linux-kernel - [RFC PATCH 2/2] ACPI / APEI: Add reporting ARM64 CPU cache corrected error count

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20201208172959.1249-3-shiju.jose@huawei.com>
Date:   Tue, 8 Dec 2020 17:29:59 +0000
From:   Shiju Jose <shiju.jose@...wei.com>
To:     <linux-edac@...r.kernel.org>, <linux-acpi@...r.kernel.org>,
        <linux-kernel@...r.kernel.org>, <james.morse@....com>,
        <mchehab+huawei@...nel.org>, <bp@...en8.de>, <tony.luck@...el.com>,
        <rjw@...ysocki.net>, <lenb@...nel.org>, <rrichter@...vell.com>
CC:     <linuxarm@...wei.com>, <xuwei5@...wei.com>,
        <jonathan.cameron@...wei.com>, <john.garry@...wei.com>,
        <tanxiaofei@...wei.com>, <shameerali.kolothum.thodi@...wei.com>,
        <salil.mehta@...wei.com>, <shiju.jose@...wei.com>
Subject: [RFC PATCH 2/2] ACPI / APEI: Add reporting ARM64 CPU cache corrected error count

Add reporting ARM64 CPU cache corrected error count to the ghes_edac.
The error count would be updated in the EDAC CPU cache sysfs
interface.

Note: This patch would be recreated after the patch
"ACPI / APEI: do memory failure on the physical address reported by ARM processor error section"
would be merged on the mainline.

Signed-off-by: Shiju Jose <shiju.jose@...wei.com>
---
 drivers/acpi/apei/ghes.c | 68 ++++++++++++++++++++++++++++++++++++++--
 include/linux/cper.h     |  4 +++
 2 files changed, 69 insertions(+), 3 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index e7b0edbda0f8..37f8b09d810d 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -41,6 +41,7 @@
 #include <linux/uuid.h>
 #include <linux/ras.h>
 #include <linux/task_work.h>
+#include <linux/cacheinfo.h>
 
 #include <acpi/actbl1.h>
 #include <acpi/ghes.h>
@@ -523,6 +524,69 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
 #endif
 }
 
+static u8 arm_err_transaction_type_to_cache_type(u8 trans_type)
+{
+	switch (trans_type) {
+	case CPER_ARM_CACHE_TRANS_TYPE_INSTRUCTION:
+		return CACHE_TYPE_INST;
+	case CPER_ARM_CACHE_TRANS_TYPE_DATA:
+		return CACHE_TYPE_DATA;
+	case CPER_ARM_CACHE_TRANS_TYPE_GENERIC:
+	default:
+		return CACHE_TYPE_UNIFIED;
+	}
+}
+
+static void ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata)
+{
+	struct cper_sec_proc_arm *error = acpi_hest_get_payload(gdata);
+	struct cper_arm_err_info *err_info;
+	struct ghes_einfo_cpu einfo;
+	u8 transaction_type;
+	u64 error_info;
+	int sec_sev;
+	int i;
+
+	log_arm_hw_error(error);
+
+	sec_sev = ghes_severity(gdata->error_severity);
+
+#if defined(CONFIG_ARM64)
+	if (sec_sev == GHES_SEV_CORRECTED) {
+		memset(&einfo, 0, sizeof(einfo));
+		einfo.cpu = get_logical_index(error->mpidr);
+		if (einfo.cpu == -EINVAL)
+			return;
+
+		/*
+		 * ARM processor error types are cache/TLB/bus errors.
+		 * Presently corrected error count for caches only
+		 * is reported.
+		 */
+		err_info = (struct cper_arm_err_info *)(error + 1);
+
+		for (i = 0; i < error->err_info_num; i++) {
+			if (err_info->type != CPER_ARM_CACHE_ERROR)
+				continue;
+			einfo.ce_count = err_info->multiple_error + 1;
+
+			error_info = err_info->error_info;
+			if (!(error_info & CPER_ARM_ERR_VALID_TRANSACTION_TYPE) ||
+			    !(error_info & CPER_ARM_ERR_VALID_LEVEL))
+				continue;
+
+			transaction_type = ((error_info >> CPER_ARM_ERR_TRANSACTION_SHIFT)
+					& CPER_ARM_ERR_TRANSACTION_MASK);
+			einfo.cache_type = arm_err_transaction_type_to_cache_type(transaction_type);
+			einfo.cache_level = ((error_info >> CPER_ARM_ERR_LEVEL_SHIFT)
+					& CPER_ARM_ERR_LEVEL_MASK);
+			ghes_edac_report_cpu_error(&einfo);
+			err_info += 1;
+		}
+	}
+#endif
+}
+
 static BLOCKING_NOTIFIER_HEAD(vendor_record_notify_list);
 
 int ghes_register_vendor_record_notifier(struct notifier_block *nb)
@@ -605,9 +669,7 @@ static bool ghes_do_proc(struct ghes *ghes,
 			ghes_handle_aer(gdata);
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
-			struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
-
-			log_arm_hw_error(err);
+			ghes_handle_arm_hw_error(gdata);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 6a511a1078ca..0ea966af6ad9 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -314,6 +314,10 @@ enum {
 #define CPER_ARM_ERR_ACCESS_MODE_SHIFT		43
 #define CPER_ARM_ERR_ACCESS_MODE_MASK		GENMASK(0,0)
 
+#define CPER_ARM_CACHE_TRANS_TYPE_INSTRUCTION	0
+#define CPER_ARM_CACHE_TRANS_TYPE_DATA		1
+#define CPER_ARM_CACHE_TRANS_TYPE_GENERIC	2
+
 /*
  * All tables and structs must be byte-packed to match CPER
  * specification, since the tables are provided by the system BIOS
-- 
2.17.1