* [PATCH 1/2] drivers/edac: Add L1 and L2 error detection for A53 and A57
2021-02-01 11:57 [PATCH iv4 0/2] Add L1 and L2 error detection for A53 and A57 Sascha Hauer
@ 2021-02-01 11:57 ` Sascha Hauer
2021-02-01 11:57 ` [PATCH 2/2] dt-bindings: arm: cpus: Add edac-enabled property Sascha Hauer
1 sibling, 0 replies; 4+ messages in thread
From: Sascha Hauer @ 2021-02-01 11:57 UTC (permalink / raw)
To: linux-edac
Cc: Borislav Petkov, Mauro Carvalho Chehab, Tony Luck, James Morse,
Robert Richter, York Sun, kernel, linux-arm-kernel, Rob Herring,
Sascha Hauer
The Cortex A53 and A57 cores have error detection capabilities for the
L1/L2 Caches, this patch adds a driver for them.
Unfortunately there is no robust way to inject errors into the caches,
so this driver doesn't contain any code to actually test it. It has
been tested though with code taken from an older version of this driver
found here: https://lkml.org/lkml/2018/3/14/1203. For reasons stated
in this thread the error injection code is not suitable for mainline,
so it is removed from the driver.
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
---
drivers/edac/Kconfig | 6 +
drivers/edac/Makefile | 1 +
drivers/edac/cortex_arm64_l1_l2.c | 218 ++++++++++++++++++++++++++++++
3 files changed, 225 insertions(+)
create mode 100644 drivers/edac/cortex_arm64_l1_l2.c
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 81c42664f21b..116ad56534a4 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -539,4 +539,10 @@ config EDAC_DMC520
Support for error detection and correction on the
SoCs with ARM DMC-520 DRAM controller.
+config EDAC_CORTEX_ARM64_L1_L2
+ tristate "ARM Cortex A57/A53"
+ depends on ARM64
+ help
+ Support for L1/L2 cache error detection on ARM Cortex A57 and A53.
+
endif # EDAC
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index 464d3d8d850a..a324fbc1693e 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -89,3 +89,4 @@ obj-$(CONFIG_EDAC_QCOM) += qcom_edac.o
obj-$(CONFIG_EDAC_ASPEED) += aspeed_edac.o
obj-$(CONFIG_EDAC_BLUEFIELD) += bluefield_edac.o
obj-$(CONFIG_EDAC_DMC520) += dmc520_edac.o
+obj-$(CONFIG_EDAC_CORTEX_ARM64_L1_L2) += cortex_arm64_l1_l2.o
diff --git a/drivers/edac/cortex_arm64_l1_l2.c b/drivers/edac/cortex_arm64_l1_l2.c
new file mode 100644
index 000000000000..3b1e2f3ccab6
--- /dev/null
+++ b/drivers/edac/cortex_arm64_l1_l2.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Cortex A57 and A53 EDAC L1 and L2 cache error detection
+ *
+ * Copyright (c) 2020 Pengutronix, Sascha Hauer <s.hauer@pengutronix.de>
+ *
+ * Based on Code from:
+ * Copyright (c) 2018, NXP Semiconductor
+ * Author: York Sun <york.sun@nxp.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/of_device.h>
+#include <linux/bitfield.h>
+#include <asm/smp_plat.h>
+
+#include "edac_module.h"
+
+#define DRVNAME "cortex-arm64-edac"
+
+#define CPUMERRSR_EL1_RAMID GENMASK(30, 24)
+
+#define CPUMERRSR_EL1_VALID BIT(31)
+#define CPUMERRSR_EL1_FATAL BIT(63)
+
+#define L1_I_TAG_RAM 0x00
+#define L1_I_DATA_RAM 0x01
+#define L1_D_TAG_RAM 0x08
+#define L1_D_DATA_RAM 0x09
+#define L1_D_DIRTY_RAM 0x14
+#define TLB_RAM 0x18
+
+#define L2MERRSR_EL1_VALID BIT(31)
+#define L2MERRSR_EL1_FATAL BIT(63)
+
+struct merrsr {
+ u64 cpumerr;
+ u64 l2merr;
+};
+
+#define MESSAGE_SIZE 64
+
+#define SYS_CPUMERRSR_EL1 sys_reg(3, 1, 15, 2, 2)
+#define SYS_L2MERRSR_EL1 sys_reg(3, 1, 15, 2, 3)
+
+static struct cpumask compat_mask;
+
+static void report_errors(struct edac_device_ctl_info *edac_ctl, int cpu,
+ struct merrsr *merrsr)
+{
+ char msg[MESSAGE_SIZE];
+ u64 cpumerr = merrsr->cpumerr;
+ u64 l2merr = merrsr->l2merr;
+
+ if (cpumerr & CPUMERRSR_EL1_VALID) {
+ const char *str;
+ bool fatal = cpumerr & CPUMERRSR_EL1_FATAL;
+
+ switch (FIELD_GET(CPUMERRSR_EL1_RAMID, cpumerr)) {
+ case L1_I_TAG_RAM:
+ str = "L1-I Tag RAM";
+ break;
+ case L1_I_DATA_RAM:
+ str = "L1-I Data RAM";
+ break;
+ case L1_D_TAG_RAM:
+ str = "L1-D Tag RAM";
+ break;
+ case L1_D_DATA_RAM:
+ str = "L1-D Data RAM";
+ break;
+ case L1_D_DIRTY_RAM:
+ str = "L1 Dirty RAM";
+ break;
+ case TLB_RAM:
+ str = "TLB RAM";
+ break;
+ default:
+ str = "unknown";
+ break;
+ }
+
+ snprintf(msg, MESSAGE_SIZE, "%s %s error(s) on CPU %d",
+ str, fatal ? "fatal" : "correctable", cpu);
+
+ if (fatal)
+ edac_device_handle_ue(edac_ctl, cpu, 0, msg);
+ else
+ edac_device_handle_ce(edac_ctl, cpu, 0, msg);
+ }
+
+ if (l2merr & L2MERRSR_EL1_VALID) {
+ bool fatal = l2merr & L2MERRSR_EL1_FATAL;
+
+ snprintf(msg, MESSAGE_SIZE, "L2 %s error(s) on CPU %d",
+ fatal ? "fatal" : "correctable", cpu);
+ if (fatal)
+ edac_device_handle_ue(edac_ctl, cpu, 1, msg);
+ else
+ edac_device_handle_ce(edac_ctl, cpu, 1, msg);
+ }
+}
+
+static void read_errors(void *data)
+{
+ struct merrsr *merrsr = data;
+
+ merrsr->cpumerr = read_sysreg_s(SYS_CPUMERRSR_EL1);
+ write_sysreg_s(0, SYS_CPUMERRSR_EL1);
+ merrsr->l2merr = read_sysreg_s(SYS_L2MERRSR_EL1);
+ write_sysreg_s(0, SYS_L2MERRSR_EL1);
+}
+
+static void cortex_arm64_edac_check(struct edac_device_ctl_info *edac_ctl)
+{
+ struct merrsr merrsr;
+ int cpu;
+
+ for_each_cpu_and(cpu, cpu_online_mask, &compat_mask) {
+ smp_call_function_single(cpu, read_errors, &merrsr, true);
+ report_errors(edac_ctl, cpu, &merrsr);
+ }
+}
+
+static int cortex_arm64_edac_probe(struct platform_device *pdev)
+{
+ struct edac_device_ctl_info *edac_ctl;
+ struct device *dev = &pdev->dev;
+ int rc;
+
+ edac_ctl = edac_device_alloc_ctl_info(0, "cpu",
+ num_possible_cpus(), "L", 2, 1, NULL, 0,
+ edac_device_alloc_index());
+ if (!edac_ctl)
+ return -ENOMEM;
+
+ edac_ctl->edac_check = cortex_arm64_edac_check;
+ edac_ctl->dev = dev;
+ edac_ctl->mod_name = dev_name(dev);
+ edac_ctl->dev_name = dev_name(dev);
+ edac_ctl->ctl_name = DRVNAME;
+ dev_set_drvdata(dev, edac_ctl);
+
+ rc = edac_device_add_device(edac_ctl);
+ if (rc)
+ goto out_dev;
+
+ return 0;
+
+out_dev:
+ edac_device_free_ctl_info(edac_ctl);
+
+ return rc;
+}
+
+static int cortex_arm64_edac_remove(struct platform_device *pdev)
+{
+ struct edac_device_ctl_info *edac_ctl = dev_get_drvdata(&pdev->dev);
+
+ edac_device_del_device(edac_ctl->dev);
+ edac_device_free_ctl_info(edac_ctl);
+
+ return 0;
+}
+
+static const struct of_device_id cortex_arm64_edac_of_match[] = {
+ { .compatible = "arm,cortex-a53" },
+ { .compatible = "arm,cortex-a57" },
+ {}
+};
+MODULE_DEVICE_TABLE(of, cortex_arm64_edac_of_match);
+
+static struct platform_driver cortex_arm64_edac_driver = {
+ .probe = cortex_arm64_edac_probe,
+ .remove = cortex_arm64_edac_remove,
+ .driver = {
+ .name = DRVNAME,
+ },
+};
+
+static int __init cortex_arm64_edac_driver_init(void)
+{
+ struct device_node *np;
+ int cpu;
+ struct platform_device *pdev;
+ int err;
+
+ for_each_possible_cpu(cpu) {
+ np = of_get_cpu_node(cpu, NULL);
+
+ if (of_match_node(cortex_arm64_edac_of_match, np))
+ cpumask_set_cpu(cpu, &compat_mask);
+ }
+
+ if (cpumask_empty(&compat_mask))
+ return 0;
+
+ err = platform_driver_register(&cortex_arm64_edac_driver);
+ if (err)
+ return err;
+
+ pdev = platform_device_register_simple(DRVNAME, -1, NULL, 0);
+ if (IS_ERR(pdev)) {
+ pr_err("failed to register cortex arm64 edac device\n");
+ platform_driver_unregister(&cortex_arm64_edac_driver);
+ return PTR_ERR(pdev);
+ }
+
+ return 0;
+}
+
+device_initcall(cortex_arm64_edac_driver_init);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de>");
+MODULE_DESCRIPTION("Cortex A57 and A53 L1 and L2 cache EDAC driver");
--
2.20.1
^ permalink raw reply related [flat|nested] 4+ messages in thread
* [PATCH 2/2] dt-bindings: arm: cpus: Add edac-enabled property
2021-02-01 11:57 [PATCH iv4 0/2] Add L1 and L2 error detection for A53 and A57 Sascha Hauer
2021-02-01 11:57 ` [PATCH 1/2] drivers/edac: " Sascha Hauer
@ 2021-02-01 11:57 ` Sascha Hauer
2021-02-01 12:00 ` Sascha Hauer
1 sibling, 1 reply; 4+ messages in thread
From: Sascha Hauer @ 2021-02-01 11:57 UTC (permalink / raw)
To: linux-edac
Cc: Borislav Petkov, Mauro Carvalho Chehab, Tony Luck, James Morse,
Robert Richter, York Sun, kernel, linux-arm-kernel, Rob Herring,
Sascha Hauer
Some CPUs like the Cortex-A53 and Cortex-A57 have Error Detection And
Correction (EDAC) support on their L1 and L2 caches. This is implemented
in implementation defined registers, so usage of this functionality is
not safe in virtualized environments or when EL3 already uses these
registers.
This patch adds a edac-enabled flag which can be explicitly set when
EDAC can be used.
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
---
Documentation/devicetree/bindings/arm/cpus.yaml | 6 ++++++
drivers/edac/cortex_arm64_l1_l2.c | 7 +++++--
2 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/Documentation/devicetree/bindings/arm/cpus.yaml b/Documentation/devicetree/bindings/arm/cpus.yaml
index f02fd10de604..80dcf90f3e78 100644
--- a/Documentation/devicetree/bindings/arm/cpus.yaml
+++ b/Documentation/devicetree/bindings/arm/cpus.yaml
@@ -269,6 +269,12 @@ properties:
For PSCI based platforms, the name corresponding to the index of the PSCI
PM domain provider, must be "psci".
+ edac-enabled:
+ $ref: '/schemas/types.yaml#/definitions/flag'
+ description:
+ Some CPUs support Error Detection And Correction (EDAC) on their L1 and
+ L2 caches. This flag marks this function as usable.
+
qcom,saw:
$ref: '/schemas/types.yaml#/definitions/phandle'
description: |
diff --git a/drivers/edac/cortex_arm64_l1_l2.c b/drivers/edac/cortex_arm64_l1_l2.c
index 3b1e2f3ccab6..6d5355bae80c 100644
--- a/drivers/edac/cortex_arm64_l1_l2.c
+++ b/drivers/edac/cortex_arm64_l1_l2.c
@@ -190,8 +190,11 @@ static int __init cortex_arm64_edac_driver_init(void)
for_each_possible_cpu(cpu) {
np = of_get_cpu_node(cpu, NULL);
- if (of_match_node(cortex_arm64_edac_of_match, np))
- cpumask_set_cpu(cpu, &compat_mask);
+ if (!of_match_node(cortex_arm64_edac_of_match, np))
+ continue;
+ if (!of_property_read_bool(np, "edac-enabled"))
+ continue;
+ cpumask_set_cpu(cpu, &compat_mask);
}
if (cpumask_empty(&compat_mask))
--
2.20.1
^ permalink raw reply related [flat|nested] 4+ messages in thread