diff mbox series

[ndctl,v2,1/5] libcxl: add interfaces for GET_POISON_LIST mailbox commands

Message ID f59b7ae3277342f54bbcf409ac075a9c122ecd79.1696196382.git.alison.schofield@intel.com
State Superseded
Headers show
Series Support poison list retrieval | expand

Commit Message

Alison Schofield Oct. 1, 2023, 10:31 p.m. UTC
From: Alison Schofield <alison.schofield@intel.com>

CXL devices maintain a list of locations that are poisoned or result
in poison if the addresses are accessed by the host.

Per the spec (CXL 3.0 8.2.9.8.4.1), the device returns the Poison
List as a set of  Media Error Records that include the source of the
error, the starting device physical address and length.

Trigger the retrieval of the poison list by writing to the memory
device sysfs attribute: trigger_poison_list. The CXL driver only
offers triggering per memdev, so the trigger by region interface
offered here is a convenience API that triggers a poison list
retrieval for each memdev contributing to a region.

int cxl_memdev_trigger_poison_list(struct cxl_memdev *memdev);
int cxl_region_trigger_poison_list(struct cxl_region *region);

The resulting poison records are logged as kernel trace events
named 'cxl_poison'.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
---
 cxl/lib/libcxl.c   | 47 ++++++++++++++++++++++++++++++++++++++++++++++
 cxl/lib/libcxl.sym |  6 ++++++
 cxl/libcxl.h       |  2 ++
 3 files changed, 55 insertions(+)

Comments

Verma, Vishal L Nov. 15, 2023, 10:08 a.m. UTC | #1
On Sun, 2023-10-01 at 15:31 -0700, alison.schofield@intel.com wrote:
> From: Alison Schofield <alison.schofield@intel.com>
> 
> CXL devices maintain a list of locations that are poisoned or result
> in poison if the addresses are accessed by the host.
> 
> Per the spec (CXL 3.0 8.2.9.8.4.1), the device returns the Poison
> List as a set of  Media Error Records that include the source of the
> error, the starting device physical address and length.
> 
> Trigger the retrieval of the poison list by writing to the memory
> device sysfs attribute: trigger_poison_list. The CXL driver only
> offers triggering per memdev, so the trigger by region interface
> offered here is a convenience API that triggers a poison list
> retrieval for each memdev contributing to a region.
> 
> int cxl_memdev_trigger_poison_list(struct cxl_memdev *memdev);
> int cxl_region_trigger_poison_list(struct cxl_region *region);
> 
> The resulting poison records are logged as kernel trace events
> named 'cxl_poison'.
> 
> Signed-off-by: Alison Schofield <alison.schofield@intel.com>
> ---
>  cxl/lib/libcxl.c   | 47 ++++++++++++++++++++++++++++++++++++++++++++++
>  cxl/lib/libcxl.sym |  6 ++++++
>  cxl/libcxl.h       |  2 ++
>  3 files changed, 55 insertions(+)
> 
> diff --git a/cxl/lib/libcxl.c b/cxl/lib/libcxl.c
> index af4ca44eae19..2f6e64ea2ae7 100644
> --- a/cxl/lib/libcxl.c
> +++ b/cxl/lib/libcxl.c
> @@ -1647,6 +1647,53 @@ CXL_EXPORT int cxl_memdev_disable_invalidate(struct cxl_memdev *memdev)
>         return 0;
>  }
>  
> +CXL_EXPORT int cxl_memdev_trigger_poison_list(struct cxl_memdev *memdev)
> +{
> +       struct cxl_ctx *ctx = cxl_memdev_get_ctx(memdev);
> +       char *path = memdev->dev_buf;
> +       int len = memdev->buf_len, rc;
> +
> +       if (snprintf(path, len, "%s/trigger_poison_list", memdev->dev_path) >=
> +           len) {

I see this unfortunate line break Jonathan commented on still crept in,
agreed that breaking up snprintf's args would look better.
Alison Schofield Nov. 17, 2023, 4:21 p.m. UTC | #2
On Wed, Nov 15, 2023 at 02:08:03AM -0800, Vishal Verma wrote:
> On Sun, 2023-10-01 at 15:31 -0700, alison.schofield@intel.com wrote:

snip

> > +CXL_EXPORT int cxl_memdev_trigger_poison_list(struct cxl_memdev *memdev)
> > +{
> > +       struct cxl_ctx *ctx = cxl_memdev_get_ctx(memdev);
> > +       char *path = memdev->dev_buf;
> > +       int len = memdev->buf_len, rc;
> > +
> > +       if (snprintf(path, len, "%s/trigger_poison_list", memdev->dev_path) >=
> > +           len) {
> 
> I see this unfortunate line break Jonathan commented on still crept in,
> agreed that breaking up snprintf's args would look better.

Fixed up in v3.
Thanks!


> 
>
diff mbox series

Patch

diff --git a/cxl/lib/libcxl.c b/cxl/lib/libcxl.c
index af4ca44eae19..2f6e64ea2ae7 100644
--- a/cxl/lib/libcxl.c
+++ b/cxl/lib/libcxl.c
@@ -1647,6 +1647,53 @@  CXL_EXPORT int cxl_memdev_disable_invalidate(struct cxl_memdev *memdev)
 	return 0;
 }
 
+CXL_EXPORT int cxl_memdev_trigger_poison_list(struct cxl_memdev *memdev)
+{
+	struct cxl_ctx *ctx = cxl_memdev_get_ctx(memdev);
+	char *path = memdev->dev_buf;
+	int len = memdev->buf_len, rc;
+
+	if (snprintf(path, len, "%s/trigger_poison_list", memdev->dev_path) >=
+	    len) {
+		err(ctx, "%s: buffer too small\n",
+		    cxl_memdev_get_devname(memdev));
+		return -ENXIO;
+	}
+	rc = sysfs_write_attr(ctx, path, "1\n");
+	if (rc < 0) {
+		fprintf(stderr,
+			"%s: Failed write sysfs attr trigger_poison_list\n",
+			cxl_memdev_get_devname(memdev));
+		return rc;
+	}
+	return 0;
+}
+
+CXL_EXPORT int cxl_region_trigger_poison_list(struct cxl_region *region)
+{
+	struct cxl_memdev_mapping *mapping;
+	int rc;
+
+	cxl_mapping_foreach(region, mapping) {
+		struct cxl_decoder *decoder;
+		struct cxl_memdev *memdev;
+
+		decoder = cxl_mapping_get_decoder(mapping);
+		if (!decoder)
+			continue;
+
+		memdev = cxl_decoder_get_memdev(decoder);
+		if (!memdev)
+			continue;
+
+		rc = cxl_memdev_trigger_poison_list(memdev);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 CXL_EXPORT int cxl_memdev_enable(struct cxl_memdev *memdev)
 {
 	struct cxl_ctx *ctx = cxl_memdev_get_ctx(memdev);
diff --git a/cxl/lib/libcxl.sym b/cxl/lib/libcxl.sym
index 8fa1cca3d0d7..277b7e21d6a6 100644
--- a/cxl/lib/libcxl.sym
+++ b/cxl/lib/libcxl.sym
@@ -264,3 +264,9 @@  global:
 	cxl_memdev_update_fw;
 	cxl_memdev_cancel_fw_update;
 } LIBCXL_5;
+
+LIBCXL_7 {
+global:
+	cxl_memdev_trigger_poison_list;
+	cxl_region_trigger_poison_list;
+} LIBCXL_6;
diff --git a/cxl/libcxl.h b/cxl/libcxl.h
index 0f4f4b2648fb..ecdffe36df2c 100644
--- a/cxl/libcxl.h
+++ b/cxl/libcxl.h
@@ -460,6 +460,8 @@  enum cxl_setpartition_mode {
 
 int cxl_cmd_partition_set_mode(struct cxl_cmd *cmd,
 		enum cxl_setpartition_mode mode);
+int cxl_memdev_trigger_poison_list(struct cxl_memdev *memdev);
+int cxl_region_trigger_poison_list(struct cxl_region *region);
 
 #ifdef __cplusplus
 } /* extern "C" */