This series adds L1 and L2 caches support for error detection and
correction for Amazon's Annapurna Labs SoCs.
Alpine SoCs support L1 and L2 single bit correction and two bits detection
capability based on ARM implementation.
Changes since v1:
-----------------
- Split into two drivers
- Get cpu-mask according to l2-cache handler from devicetree
- Remove parameter casting
- Use GENMASK() in bit mask
- Use FIELD_GET()
- Update define description PLRU_RAM -> PF_RAM
- Use sys_reg() and read_sysreg_s()
- Remove all write/read wrappers
- Check fatal field to set if the error correctable or not
- Remove un-relevant information from error prints.
- Update smp_call_function_single() call function to wait
- remove usage of get_online_cpus/put_online_cpus
- Use on_each_cpu() and smp_call_function_any() instead of loop with for_each_cpu.
- use buffer for error prints and pass to edac API
- Remove edac_op_state set
- Add for loop to report on repeated errors of the same type
- Fix error name of the TLB to be L2_TLB as written in ARM TRM
- Minor change in Kconfig
- Minor changes in commit message
Hanna Hawa (4):
dt-bindings: EDAC: Add Amazon's Annapurna Labs L1 EDAC
edac: Add support for Amazon's Annapurna Labs L1 EDAC
dt-bindings: EDAC: Add Amazon's Annapurna Labs L2 EDAC
edac: Add support for Amazon's Annapurna Labs L2 EDAC
.../devicetree/bindings/edac/amazon,al-l1-edac.txt | 14 ++
.../devicetree/bindings/edac/amazon,al-l2-edac.txt | 20 +++
MAINTAINERS | 12 ++
drivers/edac/Kconfig | 16 ++
drivers/edac/Makefile | 2 +
drivers/edac/al_l1_edac.c | 154 +++++++++++++++++
drivers/edac/al_l2_edac.c | 185 +++++++++++++++++++++
7 files changed, 403 insertions(+)
create mode 100644 Documentation/devicetree/bindings/edac/amazon,al-l1-edac.txt
create mode 100644 Documentation/devicetree/bindings/edac/amazon,al-l2-edac.txt
create mode 100644 drivers/edac/al_l1_edac.c
create mode 100644 drivers/edac/al_l2_edac.c
--
2.7.4
Adds support for Amazon's Annapurna Labs L2 EDAC driver to detect and
report L2 errors.
Signed-off-by: Hanna Hawa <[email protected]>
---
MAINTAINERS | 6 ++
drivers/edac/Kconfig | 8 ++
drivers/edac/Makefile | 1 +
drivers/edac/al_l2_edac.c | 185 ++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 200 insertions(+)
create mode 100644 drivers/edac/al_l2_edac.c
diff --git a/MAINTAINERS b/MAINTAINERS
index fd29ea6..a6dcf3d 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 <[email protected]>
+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 <[email protected]>
S: Maintained
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 58b92bc..8bbb745 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 caa2dc9..60a6b8b 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 0000000..4db6b66
--- /dev/null
+++ b/drivers/edac/al_l2_edac.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/of.h>
+
+#include "edac_device.h"
+#include "edac_module.h"
+
+/* 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 GENMASK(31, 31)
+#define ARM_CA57_L2MERRSR_REPEAT GENMASK(39, 32)
+#define ARM_CA57_L2MERRSR_OTHER GENMASK(47, 40)
+#define ARM_CA57_L2MERRSR_FATAL GENMASK(63, 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;
+
+ 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 = snprintf(p, space, "CPU%d L2 %serror detected", cpu,
+ (fatal) ? "Fatal " : "");
+ p += count;
+ space -= count;
+
+ switch (ramid) {
+ case ARM_CA57_L2_TAG_RAM:
+ count = snprintf(p, space, " RAMID='L2 Tag RAM'");
+ break;
+ case ARM_CA57_L2_DATA_RAM:
+ count = snprintf(p, space, " RAMID='L2 Data RAM'");
+ break;
+ case ARM_CA57_L2_SNOOP_RAM:
+ count = snprintf(p, space, " RAMID='L2 Snoop RAM'");
+ break;
+ case ARM_CA57_L2_DIRTY_RAM:
+ count = snprintf(p, space, " RAMID='L2 Dirty RAM'");
+ break;
+ case ARM_CA57_L2_INC_PF_RAM:
+ count = snprintf(p, space, " RAMID='L2 internal metadat'");
+ break;
+ default:
+ count = snprintf(p, space, " RAMID='unknown'");
+ break;
+ }
+
+ p += count;
+ space -= count;
+
+ count = snprintf(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);
+ }
+
+ write_sysreg_s(0, ARM_CA57_L2MERRSR_EL1);
+}
+
+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(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 = dev_name(dev);
+ edac_dev->dev_name = dev_name(dev);
+ edac_dev->ctl_name = dev_name(dev);
+ platform_set_drvdata(pdev, edac_dev);
+
+ for_each_online_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);
+ }
+
+ 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 = "al_l2_edac",
+ .of_match_table = al_l2_edac_of_match,
+ },
+};
+module_platform_driver(al_l2_edac_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Hanna Hawa <[email protected]>");
+MODULE_DESCRIPTION("Amazon's Annapurna Lab's L2 EDAC Driver");
--
2.7.4
Document Amazon's Annapurna Labs L1 EDAC SoC binding.
Signed-off-by: Hanna Hawa <[email protected]>
---
.../devicetree/bindings/edac/amazon,al-l1-edac.txt | 14 ++++++++++++++
1 file changed, 14 insertions(+)
create mode 100644 Documentation/devicetree/bindings/edac/amazon,al-l1-edac.txt
diff --git a/Documentation/devicetree/bindings/edac/amazon,al-l1-edac.txt b/Documentation/devicetree/bindings/edac/amazon,al-l1-edac.txt
new file mode 100644
index 0000000..2ae8370
--- /dev/null
+++ b/Documentation/devicetree/bindings/edac/amazon,al-l1-edac.txt
@@ -0,0 +1,14 @@
+* Amazon's Annapurna Labs L1 EDAC
+
+Amazon's Annapurna Labs SoCs supports L1 single bit correction and
+two bits detection capability based on ARM implementation.
+
+Required properties:
+- compatible:
+ should be "amazon,al-l1-edac".
+
+Example:
+
+ al_l1_edac {
+ compatible = "amazon,al-l1-edac";
+ };
--
2.7.4