(u64 record_id);
 
+int arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, void *data);
+void arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err);
+void arch_apei_flush_tlb_one(unsigned long addr);
+
 #endif
 #endif

index 4dbaa70..c826d1c 100644
@@ -11,6 +11,8 @@
 #define AER_FATAL			1
 #define AER_CORRECTABLE			2
 
+struct pci_dev;
+
 struct aer_header_log_regs {
 	unsigned int dw0;
 	unsigned int dw1;

index 2fc0ec3..76abba4 100644
@@ -22,6 +22,7 @@
 #define LINUX_CPER_H
 
 #include <linux/uuid.h>
+#include <linux/trace_seq.h>
 
 /* CPER record signature and the size */
 #define CPER_SIG_RECORD				"CPER"

@@ -36,6 +37,13 @@
 #define CPER_RECORD_REV				0x0100
 
 /*
+ * CPER record length contains the CPER fields which are relevant for further
+ * handling of a memory error in userspace (we don't carry all the fields
+ * defined in the UEFI spec because some of them don't make any sense.)
+ * Currently, a length of 256 should be more than enough.
+ */
+#define CPER_REC_LEN					256
+/*
  * Severity difinition for error_severity in struct cper_record_header
  * and section_severity in struct cper_section_descriptor
  */

@@ -356,6 +364,24 @@ struct cper_sec_mem_err {
 	__u16	mem_dev_handle;		/* module handle in UEFI 2.4 */
 };
 
+struct cper_mem_err_compact {
+	__u64	validation_bits;
+	__u16	node;
+	__u16	card;
+	__u16	module;
+	__u16	bank;
+	__u16	device;
+	__u16	row;
+	__u16	column;
+	__u16	bit_pos;
+	__u64	requestor_id;
+	__u64	responder_id;
+	__u64	target_id;
+	__u16	rank;
+	__u16	mem_array_handle;
+	__u16	mem_dev_handle;
+};
+
 struct cper_sec_pcie {
 	__u64		validation_bits;
 	__u32		port_type;

@@ -395,7 +421,13 @@ struct cper_sec_pcie {
 #pragma pack()
 
 u64 cper_next_record_id(void);
+const char *cper_severity_str(unsigned int);
+const char *cper_mem_err_type_str(unsigned int);
 void cper_print_bits(const char *prefix, unsigned int bits,
 		     const char * const strs[], unsigned int strs_size);
+void cper_mem_err_pack(const struct cper_sec_mem_err *,
+		       struct cper_mem_err_compact *);
+const char *cper_mem_err_unpack(struct trace_seq *,
+				struct cper_mem_err_compact *);
 
 #endif

index 447775e..1d2a6ab 100644
@@ -63,4 +63,8 @@ extern int proc_dowatchdog(struct ctl_table *, int ,
 			   void __user *, size_t *, loff_t *);
 #endif
 
+#ifdef CONFIG_HAVE_ACPI_APEI_NMI
+#include <asm/nmi.h>
+#endif
+
 #endif

new file mode 100644
index 0000000..2aceeaf
@@ -0,0 +1,14 @@
+#ifndef __RAS_H__
+#define __RAS_H__
+
+#ifdef CONFIG_DEBUG_FS
+int ras_userspace_consumers(void);
+void ras_debugfs_init(void);
+int ras_add_daemon_trace(void);
+#else
+static inline int ras_userspace_consumers(void) { return 0; }
+static inline void ras_debugfs_init(void) { return; }
+static inline int ras_add_daemon_trace(void) { return 0; }
+#endif
+
+#endif

140 lines not on this page · raw message

77 lines not on this page · raw message