diff options
Diffstat (limited to 'net/core/devlink.c')
-rw-r--r-- | net/core/devlink.c | 311 |
1 files changed, 243 insertions, 68 deletions
diff --git a/net/core/devlink.c b/net/core/devlink.c index 93905dc7c179..4c63c9a4c09e 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -95,16 +95,25 @@ static LIST_HEAD(devlink_list); */ static DEFINE_MUTEX(devlink_mutex); -static struct net *devlink_net(const struct devlink *devlink) +struct net *devlink_net(const struct devlink *devlink) { return read_pnet(&devlink->_net); } +EXPORT_SYMBOL_GPL(devlink_net); -static void devlink_net_set(struct devlink *devlink, struct net *net) +static void __devlink_net_set(struct devlink *devlink, struct net *net) { write_pnet(&devlink->_net, net); } +void devlink_net_set(struct devlink *devlink, struct net *net) +{ + if (WARN_ON(devlink->registered)) + return; + __devlink_net_set(devlink, net); +} +EXPORT_SYMBOL_GPL(devlink_net_set); + static struct devlink *devlink_get_from_attrs(struct net *net, struct nlattr **attrs) { @@ -434,8 +443,16 @@ static void devlink_nl_post_doit(const struct genl_ops *ops, { struct devlink *devlink; - devlink = devlink_get_from_info(info); - if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK) + /* When devlink changes netns, it would not be found + * by devlink_get_from_info(). So try if it is stored first. + */ + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) { + devlink = info->user_ptr[0]; + } else { + devlink = devlink_get_from_info(info); + WARN_ON(IS_ERR(devlink)); + } + if (!IS_ERR(devlink) && ~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK) mutex_unlock(&devlink->lock); mutex_unlock(&devlink_mutex); } @@ -1035,7 +1052,7 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, struct devlink_sb *devlink_sb; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -1058,6 +1075,9 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, out: mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -1233,7 +1253,7 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, struct devlink_sb *devlink_sb; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -1256,6 +1276,9 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, out: mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -1460,7 +1483,7 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, struct devlink_sb *devlink_sb; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -1485,6 +1508,9 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, out: mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -2674,6 +2700,72 @@ devlink_resources_validate(struct devlink *devlink, return err; } +static struct net *devlink_netns_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; + struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; + struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; + struct net *net; + + if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { + NL_SET_ERR_MSG(info->extack, "multiple netns identifying attributes specified"); + return ERR_PTR(-EINVAL); + } + + if (netns_pid_attr) { + net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); + } else if (netns_fd_attr) { + net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); + } else if (netns_id_attr) { + net = get_net_ns_by_id(sock_net(skb->sk), + nla_get_u32(netns_id_attr)); + if (!net) + net = ERR_PTR(-EINVAL); + } else { + WARN_ON(1); + net = ERR_PTR(-EINVAL); + } + if (IS_ERR(net)) { + NL_SET_ERR_MSG(info->extack, "Unknown network namespace"); + return ERR_PTR(-EINVAL); + } + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return ERR_PTR(-EPERM); + } + return net; +} + +static void devlink_param_notify(struct devlink *devlink, + unsigned int port_index, + struct devlink_param_item *param_item, + enum devlink_command cmd); + +static void devlink_reload_netns_change(struct devlink *devlink, + struct net *dest_net) +{ + struct devlink_param_item *param_item; + + /* Userspace needs to be notified about devlink objects + * removed from original and entering new network namespace. + * The rest of the devlink objects are re-created during + * reload process so the notifications are generated separatelly. + */ + + list_for_each_entry(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_DEL); + devlink_notify(devlink, DEVLINK_CMD_DEL); + + __devlink_net_set(devlink, dest_net); + + devlink_notify(devlink, DEVLINK_CMD_NEW); + list_for_each_entry(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_NEW); +} + static bool devlink_reload_supported(struct devlink *devlink) { return devlink->ops->reload_down && devlink->ops->reload_up; @@ -2694,9 +2786,30 @@ bool devlink_is_reload_failed(const struct devlink *devlink) } EXPORT_SYMBOL_GPL(devlink_is_reload_failed); +static int devlink_reload(struct devlink *devlink, struct net *dest_net, + struct netlink_ext_ack *extack) +{ + int err; + + if (!devlink->reload_enabled) + return -EOPNOTSUPP; + + err = devlink->ops->reload_down(devlink, !!dest_net, extack); + if (err) + return err; + + if (dest_net && !net_eq(dest_net, devlink_net(devlink))) + devlink_reload_netns_change(devlink, dest_net); + + err = devlink->ops->reload_up(devlink, extack); + devlink_reload_failed_set(devlink, !!err); + return err; +} + static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; + struct net *dest_net = NULL; int err; if (!devlink_reload_supported(devlink) || !devlink->reload_enabled) @@ -2707,11 +2820,20 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); return err; } - err = devlink->ops->reload_down(devlink, info->extack); - if (err) - return err; - err = devlink->ops->reload_up(devlink, info->extack); - devlink_reload_failed_set(devlink, !!err); + + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + + err = devlink_reload(devlink, dest_net, info->extack); + + if (dest_net) + put_net(dest_net); + return err; } @@ -2884,6 +3006,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_NAME, .type = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + .name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) @@ -3155,7 +3282,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, struct devlink *devlink; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -3183,6 +3310,9 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, out: mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -3411,7 +3541,7 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, struct devlink *devlink; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -3444,6 +3574,9 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, out: mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -3818,29 +3951,19 @@ static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb, static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { + const struct genl_dumpit_info *info = genl_dumpit_info(cb); u64 ret_offset, start_offset, end_offset = 0; + struct nlattr **attrs = info->attrs; struct devlink_region *region; struct nlattr *chunks_attr; const char *region_name; struct devlink *devlink; - struct nlattr **attrs; bool dump = true; void *hdr; int err; start_offset = *((u64 *)&cb->args[0]); - attrs = kmalloc_array(DEVLINK_ATTR_MAX + 1, sizeof(*attrs), GFP_KERNEL); - if (!attrs) - return -ENOMEM; - - err = nlmsg_parse_deprecated(cb->nlh, - GENL_HDRLEN + devlink_nl_family.hdrsize, - attrs, DEVLINK_ATTR_MAX, - devlink_nl_family.policy, cb->extack); - if (err) - goto out_free; - mutex_lock(&devlink_mutex); devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); if (IS_ERR(devlink)) { @@ -3917,7 +4040,6 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, genlmsg_end(skb, hdr); mutex_unlock(&devlink->lock); mutex_unlock(&devlink_mutex); - kfree(attrs); return skb->len; @@ -3927,8 +4049,6 @@ out_unlock: mutex_unlock(&devlink->lock); out_dev: mutex_unlock(&devlink_mutex); -out_free: - kfree(attrs); return err; } @@ -4066,7 +4186,7 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, struct devlink *devlink; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -4094,6 +4214,9 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, } mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -4296,12 +4419,11 @@ int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) } EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); -int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len) +static int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) { return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); } -EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, bool value) @@ -4409,19 +4531,26 @@ int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put); int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, - const void *value, u16 value_len) + const void *value, u32 value_len) { + u32 data_size; + u32 offset; int err; - err = devlink_fmsg_pair_nest_start(fmsg, name); + err = devlink_fmsg_arr_pair_nest_start(fmsg, name); if (err) return err; - err = devlink_fmsg_binary_put(fmsg, value, value_len); - if (err) - return err; + for (offset = 0; offset < value_len; offset += data_size) { + data_size = value_len - offset; + if (data_size > DEVLINK_FMSG_MAX_SIZE) + data_size = DEVLINK_FMSG_MAX_SIZE; + err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); + if (err) + return err; + } - err = devlink_fmsg_pair_nest_end(fmsg); + err = devlink_fmsg_arr_pair_nest_end(fmsg); if (err) return err; @@ -4733,14 +4862,17 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); static int devlink_health_reporter_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, struct netlink_ext_ack *extack) { int err; + if (reporter->health_state == DEVLINK_HEALTH_REPORTER_STATE_HEALTHY) + return 0; + if (!reporter->ops->recover) return -EOPNOTSUPP; - err = reporter->ops->recover(reporter, priv_ctx); + err = reporter->ops->recover(reporter, priv_ctx, extack); if (err) return err; @@ -4761,7 +4893,8 @@ devlink_health_dump_clear(struct devlink_health_reporter *reporter) } static int devlink_health_do_dump(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, + struct netlink_ext_ack *extack) { int err; @@ -4782,7 +4915,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter, goto dump_err; err = reporter->ops->dump(reporter, reporter->dump_fmsg, - priv_ctx); + priv_ctx, extack); if (err) goto dump_err; @@ -4830,11 +4963,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter, mutex_lock(&reporter->dump_lock); /* store current dump of current error, for later analysis */ - devlink_health_do_dump(reporter, priv_ctx); + devlink_health_do_dump(reporter, priv_ctx, NULL); mutex_unlock(&reporter->dump_lock); if (reporter->auto_recover) - return devlink_health_reporter_recover(reporter, priv_ctx); + return devlink_health_reporter_recover(reporter, + priv_ctx, NULL); return 0; } @@ -4869,21 +5003,10 @@ devlink_health_reporter_get_from_info(struct devlink *devlink, static struct devlink_health_reporter * devlink_health_reporter_get_from_cb(struct netlink_callback *cb) { + const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct devlink_health_reporter *reporter; + struct nlattr **attrs = info->attrs; struct devlink *devlink; - struct nlattr **attrs; - int err; - - attrs = kmalloc_array(DEVLINK_ATTR_MAX + 1, sizeof(*attrs), GFP_KERNEL); - if (!attrs) - return NULL; - - err = nlmsg_parse_deprecated(cb->nlh, - GENL_HDRLEN + devlink_nl_family.hdrsize, - attrs, DEVLINK_ATTR_MAX, - devlink_nl_family.policy, cb->extack); - if (err) - goto free; mutex_lock(&devlink_mutex); devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); @@ -4892,12 +5015,9 @@ devlink_health_reporter_get_from_cb(struct netlink_callback *cb) reporter = devlink_health_reporter_get_from_attrs(devlink, attrs); mutex_unlock(&devlink_mutex); - kfree(attrs); return reporter; unlock: mutex_unlock(&devlink_mutex); -free: - kfree(attrs); return NULL; } @@ -5090,7 +5210,7 @@ static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, if (!reporter) return -EINVAL; - err = devlink_health_reporter_recover(reporter, NULL); + err = devlink_health_reporter_recover(reporter, NULL, info->extack); devlink_health_reporter_put(reporter); return err; @@ -5123,7 +5243,7 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, if (err) goto out; - err = reporter->ops->diagnose(reporter, fmsg); + err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) goto out; @@ -5158,7 +5278,7 @@ devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, } mutex_lock(&reporter->dump_lock); if (!start) { - err = devlink_health_do_dump(reporter, NULL); + err = devlink_health_do_dump(reporter, NULL, cb->extack); if (err) goto unlock; cb->args[1] = reporter->dump_ts; @@ -5799,6 +5919,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -6029,7 +6152,8 @@ static const struct genl_ops devlink_nl_ops[] = { }, { .cmd = DEVLINK_CMD_REGION_READ, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .validate = GENL_DONT_VALIDATE_STRICT | + GENL_DONT_VALIDATE_DUMP_STRICT, .dumpit = devlink_nl_cmd_region_read_dumpit, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, @@ -6077,7 +6201,8 @@ static const struct genl_ops devlink_nl_ops[] = { }, { .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .validate = GENL_DONT_VALIDATE_STRICT | + GENL_DONT_VALIDATE_DUMP_STRICT, .dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | @@ -6161,7 +6286,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) if (!devlink) return NULL; devlink->ops = ops; - devlink_net_set(devlink, &init_net); + __devlink_net_set(devlink, &init_net); INIT_LIST_HEAD(&devlink->port_list); INIT_LIST_HEAD(&devlink->sb_list); INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); @@ -6187,6 +6312,7 @@ int devlink_register(struct devlink *devlink, struct device *dev) { mutex_lock(&devlink_mutex); devlink->dev = dev; + devlink->registered = true; list_add_tail(&devlink->list, &devlink_list); devlink_notify(devlink, DEVLINK_CMD_NEW); mutex_unlock(&devlink_mutex); @@ -7533,6 +7659,21 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP), DEVLINK_TRAP(TTL_ERROR, EXCEPTION), DEVLINK_TRAP(TAIL_DROP, DROP), + DEVLINK_TRAP(NON_IP_PACKET, DROP), + DEVLINK_TRAP(UC_DIP_MC_DMAC, DROP), + DEVLINK_TRAP(DIP_LB, DROP), + DEVLINK_TRAP(SIP_MC, DROP), + DEVLINK_TRAP(SIP_LB, DROP), + DEVLINK_TRAP(CORRUPTED_IP_HDR, DROP), + DEVLINK_TRAP(IPV4_SIP_BC, DROP), + DEVLINK_TRAP(IPV6_MC_DIP_RESERVED_SCOPE, DROP), + DEVLINK_TRAP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, DROP), + DEVLINK_TRAP(MTU_ERROR, EXCEPTION), + DEVLINK_TRAP(UNRESOLVED_NEIGH, EXCEPTION), + DEVLINK_TRAP(RPF, EXCEPTION), + DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION), + DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION), + DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -8103,9 +8244,43 @@ int devlink_compat_switch_id_get(struct net_device *dev, return 0; } +static void __net_exit devlink_pernet_pre_exit(struct net *net) +{ + struct devlink *devlink; + int err; + + /* In case network namespace is getting destroyed, reload + * all devlink instances from this namespace into init_net. + */ + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (net_eq(devlink_net(devlink), net)) { + if (WARN_ON(!devlink_reload_supported(devlink))) + continue; + err = devlink_reload(devlink, &init_net, NULL); + if (err && err != -EOPNOTSUPP) + pr_warn("Failed to reload devlink instance into init_net\n"); + } + } + mutex_unlock(&devlink_mutex); +} + +static struct pernet_operations devlink_pernet_ops __net_initdata = { + .pre_exit = devlink_pernet_pre_exit, +}; + static int __init devlink_init(void) { - return genl_register_family(&devlink_nl_family); + int err; + + err = genl_register_family(&devlink_nl_family); + if (err) + goto out; + err = register_pernet_subsys(&devlink_pernet_ops); + +out: + WARN_ON(err); + return err; } subsys_initcall(devlink_init); |