[v8,3/6] cxl/memdev: Add trigger_poison_list sysfs attribute

Message ID c245435e48d87af3994380cf2b6da0a6763de4bf.1678468593.git.alison.schofield@intel.com
State New
Headers
Series CXL Poison List Retrieval & Tracing |

Commit Message

Alison Schofield March 10, 2023, 5:54 p.m. UTC
  From: Alison Schofield <alison.schofield@intel.com>

When a boolean 'true' is written to this attribute the memdev driver
retrieves the poison list from the device. The list consists of
addresses that are poisoned, or would result in poison if accessed,
and the source of the poison. This attribute is only visible for
devices supporting the capability. The retrieved errors are logged
as kernel trace events with the label 'cxl_poison'.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/ABI/testing/sysfs-bus-cxl | 14 +++++++
 drivers/cxl/core/memdev.c               | 56 +++++++++++++++++++++++++
 drivers/cxl/cxlmem.h                    |  2 +-
 3 files changed, 71 insertions(+), 1 deletion(-)
  

Comments

Ira Weiny March 13, 2023, 10:53 p.m. UTC | #1
alison.schofield@ wrote:
> From: Alison Schofield <alison.schofield@intel.com>
> 
> When a boolean 'true' is written to this attribute the memdev driver
> retrieves the poison list from the device. The list consists of
> addresses that are poisoned, or would result in poison if accessed,
> and the source of the poison. This attribute is only visible for
> devices supporting the capability. The retrieved errors are logged
> as kernel trace events with the label 'cxl_poison'.
> 
> Signed-off-by: Alison Schofield <alison.schofield@intel.com>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

Reviewed-by: Ira Weiny <ira.weiny@intel.com>
  

Patch

diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl
index 3acf2f17a73f..02776fee6d4c 100644
--- a/Documentation/ABI/testing/sysfs-bus-cxl
+++ b/Documentation/ABI/testing/sysfs-bus-cxl
@@ -415,3 +415,17 @@  Description:
 		1), and checks that the hardware accepts the commit request.
 		Reading this value indicates whether the region is committed or
 		not.
+
+
+What:		/sys/bus/cxl/devices/memX/trigger_poison_list
+Date:		March, 2023
+KernelVersion:	v6.4
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(WO) When a boolean 'true' is written to this attribute the
+		memdev driver retrieves the poison list from the device. The
+		list consists of addresses that are poisoned, or would result
+		in poison if accessed, and the source of the poison. This
+		attribute is only visible for devices supporting the
+		capability. The retrieved errors are logged as kernel
+		trace events with the label 'cxl_poison'.
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index 0af8856936dc..ea996057815e 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -106,12 +106,60 @@  static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(numa_node);
 
+static int cxl_get_poison_by_memdev(struct cxl_memdev *cxlmd)
+{
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	u64 offset, length;
+	int rc = 0;
+
+	/* CXL 3.0 Spec 8.2.9.8.4.1 Separate pmem and ram poison requests */
+	if (resource_size(&cxlds->pmem_res)) {
+		offset = cxlds->pmem_res.start;
+		length = resource_size(&cxlds->pmem_res);
+		rc = cxl_mem_get_poison(cxlmd, offset, length, NULL);
+		if (rc)
+			return rc;
+	}
+	if (resource_size(&cxlds->ram_res)) {
+		offset = cxlds->ram_res.start;
+		length = resource_size(&cxlds->ram_res);
+		rc = cxl_mem_get_poison(cxlmd, offset, length, NULL);
+		/*
+		 * Invalid Physical Address is not an error for
+		 * volatile addresses. Device support is optional.
+		 */
+		if (rc == -EFAULT)
+			rc = 0;
+	}
+	return rc;
+}
+
+static ssize_t trigger_poison_list_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t len)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	bool trigger;
+	int rc;
+
+	if (kstrtobool(buf, &trigger) || !trigger)
+		return -EINVAL;
+
+	down_read(&cxl_dpa_rwsem);
+	rc = cxl_get_poison_by_memdev(cxlmd);
+	up_read(&cxl_dpa_rwsem);
+
+	return rc ? rc : len;
+}
+static DEVICE_ATTR_WO(trigger_poison_list);
+
 static struct attribute *cxl_memdev_attributes[] = {
 	&dev_attr_serial.attr,
 	&dev_attr_firmware_version.attr,
 	&dev_attr_payload_max.attr,
 	&dev_attr_label_storage_size.attr,
 	&dev_attr_numa_node.attr,
+	&dev_attr_trigger_poison_list.attr,
 	NULL,
 };
 
@@ -130,6 +178,14 @@  static umode_t cxl_memdev_visible(struct kobject *kobj, struct attribute *a,
 {
 	if (!IS_ENABLED(CONFIG_NUMA) && a == &dev_attr_numa_node.attr)
 		return 0;
+
+	if (a == &dev_attr_trigger_poison_list.attr) {
+		struct device *dev = kobj_to_dev(kobj);
+
+		if (!test_bit(CXL_MEM_COMMAND_ID_GET_POISON,
+			      to_cxl_memdev(dev)->cxlds->enabled_cmds))
+			return 0;
+	}
 	return a->mode;
 }
 
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 57a5999ddb35..a6eb1b42eb88 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -145,7 +145,7 @@  struct cxl_mbox_cmd {
 	C(FWROLLBACK, -ENXIO, "rolled back to the previous active FW"),         \
 	C(FWRESET, -ENXIO, "FW failed to activate, needs cold reset"),		\
 	C(HANDLE, -ENXIO, "one or more Event Record Handles were invalid"),     \
-	C(PADDR, -ENXIO, "physical address specified is invalid"),		\
+	C(PADDR, -EFAULT, "physical address specified is invalid"),		\
 	C(POISONLMT, -ENXIO, "poison injection limit has been reached"),        \
 	C(MEDIAFAILURE, -ENXIO, "permanent issue with the media"),		\
 	C(ABORT, -ENXIO, "background cmd was aborted by device"),               \