On 1/9/26 9:07 AM, Ben Cheatham wrote:
> The v6.11 Linux kernel adds CXL protocl (CXL.cache & CXL.mem) error
> injection for platforms that implement the error types as according to
> the v6.5+ ACPI specification. The interface for injecting these errors
> are provided by the kernel under the CXL debugfs. The relevant files in
> the interface are the einj_types file, which provides the available CXL
> error types for injection, and the einj_inject file, which injects the
> error into a CXL VH root port or CXL RCH downstream port.
>
> Add a library API to retrieve the CXL error types and inject them. This
> API will be used in a later commit by the 'cxl-inject-error' and
> 'cxl-list' commands.
>
> Signed-off-by: Ben Cheatham <[email protected]>
Just a nit below. otherwise
Reviewed-by: Dave Jiang <[email protected]>
> ---
> cxl/lib/libcxl.c | 194 +++++++++++++++++++++++++++++++++++++++++++++
> cxl/lib/libcxl.sym | 5 ++
> cxl/lib/private.h | 14 ++++
> cxl/libcxl.h | 13 +++
> 4 files changed, 226 insertions(+)
>
> diff --git a/cxl/lib/libcxl.c b/cxl/lib/libcxl.c
> index 6b7e92c..27ff037 100644
> --- a/cxl/lib/libcxl.c
> +++ b/cxl/lib/libcxl.c
> @@ -48,11 +48,13 @@ struct cxl_ctx {
> void *userdata;
> int memdevs_init;
> int buses_init;
> + int perrors_init;
> unsigned long timeout;
> struct udev *udev;
> struct udev_queue *udev_queue;
> struct list_head memdevs;
> struct list_head buses;
> + struct list_head perrors;
> struct kmod_ctx *kmod_ctx;
> struct daxctl_ctx *daxctl_ctx;
> void *private_data;
> @@ -207,6 +209,14 @@ static void free_bus(struct cxl_bus *bus, struct
> list_head *head)
> free(bus);
> }
>
> +static void free_protocol_error(struct cxl_protocol_error *perror,
> + struct list_head *head)
> +{
> + if (head)
> + list_del_from(head, &perror->list);
> + free(perror);
> +}
> +
> /**
> * cxl_get_userdata - retrieve stored data pointer from library context
> * @ctx: cxl library context
> @@ -325,6 +335,7 @@ CXL_EXPORT int cxl_new(struct cxl_ctx **ctx)
> *ctx = c;
> list_head_init(&c->memdevs);
> list_head_init(&c->buses);
> + list_head_init(&c->perrors);
> c->kmod_ctx = kmod_ctx;
> c->daxctl_ctx = daxctl_ctx;
> c->udev = udev;
> @@ -366,6 +377,7 @@ CXL_EXPORT struct cxl_ctx *cxl_ref(struct cxl_ctx *ctx)
> */
> CXL_EXPORT void cxl_unref(struct cxl_ctx *ctx)
> {
> + struct cxl_protocol_error *perror, *_p;
> struct cxl_memdev *memdev, *_d;
> struct cxl_bus *bus, *_b;
>
> @@ -381,6 +393,9 @@ CXL_EXPORT void cxl_unref(struct cxl_ctx *ctx)
> list_for_each_safe(&ctx->buses, bus, _b, port.list)
> free_bus(bus, &ctx->buses);
>
> + list_for_each_safe(&ctx->perrors, perror, _p, list)
> + free_protocol_error(perror, &ctx->perrors);
> +
> udev_queue_unref(ctx->udev_queue);
> udev_unref(ctx->udev);
> kmod_unref(ctx->kmod_ctx);
> @@ -3423,6 +3438,185 @@ CXL_EXPORT int cxl_port_decoders_committed(struct
> cxl_port *port)
> return port->decoders_committed;
> }
>
> +const struct cxl_protocol_error cxl_protocol_errors[] = {
> + CXL_PROTOCOL_ERROR(0x1000, "cache-correctable"),
> + CXL_PROTOCOL_ERROR(0x2000, "cache-uncorrectable"),
> + CXL_PROTOCOL_ERROR(0x4000, "cache-fatal"),
> + CXL_PROTOCOL_ERROR(0x8000, "mem-correctable"),
> + CXL_PROTOCOL_ERROR(0x10000, "mem-uncorrectable"),
> + CXL_PROTOCOL_ERROR(0x20000, "mem-fatal")
> +};
> +
> +static struct cxl_protocol_error *create_cxl_protocol_error(struct cxl_ctx
> *ctx,
> + unsigned int n)
> +{
> + struct cxl_protocol_error *perror;
> +
> + for (unsigned long i = 0; i < ARRAY_SIZE(cxl_protocol_errors); i++) {
> + if (n != cxl_protocol_errors[i].num)
> + continue;
> +
> + perror = calloc(1, sizeof(*perror));
> + if (!perror)
> + return NULL;
> +
> + *perror = cxl_protocol_errors[i];
> + perror->ctx = ctx;
> + return perror;
> + }
> +
> + return NULL;
> +}
> +
> +static void cxl_add_protocol_errors(struct cxl_ctx *ctx)
> +{
> + struct cxl_protocol_error *perror;
> + char buf[SYSFS_ATTR_SIZE];
> + char *path, *num, *save;
> + size_t path_len, len;
> + unsigned long n;
> + int rc = 0;
> +
> + if (!ctx->cxl_debugfs)
> + return;
> +
> + path_len = strlen(ctx->cxl_debugfs) + 100;
> + path = calloc(1, path_len);
Maybe just use PATH_MAX from <linux/limits.h>.
DJ
> + if (!path)
> + return;
> +
> + len = snprintf(path, path_len, "%s/einj_types", ctx->cxl_debugfs);
> + if (len >= path_len) {
> + err(ctx, "Buffer too small\n");
> + goto err;
> + }
> +
> + rc = access(path, F_OK);
> + if (rc) {
> + err(ctx, "failed to access %s: %s\n", path, strerror(errno));
> + goto err;
> + }
> +
> + rc = sysfs_read_attr(ctx, path, buf);
> + if (rc) {
> + err(ctx, "failed to read %s: %s\n", path, strerror(-rc));
> + goto err;
> + }
> +
> + /*
> + * The format of the output of the einj_types attr is:
> + * <Error number in hex 1> <Error name 1>
> + * <Error number in hex 2> <Error name 2>
> + * ...
> + *
> + * We only need the number, so parse that and skip the rest of
> + * the line.
> + */
> + num = strtok_r(buf, " \n", &save);
> + while (num) {
> + n = strtoul(num, NULL, 16);
> + perror = create_cxl_protocol_error(ctx, n);
> + if (perror)
> + list_add_tail(&ctx->perrors, &perror->list);
> +
> + num = strtok_r(NULL, "\n", &save);
> + if (!num)
> + break;
> +
> + num = strtok_r(NULL, " \n", &save);
> + }
> +
> +err:
> + free(path);
> +}
> +
> +static void cxl_protocol_errors_init(struct cxl_ctx *ctx)
> +{
> + if (ctx->perrors_init)
> + return;
> +
> + ctx->perrors_init = 1;
> + cxl_add_protocol_errors(ctx);
> +}
> +
> +CXL_EXPORT struct cxl_protocol_error *
> +cxl_protocol_error_get_first(struct cxl_ctx *ctx)
> +{
> + cxl_protocol_errors_init(ctx);
> +
> + return list_top(&ctx->perrors, struct cxl_protocol_error, list);
> +}
> +
> +CXL_EXPORT struct cxl_protocol_error *
> +cxl_protocol_error_get_next(struct cxl_protocol_error *perror)
> +{
> + struct cxl_ctx *ctx = perror->ctx;
> +
> + return list_next(&ctx->perrors, perror, list);
> +}
> +
> +CXL_EXPORT unsigned int
> +cxl_protocol_error_get_num(struct cxl_protocol_error *perror)
> +{
> + return perror->num;
> +}
> +
> +CXL_EXPORT const char *
> +cxl_protocol_error_get_str(struct cxl_protocol_error *perror)
> +{
> + return perror->string;
> +}
> +
> +CXL_EXPORT int cxl_dport_protocol_error_inject(struct cxl_dport *dport,
> + unsigned int error)
> +{
> + struct cxl_ctx *ctx = dport->port->ctx;
> + char buf[32] = { 0 };
> + size_t path_len, len;
> + char *path;
> + int rc;
> +
> + if (!ctx->cxl_debugfs)
> + return -ENOENT;
> +
> + path_len = strlen(ctx->cxl_debugfs) + 100;
> + path = calloc(path_len, sizeof(char));
> + if (!path)
> + return -ENOMEM;
> +
> + len = snprintf(path, path_len, "%s/%s/einj_inject", ctx->cxl_debugfs,
> + cxl_dport_get_devname(dport));
> + if (len >= path_len) {
> + err(ctx, "%s: buffer too small\n",
> cxl_dport_get_devname(dport));
> + free(path);
> + return -ENOMEM;
> + }
> +
> + rc = access(path, F_OK);
> + if (rc) {
> + err(ctx, "failed to access %s: %s\n", path, strerror(errno));
> + free(path);
> + return -errno;
> + }
> +
> + len = snprintf(buf, sizeof(buf), "0x%x\n", error);
> + if (len >= sizeof(buf)) {
> + err(ctx, "%s: buffer too small\n",
> cxl_dport_get_devname(dport));
> + free(path);
> + return -ENOMEM;
> + }
> +
> + rc = sysfs_write_attr(ctx, path, buf);
> + if (rc) {
> + err(ctx, "failed to write %s: %s\n", path, strerror(-rc));
> + free(path);
> + return -errno;
> + }
> +
> + free(path);
> + return 0;
> +}
> +
> static void *add_cxl_bus(void *parent, int id, const char *cxlbus_base)
> {
> const char *devname = devpath_to_devname(cxlbus_base);
> diff --git a/cxl/lib/libcxl.sym b/cxl/lib/libcxl.sym
> index 36a93c3..c683b83 100644
> --- a/cxl/lib/libcxl.sym
> +++ b/cxl/lib/libcxl.sym
> @@ -304,4 +304,9 @@ global:
> LIBCXL_11 {
> global:
> cxl_region_get_extended_linear_cache_size;
> + cxl_protocol_error_get_first;
> + cxl_protocol_error_get_next;
> + cxl_protocol_error_get_num;
> + cxl_protocol_error_get_str;
> + cxl_dport_protocol_error_inject;
> } LIBCXL_10;
> diff --git a/cxl/lib/private.h b/cxl/lib/private.h
> index 542cdb7..582eebf 100644
> --- a/cxl/lib/private.h
> +++ b/cxl/lib/private.h
> @@ -108,6 +108,20 @@ struct cxl_port {
> struct list_head dports;
> };
>
> +struct cxl_protocol_error {
> + unsigned int num;
> + const char *string;
> + struct cxl_ctx *ctx;
> + struct list_node list;
> +};
> +
> +#define CXL_PROTOCOL_ERROR(n, str) \
> + ((struct cxl_protocol_error){ \
> + .num = (n), \
> + .string = (str), \
> + .ctx = NULL, \
> + })
> +
> struct cxl_bus {
> struct cxl_port port;
> };
> diff --git a/cxl/libcxl.h b/cxl/libcxl.h
> index 9371aac..faef62e 100644
> --- a/cxl/libcxl.h
> +++ b/cxl/libcxl.h
> @@ -498,6 +498,19 @@ int cxl_cmd_alert_config_set_enable_alert_actions(struct
> cxl_cmd *cmd,
> int enable);
> struct cxl_cmd *cxl_cmd_new_set_alert_config(struct cxl_memdev *memdev);
>
> +struct cxl_protocol_error;
> +struct cxl_protocol_error *cxl_protocol_error_get_first(struct cxl_ctx *ctx);
> +struct cxl_protocol_error *
> +cxl_protocol_error_get_next(struct cxl_protocol_error *perror);
> +unsigned int cxl_protocol_error_get_num(struct cxl_protocol_error *perror);
> +const char *cxl_protocol_error_get_str(struct cxl_protocol_error *perror);
> +int cxl_dport_protocol_error_inject(struct cxl_dport *dport,
> + unsigned int error);
> +
> +#define cxl_protocol_error_foreach(ctx, perror)
> \
> + for (perror = cxl_protocol_error_get_first(ctx); perror != NULL; \
> + perror = cxl_protocol_error_get_next(perror))
> +
> #ifdef __cplusplus
> } /* extern "C" */
> #endif
