Re: [PATCH 3/7] libcxl: Add poison injection support

[Dave Jiang <dave.jiang@intel.com>]

On 1/9/26 9:07 AM, Ben Cheatham wrote:
> Add a library API for clearing and injecting poison into a CXL memory
> device through the CXL debugfs.
> 
> This API will be used by the 'cxl-inject-error' and 'cxl-clear-error'
> commands in later commits.
> 
> Signed-off-by: Ben Cheatham <Benjamin.Cheatham@amd.com>
> ---
>  cxl/lib/libcxl.c   | 83 ++++++++++++++++++++++++++++++++++++++++++++++
>  cxl/lib/libcxl.sym |  3 ++
>  cxl/libcxl.h       |  3 ++
>  3 files changed, 89 insertions(+)
> 
> diff --git a/cxl/lib/libcxl.c b/cxl/lib/libcxl.c
> index 27ff037..deebf7f 100644
> --- a/cxl/lib/libcxl.c
> +++ b/cxl/lib/libcxl.c
> @@ -5046,3 +5046,86 @@ CXL_EXPORT struct cxl_cmd *cxl_cmd_new_set_alert_config(struct cxl_memdev *memde
>  {
>  	return cxl_cmd_new_generic(memdev, CXL_MEM_COMMAND_ID_SET_ALERT_CONFIG);
>  }
> +
> +CXL_EXPORT bool cxl_memdev_has_poison_injection(struct cxl_memdev *memdev)
> +{
> +	struct cxl_ctx *ctx = memdev->ctx;
> +	size_t path_len, len;
> +	bool exists = true;
> +	char *path;
> +	int rc;
> +
> +	if (!ctx->cxl_debugfs)
> +		return false;
> +
> +	path_len = strlen(ctx->cxl_debugfs) + 100;

Same comment about PATH_MAX.

> +	path = calloc(path_len, sizeof(char));
> +	if (!path)
> +		return false;
> +
> +	len = snprintf(path, path_len, "%s/%s/inject_poison", ctx->cxl_debugfs,
> +		       cxl_memdev_get_devname(memdev));
> +	if (len >= path_len) {
> +		err(ctx, "%s: buffer too small\n",
> +		    cxl_memdev_get_devname(memdev));
> +		free(path);
> +		return false;

I think I saw in an earlier patch that you were using goto to filter error exit point. So may as well make it consistent and do it here as well.

> +	}
> +
> +	rc = access(path, F_OK);
> +	if (rc)
> +		exists = false;
> +
> +	free(path);
> +	return exists;
> +}
> +
> +static int cxl_memdev_poison_action(struct cxl_memdev *memdev, size_t dpa,
> +				    bool clear)
> +{
> +	struct cxl_ctx *ctx = memdev->ctx;
> +	size_t path_len, len;
> +	char addr[32];
> +	char *path;
> +	int rc;
> +
> +	if (!ctx->cxl_debugfs)
> +		return -ENOENT;
> +
> +	path_len = strlen(ctx->cxl_debugfs) + 100;

same comment about path len

> +	path = calloc(path_len, sizeof(char));
> +	if (!path)
> +		return -ENOMEM;
> +
> +	len = snprintf(path, path_len, "%s/%s/%s", ctx->cxl_debugfs,
> +		       cxl_memdev_get_devname(memdev),
> +		       clear ? "clear_poison" : "inject_poison");
> +	if (len >= path_len) {
> +		err(ctx, "%s: buffer too small\n",
> +		    cxl_memdev_get_devname(memdev));
> +		free(path);
> +		return -ENOMEM;

same comment about error paths

DJ

> +	}
> +
> +	len = snprintf(addr, sizeof(addr), "0x%lx\n", dpa);
> +	if (len >= sizeof(addr)) {
> +		err(ctx, "%s: buffer too small\n",
> +		    cxl_memdev_get_devname(memdev));
> +		free(path);
> +		return -ENOMEM;
> +	}
> +
> +	rc = sysfs_write_attr(ctx, path, addr);
> +	free(path);
> +	return rc;
> +}
> +
> +CXL_EXPORT int cxl_memdev_inject_poison(struct cxl_memdev *memdev, size_t addr)
> +{
> +	return cxl_memdev_poison_action(memdev, addr, false);
> +}
> +
> +CXL_EXPORT int cxl_memdev_clear_poison(struct cxl_memdev *memdev, size_t addr)
> +{
> +	return cxl_memdev_poison_action(memdev, addr, true);
> +}
> diff --git a/cxl/lib/libcxl.sym b/cxl/lib/libcxl.sym
> index c683b83..c636edb 100644
> --- a/cxl/lib/libcxl.sym
> +++ b/cxl/lib/libcxl.sym
> @@ -309,4 +309,7 @@ global:
>  	cxl_protocol_error_get_num;
>  	cxl_protocol_error_get_str;
>  	cxl_dport_protocol_error_inject;
> +	cxl_memdev_has_poison_injection;
> +	cxl_memdev_inject_poison;
> +	cxl_memdev_clear_poison;
>  } LIBCXL_10;
> diff --git a/cxl/libcxl.h b/cxl/libcxl.h
> index faef62e..4d035f0 100644
> --- a/cxl/libcxl.h
> +++ b/cxl/libcxl.h
> @@ -105,6 +105,9 @@ int cxl_memdev_read_label(struct cxl_memdev *memdev, void *buf, size_t length,
>  		size_t offset);
>  int cxl_memdev_write_label(struct cxl_memdev *memdev, void *buf, size_t length,
>  		size_t offset);
> +bool cxl_memdev_has_poison_injection(struct cxl_memdev *memdev);
> +int cxl_memdev_inject_poison(struct cxl_memdev *memdev, size_t dpa);
> +int cxl_memdev_clear_poison(struct cxl_memdev *memdev, size_t dpa);
>  struct cxl_cmd *cxl_cmd_new_get_fw_info(struct cxl_memdev *memdev);
>  unsigned int cxl_cmd_fw_info_get_num_slots(struct cxl_cmd *cmd);
>  unsigned int cxl_cmd_fw_info_get_active_slot(struct cxl_cmd *cmd);