[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20190805143911.12185-5-hhhawa@amazon.com>
Date: Mon, 5 Aug 2019 15:39:11 +0100
From: Hanna Hawa <hhhawa@...zon.com>
To: <robh+dt@...nel.org>, <mark.rutland@....com>, <bp@...en8.de>,
<mchehab@...nel.org>, <james.morse@....com>, <davem@...emloft.net>,
<gregkh@...uxfoundation.org>, <linus.walleij@...aro.org>,
<Jonathan.Cameron@...wei.com>, <nicolas.ferre@...rochip.com>,
<paulmck@...ux.ibm.com>
CC: <dwmw@...zon.co.uk>, <benh@...zon.com>, <ronenk@...zon.com>,
<talel@...zon.com>, <jonnyc@...zon.com>, <hanochu@...zon.com>,
<devicetree@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
<linux-edac@...r.kernel.org>, <hhhawa@...zon.com>
Subject: [PATCH v5 4/4] edac: Add support for Amazon's Annapurna Labs L2 EDAC
Adds support for Amazon's Annapurna Labs L2 EDAC driver to detect and
report L2 errors.
Signed-off-by: Hanna Hawa <hhhawa@...zon.com>
Reviewed-by: James Morse <james.morse@....com>
---
MAINTAINERS | 6 ++
drivers/edac/Kconfig | 8 ++
drivers/edac/Makefile | 1 +
drivers/edac/al_l2_edac.c | 192 ++++++++++++++++++++++++++++++++++++++
4 files changed, 207 insertions(+)
create mode 100644 drivers/edac/al_l2_edac.c
diff --git a/MAINTAINERS b/MAINTAINERS
index fd29ea62ba29..a6dcf3d8e12a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -749,6 +749,12 @@ S: Maintained
F: drivers/edac/al_l1_edac.c
F: Documentation/devicetree/bindings/edac/amazon,al-l1-edac.txt
+AMAZON ANNAPURNA LABS L2 EDAC
+M: Hanna Hawa <hhhawa@...zon.com>
+S: Maintained
+F: drivers/edac/al_l2_edac.c
+F: Documentation/devicetree/bindings/edac/amazon,al-l2-edac.txt
+
AMAZON ANNAPURNA LABS THERMAL MMIO DRIVER
M: Talel Shenhar <talel@...zon.com>
S: Maintained
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 58b92bcb39ce..8bbb745b84ed 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -82,6 +82,14 @@ config EDAC_AL_L1
for Amazon's Annapurna Labs SoCs.
This driver detects errors of L1 caches.
+config EDAC_AL_L2
+ bool "Amazon's Annapurna Labs L2 EDAC"
+ depends on ARCH_ALPINE
+ help
+ Support for L2 error detection and correction
+ for Amazon's Annapurna Labs SoCs.
+ This driver detects errors of L2 caches.
+
config EDAC_AMD64
tristate "AMD64 (Opteron, Athlon64)"
depends on AMD_NB && EDAC_DECODE_MCE
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index caa2dc91e8a0..60a6b8bbe2f8 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -23,6 +23,7 @@ edac_mce_amd-y := mce_amd.o
obj-$(CONFIG_EDAC_DECODE_MCE) += edac_mce_amd.o
obj-$(CONFIG_EDAC_AL_L1) += al_l1_edac.o
+obj-$(CONFIG_EDAC_AL_L2) += al_l2_edac.o
obj-$(CONFIG_EDAC_AMD76X) += amd76x_edac.o
obj-$(CONFIG_EDAC_CPC925) += cpc925_edac.o
obj-$(CONFIG_EDAC_I5000) += i5000_edac.o
diff --git a/drivers/edac/al_l2_edac.c b/drivers/edac/al_l2_edac.c
new file mode 100644
index 000000000000..3dcca380d2aa
--- /dev/null
+++ b/drivers/edac/al_l2_edac.c
@@ -0,0 +1,192 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#include <asm/sysreg.h>
+#include <linux/bitfield.h>
+#include <linux/cpumask.h>
+#include <linux/of.h>
+#include <linux/smp.h>
+
+#include "edac_device.h"
+#include "edac_module.h"
+
+#define DRV_NAME "al_l2_edac"
+
+/* Same bit assignments of L2MERRSR_EL1 in ARM CA57/CA72 */
+#define ARM_CA57_L2MERRSR_EL1 sys_reg(3, 1, 15, 2, 3)
+#define ARM_CA57_L2MERRSR_RAMID GENMASK(30, 24)
+#define ARM_CA57_L2_TAG_RAM 0x10
+#define ARM_CA57_L2_DATA_RAM 0x11
+#define ARM_CA57_L2_SNOOP_RAM 0x12
+#define ARM_CA57_L2_DIRTY_RAM 0x14
+#define ARM_CA57_L2_INC_PF_RAM 0x18
+#define ARM_CA57_L2MERRSR_VALID BIT(31)
+#define ARM_CA57_L2MERRSR_REPEAT GENMASK_ULL(39, 32)
+#define ARM_CA57_L2MERRSR_OTHER GENMASK_ULL(47, 40)
+#define ARM_CA57_L2MERRSR_FATAL BIT_ULL(63)
+
+#define AL_L2_EDAC_MSG_MAX 256
+
+struct al_l2_edac {
+ cpumask_t cluster_cpus;
+};
+
+static void al_l2_edac_l2merrsr(void *arg)
+{
+ struct edac_device_ctl_info *edac_dev = arg;
+ int cpu, i;
+ u32 ramid, repeat, other, fatal;
+ u64 val = read_sysreg_s(ARM_CA57_L2MERRSR_EL1);
+ char msg[AL_L2_EDAC_MSG_MAX];
+ int space, count;
+ char *p;
+
+ if (!(FIELD_GET(ARM_CA57_L2MERRSR_VALID, val)))
+ return;
+
+ write_sysreg_s(0, ARM_CA57_L2MERRSR_EL1);
+
+ cpu = smp_processor_id();
+ ramid = FIELD_GET(ARM_CA57_L2MERRSR_RAMID, val);
+ repeat = FIELD_GET(ARM_CA57_L2MERRSR_REPEAT, val);
+ other = FIELD_GET(ARM_CA57_L2MERRSR_OTHER, val);
+ fatal = FIELD_GET(ARM_CA57_L2MERRSR_FATAL, val);
+
+ space = sizeof(msg);
+ p = msg;
+ count = scnprintf(p, space, "CPU%d L2 %serror detected", cpu,
+ (fatal) ? "Fatal " : "");
+ p += count;
+ space -= count;
+
+ switch (ramid) {
+ case ARM_CA57_L2_TAG_RAM:
+ count = scnprintf(p, space, " RAMID='L2 Tag RAM'");
+ break;
+ case ARM_CA57_L2_DATA_RAM:
+ count = scnprintf(p, space, " RAMID='L2 Data RAM'");
+ break;
+ case ARM_CA57_L2_SNOOP_RAM:
+ count = scnprintf(p, space, " RAMID='L2 Snoop Tag RAM'");
+ break;
+ case ARM_CA57_L2_DIRTY_RAM:
+ count = scnprintf(p, space, " RAMID='L2 Dirty RAM'");
+ break;
+ case ARM_CA57_L2_INC_PF_RAM:
+ count = scnprintf(p, space, " RAMID='L2 internal metadata'");
+ break;
+ default:
+ count = scnprintf(p, space, " RAMID='unknown'");
+ break;
+ }
+
+ p += count;
+ space -= count;
+
+ count = scnprintf(p, space,
+ " repeat=%d, other=%d (L2MERRSR_EL1=0x%llx)",
+ repeat, other, val);
+
+ for (i = 0; i < repeat; i++) {
+ if (fatal)
+ edac_device_handle_ue(edac_dev, 0, 0, msg);
+ else
+ edac_device_handle_ce(edac_dev, 0, 0, msg);
+ }
+}
+
+static void al_l2_edac_check(struct edac_device_ctl_info *edac_dev)
+{
+ struct al_l2_edac *al_l2 = edac_dev->pvt_info;
+
+ smp_call_function_any(&al_l2->cluster_cpus, al_l2_edac_l2merrsr,
+ edac_dev, 1);
+}
+
+static int al_l2_edac_probe(struct platform_device *pdev)
+{
+ struct edac_device_ctl_info *edac_dev;
+ struct al_l2_edac *al_l2;
+ struct device *dev = &pdev->dev;
+ int ret, i;
+
+ edac_dev = edac_device_alloc_ctl_info(sizeof(*al_l2),
+ (char *)dev_name(dev), 1, "L", 1,
+ 2, NULL, 0,
+ edac_device_alloc_index());
+ if (IS_ERR_OR_NULL(edac_dev))
+ return -ENOMEM;
+
+ al_l2 = edac_dev->pvt_info;
+ edac_dev->edac_check = al_l2_edac_check;
+ edac_dev->dev = dev;
+ edac_dev->mod_name = DRV_NAME;
+ edac_dev->dev_name = dev_name(dev);
+ edac_dev->ctl_name = "L2 cache";
+ platform_set_drvdata(pdev, edac_dev);
+
+ for_each_possible_cpu(i) {
+ struct device_node *cpu;
+ struct device_node *cpu_cache, *l2_cache;
+
+ cpu = of_get_cpu_node(i, NULL);
+ cpu_cache = of_find_next_cache_node(cpu);
+ l2_cache = of_parse_phandle(dev->of_node, "l2-cache", 0);
+
+ if (cpu_cache == l2_cache)
+ cpumask_set_cpu(i, &al_l2->cluster_cpus);
+
+ of_node_put(cpu);
+ }
+
+ if (cpumask_empty(&al_l2->cluster_cpus)) {
+ dev_err(dev, "CPU mask is empty for this L2 cache\n");
+ ret = -EINVAL;
+ goto err;
+ }
+
+ ret = edac_device_add_device(edac_dev);
+ if (ret) {
+ dev_err(dev, "Failed to add L2 edac device\n");
+ goto err;
+ }
+
+ return 0;
+
+err:
+ edac_device_free_ctl_info(edac_dev);
+
+ return ret;
+}
+
+static int al_l2_edac_remove(struct platform_device *pdev)
+{
+ struct edac_device_ctl_info *edac_dev = platform_get_drvdata(pdev);
+
+ edac_device_del_device(edac_dev->dev);
+ edac_device_free_ctl_info(edac_dev);
+
+ return 0;
+}
+
+static const struct of_device_id al_l2_edac_of_match[] = {
+ { .compatible = "amazon,al-l2-edac" },
+ {}
+};
+MODULE_DEVICE_TABLE(of, al_l2_edac_of_match);
+
+static struct platform_driver al_l2_edac_driver = {
+ .probe = al_l2_edac_probe,
+ .remove = al_l2_edac_remove,
+ .driver = {
+ .name = DRV_NAME,
+ .of_match_table = al_l2_edac_of_match,
+ },
+};
+module_platform_driver(al_l2_edac_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Hanna Hawa <hhhawa@...zon.com>");
+MODULE_DESCRIPTION("Amazon's Annapurna Lab's L2 EDAC Driver");
--
2.17.1
Powered by blists - more mailing lists