Something went wrong. Try again.
(I'm so sorry!) Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658// SPDX-License-Identifier: MIT/* * Copyright © 2026 Intel Corporation */
#include <linux/module.h>#include <linux/kernel.h>#include <linux/netdevice.h>#include <linux/xarray.h>#include <net/genetlink.h>
#include <drm/drm_ras.h>
#include "drm_ras_nl.h"
/** * DOC: DRM RAS Node Management * * This module provides the infrastructure to manage RAS (Reliability, * Availability, and Serviceability) nodes for DRM drivers. Each * DRM driver may register one or more RAS nodes, which represent * logical components capable of reporting error counters and other * reliability metrics. * * The nodes are stored in a global xarray `drm_ras_xa` to allow * efficient lookup by ID. Nodes can be registered or unregistered * dynamically at runtime. * * A Generic Netlink family `drm_ras` exposes the below operations to * userspace: * * 1. LIST_NODES: Dump all currently registered RAS nodes. * The user receives an array of node IDs, names, and types. * * 2. GET_ERROR_COUNTER: Get error counters of a given node. * Userspace must provide Node ID, Error ID (Optional for specific counter). * Returns all counters of a node if only Node ID is provided or specific * error counters. * * 3. CLEAR_ERROR_COUNTER: Clear error counter of a given node. * Userspace must provide Node ID, Error ID. * Clears specific error counter of a node if supported. * * 4. ERROR_REPORT: Subscribe to this multicast group to receive error events * * 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 * it a unique ID in the xarray. * - drm_ras_node_unregister(): Removes a previously registered * node from the xarray. * * 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 * last valid error ID. * + The driver can provide a error_counter_range.first value informing the * first valid error ID. * + 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: * * - drm_ras_nl_list_nodes_dumpit(): Implements the LIST_NODES * operation, iterating over the xarray. * - drm_ras_nl_get_error_counter_dumpit(): Implements the GET_ERROR_COUNTER dumpit * operation, fetching all counters from a specific node. * - drm_ras_nl_get_error_counter_doit(): Implements the GET_ERROR_COUNTER doit * 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);
/* * The netlink callback context carries dump state across multiple dumpit calls */struct drm_ras_ctx { /* Which xarray id to restart the dump from */ unsigned long restart;};
/** * drm_ras_nl_list_nodes_dumpit() - Dump all registered RAS nodes * @skb: Netlink message buffer * @cb: Callback context for multi-part dumps * * Iterates over all registered RAS nodes in the global xarray and appends * their attributes (ID, name, type) to the given netlink message buffer. * Uses @cb->ctx to track progress in case the message buffer fills up, allowing * multi-part dump support. On buffer overflow, updates the context to resume * from the last node on the next invocation. * * Return: 0 if all nodes fit in @skb, number of bytes added to @skb if * the buffer filled up (requires multi-part continuation), or * a negative error code on failure. */int drm_ras_nl_list_nodes_dumpit(struct sk_buff *skb, struct netlink_callback *cb){ const struct genl_info *info = genl_info_dump(cb); struct drm_ras_ctx *ctx = (void *)cb->ctx; struct drm_ras_node *node; struct nlattr *hdr; unsigned long id; int ret;
xa_for_each_start(&drm_ras_xa, id, node, ctx->restart) { hdr = genlmsg_iput(skb, info); if (!hdr) { ret = -EMSGSIZE; break; }
ret = nla_put_u32(skb, DRM_RAS_A_NODE_ATTRS_NODE_ID, node->id); if (ret) { genlmsg_cancel(skb, hdr); break; }
ret = nla_put_string(skb, DRM_RAS_A_NODE_ATTRS_DEVICE_NAME, node->device_name); if (ret) { genlmsg_cancel(skb, hdr); break; }
ret = nla_put_string(skb, DRM_RAS_A_NODE_ATTRS_NODE_NAME, node->node_name); if (ret) { genlmsg_cancel(skb, hdr); break; }
ret = nla_put_u32(skb, DRM_RAS_A_NODE_ATTRS_NODE_TYPE, node->type); if (ret) { genlmsg_cancel(skb, hdr); break; }
genlmsg_end(skb, hdr); }
if (ret == -EMSGSIZE) ctx->restart = id;
return ret;}
static int get_node_error_counter(u32 node_id, u32 error_id, const char **name, u32 *value){ struct drm_ras_node *node;
node = xa_load(&drm_ras_xa, node_id); if (!node || !node->query_error_counter) return -ENOENT;
if (error_id < node->error_counter_range.first || error_id > node->error_counter_range.last) return -EINVAL;
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){ 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_VALUE, value);}
static int msg_put_error_event_attrs(struct sk_buff *msg, struct drm_ras_node *node, u32 error_id, const char *error_name, u32 value){ int ret;
ret = nla_put_string(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_DEVICE_NAME, node->device_name); if (ret) return ret;
ret = nla_put_u32(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_NODE_ID, node->id); if (ret) return ret;
ret = nla_put_string(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_NODE_NAME, node->node_name); if (ret) return ret;
ret = nla_put_u32(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_ID, error_id); if (ret) return ret;
ret = nla_put_string(msg, DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_NAME, error_name); if (ret) return ret;
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){ struct sk_buff *msg; struct nlattr *hdr; const char *error_name; u32 value; 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_counter(node_id, error_id, &error_name, &value); if (ret) goto cancel_msg;
ret = msg_reply_value(msg, error_id, error_name, value); 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;}
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 * @error_id: ID of the error * @error_name: Name of the error * @value: Value of the error counter * * Report an error-event to userspace using the error-report multicast group. * * Context: Process context only. Uses %GFP_KERNEL and multicasts to all * netns, which is unbounded work; callers in interrupt handlers * or other atomic context must defer event. * * Return: 0 on success, or negative errno on failure. */int drm_ras_nl_error_event(struct drm_ras_node *node, u32 error_id, const char *error_name, u32 value){ struct genl_info info; struct sk_buff *msg; struct nlattr *hdr; int ret;
if (!node || !error_name) return -EINVAL;
/* Check the node is currently registered */ if (xa_load(&drm_ras_xa, node->id) != node) return -ENOENT;
/* Currently only Error Counter events are supported */ if (node->type != DRM_RAS_NODE_TYPE_ERROR_COUNTER) return -EOPNOTSUPP;
/* Check the error ID is within the valid range */ if (error_id < node->error_counter_range.first || error_id > node->error_counter_range.last) return -EINVAL;
genl_info_init_ntf(&info, &drm_ras_nl_family, DRM_RAS_CMD_ERROR_EVENT);
msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!msg) return -ENOMEM;
hdr = genlmsg_iput(msg, &info); if (!hdr) { ret = -EMSGSIZE; goto free_msg; }
ret = msg_put_error_event_attrs(msg, node, error_id, error_name, value); if (ret) goto cancel_msg;
genlmsg_end(msg, hdr); genlmsg_multicast_allns(&drm_ras_nl_family, msg, 0, DRM_RAS_NLGRP_ERROR_REPORT);
return 0;
cancel_msg: genlmsg_cancel(msg, hdr);free_msg: nlmsg_free(msg); return ret;}EXPORT_SYMBOL(drm_ras_nl_error_event);
/** * drm_ras_nl_get_error_counter_dumpit() - Dump all Error Counters * @skb: Netlink message buffer * @cb: Callback context for multi-part dumps * * Iterates over all error counters in a given Node and appends * their attributes (ID, name, value) to the given netlink message buffer. * Uses @cb->ctx to track progress in case the message buffer fills up, allowing * multi-part dump support. On buffer overflow, updates the context to resume * from the last node on the next invocation. * * Return: 0 if all errors fit in @skb, number of bytes added to @skb if * the buffer filled up (requires multi-part continuation), or * a negative error code on failure. */int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb, struct netlink_callback *cb){ const struct genl_info *info = genl_info_dump(cb); struct drm_ras_ctx *ctx = (void *)cb->ctx; struct drm_ras_node *node; struct nlattr *hdr; const char *error_name; u32 node_id, error_id, value; int ret;
if (!info->attrs || GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID)) return -EINVAL;
node_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID]);
node = xa_load(&drm_ras_xa, node_id); if (!node) return -ENOENT;
for (error_id = max(node->error_counter_range.first, ctx->restart); error_id <= node->error_counter_range.last; error_id++) { ret = get_node_error_counter(node_id, error_id, &error_name, &value); /* * For non-contiguous range, driver return -ENOENT as indication * to skip this ID when listing all errors. */ if (ret == -ENOENT) continue; if (ret) return ret;
hdr = genlmsg_iput(skb, info);
if (!hdr) { ret = -EMSGSIZE; break; }
ret = msg_reply_value(skb, error_id, error_name, value); if (ret) { genlmsg_cancel(skb, hdr); break; }
genlmsg_end(skb, hdr); }
if (ret == -EMSGSIZE) ctx->restart = error_id;
return ret;}
/** * drm_ras_nl_get_error_counter_doit() - Query an error counter of an node * @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 current value of the corresponding error 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_counter_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_value(info, node_id, error_id);}
/** * drm_ras_nl_clear_error_counter_doit() - Clear an error counter of a node * @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 * clears the current value. * * Return: 0 on success, or negative errno on failure. */int drm_ras_nl_clear_error_counter_doit(struct sk_buff *skb, struct genl_info *info){ struct drm_ras_node *node; 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]);
node = xa_load(&drm_ras_xa, node_id); if (!node || !node->clear_error_counter) return -ENOENT;
if (error_id < node->error_counter_range.first || error_id > node->error_counter_range.last) return -EINVAL;
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 * * Adds the given RAS node to the global node xarray and assigns it * a unique ID. Both @node->name and @node->type must be valid. * * Return: 0 on success, or negative errno on failure: */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)) return -EINVAL;
return xa_alloc(&drm_ras_xa, &node->id, node, xa_limit_32b, GFP_KERNEL);}EXPORT_SYMBOL(drm_ras_node_register);
/** * drm_ras_node_unregister() - Unregister a previously registered node * @node: Node structure to unregister * * Removes the given node from the global node xarray using its ID. */void drm_ras_node_unregister(struct drm_ras_node *node){ xa_erase(&drm_ras_xa, node->id);}EXPORT_SYMBOL(drm_ras_node_unregister);