diff options
Diffstat (limited to 'include/linux')
55 files changed, 1389 insertions, 655 deletions
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index c15221dcb75e..d0807ad43f93 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -268,10 +268,11 @@ struct virtchnl_vf_resource { u32 rss_key_size; u32 rss_lut_size; - struct virtchnl_vsi_resource vsi_res[1]; + struct virtchnl_vsi_resource vsi_res[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(36, virtchnl_vf_resource); +VIRTCHNL_CHECK_STRUCT_LEN(20, virtchnl_vf_resource); +#define virtchnl_vf_resource_LEGACY_SIZEOF 36 /* VIRTCHNL_OP_CONFIG_TX_QUEUE * VF sends this message to set up parameters for one TX queue. @@ -340,10 +341,11 @@ struct virtchnl_vsi_queue_config_info { u16 vsi_id; u16 num_queue_pairs; u32 pad; - struct virtchnl_queue_pair_info qpair[1]; + struct virtchnl_queue_pair_info qpair[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vsi_queue_config_info); +#define virtchnl_vsi_queue_config_info_LEGACY_SIZEOF 72 /* VIRTCHNL_OP_REQUEST_QUEUES * VF sends this message to request the PF to allocate additional queues to @@ -385,10 +387,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_vector_map); struct virtchnl_irq_map_info { u16 num_vectors; - struct virtchnl_vector_map vecmap[1]; + struct virtchnl_vector_map vecmap[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(14, virtchnl_irq_map_info); +VIRTCHNL_CHECK_STRUCT_LEN(2, virtchnl_irq_map_info); +#define virtchnl_irq_map_info_LEGACY_SIZEOF 14 /* VIRTCHNL_OP_ENABLE_QUEUES * VIRTCHNL_OP_DISABLE_QUEUES @@ -459,10 +462,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr); struct virtchnl_ether_addr_list { u16 vsi_id; u16 num_elements; - struct virtchnl_ether_addr list[1]; + struct virtchnl_ether_addr list[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_ether_addr_list); +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_ether_addr_list); +#define virtchnl_ether_addr_list_LEGACY_SIZEOF 12 /* VIRTCHNL_OP_ADD_VLAN * VF sends this message to add one or more VLAN tag filters for receives. @@ -481,10 +485,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_ether_addr_list); struct virtchnl_vlan_filter_list { u16 vsi_id; u16 num_elements; - u16 vlan_id[1]; + u16 vlan_id[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_vlan_filter_list); +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_vlan_filter_list); +#define virtchnl_vlan_filter_list_LEGACY_SIZEOF 6 /* This enum is used for all of the VIRTCHNL_VF_OFFLOAD_VLAN_V2_CAPS related * structures and opcodes. @@ -711,10 +716,11 @@ struct virtchnl_vlan_filter_list_v2 { u16 vport_id; u16 num_elements; u8 pad[4]; - struct virtchnl_vlan_filter filters[1]; + struct virtchnl_vlan_filter filters[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_vlan_filter_list_v2); +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vlan_filter_list_v2); +#define virtchnl_vlan_filter_list_v2_LEGACY_SIZEOF 40 /* VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 * VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 @@ -866,18 +872,20 @@ VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_promisc_info); struct virtchnl_rss_key { u16 vsi_id; u16 key_len; - u8 key[1]; /* RSS hash key, packed bytes */ + u8 key[]; /* RSS hash key, packed bytes */ }; -VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key); +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rss_key); +#define virtchnl_rss_key_LEGACY_SIZEOF 6 struct virtchnl_rss_lut { u16 vsi_id; u16 lut_entries; - u8 lut[1]; /* RSS lookup table */ + u8 lut[]; /* RSS lookup table */ }; -VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut); +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rss_lut); +#define virtchnl_rss_lut_LEGACY_SIZEOF 6 /* VIRTCHNL_OP_GET_RSS_HENA_CAPS * VIRTCHNL_OP_SET_RSS_HENA @@ -911,10 +919,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_channel_info); struct virtchnl_tc_info { u32 num_tc; u32 pad; - struct virtchnl_channel_info list[1]; + struct virtchnl_channel_info list[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_tc_info); +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_tc_info); +#define virtchnl_tc_info_LEGACY_SIZEOF 24 /* VIRTCHNL_ADD_CLOUD_FILTER * VIRTCHNL_DEL_CLOUD_FILTER @@ -1052,10 +1061,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_rdma_qv_info); struct virtchnl_rdma_qvlist_info { u32 num_vectors; - struct virtchnl_rdma_qv_info qv_info[1]; + struct virtchnl_rdma_qv_info qv_info[]; }; -VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_rdma_qvlist_info); +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rdma_qvlist_info); +#define virtchnl_rdma_qvlist_info_LEGACY_SIZEOF 16 /* VF reset states - these are written into the RSTAT register: * VFGEN_RSTAT on the VF @@ -1367,6 +1377,31 @@ struct virtchnl_fdir_del { VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del); +#define __vss_byone(p, member, count, old) \ + (struct_size(p, member, count) + (old - 1 - struct_size(p, member, 0))) + +#define __vss_byelem(p, member, count, old) \ + (struct_size(p, member, count - 1) + (old - struct_size(p, member, 0))) + +#define __vss_full(p, member, count, old) \ + (struct_size(p, member, count) + (old - struct_size(p, member, 0))) + +#define __vss(type, func, p, member, count) \ + struct type: func(p, member, count, type##_LEGACY_SIZEOF) + +#define virtchnl_struct_size(p, m, c) \ + _Generic(*p, \ + __vss(virtchnl_vf_resource, __vss_full, p, m, c), \ + __vss(virtchnl_vsi_queue_config_info, __vss_full, p, m, c), \ + __vss(virtchnl_irq_map_info, __vss_full, p, m, c), \ + __vss(virtchnl_ether_addr_list, __vss_full, p, m, c), \ + __vss(virtchnl_vlan_filter_list, __vss_full, p, m, c), \ + __vss(virtchnl_vlan_filter_list_v2, __vss_byelem, p, m, c), \ + __vss(virtchnl_tc_info, __vss_byelem, p, m, c), \ + __vss(virtchnl_rdma_qvlist_info, __vss_byelem, p, m, c), \ + __vss(virtchnl_rss_key, __vss_byone, p, m, c), \ + __vss(virtchnl_rss_lut, __vss_byone, p, m, c)) + /** * virtchnl_vc_validate_vf_msg * @ver: Virtchnl version info @@ -1401,24 +1436,23 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, valid_len = sizeof(struct virtchnl_rxq_info); break; case VIRTCHNL_OP_CONFIG_VSI_QUEUES: - valid_len = sizeof(struct virtchnl_vsi_queue_config_info); + valid_len = virtchnl_vsi_queue_config_info_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_vsi_queue_config_info *vqc = (struct virtchnl_vsi_queue_config_info *)msg; - valid_len += (vqc->num_queue_pairs * - sizeof(struct - virtchnl_queue_pair_info)); + valid_len = virtchnl_struct_size(vqc, qpair, + vqc->num_queue_pairs); if (vqc->num_queue_pairs == 0) err_msg_format = true; } break; case VIRTCHNL_OP_CONFIG_IRQ_MAP: - valid_len = sizeof(struct virtchnl_irq_map_info); + valid_len = virtchnl_irq_map_info_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_irq_map_info *vimi = (struct virtchnl_irq_map_info *)msg; - valid_len += (vimi->num_vectors * - sizeof(struct virtchnl_vector_map)); + valid_len = virtchnl_struct_size(vimi, vecmap, + vimi->num_vectors); if (vimi->num_vectors == 0) err_msg_format = true; } @@ -1429,23 +1463,24 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, break; case VIRTCHNL_OP_ADD_ETH_ADDR: case VIRTCHNL_OP_DEL_ETH_ADDR: - valid_len = sizeof(struct virtchnl_ether_addr_list); + valid_len = virtchnl_ether_addr_list_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_ether_addr_list *veal = (struct virtchnl_ether_addr_list *)msg; - valid_len += veal->num_elements * - sizeof(struct virtchnl_ether_addr); + valid_len = virtchnl_struct_size(veal, list, + veal->num_elements); if (veal->num_elements == 0) err_msg_format = true; } break; case VIRTCHNL_OP_ADD_VLAN: case VIRTCHNL_OP_DEL_VLAN: - valid_len = sizeof(struct virtchnl_vlan_filter_list); + valid_len = virtchnl_vlan_filter_list_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_vlan_filter_list *vfl = (struct virtchnl_vlan_filter_list *)msg; - valid_len += vfl->num_elements * sizeof(u16); + valid_len = virtchnl_struct_size(vfl, vlan_id, + vfl->num_elements); if (vfl->num_elements == 0) err_msg_format = true; } @@ -1469,29 +1504,31 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_RELEASE_RDMA_IRQ_MAP: break; case VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP: - valid_len = sizeof(struct virtchnl_rdma_qvlist_info); + valid_len = virtchnl_rdma_qvlist_info_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_rdma_qvlist_info *qv = (struct virtchnl_rdma_qvlist_info *)msg; - valid_len += ((qv->num_vectors - 1) * - sizeof(struct virtchnl_rdma_qv_info)); + valid_len = virtchnl_struct_size(qv, qv_info, + qv->num_vectors); } break; case VIRTCHNL_OP_CONFIG_RSS_KEY: - valid_len = sizeof(struct virtchnl_rss_key); + valid_len = virtchnl_rss_key_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_rss_key *vrk = (struct virtchnl_rss_key *)msg; - valid_len += vrk->key_len - 1; + valid_len = virtchnl_struct_size(vrk, key, + vrk->key_len); } break; case VIRTCHNL_OP_CONFIG_RSS_LUT: - valid_len = sizeof(struct virtchnl_rss_lut); + valid_len = virtchnl_rss_lut_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; - valid_len += vrl->lut_entries - 1; + valid_len = virtchnl_struct_size(vrl, lut, + vrl->lut_entries); } break; case VIRTCHNL_OP_GET_RSS_HENA_CAPS: @@ -1506,12 +1543,12 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, valid_len = sizeof(struct virtchnl_vf_res_request); break; case VIRTCHNL_OP_ENABLE_CHANNELS: - valid_len = sizeof(struct virtchnl_tc_info); + valid_len = virtchnl_tc_info_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_tc_info *vti = (struct virtchnl_tc_info *)msg; - valid_len += (vti->num_tc - 1) * - sizeof(struct virtchnl_channel_info); + valid_len = virtchnl_struct_size(vti, list, + vti->num_tc); if (vti->num_tc == 0) err_msg_format = true; } @@ -1538,13 +1575,13 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, break; case VIRTCHNL_OP_ADD_VLAN_V2: case VIRTCHNL_OP_DEL_VLAN_V2: - valid_len = sizeof(struct virtchnl_vlan_filter_list_v2); + valid_len = virtchnl_vlan_filter_list_v2_LEGACY_SIZEOF; if (msglen >= valid_len) { struct virtchnl_vlan_filter_list_v2 *vfl = (struct virtchnl_vlan_filter_list_v2 *)msg; - valid_len += (vfl->num_elements - 1) * - sizeof(struct virtchnl_vlan_filter); + valid_len = virtchnl_struct_size(vfl, filters, + vfl->num_elements); if (vfl->num_elements == 0) { err_msg_format = true; diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 57e9e109257e..8506690dbb9c 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -199,9 +199,9 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ + if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ - if (sk_fullsock(__sk) && \ + if (sk_fullsock(__sk) && __sk == skb_to_full_sk(skb) && \ cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ CGROUP_INET_EGRESS); \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f58895830ada..12596af59c00 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -228,6 +228,18 @@ struct btf_record { struct btf_field fields[]; }; +/* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */ +struct bpf_rb_node_kern { + struct rb_node rb_node; + void *owner; +} __attribute__((aligned(8))); + +/* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */ +struct bpf_list_node_kern { + struct list_head list_head; + void *owner; +} __attribute__((aligned(8))); + struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -275,6 +287,7 @@ struct bpf_map { } owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ + s64 __percpu *elem_count; }; static inline const char *btf_field_type_name(enum btf_field_type type) @@ -640,7 +653,8 @@ enum bpf_type_flag { MEM_RCU = BIT(13 + BPF_BASE_TYPE_BITS), /* Used to tag PTR_TO_BTF_ID | MEM_ALLOC references which are non-owning. - * Currently only valid for linked-list and rbtree nodes. + * Currently only valid for linked-list and rbtree nodes. If the nodes + * have a bpf_refcount_field, they must be tagged MEM_RCU as well. */ NON_OWN_REF = BIT(14 + BPF_BASE_TYPE_BITS), @@ -1537,6 +1551,53 @@ struct bpf_struct_ops_value; struct btf_member; #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 +/** + * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to + * define a BPF_MAP_TYPE_STRUCT_OPS map type composed + * of BPF_PROG_TYPE_STRUCT_OPS progs. + * @verifier_ops: A structure of callbacks that are invoked by the verifier + * when determining whether the struct_ops progs in the + * struct_ops map are valid. + * @init: A callback that is invoked a single time, and before any other + * callback, to initialize the structure. A nonzero return value means + * the subsystem could not be initialized. + * @check_member: When defined, a callback invoked by the verifier to allow + * the subsystem to determine if an entry in the struct_ops map + * is valid. A nonzero return value means that the map is + * invalid and should be rejected by the verifier. + * @init_member: A callback that is invoked for each member of the struct_ops + * map to allow the subsystem to initialize the member. A nonzero + * value means the member could not be initialized. This callback + * is exclusive with the @type, @type_id, @value_type, and + * @value_id fields. + * @reg: A callback that is invoked when the struct_ops map has been + * initialized and is being attached to. Zero means the struct_ops map + * has been successfully registered and is live. A nonzero return value + * means the struct_ops map could not be registered. + * @unreg: A callback that is invoked when the struct_ops map should be + * unregistered. + * @update: A callback that is invoked when the live struct_ops map is being + * updated to contain new values. This callback is only invoked when + * the struct_ops map is loaded with BPF_F_LINK. If not defined, the + * it is assumed that the struct_ops map cannot be updated. + * @validate: A callback that is invoked after all of the members have been + * initialized. This callback should perform static checks on the + * map, meaning that it should either fail or succeed + * deterministically. A struct_ops map that has been validated may + * not necessarily succeed in being registered if the call to @reg + * fails. For example, a valid struct_ops map may be loaded, but + * then fail to be registered due to there being another active + * struct_ops map on the system in the subsystem already. For this + * reason, if this callback is not defined, the check is skipped as + * the struct_ops map will have final verification performed in + * @reg. + * @type: BTF type. + * @value_type: Value type. + * @name: The name of the struct bpf_struct_ops object. + * @func_models: Func models + * @type_id: BTF type id. + * @value_id: BTF value id. + */ struct bpf_struct_ops { const struct bpf_verifier_ops *verifier_ops; int (*init)(struct btf *btf); @@ -1806,6 +1867,7 @@ struct bpf_cg_run_ctx { struct bpf_trace_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; + bool is_uprobe; }; struct bpf_tramp_run_ctx { @@ -1854,6 +1916,8 @@ bpf_prog_run_array(const struct bpf_prog_array *array, if (unlikely(!array)) return ret; + run_ctx.is_uprobe = false; + migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; @@ -1878,8 +1942,8 @@ bpf_prog_run_array(const struct bpf_prog_array *array, * rcu-protected dynamically sized maps. */ static __always_inline u32 -bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog) +bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; @@ -1893,6 +1957,8 @@ bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu, rcu_read_lock_trace(); migrate_disable(); + run_ctx.is_uprobe = true; + array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); if (unlikely(!array)) goto out; @@ -2040,6 +2106,35 @@ bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, } #endif +static inline int +bpf_map_init_elem_count(struct bpf_map *map) +{ + size_t size = sizeof(*map->elem_count), align = size; + gfp_t flags = GFP_USER | __GFP_NOWARN; + + map->elem_count = bpf_map_alloc_percpu(map, size, align, flags); + if (!map->elem_count) + return -ENOMEM; + + return 0; +} + +static inline void +bpf_map_free_elem_count(struct bpf_map *map) +{ + free_percpu(map->elem_count); +} + +static inline void bpf_map_inc_elem_count(struct bpf_map *map) +{ + this_cpu_inc(*map->elem_count); +} + +static inline void bpf_map_dec_elem_count(struct bpf_map *map) +{ + this_cpu_dec(*map->elem_count); +} + extern int sysctl_unprivileged_bpf_disabled; static inline bool bpf_allow_ptr_leaks(void) @@ -2073,7 +2168,6 @@ void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); -struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); @@ -2619,6 +2713,18 @@ static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) } #endif /* CONFIG_BPF_SYSCALL */ +static __always_inline int +bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) +{ + int ret = -EFAULT; + + if (IS_ENABLED(CONFIG_BPF_EVENTS)) + ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); + if (unlikely(ret < 0)) + memset(dst, 0, size); + return ret; +} + void __bpf_free_used_btfs(struct bpf_prog_aux *aux, struct btf_mod_pair *used_btfs, u32 len); diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index 3929be5743f4..d644bbb298af 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -27,10 +27,12 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); /* kmalloc/kfree equivalent: */ void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); +void bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr); /* kmem_cache_alloc/free equivalent: */ void *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma); void bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr); +void bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr); void bpf_mem_cache_raw_free(void *ptr); void *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags); diff --git a/include/linux/bpf_mprog.h b/include/linux/bpf_mprog.h new file mode 100644 index 000000000000..929225f7b095 --- /dev/null +++ b/include/linux/bpf_mprog.h @@ -0,0 +1,343 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Isovalent */ +#ifndef __BPF_MPROG_H +#define __BPF_MPROG_H + +#include <linux/bpf.h> + +/* bpf_mprog framework: + * + * bpf_mprog is a generic layer for multi-program attachment. In-kernel users + * of the bpf_mprog don't need to care about the dependency resolution + * internals, they can just consume it with few API calls. Currently available + * dependency directives are BPF_F_{BEFORE,AFTER} which enable insertion of + * a BPF program or BPF link relative to an existing BPF program or BPF link + * inside the multi-program array as well as prepend and append behavior if + * no relative object was specified, see corresponding selftests for concrete + * examples (e.g. tc_links and tc_opts test cases of test_progs). + * + * Usage of bpf_mprog_{attach,detach,query}() core APIs with pseudo code: + * + * Attach case: + * + * struct bpf_mprog_entry *entry, *entry_new; + * int ret; + * + * // bpf_mprog user-side lock + * // fetch active @entry from attach location + * [...] + * ret = bpf_mprog_attach(entry, &entry_new, [...]); + * if (!ret) { + * if (entry != entry_new) { + * // swap @entry to @entry_new at attach location + * // ensure there are no inflight users of @entry: + * synchronize_rcu(); + * } + * bpf_mprog_commit(entry); + * } else { + * // error path, bail out, propagate @ret + * } + * // bpf_mprog user-side unlock + * + * Detach case: + * + * struct bpf_mprog_entry *entry, *entry_new; + * int ret; + * + * // bpf_mprog user-side lock + * // fetch active @entry from attach location + * [...] + * ret = bpf_mprog_detach(entry, &entry_new, [...]); + * if (!ret) { + * // all (*) marked is optional and depends on the use-case + * // whether bpf_mprog_bundle should be freed or not + * if (!bpf_mprog_total(entry_new)) (*) + * entry_new = NULL (*) + * // swap @entry to @entry_new at attach location + * // ensure there are no inflight users of @entry: + * synchronize_rcu(); + * bpf_mprog_commit(entry); + * if (!entry_new) (*) + * // free bpf_mprog_bundle (*) + * } else { + * // error path, bail out, propagate @ret + * } + * // bpf_mprog user-side unlock + * + * Query case: + * + * struct bpf_mprog_entry *entry; + * int ret; + * + * // bpf_mprog user-side lock + * // fetch active @entry from attach location + * [...] + * ret = bpf_mprog_query(attr, uattr, entry); + * // bpf_mprog user-side unlock + * + * Data/fast path: + * + * struct bpf_mprog_entry *entry; + * struct bpf_mprog_fp *fp; + * struct bpf_prog *prog; + * int ret = [...]; + * + * rcu_read_lock(); + * // fetch active @entry from attach location + * [...] + * bpf_mprog_foreach_prog(entry, fp, prog) { + * ret = bpf_prog_run(prog, [...]); + * // process @ret from program + * } + * [...] + * rcu_read_unlock(); + * + * bpf_mprog locking considerations: + * + * bpf_mprog_{attach,detach,query}() must be protected by an external lock + * (like RTNL in case of tcx). + * + * bpf_mprog_entry pointer can be an __rcu annotated pointer (in case of tcx + * the netdevice has tcx_ingress and tcx_egress __rcu pointer) which gets + * updated via rcu_assign_pointer() pointing to the active bpf_mprog_entry of + * the bpf_mprog_bundle. + * + * Fast path accesses the active bpf_mprog_entry within RCU critical section + * (in case of tcx it runs in NAPI which provides RCU protection there, + * other users might need explicit rcu_read_lock()). The bpf_mprog_commit() + * assumes that for the old bpf_mprog_entry there are no inflight users + * anymore. + * + * The READ_ONCE()/WRITE_ONCE() pairing for bpf_mprog_fp's prog access is for + * the replacement case where we don't swap the bpf_mprog_entry. + */ + +#define bpf_mprog_foreach_tuple(entry, fp, cp, t) \ + for (fp = &entry->fp_items[0], cp = &entry->parent->cp_items[0];\ + ({ \ + t.prog = READ_ONCE(fp->prog); \ + t.link = cp->link; \ + t.prog; \ + }); \ + fp++, cp++) + +#define bpf_mprog_foreach_prog(entry, fp, p) \ + for (fp = &entry->fp_items[0]; \ + (p = READ_ONCE(fp->prog)); \ + fp++) + +#define BPF_MPROG_MAX 64 + +struct bpf_mprog_fp { + struct bpf_prog *prog; +}; + +struct bpf_mprog_cp { + struct bpf_link *link; +}; + +struct bpf_mprog_entry { + struct bpf_mprog_fp fp_items[BPF_MPROG_MAX]; + struct bpf_mprog_bundle *parent; +}; + +struct bpf_mprog_bundle { + struct bpf_mprog_entry a; + struct bpf_mprog_entry b; + struct bpf_mprog_cp cp_items[BPF_MPROG_MAX]; + struct bpf_prog *ref; + atomic64_t revision; + u32 count; +}; + +struct bpf_tuple { + struct bpf_prog *prog; + struct bpf_link *link; +}; + +static inline struct bpf_mprog_entry * +bpf_mprog_peer(const struct bpf_mprog_entry *entry) +{ + if (entry == &entry->parent->a) + return &entry->parent->b; + else + return &entry->parent->a; +} + +static inline void bpf_mprog_bundle_init(struct bpf_mprog_bundle *bundle) +{ + BUILD_BUG_ON(sizeof(bundle->a.fp_items[0]) > sizeof(u64)); + BUILD_BUG_ON(ARRAY_SIZE(bundle->a.fp_items) != + ARRAY_SIZE(bundle->cp_items)); + + memset(bundle, 0, sizeof(*bundle)); + atomic64_set(&bundle->revision, 1); + bundle->a.parent = bundle; + bundle->b.parent = bundle; +} + +static inline void bpf_mprog_inc(struct bpf_mprog_entry *entry) +{ + entry->parent->count++; +} + +static inline void bpf_mprog_dec(struct bpf_mprog_entry *entry) +{ + entry->parent->count--; +} + +static inline int bpf_mprog_max(void) +{ + return ARRAY_SIZE(((struct bpf_mprog_entry *)NULL)->fp_items) - 1; +} + +static inline int bpf_mprog_total(struct bpf_mprog_entry *entry) +{ + int total = entry->parent->count; + + WARN_ON_ONCE(total > bpf_mprog_max()); + return total; +} + +static inline bool bpf_mprog_exists(struct bpf_mprog_entry *entry, + struct bpf_prog *prog) +{ + const struct bpf_mprog_fp *fp; + const struct bpf_prog *tmp; + + bpf_mprog_foreach_prog(entry, fp, tmp) { + if (tmp == prog) + return true; + } + return false; +} + +static inline void bpf_mprog_mark_for_release(struct bpf_mprog_entry *entry, + struct bpf_tuple *tuple) +{ + WARN_ON_ONCE(entry->parent->ref); + if (!tuple->link) + entry->parent->ref = tuple->prog; +} + +static inline void bpf_mprog_complete_release(struct bpf_mprog_entry *entry) +{ + /* In the non-link case prog deletions can only drop the reference + * to the prog after the bpf_mprog_entry got swapped and the + * bpf_mprog ensured that there are no inflight users anymore. + * + * Paired with bpf_mprog_mark_for_release(). + */ + if (entry->parent->ref) { + bpf_prog_put(entry->parent->ref); + entry->parent->ref = NULL; + } +} + +static inline void bpf_mprog_revision_new(struct bpf_mprog_entry *entry) +{ + atomic64_inc(&entry->parent->revision); +} + +static inline void bpf_mprog_commit(struct bpf_mprog_entry *entry) +{ + bpf_mprog_complete_release(entry); + bpf_mprog_revision_new(entry); +} + +static inline u64 bpf_mprog_revision(struct bpf_mprog_entry *entry) +{ + return atomic64_read(&entry->parent->revision); +} + +static inline void bpf_mprog_entry_copy(struct bpf_mprog_entry *dst, + struct bpf_mprog_entry *src) +{ + memcpy(dst->fp_items, src->fp_items, sizeof(src->fp_items)); +} + +static inline void bpf_mprog_entry_clear(struct bpf_mprog_entry *dst) +{ + memset(dst->fp_items, 0, sizeof(dst->fp_items)); +} + +static inline void bpf_mprog_clear_all(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new) +{ + struct bpf_mprog_entry *peer; + + peer = bpf_mprog_peer(entry); + bpf_mprog_entry_clear(peer); + peer->parent->count = 0; + *entry_new = peer; +} + +static inline void bpf_mprog_entry_grow(struct bpf_mprog_entry *entry, int idx) +{ + int total = bpf_mprog_total(entry); + + memmove(entry->fp_items + idx + 1, + entry->fp_items + idx, + (total - idx) * sizeof(struct bpf_mprog_fp)); + + memmove(entry->parent->cp_items + idx + 1, + entry->parent->cp_items + idx, + (total - idx) * sizeof(struct bpf_mprog_cp)); +} + +static inline void bpf_mprog_entry_shrink(struct bpf_mprog_entry *entry, int idx) +{ + /* Total array size is needed in this case to enure the NULL + * entry is copied at the end. + */ + int total = ARRAY_SIZE(entry->fp_items); + + memmove(entry->fp_items + idx, + entry->fp_items + idx + 1, + (total - idx - 1) * sizeof(struct bpf_mprog_fp)); + + memmove(entry->parent->cp_items + idx, + entry->parent->cp_items + idx + 1, + (total - idx - 1) * sizeof(struct bpf_mprog_cp)); +} + +static inline void bpf_mprog_read(struct bpf_mprog_entry *entry, u32 idx, + struct bpf_mprog_fp **fp, + struct bpf_mprog_cp **cp) +{ + *fp = &entry->fp_items[idx]; + *cp = &entry->parent->cp_items[idx]; +} + +static inline void bpf_mprog_write(struct bpf_mprog_fp *fp, + struct bpf_mprog_cp *cp, + struct bpf_tuple *tuple) +{ + WRITE_ONCE(fp->prog, tuple->prog); + cp->link = tuple->link; +} + +int bpf_mprog_attach(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_prog *prog_new, struct bpf_link *link, + struct bpf_prog *prog_old, + u32 flags, u32 id_or_fd, u64 revision); + +int bpf_mprog_detach(struct bpf_mprog_entry *entry, + struct bpf_mprog_entry **entry_new, + struct bpf_prog *prog, struct bpf_link *link, + u32 flags, u32 id_or_fd, u64 revision); + +int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, + struct bpf_mprog_entry *entry); + +static inline bool bpf_mprog_supported(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_SCHED_CLS: + return true; + default: + return false; + } +} +#endif /* __BPF_MPROG_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index f70f9ac884d2..b6e58dab8e27 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -745,7 +745,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) } } -#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED) +#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED | NON_OWN_REF) static inline bool bpf_type_has_unsafe_modifiers(u32 type) { diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 5d732f48f787..c55810a43541 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -44,6 +44,7 @@ #define PHY_ID_BCM7366 0x600d8490 #define PHY_ID_BCM7346 0x600d8650 #define PHY_ID_BCM7362 0x600d84b0 +#define PHY_ID_BCM74165 0x359052c0 #define PHY_ID_BCM7425 0x600d86b0 #define PHY_ID_BCM7429 0x600d8730 #define PHY_ID_BCM7435 0x600d8750 diff --git a/include/linux/btf.h b/include/linux/btf.h index cac9f304e27a..df64cc642074 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -204,8 +204,6 @@ u32 btf_nr_types(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); -int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); -int btf_find_timer(const struct btf *btf, const struct btf_type *t); struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size); int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec); diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 00950cc03bff..a3462a9b8e18 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -267,5 +267,6 @@ MAX_BTF_TRACING_TYPE, extern u32 btf_tracing_ids[]; extern u32 bpf_cgroup_btf_id[]; extern u32 bpf_local_storage_map_btf_id[]; +extern u32 btf_bpf_map_id[]; #endif diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index c205c51d79c9..d29bb4521947 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -3,7 +3,7 @@ * linux/can/rx-offload.h * * Copyright (c) 2014 David Jander, Protonic Holland - * Copyright (c) 2014-2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de> + * Copyright (c) 2014-2017, 2023 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de> */ #ifndef _CAN_RX_OFFLOAD_H @@ -44,11 +44,14 @@ int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); int can_rx_offload_queue_timestamp(struct can_rx_offload *offload, struct sk_buff *skb, u32 timestamp); -unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, - unsigned int idx, u32 timestamp, - unsigned int *frame_len_ptr); +unsigned int can_rx_offload_get_echo_skb_queue_timestamp(struct can_rx_offload *offload, + unsigned int idx, u32 timestamp, + unsigned int *frame_len_ptr); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb); +unsigned int can_rx_offload_get_echo_skb_queue_tail(struct can_rx_offload *offload, + unsigned int idx, + unsigned int *frame_len_ptr); void can_rx_offload_irq_finish(struct can_rx_offload *offload); void can_rx_offload_threaded_irq_finish(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); diff --git a/include/linux/connector.h b/include/linux/connector.h index 487350bb19c3..cec2d99ae902 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -90,13 +90,19 @@ void cn_del_callback(const struct cb_id *id); * If @group is not zero, then message will be delivered * to the specified group. * @gfp_mask: GFP mask. + * @filter: Filter function to be used at netlink layer. + * @filter_data:Filter data to be supplied to the filter function * * It can be safely called from softirq context, but may silently * fail under strong memory pressure. * * If there are no listeners for given group %-ESRCH can be returned. */ -int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 group, gfp_t gfp_mask); +int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, + u32 group, gfp_t gfp_mask, + int (*filter)(struct sock *dsk, struct sk_buff *skb, + void *data), + void *filter_data); /** * cn_netlink_send - Sends message to the specified groups. diff --git a/include/linux/filter.h b/include/linux/filter.h index f69114083ec7..761af6b3cf2b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -69,6 +69,9 @@ struct ctl_table_header; /* unused opcode to mark special load instruction. Same as BPF_ABS */ #define BPF_PROBE_MEM 0x20 +/* unused opcode to mark special ldsx instruction. Same as BPF_IND */ +#define BPF_PROBE_MEMSX 0x40 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 @@ -90,22 +93,28 @@ struct ctl_table_header; /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ -#define BPF_ALU64_REG(OP, DST, SRC) \ +#define BPF_ALU64_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ - .off = 0, \ + .off = OFF, \ .imm = 0 }) -#define BPF_ALU32_REG(OP, DST, SRC) \ +#define BPF_ALU64_REG(OP, DST, SRC) \ + BPF_ALU64_REG_OFF(OP, DST, SRC, 0) + +#define BPF_ALU32_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ - .off = 0, \ + .off = OFF, \ .imm = 0 }) +#define BPF_ALU32_REG(OP, DST, SRC) \ + BPF_ALU32_REG_OFF(OP, DST, SRC, 0) + /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ #define BPF_ALU64_IMM(OP, DST, IMM) \ @@ -765,23 +774,6 @@ DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp); -static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, - struct xdp_buff *xdp) -{ - /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus - * under local_bh_disable(), which provides the needed RCU protection - * for accessing map entries. - */ - u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); - - if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) { - if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev)) - act = xdp_master_redirect(xdp); - } - - return act; -} - void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) @@ -1580,10 +1572,9 @@ static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) return NULL; } -static inline void *bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, - unsigned long len, bool flush) +static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, + unsigned long len, bool flush) { - return NULL; } #endif /* CONFIG_NET */ diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h deleted file mode 100644 index 77d783f71527..000000000000 --- a/include/linux/fs_enet_pd.h +++ /dev/null @@ -1,165 +0,0 @@ -/* - * Platform information definitions for the - * universal Freescale Ethernet driver. - * - * Copyright (c) 2003 Intracom S.A. - * by Pantelis Antoniou <panto@intracom.gr> - * - * 2005 (c) MontaVista Software, Inc. - * Vitaly Bordug <vbordug@ru.mvista.com> - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef FS_ENET_PD_H -#define FS_ENET_PD_H - -#include <linux/clk.h> -#include <linux/string.h> -#include <linux/of_mdio.h> -#include <linux/if_ether.h> -#include <asm/types.h> - -#define FS_ENET_NAME "fs_enet" - -enum fs_id { - fsid_fec1, - fsid_fec2, - fsid_fcc1, - fsid_fcc2, - fsid_fcc3, - fsid_scc1, - fsid_scc2, - fsid_scc3, - fsid_scc4, -}; - -#define FS_MAX_INDEX 9 - -static inline int fs_get_fec_index(enum fs_id id) -{ - if (id >= fsid_fec1 && id <= fsid_fec2) - return id - fsid_fec1; - return -1; -} - -static inline int fs_get_fcc_index(enum fs_id id) -{ - if (id >= fsid_fcc1 && id <= fsid_fcc3) - return id - fsid_fcc1; - return -1; -} - -static inline int fs_get_scc_index(enum fs_id id) -{ - if (id >= fsid_scc1 && id <= fsid_scc4) - return id - fsid_scc1; - return -1; -} - -static inline int fs_fec_index2id(int index) -{ - int id = fsid_fec1 + index - 1; - if (id >= fsid_fec1 && id <= fsid_fec2) - return id; - return FS_MAX_INDEX; - } - -static inline int fs_fcc_index2id(int index) -{ - int id = fsid_fcc1 + index - 1; - if (id >= fsid_fcc1 && id <= fsid_fcc3) - return id; - return FS_MAX_INDEX; -} - -static inline int fs_scc_index2id(int index) -{ - int id = fsid_scc1 + index - 1; - if (id >= fsid_scc1 && id <= fsid_scc4) - return id; - return FS_MAX_INDEX; -} - -enum fs_mii_method { - fsmii_fixed, - fsmii_fec, - fsmii_bitbang, -}; - -enum fs_ioport { - fsiop_porta, - fsiop_portb, - fsiop_portc, - fsiop_portd, - fsiop_porte, -}; - -struct fs_mii_bit { - u32 offset; - u8 bit; - u8 polarity; -}; -struct fs_mii_bb_platform_info { - struct fs_mii_bit mdio_dir; - struct fs_mii_bit mdio_dat; - struct fs_mii_bit mdc_dat; - int delay; /* delay in us */ - int irq[32]; /* irqs per phy's */ -}; - -struct fs_platform_info { - - void(*init_ioports)(struct fs_platform_info *); - /* device specific information */ - int fs_no; /* controller index */ - char fs_type[4]; /* controller type */ - - u32 cp_page; /* CPM page */ - u32 cp_block; /* CPM sblock */ - u32 cp_command; /* CPM page/sblock/mcn */ - - u32 clk_trx; /* some stuff for pins & mux configuration*/ - u32 clk_rx; - u32 clk_tx; - u32 clk_route; - u32 clk_mask; - - u32 mem_offset; - u32 dpram_offset; - u32 fcc_regs_c; - - u32 device_flags; - - struct device_node *phy_node; - const struct fs_mii_bus_info *bus_info; - - int rx_ring, tx_ring; /* number of buffers on rx */ - __u8 macaddr[ETH_ALEN]; /* mac address */ - int rx_copybreak; /* limit we copy small frames */ - int napi_weight; /* NAPI weight */ - - int use_rmii; /* use RMII mode */ - int has_phy; /* if the network is phy container as well...*/ - - struct clk *clk_per; /* 'per' clock for register access */ -}; -struct fs_mii_fec_platform_info { - u32 irq[32]; - u32 mii_speed; -}; - -static inline int fs_get_id(struct fs_platform_info *fpi) -{ - if(strstr(fpi->fs_type, "SCC")) - return fs_scc_index2id(fpi->fs_no); - if(strstr(fpi->fs_type, "FCC")) - return fs_fcc_index2id(fpi->fs_no); - if(strstr(fpi->fs_type, "FEC")) - return fs_fec_index2id(fpi->fs_no); - return fpi->fs_no; -} - -#endif diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index db0f4fcfdaf4..e3b3b0fa2a8f 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -85,12 +85,10 @@ extern void icmpv6_param_prob_reason(struct sk_buff *skb, struct flowi6; struct in6_addr; -extern void icmpv6_flow_init(struct sock *sk, - struct flowi6 *fl6, - u8 type, - const struct in6_addr *saddr, - const struct in6_addr *daddr, - int oif); + +void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type, + const struct in6_addr *saddr, + const struct in6_addr *daddr, int oif); static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 4b998090898e..bd2f6e19c357 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -836,9 +836,14 @@ enum ieee80211_preq_target_flags { }; /** - * struct ieee80211_quiet_ie + * struct ieee80211_quiet_ie - Quiet element + * @count: Quiet Count + * @period: Quiet Period + * @duration: Quiet Duration + * @offset: Quiet Offset * - * This structure refers to "Quiet information element" + * This structure represents the payload of the "Quiet element" as + * described in IEEE Std 802.11-2020 section 9.4.2.22. */ struct ieee80211_quiet_ie { u8 count; @@ -848,9 +853,15 @@ struct ieee80211_quiet_ie { } __packed; /** - * struct ieee80211_msrment_ie + * struct ieee80211_msrment_ie - Measurement element + * @token: Measurement Token + * @mode: Measurement Report Mode + * @type: Measurement Type + * @request: Measurement Request or Measurement Report * - * This structure refers to "Measurement Request/Report information element" + * This structure represents the payload of both the "Measurement + * Request element" and the "Measurement Report element" as described + * in IEEE Std 802.11-2020 sections 9.4.2.20 and 9.4.2.21. */ struct ieee80211_msrment_ie { u8 token; @@ -860,9 +871,14 @@ struct ieee80211_msrment_ie { } __packed; /** - * struct ieee80211_channel_sw_ie + * struct ieee80211_channel_sw_ie - Channel Switch Announcement element + * @mode: Channel Switch Mode + * @new_ch_num: New Channel Number + * @count: Channel Switch Count * - * This structure refers to "Channel Switch Announcement information element" + * This structure represents the payload of the "Channel Switch + * Announcement element" as described in IEEE Std 802.11-2020 section + * 9.4.2.18. */ struct ieee80211_channel_sw_ie { u8 mode; @@ -871,9 +887,14 @@ struct ieee80211_channel_sw_ie { } __packed; /** - * struct ieee80211_ext_chansw_ie + * struct ieee80211_ext_chansw_ie - Extended Channel Switch Announcement element + * @mode: Channel Switch Mode + * @new_operating_class: New Operating Class + * @new_ch_num: New Channel Number + * @count: Channel Switch Count * - * This structure represents the "Extended Channel Switch Announcement element" + * This structure represents the "Extended Channel Switch Announcement + * element" as described in IEEE Std 802.11-2020 section 9.4.2.52. */ struct ieee80211_ext_chansw_ie { u8 mode; @@ -894,8 +915,14 @@ struct ieee80211_sec_chan_offs_ie { /** * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE + * @mesh_ttl: Time To Live + * @mesh_flags: Flags + * @mesh_reason: Reason Code + * @mesh_pre_value: Precedence Value * - * This structure represents the "Mesh Channel Switch Paramters element" + * This structure represents the payload of the "Mesh Channel Switch + * Parameters element" as described in IEEE Std 802.11-2020 section + * 9.4.2.102. */ struct ieee80211_mesh_chansw_params_ie { u8 mesh_ttl; @@ -906,6 +933,13 @@ struct ieee80211_mesh_chansw_params_ie { /** * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE + * @new_channel_width: New Channel Width + * @new_center_freq_seg0: New Channel Center Frequency Segment 0 + * @new_center_freq_seg1: New Channel Center Frequency Segment 1 + * + * This structure represents the payload of the "Wide Bandwidth + * Channel Switch element" as described in IEEE Std 802.11-2020 + * section 9.4.2.160. */ struct ieee80211_wide_bw_chansw_ie { u8 new_channel_width; @@ -913,9 +947,14 @@ struct ieee80211_wide_bw_chansw_ie { } __packed; /** - * struct ieee80211_tim + * struct ieee80211_tim_ie - Traffic Indication Map information element + * @dtim_count: DTIM Count + * @dtim_period: DTIM Period + * @bitmap_ctrl: Bitmap Control + * @virtual_map: Partial Virtual Bitmap * - * This structure refers to "Traffic Indication Map information element" + * This structure represents the payload of the "TIM element" as + * described in IEEE Std 802.11-2020 section 9.4.2.5. */ struct ieee80211_tim_ie { u8 dtim_count; @@ -926,9 +965,17 @@ struct ieee80211_tim_ie { } __packed; /** - * struct ieee80211_meshconf_ie + * struct ieee80211_meshconf_ie - Mesh Configuration element + * @meshconf_psel: Active Path Selection Protocol Identifier + * @meshconf_pmetric: Active Path Selection Metric Identifier + * @meshconf_congest: Congestion Control Mode Identifier + * @meshconf_synch: Synchronization Method Identifier + * @meshconf_auth: Authentication Protocol Identifier + * @meshconf_form: Mesh Formation Info + * @meshconf_cap: Mesh Capability (see &enum mesh_config_capab_flags) * - * This structure refers to "Mesh Configuration information element" + * This structure represents the payload of the "Mesh Configuration + * element" as described in IEEE Std 802.11-2020 section 9.4.2.97. */ struct ieee80211_meshconf_ie { u8 meshconf_psel; @@ -950,6 +997,9 @@ struct ieee80211_meshconf_ie { * is ongoing * @IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL: STA is in deep sleep mode or has * neighbors in deep sleep mode + * + * Enumerates the "Mesh Capability" as described in IEEE Std + * 802.11-2020 section 9.4.2.97.7. */ enum mesh_config_capab_flags { IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS = 0x01, @@ -960,7 +1010,7 @@ enum mesh_config_capab_flags { #define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1 -/** +/* * mesh channel switch parameters element's flag indicator * */ @@ -969,9 +1019,17 @@ enum mesh_config_capab_flags { #define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2) /** - * struct ieee80211_rann_ie + * struct ieee80211_rann_ie - RANN (root announcement) element + * @rann_flags: Flags + * @rann_hopcount: Hop Count + * @rann_ttl: Element TTL + * @rann_addr: Root Mesh STA Address + * @rann_seq: HWMP Sequence Number + * @rann_interval: Interval + * @rann_metric: Metric * - * This structure refers to "Root Announcement information element" + * This structure represents the payload of the "RANN element" as + * described in IEEE Std 802.11-2020 section 9.4.2.111. */ struct ieee80211_rann_ie { u8 rann_flags; @@ -993,7 +1051,7 @@ enum ieee80211_ht_chanwidth_values { }; /** - * enum ieee80211_opmode_bits - VHT operating mode field bits + * enum ieee80211_vht_opmode_bits - VHT operating mode field bits * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: 20 MHz channel width * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width @@ -1042,9 +1100,12 @@ enum ieee80211_s1g_chanwidth { #define WLAN_USER_POSITION_LEN 16 /** - * struct ieee80211_tpc_report_ie + * struct ieee80211_tpc_report_ie - TPC Report element + * @tx_power: Transmit Power + * @link_margin: Link Margin * - * This structure refers to "TPC Report element" + * This structure represents the payload of the "TPC Report element" as + * described in IEEE Std 802.11-2020 section 9.4.2.16. */ struct ieee80211_tpc_report_ie { u8 tx_power; @@ -1062,9 +1123,14 @@ struct ieee80211_addba_ext_ie { } __packed; /** - * struct ieee80211_s1g_bcn_compat_ie + * struct ieee80211_s1g_bcn_compat_ie - S1G Beacon Compatibility element + * @compat_info: Compatibility Information + * @beacon_int: Beacon Interval + * @tsf_completion: TSF Completion * - * S1G Beacon Compatibility element + * This structure represents the payload of the "S1G Beacon + * Compatibility element" as described in IEEE Std 802.11-2020 section + * 9.4.2.196. */ struct ieee80211_s1g_bcn_compat_ie { __le16 compat_info; @@ -1073,9 +1139,15 @@ struct ieee80211_s1g_bcn_compat_ie { } __packed; /** - * struct ieee80211_s1g_oper_ie + * struct ieee80211_s1g_oper_ie - S1G Operation element + * @ch_width: S1G Operation Information Channel Width + * @oper_class: S1G Operation Information Operating Class + * @primary_ch: S1G Operation Information Primary Channel Number + * @oper_ch: S1G Operation Information Channel Center Frequency + * @basic_mcs_nss: Basic S1G-MCS and NSS Set * - * S1G Operation element + * This structure represents the payload of the "S1G Operation + * element" as described in IEEE Std 802.11-2020 section 9.4.2.212. */ struct ieee80211_s1g_oper_ie { u8 ch_width; @@ -1086,9 +1158,13 @@ struct ieee80211_s1g_oper_ie { } __packed; /** - * struct ieee80211_aid_response_ie + * struct ieee80211_aid_response_ie - AID Response element + * @aid: AID/Group AID + * @switch_count: AID Switch Count + * @response_int: AID Response Interval * - * AID Response element + * This structure represents the payload of the "AID Response element" + * as described in IEEE Std 802.11-2020 section 9.4.2.194. */ struct ieee80211_aid_response_ie { __le16 aid; @@ -1489,7 +1565,7 @@ struct ieee80211_tdls_data { /* * Peer-to-Peer IE attribute related definitions. */ -/** +/* * enum ieee80211_p2p_attr_id - identifies type of peer-to-peer attribute. */ enum ieee80211_p2p_attr_id { @@ -1539,11 +1615,17 @@ struct ieee80211_p2p_noa_attr { #define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F /** - * struct ieee80211_bar - HT Block Ack Request + * struct ieee80211_bar - Block Ack Request frame format + * @frame_control: Frame Control + * @duration: Duration + * @ra: RA + * @ta: TA + * @control: BAR Control + * @start_seq_num: Starting Sequence Number (see Figure 9-37) * - * This structure refers to "HT BlockAckReq" as - * described in 802.11n draft section 7.2.1.7.1 - */ + * This structure represents the "BlockAckReq frame format" + * as described in IEEE Std 802.11-2020 section 9.3.1.7. +*/ struct ieee80211_bar { __le16 frame_control; __le16 duration; @@ -1563,13 +1645,17 @@ struct ieee80211_bar { #define IEEE80211_HT_MCS_MASK_LEN 10 /** - * struct ieee80211_mcs_info - MCS information + * struct ieee80211_mcs_info - Supported MCS Set field * @rx_mask: RX mask * @rx_highest: highest supported RX rate. If set represents * the highest supported RX data rate in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest RX data rate supported. * @tx_params: TX parameters + * @reserved: Reserved bits + * + * This structure represents the "Supported MCS Set field" as + * described in IEEE Std 802.11-2020 section 9.4.2.55.4. */ struct ieee80211_mcs_info { u8 rx_mask[IEEE80211_HT_MCS_MASK_LEN]; @@ -1600,10 +1686,16 @@ struct ieee80211_mcs_info { (IEEE80211_HT_MCS_UNEQUAL_MODULATION_START / 8) /** - * struct ieee80211_ht_cap - HT capabilities + * struct ieee80211_ht_cap - HT capabilities element + * @cap_info: HT Capability Information + * @ampdu_params_info: A-MPDU Parameters + * @mcs: Supported MCS Set + * @extended_ht_cap_info: HT Extended Capabilities + * @tx_BF_cap_info: Transmit Beamforming Capabilities + * @antenna_selection_info: ASEL Capability * - * This structure is the "HT capabilities element" as - * described in 802.11n D5.0 7.3.2.57 + * This structure represents the payload of the "HT Capabilities + * element" as described in IEEE Std 802.11-2020 section 9.4.2.55. */ struct ieee80211_ht_cap { __le16 cap_info; @@ -1691,9 +1783,14 @@ enum ieee80211_min_mpdu_spacing { /** * struct ieee80211_ht_operation - HT operation IE + * @primary_chan: Primary Channel + * @ht_param: HT Operation Information parameters + * @operation_mode: HT Operation Information operation mode + * @stbc_param: HT Operation Information STBC params + * @basic_set: Basic HT-MCS Set * - * This structure is the "HT operation element" as - * described in 802.11n-2009 7.3.2.57 + * This structure represents the payload of the "HT Operation + * element" as described in IEEE Std 802.11-2020 section 9.4.2.56. */ struct ieee80211_ht_operation { u8 primary_chan; @@ -1862,9 +1959,12 @@ struct ieee80211_vht_operation { /** * struct ieee80211_he_cap_elem - HE capabilities element + * @mac_cap_info: HE MAC Capabilities Information + * @phy_cap_info: HE PHY Capabilities Information * - * This structure is the "HE capabilities element" fixed fields as - * described in P802.11ax_D4.0 section 9.4.2.242.2 and 9.4.2.242.3 + * This structure represents the fixed fields of the payload of the + * "HE capabilities element" as described in IEEE Std 802.11ax-2021 + * sections 9.4.2.248.2 and 9.4.2.248.3. */ struct ieee80211_he_cap_elem { u8 mac_cap_info[6]; @@ -1923,35 +2023,45 @@ struct ieee80211_he_mcs_nss_supp { } __packed; /** - * struct ieee80211_he_operation - HE capabilities element + * struct ieee80211_he_operation - HE Operation element + * @he_oper_params: HE Operation Parameters + BSS Color Information + * @he_mcs_nss_set: Basic HE-MCS And NSS Set + * @optional: Optional fields VHT Operation Information, Max Co-Hosted + * BSSID Indicator, and 6 GHz Operation Information * - * This structure is the "HE operation element" fields as - * described in P802.11ax_D4.0 section 9.4.2.243 + * This structure represents the payload of the "HE Operation + * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.249. */ struct ieee80211_he_operation { __le32 he_oper_params; __le16 he_mcs_nss_set; - /* Optional 0,1,3,4,5,7 or 8 bytes: depends on @he_oper_params */ u8 optional[]; } __packed; /** - * struct ieee80211_he_spr - HE spatial reuse element + * struct ieee80211_he_spr - Spatial Reuse Parameter Set element + * @he_sr_control: SR Control + * @optional: Optional fields Non-SRG OBSS PD Max Offset, SRG OBSS PD + * Min Offset, SRG OBSS PD Max Offset, SRG BSS Color + * Bitmap, and SRG Partial BSSID Bitmap * - * This structure is the "HE spatial reuse element" element as - * described in P802.11ax_D4.0 section 9.4.2.241 + * This structure represents the payload of the "Spatial Reuse + * Parameter Set element" as described in IEEE Std 802.11ax-2021 + * section 9.4.2.252. */ struct ieee80211_he_spr { u8 he_sr_control; - /* Optional 0 to 19 bytes: depends on @he_sr_control */ u8 optional[]; } __packed; /** * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field + * @aifsn: ACI/AIFSN + * @ecw_min_max: ECWmin/ECWmax + * @mu_edca_timer: MU EDCA Timer * - * This structure is the "MU AC Parameter Record" fields as - * described in P802.11ax_D4.0 section 9.4.2.245 + * This structure represents the "MU AC Parameter Record" as described + * in IEEE Std 802.11ax-2021 section 9.4.2.251, Figure 9-788p. */ struct ieee80211_he_mu_edca_param_ac_rec { u8 aifsn; @@ -1961,9 +2071,14 @@ struct ieee80211_he_mu_edca_param_ac_rec { /** * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element + * @mu_qos_info: QoS Info + * @ac_be: MU AC_BE Parameter Record + * @ac_bk: MU AC_BK Parameter Record + * @ac_vi: MU AC_VI Parameter Record + * @ac_vo: MU AC_VO Parameter Record * - * This structure is the "MU EDCA Parameter Set element" fields as - * described in P802.11ax_D4.0 section 9.4.2.245 + * This structure represents the payload of the "MU EDCA Parameter Set + * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.251. */ struct ieee80211_mu_edca_param_set { u8 mu_qos_info; @@ -2177,9 +2292,9 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, * enum ieee80211_ap_reg_power - regulatory power for a Access Point * * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode - * @IEEE80211_REG_LPI: Indoor Access Point - * @IEEE80211_REG_SP: Standard power Access Point - * @IEEE80211_REG_VLP: Very low power Access Point + * @IEEE80211_REG_LPI_AP: Indoor Access Point + * @IEEE80211_REG_SP_AP: Standard power Access Point + * @IEEE80211_REG_VLP_AP: Very low power Access Point * @IEEE80211_REG_AP_POWER_AFTER_LAST: internal * @IEEE80211_REG_AP_POWER_MAX: maximum value */ @@ -2567,7 +2682,7 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) #define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 /** - * ieee80211_he_6ghz_oper - HE 6 GHz operation Information field + * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field * @primary: primary channel * @control: control flags * @ccfs0: channel center frequency segment 0 @@ -2614,9 +2729,13 @@ enum ieee80211_tx_power_intrpt_type { }; /** - * struct ieee80211_tx_pwr_env + * struct ieee80211_tx_pwr_env - Transmit Power Envelope + * @tx_power_info: Transmit Power Information field + * @tx_power: Maximum Transmit Power field * - * This structure represents the "Transmit Power Envelope element" + * This structure represents the payload of the "Transmit Power + * Envelope element" as described in IEEE Std 802.11ax-2021 section + * 9.4.2.161 */ struct ieee80211_tx_pwr_env { u8 tx_power_info; @@ -4478,7 +4597,7 @@ static inline bool for_each_element_completed(const struct element *element, return (const u8 *)element == (const u8 *)data + datalen; } -/** +/* * RSNX Capabilities: * bits 0-3: Field length (n-1) */ @@ -4721,7 +4840,7 @@ ieee80211_mle_get_bss_param_ch_cnt(const struct ieee80211_multi_link_elem *mle) } /** - * ieee80211_mle_get_eml_sync_delay - returns the medium sync delay + * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay * @data: pointer to the multi link EHT IE * * The element is assumed to be of the correct type (BASIC) and big enough, diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 1ed52441972f..10a1e81434cb 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -53,6 +53,10 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_NONE: case ARPHRD_RAWIP: case ARPHRD_PIMREG: + /* PPP adds its l2 header automatically in ppp_start_xmit(). + * This makes it look like an l3 device to __bpf_redirect() and tcf_mirred_init(). + */ + case ARPHRD_PPP: return false; default: return true; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 8de6b6e67829..1b9b15a492fa 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -162,8 +162,8 @@ struct team_option { bool per_port; unsigned int array_size; /* != 0 means the option is array */ enum team_option_type type; - int (*init)(struct team *team, struct team_option_inst_info *info); - int (*getter)(struct team *team, struct team_gsetter_ctx *ctx); + void (*init)(struct team *team, struct team_option_inst_info *info); + void (*getter)(struct team *team, struct team_gsetter_ctx *ctx); int (*setter)(struct team *team, struct team_gsetter_ctx *ctx); }; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 6ba71957851e..3028af87716e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -408,7 +408,7 @@ static inline int __vlan_insert_tag(struct sk_buff *skb, * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len - * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. @@ -437,7 +437,7 @@ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload - * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. @@ -457,7 +457,7 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload - * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 839247a4f48e..5883551b1ee8 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -33,6 +33,7 @@ struct ipv6_devconf { __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; + __s32 accept_ra_min_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF @@ -199,14 +200,7 @@ struct inet6_cork { u8 tclass; }; -/** - * struct ipv6_pinfo - ipv6 private area - * - * In the struct sock hierarchy (tcp6_sock, upd6_sock, etc) - * this _must_ be the last member, so that inet6_sk_generic - * is able to calculate its offset from the base struct sock - * by using the struct proto->slab_obj_size member. -acme - */ +/* struct ipv6_pinfo - ipv6 private area */ struct ipv6_pinfo { struct in6_addr saddr; struct in6_pktinfo sticky_pktinfo; @@ -306,19 +300,19 @@ struct raw6_sock { __u32 offset; /* checksum offset */ struct icmp6_filter filter; __u32 ip6mr_table; - /* ipv6_pinfo has to be the last member of raw6_sock, see inet6_sk_generic */ + struct ipv6_pinfo inet6; }; struct udp6_sock { struct udp_sock udp; - /* ipv6_pinfo has to be the last member of udp6_sock, see inet6_sk_generic */ + struct ipv6_pinfo inet6; }; struct tcp6_sock { struct tcp_sock tcp; - /* ipv6_pinfo has to be the last member of tcp6_sock, see inet6_sk_generic */ + struct ipv6_pinfo inet6; }; diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 310f85903c91..dc2844b071c2 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -625,6 +625,12 @@ do { \ WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirq_context)); \ } while (0) +#define lockdep_assert_no_hardirq() \ +do { \ + WARN_ON_ONCE(__lockdep_enabled && (this_cpu_read(hardirq_context) || \ + !this_cpu_read(hardirqs_enabled))); \ +} while (0) + #define lockdep_assert_preemption_enabled() \ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ @@ -659,6 +665,7 @@ do { \ # define lockdep_assert_irqs_enabled() do { } while (0) # define lockdep_assert_irqs_disabled() do { } while (0) # define lockdep_assert_in_irq() do { } while (0) +# define lockdep_assert_no_hardirq() do { } while (0) # define lockdep_assert_preemption_enabled() do { } while (0) # define lockdep_assert_preemption_disabled() do { } while (0) diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index af796986baee..f5b7352afaac 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -317,7 +317,7 @@ LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority) LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk) LSM_HOOK(void, LSM_RET_VOID, sk_clone_security, const struct sock *sk, struct sock *newsk) -LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, struct sock *sk, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, const struct sock *sk, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, sock_graft, struct sock *sk, struct socket *parent) LSM_HOOK(int, 0, inet_conn_request, const struct sock *sk, struct sk_buff *skb, struct request_sock *req) diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 0f06c2287b52..9b54c4f0677f 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -25,6 +25,7 @@ #define MARVELL_PHY_ID_88X3310 0x002b09a0 #define MARVELL_PHY_ID_88E2110 0x002b09b0 #define MARVELL_PHY_ID_88X2222 0x01410f10 +#define MARVELL_PHY_ID_88Q2110 0x002b0980 /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 diff --git a/include/linux/mdio.h b/include/linux/mdio.h index c1b7008826e5..8fa23bdcedbf 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -537,6 +537,8 @@ static inline void mii_c73_mod_linkmode(unsigned long *adv, u16 *lpa) int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); +int __mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, + u16 set); int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set); @@ -564,6 +566,30 @@ int mdiobus_c45_modify(struct mii_bus *bus, int addr, int devad, u32 regnum, int mdiobus_c45_modify_changed(struct mii_bus *bus, int addr, int devad, u32 regnum, u16 mask, u16 set); +static inline int __mdiodev_read(struct mdio_device *mdiodev, u32 regnum) +{ + return __mdiobus_read(mdiodev->bus, mdiodev->addr, regnum); +} + +static inline int __mdiodev_write(struct mdio_device *mdiodev, u32 regnum, + u16 val) +{ + return __mdiobus_write(mdiodev->bus, mdiodev->addr, regnum, val); +} + +static inline int __mdiodev_modify(struct mdio_device *mdiodev, u32 regnum, + u16 mask, u16 set) +{ + return __mdiobus_modify(mdiodev->bus, mdiodev->addr, regnum, mask, set); +} + +static inline int __mdiodev_modify_changed(struct mdio_device *mdiodev, + u32 regnum, u16 mask, u16 set) +{ + return __mdiobus_modify_changed(mdiodev->bus, mdiodev->addr, regnum, + mask, set); +} + static inline int mdiodev_read(struct mdio_device *mdiodev, u32 regnum) { return mdiobus_read(mdiodev->bus, mdiodev->addr, regnum); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5818af8eca5a..dbf26bc89dd4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -284,6 +284,11 @@ struct mem_cgroup { atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; + /* + * Hint of reclaim pressure for socket memroy management. Note + * that this indicator should NOT be used in legacy cgroup mode + * where socket memory is accounted/charged separately. + */ unsigned long socket_pressure; /* Legacy tcp memory accounting */ @@ -1727,8 +1732,8 @@ void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) - return true; + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return !!memcg->tcpmem_pressure; do { if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6646634a0b9d..27f42f713c89 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -33,6 +33,7 @@ #ifndef MLX4_DEVICE_H #define MLX4_DEVICE_H +#include <linux/auxiliary_bus.h> #include <linux/if_ether.h> #include <linux/pci.h> #include <linux/completion.h> @@ -889,6 +890,12 @@ struct mlx4_dev { u8 uar_page_shift; }; +struct mlx4_adev { + struct auxiliary_device adev; + struct mlx4_dev *mdev; + int idx; +}; + struct mlx4_clock_params { u64 offset; u8 bar; @@ -1087,6 +1094,19 @@ static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset) (offset & (PAGE_SIZE - 1)); } +static inline int mlx4_is_bonded(struct mlx4_dev *dev) +{ + return !!(dev->flags & MLX4_FLAG_BONDED); +} + +static inline int mlx4_is_mf_bonded(struct mlx4_dev *dev) +{ + return (mlx4_is_bonded(dev) && mlx4_is_mfunc(dev)); +} + +int mlx4_queue_bond_work(struct mlx4_dev *dev, int is_bonded, u8 v2p_p1, + u8 v2p_p2); + int mlx4_pd_alloc(struct mlx4_dev *dev, u32 *pdn); void mlx4_pd_free(struct mlx4_dev *dev, u32 pdn); int mlx4_xrcd_alloc(struct mlx4_dev *dev, u32 *xrcdn); diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 1834c8fad12e..69825223081f 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -34,8 +34,12 @@ #define MLX4_DRIVER_H #include <net/devlink.h> +#include <linux/auxiliary_bus.h> +#include <linux/notifier.h> #include <linux/mlx4/device.h> +#define MLX4_ADEV_NAME "mlx4_core" + struct mlx4_dev; #define MLX4_MAC_MASK 0xffffffffffffULL @@ -54,41 +58,19 @@ enum { MLX4_INTFF_BONDING = 1 << 0 }; -struct mlx4_interface { - void * (*add) (struct mlx4_dev *dev); - void (*remove)(struct mlx4_dev *dev, void *context); - void (*event) (struct mlx4_dev *dev, void *context, - enum mlx4_dev_event event, unsigned long param); - void * (*get_dev)(struct mlx4_dev *dev, void *context, u8 port); - void (*activate)(struct mlx4_dev *dev, void *context); - struct list_head list; +struct mlx4_adrv { + struct auxiliary_driver adrv; enum mlx4_protocol protocol; int flags; }; -int mlx4_register_interface(struct mlx4_interface *intf); -void mlx4_unregister_interface(struct mlx4_interface *intf); - -int mlx4_bond(struct mlx4_dev *dev); -int mlx4_unbond(struct mlx4_dev *dev); -static inline int mlx4_is_bonded(struct mlx4_dev *dev) -{ - return !!(dev->flags & MLX4_FLAG_BONDED); -} - -static inline int mlx4_is_mf_bonded(struct mlx4_dev *dev) -{ - return (mlx4_is_bonded(dev) && mlx4_is_mfunc(dev)); -} - -struct mlx4_port_map { - u8 port1; - u8 port2; -}; - -int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p); +int mlx4_register_auxiliary_driver(struct mlx4_adrv *madrv); +void mlx4_unregister_auxiliary_driver(struct mlx4_adrv *madrv); -void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port); +int mlx4_register_event_notifier(struct mlx4_dev *dev, + struct notifier_block *nb); +int mlx4_unregister_event_notifier(struct mlx4_dev *dev, + struct notifier_block *nb); struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 80cc12a9a531..4d5be378fa8c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -364,6 +364,8 @@ enum mlx5_event { enum mlx5_driver_event { MLX5_DRIVER_EVENT_TYPE_TRAP = 0, MLX5_DRIVER_EVENT_UPLINK_NETDEV, + MLX5_DRIVER_EVENT_MACSEC_SA_ADDED, + MLX5_DRIVER_EVENT_MACSEC_SA_DELETED, }; enum { @@ -1208,9 +1210,7 @@ enum mlx5_cap_type { MLX5_CAP_FLOW_TABLE, MLX5_CAP_ESWITCH_FLOW_TABLE, MLX5_CAP_ESWITCH, - MLX5_CAP_RESERVED, - MLX5_CAP_VECTOR_CALC, - MLX5_CAP_QOS, + MLX5_CAP_QOS = 0xc, MLX5_CAP_DEBUG, MLX5_CAP_RESERVED_14, MLX5_CAP_DEV_MEM, @@ -1220,7 +1220,6 @@ enum mlx5_cap_type { MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, MLX5_CAP_CRYPTO = 0x1a, - MLX5_CAP_DEV_SHAMPO = 0x1d, MLX5_CAP_MACSEC = 0x1f, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, @@ -1239,7 +1238,6 @@ enum mlx5_pcam_feature_groups { enum mlx5_mcam_reg_groups { MLX5_MCAM_REGS_FIRST_128 = 0x0, - MLX5_MCAM_REGS_0x9080_0x90FF = 0x1, MLX5_MCAM_REGS_0x9100_0x917F = 0x2, MLX5_MCAM_REGS_NUM = 0x3, }; @@ -1279,10 +1277,6 @@ enum mlx5_qcam_feature_groups { MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->cur, cap) -#define MLX5_CAP_ETH_MAX(mdev, cap) \ - MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->max, cap) - #define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS]->cur, cap) @@ -1305,77 +1299,40 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP64_FLOWTABLE(mdev, cap) \ MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca[MLX5_CAP_FLOW_TABLE]->cur, cap) -#define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ - MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE]->max, cap) - #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap) -#define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap) - #define MLX5_CAP_FLOWTABLE_NIC_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit.cap) -#define MLX5_CAP_FLOWTABLE_NIC_TX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit.cap) - #define MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_sniffer.cap) -#define MLX5_CAP_FLOWTABLE_SNIFFER_RX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_sniffer.cap) - #define MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_sniffer.cap) -#define MLX5_CAP_FLOWTABLE_SNIFFER_TX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_sniffer.cap) - #define MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_rdma.cap) -#define MLX5_CAP_FLOWTABLE_RDMA_RX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_rdma.cap) - #define MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_rdma.cap) -#define MLX5_CAP_FLOWTABLE_RDMA_TX_MAX(mdev, cap) \ - MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_rdma.cap) - #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap) -#define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \ - MLX5_GET(flow_table_eswitch_cap, \ - mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->max, cap) - #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap) -#define MLX5_CAP_ESW_FLOWTABLE_FDB_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_nic_esw_fdb.cap) - #define MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_egress.cap) -#define MLX5_CAP_ESW_EGRESS_ACL_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_egress.cap) - #define MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_ingress.cap) -#define MLX5_CAP_ESW_INGRESS_ACL_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_ingress.cap) - #define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap) -#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2_MAX(mdev, cap) \ - MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, ft_field_support_2_esw_fdb.cap) - #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) @@ -1384,10 +1341,6 @@ enum mlx5_qcam_feature_groups { MLX5_GET64(flow_table_eswitch_cap, \ (mdev)->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap) -#define MLX5_CAP_ESW_MAX(mdev, cap) \ - MLX5_GET(e_switch_cap, \ - mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap) - #define MLX5_CAP_PORT_SELECTION(mdev, cap) \ MLX5_GET(port_selection_cap, \ mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->cur, cap) @@ -1400,26 +1353,15 @@ enum mlx5_qcam_feature_groups { MLX5_GET(adv_virtualization_cap, \ mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->cur, cap) -#define MLX5_CAP_ADV_VIRTUALIZATION_MAX(mdev, cap) \ - MLX5_GET(adv_virtualization_cap, \ - mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->max, cap) - #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) -#define MLX5_CAP_FLOWTABLE_PORT_SELECTION_MAX(mdev, cap) \ - MLX5_CAP_PORT_SELECTION_MAX(mdev, flow_table_properties_port_selection.cap) - #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) #define MLX5_CAP_ODP_MAX(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap) -#define MLX5_CAP_VECTOR_CALC(mdev, cap) \ - MLX5_GET(vector_calc_cap, \ - mdev->caps.hca[MLX5_CAP_VECTOR_CALC]->cur, cap) - #define MLX5_CAP_QOS(mdev, cap)\ MLX5_GET(qos_cap, mdev->caps.hca[MLX5_CAP_QOS]->cur, cap) @@ -1436,10 +1378,6 @@ enum mlx5_qcam_feature_groups { MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_FIRST_128], \ mng_access_reg_cap_mask.access_regs.reg) -#define MLX5_CAP_MCAM_REG1(mdev, reg) \ - MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9080_0x90FF], \ - mng_access_reg_cap_mask.access_regs1.reg) - #define MLX5_CAP_MCAM_REG2(mdev, reg) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \ mng_access_reg_cap_mask.access_regs2.reg) @@ -1485,9 +1423,6 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_CRYPTO(mdev, cap)\ MLX5_GET(crypto_cap, (mdev)->caps.hca[MLX5_CAP_CRYPTO]->cur, cap) -#define MLX5_CAP_DEV_SHAMPO(mdev, cap)\ - MLX5_GET(shampo_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_SHAMPO], cap) - #define MLX5_CAP_MACSEC(mdev, cap)\ MLX5_GET(macsec_cap, (mdev)->caps.hca[MLX5_CAP_MACSEC]->cur, cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 25d0528f9219..3033bbaeac81 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -134,6 +134,7 @@ enum { MLX5_REG_PCAM = 0x507f, MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, + MLX5_REG_MTCAP = 0x9009, MLX5_REG_MTMP = 0x900A, MLX5_REG_MCIA = 0x9014, MLX5_REG_MFRL = 0x9028, @@ -287,18 +288,23 @@ struct mlx5_cmd_stats { struct mlx5_cmd { struct mlx5_nb nb; + /* members which needs to be queried or reinitialized each reload */ + struct { + u16 cmdif_rev; + u8 log_sz; + u8 log_stride; + int max_reg_cmds; + unsigned long bitmask; + struct semaphore sem; + struct semaphore pages_sem; + struct semaphore throttle_sem; + } vars; enum mlx5_cmdif_state state; void *cmd_alloc_buf; dma_addr_t alloc_dma; int alloc_size; void *cmd_buf; dma_addr_t dma; - u16 cmdif_rev; - u8 log_sz; - u8 log_stride; - int max_reg_cmds; - int events; - u32 __iomem *vector; /* protect command queue allocations */ @@ -308,12 +314,8 @@ struct mlx5_cmd { */ spinlock_t token_lock; u8 token; - unsigned long bitmask; char wq_name[MLX5_CMD_WQ_MAX_NAME]; struct workqueue_struct *wq; - struct semaphore sem; - struct semaphore pages_sem; - struct semaphore throttle_sem; int mode; u16 allowed_opcode; struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS]; @@ -321,7 +323,7 @@ struct mlx5_cmd { struct mlx5_cmd_debug dbg; struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES]; int checksum_disabled; - struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX]; + struct xarray stats; }; struct mlx5_cmd_mailbox { @@ -501,7 +503,7 @@ struct mlx5_events; struct mlx5_mpfs; struct mlx5_eswitch; struct mlx5_lag; -struct mlx5_devcom; +struct mlx5_devcom_dev; struct mlx5_fw_reset; struct mlx5_eq_table; struct mlx5_irq_table; @@ -618,7 +620,7 @@ struct mlx5_priv { struct mlx5_core_sriov sriov; struct mlx5_lag *lag; u32 flags; - struct mlx5_devcom *devcom; + struct mlx5_devcom_dev *devc; struct mlx5_fw_reset *fw_reset; struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; @@ -725,7 +727,6 @@ struct mlx5_fw_tracer; struct mlx5_vxlan; struct mlx5_geneve; struct mlx5_hv_vhca; -struct mlx5_thermal; #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity)) #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) @@ -804,7 +805,15 @@ struct mlx5_core_dev { struct mlx5_rsc_dump *rsc_dump; u32 vsc_addr; struct mlx5_hv_vhca *hv_vhca; - struct mlx5_thermal *thermal; + struct mlx5_hwmon *hwmon; + u64 num_block_tc; + u64 num_block_ipsec; +#ifdef CONFIG_MLX5_MACSEC + struct mlx5_macsec_fs *macsec_fs; + /* MACsec notifier chain to sync MACsec core and IB database */ + struct blocking_notifier_head macsec_nh; +#endif + u64 num_ipsec_offloads; }; struct mlx5_db { @@ -1018,7 +1027,6 @@ bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev); void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev); -int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); @@ -1055,7 +1063,7 @@ void mlx5_unregister_debugfs(void); void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn); +int mlx5_comp_eqn_get(struct mlx5_core_dev *dev, u16 vecidx, int *eqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); @@ -1105,9 +1113,8 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg, bool map_wc, bool fast_path); void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg); -unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev); -struct cpumask * -mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector); +unsigned int mlx5_comp_vectors_max(struct mlx5_core_dev *dev); +int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector); unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev); int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index, u8 roce_version, u8 roce_l3_type, const u8 *gid, @@ -1320,6 +1327,52 @@ static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev) return mlx5_is_roce_on(dev); } +#ifdef CONFIG_MLX5_MACSEC +static inline bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev) +{ + if (!(MLX5_CAP_GEN_64(mdev, general_obj_types) & + MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD)) + return false; + + if (!MLX5_CAP_GEN(mdev, log_max_dek)) + return false; + + if (!MLX5_CAP_MACSEC(mdev, log_max_macsec_offload)) + return false; + + if (!MLX5_CAP_FLOWTABLE_NIC_RX(mdev, macsec_decrypt) || + !MLX5_CAP_FLOWTABLE_NIC_RX(mdev, reformat_remove_macsec)) + return false; + + if (!MLX5_CAP_FLOWTABLE_NIC_TX(mdev, macsec_encrypt) || + !MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_macsec)) + return false; + + if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_encrypt) && + !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_encrypt)) + return false; + + if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_decrypt) && + !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_decrypt)) + return false; + + return true; +} + +#define NIC_RDMA_BOTH_DIRS_CAPS (MLX5_FT_NIC_RX_2_NIC_RX_RDMA | MLX5_FT_NIC_TX_RDMA_2_NIC_TX) + +static inline bool mlx5_is_macsec_roce_supported(struct mlx5_core_dev *mdev) +{ + if (((MLX5_CAP_GEN_2(mdev, flow_table_type_2_type) & + NIC_RDMA_BOTH_DIRS_CAPS) != NIC_RDMA_BOTH_DIRS_CAPS) || + !MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, max_modify_header_actions) || + !mlx5e_is_macsec_device(mdev) || !mdev->macsec_fs) + return false; + + return true; +} +#endif + enum { MLX5_OCTWORD = 16, }; diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index e2701ed0200e..950d2431a53c 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -144,6 +144,9 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \ ESW_TUN_OPTS_OFFSET + 1) +/* reuse tun_opts for the mapped ipsec obj id when tun_id is 0 (invalid) */ +#define ESW_IPSEC_RX_MAPPED_ID_MASK GENMASK(ESW_TUN_OPTS_BITS - 1, 0) + u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 2cb404c7ea13..1e00c2436377 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -105,15 +105,19 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS, MLX5_FLOW_NAMESPACE_RDMA_RX_IPSEC, MLX5_FLOW_NAMESPACE_RDMA_TX_IPSEC, + MLX5_FLOW_NAMESPACE_RDMA_RX_MACSEC, + MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC, }; enum { FDB_BYPASS_PATH, + FDB_CRYPTO_INGRESS, FDB_TC_OFFLOAD, FDB_FT_OFFLOAD, FDB_TC_MISS, FDB_BR_OFFLOAD, FDB_SLOW_PATH, + FDB_CRYPTO_EGRESS, FDB_PER_VPORT, }; diff --git a/include/linux/mlx5/macsec.h b/include/linux/mlx5/macsec.h new file mode 100644 index 000000000000..f7ff4c2a95d0 --- /dev/null +++ b/include/linux/mlx5/macsec.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */ + +#ifndef MLX5_MACSEC_H +#define MLX5_MACSEC_H + +#ifdef CONFIG_MLX5_MACSEC +struct mlx5_macsec_event_data { + struct mlx5_macsec_fs *macsec_fs; + void *macdev; + u32 fs_id; + bool is_tx; +}; + +int mlx5_macsec_add_roce_rule(void *macdev, const struct sockaddr *addr, u16 gid_idx, + struct list_head *tx_rules_list, struct list_head *rx_rules_list, + struct mlx5_macsec_fs *macsec_fs); + +void mlx5_macsec_del_roce_rule(u16 gid_idx, struct mlx5_macsec_fs *macsec_fs, + struct list_head *tx_rules_list, struct list_head *rx_rules_list); + +void mlx5_macsec_add_roce_sa_rules(u32 fs_id, const struct sockaddr *addr, u16 gid_idx, + struct list_head *tx_rules_list, + struct list_head *rx_rules_list, + struct mlx5_macsec_fs *macsec_fs, bool is_tx); + +void mlx5_macsec_del_roce_sa_rules(u32 fs_id, struct mlx5_macsec_fs *macsec_fs, + struct list_head *tx_rules_list, + struct list_head *rx_rules_list, bool is_tx); + +#endif +#endif /* MLX5_MACSEC_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 33344a71c3e3..fc3db401f8a2 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -65,9 +65,11 @@ enum { enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, + MLX5_SET_HCA_CAP_OP_MOD_ETHERNET_OFFLOADS = 0x1, MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, MLX5_SET_HCA_CAP_OP_MOD_ROCE = 0x4, + MLX5_SET_HCA_CAP_OP_MOD_IPSEC = 0x15, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2 = 0x20, MLX5_SET_HCA_CAP_OP_MOD_PORT_SELECTION = 0x25, }; @@ -464,10 +466,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reformat_add_esp_trasport[0x1]; u8 reformat_l2_to_l3_esp_tunnel[0x1]; - u8 reserved_at_42[0x1]; + u8 reformat_add_esp_transport_over_udp[0x1]; u8 reformat_del_esp_trasport[0x1]; u8 reformat_l3_esp_tunnel_to_l2[0x1]; - u8 reserved_at_45[0x1]; + u8 reformat_del_esp_transport_over_udp[0x1]; u8 execute_aso[0x1]; u8 reserved_at_47[0x19]; @@ -1314,33 +1316,6 @@ struct mlx5_ifc_odp_cap_bits { u8 reserved_at_120[0x6E0]; }; -struct mlx5_ifc_calc_op { - u8 reserved_at_0[0x10]; - u8 reserved_at_10[0x9]; - u8 op_swap_endianness[0x1]; - u8 op_min[0x1]; - u8 op_xor[0x1]; - u8 op_or[0x1]; - u8 op_and[0x1]; - u8 op_max[0x1]; - u8 op_add[0x1]; -}; - -struct mlx5_ifc_vector_calc_cap_bits { - u8 calc_matrix[0x1]; - u8 reserved_at_1[0x1f]; - u8 reserved_at_20[0x8]; - u8 max_vec_count[0x8]; - u8 reserved_at_30[0xd]; - u8 max_chunk_size[0x3]; - struct mlx5_ifc_calc_op calc0; - struct mlx5_ifc_calc_op calc1; - struct mlx5_ifc_calc_op calc2; - struct mlx5_ifc_calc_op calc3; - - u8 reserved_at_c0[0x720]; -}; - struct mlx5_ifc_tls_cap_bits { u8 tls_1_2_aes_gcm_128[0x1]; u8 tls_1_3_aes_gcm_128[0x1]; @@ -3435,20 +3410,6 @@ struct mlx5_ifc_roce_addr_layout_bits { u8 reserved_at_e0[0x20]; }; -struct mlx5_ifc_shampo_cap_bits { - u8 reserved_at_0[0x3]; - u8 shampo_log_max_reservation_size[0x5]; - u8 reserved_at_8[0x3]; - u8 shampo_log_min_reservation_size[0x5]; - u8 shampo_min_mss_size[0x10]; - - u8 reserved_at_20[0x3]; - u8 shampo_max_log_headers_entry_size[0x5]; - u8 reserved_at_28[0x18]; - - u8 reserved_at_40[0x7c0]; -}; - struct mlx5_ifc_crypto_cap_bits { u8 reserved_at_0[0x3]; u8 synchronize_dek[0x1]; @@ -3484,16 +3445,15 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; struct mlx5_ifc_port_selection_cap_bits port_selection_cap; - struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; struct mlx5_ifc_qos_cap_bits qos_cap; struct mlx5_ifc_debug_cap_bits debug_cap; struct mlx5_ifc_fpga_cap_bits fpga_cap; struct mlx5_ifc_tls_cap_bits tls_cap; struct mlx5_ifc_device_mem_cap_bits device_mem_cap; struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap; - struct mlx5_ifc_shampo_cap_bits shampo_cap; struct mlx5_ifc_macsec_cap_bits macsec_cap; struct mlx5_ifc_crypto_cap_bits crypto_cap; + struct mlx5_ifc_ipsec_cap_bits ipsec_cap; u8 reserved_at_0[0x8000]; }; @@ -6665,9 +6625,12 @@ enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4 = 0x5, MLX5_REFORMAT_TYPE_L2_TO_L3_ESP_TUNNEL = 0x6, + MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV4 = 0x7, MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT = 0x8, MLX5_REFORMAT_TYPE_L3_ESP_TUNNEL_TO_L2 = 0x9, + MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT_OVER_UDP = 0xa, MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6 = 0xb, + MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV6 = 0xc, MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, MLX5_REFORMAT_TYPE_ADD_MACSEC = 0x11, @@ -10193,7 +10156,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mrtc[0x1]; u8 regs_44_to_32[0xd]; - u8 regs_31_to_0[0x20]; + u8 regs_31_to_10[0x16]; + u8 mtmp[0x1]; + u8 regs_8_to_0[0x9]; }; struct mlx5_ifc_mcam_access_reg_bits1 { @@ -10853,8 +10818,9 @@ enum { MLX5_MFRL_REG_RESET_STATE_IDLE = 0, MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1, MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS = 2, - MLX5_MFRL_REG_RESET_STATE_TIMEOUT = 3, + MLX5_MFRL_REG_RESET_STATE_NEG_TIMEOUT = 3, MLX5_MFRL_REG_RESET_STATE_NACK = 4, + MLX5_MFRL_REG_RESET_STATE_UNLOAD_TIMEOUT = 5, }; enum { @@ -10946,6 +10912,15 @@ struct mlx5_ifc_mrtc_reg_bits { u8 time_l[0x20]; }; +struct mlx5_ifc_mtcap_reg_bits { + u8 reserved_at_0[0x19]; + u8 sensor_count[0x7]; + + u8 reserved_at_20[0x20]; + + u8 sensor_map[0x40]; +}; + struct mlx5_ifc_mtmp_reg_bits { u8 reserved_at_0[0x14]; u8 sensor_index[0xc]; @@ -11033,6 +11008,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mfrl_reg_bits mfrl_reg; struct mlx5_ifc_mtutc_reg_bits mtutc_reg; struct mlx5_ifc_mrtc_reg_bits mrtc_reg; + struct mlx5_ifc_mtcap_reg_bits mtcap_reg; struct mlx5_ifc_mtmp_reg_bits mtmp_reg; u8 reserved_at_0[0x60e0]; }; diff --git a/include/linux/net.h b/include/linux/net.h index 41c608c1b02c..c9b4a63791a4 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -123,7 +123,7 @@ struct socket { struct file *file; struct sock *sk; - const struct proto_ops *ops; + const struct proto_ops *ops; /* Might change with IPV6_ADDRFORM or MPTCP. */ struct socket_wq wq; }; diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h index fd67f3cc0c4b..eb01c37e71e0 100644 --- a/include/linux/net_tstamp.h +++ b/include/linux/net_tstamp.h @@ -5,12 +5,23 @@ #include <uapi/linux/net_tstamp.h> +enum hwtstamp_source { + HWTSTAMP_SOURCE_NETDEV, + HWTSTAMP_SOURCE_PHYLIB, +}; + /** * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config * * @flags: see struct hwtstamp_config * @tx_type: see struct hwtstamp_config * @rx_filter: see struct hwtstamp_config + * @ifr: pointer to ifreq structure from the original ioctl request, to pass to + * a legacy implementation of a lower driver + * @copied_to_user: request was passed to a legacy implementation which already + * copied the ioctl request back to user space + * @source: indication whether timestamps should come from the netdev or from + * an attached phylib PHY * * Prefer using this structure for in-kernel processing of hardware * timestamping configuration, over the inextensible struct hwtstamp_config @@ -20,6 +31,9 @@ struct kernel_hwtstamp_config { int flags; int tx_type; int rx_filter; + struct ifreq *ifr; + bool copied_to_user; + enum hwtstamp_source source; }; static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg, @@ -30,4 +44,20 @@ static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kern kernel_cfg->rx_filter = cfg->rx_filter; } +static inline void hwtstamp_config_from_kernel(struct hwtstamp_config *cfg, + const struct kernel_hwtstamp_config *kernel_cfg) +{ + cfg->flags = kernel_cfg->flags; + cfg->tx_type = kernel_cfg->tx_type; + cfg->rx_filter = kernel_cfg->rx_filter; +} + +static inline bool kernel_hwtstamp_config_changed(const struct kernel_hwtstamp_config *a, + const struct kernel_hwtstamp_config *b) +{ + return a->flags != b->flags || + a->tx_type != b->tx_type || + a->rx_filter != b->rx_filter; +} + #endif /* _LINUX_NET_TIMESTAMPING_H_ */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b828c7a75be2..0896aaa91dd7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -40,7 +40,6 @@ #include <net/dcbnl.h> #endif #include <net/netprio_cgroup.h> -#include <net/xdp.h> #include <linux/netdev_features.h> #include <linux/neighbour.h> @@ -57,6 +56,7 @@ struct netpoll_info; struct device; struct ethtool_ops; +struct kernel_hwtstamp_config; struct phy_device; struct dsa_port; struct ip_tunnel_parm; @@ -76,8 +76,12 @@ struct udp_tunnel_nic_info; struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; +struct xdp_frame; +struct xdp_metadata_ops; struct xdp_md; +typedef u32 xdp_features_t; + void synchronize_net(void); void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -782,32 +786,6 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, #endif #endif /* CONFIG_RPS */ -/* This structure contains an instance of an RX queue. */ -struct netdev_rx_queue { - struct xdp_rxq_info xdp_rxq; -#ifdef CONFIG_RPS - struct rps_map __rcu *rps_map; - struct rps_dev_flow_table __rcu *rps_flow_table; -#endif - struct kobject kobj; - struct net_device *dev; - netdevice_tracker dev_tracker; - -#ifdef CONFIG_XDP_SOCKETS - struct xsk_buff_pool *pool; -#endif -} ____cacheline_aligned_in_smp; - -/* - * RX queue sysfs structures and functions. - */ -struct rx_queue_attribute { - struct attribute attr; - ssize_t (*show)(struct netdev_rx_queue *queue, char *buf); - ssize_t (*store)(struct netdev_rx_queue *queue, - const char *buf, size_t len); -}; - /* XPS map type and offset of the xps map within net_device->xps_maps[]. */ enum xps_map_type { XPS_CPUS = 0, @@ -1418,6 +1396,16 @@ struct netdev_net_notifier { * Get hardware timestamp based on normal/adjustable time or free running * cycle counter. This function is required if physical clock supports a * free running cycle counter. + * + * int (*ndo_hwtstamp_get)(struct net_device *dev, + * struct kernel_hwtstamp_config *kernel_config); + * Get the currently configured hardware timestamping parameters for the + * NIC device. + * + * int (*ndo_hwtstamp_set)(struct net_device *dev, + * struct kernel_hwtstamp_config *kernel_config, + * struct netlink_ext_ack *extack); + * Change the hardware timestamping parameters for NIC device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1652,12 +1640,11 @@ struct net_device_ops { ktime_t (*ndo_get_tstamp)(struct net_device *dev, const struct skb_shared_hwtstamps *hwtstamps, bool cycles); -}; - -struct xdp_metadata_ops { - int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); - int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, - enum xdp_rss_hash_type *rss_type); + int (*ndo_hwtstamp_get)(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_config); + int (*ndo_hwtstamp_set)(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_config, + struct netlink_ext_ack *extack); }; /** @@ -1708,6 +1695,9 @@ struct xdp_metadata_ops { * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN + * @IFF_SEE_ALL_HWTSTAMP_REQUESTS: device wants to see calls to + * ndo_hwtstamp_set() for all timestamp requests regardless of source, + * even if those aren't HWTSTAMP_SOURCE_NETDEV. */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1743,6 +1733,7 @@ enum netdev_priv_flags { IFF_NO_ADDRCONF = BIT_ULL(30), IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), + IFF_SEE_ALL_HWTSTAMP_REQUESTS = BIT_ULL(33), }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1930,8 +1921,7 @@ enum netdev_ml_priv_type { * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one - * @miniq_ingress: ingress/clsact qdisc specific data for - * ingress processing + * @tcx_ingress: BPF & clsact qdisc specific data for ingress processing * @ingress_queue: XXX: need comments on this one * @nf_hooks_ingress: netfilter hooks executed for ingress packets * @broadcast: hw bcast address @@ -1952,8 +1942,7 @@ enum netdev_ml_priv_type { * @xps_maps: all CPUs/RXQs maps for XPS device * * @xps_maps: XXX: need comments on this one - * @miniq_egress: clsact qdisc specific data for - * egress processing + * @tcx_egress: BPF & clsact qdisc specific data for egress processing * @nf_hooks_egress: netfilter hooks executed for egress packets * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by @@ -2045,6 +2034,8 @@ enum netdev_ml_priv_type { * receive offload (GRO) * @gro_ipv4_max_size: Maximum size of aggregated packet in generic * receive offload (GRO), for IPv4. + * @xdp_zc_max_segs: Maximum number of segments supported by AF_XDP + * zero copy driver * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. @@ -2250,11 +2241,11 @@ struct net_device { #define GRO_MAX_SIZE (8 * 65535u) unsigned int gro_max_size; unsigned int gro_ipv4_max_size; + unsigned int xdp_zc_max_segs; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; - -#ifdef CONFIG_NET_CLS_ACT - struct mini_Qdisc __rcu *miniq_ingress; +#ifdef CONFIG_NET_XGRESS + struct bpf_mprog_entry __rcu *tcx_ingress; #endif struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS @@ -2282,8 +2273,8 @@ struct net_device { #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX]; #endif -#ifdef CONFIG_NET_CLS_ACT - struct mini_Qdisc __rcu *miniq_egress; +#ifdef CONFIG_NET_XGRESS + struct bpf_mprog_entry __rcu *tcx_egress; #endif #ifdef CONFIG_NETFILTER_EGRESS struct nf_hook_entries __rcu *nf_hooks_egress; @@ -3016,6 +3007,9 @@ extern rwlock_t dev_base_lock; /* Device list lock */ if (netdev_master_upper_dev_get_rcu(slave) == (bond)) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) +#define for_each_netdev_dump(net, d, ifindex) \ + xa_for_each_start(&(net)->dev_by_index, (ifindex), (d), (ifindex)) + static inline struct net_device *next_net_device(struct net_device *dev) { struct list_head *lh; @@ -3130,8 +3124,6 @@ struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); -int dev_restart(struct net_device *dev); - static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -3830,24 +3822,6 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev, int netif_set_real_num_queues(struct net_device *dev, unsigned int txq, unsigned int rxq); -static inline struct netdev_rx_queue * -__netif_get_rx_queue(struct net_device *dev, unsigned int rxq) -{ - return dev->_rx + rxq; -} - -#ifdef CONFIG_SYSFS -static inline unsigned int get_netdev_rx_queue_index( - struct netdev_rx_queue *queue) -{ - struct net_device *dev = queue->dev; - int index = queue - dev->_rx; - - BUG_ON(index >= dev->num_rx_queues); - return index; -} -#endif - int netif_get_num_default_rss_queues(void); void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason); @@ -3933,6 +3907,11 @@ int put_user_ifreq(struct ifreq *ifr, void __user *arg); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, void __user *data, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf __user *ifc); +int generic_hwtstamp_get_lower(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_cfg); +int generic_hwtstamp_set_lower(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_cfg, + struct netlink_ext_ack *extack); int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, @@ -5102,6 +5081,11 @@ static inline bool netif_is_ovs_port(const struct net_device *dev) return dev->priv_flags & IFF_OVS_DATAPATH; } +static inline bool netif_is_any_bridge_master(const struct net_device *dev) +{ + return netif_is_bridge_master(dev) || netif_is_ovs_master(dev); +} + static inline bool netif_is_any_bridge_port(const struct net_device *dev) { return netif_is_bridge_port(dev) || netif_is_ovs_port(dev); diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d4fed4c508ca..d68644b7c299 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -11,6 +11,7 @@ #include <linux/wait.h> #include <linux/list.h> #include <linux/static_key.h> +#include <linux/module.h> #include <linux/netfilter_defs.h> #include <linux/netdevice.h> #include <linux/sockptr.h> @@ -481,6 +482,15 @@ struct nfnl_ct_hook { }; extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; +struct nf_defrag_hook { + struct module *owner; + int (*enable)(struct net *net); + void (*disable)(struct net *net); +}; + +extern const struct nf_defrag_hook __rcu *nf_defrag_v4_hook; +extern const struct nf_defrag_hook __rcu *nf_defrag_v6_hook; + /* * nf_skb_duplicated - TEE target has sent a packet * diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h index 9e937f64a1ad..81286c499325 100644 --- a/include/linux/netfilter/nf_conntrack_h323.h +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -34,10 +34,6 @@ struct nf_ct_h323_master { int get_h225_addr(struct nf_conn *ct, unsigned char *data, TransportAddress *taddr, union nf_inet_addr *addr, __be16 *port); -void nf_conntrack_h245_expect(struct nf_conn *new, - struct nf_conntrack_expect *this); -void nf_conntrack_q931_expect(struct nf_conn *new, - struct nf_conntrack_expect *this); struct nfct_h323_nat_hooks { int (*set_h245_addr)(struct sk_buff *skb, unsigned int protoff, diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index f33aa6021364..34ce5d2f37a2 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -25,7 +25,6 @@ struct nf_ct_gre_keymap { int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t); -void nf_ct_gre_keymap_flush(struct net *net); /* delete keymap entries */ void nf_ct_gre_keymap_destroy(struct nf_conn *ct); diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 9eec3f4f5351..75d7de34c908 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -50,6 +50,7 @@ struct netlink_kernel_cfg { struct mutex *cb_mutex; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); + void (*release) (struct sock *sk, unsigned long *groups); }; struct sock *__netlink_kernel_create(struct net *net, int unit, @@ -227,6 +228,11 @@ bool netlink_strict_get_check(struct sk_buff *skb); int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); +int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, + __u32 portid, __u32 group, gfp_t allocation, + int (*filter)(struct sock *dsk, + struct sk_buff *skb, void *data), + void *filter_data); int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code); int netlink_register_notifier(struct notifier_block *nb); int netlink_unregister_notifier(struct notifier_block *nb); diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index ff99cf7a5d0d..da3a6c30f6d2 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -20,12 +20,20 @@ #define DW_AN_C37_1000BASEX 4 #define DW_10GBASER 5 +/* device vendor OUI */ +#define DW_OUI_WX 0x0018fc80 + +/* dev_flag */ +#define DW_DEV_TXGBE BIT(0) + struct xpcs_id; struct dw_xpcs { struct mdio_device *mdiodev; const struct xpcs_id *id; struct phylink_pcs pcs; + phy_interface_t interface; + int dev_flag; }; int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); diff --git a/include/linux/phy.h b/include/linux/phy.h index 11c1e91563d4..1351b802ffcf 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -110,6 +110,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax + * @PHY_INTERFACE_MODE_PSGMII: Penta SGMII * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX @@ -147,6 +148,7 @@ typedef enum { PHY_INTERFACE_MODE_XGMII, PHY_INTERFACE_MODE_XLGMII, PHY_INTERFACE_MODE_MOCA, + PHY_INTERFACE_MODE_PSGMII, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, PHY_INTERFACE_MODE_100BASEX, @@ -254,6 +256,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "xlgmii"; case PHY_INTERFACE_MODE_MOCA: return "moca"; + case PHY_INTERFACE_MODE_PSGMII: + return "psgmii"; case PHY_INTERFACE_MODE_QSGMII: return "qsgmii"; case PHY_INTERFACE_MODE_TRGMII: @@ -298,6 +302,7 @@ static inline const char *phy_modes(phy_interface_t interface) #define MII_BUS_ID_SIZE 61 struct device; +struct kernel_hwtstamp_config; struct phylink; struct sfp_bus; struct sfp_upstream_ops; @@ -1104,6 +1109,39 @@ struct phy_driver { int (*led_blink_set)(struct phy_device *dev, u8 index, unsigned long *delay_on, unsigned long *delay_off); + /** + * @led_hw_is_supported: Can the HW support the given rules. + * @dev: PHY device which has the LED + * @index: Which LED of the PHY device + * @rules The core is interested in these rules + * + * Return 0 if yes, -EOPNOTSUPP if not, or an error code. + */ + int (*led_hw_is_supported)(struct phy_device *dev, u8 index, + unsigned long rules); + /** + * @led_hw_control_set: Set the HW to control the LED + * @dev: PHY device which has the LED + * @index: Which LED of the PHY device + * @rules The rules used to control the LED + * + * Returns 0, or a an error code. + */ + int (*led_hw_control_set)(struct phy_device *dev, u8 index, + unsigned long rules); + /** + * @led_hw_control_get: Get how the HW is controlling the LED + * @dev: PHY device which has the LED + * @index: Which LED of the PHY device + * @rules Pointer to the rules used to control the LED + * + * Set *@rules to how the HW is currently blinking. Returns 0 + * on success, or a error code if the current blinking cannot + * be represented in rules, or some other error happens. + */ + int (*led_hw_control_get)(struct phy_device *dev, u8 index, + unsigned long *rules); + }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) @@ -1731,10 +1769,6 @@ int phy_start_cable_test_tdr(struct phy_device *phydev, } #endif -int phy_cable_test_result(struct phy_device *phydev, u8 pair, u16 result); -int phy_cable_test_fault_length(struct phy_device *phydev, u8 pair, - u16 cm); - static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); @@ -1826,6 +1860,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); +int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev); int genphy_c45_read_eee_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); @@ -1954,6 +1989,12 @@ int phy_ethtool_set_plca_cfg(struct phy_device *phydev, int phy_ethtool_get_plca_status(struct phy_device *phydev, struct phy_plca_status *plca_st); +int __phy_hwtstamp_get(struct phy_device *phydev, + struct kernel_hwtstamp_config *config); +int __phy_hwtstamp_set(struct phy_device *phydev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); + static inline int phy_package_read(struct phy_device *phydev, u32 regnum) { struct phy_package_shared *shared = phydev->shared; diff --git a/include/linux/phylib_stubs.h b/include/linux/phylib_stubs.h new file mode 100644 index 000000000000..1279f48c8a70 --- /dev/null +++ b/include/linux/phylib_stubs.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Stubs for the Network PHY library + */ + +#include <linux/rtnetlink.h> + +struct kernel_hwtstamp_config; +struct netlink_ext_ack; +struct phy_device; + +#if IS_ENABLED(CONFIG_PHYLIB) + +extern const struct phylib_stubs *phylib_stubs; + +struct phylib_stubs { + int (*hwtstamp_get)(struct phy_device *phydev, + struct kernel_hwtstamp_config *config); + int (*hwtstamp_set)(struct phy_device *phydev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); +}; + +static inline int phy_hwtstamp_get(struct phy_device *phydev, + struct kernel_hwtstamp_config *config) +{ + /* phylib_register_stubs() and phylib_unregister_stubs() + * also run under rtnl_lock(). + */ + ASSERT_RTNL(); + + if (!phylib_stubs) + return -EOPNOTSUPP; + + return phylib_stubs->hwtstamp_get(phydev, config); +} + +static inline int phy_hwtstamp_set(struct phy_device *phydev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + /* phylib_register_stubs() and phylib_unregister_stubs() + * also run under rtnl_lock(). + */ + ASSERT_RTNL(); + + if (!phylib_stubs) + return -EOPNOTSUPP; + + return phylib_stubs->hwtstamp_set(phydev, config, extack); +} + +#else + +static inline int phy_hwtstamp_get(struct phy_device *phydev, + struct kernel_hwtstamp_config *config) +{ + return -EOPNOTSUPP; +} + +static inline int phy_hwtstamp_set(struct phy_device *phydev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +#endif diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 1817940a3418..7d07f8736431 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -9,6 +9,7 @@ struct device_node; struct ethtool_cmd; struct fwnode_handle; struct net_device; +struct phylink; enum { MLO_PAUSE_NONE, @@ -200,8 +201,6 @@ enum phylink_op_type { * struct phylink_config - PHYLINK configuration structure * @dev: a pointer to a struct device associated with the MAC * @type: operation type of PHYLINK instance - * @legacy_pre_march2020: driver has not been updated for March 2020 updates - * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. @@ -215,7 +214,6 @@ enum phylink_op_type { struct phylink_config { struct device *dev; enum phylink_op_type type; - bool legacy_pre_march2020; bool poll_fixed_state; bool mac_managed_pm; bool ovr_an_inband; @@ -225,15 +223,15 @@ struct phylink_config { unsigned long mac_capabilities; }; +void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); + /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. * @mac_select_pcs: Select a PCS for the interface mode. - * @mac_pcs_get_state: Read the current link state from the hardware. * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. * @mac_finish: finish a major reconfiguration of the interface. - * @mac_an_restart: restart 802.3z BaseX autonegotiation. * @mac_link_down: take the link down. * @mac_link_up: allow the link to come up. * @@ -245,15 +243,12 @@ struct phylink_mac_ops { struct phylink_link_state *state); struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config, phy_interface_t interface); - void (*mac_pcs_get_state)(struct phylink_config *config, - struct phylink_link_state *state); int (*mac_prepare)(struct phylink_config *config, unsigned int mode, phy_interface_t iface); void (*mac_config)(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); int (*mac_finish)(struct phylink_config *config, unsigned int mode, phy_interface_t iface); - void (*mac_an_restart)(struct phylink_config *config); void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface); void (*mac_link_up)(struct phylink_config *config, @@ -314,25 +309,6 @@ struct phylink_pcs *mac_select_pcs(struct phylink_config *config, phy_interface_t interface); /** - * mac_pcs_get_state() - Read the current inband link state from the hardware - * @config: a pointer to a &struct phylink_config. - * @state: a pointer to a &struct phylink_link_state. - * - * Read the current inband link state from the MAC PCS, reporting the - * current speed in @state->speed, duplex mode in @state->duplex, pause - * mode in @state->pause using the %MLO_PAUSE_RX and %MLO_PAUSE_TX bits, - * negotiation completion state in @state->an_complete, and link up state - * in @state->link. If possible, @state->lp_advertising should also be - * populated. - * - * Note: This is a legacy method. This function will not be called unless - * legacy_pre_march2020 is set in &struct phylink_config and there is no - * PCS attached. - */ -void mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state); - -/** * mac_prepare() - prepare to change the PHY interface mode * @config: a pointer to a &struct phylink_config. * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. @@ -368,17 +344,9 @@ int mac_prepare(struct phylink_config *config, unsigned int mode, * guaranteed to be correct, and so any mac_config() implementation must * never reference these fields. * - * Note: For legacy March 2020 drivers (drivers with legacy_pre_march2020 set - * in their &phylnk_config and which don't have a PCS), this function will be - * called on each link up event, and to also change the in-band advert. For - * non-legacy drivers, it will only be called to reconfigure the MAC for a - * "major" change in e.g. interface mode. It will not be called for changes - * in speed, duplex or pause modes or to change the in-band advertisement. - * In any case, it is strongly preferred that speed, duplex and pause settings - * are handled in the mac_link_up() method and not in this method. - * - * (this requires a rewrite - please refer to mac_link_up() for situations - * where the PCS and MAC are not tightly integrated.) + * This will only be called to reconfigure the MAC for a "major" change in + * e.g. interface mode. It will not be called for changes in speed, duplex + * or pause modes or to change the in-band advertisement. * * In all negotiation modes, as defined by @mode, @state->pause indicates the * pause settings which should be applied as follows. If %MLO_PAUSE_AN is not @@ -410,7 +378,7 @@ int mac_prepare(struct phylink_config *config, unsigned int mode, * 1000base-X or Cisco SGMII mode depending on the @state->interface * mode). In both cases, link state management (whether the link * is up or not) is performed by the MAC, and reported via the - * mac_pcs_get_state() callback. Changes in link state must be made + * pcs_get_state() callback. Changes in link state must be made * by calling phylink_mac_change(). * * Interface mode specific details are mentioned below. @@ -459,16 +427,6 @@ int mac_finish(struct phylink_config *config, unsigned int mode, phy_interface_t iface); /** - * mac_an_restart() - restart 802.3z BaseX autonegotiation - * @config: a pointer to a &struct phylink_config. - * - * Note: This is a legacy method. This function will not be called unless - * legacy_pre_march2020 is set in &struct phylink_config and there is no - * PCS attached. - */ -void mac_an_restart(struct phylink_config *config); - -/** * mac_link_down() - take the link down * @config: a pointer to a &struct phylink_config. * @mode: link autonegotiation mode @@ -520,14 +478,19 @@ struct phylink_pcs_ops; /** * struct phylink_pcs - PHYLINK PCS instance * @ops: a pointer to the &struct phylink_pcs_ops structure + * @phylink: pointer to &struct phylink_config * @neg_mode: provide PCS neg mode via "mode" argument * @poll: poll the PCS for link changes * * This structure is designed to be embedded within the PCS private data, * and will be passed between phylink and the PCS. + * + * The @phylink member is private to phylink and must not be touched by + * the PCS driver. */ struct phylink_pcs { const struct phylink_pcs_ops *ops; + struct phylink *phylink; bool neg_mode; bool poll; }; @@ -535,6 +498,10 @@ struct phylink_pcs { /** * struct phylink_pcs_ops - MAC PCS operations structure. * @pcs_validate: validate the link configuration. + * @pcs_enable: enable the PCS. + * @pcs_disable: disable the PCS. + * @pcs_pre_config: pre-mac_config method (for errata) + * @pcs_post_config: post-mac_config method (for arrata) * @pcs_get_state: read the current MAC PCS link state from the hardware. * @pcs_config: configure the MAC PCS for the selected mode and state. * @pcs_an_restart: restart 802.3z BaseX autonegotiation. @@ -544,6 +511,12 @@ struct phylink_pcs { struct phylink_pcs_ops { int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, const struct phylink_link_state *state); + int (*pcs_enable)(struct phylink_pcs *pcs); + void (*pcs_disable)(struct phylink_pcs *pcs); + void (*pcs_pre_config)(struct phylink_pcs *pcs, + phy_interface_t interface); + int (*pcs_post_config)(struct phylink_pcs *pcs, + phy_interface_t interface); void (*pcs_get_state)(struct phylink_pcs *pcs, struct phylink_link_state *state); int (*pcs_config)(struct phylink_pcs *pcs, unsigned int neg_mode, @@ -574,6 +547,18 @@ int pcs_validate(struct phylink_pcs *pcs, unsigned long *supported, const struct phylink_link_state *state); /** + * pcs_enable() - enable the PCS. + * @pcs: a pointer to a &struct phylink_pcs. + */ +int pcs_enable(struct phylink_pcs *pcs); + +/** + * pcs_disable() - disable the PCS. + * @pcs: a pointer to a &struct phylink_pcs. + */ +void pcs_disable(struct phylink_pcs *pcs); + +/** * pcs_get_state() - Read the current inband link state from the hardware * @pcs: a pointer to a &struct phylink_pcs. * @state: a pointer to a &struct phylink_link_state. @@ -585,8 +570,8 @@ int pcs_validate(struct phylink_pcs *pcs, unsigned long *supported, * in @state->link. If possible, @state->lp_advertising should also be * populated. * - * When present, this overrides mac_pcs_get_state() in &struct - * phylink_mac_ops. + * When present, this overrides pcs_get_state() in &struct + * phylink_pcs_ops. */ void pcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state); @@ -677,6 +662,7 @@ int phylink_fwnode_phy_connect(struct phylink *pl, void phylink_disconnect_phy(struct phylink *); void phylink_mac_change(struct phylink *, bool up); +void phylink_pcs_change(struct phylink_pcs *, bool up); void phylink_start(struct phylink *); void phylink_stop(struct phylink *); diff --git a/include/linux/platform_data/hirschmann-hellcreek.h b/include/linux/platform_data/hirschmann-hellcreek.h index 6a000df5541f..8748680e9e3c 100644 --- a/include/linux/platform_data/hirschmann-hellcreek.h +++ b/include/linux/platform_data/hirschmann-hellcreek.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 or MIT) */ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ /* * Hirschmann Hellcreek TSN switch platform data. * diff --git a/include/linux/ptp_mock.h b/include/linux/ptp_mock.h new file mode 100644 index 000000000000..72eb401034d9 --- /dev/null +++ b/include/linux/ptp_mock.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Mock-up PTP Hardware Clock driver for virtual network devices + * + * Copyright 2023 NXP + */ + +#ifndef _PTP_MOCK_H_ +#define _PTP_MOCK_H_ + +struct device; +struct mock_phc; + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK_MOCK) + +struct mock_phc *mock_phc_create(struct device *dev); +void mock_phc_destroy(struct mock_phc *phc); +int mock_phc_index(struct mock_phc *phc); + +#else + +static inline struct mock_phc *mock_phc_create(struct device *dev) +{ + return NULL; +} + +static inline void mock_phc_destroy(struct mock_phc *phc) +{ +} + +static inline int mock_phc_index(struct mock_phc *phc) +{ + return -1; +} + +#endif + +#endif /* _PTP_MOCK_H_ */ diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h index 90e3045b2dcb..0d3b6ed21628 100644 --- a/include/linux/qed/qed_fcoe_if.h +++ b/include/linux/qed/qed_fcoe_if.h @@ -67,9 +67,6 @@ struct qed_fcoe_cb_ops { u32 (*get_login_failures)(void *cookie); }; -void qed_fcoe_set_pf_params(struct qed_dev *cdev, - struct qed_fcoe_pf_params *params); - /** * struct qed_fcoe_ops - qed FCoE operations. * @common: common operations pointer diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 7f17acf29dda..7b949292908a 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -138,6 +138,8 @@ static inline int rcu_needs_cpu(void) return 0; } +static inline void rcu_request_urgent_qs_task(struct task_struct *t) { } + /* * Take advantage of the fact that there is only one CPU, which * allows us to ignore virtualization-based context switches. diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 56bccb5a8fde..126f6b418f6a 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -21,6 +21,7 @@ void rcu_softirq_qs(void); void rcu_note_context_switch(bool preempt); int rcu_needs_cpu(void); void rcu_cpu_stall_reset(void); +void rcu_request_urgent_qs_task(struct task_struct *t); /* * Note a virtualization-based context switch. This is simply a diff --git a/include/linux/security.h b/include/linux/security.h index bac98ea18f78..b2c38bfe5647 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1445,7 +1445,8 @@ int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u int security_sk_alloc(struct sock *sk, int family, gfp_t priority); void security_sk_free(struct sock *sk); void security_sk_clone(const struct sock *sk, struct sock *newsk); -void security_sk_classify_flow(struct sock *sk, struct flowi_common *flic); +void security_sk_classify_flow(const struct sock *sk, + struct flowi_common *flic); void security_req_classify_flow(const struct request_sock *req, struct flowi_common *flic); void security_sock_graft(struct sock*sk, struct socket *parent); @@ -1603,7 +1604,7 @@ static inline void security_sk_clone(const struct sock *sk, struct sock *newsk) { } -static inline void security_sk_classify_flow(struct sock *sk, +static inline void security_sk_classify_flow(const struct sock *sk, struct flowi_common *flic) { } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 91ed66952580..4174c4b82d13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -32,7 +32,6 @@ #include <linux/if_packet.h> #include <linux/llist.h> #include <net/flow.h> -#include <net/page_pool.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif @@ -441,8 +440,6 @@ static inline bool skb_frag_must_loop(struct page *p) copied += p_len, p++, p_off = 0, \ p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ -#define HAVE_HW_TIME_STAMP - /** * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration @@ -944,7 +941,7 @@ struct sk_buff { __u8 __mono_tc_offset[0]; /* public: */ __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; #endif @@ -993,7 +990,7 @@ struct sk_buff { __u8 csum_not_inet:1; #endif -#ifdef CONFIG_NET_SCHED +#if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif @@ -3152,22 +3149,38 @@ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) } /** - * __skb_queue_purge - empty a list + * __skb_queue_purge_reason - empty a list * @list: list to empty + * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ -static inline void __skb_queue_purge(struct sk_buff_head *list) +static inline void __skb_queue_purge_reason(struct sk_buff_head *list, + enum skb_drop_reason reason) { struct sk_buff *skb; + while ((skb = __skb_dequeue(list)) != NULL) - kfree_skb(skb); + kfree_skb_reason(skb, reason); +} + +static inline void __skb_queue_purge(struct sk_buff_head *list) +{ + __skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); +} + +void skb_queue_purge_reason(struct sk_buff_head *list, + enum skb_drop_reason reason); + +static inline void skb_queue_purge(struct sk_buff_head *list) +{ + skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } -void skb_queue_purge(struct sk_buff_head *list); unsigned int skb_rbtree_purge(struct rb_root *root); +void skb_errqueue_purge(struct sk_buff_head *list); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); @@ -3423,13 +3436,15 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } +bool napi_pp_put_page(struct page *page, bool napi_safe); + static inline void napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) { struct page *page = skb_frag_page(frag); #ifdef CONFIG_PAGE_POOL - if (recycle && page_pool_return_skb_page(page, napi_safe)) + if (recycle && napi_pp_put_page(page, napi_safe)) return; #endif put_page(page); @@ -4023,7 +4038,7 @@ __skb_header_pointer(const struct sk_buff *skb, int offset, int len, if (likely(hlen - offset >= len)) return (void *)data + offset; - if (!skb || !buffer || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) + if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; @@ -4036,6 +4051,14 @@ skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) skb_headlen(skb), buffer); } +static inline void * __must_check +skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) +{ + if (likely(skb_headlen(skb) - offset >= len)) + return skb->data + offset; + return NULL; +} + /** * skb_needs_linearize - check if we need to linearize a given skb * depending on the given device features. diff --git a/include/linux/smscphy.h b/include/linux/smscphy.h index e1c88627755a..1a6a851d2cf8 100644 --- a/include/linux/smscphy.h +++ b/include/linux/smscphy.h @@ -38,4 +38,38 @@ int smsc_phy_set_tunable(struct phy_device *phydev, struct ethtool_tunable *tuna, const void *data); int smsc_phy_probe(struct phy_device *phydev); +#define MII_LAN874X_PHY_MMD_WOL_WUCSR 0x8010 +#define MII_LAN874X_PHY_MMD_WOL_WUF_CFGA 0x8011 +#define MII_LAN874X_PHY_MMD_WOL_WUF_CFGB 0x8012 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK0 0x8021 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK1 0x8022 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK2 0x8023 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK3 0x8024 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK4 0x8025 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK5 0x8026 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK6 0x8027 +#define MII_LAN874X_PHY_MMD_WOL_WUF_MASK7 0x8028 +#define MII_LAN874X_PHY_MMD_WOL_RX_ADDRA 0x8061 +#define MII_LAN874X_PHY_MMD_WOL_RX_ADDRB 0x8062 +#define MII_LAN874X_PHY_MMD_WOL_RX_ADDRC 0x8063 +#define MII_LAN874X_PHY_MMD_MCFGR 0x8064 + +#define MII_LAN874X_PHY_PME1_SET (2 << 13) +#define MII_LAN874X_PHY_PME2_SET (2 << 11) +#define MII_LAN874X_PHY_PME_SELF_CLEAR BIT(9) +#define MII_LAN874X_PHY_WOL_PFDA_FR BIT(7) +#define MII_LAN874X_PHY_WOL_WUFR BIT(6) +#define MII_LAN874X_PHY_WOL_MPR BIT(5) +#define MII_LAN874X_PHY_WOL_BCAST_FR BIT(4) +#define MII_LAN874X_PHY_WOL_PFDAEN BIT(3) +#define MII_LAN874X_PHY_WOL_WUEN BIT(2) +#define MII_LAN874X_PHY_WOL_MPEN BIT(1) +#define MII_LAN874X_PHY_WOL_BCSTEN BIT(0) + +#define MII_LAN874X_PHY_WOL_FILTER_EN BIT(15) +#define MII_LAN874X_PHY_WOL_FILTER_MCASTTEN BIT(9) +#define MII_LAN874X_PHY_WOL_FILTER_BCSTEN BIT(8) + +#define MII_LAN874X_PHY_PME_SELF_CLEAR_DELAY 0x1000 /* 81 milliseconds */ + #endif /* __LINUX_SMSCPHY_H__ */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 06090538fe2d..ce89cc3e4913 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -76,6 +76,8 @@ | DMA_AXI_BLEN_32 | DMA_AXI_BLEN_64 \ | DMA_AXI_BLEN_128 | DMA_AXI_BLEN_256) +struct stmmac_priv; + /* Platfrom data for platform device structure's platform_data field */ struct stmmac_mdio_bus_data { @@ -204,14 +206,41 @@ struct dwmac4_addrs { u32 mtl_low_cred_offset; }; +#define STMMAC_FLAG_HAS_INTEGRATED_PCS BIT(0) +#define STMMAC_FLAG_SPH_DISABLE BIT(1) +#define STMMAC_FLAG_USE_PHY_WOL BIT(2) +#define STMMAC_FLAG_HAS_SUN8I BIT(3) +#define STMMAC_FLAG_TSO_EN BIT(4) +#define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP BIT(5) +#define STMMAC_FLAG_VLAN_FAIL_Q_EN BIT(6) +#define STMMAC_FLAG_MULTI_MSI_EN BIT(7) +#define STMMAC_FLAG_EXT_SNAPSHOT_EN BIT(8) +#define STMMAC_FLAG_INT_SNAPSHOT_EN BIT(9) +#define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI BIT(10) +#define STMMAC_FLAG_EN_TX_LPI_CLOCKGATING BIT(11) +#define STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY BIT(12) + struct plat_stmmacenet_data { int bus_id; int phy_addr; - int interface; + /* MAC ----- optional PCS ----- SerDes ----- optional PHY ----- Media + * ^ ^ + * mac_interface phy_interface + * + * mac_interface is the MAC-side interface, which may be the same + * as phy_interface if there is no intervening PCS. If there is a + * PCS, then mac_interface describes the interface mode between the + * MAC and PCS, and phy_interface describes the interface mode + * between the PCS and PHY. + */ + phy_interface_t mac_interface; + /* phy_interface is the PHY-side interface - the interface used by + * an attached PHY. + */ phy_interface_t phy_interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; - struct device_node *phylink_node; + struct fwnode_handle *port_node; struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; struct stmmac_est *est; @@ -240,12 +269,12 @@ struct plat_stmmacenet_data { u8 tx_sched_algorithm; struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; - void (*fix_mac_speed)(void *priv, unsigned int speed); + void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode); int (*fix_soc_reset)(void *priv, void __iomem *ioaddr); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); void (*speed_mode_2500)(struct net_device *ndev, void *priv); - void (*ptp_clk_freq_config)(void *priv); + void (*ptp_clk_freq_config)(struct stmmac_priv *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); struct mac_device_info *(*setup)(void *priv); @@ -266,22 +295,14 @@ struct plat_stmmacenet_data { struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; int has_gmac4; - bool has_sun8i; - bool tso_en; int rss_en; int mac_port_sel_speed; - bool en_tx_lpi_clockgating; - bool rx_clk_runs_in_lpi; int has_xgmac; - bool vlan_fail_q_en; u8 vlan_fail_q; unsigned int eee_usecs_rate; struct pci_dev *pdev; int int_snapshot_num; int ext_snapshot_num; - bool int_snapshot_en; - bool ext_snapshot_en; - bool multi_msi_en; int msi_mac_vec; int msi_wol_vec; int msi_lpi_vec; @@ -289,10 +310,7 @@ struct plat_stmmacenet_data { int msi_sfty_ue_vec; int msi_rx_base_vec; int msi_tx_base_vec; - bool use_phy_wol; - bool sph_disable; - bool serdes_up_after_phy_linkup; const struct dwmac4_addrs *dwmac4_addrs; - bool has_integrated_pcs; + unsigned int flags; }; #endif diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 91a37c99ba66..3c5efeeb024f 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -172,6 +172,8 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) return (struct tcp_request_sock *)req; } +#define TCP_RMEM_TO_WIN_SCALE 8 + struct tcp_sock { /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; @@ -238,7 +240,7 @@ struct tcp_sock { u32 window_clamp; /* Maximal window to advertise */ u32 rcv_ssthresh; /* Current window clamp */ - + u8 scaling_ratio; /* see tcp_win_from_space() */ /* Information of the most recently (s)acked skb */ struct tcp_rack { u64 mstamp; /* (Re)sent time of the skb */ @@ -562,6 +564,6 @@ void __tcp_sock_set_nodelay(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); -void tcp_sock_set_user_timeout(struct sock *sk, u32 val); +int tcp_sock_set_user_timeout(struct sock *sk, int val); #endif /* _LINUX_TCP_H */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 1e8bbdb8da90..c1a0a19d80fb 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -763,6 +763,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr); int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { @@ -809,6 +810,11 @@ bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } +static inline int +bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif enum { @@ -878,7 +884,8 @@ extern int perf_uprobe_init(struct perf_event *event, extern void perf_uprobe_destroy(struct perf_event *event); extern int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, - u64 *probe_offset, bool perf_type_tracepoint); + u64 *probe_offset, u64 *probe_addr, + bool perf_type_tracepoint); #endif extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 20d88b1defc3..287e9d83fb8b 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -29,6 +29,7 @@ #define VENDOR_ID_LINKSYS 0x13b1 #define VENDOR_ID_NVIDIA 0x0955 #define VENDOR_ID_TPLINK 0x2357 +#define VENDOR_ID_DLINK 0x2001 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); |