Merge tag 'please-pull-extlog-trace' into x86/ras

Report extended error information ("extlog") using
a trace/event.  Provide a mechanism for a smart
daemon collecting this information to tell the kernel
to skip logging corrected errors to the console.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

drivers/Kconfig

@@ -176,4 +176,6 @@ source "drivers/powercap/Kconfig"
 
 source "drivers/mcb/Kconfig"
 
+source "drivers/ras/Kconfig"
+
 endmenu

drivers/Makefile

@@ -158,3 +158,4 @@ obj-$(CONFIG_NTB)		+= ntb/
 obj-$(CONFIG_FMC)		+= fmc/
 obj-$(CONFIG_POWERCAP)		+= powercap/
 obj-$(CONFIG_MCB)		+= mcb/
+obj-$(CONFIG_RAS)		+= ras/

drivers/acpi/Kconfig

@@ -370,6 +370,7 @@ config ACPI_EXTLOG
 	tristate "Extended Error Log support"
 	depends on X86_MCE && X86_LOCAL_APIC
 	select UEFI_CPER
+	select RAS
 	default n
 	help
 	  Certain usages such as Predictive Failure Analysis (PFA) require
@@ -384,6 +385,7 @@ config ACPI_EXTLOG
 
 	  Enhanced MCA Logging allows firmware to provide additional error
 	  information to system software, synchronous with MCE or CMCI. This
-	  driver adds support for that functionality.
+	  driver adds support for that functionality with corresponding
+	  tracepoint which carries that information to userspace.
 
 endif	# ACPI

drivers/acpi/acpi_extlog.c

@@ -12,10 +12,12 @@
 #include <linux/cper.h>
 #include <linux/ratelimit.h>
 #include <linux/edac.h>
+#include <linux/ras.h>
 #include <asm/cpu.h>
 #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 +139,12 @@ 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)
@@ -148,8 +154,29 @@ 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;
+
+	if (!ras_userspace_consumers()) {
+		print_extlog_rcd(NULL, tmp, cpu);
+		goto out;
+	}
+
+	/* 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);
+	}
 
+out:
 	return NOTIFY_STOP;
 }
 
@@ -196,19 +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);

drivers/edac/Kconfig

@@ -72,6 +72,7 @@ config EDAC_MCE_INJ
 
 config EDAC_MM_EDAC
 	tristate "Main Memory EDAC (Error Detection And Correction) reporting"
+	select RAS
 	help
 	  Some systems are able to detect and correct errors in main
 	  memory.  EDAC can report statistics on memory error

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 */

drivers/firmware/efi/cper.c

@@ -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 +200,136 @@ 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);
+
+static int cper_mem_err_location(struct cper_mem_err_compact *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;
+}
+
+static int cper_dimm_err_location(struct cper_mem_err_compact *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;
+}
+
+void cper_mem_err_pack(const struct cper_sec_mem_err *mem,
+		       struct cper_mem_err_compact *cmem)
+{
+	cmem->validation_bits = mem->validation_bits;
+	cmem->node = mem->node;
+	cmem->card = mem->card;
+	cmem->module = mem->module;
+	cmem->bank = mem->bank;
+	cmem->device = mem->device;
+	cmem->row = mem->row;
+	cmem->column = mem->column;
+	cmem->bit_pos = mem->bit_pos;
+	cmem->requestor_id = mem->requestor_id;
+	cmem->responder_id = mem->responder_id;
+	cmem->target_id = mem->target_id;
+	cmem->rank = mem->rank;
+	cmem->mem_array_handle = mem->mem_array_handle;
+	cmem->mem_dev_handle = mem->mem_dev_handle;
+}
+
+const char *cper_mem_err_unpack(struct trace_seq *p,
+				struct cper_mem_err_compact *cmem)
+{
+	const char *ret = p->buffer + p->len;
+
+	if (cper_mem_err_location(cmem, rcd_decode_str))
+		trace_seq_printf(p, "%s", rcd_decode_str);
+	if (cper_dimm_err_location(cmem, rcd_decode_str))
+		trace_seq_printf(p, "%s", rcd_decode_str);
+	trace_seq_putc(p, '\0');
+
+	return ret;
+}
+
+static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
+{
+	struct cper_mem_err_compact cmem;
+
+	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);
+	cper_mem_err_pack(mem, &cmem);
+	if (cper_mem_err_location(&cmem, 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(&cmem, 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 +348,8 @@ 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);

drivers/pci/pcie/aer/Kconfig

@@ -5,6 +5,7 @@
 config PCIEAER
 	boolean "Root Port Advanced Error Reporting support"
 	depends on PCIEPORTBUS
+	select RAS
 	default y
 	help
 	  This enables PCI Express Root Port Advanced Error Reporting

drivers/pci/pcie/aer/aerdrv_errprint.c

@@ -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

drivers/ras/Kconfig

+config RAS
+	bool

drivers/ras/Makefile

+obj-$(CONFIG_RAS) += ras.o debugfs.o

drivers/ras/debugfs.c

+#include <linux/debugfs.h>
+
+static struct dentry *ras_debugfs_dir;
+
+static atomic_t trace_count = ATOMIC_INIT(0);
+
+int ras_userspace_consumers(void)
+{
+	return atomic_read(&trace_count);
+}
+EXPORT_SYMBOL_GPL(ras_userspace_consumers);
+
+static int trace_show(struct seq_file *m, void *v)
+{
+	return atomic_read(&trace_count);
+}
+
+static int trace_open(struct inode *inode, struct file *file)
+{
+	atomic_inc(&trace_count);
+	return single_open(file, trace_show, NULL);
+}
+
+static int trace_release(struct inode *inode, struct file *file)
+{
+	atomic_dec(&trace_count);
+	return single_release(inode, file);
+}
+
+static const struct file_operations trace_fops = {
+	.open    = trace_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = trace_release,
+};
+
+int __init ras_add_daemon_trace(void)
+{
+	struct dentry *fentry;
+
+	if (!ras_debugfs_dir)
+		return -ENOENT;
+
+	fentry = debugfs_create_file("daemon_active", S_IRUSR, ras_debugfs_dir,
+				     NULL, &trace_fops);
+	if (!fentry)
+		return -ENODEV;
+
+	return 0;
+
+}
+
+void __init ras_debugfs_init(void)
+{
+	ras_debugfs_dir = debugfs_create_dir("ras", NULL);
+}

drivers/ras/ras.c

+/*
+ * Copyright (C) 2014 Intel Corporation
+ *
+ * Authors:
+ *	Chen, Gong <gong.chen@linux.intel.com>
+ */
+
+#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);

include/linux/cper.h

@@ -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"
@@ -35,6 +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
@@ -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

include/linux/ras.h

+#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

include/ras/ras_event.h

@@ -8,6 +8,71 @@
 #include <linux/tracepoint.h>
 #include <linux/edac.h>
 #include <linux/ktime.h>
+#include <linux/aer.h>
+#include <linux/cper.h>
+
+/*
+ * MCE Extended Error Log trace event
+ *
+ * These events are generated when hardware detects a corrected or
+ * uncorrected event.
+ */
+
+/* memory trace event */
+
+#if defined(CONFIG_ACPI_EXTLOG) || defined(CONFIG_ACPI_EXTLOG_MODULE)
+TRACE_EVENT(extlog_mem_event,
+	TP_PROTO(struct cper_sec_mem_err *mem,
+		 u32 err_seq,
+		 const uuid_le *fru_id,
+		 const char *fru_text,
+		 u8 sev),
+
+	TP_ARGS(mem, err_seq, fru_id, fru_text, sev),
+
+	TP_STRUCT__entry(
+		__field(u32, err_seq)
+		__field(u8, etype)
+		__field(u8, sev)
+		__field(u64, pa)
+		__field(u8, pa_mask_lsb)
+		__field_struct(uuid_le, fru_id)
+		__string(fru_text, fru_text)
+		__field_struct(struct cper_mem_err_compact, data)
+	),
+
+	TP_fast_assign(
+		__entry->err_seq = err_seq;
+		if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE)
+			__entry->etype = mem->error_type;
+		else
+			__entry->etype = ~0;
+		__entry->sev = sev;
+		if (mem->validation_bits & CPER_MEM_VALID_PA)
+			__entry->pa = mem->physical_addr;
+		else
+			__entry->pa = ~0ull;
+
+		if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
+			__entry->pa_mask_lsb = (u8)__ffs64(mem->physical_addr_mask);
+		else
+			__entry->pa_mask_lsb = ~0;
+		__entry->fru_id = *fru_id;
+		__assign_str(fru_text, fru_text);
+		cper_mem_err_pack(mem, &__entry->data);
+	),
+
+	TP_printk("{%d} %s error: %s physical addr: %016llx (mask lsb: %x) %sFRU: %pUl %.20s",
+		  __entry->err_seq,
+		  cper_severity_str(__entry->sev),
+		  cper_mem_err_type_str(__entry->etype),
+		  __entry->pa,
+		  __entry->pa_mask_lsb,
+		  cper_mem_err_unpack(p, &__entry->data),
+		  &__entry->fru_id,
+		  __get_str(fru_text))
+);
+#endif
 
 /*
  * Hardware Events Report
@@ -94,6 +159,69 @@ TRACE_EVENT(mc_event,
 		  __get_str(driver_detail))
 );
 
+/*
+ * PCIe AER Trace event
+ *
+ * These events are generated when hardware detects a corrected or
+ * uncorrected event on a PCIe device. The event report has
+ * the following structure:
+ *
+ * char * dev_name -	The name of the slot where the device resides
+ *			([domain:]bus:device.function).
+ * u32 status -		Either the correctable or uncorrectable register
+ *			indicating what error or errors have been seen
+ * u8 severity -	error severity 0:NONFATAL 1:FATAL 2:CORRECTED
+ */
+
+#define aer_correctable_errors		\
+	{BIT(0),	"Receiver Error"},		\
+	{BIT(6),	"Bad TLP"},			\
+	{BIT(7),	"Bad DLLP"},			\
+	{BIT(8),	"RELAY_NUM Rollover"},		\
+	{BIT(12),	"Replay Timer Timeout"},	\
+	{BIT(13),	"Advisory Non-Fatal"}
+
+#define aer_uncorrectable_errors		\
+	{BIT(4),	"Data Link Protocol"},		\
+	{BIT(12),	"Poisoned TLP"},		\
+	{BIT(13),	"Flow Control Protocol"},	\
+	{BIT(14),	"Completion Timeout"},		\
+	{BIT(15),	"Completer Abort"},		\
+	{BIT(16),	"Unexpected Completion"},	\
+	{BIT(17),	"Receiver Overflow"},		\
+	{BIT(18),	"Malformed TLP"},		\
+	{BIT(19),	"ECRC"},			\
+	{BIT(20),	"Unsupported Request"}
+
+TRACE_EVENT(aer_event,
+	TP_PROTO(const char *dev_name,
+		 const u32 status,
+		 const u8 severity),
+
+	TP_ARGS(dev_name, status, severity),
+
+	TP_STRUCT__entry(
+		__string(	dev_name,	dev_name	)
+		__field(	u32,		status		)
+		__field(	u8,		severity	)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name);
+		__entry->status		= status;
+		__entry->severity	= severity;
+	),
+
+	TP_printk("%s PCIe Bus Error: severity=%s, %s\n",
+		__get_str(dev_name),
+		__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))
+);
+
 #endif /* _TRACE_HW_EVENT_MC_H */
 
 /* This part must be outside protection */

include/trace/events/ras.h

-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM ras
-
-#if !defined(_TRACE_AER_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_AER_H
-
-#include <linux/tracepoint.h>
-#include <linux/aer.h>
-
-
-/*
- * PCIe AER Trace event
- *
- * These events are generated when hardware detects a corrected or
- * uncorrected event on a PCIe device. The event report has
- * the following structure:
- *
- * char * dev_name -	The name of the slot where the device resides
- *			([domain:]bus:device.function).
- * u32 status -		Either the correctable or uncorrectable register
- *			indicating what error or errors have been seen
- * u8 severity -	error severity 0:NONFATAL 1:FATAL 2:CORRECTED
- */
-
-#define aer_correctable_errors		\
-	{BIT(0),	"Receiver Error"},		\
-	{BIT(6),	"Bad TLP"},			\
-	{BIT(7),	"Bad DLLP"},			\
-	{BIT(8),	"RELAY_NUM Rollover"},		\
-	{BIT(12),	"Replay Timer Timeout"},	\
-	{BIT(13),	"Advisory Non-Fatal"}
-
-#define aer_uncorrectable_errors		\
-	{BIT(4),	"Data Link Protocol"},		\
-	{BIT(12),	"Poisoned TLP"},		\
-	{BIT(13),	"Flow Control Protocol"},	\
-	{BIT(14),	"Completion Timeout"},		\
-	{BIT(15),	"Completer Abort"},		\
-	{BIT(16),	"Unexpected Completion"},	\
-	{BIT(17),	"Receiver Overflow"},		\
-	{BIT(18),	"Malformed TLP"},		\
-	{BIT(19),	"ECRC"},			\
-	{BIT(20),	"Unsupported Request"}
-
-TRACE_EVENT(aer_event,
-	TP_PROTO(const char *dev_name,
-		 const u32 status,
-		 const u8 severity),
-
-	TP_ARGS(dev_name, status, severity),
-
-	TP_STRUCT__entry(
-		__string(	dev_name,	dev_name	)
-		__field(	u32,		status		)
-		__field(	u8,		severity	)
-	),
-
-	TP_fast_assign(
-		__assign_str(dev_name, dev_name);
-		__entry->status		= status;
-		__entry->severity	= severity;
-	),
-
-	TP_printk("%s PCIe Bus Error: severity=%s, %s\n",
-		__get_str(dev_name),
-		__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))
-);
-
-#endif /* _TRACE_AER_H */
-
-/* This part must be outside protection */
-#include <trace/define_trace.h>

include/trace/ftrace.h

@@ -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)
 

include/trace/syscall.h

@@ -4,6 +4,7 @@
 #include <linux/tracepoint.h>
 #include <linux/unistd.h>
 #include <linux/ftrace_event.h>
+#include <linux/thread_info.h>
 
 #include <asm/ptrace.h>
 
@@ -32,4 +33,18 @@ struct syscall_metadata {
 	struct ftrace_event_call *exit_event;
 };
 
+#if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS)
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+	else
+		clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+}
+#else
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+}
+#endif
+
 #endif /* _TRACE_SYSCALL_H */

kernel/fork.c

@@ -1487,7 +1487,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	total_forks++;
 	spin_unlock(&current->sighand->siglock);
+	syscall_tracepoint_update(p);
 	write_unlock_irq(&tasklist_lock);
+
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
 	if (clone_flags & CLONE_THREAD)

kernel/tracepoint.c

@@ -492,33 +492,29 @@ static int sys_tracepoint_refcount;
 
 void syscall_regfunc(void)
 {
-	unsigned long flags;
-	struct task_struct *g, *t;
+	struct task_struct *p, *t;
 
 	if (!sys_tracepoint_refcount) {
-		read_lock_irqsave(&tasklist_lock, flags);
-		do_each_thread(g, t) {
-			/* Skip kernel threads. */
-			if (t->mm)
-				set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
-		} while_each_thread(g, t);
-		read_unlock_irqrestore(&tasklist_lock, flags);
+		read_lock(&tasklist_lock);
+		for_each_process_thread(p, t) {
+			set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+		}
+		read_unlock(&tasklist_lock);
 	}
 	sys_tracepoint_refcount++;
 }
 
 void syscall_unregfunc(void)
 {
-	unsigned long flags;
-	struct task_struct *g, *t;
+	struct task_struct *p, *t;
 
 	sys_tracepoint_refcount--;
 	if (!sys_tracepoint_refcount) {
-		read_lock_irqsave(&tasklist_lock, flags);
-		do_each_thread(g, t) {
+		read_lock(&tasklist_lock);
+		for_each_process_thread(p, t) {
 			clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
-		} while_each_thread(g, t);
-		read_unlock_irqrestore(&tasklist_lock, flags);
+		}
+		read_unlock(&tasklist_lock);
 	}
 }
 #endif

samples/trace_events/trace-events-sample.h

@@ -56,7 +56,8 @@
  * struct:  This defines the way the data will be stored in the ring buffer.
  *    There are currently two types of elements. __field and __array.
  *    a __field is broken up into (type, name). Where type can be any
- *    type but an array.
+ *    primitive type (integer, long or pointer). __field_struct() can
+ *    be any static complex data value (struct, union, but not an array).
  *    For an array. there are three fields. (type, name, size). The
  *    type of elements in the array, the name of the field and the size
  *    of the array.