Add a new node type, attribute set, and doit function for performing telemetry read and write operations using the DRM RAS interface.
Signed-off-by: Zack McKevitt <[email protected]> --- Documentation/netlink/specs/drm_ras.yaml | 55 ++++++- drivers/gpu/drm/drm_ras.c | 193 ++++++++++++++++++++++- drivers/gpu/drm/drm_ras_nl.c | 29 ++++ drivers/gpu/drm/drm_ras_nl.h | 6 + include/drm/drm_ras.h | 39 +++++ include/uapi/drm/drm_ras.h | 14 ++ 6 files changed, 327 insertions(+), 9 deletions(-) diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml index a88fdab7a1c7..d558eb1cba3f 100644 --- a/Documentation/netlink/specs/drm_ras.yaml +++ b/Documentation/netlink/specs/drm_ras.yaml @@ -16,7 +16,7 @@ definitions: type: enum name: node-type value-start: 1 - entries: [error-counter] + entries: [error-counter, telemetry] doc: >- Type of the node. Currently, only error-counter nodes are supported, which expose reliability counters for a hardware/software @@ -100,6 +100,31 @@ attribute-sets: name: error-value type: u32 doc: Current value of the error counter. + - + name: telemetry-attrs + attributes: + - + name: node-id + type: u32 + doc: >- + Unique identifier for the node. + Assigned dynamically by the DRM RAS core upon registration. + - + name: field + type: u32 + doc: Telemetry field to be read/written, e.g., SoC temp. + - + name: value + type: u64 + doc: Value of telemetry field that was read/written. + - + name: status + type: s32 + doc: Status of the telemetry operation. + - + name: pad + type: pad + doc: Alignment padding used for 64-bit operations: list: @@ -198,6 +223,34 @@ operations: - node-id - error-id - error-threshold + - + name: telemetry-read + doc: Perform a read of the specified telemetry field. + attribute-set: telemetry-attrs + do: + pre: drm-ras-nl-pre-telemetry + request: + attributes: + - node-id + - field + reply: + attributes: + - value + - status + - + name: telemetry-write + doc: Perform a write of the specified telemetry field. + attribute-set: telemetry-attrs + do: + pre: drm-ras-nl-pre-telemetry + request: + attributes: + - node-id + - field + - value + reply: + attributes: + - status mcast-groups: list: diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c index b099eb67836e..b88293295cda 100644 --- a/drivers/gpu/drm/drm_ras.c +++ b/drivers/gpu/drm/drm_ras.c @@ -53,6 +53,15 @@ * 7. SET_ERROR_THRESHOLD: Set error threshold of a given counter. * Userspace must provide Node ID, Error ID and threshold to be set. * + * 8. TELEMETRY_READ: Read a telemetry value. + * Userspace must provide Node ID and telemetry field to be read. + * Returns the status of the read and the value read (if valid). + * + * 9. TELEMETRY_WRITE: Write a telemetry value. + * Userspace must provide Node ID, the telemetry field to write, and the value + * to be written. + * Returns the status of the write. + * * Node registration: * * - drm_ras_node_register(): Registers a new node and assigns @@ -63,7 +72,6 @@ * Node type: * * - ERROR_COUNTER: - * + Currently, only error counters are supported. * + The driver must implement the query_error_counter() callback to provide * the name and the value of the error counter. * + The driver must provide a error_counter_range.last value informing the @@ -81,6 +89,12 @@ * that are raised by the hardware. * + The driver is responsible for error threshold bounds checking. * + * - TELEMETRY: + * + The driver must implement the telemetry_read() and telemetry_write() + * callbacks. + * + The driver can optionally provide a pre_doit callback, telemetry_pre(), + * to enforce permissions checks on telemetry operations. + * * Netlink handlers: * * - drm_ras_nl_list_nodes_dumpit(): Implements the LIST_NODES @@ -95,6 +109,12 @@ * 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. + * - drm_ras_nl_pre_telemetry(): Implements the TELEMETRY_READ and TELEMETRY_WRITE + * pre_doit operation, returning 0 if valid. + * - drm_ras_nl_telemetry_read_doit(): Implements the TELEMETRY_READ doit operation, + * invoking the driver's telemetry_read callback and returning the results. + * - drm_ras_nl_telemetry_write_doit(): Implements the TELEMETRY_WRITE doit operation, + * invoking the driver's telemetry_write callback and returning the results. */ static DEFINE_XARRAY_ALLOC(drm_ras_xa); @@ -617,6 +637,156 @@ int drm_ras_nl_set_error_threshold_doit(struct sk_buff *skb, struct genl_info *i return set_node_error_threshold(node_id, error_id, threshold); } +/** + * drm_ras_nl_pre_telemetry - Enforce permission checks + * @ops: Generic netlink operations + * @skb: Netlink message buffer + * @info: Generic Netlink info containing attributes of the request + * + * Enforces a telemetry node's pre_doit conditions (if they exist). + * + * Returns 0 if no pre_doit is specified, otherwise returns the pre_doit. + */ +int drm_ras_nl_pre_telemetry(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + struct drm_ras_node *node; + u32 node_id; + + node_id = nla_get_u32(info->attrs[DRM_RAS_A_TELEMETRY_ATTRS_NODE_ID]); + node = xa_load(&drm_ras_xa, node_id); + + if (node->telemetry_pre) + return node->telemetry_pre(node); + + return 0; +} + +/** + * drm_ras_nl_telemetry_read_doit() - Query a telemetry value + * @skb: Netlink message buffer + * @info: Generic Netlink info containing attributes of the request + * + * Extracts the telemetry field from the netlink attributes and + * reads that value from the device. + * + * Return: 0 on success, or negative errno on failure. + */ +int drm_ras_nl_telemetry_read_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct drm_ras_node *node; + struct sk_buff *msg; + struct nlattr *hdr; + u32 node_id, field; + s32 status; + u64 value; + int ret; + + if (!info->attrs || !info->attrs[DRM_RAS_A_TELEMETRY_ATTRS_FIELD]) + return -EINVAL; + + field = nla_get_u32(info->attrs[DRM_RAS_A_TELEMETRY_ATTRS_FIELD]); + node_id = nla_get_u32(info->attrs[DRM_RAS_A_TELEMETRY_ATTRS_NODE_ID]); + + node = xa_load(&drm_ras_xa, node_id); + if (!node || !node->telemetry_read) + return -ENOENT; + + msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_iput(msg, info); + if (!hdr) { + nlmsg_free(msg); + return -EMSGSIZE; + } + + ret = node->telemetry_read(node, &field, &value, &status); + if (ret) { + nlmsg_free(msg); + return ret; + } + + ret = nla_put_s32(msg, DRM_RAS_A_TELEMETRY_ATTRS_STATUS, status); + if (ret) { + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); + return ret; + } + + ret = nla_put_64bit(msg, DRM_RAS_A_TELEMETRY_ATTRS_VALUE, sizeof(value), + &value, DRM_RAS_A_TELEMETRY_ATTRS_PAD); + if (ret) { + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); + return ret; + } + + genlmsg_end(msg, hdr); + + return genlmsg_reply(msg, info); +} + +/** + * drm_ras_nl_telemetry_write_doit() - Write a telemetry value + * @skb: Netlink message buffer + * @info: Generic Netlink info containing attributes of the request + * + * Extracts the telemetry field and value to be written from the netlink + * attributes and writes that value to the specified field on the device. + * + * Return: 0 on success, or negative errno on failure. + */ +int drm_ras_nl_telemetry_write_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct drm_ras_node *node; + struct sk_buff *msg; + struct nlattr *hdr; + u32 node_id, field; + s32 status; + u64 value; + int ret; + + if (!info->attrs || !info->attrs[DRM_RAS_A_TELEMETRY_ATTRS_FIELD]) + return -EINVAL; + + value = nla_get_u64(info->attrs[DRM_RAS_A_TELEMETRY_ATTRS_VALUE]); + field = nla_get_u32(info->attrs[DRM_RAS_A_TELEMETRY_ATTRS_FIELD]); + node_id = nla_get_u32(info->attrs[DRM_RAS_A_TELEMETRY_ATTRS_NODE_ID]); + + node = xa_load(&drm_ras_xa, node_id); + if (!node || !node->telemetry_read) + return -ENOENT; + + msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_iput(msg, info); + if (!hdr) { + nlmsg_free(msg); + return -EMSGSIZE; + } + + ret = node->telemetry_write(node, &field, &value, &status); + if (ret) { + nlmsg_free(msg); + return ret; + } + + ret = nla_put_s32(msg, DRM_RAS_A_TELEMETRY_ATTRS_STATUS, status); + if (ret) { + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); + return ret; + } + + genlmsg_end(msg, hdr); + + return genlmsg_reply(msg, info); +} + /** * drm_ras_node_register() - Register a new RAS node * @node: Node structure to register @@ -631,14 +801,21 @@ int drm_ras_node_register(struct drm_ras_node *node) if (!node->device_name || !node->node_name) return -EINVAL; - /* Currently, only Error Counter Endpoints are supported */ - if (node->type != DRM_RAS_NODE_TYPE_ERROR_COUNTER) - return -EINVAL; - - /* Mandatory entries for Error Counter Node */ - if (node->type == DRM_RAS_NODE_TYPE_ERROR_COUNTER && - (!node->error_counter_range.last || !node->query_error_counter)) + /* Currently, only Error Counter and Telemetry endpoints are supported */ + switch (node->type) { + case DRM_RAS_NODE_TYPE_ERROR_COUNTER: + /* Mandatory entries for Error Counter Node */ + if (!node->error_counter_range.last || !node->query_error_counter) + return -EINVAL; + break; + case DRM_RAS_NODE_TYPE_TELEMETRY: + /* Mandatory entries for Telemetry Node */ + if (!node->telemetry_read || !node->telemetry_write) + return -EINVAL; + break; + default: return -EINVAL; + } return xa_alloc(&drm_ras_xa, &node->id, node, xa_limit_32b, GFP_KERNEL); } diff --git a/drivers/gpu/drm/drm_ras_nl.c b/drivers/gpu/drm/drm_ras_nl.c index ff0dc406c27c..4577bc1a333e 100644 --- a/drivers/gpu/drm/drm_ras_nl.c +++ b/drivers/gpu/drm/drm_ras_nl.c @@ -41,6 +41,19 @@ static const struct nla_policy drm_ras_set_error_threshold_nl_policy[DRM_RAS_A_E [DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD] = { .type = NLA_U32, }, }; +/* DRM_RAS_CMD_TELEMETRY_READ - do */ +static const struct nla_policy drm_ras_telemetry_read_nl_policy[DRM_RAS_A_TELEMETRY_ATTRS_FIELD + 1] = { + [DRM_RAS_A_TELEMETRY_ATTRS_NODE_ID] = { .type = NLA_U32, }, + [DRM_RAS_A_TELEMETRY_ATTRS_FIELD] = { .type = NLA_U32, }, +}; + +/* DRM_RAS_CMD_TELEMETRY_WRITE - do */ +static const struct nla_policy drm_ras_telemetry_write_nl_policy[DRM_RAS_A_TELEMETRY_ATTRS_VALUE + 1] = { + [DRM_RAS_A_TELEMETRY_ATTRS_NODE_ID] = { .type = NLA_U32, }, + [DRM_RAS_A_TELEMETRY_ATTRS_FIELD] = { .type = NLA_U32, }, + [DRM_RAS_A_TELEMETRY_ATTRS_VALUE] = { .type = NLA_U64, }, +}; + /* Ops table for drm_ras */ static const struct genl_split_ops drm_ras_nl_ops[] = { { @@ -83,6 +96,22 @@ static const struct genl_split_ops drm_ras_nl_ops[] = { .maxattr = DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = DRM_RAS_CMD_TELEMETRY_READ, + .pre_doit = drm_ras_nl_pre_telemetry, + .doit = drm_ras_nl_telemetry_read_doit, + .policy = drm_ras_telemetry_read_nl_policy, + .maxattr = DRM_RAS_A_TELEMETRY_ATTRS_FIELD, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DRM_RAS_CMD_TELEMETRY_WRITE, + .pre_doit = drm_ras_nl_pre_telemetry, + .doit = drm_ras_nl_telemetry_write_doit, + .policy = drm_ras_telemetry_write_nl_policy, + .maxattr = DRM_RAS_A_TELEMETRY_ATTRS_VALUE, + .flags = 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 9aef097ea10f..4bdd7ed268a1 100644 --- a/drivers/gpu/drm/drm_ras_nl.h +++ b/drivers/gpu/drm/drm_ras_nl.h @@ -12,6 +12,9 @@ #include <uapi/drm/drm_ras.h> +int drm_ras_nl_pre_telemetry(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info); + int drm_ras_nl_list_nodes_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int drm_ras_nl_get_error_counter_doit(struct sk_buff *skb, @@ -24,6 +27,9 @@ 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); +int drm_ras_nl_telemetry_read_doit(struct sk_buff *skb, struct genl_info *info); +int drm_ras_nl_telemetry_write_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 1765a3130b09..2a2cdd44839d 100644 --- a/include/drm/drm_ras.h +++ b/include/drm/drm_ras.h @@ -100,6 +100,45 @@ struct drm_ras_node { */ int (*set_error_threshold)(struct drm_ras_node *node, u32 error_id, u32 threshold); + /** + * @telemetry_pre: + * + * This callback is used to enforce any pre_doit conditions necessary + * for telemetry. This is an optional callback for telemetry_node. + * + * Returns 0 on success, negative error code on failure. + */ + int (*telemetry_pre)(struct drm_ras_node *ep); + + /** + * @telemetry_read: + * + * This callback is used for a drm-ras telemetry node to read a + * telemetry value. This is a mandatory callback for telemetry_node. + * + * The callback will read the desired device-specific field into value + * and update status corresponding to a device-specific error code. + * + * Returns 0 on success, negative error code on failure. + */ + int (*telemetry_read)(struct drm_ras_node *ep, u32 *field, u64 *value, + s32 *status); + + /** + * @telemetry_write: + * + * This callback is used for a drm-ras telemetry node to write a + * telemetry value. This is a mandatory callback for telemetry_node. + * + * The callback will write the value to the desired device-specific + * field and update status corresponding to a device-specific error + * code. + * + * Returns 0 on success, negative error code on failure. + */ + int (*telemetry_write)(struct drm_ras_node *ep, u32 *field, u64 *value, + s32 *status); + /** @priv: Driver private data */ void *priv; }; diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h index 2f832275ee6e..d39c78a9ed5a 100644 --- a/include/uapi/drm/drm_ras.h +++ b/include/uapi/drm/drm_ras.h @@ -16,6 +16,7 @@ */ enum drm_ras_node_type { DRM_RAS_NODE_TYPE_ERROR_COUNTER = 1, + DRM_RAS_NODE_TYPE_TELEMETRY, }; enum { @@ -51,6 +52,17 @@ enum { DRM_RAS_A_ERROR_EVENT_ATTRS_MAX = (__DRM_RAS_A_ERROR_EVENT_ATTRS_MAX - 1) }; +enum { + DRM_RAS_A_TELEMETRY_ATTRS_NODE_ID = 1, + DRM_RAS_A_TELEMETRY_ATTRS_FIELD, + DRM_RAS_A_TELEMETRY_ATTRS_VALUE, + DRM_RAS_A_TELEMETRY_ATTRS_STATUS, + DRM_RAS_A_TELEMETRY_ATTRS_PAD, + + __DRM_RAS_A_TELEMETRY_ATTRS_MAX, + DRM_RAS_A_TELEMETRY_ATTRS_MAX = (__DRM_RAS_A_TELEMETRY_ATTRS_MAX - 1) +}; + enum { DRM_RAS_CMD_LIST_NODES = 1, DRM_RAS_CMD_GET_ERROR_COUNTER, @@ -58,6 +70,8 @@ enum { DRM_RAS_CMD_ERROR_EVENT, DRM_RAS_CMD_GET_ERROR_THRESHOLD, DRM_RAS_CMD_SET_ERROR_THRESHOLD, + DRM_RAS_CMD_TELEMETRY_READ, + DRM_RAS_CMD_TELEMETRY_WRITE, __DRM_RAS_CMD_MAX, DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1) -- 2.43.0
