All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tyler Baicar <tbaicar@codeaurora.org>
To: christoffer.dall@linaro.org, marc.zyngier@arm.com,
	pbonzini@redhat.com, rkrcmar@redhat.com, linux@armlinux.org.uk,
	catalin.marinas@arm.com, will.deacon@arm.com, rjw@rjwysocki.net,
	lenb@kernel.org, matt@codeblueprint.co.uk,
	robert.moore@intel.com, lv.zheng@intel.com, nkaje@codeaurora.org,
	zjzhang@codeaurora.org, mark.rutland@arm.com,
	james.morse@arm.com, akpm@linux-foundation.org,
	eun.taik.lee@samsung.com, sandeepa.s.prabhu@gmail.com,
	labbott@redhat.com, shijie.huang@arm.com,
	rruigrok@codeaurora.org, paul.gortmaker@windriver.com,
	tn@semihalf.com, fu.wei@linaro.org, rostedt@goodmis.org,
	bristot@redhat.com, linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu, kvm@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-acpi@vger.kernel.org,
	linux-efi@vger.kernel.org, devel@acpica.org,
	Suzuki.Poulose@arm.com, punit.agrawal@arm.com, astone@redhat.com,
	harba@codeaur
Cc: Tyler Baicar <tbaicar@codeaurora.org>
Subject: [PATCH V9 02/10] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1
Date: Wed, 15 Feb 2017 10:44:44 -0700	[thread overview]
Message-ID: <1487180692-16732-3-git-send-email-tbaicar@codeaurora.org> (raw)
In-Reply-To: <1487180692-16732-1-git-send-email-tbaicar@codeaurora.org>

Currently when a RAS error is reported it is not timestamped.
The ACPI 6.1 spec adds the timestamp field to the generic error
data entry v3 structure. The timestamp of when the firmware
generated the error is now being reported.

Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Richard Ruigrok <rruigrok@codeaurora.org>
Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
Reviewed-by: James Morse <james.morse@arm.com>
---
 drivers/acpi/apei/ghes.c    |  9 ++++---
 drivers/firmware/efi/cper.c | 63 +++++++++++++++++++++++++++++++++++----------
 include/acpi/ghes.h         | 22 ++++++++++++++++
 3 files changed, 77 insertions(+), 17 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 5e1ec41..b25e7cf 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -420,7 +420,8 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int
 	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);
+
+	mem_err = acpi_hest_generic_data_payload(gdata);
 
 	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
@@ -457,7 +458,8 @@ static void ghes_do_proc(struct ghes *ghes,
 		if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
 				 CPER_SEC_PLATFORM_MEM)) {
 			struct cper_sec_mem_err *mem_err;
-			mem_err = (struct cper_sec_mem_err *)(gdata+1);
+
+			mem_err = acpi_hest_generic_data_payload(gdata);
 			ghes_edac_report_mem_error(ghes, sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
@@ -467,7 +469,8 @@ static void ghes_do_proc(struct ghes *ghes,
 		else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
 				      CPER_SEC_PCIE)) {
 			struct cper_sec_pcie *pcie_err;
-			pcie_err = (struct cper_sec_pcie *)(gdata+1);
+
+			pcie_err = acpi_hest_generic_data_payload(gdata);
 			if (sev == GHES_SEV_RECOVERABLE &&
 			    sec_sev == GHES_SEV_RECOVERABLE &&
 			    pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index d425374..8fa4e23 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -32,6 +32,9 @@
 #include <linux/acpi.h>
 #include <linux/pci.h>
 #include <linux/aer.h>
+#include <linux/printk.h>
+#include <linux/bcd.h>
+#include <acpi/ghes.h>
 
 #define INDENT_SP	" "
 
@@ -386,13 +389,37 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
 }
 
+static void cper_estatus_print_section_v300(const char *pfx,
+	const struct acpi_hest_generic_data_v300 *gdata)
+{
+	__u8 hour, min, sec, day, mon, year, century, *timestamp;
+
+	if (gdata->validation_bits & ACPI_HEST_GEN_VALID_TIMESTAMP) {
+		timestamp = (__u8 *)&(gdata->time_stamp);
+		sec = bcd2bin(timestamp[0]);
+		min = bcd2bin(timestamp[1]);
+		hour = bcd2bin(timestamp[2]);
+		day = bcd2bin(timestamp[4]);
+		mon = bcd2bin(timestamp[5]);
+		year = bcd2bin(timestamp[6]);
+		century = bcd2bin(timestamp[7]);
+		printk("%stime: %7s %02d%02d-%02d-%02d %02d:%02d:%02d\n", pfx,
+			0x01 & *(timestamp + 3) ? "precise" : "", century,
+			year, mon, day, hour, min, sec);
+	}
+}
+
 static void cper_estatus_print_section(
-	const char *pfx, const struct acpi_hest_generic_data *gdata, int sec_no)
+	const char *pfx, struct acpi_hest_generic_data *gdata, int sec_no)
 {
 	uuid_le *sec_type = (uuid_le *)gdata->section_type;
 	__u16 severity;
 	char newpfx[64];
 
+	if (acpi_hest_generic_data_version(gdata) >= 3)
+		cper_estatus_print_section_v300(pfx,
+			(const struct acpi_hest_generic_data_v300 *)gdata);
+
 	severity = gdata->error_severity;
 	printk("%s""Error %d, type: %s\n", pfx, sec_no,
 	       cper_severity_str(severity));
@@ -403,14 +430,18 @@ static void cper_estatus_print_section(
 
 	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
 	if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_GENERIC)) {
-		struct cper_sec_proc_generic *proc_err = (void *)(gdata + 1);
+		struct cper_sec_proc_generic *proc_err;
+
+		proc_err = acpi_hest_generic_data_payload(gdata);
 		printk("%s""section_type: general processor error\n", newpfx);
 		if (gdata->error_data_length >= sizeof(*proc_err))
 			cper_print_proc_generic(newpfx, proc_err);
 		else
 			goto err_section_too_small;
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
-		struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
+		struct cper_sec_mem_err *mem_err;
+
+		mem_err = acpi_hest_generic_data_payload(gdata);
 		printk("%s""section_type: memory error\n", newpfx);
 		if (gdata->error_data_length >=
 		    sizeof(struct cper_sec_mem_err_old))
@@ -419,7 +450,9 @@ static void cper_estatus_print_section(
 		else
 			goto err_section_too_small;
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {
-		struct cper_sec_pcie *pcie = (void *)(gdata + 1);
+		struct cper_sec_pcie *pcie;
+
+		pcie = acpi_hest_generic_data_payload(gdata);
 		printk("%s""section_type: PCIe error\n", newpfx);
 		if (gdata->error_data_length >= sizeof(*pcie))
 			cper_print_pcie(newpfx, pcie, gdata);
@@ -438,7 +471,7 @@ void cper_estatus_print(const char *pfx,
 			const struct acpi_hest_generic_status *estatus)
 {
 	struct acpi_hest_generic_data *gdata;
-	unsigned int data_len, gedata_len;
+	unsigned int data_len;
 	int sec_no = 0;
 	char newpfx[64];
 	__u16 severity;
@@ -451,12 +484,13 @@ void cper_estatus_print(const char *pfx,
 	printk("%s""event severity: %s\n", pfx, cper_severity_str(severity));
 	data_len = estatus->data_length;
 	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+
 	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
-	while (data_len >= sizeof(*gdata)) {
-		gedata_len = gdata->error_data_length;
+
+	while (data_len >= acpi_hest_generic_data_size(gdata)) {
 		cper_estatus_print_section(newpfx, gdata, sec_no);
-		data_len -= gedata_len + sizeof(*gdata);
-		gdata = (void *)(gdata + 1) + gedata_len;
+		data_len -= acpi_hest_generic_data_record_size(gdata);
+		gdata = acpi_hest_generic_data_next(gdata);
 		sec_no++;
 	}
 }
@@ -486,12 +520,13 @@ int cper_estatus_check(const struct acpi_hest_generic_status *estatus)
 		return rc;
 	data_len = estatus->data_length;
 	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
-	while (data_len >= sizeof(*gdata)) {
-		gedata_len = gdata->error_data_length;
-		if (gedata_len > data_len - sizeof(*gdata))
+
+	while (data_len >= acpi_hest_generic_data_size(gdata)) {
+		gedata_len = acpi_hest_generic_data_error_length(gdata);
+		if (gedata_len > data_len - acpi_hest_generic_data_size(gdata))
 			return -EINVAL;
-		data_len -= gedata_len + sizeof(*gdata);
-		gdata = (void *)(gdata + 1) + gedata_len;
+		data_len -= gedata_len + acpi_hest_generic_data_size(gdata);
+		gdata = acpi_hest_generic_data_next(gdata);
 	}
 	if (data_len)
 		return -EINVAL;
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 68f088a..6ae318b 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -12,6 +12,18 @@
 #define GHES_TO_CLEAR		0x0001
 #define GHES_EXITING		0x0002
 
+#define acpi_hest_generic_data_error_length(gdata)	\
+	(((struct acpi_hest_generic_data *)(gdata))->error_data_length)
+#define acpi_hest_generic_data_size(gdata)		\
+	((acpi_hest_generic_data_version(gdata) >= 3) ?	\
+	sizeof(struct acpi_hest_generic_data_v300) :	\
+	sizeof(struct acpi_hest_generic_data))
+#define acpi_hest_generic_data_record_size(gdata)	\
+	(acpi_hest_generic_data_size(gdata) +		\
+	acpi_hest_generic_data_error_length(gdata))
+#define acpi_hest_generic_data_next(gdata)		\
+	((void *)(gdata) + acpi_hest_generic_data_record_size(gdata))
+
 struct ghes {
 	union {
 		struct acpi_hest_generic *generic;
@@ -73,3 +85,13 @@ static inline void ghes_edac_unregister(struct ghes *ghes)
 {
 }
 #endif
+
+#define acpi_hest_generic_data_version(gdata)			\
+	(gdata->revision >> 8)
+
+static inline void *acpi_hest_generic_data_payload(struct acpi_hest_generic_data *gdata)
+{
+	return acpi_hest_generic_data_version(gdata) >= 3 ?
+		(void *)(((struct acpi_hest_generic_data_v300 *)(gdata)) + 1) :
+		gdata + 1;
+}
-- 
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.

WARNING: multiple messages have this Message-ID (diff)
From: Tyler Baicar <tbaicar@codeaurora.org>
To: christoffer.dall@linaro.org, marc.zyngier@arm.com,
	pbonzini@redhat.com, rkrcmar@redhat.com, linux@armlinux.org.uk,
	catalin.marinas@arm.com, will.deacon@arm.com, rjw@rjwysocki.net,
	lenb@kernel.org, matt@codeblueprint.co.uk,
	robert.moore@intel.com, lv.zheng@intel.com, nkaje@codeaurora.org,
	zjzhang@codeaurora.org, mark.rutland@arm.com,
	james.morse@arm.com, akpm@linux-foundation.org,
	eun.taik.lee@samsung.com, sandeepa.s.prabhu@gmail.com,
	labbott@redhat.com, shijie.huang@arm.com,
	rruigrok@codeaurora.org, paul.gortmaker@windriver.com,
	tn@semihalf.com, fu.wei@linaro.org, rostedt@goodmis.org,
	bristot@redhat.com, linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu, kvm@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-acpi@vger.kernel.org,
	linux-efi@vger.kernel.org, devel@acpica.org,
	Suzuki.Poulose@arm.com, punit.agrawal@arm.com, astone@redhat.com,
	harba@codeaurora.org, hanjun.guo@linaro.org,
	john.garry@huawei.com, shiju.jose@huawei.com
Cc: Tyler Baicar <tbaicar@codeaurora.org>
Subject: [PATCH V9 02/10] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1
Date: Wed, 15 Feb 2017 10:44:44 -0700	[thread overview]
Message-ID: <1487180692-16732-3-git-send-email-tbaicar@codeaurora.org> (raw)
In-Reply-To: <1487180692-16732-1-git-send-email-tbaicar@codeaurora.org>

Currently when a RAS error is reported it is not timestamped.
The ACPI 6.1 spec adds the timestamp field to the generic error
data entry v3 structure. The timestamp of when the firmware
generated the error is now being reported.

Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Richard Ruigrok <rruigrok@codeaurora.org>
Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
Reviewed-by: James Morse <james.morse@arm.com>
---
 drivers/acpi/apei/ghes.c    |  9 ++++---
 drivers/firmware/efi/cper.c | 63 +++++++++++++++++++++++++++++++++++----------
 include/acpi/ghes.h         | 22 ++++++++++++++++
 3 files changed, 77 insertions(+), 17 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 5e1ec41..b25e7cf 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -420,7 +420,8 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int
 	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);
+
+	mem_err = acpi_hest_generic_data_payload(gdata);
 
 	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
@@ -457,7 +458,8 @@ static void ghes_do_proc(struct ghes *ghes,
 		if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
 				 CPER_SEC_PLATFORM_MEM)) {
 			struct cper_sec_mem_err *mem_err;
-			mem_err = (struct cper_sec_mem_err *)(gdata+1);
+
+			mem_err = acpi_hest_generic_data_payload(gdata);
 			ghes_edac_report_mem_error(ghes, sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
@@ -467,7 +469,8 @@ static void ghes_do_proc(struct ghes *ghes,
 		else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
 				      CPER_SEC_PCIE)) {
 			struct cper_sec_pcie *pcie_err;
-			pcie_err = (struct cper_sec_pcie *)(gdata+1);
+
+			pcie_err = acpi_hest_generic_data_payload(gdata);
 			if (sev == GHES_SEV_RECOVERABLE &&
 			    sec_sev == GHES_SEV_RECOVERABLE &&
 			    pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index d425374..8fa4e23 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -32,6 +32,9 @@
 #include <linux/acpi.h>
 #include <linux/pci.h>
 #include <linux/aer.h>
+#include <linux/printk.h>
+#include <linux/bcd.h>
+#include <acpi/ghes.h>
 
 #define INDENT_SP	" "
 
@@ -386,13 +389,37 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
 }
 
+static void cper_estatus_print_section_v300(const char *pfx,
+	const struct acpi_hest_generic_data_v300 *gdata)
+{
+	__u8 hour, min, sec, day, mon, year, century, *timestamp;
+
+	if (gdata->validation_bits & ACPI_HEST_GEN_VALID_TIMESTAMP) {
+		timestamp = (__u8 *)&(gdata->time_stamp);
+		sec = bcd2bin(timestamp[0]);
+		min = bcd2bin(timestamp[1]);
+		hour = bcd2bin(timestamp[2]);
+		day = bcd2bin(timestamp[4]);
+		mon = bcd2bin(timestamp[5]);
+		year = bcd2bin(timestamp[6]);
+		century = bcd2bin(timestamp[7]);
+		printk("%stime: %7s %02d%02d-%02d-%02d %02d:%02d:%02d\n", pfx,
+			0x01 & *(timestamp + 3) ? "precise" : "", century,
+			year, mon, day, hour, min, sec);
+	}
+}
+
 static void cper_estatus_print_section(
-	const char *pfx, const struct acpi_hest_generic_data *gdata, int sec_no)
+	const char *pfx, struct acpi_hest_generic_data *gdata, int sec_no)
 {
 	uuid_le *sec_type = (uuid_le *)gdata->section_type;
 	__u16 severity;
 	char newpfx[64];
 
+	if (acpi_hest_generic_data_version(gdata) >= 3)
+		cper_estatus_print_section_v300(pfx,
+			(const struct acpi_hest_generic_data_v300 *)gdata);
+
 	severity = gdata->error_severity;
 	printk("%s""Error %d, type: %s\n", pfx, sec_no,
 	       cper_severity_str(severity));
@@ -403,14 +430,18 @@ static void cper_estatus_print_section(
 
 	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
 	if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_GENERIC)) {
-		struct cper_sec_proc_generic *proc_err = (void *)(gdata + 1);
+		struct cper_sec_proc_generic *proc_err;
+
+		proc_err = acpi_hest_generic_data_payload(gdata);
 		printk("%s""section_type: general processor error\n", newpfx);
 		if (gdata->error_data_length >= sizeof(*proc_err))
 			cper_print_proc_generic(newpfx, proc_err);
 		else
 			goto err_section_too_small;
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
-		struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
+		struct cper_sec_mem_err *mem_err;
+
+		mem_err = acpi_hest_generic_data_payload(gdata);
 		printk("%s""section_type: memory error\n", newpfx);
 		if (gdata->error_data_length >=
 		    sizeof(struct cper_sec_mem_err_old))
@@ -419,7 +450,9 @@ static void cper_estatus_print_section(
 		else
 			goto err_section_too_small;
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {
-		struct cper_sec_pcie *pcie = (void *)(gdata + 1);
+		struct cper_sec_pcie *pcie;
+
+		pcie = acpi_hest_generic_data_payload(gdata);
 		printk("%s""section_type: PCIe error\n", newpfx);
 		if (gdata->error_data_length >= sizeof(*pcie))
 			cper_print_pcie(newpfx, pcie, gdata);
@@ -438,7 +471,7 @@ void cper_estatus_print(const char *pfx,
 			const struct acpi_hest_generic_status *estatus)
 {
 	struct acpi_hest_generic_data *gdata;
-	unsigned int data_len, gedata_len;
+	unsigned int data_len;
 	int sec_no = 0;
 	char newpfx[64];
 	__u16 severity;
@@ -451,12 +484,13 @@ void cper_estatus_print(const char *pfx,
 	printk("%s""event severity: %s\n", pfx, cper_severity_str(severity));
 	data_len = estatus->data_length;
 	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+
 	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
-	while (data_len >= sizeof(*gdata)) {
-		gedata_len = gdata->error_data_length;
+
+	while (data_len >= acpi_hest_generic_data_size(gdata)) {
 		cper_estatus_print_section(newpfx, gdata, sec_no);
-		data_len -= gedata_len + sizeof(*gdata);
-		gdata = (void *)(gdata + 1) + gedata_len;
+		data_len -= acpi_hest_generic_data_record_size(gdata);
+		gdata = acpi_hest_generic_data_next(gdata);
 		sec_no++;
 	}
 }
@@ -486,12 +520,13 @@ int cper_estatus_check(const struct acpi_hest_generic_status *estatus)
 		return rc;
 	data_len = estatus->data_length;
 	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
-	while (data_len >= sizeof(*gdata)) {
-		gedata_len = gdata->error_data_length;
-		if (gedata_len > data_len - sizeof(*gdata))
+
+	while (data_len >= acpi_hest_generic_data_size(gdata)) {
+		gedata_len = acpi_hest_generic_data_error_length(gdata);
+		if (gedata_len > data_len - acpi_hest_generic_data_size(gdata))
 			return -EINVAL;
-		data_len -= gedata_len + sizeof(*gdata);
-		gdata = (void *)(gdata + 1) + gedata_len;
+		data_len -= gedata_len + acpi_hest_generic_data_size(gdata);
+		gdata = acpi_hest_generic_data_next(gdata);
 	}
 	if (data_len)
 		return -EINVAL;
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 68f088a..6ae318b 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -12,6 +12,18 @@
 #define GHES_TO_CLEAR		0x0001
 #define GHES_EXITING		0x0002
 
+#define acpi_hest_generic_data_error_length(gdata)	\
+	(((struct acpi_hest_generic_data *)(gdata))->error_data_length)
+#define acpi_hest_generic_data_size(gdata)		\
+	((acpi_hest_generic_data_version(gdata) >= 3) ?	\
+	sizeof(struct acpi_hest_generic_data_v300) :	\
+	sizeof(struct acpi_hest_generic_data))
+#define acpi_hest_generic_data_record_size(gdata)	\
+	(acpi_hest_generic_data_size(gdata) +		\
+	acpi_hest_generic_data_error_length(gdata))
+#define acpi_hest_generic_data_next(gdata)		\
+	((void *)(gdata) + acpi_hest_generic_data_record_size(gdata))
+
 struct ghes {
 	union {
 		struct acpi_hest_generic *generic;
@@ -73,3 +85,13 @@ static inline void ghes_edac_unregister(struct ghes *ghes)
 {
 }
 #endif
+
+#define acpi_hest_generic_data_version(gdata)			\
+	(gdata->revision >> 8)
+
+static inline void *acpi_hest_generic_data_payload(struct acpi_hest_generic_data *gdata)
+{
+	return acpi_hest_generic_data_version(gdata) >= 3 ?
+		(void *)(((struct acpi_hest_generic_data_v300 *)(gdata)) + 1) :
+		gdata + 1;
+}
-- 
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.

WARNING: multiple messages have this Message-ID (diff)
From: tbaicar@codeaurora.org (Tyler Baicar)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH V9 02/10] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1
Date: Wed, 15 Feb 2017 10:44:44 -0700	[thread overview]
Message-ID: <1487180692-16732-3-git-send-email-tbaicar@codeaurora.org> (raw)
In-Reply-To: <1487180692-16732-1-git-send-email-tbaicar@codeaurora.org>

Currently when a RAS error is reported it is not timestamped.
The ACPI 6.1 spec adds the timestamp field to the generic error
data entry v3 structure. The timestamp of when the firmware
generated the error is now being reported.

Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Richard Ruigrok <rruigrok@codeaurora.org>
Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
Reviewed-by: James Morse <james.morse@arm.com>
---
 drivers/acpi/apei/ghes.c    |  9 ++++---
 drivers/firmware/efi/cper.c | 63 +++++++++++++++++++++++++++++++++++----------
 include/acpi/ghes.h         | 22 ++++++++++++++++
 3 files changed, 77 insertions(+), 17 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 5e1ec41..b25e7cf 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -420,7 +420,8 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int
 	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);
+
+	mem_err = acpi_hest_generic_data_payload(gdata);
 
 	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
@@ -457,7 +458,8 @@ static void ghes_do_proc(struct ghes *ghes,
 		if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
 				 CPER_SEC_PLATFORM_MEM)) {
 			struct cper_sec_mem_err *mem_err;
-			mem_err = (struct cper_sec_mem_err *)(gdata+1);
+
+			mem_err = acpi_hest_generic_data_payload(gdata);
 			ghes_edac_report_mem_error(ghes, sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
@@ -467,7 +469,8 @@ static void ghes_do_proc(struct ghes *ghes,
 		else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
 				      CPER_SEC_PCIE)) {
 			struct cper_sec_pcie *pcie_err;
-			pcie_err = (struct cper_sec_pcie *)(gdata+1);
+
+			pcie_err = acpi_hest_generic_data_payload(gdata);
 			if (sev == GHES_SEV_RECOVERABLE &&
 			    sec_sev == GHES_SEV_RECOVERABLE &&
 			    pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index d425374..8fa4e23 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -32,6 +32,9 @@
 #include <linux/acpi.h>
 #include <linux/pci.h>
 #include <linux/aer.h>
+#include <linux/printk.h>
+#include <linux/bcd.h>
+#include <acpi/ghes.h>
 
 #define INDENT_SP	" "
 
@@ -386,13 +389,37 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
 }
 
+static void cper_estatus_print_section_v300(const char *pfx,
+	const struct acpi_hest_generic_data_v300 *gdata)
+{
+	__u8 hour, min, sec, day, mon, year, century, *timestamp;
+
+	if (gdata->validation_bits & ACPI_HEST_GEN_VALID_TIMESTAMP) {
+		timestamp = (__u8 *)&(gdata->time_stamp);
+		sec = bcd2bin(timestamp[0]);
+		min = bcd2bin(timestamp[1]);
+		hour = bcd2bin(timestamp[2]);
+		day = bcd2bin(timestamp[4]);
+		mon = bcd2bin(timestamp[5]);
+		year = bcd2bin(timestamp[6]);
+		century = bcd2bin(timestamp[7]);
+		printk("%stime: %7s %02d%02d-%02d-%02d %02d:%02d:%02d\n", pfx,
+			0x01 & *(timestamp + 3) ? "precise" : "", century,
+			year, mon, day, hour, min, sec);
+	}
+}
+
 static void cper_estatus_print_section(
-	const char *pfx, const struct acpi_hest_generic_data *gdata, int sec_no)
+	const char *pfx, struct acpi_hest_generic_data *gdata, int sec_no)
 {
 	uuid_le *sec_type = (uuid_le *)gdata->section_type;
 	__u16 severity;
 	char newpfx[64];
 
+	if (acpi_hest_generic_data_version(gdata) >= 3)
+		cper_estatus_print_section_v300(pfx,
+			(const struct acpi_hest_generic_data_v300 *)gdata);
+
 	severity = gdata->error_severity;
 	printk("%s""Error %d, type: %s\n", pfx, sec_no,
 	       cper_severity_str(severity));
@@ -403,14 +430,18 @@ static void cper_estatus_print_section(
 
 	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
 	if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_GENERIC)) {
-		struct cper_sec_proc_generic *proc_err = (void *)(gdata + 1);
+		struct cper_sec_proc_generic *proc_err;
+
+		proc_err = acpi_hest_generic_data_payload(gdata);
 		printk("%s""section_type: general processor error\n", newpfx);
 		if (gdata->error_data_length >= sizeof(*proc_err))
 			cper_print_proc_generic(newpfx, proc_err);
 		else
 			goto err_section_too_small;
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
-		struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
+		struct cper_sec_mem_err *mem_err;
+
+		mem_err = acpi_hest_generic_data_payload(gdata);
 		printk("%s""section_type: memory error\n", newpfx);
 		if (gdata->error_data_length >=
 		    sizeof(struct cper_sec_mem_err_old))
@@ -419,7 +450,9 @@ static void cper_estatus_print_section(
 		else
 			goto err_section_too_small;
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {
-		struct cper_sec_pcie *pcie = (void *)(gdata + 1);
+		struct cper_sec_pcie *pcie;
+
+		pcie = acpi_hest_generic_data_payload(gdata);
 		printk("%s""section_type: PCIe error\n", newpfx);
 		if (gdata->error_data_length >= sizeof(*pcie))
 			cper_print_pcie(newpfx, pcie, gdata);
@@ -438,7 +471,7 @@ void cper_estatus_print(const char *pfx,
 			const struct acpi_hest_generic_status *estatus)
 {
 	struct acpi_hest_generic_data *gdata;
-	unsigned int data_len, gedata_len;
+	unsigned int data_len;
 	int sec_no = 0;
 	char newpfx[64];
 	__u16 severity;
@@ -451,12 +484,13 @@ void cper_estatus_print(const char *pfx,
 	printk("%s""event severity: %s\n", pfx, cper_severity_str(severity));
 	data_len = estatus->data_length;
 	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+
 	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
-	while (data_len >= sizeof(*gdata)) {
-		gedata_len = gdata->error_data_length;
+
+	while (data_len >= acpi_hest_generic_data_size(gdata)) {
 		cper_estatus_print_section(newpfx, gdata, sec_no);
-		data_len -= gedata_len + sizeof(*gdata);
-		gdata = (void *)(gdata + 1) + gedata_len;
+		data_len -= acpi_hest_generic_data_record_size(gdata);
+		gdata = acpi_hest_generic_data_next(gdata);
 		sec_no++;
 	}
 }
@@ -486,12 +520,13 @@ int cper_estatus_check(const struct acpi_hest_generic_status *estatus)
 		return rc;
 	data_len = estatus->data_length;
 	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
-	while (data_len >= sizeof(*gdata)) {
-		gedata_len = gdata->error_data_length;
-		if (gedata_len > data_len - sizeof(*gdata))
+
+	while (data_len >= acpi_hest_generic_data_size(gdata)) {
+		gedata_len = acpi_hest_generic_data_error_length(gdata);
+		if (gedata_len > data_len - acpi_hest_generic_data_size(gdata))
 			return -EINVAL;
-		data_len -= gedata_len + sizeof(*gdata);
-		gdata = (void *)(gdata + 1) + gedata_len;
+		data_len -= gedata_len + acpi_hest_generic_data_size(gdata);
+		gdata = acpi_hest_generic_data_next(gdata);
 	}
 	if (data_len)
 		return -EINVAL;
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 68f088a..6ae318b 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -12,6 +12,18 @@
 #define GHES_TO_CLEAR		0x0001
 #define GHES_EXITING		0x0002
 
+#define acpi_hest_generic_data_error_length(gdata)	\
+	(((struct acpi_hest_generic_data *)(gdata))->error_data_length)
+#define acpi_hest_generic_data_size(gdata)		\
+	((acpi_hest_generic_data_version(gdata) >= 3) ?	\
+	sizeof(struct acpi_hest_generic_data_v300) :	\
+	sizeof(struct acpi_hest_generic_data))
+#define acpi_hest_generic_data_record_size(gdata)	\
+	(acpi_hest_generic_data_size(gdata) +		\
+	acpi_hest_generic_data_error_length(gdata))
+#define acpi_hest_generic_data_next(gdata)		\
+	((void *)(gdata) + acpi_hest_generic_data_record_size(gdata))
+
 struct ghes {
 	union {
 		struct acpi_hest_generic *generic;
@@ -73,3 +85,13 @@ static inline void ghes_edac_unregister(struct ghes *ghes)
 {
 }
 #endif
+
+#define acpi_hest_generic_data_version(gdata)			\
+	(gdata->revision >> 8)
+
+static inline void *acpi_hest_generic_data_payload(struct acpi_hest_generic_data *gdata)
+{
+	return acpi_hest_generic_data_version(gdata) >= 3 ?
+		(void *)(((struct acpi_hest_generic_data_v300 *)(gdata)) + 1) :
+		gdata + 1;
+}
-- 
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.

  parent reply	other threads:[~2017-02-15 17:44 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-02-15 17:44 [PATCH V9 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
2017-02-15 17:44 ` Tyler Baicar
2017-02-15 17:44 ` Tyler Baicar
2017-02-15 17:44 ` Tyler Baicar
2017-02-15 17:44 ` [PATCH V9 01/10] acpi: apei: read ack upon ghes record consumption Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44 ` Tyler Baicar [this message]
2017-02-15 17:44   ` [PATCH V9 02/10] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1 Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44 ` [PATCH V9 03/10] efi: parse ARM processor error Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44 ` [PATCH V9 04/10] arm64: exception: handle Synchronous External Abort Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44 ` [PATCH V9 05/10] acpi: apei: handle SEA notification type for ARMv8 Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 20:52   ` kbuild test robot
2017-02-15 20:52     ` kbuild test robot
2017-02-15 20:52     ` kbuild test robot
2017-02-15 20:52     ` kbuild test robot
2017-02-15 17:44 ` [PATCH V9 06/10] acpi: apei: panic OS with fatal error status block Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44 ` [PATCH V9 07/10] efi: print unrecognized CPER section Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44 ` [PATCH V9 08/10] ras: acpi / apei: generate trace event for " Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44 ` [PATCH V9 09/10] trace, ras: add ARM processor error trace event Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:47   ` Steven Rostedt
2017-02-15 17:47     ` Steven Rostedt
2017-02-15 17:47     ` Steven Rostedt
2017-02-15 17:51     ` Baicar, Tyler
2017-02-15 17:51       ` Baicar, Tyler
2017-02-15 17:51       ` Baicar, Tyler
2017-02-15 17:44 ` [PATCH V9 10/10] arm/arm64: KVM: add guest SEA support Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar
2017-02-15 17:44   ` Tyler Baicar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1487180692-16732-3-git-send-email-tbaicar@codeaurora.org \
    --to=tbaicar@codeaurora.org \
    --cc=Suzuki.Poulose@arm.com \
    --cc=akpm@linux-foundation.org \
    --cc=astone@redhat.com \
    --cc=bristot@redhat.com \
    --cc=catalin.marinas@arm.com \
    --cc=christoffer.dall@linaro.org \
    --cc=devel@acpica.org \
    --cc=eun.taik.lee@samsung.com \
    --cc=fu.wei@linaro.org \
    --cc=harba@codeaur \
    --cc=james.morse@arm.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=labbott@redhat.com \
    --cc=lenb@kernel.org \
    --cc=linux-acpi@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-efi@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=lv.zheng@intel.com \
    --cc=marc.zyngier@arm.com \
    --cc=mark.rutland@arm.com \
    --cc=matt@codeblueprint.co.uk \
    --cc=nkaje@codeaurora.org \
    --cc=paul.gortmaker@windriver.com \
    --cc=pbonzini@redhat.com \
    --cc=punit.agrawal@arm.com \
    --cc=rjw@rjwysocki.net \
    --cc=rkrcmar@redhat.com \
    --cc=robert.moore@intel.com \
    --cc=rostedt@goodmis.org \
    --cc=rruigrok@codeaurora.org \
    --cc=sandeepa.s.prabhu@gmail.com \
    --cc=shijie.huang@arm.com \
    --cc=tn@semihalf.com \
    --cc=will.deacon@arm.com \
    --cc=zjzhang@codeaurora.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.