New eMCA trace event interface V4

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 */

new file mode 100644
index 0000000..b0c6ed1
@@ -0,0 +1,12 @@
+/*
+ * Copyright (C) 2014 Intel Corporation
+ *
+ * Authors:
+ *	Chen, Gong <[email protected]>
+ */
+
+#define CREATE_TRACE_POINTS
+#define TRACE_INCLUDE_PATH ../../include/ras
+#include <ras/ras_event.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);

Index: linux/drivers/edac/edac_mc.c
===================================================================
@@ -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 */

Index: linux/drivers/ras/ras.c
===================================================================
@@ -0,0 +1,12 @@
+/*
+ * Copyright (C) 2014 Intel Corporation
+ *
+ * Authors:
+ *	Chen, Gong <[email protected]>
+ */
+
+#define CREATE_TRACE_POINTS
+#define TRACE_INCLUDE_PATH ../../include/ras
+#include <ras/ras_event.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);

57 lines not on this page · raw message

index b0c6ed1..4cac43a 100644
@@ -5,8 +5,22 @@
  *	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);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);

new file mode 100644
index 0000000..af53248
@@ -0,0 +1,15 @@
+#ifndef __RAS_H__
+#define __RAS_H__
+
+#ifdef CONFIG_DEBUG_FS
+extern struct dentry *ras_debugfs_dir;
+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

index 1491dd4..83b56b61 100644
@@ -34,6 +34,9 @@
 #include <linux/aer.h>
 
 #define INDENT_SP	" "
+
+static char rcd_decode_str[CPER_REC_LEN];
+
 /*
  * CPER record ID need to be unique even after reboot, because record
  * ID is used as index for ERST storage, while CPER records from

@@ -50,18 +53,19 @@ u64 cper_next_record_id(void)
 }
 EXPORT_SYMBOL_GPL(cper_next_record_id);
 
-static const char *cper_severity_strs[] = {
+static const char * const severity_strs[] = {
 	"recoverable",
 	"fatal",
 	"corrected",
 	"info",
 };
 
-static const char *cper_severity_str(unsigned int severity)
+const char *cper_severity_str(unsigned int severity)
 {
-	return severity < ARRAY_SIZE(cper_severity_strs) ?
-		cper_severity_strs[severity] : "unknown";
+	return severity < ARRAY_SIZE(severity_strs) ?
+		severity_strs[severity] : "unknown";
 }
+EXPORT_SYMBOL_GPL(cper_severity_str);
 
 /*
  * cper_print_bits - print strings for set bits

@@ -100,32 +104,32 @@ void cper_print_bits(const char *pfx, unsigned int bits,
 		printk("%s\n", buf);
 }
 
-static const char * const cper_proc_type_strs[] = {
+static const char * const proc_type_strs[] = {
 	"IA32/X64",
 	"IA64",
 };
 
-static const char * const cper_proc_isa_strs[] = {
+static const char * const proc_isa_strs[] = {
 	"IA32",
 	"IA64",
 	"X64",
 };
 
-static const char * const cper_proc_error_type_strs[] = {
+static const char * const proc_error_type_strs[] = {
 	"cache error",
 	"TLB error",
 	"bus error",
 	"micro-architectural error",
 };
 
-static const char * const cper_proc_op_strs[] = {
+static const char * const proc_op_strs[] = {
 	"unknown or generic",
 	"data read",
 	"data write",
 	"instruction execution",
 };
 
-static const char * const cper_proc_flag_strs[] = {
+static const char * const proc_flag_strs[] = {
 	"restartable",
 	"precise IP",
 	"overflow",

@@ -137,26 +141,26 @@ static void cper_print_proc_generic(const char *pfx,
 {
 	if (proc->validation_bits & CPER_PROC_VALID_TYPE)
 		printk("%s""processor_type: %d, %s\n", pfx, proc->proc_type,
-		       proc->proc_type < ARRAY_SIZE(cper_proc_type_strs) ?
-		       cper_proc_type_strs[proc->proc_type] : "unknown");
+		       proc->proc_type < ARRAY_SIZE(proc_type_strs) ?
+		       proc_type_strs[proc->proc_type] : "unknown");
 	if (proc->validation_bits & CPER_PROC_VALID_ISA)
 		printk("%s""processor_isa: %d, %s\n", pfx, proc->proc_isa,
-		       proc->proc_isa < ARRAY_SIZE(cper_proc_isa_strs) ?
-		       cper_proc_isa_strs[proc->proc_isa] : "unknown");
+		       proc->proc_isa < ARRAY_SIZE(proc_isa_strs) ?
+		       proc_isa_strs[proc->proc_isa] : "unknown");
 	if (proc->validation_bits & CPER_PROC_VALID_ERROR_TYPE) {
 		printk("%s""error_type: 0x%02x\n", pfx, proc->proc_error_type);
 		cper_print_bits(pfx, proc->proc_error_type,
-				cper_proc_error_type_strs,
-				ARRAY_SIZE(cper_proc_error_type_strs));
+				proc_error_type_strs,
+				ARRAY_SIZE(proc_error_type_strs));
 	}
 	if (proc->validation_bits & CPER_PROC_VALID_OPERATION)
 		printk("%s""operation: %d, %s\n", pfx, proc->operation,
-		       proc->operation < ARRAY_SIZE(cper_proc_op_strs) ?
-		       cper_proc_op_strs[proc->operation] : "unknown");
+		       proc->operation < ARRAY_SIZE(proc_op_strs) ?
+		       proc_op_strs[proc->operation] : "unknown");
 	if (proc->validation_bits & CPER_PROC_VALID_FLAGS) {
 		printk("%s""flags: 0x%02x\n", pfx, proc->flags);
-		cper_print_bits(pfx, proc->flags, cper_proc_flag_strs,
-				ARRAY_SIZE(cper_proc_flag_strs));
+		cper_print_bits(pfx, proc->flags, proc_flag_strs,
+				ARRAY_SIZE(proc_flag_strs));
 	}
 	if (proc->validation_bits & CPER_PROC_VALID_LEVEL)
 		printk("%s""level: %d\n", pfx, proc->level);

@@ -177,7 +181,7 @@ static void cper_print_proc_generic(const char *pfx,
 		printk("%s""IP: 0x%016llx\n", pfx, proc->ip);
 }
 
-static const char *cper_mem_err_type_strs[] = {
+static const char * const mem_err_type_strs[] = {
 	"unknown",
 	"no error",
 	"single-bit ECC",

@@ -196,58 +200,99 @@ static const char *cper_mem_err_type_strs[] = {
 	"physical memory map-out event",
 };
 
-static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
+const char *cper_mem_err_type_str(unsigned int etype)
 {
-	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
-		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
-	if (mem->validation_bits & CPER_MEM_VALID_PA)
-		printk("%s""physical_address: 0x%016llx\n",
-		       pfx, mem->physical_addr);
-	if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
-		printk("%s""physical_address_mask: 0x%016llx\n",
-		       pfx, mem->physical_addr_mask);
+	return etype < ARRAY_SIZE(mem_err_type_strs) ?
+		mem_err_type_strs[etype] : "unknown";
+}
+EXPORT_SYMBOL_GPL(cper_mem_err_type_str);
+
+int cper_mem_err_location(const struct cper_sec_mem_err *mem, char *msg)
+{
+	u32 len, n;
+
+	if (!msg)
+		return 0;
+
+	n = 0;
+	len = CPER_REC_LEN - 1;
 	if (mem->validation_bits & CPER_MEM_VALID_NODE)
-		pr_debug("node: %d\n", mem->node);
+		n += scnprintf(msg + n, len - n, "node: %d ", mem->node);
 	if (mem->validation_bits & CPER_MEM_VALID_CARD)
-		pr_debug("card: %d\n", mem->card);
+		n += scnprintf(msg + n, len - n, "card: %d ", mem->card);
 	if (mem->validation_bits & CPER_MEM_VALID_MODULE)
-		pr_debug("module: %d\n", mem->module);
+		n += scnprintf(msg + n, len - n, "module: %d ", mem->module);
 	if (mem->validation_bits & CPER_MEM_VALID_RANK_NUMBER)
-		pr_debug("rank: %d\n", mem->rank);
+		n += scnprintf(msg + n, len - n, "rank: %d ", mem->rank);
 	if (mem->validation_bits & CPER_MEM_VALID_BANK)
-		pr_debug("bank: %d\n", mem->bank);
+		n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank);
 	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)
-		pr_debug("device: %d\n", mem->device);
+		n += scnprintf(msg + n, len - n, "device: %d ", mem->device);
 	if (mem->validation_bits & CPER_MEM_VALID_ROW)
-		pr_debug("row: %d\n", mem->row);
+		n += scnprintf(msg + n, len - n, "row: %d ", mem->row);
 	if (mem->validation_bits & CPER_MEM_VALID_COLUMN)
-		pr_debug("column: %d\n", mem->column);
+		n += scnprintf(msg + n, len - n, "column: %d ", mem->column);
 	if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION)
-		pr_debug("bit_position: %d\n", mem->bit_pos);
+		n += scnprintf(msg + n, len - n, "bit_position: %d ",
+			       mem->bit_pos);
 	if (mem->validation_bits & CPER_MEM_VALID_REQUESTOR_ID)
-		pr_debug("requestor_id: 0x%016llx\n", mem->requestor_id);
+		n += scnprintf(msg + n, len - n, "requestor_id: 0x%016llx ",
+			       mem->requestor_id);
 	if (mem->validation_bits & CPER_MEM_VALID_RESPONDER_ID)
-		pr_debug("responder_id: 0x%016llx\n", mem->responder_id);
+		n += scnprintf(msg + n, len - n, "responder_id: 0x%016llx ",
+			       mem->responder_id);
 	if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID)
-		pr_debug("target_id: 0x%016llx\n", mem->target_id);
+		scnprintf(msg + n, len - n, "target_id: 0x%016llx ",
+			  mem->target_id);
+
+	msg[n] = '\0';
+	return n;
+}
+
+int cper_dimm_err_location(const struct cper_sec_mem_err *mem, char *msg)
+{
+	u32 len, n;
+	const char *bank = NULL, *device = NULL;
+
+	if (!msg || !(mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE))
+		return 0;
+
+	n = 0;
+	len = CPER_REC_LEN - 1;
+	dmi_memdev_name(mem->mem_dev_handle, &bank, &device);
+	if (bank && device)
+		n = snprintf(msg, len, "DIMM location: %s %s ", bank, device);
+	else
+		n = snprintf(msg, len,
+			     "DIMM location: not present. DMI handle: 0x%.4x ",
+			     mem->mem_dev_handle);
+
+	msg[n] = '\0';
+	return n;
+}
+
+static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
+{
+	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
+		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
+	if (mem->validation_bits & CPER_MEM_VALID_PA)
+		printk("%s""physical_address: 0x%016llx\n",
+		       pfx, mem->physical_addr);
+	if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
+		printk("%s""physical_address_mask: 0x%016llx\n",
+		       pfx, mem->physical_addr_mask);
+	if (cper_mem_err_location(mem, rcd_decode_str))
+		printk("%s%s\n", pfx, rcd_decode_str);
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE) {
 		u8 etype = mem->error_type;
 		printk("%s""error_type: %d, %s\n", pfx, etype,
-		       etype < ARRAY_SIZE(cper_mem_err_type_strs) ?
-		       cper_mem_err_type_strs[etype] : "unknown");
-	}
-	if (mem->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) {
-		const char *bank = NULL, *device = NULL;
-		dmi_memdev_name(mem->mem_dev_handle, &bank, &device);
-		if (bank != NULL && device != NULL)
-			printk("%s""DIMM location: %s %s", pfx, bank, device);
-		else
-			printk("%s""DIMM DMI handle: 0x%.4x",
-			       pfx, mem->mem_dev_handle);
+		       cper_mem_err_type_str(etype));
 	}
+	if (cper_dimm_err_location(mem, rcd_decode_str))
+		printk("%s%s\n", pfx, rcd_decode_str);
 }
 
-static const char *cper_pcie_port_type_strs[] = {
+static const char * const pcie_port_type_strs[] = {
 	"PCIe end point",
 	"legacy PCI end point",
 	"unknown",

@@ -266,8 +311,8 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 {
 	if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE)
 		printk("%s""port_type: %d, %s\n", pfx, pcie->port_type,
-		       pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ?
-		       cper_pcie_port_type_strs[pcie->port_type] : "unknown");
+		       pcie->port_type < ARRAY_SIZE(pcie_port_type_strs) ?
+		       pcie_port_type_strs[pcie->port_type] : "unknown");
 	if (pcie->validation_bits & CPER_PCIE_VALID_VERSION)
 		printk("%s""version: %d.%d\n", pfx,
 		       pcie->version.major, pcie->version.minor);

index 2fc0ec3..ed088b9 100644
@@ -36,6 +36,13 @@
 #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
  */

@@ -395,6 +402,8 @@ 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);
 

index e61da95..a99d4a6 100644
@@ -12,6 +12,7 @@
 #include <linux/cper.h>
 #include <linux/ratelimit.h>
 #include <linux/edac.h>
+#include <linux/ras.h>
 #include <asm/cpu.h>
 #include <asm/mce.h>
 

@@ -154,7 +155,11 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	estatus->block_status = 0;
 
 	tmp = (struct acpi_generic_status *)elog_buf;
-	print_extlog_rcd(NULL, tmp, cpu);
+
+	if (!ras_userspace_consumers()) {
+		print_extlog_rcd(NULL, tmp, cpu);
+		goto out;
+	}
 
 	/* log event via trace */
 	err_seq++;

@@ -171,6 +176,7 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 					       (u8)gdata->error_severity);
 	}
 
+out:
 	return NOTIFY_STOP;
 }
 

index 1853341..e61da95 100644
@@ -16,6 +16,7 @@
 #include <asm/mce.h>
 
 #include "apei/apei-internal.h"
+#include <ras/ras_event.h>
 
 #define EXT_ELOG_ENTRY_MASK	GENMASK_ULL(51, 0) /* elog entry address mask */
 

@@ -137,8 +138,12 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	struct mce *mce = (struct mce *)data;
 	int	bank = mce->bank;
 	int	cpu = mce->extcpu;
-	struct acpi_generic_status *estatus;
-	int rc;
+	struct acpi_generic_status *estatus, *tmp;
+	struct acpi_generic_data *gdata;
+	const uuid_le *fru_id = &NULL_UUID_LE;
+	char *fru_text = "";
+	uuid_le *sec_type;
+	static u32 err_seq;
 
 	estatus = extlog_elog_entry_check(cpu, bank);
 	if (estatus == NULL)

@@ -148,7 +153,23 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	/* clear record status to enable BIOS to update it again */
 	estatus->block_status = 0;
 
-	rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu);
+	tmp = (struct acpi_generic_status *)elog_buf;
+	print_extlog_rcd(NULL, tmp, cpu);
+
+	/* log event via trace */
+	err_seq++;
+	gdata = (struct acpi_generic_data *)(tmp + 1);
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
+		fru_id = (uuid_le *)gdata->fru_id;
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
+		fru_text = gdata->fru_text;
+	sec_type = (uuid_le *)gdata->section_type;
+	if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
+		struct cper_sec_mem_err *mem = (void *)(gdata + 1);
+		if (gdata->error_data_length >= sizeof(*mem))
+			trace_extlog_mem_event(mem, err_seq, fru_id, fru_text,
+					       (u8)gdata->error_severity);
+	}
 
 	return NOTIFY_STOP;
 }

80 lines not on this page · raw message

index 4cac43a..da227a3 100644
@@ -23,4 +23,5 @@ static int __init ras_init(void)
 }
 subsys_initcall(ras_init);
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
 EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);

index ed088b9..3548160 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"

@@ -363,6 +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;

@@ -406,5 +425,7 @@ 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 *, void *);
+const char *cper_mem_err_unpack(struct trace_seq *, void *);
 
 #endif

69 lines not on this page · raw message

index 34ff702..73e73b7 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

76 lines not on this page · raw message

77 lines not on this page · raw message

index c4a5d87..3c4a8aa 100644
@@ -16,6 +16,7 @@
 #include <asm/mce.h>
 
 #include "apei/apei-internal.h"
+#include <ras/ras_event.h>
 
 #define EXT_ELOG_ENTRY_MASK	GENMASK_ULL(51, 0) /* elog entry address mask */
 

@@ -137,8 +138,12 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	struct mce *mce = (struct mce *)data;
 	int	bank = mce->bank;
 	int	cpu = mce->extcpu;
-	struct acpi_generic_status *estatus;
-	int rc;
+	struct acpi_generic_status *estatus, *tmp;
+	struct acpi_generic_data *gdata;
+	const uuid_le *fru_id = &NULL_UUID_LE;
+	char *fru_text = "";
+	uuid_le *sec_type;
+	static u32 err_seq;
 
 	estatus = extlog_elog_entry_check(cpu, bank);
 	if (estatus == NULL)

@@ -148,7 +153,23 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	/* clear record status to enable BIOS to update it again */
 	estatus->block_status = 0;
 
-	rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu);
+	tmp = (struct acpi_generic_status *)elog_buf;
+	print_extlog_rcd(NULL, tmp, cpu);
+
+	/* log event via trace */
+	err_seq++;
+	gdata = (struct acpi_generic_data *)(tmp + 1);
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
+		fru_id = (uuid_le *)gdata->fru_id;
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
+		fru_text = gdata->fru_text;
+	sec_type = (uuid_le *)gdata->section_type;
+	if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
+		struct cper_sec_mem_err *mem = (void *)(gdata + 1);
+		if (gdata->error_data_length >= sizeof(*mem))
+			trace_extlog_mem_event(mem, err_seq, fru_id, fru_text,
+					       (u8)gdata->error_severity);
+	}
 
 	return NOTIFY_STOP;
 }

78 lines not on this page · raw message

index 4cac43a..da227a3 100644
@@ -23,4 +23,5 @@ static int __init ras_init(void)
 }
 subsys_initcall(ras_init);
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
 EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);

index ed088b9..3548160 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"

@@ -363,6 +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;

@@ -406,5 +425,7 @@ 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 *, void *);
+const char *cper_mem_err_unpack(struct trace_seq *, void *);
 
 #endif

68 lines not on this page · raw message

index a794691..174aac1 100644
@@ -35,7 +35,7 @@ TRACE_EVENT(extlog_mem_event,
                __field(u8, sev)
                __field(u64, pa)
                __field(u8, pa_mask_lsb)
-               __array(u8, fru_id, sizeof(uuid_le))
+               __field(uuid_le, fru_id)
                __string(fru_text, fru_text)
                __array(u8, data, sizeof(struct cper_mem_err_compact))
        ),

@@ -56,7 +56,7 @@ TRACE_EVENT(extlog_mem_event,
                        __entry->pa_mask_lsb = (u8)__ffs64(mem->physical_addr_mask);
                else
                        __entry->pa_mask_lsb = ~0;
-               memcpy(__entry->fru_id, fru_id, sizeof(uuid_le));
+               __entry->fru_id = *fru_id;
                __assign_str(fru_text, fru_text);
                cper_mem_err_pack(mem, __entry->data);
        ),

@@ -68,7 +68,7 @@ TRACE_EVENT(extlog_mem_event,
                  __entry->pa,
                  __entry->pa_mask_lsb,
                  cper_mem_err_unpack(p, __entry->data),
-                 __entry->fru_id,
+                 &__entry->fru_id,
                  __get_str(fru_text))
 );
 

index 0fd06fe..26b4f2e 100644
@@ -44,6 +44,12 @@
 #undef __field_ext
 #define __field_ext(type, item, filter_type)	type	item;
 
+#undef __field_struct
+#define __field_struct(type, item)	type	item;
+
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)	type	item;
+
 #undef __array
 #define __array(type, item, len)	type	item[len];
 

@@ -122,6 +128,12 @@
 #undef __field_ext
 #define __field_ext(type, item, filter_type)
 
+#undef __field_struct
+#define __field_struct(type, item)
+
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)
+
 #undef __array
 #define __array(type, item, len)
 

@@ -315,9 +327,21 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 	if (ret)							\
 		return ret;
 
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)			\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item),			\
+				 0, filter_type);			\
+	if (ret)							\
+		return ret;
+
 #undef __field
 #define __field(type, item)	__field_ext(type, item, FILTER_OTHER)
 
+#undef __field_struct
+#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER)
+
 #undef __array
 #define __array(type, item, len)					\
 	do {								\

@@ -379,6 +403,12 @@ ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 #undef __field_ext
 #define __field_ext(type, item, filter_type)
 
+#undef __field_struct
+#define __field_struct(type, item)
+
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)
+
 #undef __array
 #define __array(type, item, len)
 

@@ -550,6 +580,9 @@ static inline notrace int ftrace_get_offsets_##call(			\
 #undef __field
 #define __field(type, item)
 
+#undef __field_struct
+#define __field_struct(type, item)
+
 #undef __array
 #define __array(type, item, len)
 

index 1853341..e61da95 100644
@@ -16,6 +16,7 @@
 #include <asm/mce.h>
 
 #include "apei/apei-internal.h"
+#include <ras/ras_event.h>
 
 #define EXT_ELOG_ENTRY_MASK	GENMASK_ULL(51, 0) /* elog entry address mask */
 

@@ -137,8 +138,12 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	struct mce *mce = (struct mce *)data;
 	int	bank = mce->bank;
 	int	cpu = mce->extcpu;
-	struct acpi_generic_status *estatus;
-	int rc;
+	struct acpi_generic_status *estatus, *tmp;
+	struct acpi_generic_data *gdata;
+	const uuid_le *fru_id = &NULL_UUID_LE;
+	char *fru_text = "";
+	uuid_le *sec_type;
+	static u32 err_seq;
 
 	estatus = extlog_elog_entry_check(cpu, bank);
 	if (estatus == NULL)

@@ -148,7 +153,23 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 	/* clear record status to enable BIOS to update it again */
 	estatus->block_status = 0;
 
-	rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu);
+	tmp = (struct acpi_generic_status *)elog_buf;
+	print_extlog_rcd(NULL, tmp, cpu);
+
+	/* log event via trace */
+	err_seq++;
+	gdata = (struct acpi_generic_data *)(tmp + 1);
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
+		fru_id = (uuid_le *)gdata->fru_id;
+	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
+		fru_text = gdata->fru_text;
+	sec_type = (uuid_le *)gdata->section_type;
+	if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
+		struct cper_sec_mem_err *mem = (void *)(gdata + 1);
+		if (gdata->error_data_length >= sizeof(*mem))
+			trace_extlog_mem_event(mem, err_seq, fru_id, fru_text,
+					       (u8)gdata->error_severity);
+	}
 
 	return NOTIFY_STOP;
 }

77 lines not on this page · raw message

index 4cac43a..da227a3 100644
@@ -23,4 +23,5 @@ static int __init ras_init(void)
 }
 subsys_initcall(ras_init);
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
 EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);

index ed088b9..b65db8a 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"

@@ -363,6 +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;

@@ -406,5 +425,9 @@ 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

68 lines not on this page · raw message

index a99d4a6..0ad6f38 100644
@@ -223,19 +223,16 @@ static int __init extlog_init(void)
 	u64 cap;
 	int rc;
 
+	rdmsrl(MSR_IA32_MCG_CAP, cap);
+
+	if (!(cap & MCG_ELOG_P) || !extlog_get_l1addr())
+		return -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;
-
-	if (!extlog_get_l1addr())
-		return rc;
-
 	rc = -EINVAL;
 	/* get L1 header to fetch necessary information */
 	l1_hdr_size = sizeof(struct extlog_l1_head);