linux-edac.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH 1/2] drivers/edac: Add L1 and L2 error detection for A53, A57 and A72
  2025-04-09 23:36 [PATCH v6 0/2] " Vijay Balakrishna
@ 2025-04-09 23:36 ` Vijay Balakrishna
  2025-04-10 20:04   ` Tyler Hicks (Microsoft)
  0 siblings, 1 reply; 10+ messages in thread
From: Vijay Balakrishna @ 2025-04-09 23:36 UTC (permalink / raw)
  To: Borislav Petkov, Tony Luck
  Cc: James Morse, Mauro Carvalho Chehab, Robert Richter, linux-edac,
	linux-kernel, Tyler Hicks, Marc Zyngier, Sascha Hauer

From: Sascha Hauer <s.hauer@pengutronix.de>

The Cortex A53, A57 and A72 cores have error detection capabilities for
the L1/L2 Caches, this patch adds a driver for them. The selected errors
to detect/report have compatible bit assignments concerning CPU/L2 memory
error syndrome registers.

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 [1] of this
driver.  For reasons stated in thread [1], the error injection code is
not suitable for mainline, so it is removed from the driver.

[1] https://lore.kernel.org/all/1521073067-24348-1-git-send-email-york.sun@nxp.com/#t

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Co-developed-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
Signed-off-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
---
 drivers/edac/Kconfig              |   9 ++
 drivers/edac/Makefile             |   1 +
 drivers/edac/cortex_arm64_l1_l2.c | 225 ++++++++++++++++++++++++++++++
 3 files changed, 235 insertions(+)
 create mode 100644 drivers/edac/cortex_arm64_l1_l2.c

diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 19ad3c3b675d..20c15a18437f 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -576,4 +576,13 @@ config EDAC_LOONGSON
 	  errors (CE) only. Loongson-3A5000/3C5000/3D5000/3A6000/3C6000
 	  are compatible.
 
+config EDAC_CORTEX_ARM64_L1_L2
+	tristate "ARM Cortex A72/A57/A53"
+	depends on ARM64
+	help
+	  Support for L1/L2 cache error detection is provided for ARM Cortex
+	  A72, A57, and A53 processors. The selected subset of errors is common
+	  across these three MPCore processors, featuring compatible bit
+	  assignments in their CPU/L2 memory error syndrome registers.
+
 endif # EDAC
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index a8f2d8f6c894..157062410e61 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -88,3 +88,4 @@ obj-$(CONFIG_EDAC_NPCM)			+= npcm_edac.o
 obj-$(CONFIG_EDAC_ZYNQMP)		+= zynqmp_edac.o
 obj-$(CONFIG_EDAC_VERSAL)		+= versal_edac.o
 obj-$(CONFIG_EDAC_LOONGSON)		+= loongson_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..2ffe20212acb
--- /dev/null
+++ b/drivers/edac/cortex_arm64_l1_l2.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Cortex A72, 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 TLB_RAM				0x18
+
+#define L2MERRSR_EL1_CPUID_WAY	GENMASK(21, 18)
+
+#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 TLB_RAM:
+			str = "TLB RAM";
+			break;
+		default:
+			str = "Unspecified";
+			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);
+
+		write_sysreg_s(0, SYS_CPUMERRSR_EL1);
+		isb();
+	}
+
+	if (l2merr & L2MERRSR_EL1_VALID) {
+		bool fatal = l2merr & L2MERRSR_EL1_FATAL;
+
+		snprintf(msg, MESSAGE_SIZE, "L2 %s error(s) on CPU %d CPUID/WAY 0x%x",
+			 fatal ? "fatal" : "correctable", cpu,
+			 FIELD_GET(L2MERRSR_EL1_CPUID_WAY, l2merr));
+		if (fatal)
+			edac_device_handle_ue(edac_ctl, cpu, 1, msg);
+		else
+			edac_device_handle_ce(edac_ctl, cpu, 1, msg);
+
+		write_sysreg_s(0, SYS_L2MERRSR_EL1);
+		isb();
+	}
+}
+
+static void read_errors(void *data)
+{
+	struct merrsr *merrsr = data;
+
+	merrsr->cpumerr = read_sysreg_s(SYS_CPUMERRSR_EL1);
+	merrsr->l2merr = read_sysreg_s(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" },
+	{ .compatible = "arm,cortex-a72" },
+	{}
+};
+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))
+			continue;
+		if (!of_property_read_bool(np, "edac-enabled"))
+			continue;
+		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");
+MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de>");
+MODULE_DESCRIPTION("Cortex A72, A57 and A53 L1 and L2 cache EDAC driver");
-- 
2.49.0


^ permalink raw reply related	[flat|nested] 10+ messages in thread

* Re: [PATCH 1/2] drivers/edac: Add L1 and L2 error detection for A53, A57 and A72
  2025-04-09 23:36 ` [PATCH 1/2] drivers/edac: " Vijay Balakrishna
@ 2025-04-10 20:04   ` Tyler Hicks (Microsoft)
  2025-04-10 22:27     ` Vijay Balakrishna
  2025-04-10 22:29     ` Vijay Balakrishna
  0 siblings, 2 replies; 10+ messages in thread
From: Tyler Hicks (Microsoft) @ 2025-04-10 20:04 UTC (permalink / raw)
  To: Vijay Balakrishna
  Cc: Borislav Petkov, Tony Luck, James Morse, Mauro Carvalho Chehab,
	Robert Richter, linux-edac, linux-kernel, Marc Zyngier,
	Sascha Hauer

On 2025-04-09 16:36:24, Vijay Balakrishna wrote:
> From: Sascha Hauer <s.hauer@pengutronix.de>
> 
> The Cortex A53, A57 and A72 cores have error detection capabilities for
> the L1/L2 Caches, this patch adds a driver for them. The selected errors
> to detect/report have compatible bit assignments concerning CPU/L2 memory
> error syndrome registers.
> 
> 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 [1] of this
> driver.  For reasons stated in thread [1], the error injection code is
> not suitable for mainline, so it is removed from the driver.
> 
> [1] https://lore.kernel.org/all/1521073067-24348-1-git-send-email-york.sun@nxp.com/#t
> 
> Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
> Co-developed-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
> Signed-off-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
> ---
>  drivers/edac/Kconfig              |   9 ++
>  drivers/edac/Makefile             |   1 +
>  drivers/edac/cortex_arm64_l1_l2.c | 225 ++++++++++++++++++++++++++++++
>  3 files changed, 235 insertions(+)
>  create mode 100644 drivers/edac/cortex_arm64_l1_l2.c
> 
> diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
> index 19ad3c3b675d..20c15a18437f 100644
> --- a/drivers/edac/Kconfig
> +++ b/drivers/edac/Kconfig
> @@ -576,4 +576,13 @@ config EDAC_LOONGSON
>  	  errors (CE) only. Loongson-3A5000/3C5000/3D5000/3A6000/3C6000
>  	  are compatible.
>  
> +config EDAC_CORTEX_ARM64_L1_L2
> +	tristate "ARM Cortex A72/A57/A53"
> +	depends on ARM64
> +	help
> +	  Support for L1/L2 cache error detection is provided for ARM Cortex
> +	  A72, A57, and A53 processors. The selected subset of errors is common
> +	  across these three MPCore processors, featuring compatible bit
> +	  assignments in their CPU/L2 memory error syndrome registers.
> +
>  endif # EDAC
> diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
> index a8f2d8f6c894..157062410e61 100644
> --- a/drivers/edac/Makefile
> +++ b/drivers/edac/Makefile
> @@ -88,3 +88,4 @@ obj-$(CONFIG_EDAC_NPCM)			+= npcm_edac.o
>  obj-$(CONFIG_EDAC_ZYNQMP)		+= zynqmp_edac.o
>  obj-$(CONFIG_EDAC_VERSAL)		+= versal_edac.o
>  obj-$(CONFIG_EDAC_LOONGSON)		+= loongson_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..2ffe20212acb
> --- /dev/null
> +++ b/drivers/edac/cortex_arm64_l1_l2.c
> @@ -0,0 +1,225 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Cortex A72, 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 TLB_RAM				0x18
> +
> +#define L2MERRSR_EL1_CPUID_WAY	GENMASK(21, 18)
> +
> +#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 TLB_RAM:
> +			str = "TLB RAM";
> +			break;
> +		default:
> +			str = "Unspecified";
> +			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);
> +
> +		write_sysreg_s(0, SYS_CPUMERRSR_EL1);
> +		isb();

I think the register writes and barriers should happen much closer to the
register reads, in read_errors(). Looking back at Marc's feedback on v5, I
think his most important piece of feedback was to only clear the register when
the valid bit is set to avoid accidentally clobbering an error that came in
between the register read and write.

By moving the register writes into report_errors() in this v6 series, there's
now a much larger window where new errors could occur between the register
read and the register write. Those new errors would be silently lost/ignored.
Reducing the window to the least number of cycles seems important for accurate
reporting.

> +	}
> +
> +	if (l2merr & L2MERRSR_EL1_VALID) {
> +		bool fatal = l2merr & L2MERRSR_EL1_FATAL;
> +
> +		snprintf(msg, MESSAGE_SIZE, "L2 %s error(s) on CPU %d CPUID/WAY 0x%x",
> +			 fatal ? "fatal" : "correctable", cpu,
> +			 FIELD_GET(L2MERRSR_EL1_CPUID_WAY, l2merr));
> +		if (fatal)
> +			edac_device_handle_ue(edac_ctl, cpu, 1, msg);
> +		else
> +			edac_device_handle_ce(edac_ctl, cpu, 1, msg);
> +
> +		write_sysreg_s(0, SYS_L2MERRSR_EL1);
> +		isb();
> +	}
> +}
> +
> +static void read_errors(void *data)
> +{
> +	struct merrsr *merrsr = data;
> +
> +	merrsr->cpumerr = read_sysreg_s(SYS_CPUMERRSR_EL1);
> +	merrsr->l2merr = read_sysreg_s(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" },
> +	{ .compatible = "arm,cortex-a72" },
> +	{}
> +};
> +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);

Copilot correctly points out that we don't check np for NULL here. I think
of_match_node() handles that fine but we get fairly deep into the call stack
before it is caught. Let's go ahead and proactive check the return value.

More importantly, it pointed out that we don't call of_node_put(np) before
moving onto the next CPU. This would result in a refcount issue and will need
to be fixed.

Thanks!

Tyler

> +
> +		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))
> +		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");
> +MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de>");
> +MODULE_DESCRIPTION("Cortex A72, A57 and A53 L1 and L2 cache EDAC driver");
> -- 
> 2.49.0
> 

^ permalink raw reply	[flat|nested] 10+ messages in thread

* Re: [PATCH 1/2] drivers/edac: Add L1 and L2 error detection for A53, A57 and A72
  2025-04-10 20:04   ` Tyler Hicks (Microsoft)
@ 2025-04-10 22:27     ` Vijay Balakrishna
  2025-04-10 22:29     ` Vijay Balakrishna
  1 sibling, 0 replies; 10+ messages in thread
From: Vijay Balakrishna @ 2025-04-10 22:27 UTC (permalink / raw)
  To: Tyler Hicks (Microsoft)
  Cc: Borislav Petkov, Tony Luck, James Morse, Mauro Carvalho Chehab,
	Robert Richter, linux-edac, linux-kernel, Marc Zyngier,
	Sascha Hauer

On 4/10/2025 1:04 PM, Tyler Hicks (Microsoft) wrote:
>> +		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);
>> +
>> +		write_sysreg_s(0, SYS_CPUMERRSR_EL1);
>> +		isb();
> I think the register writes and barriers should happen much closer to the
> register reads, in read_errors(). Looking back at Marc's feedback on v5, I
> think his most important piece of feedback was to only clear the register when
> the valid bit is set to avoid accidentally clobbering an error that came in
> between the register read and write.
> 
> By moving the register writes into report_errors() in this v6 series, there's
> now a much larger window where new errors could occur between the register
> read and the register write. Those new errors would be silently lost/ignored.
> Reducing the window to the least number of cycles seems important for accurate
> reporting.

Moving clear to report_errors() is wrong actually, it has be cleared 
from the CPU, from read_errors() which is a SMP call. Let me share new 
version with changes.

Thanks,
Vijay

^ permalink raw reply	[flat|nested] 10+ messages in thread

* Re: [PATCH 1/2] drivers/edac: Add L1 and L2 error detection for A53, A57 and A72
  2025-04-10 20:04   ` Tyler Hicks (Microsoft)
  2025-04-10 22:27     ` Vijay Balakrishna
@ 2025-04-10 22:29     ` Vijay Balakrishna
  1 sibling, 0 replies; 10+ messages in thread
From: Vijay Balakrishna @ 2025-04-10 22:29 UTC (permalink / raw)
  To: Tyler Hicks (Microsoft)
  Cc: Borislav Petkov, Tony Luck, James Morse, Mauro Carvalho Chehab,
	Robert Richter, linux-edac, linux-kernel, Marc Zyngier,
	Sascha Hauer

On 4/10/2025 1:04 PM, Tyler Hicks (Microsoft) wrote:
>> +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);
> Copilot correctly points out that we don't check np for NULL here. I think
> of_match_node() handles that fine but we get fairly deep into the call stack
> before it is caught. Let's go ahead and proactive check the return value.
> 
> More importantly, it pointed out that we don't call of_node_put(np) before
> moving onto the next CPU. This would result in a refcount issue and will need
> to be fixed.

Good catch. Let me change in next version.

Thanks,
Vijay

^ permalink raw reply	[flat|nested] 10+ messages in thread

* [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72
@ 2025-04-11 22:08 Vijay Balakrishna
  2025-04-11 22:08 ` [PATCH 1/2] drivers/edac: " Vijay Balakrishna
                   ` (2 more replies)
  0 siblings, 3 replies; 10+ messages in thread
From: Vijay Balakrishna @ 2025-04-11 22:08 UTC (permalink / raw)
  To: Borislav Petkov, Tony Luck, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley
  Cc: James Morse, Mauro Carvalho Chehab, Robert Richter, linux-edac,
	linux-kernel, Tyler Hicks, Marc Zyngier, Sascha Hauer,
	Lorenzo Pieralisi, devicetree, Vijay Balakrishna

Hello,

This is an attempt to revive [v5] series. I have attempted to address comments
and suggestions from Marc Zyngier since [v5]. Additionally, I have extended
support for A72 processors. Testing on a problematic A72 SoC has led to the
detection of Correctable Errors (CEs). I am eager to hear your suggestions and
feedback on this series.

Thanks,
Vijay

[v5] https://lore.kernel.org/all/20210401110615.15326-1-s.hauer@pengutronix.de/#t
[v6] https://lore.kernel.org/all/1744241785-20256-1-git-send-email-vijayb@linux.microsoft.com/

Changes since v6:
- restore the change made in [v5] to clear CPU/L2 syndrome registers
  back to read_errors() (Tyler)
- upon detecting a valid error, clear syndrome registers immediately
  to avoid clobbering between the read and write (Marc)
- NULL return check for of_get_cpu_node() (Tyler)
- of_node_put() to avoid refcount issue (Tyler)
- quotes are dropped in yaml file (Krzysztof)

Changes since v5:
- rebase on v6.15-rc1
- the syndrome registers for CPU/L2 memory errors are cleared only upon
  detecting an error and an isb() after for synchronization (Marc)
- "edac-enabled" hunk moved to initial patch to avoid breaking virtual
  environments (Marc)
- to ensure compatibility across all three families, we are not reporting
  "L1 Dirty RAM," documented only in the A53 TRM
- above prompted changing default CPU L1 error meesage from "unknown"
  to "Unspecified" 
- capturing CPUID/WAY information in L2 memory error log (Marc)
- module license from "GPL v2" to "GPL" (checkpatch.pl warning)
- extend support for A72

Changes since v4:
- Rebase on v5.12-rc5

Changes since v3:
- Add edac-enabled property to make EDAC 3support optional

Changes since v2:
- drop usage of virtual dt node (Robh)
- use read_sysreg_s instead of open coded variant (James Morse)
- separate error retrieving from error reporting
- use smp_call_function_single rather than smp_call_function_single_async
- make driver single instance and register all 'cpu' hierarchy up front once

Changes since v1:
- Split dt-binding into separate patch
- Sort local function variables in reverse-xmas tree order
- drop unnecessary comparison and make variable bool

Sascha Hauer (2):
  drivers/edac: Add L1 and L2 error detection for A53, A57 and A72
  dt-bindings: arm: cpus: Add edac-enabled property

 .../devicetree/bindings/arm/cpus.yaml         |   6 +
 drivers/edac/Kconfig                          |   9 +
 drivers/edac/Makefile                         |   1 +
 drivers/edac/cortex_arm64_l1_l2.c             | 232 ++++++++++++++++++
 4 files changed, 248 insertions(+)
 create mode 100644 drivers/edac/cortex_arm64_l1_l2.c


base-commit: 0af2f6be1b4281385b618cb86ad946eded089ac8
-- 
2.49.0


^ permalink raw reply	[flat|nested] 10+ messages in thread

* [PATCH 1/2] drivers/edac: Add L1 and L2 error detection for A53, A57 and A72
  2025-04-11 22:08 [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72 Vijay Balakrishna
@ 2025-04-11 22:08 ` Vijay Balakrishna
  2025-04-11 22:08 ` [PATCH 2/2] dt-bindings: arm: cpus: Add edac-enabled property Vijay Balakrishna
  2025-04-13 20:39 ` [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72 Borislav Petkov
  2 siblings, 0 replies; 10+ messages in thread
From: Vijay Balakrishna @ 2025-04-11 22:08 UTC (permalink / raw)
  To: Borislav Petkov, Tony Luck, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley
  Cc: James Morse, Mauro Carvalho Chehab, Robert Richter, linux-edac,
	linux-kernel, Tyler Hicks, Marc Zyngier, Sascha Hauer,
	Lorenzo Pieralisi, devicetree, Vijay Balakrishna

From: Sascha Hauer <s.hauer@pengutronix.de>

The Cortex A53, A57 and A72 cores have error detection capabilities for
the L1/L2 Caches, this patch adds a driver for them. The selected errors
to detect/report have compatible bit assignments concerning CPU/L2 memory
error syndrome registers.

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 [1] of this
driver.  For reasons stated in thread [1], the error injection code is
not suitable for mainline, so it is removed from the driver.

[1] https://lore.kernel.org/all/1521073067-24348-1-git-send-email-york.sun@nxp.com/#t

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Co-developed-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
Signed-off-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
---
 drivers/edac/Kconfig              |   9 ++
 drivers/edac/Makefile             |   1 +
 drivers/edac/cortex_arm64_l1_l2.c | 232 ++++++++++++++++++++++++++++++
 3 files changed, 242 insertions(+)
 create mode 100644 drivers/edac/cortex_arm64_l1_l2.c

diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 19ad3c3b675d..20c15a18437f 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -576,4 +576,13 @@ config EDAC_LOONGSON
 	  errors (CE) only. Loongson-3A5000/3C5000/3D5000/3A6000/3C6000
 	  are compatible.
 
+config EDAC_CORTEX_ARM64_L1_L2
+	tristate "ARM Cortex A72/A57/A53"
+	depends on ARM64
+	help
+	  Support for L1/L2 cache error detection is provided for ARM Cortex
+	  A72, A57, and A53 processors. The selected subset of errors is common
+	  across these three MPCore processors, featuring compatible bit
+	  assignments in their CPU/L2 memory error syndrome registers.
+
 endif # EDAC
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index a8f2d8f6c894..157062410e61 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -88,3 +88,4 @@ obj-$(CONFIG_EDAC_NPCM)			+= npcm_edac.o
 obj-$(CONFIG_EDAC_ZYNQMP)		+= zynqmp_edac.o
 obj-$(CONFIG_EDAC_VERSAL)		+= versal_edac.o
 obj-$(CONFIG_EDAC_LOONGSON)		+= loongson_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..650a7b10d24d
--- /dev/null
+++ b/drivers/edac/cortex_arm64_l1_l2.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Cortex A72, 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 TLB_RAM				0x18
+
+#define L2MERRSR_EL1_CPUID_WAY	GENMASK(21, 18)
+
+#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 TLB_RAM:
+			str = "TLB RAM";
+			break;
+		default:
+			str = "Unspecified";
+			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 CPUID/WAY 0x%x",
+			 fatal ? "fatal" : "correctable", cpu,
+			 FIELD_GET(L2MERRSR_EL1_CPUID_WAY, l2merr));
+		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);
+	if (merrsr->cpumerr & CPUMERRSR_EL1_VALID) {
+		write_sysreg_s(0, SYS_CPUMERRSR_EL1);
+		isb();
+	}
+	merrsr->l2merr = read_sysreg_s(SYS_L2MERRSR_EL1);
+	if (merrsr->l2merr & L2MERRSR_EL1_VALID) {
+		write_sysreg_s(0, SYS_L2MERRSR_EL1);
+		isb();
+	}
+}
+
+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" },
+	{ .compatible = "arm,cortex-a72" },
+	{}
+};
+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 (!np) {
+			pr_warn("failed to find device node for cpu %d\n", cpu);
+			continue;
+		}
+		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);
+		of_node_put(np);
+	}
+
+	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");
+MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de>");
+MODULE_DESCRIPTION("Cortex A72, A57 and A53 L1 and L2 cache EDAC driver");
-- 
2.49.0


^ permalink raw reply related	[flat|nested] 10+ messages in thread

* [PATCH 2/2] dt-bindings: arm: cpus: Add edac-enabled property
  2025-04-11 22:08 [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72 Vijay Balakrishna
  2025-04-11 22:08 ` [PATCH 1/2] drivers/edac: " Vijay Balakrishna
@ 2025-04-11 22:08 ` Vijay Balakrishna
  2025-04-13 20:39 ` [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72 Borislav Petkov
  2 siblings, 0 replies; 10+ messages in thread
From: Vijay Balakrishna @ 2025-04-11 22:08 UTC (permalink / raw)
  To: Borislav Petkov, Tony Luck, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley
  Cc: James Morse, Mauro Carvalho Chehab, Robert Richter, linux-edac,
	linux-kernel, Tyler Hicks, Marc Zyngier, Sascha Hauer,
	Lorenzo Pieralisi, devicetree, Vijay Balakrishna

From: Sascha Hauer <s.hauer@pengutronix.de>

Some ARM Cortex CPUs like the A53, A57 and A72 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>
[vijayb: Added A72 to the commit message]
Signed-off-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
---
 Documentation/devicetree/bindings/arm/cpus.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/arm/cpus.yaml b/Documentation/devicetree/bindings/arm/cpus.yaml
index 2e666b2a4dcd..d1dc0a843d07 100644
--- a/Documentation/devicetree/bindings/arm/cpus.yaml
+++ b/Documentation/devicetree/bindings/arm/cpus.yaml
@@ -331,6 +331,12 @@ properties:
       corresponding to the index of an SCMI performance domain provider, must be
       "perf".
 
+  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: |
-- 
2.49.0


^ permalink raw reply related	[flat|nested] 10+ messages in thread

* Re: [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72
  2025-04-11 22:08 [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72 Vijay Balakrishna
  2025-04-11 22:08 ` [PATCH 1/2] drivers/edac: " Vijay Balakrishna
  2025-04-11 22:08 ` [PATCH 2/2] dt-bindings: arm: cpus: Add edac-enabled property Vijay Balakrishna
@ 2025-04-13 20:39 ` Borislav Petkov
  2025-04-16  0:05   ` Vijay Balakrishna
  2 siblings, 1 reply; 10+ messages in thread
From: Borislav Petkov @ 2025-04-13 20:39 UTC (permalink / raw)
  To: Vijay Balakrishna
  Cc: Tony Luck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
	James Morse, Mauro Carvalho Chehab, Robert Richter, linux-edac,
	linux-kernel, Tyler Hicks, Marc Zyngier, Sascha Hauer,
	Lorenzo Pieralisi, devicetree

On Fri, Apr 11, 2025 at 03:08:37PM -0700, Vijay Balakrishna wrote:
> Hello,
> 
> This is an attempt to revive [v5] series. I have attempted to address comments
> and suggestions from Marc Zyngier since [v5]. Additionally, I have extended
> support for A72 processors. Testing on a problematic A72 SoC has led to the
> detection of Correctable Errors (CEs). I am eager to hear your suggestions and
> feedback on this series.

Did you not read Marc's note:

https://lore.kernel.org/all/86a58kl51r.wl-maz@kernel.org/

or

https://lore.kernel.org/all/86frigkmtd.wl-maz@kernel.org/

?

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette

^ permalink raw reply	[flat|nested] 10+ messages in thread

* Re: [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72
  2025-04-13 20:39 ` [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72 Borislav Petkov
@ 2025-04-16  0:05   ` Vijay Balakrishna
  0 siblings, 0 replies; 10+ messages in thread
From: Vijay Balakrishna @ 2025-04-16  0:05 UTC (permalink / raw)
  To: Borislav Petkov
  Cc: Tony Luck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
	James Morse, Mauro Carvalho Chehab, Robert Richter, linux-edac,
	linux-kernel, Tyler Hicks, Marc Zyngier, Sascha Hauer,
	Lorenzo Pieralisi, devicetree

On 4/13/25 13:39, Borislav Petkov wrote:
> On Fri, Apr 11, 2025 at 03:08:37PM -0700, Vijay Balakrishna wrote:
>> Hello,
>>
>> This is an attempt to revive [v5] series. I have attempted to address comments
>> and suggestions from Marc Zyngier since [v5]. Additionally, I have extended
>> support for A72 processors. Testing on a problematic A72 SoC has led to the
>> detection of Correctable Errors (CEs). I am eager to hear your suggestions and
>> feedback on this series.
> 
> Did you not read Marc's note:
> 
> https://lore.kernel.org/all/86a58kl51r.wl-maz@kernel.org/
> 
> or
> 
> https://lore.kernel.org/all/86frigkmtd.wl-maz@kernel.org/
> 
> ?
> 

Hi Borislav,

I did see the second reply above, but not the first before posting v7. I 
opted to submit v7 after addressing the comments and issues identified 
in v6 for the benefit of those interested. Sascha's v5 series has helped 
us in confirming a problematic A72 indeed suffering from CEs.

Our primary focus is on A72. I can re-submit with modifications solely 
related to A72 and exclude A53 and A57. As Tyler mentioned, we have a 
significant number of A72-based systems in our fleet, and timely 
replacements via monitoring CEs will be instrumental in managing them 
effectively. Please share your thoughts.

Thanks,
Vijay



^ permalink raw reply	[flat|nested] 10+ messages in thread

* [PATCH 1/2] drivers/edac: Add L1 and L2 error detection for A53, A57 and A72
  2025-05-05  0:27 [v8 " Vijay Balakrishna
@ 2025-05-05  0:27 ` Vijay Balakrishna
  0 siblings, 0 replies; 10+ messages in thread
From: Vijay Balakrishna @ 2025-05-05  0:27 UTC (permalink / raw)
  To: Borislav Petkov, Tony Luck, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley
  Cc: James Morse, Mauro Carvalho Chehab, Robert Richter, linux-edac,
	linux-kernel, Tyler Hicks, Marc Zyngier, Sascha Hauer,
	Lorenzo Pieralisi, devicetree, Vijay Balakrishna

From: Sascha Hauer <s.hauer@pengutronix.de>

The Cortex A53, A57 and A72 cores have error detection capabilities for
the L1/L2 Caches, this patch adds a driver for them. The selected errors
to detect/report have compatible bit assignments concerning CPU/L2 memory
error syndrome registers.

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 [1] of this
driver.  For reasons stated in thread [1], the error injection code is
not suitable for mainline, so it is removed from the driver.

[1] https://lore.kernel.org/all/1521073067-24348-1-git-send-email-york.sun@nxp.com/#t

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Co-developed-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
Signed-off-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
---
 drivers/edac/Kconfig              |   9 ++
 drivers/edac/Makefile             |   1 +
 drivers/edac/cortex_arm64_l1_l2.c | 229 ++++++++++++++++++++++++++++++
 3 files changed, 239 insertions(+)
 create mode 100644 drivers/edac/cortex_arm64_l1_l2.c

diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 19ad3c3b675d..20c15a18437f 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -576,4 +576,13 @@ config EDAC_LOONGSON
 	  errors (CE) only. Loongson-3A5000/3C5000/3D5000/3A6000/3C6000
 	  are compatible.
 
+config EDAC_CORTEX_ARM64_L1_L2
+	tristate "ARM Cortex A72/A57/A53"
+	depends on ARM64
+	help
+	  Support for L1/L2 cache error detection is provided for ARM Cortex
+	  A72, A57, and A53 processors. The selected subset of errors is common
+	  across these three MPCore processors, featuring compatible bit
+	  assignments in their CPU/L2 memory error syndrome registers.
+
 endif # EDAC
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index a8f2d8f6c894..157062410e61 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -88,3 +88,4 @@ obj-$(CONFIG_EDAC_NPCM)			+= npcm_edac.o
 obj-$(CONFIG_EDAC_ZYNQMP)		+= zynqmp_edac.o
 obj-$(CONFIG_EDAC_VERSAL)		+= versal_edac.o
 obj-$(CONFIG_EDAC_LOONGSON)		+= loongson_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..ad411259debd
--- /dev/null
+++ b/drivers/edac/cortex_arm64_l1_l2.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Cortex A72, 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.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 TLB_RAM				0x18
+
+#define L2MERRSR_EL1_CPUID_WAY	GENMASK(21, 18)
+
+#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 TLB_RAM:
+			str = "TLB RAM";
+			break;
+		default:
+			str = "Unspecified";
+			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 CPUID/WAY 0x%lx",
+			 fatal ? "fatal" : "correctable", cpu,
+			 FIELD_GET(L2MERRSR_EL1_CPUID_WAY, l2merr));
+		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);
+	if (merrsr->cpumerr & CPUMERRSR_EL1_VALID) {
+		write_sysreg_s(0, SYS_CPUMERRSR_EL1);
+		isb();
+	}
+	merrsr->l2merr = read_sysreg_s(SYS_L2MERRSR_EL1);
+	if (merrsr->l2merr & L2MERRSR_EL1_VALID) {
+		write_sysreg_s(0, SYS_L2MERRSR_EL1);
+		isb();
+	}
+}
+
+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,
+					      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 void 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);
+}
+
+static const struct of_device_id cortex_arm64_edac_of_match[] = {
+	{ .compatible = "arm,cortex-a53" },
+	{ .compatible = "arm,cortex-a57" },
+	{ .compatible = "arm,cortex-a72" },
+	{}
+};
+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 (!np) {
+			pr_warn("failed to find device node for cpu %d\n", cpu);
+			continue;
+		}
+		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);
+		of_node_put(np);
+	}
+
+	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");
+MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de>");
+MODULE_DESCRIPTION("Cortex A72, A57 and A53 L1 and L2 cache EDAC driver");
-- 
2.49.0


^ permalink raw reply related	[flat|nested] 10+ messages in thread

end of thread, other threads:[~2025-05-05  0:27 UTC | newest]

Thread overview: 10+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-04-11 22:08 [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72 Vijay Balakrishna
2025-04-11 22:08 ` [PATCH 1/2] drivers/edac: " Vijay Balakrishna
2025-04-11 22:08 ` [PATCH 2/2] dt-bindings: arm: cpus: Add edac-enabled property Vijay Balakrishna
2025-04-13 20:39 ` [v7 PATCH 0/2] Add L1 and L2 error detection for A53, A57 and A72 Borislav Petkov
2025-04-16  0:05   ` Vijay Balakrishna
  -- strict thread matches above, loose matches on Subject: below --
2025-05-05  0:27 [v8 " Vijay Balakrishna
2025-05-05  0:27 ` [PATCH 1/2] drivers/edac: " Vijay Balakrishna
2025-04-09 23:36 [PATCH v6 0/2] " Vijay Balakrishna
2025-04-09 23:36 ` [PATCH 1/2] drivers/edac: " Vijay Balakrishna
2025-04-10 20:04   ` Tyler Hicks (Microsoft)
2025-04-10 22:27     ` Vijay Balakrishna
2025-04-10 22:29     ` Vijay Balakrishna

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).