diff --git a/Documentation/gpu/drm-ras.rst b/Documentation/gpu/drm-ras.rst index 406e4c49bac1..c4ce24067d4b 100644 --- a/Documentation/gpu/drm-ras.rst +++ b/Documentation/gpu/drm-ras.rst @@ -57,6 +57,10 @@ User space tools can: * Clear specific error counters with the ``clear-error-counter`` command, using both ``node-id`` and ``error-id`` as parameters. * Subscribe to the ``error-report`` multicast group to receive ``error-event``. +* Query specific error counter threshold with the ``get-error-threshold`` command, using both + ``node-id`` and ``error-id`` as parameters. +* Set specific error counter threshold with the ``set-error-threshold`` command, using + ``node-id``, ``error-id`` and ``error-threshold`` as parameters. YAML-based Interface -------------------- @@ -132,3 +136,17 @@ Example: Subscribe to ``error-report`` multicast group "error-value": 1 } } + +Example: Query error threshold of a given counter + +.. code-block:: bash + + sudo ynl --family drm_ras --do get-error-threshold --json '{"node-id":0, "error-id":1}' + {'error-id': 1, 'error-name': 'error_name1', 'error-threshold': 16} + +Example: Set error threshold of a given counter + +.. code-block:: bash + + sudo ynl --family drm_ras --do set-error-threshold --json '{"node-id":0, "error-id":1, "error-threshold":8}' + None diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml index 8aed3d4515e5..4c2ac9a1ba3f 100644 --- a/Documentation/netlink/specs/drm_ras.yaml +++ b/Documentation/netlink/specs/drm_ras.yaml @@ -69,6 +69,10 @@ attribute-sets: name: error-value type: u32 doc: Current value of the requested error counter. + - + name: error-threshold + type: u32 + doc: Error threshold of the counter. - name: error-event-attrs attributes: @@ -167,6 +171,34 @@ operations: - error-id - error-name - error-value + - + name: get-error-threshold + doc: >- + Retrieve error threshold of a given counter. + The response includes the id, the name, and current threshold + of the counter. + attribute-set: error-counter-attrs + flags: [admin-perm] + do: + request: + attributes: *id-attrs + reply: + attributes: + - error-id + - error-name + - error-threshold + - + name: set-error-threshold + doc: >- + Set error threshold of a given counter. + attribute-set: error-counter-attrs + flags: [admin-perm] + do: + request: + attributes: + - node-id + - error-id + - error-threshold mcast-groups: list: diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c index 4fa1a257b0ed..b099eb67836e 100644 --- a/drivers/gpu/drm/drm_ras.c +++ b/drivers/gpu/drm/drm_ras.c @@ -46,6 +46,13 @@ * 5. ERROR_EVENT: Report an error event to userspace. The event contains device, node * and error information that triggered the event. * + * 6. GET_ERROR_THRESHOLD: Query error threshold of a given counter. + * Userspace must provide Node ID and Error ID. + * Returns the error threshold of a specific counter. + * + * 7. SET_ERROR_THRESHOLD: Set error threshold of a given counter. + * Userspace must provide Node ID, Error ID and threshold to be set. + * * Node registration: * * - drm_ras_node_register(): Registers a new node and assigns @@ -66,6 +73,13 @@ * + The error counters in the driver doesn't need to be contiguous, but the * driver must return -ENOENT to the query_error_counter as an indication * that the ID should be skipped and not listed in the netlink API. + * + The driver can optionally implement query_error_threshold() and + * set_error_threshold() callbacks to facilitate getting/setting error + * threshold of the counter. Threshold in RAS context means the number of + * errors the hardware is expected to accumulate before it raises them to + * software. This is to have a fine grained control over error notifications + * that are raised by the hardware. + * + The driver is responsible for error threshold bounds checking. * * Netlink handlers: * @@ -77,6 +91,10 @@ * operation, fetching a counter value from a specific node. * - drm_ras_nl_clear_error_counter_doit(): Implements the CLEAR_ERROR_COUNTER doit * operation, clearing a counter value from a specific node. + * - drm_ras_nl_get_error_threshold_doit(): Implements the GET_ERROR_THRESHOLD doit + * operation, fetching the error threshold of a specific counter. + * - drm_ras_nl_set_error_threshold_doit(): Implements the SET_ERROR_THRESHOLD doit + * operation, setting the error threshold of a specific counter. */ static DEFINE_XARRAY_ALLOC(drm_ras_xa); @@ -173,6 +191,40 @@ static int get_node_error_counter(u32 node_id, u32 error_id, return node->query_error_counter(node, error_id, name, value); } +static int get_node_error_threshold(u32 node_id, u32 error_id, const char **name, u32 *threshold) +{ + struct drm_ras_node *node; + + node = xa_load(&drm_ras_xa, node_id); + if (!node) + return -ENOENT; + + if (!node->query_error_threshold) + return -EOPNOTSUPP; + + if (error_id < node->error_counter_range.first || error_id > node->error_counter_range.last) + return -EINVAL; + + return node->query_error_threshold(node, error_id, name, threshold); +} + +static int set_node_error_threshold(u32 node_id, u32 error_id, u32 threshold) +{ + struct drm_ras_node *node; + + node = xa_load(&drm_ras_xa, node_id); + if (!node) + return -ENOENT; + + if (!node->set_error_threshold) + return -EOPNOTSUPP; + + if (error_id < node->error_counter_range.first || error_id > node->error_counter_range.last) + return -EINVAL; + + return node->set_error_threshold(node, error_id, threshold); +} + static int msg_reply_value(struct sk_buff *msg, u32 error_id, const char *error_name, u32 value) { @@ -219,6 +271,22 @@ static int msg_put_error_event_attrs(struct sk_buff *msg, struct drm_ras_node *n return nla_put_u32(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_VALUE, value); } +static int msg_reply_threshold(struct sk_buff *msg, u32 error_id, const char *error_name, + u32 threshold) +{ + int ret; + + ret = nla_put_u32(msg, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID, error_id); + if (ret) + return ret; + + ret = nla_put_string(msg, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_NAME, error_name); + if (ret) + return ret; + + return nla_put_u32(msg, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD, threshold); +} + static int doit_reply_value(struct genl_info *info, u32 node_id, u32 error_id) { @@ -258,6 +326,43 @@ free_msg: return ret; } +static int doit_reply_threshold(struct genl_info *info, u32 node_id, u32 error_id) +{ + const char *error_name; + struct sk_buff *msg; + struct nlattr *hdr; + u32 threshold; + int ret; + + msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_iput(msg, info); + if (!hdr) { + ret = -EMSGSIZE; + goto free_msg; + } + + ret = get_node_error_threshold(node_id, error_id, &error_name, &threshold); + if (ret) + goto cancel_msg; + + ret = msg_reply_threshold(msg, error_id, error_name, threshold); + if (ret) + goto cancel_msg; + + genlmsg_end(msg, hdr); + + return genlmsg_reply(msg, info); + +cancel_msg: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return ret; +} + /** * drm_ras_nl_error_event() - Report an error event * @node: Node structure @@ -459,6 +564,59 @@ int drm_ras_nl_clear_error_counter_doit(struct sk_buff *skb, return node->clear_error_counter(node, error_id); } +/** + * drm_ras_nl_get_error_threshold_doit() - Query error threshold of a counter + * @skb: Netlink message buffer + * @info: Generic Netlink info containing attributes of the request + * + * Extracts the Node ID and Error ID from the netlink attributes and retrieves + * the error threshold of the corresponding counter. Sends the result back to + * the requesting user via the standard Genl reply. + * + * Return: 0 on success, or negative errno on failure. + */ +int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb, struct genl_info *info) +{ + u32 node_id, error_id; + + if (!info->attrs || + GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID) || + GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID)) + return -EINVAL; + + node_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID]); + error_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID]); + + return doit_reply_threshold(info, node_id, error_id); +} + +/** + * drm_ras_nl_set_error_threshold_doit() - Set error threshold of a counter + * @skb: Netlink message buffer + * @info: Generic Netlink info containing attributes of the request + * + * Extracts the Node ID, Error ID and threshold from the netlink attributes and + * sets the error threshold of the corresponding counter. + * + * Return: 0 on success, or negative errno on failure. + */ +int drm_ras_nl_set_error_threshold_doit(struct sk_buff *skb, struct genl_info *info) +{ + u32 node_id, error_id, threshold; + + if (!info->attrs || + GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID) || + GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID) || + GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD)) + return -EINVAL; + + node_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID]); + error_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID]); + threshold = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD]); + + return set_node_error_threshold(node_id, error_id, threshold); +} + /** * drm_ras_node_register() - Register a new RAS node * @node: Node structure to register diff --git a/drivers/gpu/drm/drm_ras_nl.c b/drivers/gpu/drm/drm_ras_nl.c index 9d3123cc9f9c..c9f5e0ceb3b5 100644 --- a/drivers/gpu/drm/drm_ras_nl.c +++ b/drivers/gpu/drm/drm_ras_nl.c @@ -28,6 +28,19 @@ static const struct nla_policy drm_ras_clear_error_counter_nl_policy[DRM_RAS_A_E [DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID] = { .type = NLA_U32, }, }; +/* DRM_RAS_CMD_GET_ERROR_THRESHOLD - do */ +static const struct nla_policy drm_ras_get_error_threshold_nl_policy[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID + 1] = { + [DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID] = { .type = NLA_U32, }, + [DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID] = { .type = NLA_U32, }, +}; + +/* DRM_RAS_CMD_SET_ERROR_THRESHOLD - do */ +static const struct nla_policy drm_ras_set_error_threshold_nl_policy[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD + 1] = { + [DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID] = { .type = NLA_U32, }, + [DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID] = { .type = NLA_U32, }, + [DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD] = { .type = NLA_U32, }, +}; + /* Ops table for drm_ras */ static const struct genl_split_ops drm_ras_nl_ops[] = { { @@ -56,6 +69,20 @@ static const struct genl_split_ops drm_ras_nl_ops[] = { .maxattr = DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = DRM_RAS_CMD_GET_ERROR_THRESHOLD, + .doit = drm_ras_nl_get_error_threshold_doit, + .policy = drm_ras_get_error_threshold_nl_policy, + .maxattr = DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DRM_RAS_CMD_SET_ERROR_THRESHOLD, + .doit = drm_ras_nl_set_error_threshold_doit, + .policy = drm_ras_set_error_threshold_nl_policy, + .maxattr = DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group drm_ras_nl_mcgrps[] = { diff --git a/drivers/gpu/drm/drm_ras_nl.h b/drivers/gpu/drm/drm_ras_nl.h index 03ec275aca92..9aef097ea10f 100644 --- a/drivers/gpu/drm/drm_ras_nl.h +++ b/drivers/gpu/drm/drm_ras_nl.h @@ -20,6 +20,10 @@ int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int drm_ras_nl_clear_error_counter_doit(struct sk_buff *skb, struct genl_info *info); +int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb, + struct genl_info *info); +int drm_ras_nl_set_error_threshold_doit(struct sk_buff *skb, + struct genl_info *info); enum { DRM_RAS_NLGRP_ERROR_REPORT, diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h index ee2caa0edc6f..1765a3130b09 100644 --- a/include/drm/drm_ras.h +++ b/include/drm/drm_ras.h @@ -71,6 +71,35 @@ struct drm_ras_node { */ int (*clear_error_counter)(struct drm_ras_node *node, u32 error_id); + /** + * @query_error_threshold: + * + * This callback is used by drm-ras to query error threshold of a + * specific counter. + * + * Driver should expect query_error_threshold() to be called with + * error_id from `error_counter_range.first` to + * `error_counter_range.last`. + * + * Returns: 0 on success, negative error code on failure. + */ + int (*query_error_threshold)(struct drm_ras_node *node, u32 error_id, const char **name, + u32 *threshold); + + /** + * @set_error_threshold: + * + * This callback is used by drm-ras to set error threshold of a specific + * counter. + * + * Driver should expect set_error_threshold() to be called with error_id + * from `error_counter_range.first` to `error_counter_range.last`. + * Driver is responsible for error threshold bounds checking. + * + * Returns: 0 on success, negative error code on failure. + */ + int (*set_error_threshold)(struct drm_ras_node *node, u32 error_id, u32 threshold); + /** @priv: Driver private data */ void *priv; }; diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h index eab8231aa87c..2f832275ee6e 100644 --- a/include/uapi/drm/drm_ras.h +++ b/include/uapi/drm/drm_ras.h @@ -33,6 +33,7 @@ enum { DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_NAME, DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_VALUE, + DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD, __DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX, DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1) @@ -55,6 +56,8 @@ enum { DRM_RAS_CMD_GET_ERROR_COUNTER, DRM_RAS_CMD_CLEAR_ERROR_COUNTER, DRM_RAS_CMD_ERROR_EVENT, + DRM_RAS_CMD_GET_ERROR_THRESHOLD, + DRM_RAS_CMD_SET_ERROR_THRESHOLD, __DRM_RAS_CMD_MAX, DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)