diff options
Diffstat (limited to 'include')
153 files changed, 2822 insertions, 799 deletions
diff --git a/include/drm/drm_hdcp.h b/include/drm/drm_hdcp.h index c6bab4986a65..fe58dbb46962 100644 --- a/include/drm/drm_hdcp.h +++ b/include/drm/drm_hdcp.h @@ -29,6 +29,9 @@ /* Slave address for the HDCP registers in the receiver */ #define DRM_HDCP_DDC_ADDR 0x3A +/* Value to use at the end of the SHA-1 bytestream used for repeaters */ +#define DRM_HDCP_SHA1_TERMINATOR 0x80 + /* HDCP register offsets for HDMI/DVI devices */ #define DRM_HDCP_DDC_BKSV 0x00 #define DRM_HDCP_DDC_RI_PRIME 0x08 diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h index 4fc9a43ac45a..aafd07388eb7 100644 --- a/include/drm/drm_modeset_lock.h +++ b/include/drm/drm_modeset_lock.h @@ -164,6 +164,8 @@ int drm_modeset_lock_all_ctx(struct drm_device *dev, * is 0, so no error checking is necessary */ #define DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx, flags, ret) \ + if (!drm_drv_uses_atomic_modeset(dev)) \ + mutex_lock(&dev->mode_config.mutex); \ drm_modeset_acquire_init(&ctx, flags); \ modeset_lock_retry: \ ret = drm_modeset_lock_all_ctx(dev, &ctx); \ @@ -172,6 +174,7 @@ modeset_lock_retry: \ /** * DRM_MODESET_LOCK_ALL_END - Helper to release and cleanup modeset locks + * @dev: drm device * @ctx: local modeset acquire context, will be dereferenced * @ret: local ret/err/etc variable to track error status * @@ -188,7 +191,7 @@ modeset_lock_retry: \ * to that failure. In both of these cases the code between BEGIN/END will not * be run, so the failure will reflect the inability to grab the locks. */ -#define DRM_MODESET_LOCK_ALL_END(ctx, ret) \ +#define DRM_MODESET_LOCK_ALL_END(dev, ctx, ret) \ modeset_lock_fail: \ if (ret == -EDEADLK) { \ ret = drm_modeset_backoff(&ctx); \ @@ -196,6 +199,8 @@ modeset_lock_fail: \ goto modeset_lock_retry; \ } \ drm_modeset_drop_locks(&ctx); \ - drm_modeset_acquire_fini(&ctx); + drm_modeset_acquire_fini(&ctx); \ + if (!drm_drv_uses_atomic_modeset(dev)) \ + mutex_unlock(&dev->mode_config.mutex); #endif /* DRM_MODESET_LOCK_H_ */ diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 64f367044e25..2f98d2fce62e 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -279,6 +279,31 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_RECVMSG, NULL) +/* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a + * fullsock and its parent fullsock cannot be traced by + * sk_to_full_sk(). + * + * e.g. sock_ops->sk is a request_sock and it is under syncookie mode. + * Its listener-sk is not attached to the rsk_listener. + * In this case, the caller holds the listener-sk (unlocked), + * set its sock_ops->sk to req_sk, and call this SOCK_OPS"_SK" with + * the listener-sk such that the cgroup-bpf-progs of the + * listener-sk will be run. + * + * Regardless of syncookie mode or not, + * calling bpf_setsockopt on listener-sk will not make sense anyway, + * so passing 'sock_ops->sk == req_sk' to the bpf prog is appropriate here. + */ +#define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ + sock_ops, \ + BPF_CGROUP_SOCK_OPS); \ + __ret; \ +}) + #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 55f694b63164..fc5c901c7542 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -34,6 +34,8 @@ struct btf_type; struct exception_table_entry; struct seq_operations; struct bpf_iter_aux_info; +struct bpf_local_storage; +struct bpf_local_storage_map; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -104,6 +106,25 @@ struct bpf_map_ops { __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); + /* Functions called by bpf_local_storage maps */ + int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, + void *owner, u32 size); + void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, + void *owner, u32 size); + struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); + + /* map_meta_equal must be implemented for maps that can be + * used as an inner map. It is a runtime check to ensure + * an inner map can be inserted to an outer map. + * + * Some properties of the inner map has been used during the + * verification time. When inserting an inner map at the runtime, + * map_meta_equal has to ensure the inserting map has the same + * properties that the verifier has used earlier. + */ + bool (*map_meta_equal)(const struct bpf_map *meta0, + const struct bpf_map *meta1); + /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; @@ -227,6 +248,9 @@ int map_check_no_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type); +bool bpf_map_meta_equal(const struct bpf_map *meta0, + const struct bpf_map *meta1); + extern const struct bpf_map_ops bpf_map_offload_ops; /* function argument constraints */ @@ -268,6 +292,7 @@ enum bpf_arg_type { ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ + __BPF_ARG_TYPE_MAX, }; /* type of values returned from helper functions */ @@ -302,13 +327,18 @@ struct bpf_func_proto { }; enum bpf_arg_type arg_type[5]; }; - int *btf_id; /* BTF ids of arguments */ - bool (*check_btf_id)(u32 btf_id, u32 arg); /* if the argument btf_id is - * valid. Often used if more - * than one btf id is permitted - * for this argument. - */ + union { + struct { + u32 *arg1_btf_id; + u32 *arg2_btf_id; + u32 *arg3_btf_id; + u32 *arg4_btf_id; + u32 *arg5_btf_id; + }; + u32 *arg_btf_id[5]; + }; int *ret_btf_id; /* return value btf_id */ + bool (*allowed)(const struct bpf_prog *prog); }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is @@ -514,6 +544,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(void); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); +void notrace __bpf_prog_enter_sleepable(void); +void notrace __bpf_prog_exit_sleepable(void); struct bpf_ksym { unsigned long start; @@ -670,16 +702,19 @@ enum bpf_jit_poke_reason { /* Descriptor of pokes pointing /into/ the JITed image. */ struct bpf_jit_poke_descriptor { - void *ip; + void *tailcall_target; + void *tailcall_bypass; + void *bypass_addr; union { struct { struct bpf_map *map; u32 key; } tail_call; }; - bool ip_stable; + bool tailcall_target_stable; u8 adj_off; u16 reason; + u32 insn_idx; }; /* reg_type info for ctx arguments */ @@ -709,6 +744,8 @@ struct bpf_prog_aux { bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; + bool sleepable; + bool tail_call_reachable; enum bpf_tramp_prog_type trampoline_prog_type; struct bpf_trampoline *trampoline; struct hlist_node tramp_hlist; @@ -723,6 +760,7 @@ struct bpf_prog_aux { struct bpf_ksym ksym; const struct bpf_prog_ops *ops; struct bpf_map **used_maps; + struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ @@ -1218,12 +1256,18 @@ typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux); +typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux, + struct seq_file *seq); +typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux, + struct bpf_link_info *info); #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; bpf_iter_attach_target_t attach_target; bpf_iter_detach_target_t detach_target; + bpf_iter_show_fdinfo_t show_fdinfo; + bpf_iter_fill_link_info_t fill_link_info; u32 ctx_arg_info_size; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; @@ -1250,6 +1294,10 @@ int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx); +void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, + struct seq_file *seq); +int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, + struct bpf_link_info *info); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); @@ -1340,8 +1388,8 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); -int btf_resolve_helper_id(struct bpf_verifier_log *log, - const struct bpf_func_proto *fn, int); +bool btf_struct_ids_match(struct bpf_verifier_log *log, + int off, u32 id, u32 need_type_id); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, @@ -1358,6 +1406,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); struct bpf_prog *bpf_prog_by_id(u32 id); +struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); #else /* !CONFIG_BPF_SYSCALL */ @@ -1637,6 +1686,7 @@ int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); +int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else @@ -1658,6 +1708,12 @@ static inline int sock_map_prog_detach(const union bpf_attr *attr, { return -EOPNOTSUPP; } + +static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, + u64 flags) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_STREAM_PARSER */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) @@ -1736,6 +1792,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; +extern const struct bpf_func_proto bpf_copy_from_user_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -1850,4 +1907,7 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +struct btf_id_set; +bool btf_id_set_contains(const struct btf_id_set *set, u32 id); + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h new file mode 100644 index 000000000000..b2c9463f36a1 --- /dev/null +++ b/include/linux/bpf_local_storage.h @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2019 Facebook + * Copyright 2020 Google LLC. + */ + +#ifndef _BPF_LOCAL_STORAGE_H +#define _BPF_LOCAL_STORAGE_H + +#include <linux/bpf.h> +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <uapi/linux/btf.h> + +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 + +struct bpf_local_storage_map_bucket { + struct hlist_head list; + raw_spinlock_t lock; +}; + +/* Thp map is not the primary owner of a bpf_local_storage_elem. + * Instead, the container object (eg. sk->sk_bpf_storage) is. + * + * The map (bpf_local_storage_map) is for two purposes + * 1. Define the size of the "local storage". It is + * the map's value_size. + * + * 2. Maintain a list to keep track of all elems such + * that they can be cleaned up during the map destruction. + * + * When a bpf local storage is being looked up for a + * particular object, the "bpf_map" pointer is actually used + * as the "key" to search in the list of elem in + * the respective bpf_local_storage owned by the object. + * + * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer + * as the searching key. + */ +struct bpf_local_storage_map { + struct bpf_map map; + /* Lookup elem does not require accessing the map. + * + * Updating/Deleting requires a bucket lock to + * link/unlink the elem from the map. Having + * multiple buckets to improve contention. + */ + struct bpf_local_storage_map_bucket *buckets; + u32 bucket_log; + u16 elem_size; + u16 cache_idx; +}; + +struct bpf_local_storage_data { + /* smap is used as the searching key when looking up + * from the object's bpf_local_storage. + * + * Put it in the same cacheline as the data to minimize + * the number of cachelines access during the cache hit case. + */ + struct bpf_local_storage_map __rcu *smap; + u8 data[] __aligned(8); +}; + +/* Linked to bpf_local_storage and bpf_local_storage_map */ +struct bpf_local_storage_elem { + struct hlist_node map_node; /* Linked to bpf_local_storage_map */ + struct hlist_node snode; /* Linked to bpf_local_storage */ + struct bpf_local_storage __rcu *local_storage; + struct rcu_head rcu; + /* 8 bytes hole */ + /* The data is stored in aother cacheline to minimize + * the number of cachelines access during a cache hit. + */ + struct bpf_local_storage_data sdata ____cacheline_aligned; +}; + +struct bpf_local_storage { + struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; + struct hlist_head list; /* List of bpf_local_storage_elem */ + void *owner; /* The object that owns the above "list" of + * bpf_local_storage_elem. + */ + struct rcu_head rcu; + raw_spinlock_t lock; /* Protect adding/removing from the "list" */ +}; + +/* U16_MAX is much more than enough for sk local storage + * considering a tcp_sock is ~2k. + */ +#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE \ + min_t(u32, \ + (KMALLOC_MAX_SIZE - MAX_BPF_STACK - \ + sizeof(struct bpf_local_storage_elem)), \ + (U16_MAX - sizeof(struct bpf_local_storage_elem))) + +#define SELEM(_SDATA) \ + container_of((_SDATA), struct bpf_local_storage_elem, sdata) +#define SDATA(_SELEM) (&(_SELEM)->sdata) + +#define BPF_LOCAL_STORAGE_CACHE_SIZE 16 + +struct bpf_local_storage_cache { + spinlock_t idx_lock; + u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE]; +}; + +#define DEFINE_BPF_STORAGE_CACHE(name) \ +static struct bpf_local_storage_cache name = { \ + .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \ +} + +u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); +void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx); + +/* Helper functions for bpf_local_storage */ +int bpf_local_storage_map_alloc_check(union bpf_attr *attr); + +struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr); + +struct bpf_local_storage_data * +bpf_local_storage_lookup(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + bool cacheit_lockit); + +void bpf_local_storage_map_free(struct bpf_local_storage_map *smap); + +int bpf_local_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type); + +void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem); + +bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_omem); + +void bpf_selem_unlink(struct bpf_local_storage_elem *selem); + +void bpf_selem_link_map(struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem); + +void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); + +struct bpf_local_storage_elem * +bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, + bool charge_mem); + +int +bpf_local_storage_alloc(void *owner, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *first_selem); + +struct bpf_local_storage_data * +bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, + void *value, u64 map_flags); + +#endif /* _BPF_LOCAL_STORAGE_H */ diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index af74712af585..aaacb6aafc87 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -17,9 +17,28 @@ #include <linux/lsm_hook_defs.h> #undef LSM_HOOK +struct bpf_storage_blob { + struct bpf_local_storage __rcu *storage; +}; + +extern struct lsm_blob_sizes bpf_lsm_blob_sizes; + int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog); +static inline struct bpf_storage_blob *bpf_inode( + const struct inode *inode) +{ + if (unlikely(!inode->i_security)) + return NULL; + + return inode->i_security + bpf_lsm_blob_sizes.lbs_inode; +} + +extern const struct bpf_func_proto bpf_inode_storage_get_proto; +extern const struct bpf_func_proto bpf_inode_storage_delete_proto; +void bpf_inode_storage_free(struct inode *inode); + #else /* !CONFIG_BPF_LSM */ static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, @@ -28,6 +47,16 @@ static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return -EOPNOTSUPP; } +static inline struct bpf_storage_blob *bpf_inode( + const struct inode *inode) +{ + return NULL; +} + +static inline void bpf_inode_storage_free(struct inode *inode) +{ +} + #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a52a5688418e..2e6f568377f1 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -107,6 +107,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) #endif +#ifdef CONFIG_BPF_LSM +BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #if defined(CONFIG_XDP_SOCKETS) BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 53c7bd568c5d..2bb48a2c4d08 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -358,6 +358,9 @@ struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ + bool has_tail_call; + bool tail_call_reachable; + bool has_ld_abs; }; /* single container for all structs diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6ad4c000661a..d0bd226d6bd9 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -30,6 +30,7 @@ #define PHY_ID_BCM57780 0x03625d90 #define PHY_ID_BCM89610 0x03625cd0 +#define PHY_ID_BCM72113 0x35905310 #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7255 0xae025120 #define PHY_ID_BCM7260 0xae025190 diff --git a/include/linux/btf.h b/include/linux/btf.h index 8b81fbb4497c..a9af5e7a7ece 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -64,8 +64,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, u32 id, u32 *res_id); const struct btf_type * btf_resolve_size(const struct btf *btf, const struct btf_type *type, - u32 *type_size, const struct btf_type **elem_type, - u32 *total_nelems); + u32 *type_size); #define for_each_member(i, struct_type, member) \ for (i = 0, member = btf_type_member(struct_type); \ diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 4867d549e3c1..57890b357f85 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -3,6 +3,11 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +struct btf_id_set { + u32 cnt; + u32 ids[]; +}; + #ifdef CONFIG_DEBUG_INFO_BTF #include <linux/compiler.h> /* for __PASTE */ @@ -62,7 +67,7 @@ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ "." #scope " " #name "; \n" \ #name ":; \n" \ -".popsection; \n"); \ +".popsection; \n"); #define BTF_ID_LIST(name) \ __BTF_ID_LIST(name, local) \ @@ -71,6 +76,13 @@ extern u32 name[]; #define BTF_ID_LIST_GLOBAL(name) \ __BTF_ID_LIST(name, globl) +/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with + * a single entry. + */ +#define BTF_ID_LIST_SINGLE(name, prefix, typename) \ + BTF_ID_LIST(name) \ + BTF_ID(prefix, typename) + /* * The BTF_ID_UNUSED macro defines 4 zero bytes. * It's used when we want to define 'unused' entry @@ -88,12 +100,57 @@ asm( \ ".zero 4 \n" \ ".popsection; \n"); +/* + * The BTF_SET_START/END macros pair defines sorted list of + * BTF IDs plus its members count, with following layout: + * + * BTF_SET_START(list) + * BTF_ID(type1, name1) + * BTF_ID(type2, name2) + * BTF_SET_END(list) + * + * __BTF_ID__set__list: + * .zero 4 + * list: + * __BTF_ID__type1__name1__3: + * .zero 4 + * __BTF_ID__type2__name2__4: + * .zero 4 + * + */ +#define __BTF_SET_START(name, scope) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +"." #scope " __BTF_ID__set__" #name "; \n" \ +"__BTF_ID__set__" #name ":; \n" \ +".zero 4 \n" \ +".popsection; \n"); + +#define BTF_SET_START(name) \ +__BTF_ID_LIST(name, local) \ +__BTF_SET_START(name, local) + +#define BTF_SET_START_GLOBAL(name) \ +__BTF_ID_LIST(name, globl) \ +__BTF_SET_START(name, globl) + +#define BTF_SET_END(name) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".size __BTF_ID__set__" #name ", .-" #name " \n" \ +".popsection; \n"); \ +extern struct btf_id_set name; + #else #define BTF_ID_LIST(name) static u32 name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED #define BTF_ID_LIST_GLOBAL(name) u32 name[1]; +#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; +#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ diff --git a/include/linux/bvec.h b/include/linux/bvec.h index ac0c7299d5b8..dd74503f7e5e 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -117,11 +117,18 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv, return true; } +static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter) +{ + iter->bi_bvec_done = 0; + iter->bi_idx++; +} + #define for_each_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ - bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len)) + (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter), \ + (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter))) /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ diff --git a/include/linux/can/core.h b/include/linux/can/core.h index e20a0cd09ba5..7da9f1f82e8e 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -2,7 +2,7 @@ /* * linux/can/core.h * - * Protoypes and definitions for CAN protocol modules using the PF_CAN core + * Prototypes and definitions for CAN protocol modules using the PF_CAN core * * Authors: Oliver Hartkopp <oliver.hartkopp@volkswagen.de> * Urs Thuermann <urs.thuermann@volkswagen.de> diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 5e3d45525bd3..ed0482b2f4b2 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -108,7 +108,7 @@ static inline bool can_skb_headroom_valid(struct net_device *dev, skb->ip_summed = CHECKSUM_UNNECESSARY; - /* preform proper loopback on capable devices */ + /* perform proper loopback on capable devices */ if (dev->flags & IFF_ECHO) skb->pkt_type = PACKET_LOOPBACK; else @@ -201,8 +201,8 @@ void can_bus_off(struct net_device *dev); void can_change_state(struct net_device *dev, struct can_frame *cf, enum can_state tx_state, enum can_state rx_state); -void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, - unsigned int idx); +int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, + unsigned int idx); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr); unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 1b78a0cfb615..f1b38088b765 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -35,6 +35,9 @@ int can_rx_offload_add_timestamp(struct net_device *dev, int can_rx_offload_add_fifo(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight); +int can_rx_offload_add_manual(struct net_device *dev, + struct can_rx_offload *offload, + unsigned int weight); int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 reg); int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index fcd84e8d88f4..999636d53cf2 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -11,14 +11,14 @@ #define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL #define DEFINE_CEPH_FEATURE(bit, incarnation, name) \ - static const uint64_t CEPH_FEATURE_##name = (1ULL<<bit); \ - static const uint64_t CEPH_FEATUREMASK_##name = \ + static const uint64_t __maybe_unused CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t __maybe_unused CEPH_FEATUREMASK_##name = \ (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* this bit is ignored but still advertised by release *when* */ #define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \ - static const uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ - static const uint64_t DEPRECATED_CEPH_FEATUREMASK_##name = \ + static const uint64_t __maybe_unused DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t __maybe_unused DEPRECATED_CEPH_FEATUREMASK_##name = \ (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* diff --git a/include/linux/compat.h b/include/linux/compat.h index d38c4d7e83bd..b354ce58966e 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -429,11 +429,11 @@ put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, compat_sigset_t v; switch (_NSIG_WORDS) { case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; - /* fall through */ + fallthrough; case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; - /* fall through */ + fallthrough; case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; - /* fall through */ + fallthrough; case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; } return copy_to_user(compat, &v, size) ? -EFAULT : 0; diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 6122efdad6ad..ea7b756b1c8f 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -22,14 +22,8 @@ /* * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. - * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute + * In the meantime, to support gcc < 5, we implement __has_attribute * by hand. - * - * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ - * depending on the compiler used to build it; however, these attributes have - * no semantic effects for sparse, so it does not matter. Also note that, - * in order to avoid sparse's warnings, even the unsupported ones must be - * defined to 0. */ #ifndef __has_attribute # define __has_attribute(x) __GCC4_has_attribute_##x diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 4b33cb385f96..6e390d58a9f8 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -11,8 +11,8 @@ # define __iomem __attribute__((noderef, address_space(__iomem))) # define __percpu __attribute__((noderef, address_space(__percpu))) # define __rcu __attribute__((noderef, address_space(__rcu))) -extern void __chk_user_ptr(const volatile void __user *); -extern void __chk_io_ptr(const volatile void __iomem *); +static inline void __chk_user_ptr(const volatile void __user *ptr) { } +static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } /* context/locking */ # define __must_hold(x) __attribute__((context(x,1,1))) # define __acquires(x) __attribute__((context(x,0,1))) diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 8f141d4c859c..a911e5d06845 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -956,8 +956,8 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, case CPUFREQ_RELATION_C: return cpufreq_table_find_index_c(policy, target_freq); default: - pr_err("%s: Invalid relation: %d\n", __func__, relation); - return -EINVAL; + WARN_ON_ONCE(1); + return 0; } } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index a2710e654b64..bf9181cef444 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -132,6 +132,7 @@ enum cpuhp_state { CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, + CPUHP_AP_CLINT_TIMER_STARTING, CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, CPUHP_AP_KVM_STARTING, @@ -141,7 +142,6 @@ enum cpuhp_state { /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, - CPUHP_AP_ARM_KVMPV_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b65909ae4e20..6175c77bf25e 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -75,12 +75,14 @@ struct cpuidle_state { }; /* Idle State Flags */ -#define CPUIDLE_FLAG_NONE (0x00) -#define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ -#define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ -#define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ -#define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ -#define CPUIDLE_FLAG_OFF BIT(4) /* disable this state by default */ +#define CPUIDLE_FLAG_NONE (0x00) +#define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ +#define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ +#define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ +#define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ +#define CPUIDLE_FLAG_OFF BIT(4) /* disable this state by default */ +#define CPUIDLE_FLAG_TLB_FLUSHED BIT(5) /* idle-state flushes TLBs */ +#define CPUIDLE_FLAG_RCU_IDLE BIT(6) /* idle-state takes care of RCU */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; diff --git a/include/linux/dax.h b/include/linux/dax.h index 6904d4e0b2e0..43b39ab9de1a 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -58,6 +58,8 @@ static inline void set_dax_synchronous(struct dax_device *dax_dev) { __set_dax_synchronous(dax_dev); } +bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, + int blocksize, sector_t start, sector_t len); /* * Check if given mapping is supported by the file / underlying device. */ @@ -104,6 +106,12 @@ static inline bool dax_synchronous(struct dax_device *dax_dev) static inline void set_dax_synchronous(struct dax_device *dax_dev) { } +static inline bool dax_supported(struct dax_device *dax_dev, + struct block_device *bdev, int blocksize, sector_t start, + sector_t len) +{ + return false; +} static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { @@ -189,14 +197,23 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) } #endif +#if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); +#else +static inline int dax_read_lock(void) +{ + return 0; +} + +static inline void dax_read_unlock(int id) +{ +} +#endif /* CONFIG_DAX */ bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, diff --git a/include/linux/device.h b/include/linux/device.h index ca18da4768e3..9e6ea8931a52 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -454,6 +454,7 @@ struct dev_links_info { * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. + * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pinctl.rst for details. * @msi_list: Hosts MSI descriptors diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 5a3ce2a24794..6e87225600ae 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -73,9 +73,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, } u64 dma_direct_get_required_mask(struct device *dev); -gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, - u64 *phys_mask); -bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 016b96b384bd..52635e91143b 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -522,8 +522,9 @@ void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot, const void *caller); void dma_common_free_remap(void *cpu_addr, size_t size); -void *dma_alloc_from_pool(struct device *dev, size_t size, - struct page **ret_page, gfp_t flags); +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t flags, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)); bool dma_free_from_pool(struct device *dev, void *start, size_t size); int diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 311aa04e7520..88cd72dfa4e0 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -5,37 +5,49 @@ #ifndef _NET_DSA_8021Q_H #define _NET_DSA_8021Q_H +#include <linux/refcount.h> #include <linux/types.h> struct dsa_switch; struct sk_buff; struct net_device; struct packet_type; +struct dsa_8021q_context; struct dsa_8021q_crosschip_link { struct list_head list; int port; - struct dsa_switch *other_ds; + struct dsa_8021q_context *other_ctx; int other_port; refcount_t refcount; }; +struct dsa_8021q_ops { + int (*vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); + int (*vlan_del)(struct dsa_switch *ds, int port, u16 vid); +}; + +struct dsa_8021q_context { + const struct dsa_8021q_ops *ops; + struct dsa_switch *ds; + struct list_head crosschip_links; + /* EtherType of RX VID, used for filtering on master interface */ + __be16 proto; +}; + #define DSA_8021Q_N_SUBVLAN 8 #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) -int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, - bool enabled); +int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); -int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links); +int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port); -int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links); +int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port); struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); @@ -56,24 +68,21 @@ bool vid_is_dsa_8021q(u16 vid); #else -int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, - bool enabled) +int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) { return 0; } -int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links) +int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port) { return 0; } -int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links) +int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port) { return 0; } diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index aa9ff9e1c0b3..8aa0c7c2608c 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -49,6 +49,10 @@ struct _ddebug { #if defined(CONFIG_DYNAMIC_DEBUG_CORE) + +/* exported for module authors to exercise >control */ +int dynamic_debug_exec_queries(const char *query, const char *modname); + int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *modname); extern int ddebug_remove_module(const char *mod_name); @@ -105,7 +109,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, static_branch_unlikely(&descriptor.key.dd_key_false) #endif -#else /* !HAVE_JUMP_LABEL */ +#else /* !CONFIG_JUMP_LABEL */ #define _DPRINTK_KEY_INIT @@ -117,7 +121,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) #endif -#endif +#endif /* CONFIG_JUMP_LABEL */ #define __dynamic_func_call(id, fmt, func, ...) do { \ DEFINE_DYNAMIC_DEBUG_METADATA(id, fmt); \ @@ -172,10 +176,11 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii) -#else +#else /* !CONFIG_DYNAMIC_DEBUG_CORE */ #include <linux/string.h> #include <linux/errno.h> +#include <linux/printk.h> static inline int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *modname) @@ -210,6 +215,13 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii); \ } while (0) -#endif + +static inline int dynamic_debug_exec_queries(const char *query, const char *modname) +{ + pr_warn("kernel not built with CONFIG_DYNAMIC_DEBUG_CORE\n"); + return 0; +} + +#endif /* !CONFIG_DYNAMIC_DEBUG_CORE */ #endif diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h index 57eac5241303..a97a12bb2c9e 100644 --- a/include/linux/efi_embedded_fw.h +++ b/include/linux/efi_embedded_fw.h @@ -8,8 +8,8 @@ #define EFI_EMBEDDED_FW_PREFIX_LEN 8 /* - * This struct and efi_embedded_fw_list are private to the efi-embedded fw - * implementation they are in this header for use by lib/test_firmware.c only! + * This struct is private to the efi-embedded fw implementation. + * They are in this header for use by lib/test_firmware.c only! */ struct efi_embedded_fw { struct list_head list; @@ -18,8 +18,6 @@ struct efi_embedded_fw { size_t length; }; -extern struct list_head efi_embedded_fw_list; - /** * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw * code to search for embedded firmwares. diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index efebbffcd5cc..159c7476b11b 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -110,15 +110,30 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs #endif /** - * syscall_enter_from_user_mode - Check and handle work before invoking - * a syscall + * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts * @regs: Pointer to currents pt_regs - * @syscall: The syscall number * * Invoked from architecture specific syscall entry code with interrupts * disabled. The calling code has to be non-instrumentable. When the - * function returns all state is correct and the subsequent functions can be - * instrumented. + * function returns all state is correct, interrupts are enabled and the + * subsequent functions can be instrumented. + * + * This handles lockdep, RCU (context tracking) and tracing state. + * + * This is invoked when there is extra architecture specific functionality + * to be done between establishing state and handling user mode entry work. + */ +void syscall_enter_from_user_mode_prepare(struct pt_regs *regs); + +/** + * syscall_enter_from_user_mode_work - Check and handle work before invoking + * a syscall + * @regs: Pointer to currents pt_regs + * @syscall: The syscall number + * + * Invoked from architecture specific syscall entry code with interrupts + * enabled after invoking syscall_enter_from_user_mode_prepare() and extra + * architecture specific work. * * Returns: The original or a modified syscall number * @@ -127,12 +142,30 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs * syscall_set_return_value() first. If neither of those are called and -1 * is returned, then the syscall will fail with ENOSYS. * - * The following functionality is handled here: + * It handles the following work items: * - * 1) Establish state (lockdep, RCU (context tracking), tracing) - * 2) TIF flag dependent invocations of arch_syscall_enter_tracehook(), + * 1) TIF flag dependent invocations of arch_syscall_enter_tracehook(), * __secure_computing(), trace_sys_enter() - * 3) Invocation of audit_syscall_entry() + * 2) Invocation of audit_syscall_entry() + */ +long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall); + +/** + * syscall_enter_from_user_mode - Establish state and check and handle work + * before invoking a syscall + * @regs: Pointer to currents pt_regs + * @syscall: The syscall number + * + * Invoked from architecture specific syscall entry code with interrupts + * disabled. The calling code has to be non-instrumentable. When the + * function returns all state is correct, interrupts are enabled and the + * subsequent functions can be instrumented. + * + * This is combination of syscall_enter_from_user_mode_prepare() and + * syscall_enter_from_user_mode_work(). + * + * Returns: The original or a modified syscall number. See + * syscall_enter_from_user_mode_work() for further explanation. */ long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 969a80211df6..060b20f0b20f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -241,6 +241,27 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, ETHTOOL_COALESCE_PKT_RATE_LOW | ETHTOOL_COALESCE_PKT_RATE_HIGH | \ ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL) +#define ETHTOOL_STAT_NOT_SET (~0ULL) + +/** + * struct ethtool_pause_stats - statistics for IEEE 802.3x pause frames + * @tx_pause_frames: transmitted pause frame count. Reported to user space + * as %ETHTOOL_A_PAUSE_STAT_TX_FRAMES. + * + * Equivalent to `30.3.4.2 aPAUSEMACCtrlFramesTransmitted` + * from the standard. + * + * @rx_pause_frames: received pause frame count. Reported to user space + * as %ETHTOOL_A_PAUSE_STAT_RX_FRAMES. Equivalent to: + * + * Equivalent to `30.3.4.3 aPAUSEMACCtrlFramesReceived` + * from the standard. + */ +struct ethtool_pause_stats { + u64 tx_pause_frames; + u64 rx_pause_frames; +}; + /** * struct ethtool_ops - optional netdev operations * @supported_coalesce_params: supported types of interrupt coalescing. @@ -282,6 +303,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * Returns a negative error code or zero. * @get_ringparam: Report ring sizes * @set_ringparam: Set ring sizes. Returns a negative error code or zero. + * @get_pause_stats: Report pause frame statistics. Drivers must not zero + * statistics which they don't report. The stats structure is initialized + * to ETHTOOL_STAT_NOT_SET indicating driver does not report statistics. * @get_pauseparam: Report pause parameters * @set_pauseparam: Set pause parameters. Returns a negative error code * or zero. @@ -418,6 +442,8 @@ struct ethtool_ops { struct ethtool_ringparam *); int (*set_ringparam)(struct net_device *, struct ethtool_ringparam *); + void (*get_pause_stats)(struct net_device *dev, + struct ethtool_pause_stats *pause_stats); void (*get_pauseparam)(struct net_device *, struct ethtool_pauseparam*); int (*set_pauseparam)(struct net_device *, diff --git a/include/linux/filter.h b/include/linux/filter.h index 0a355b005bf4..20fc24c9779a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1200,7 +1200,7 @@ static inline u16 bpf_anc_helper(const struct sock_filter *ftest) BPF_ANCILLARY(RANDOM); BPF_ANCILLARY(VLAN_TPID); } - /* Fallthrough. */ + fallthrough; default: return ftest->code; } @@ -1236,13 +1236,17 @@ struct bpf_sock_addr_kern { struct bpf_sock_ops_kern { struct sock *sk; - u32 op; union { u32 args[4]; u32 reply; u32 replylong[4]; }; - u32 is_fullsock; + struct sk_buff *syn_skb; + struct sk_buff *skb; + void *skb_data_end; + u8 op; + u8 is_fullsock; + u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that @@ -1283,6 +1287,8 @@ int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); struct bpf_sk_lookup_kern { u16 family; u16 protocol; + __be16 sport; + u16 dport; struct { __be32 saddr; __be32 daddr; @@ -1291,8 +1297,6 @@ struct bpf_sk_lookup_kern { const struct in6_addr *saddr; const struct in6_addr *daddr; } v6; - __be16 sport; - u16 dport; struct sock *selected_sk; bool no_reuseport; }; diff --git a/include/linux/fs.h b/include/linux/fs.h index e019ea2f1347..7519ae003a08 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2132,6 +2132,10 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_DONTCACHE Evict inode as soon as it is not used anymore. * + * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. + * Used to detect that mark_inode_dirty() should not move + * inode between dirty lists. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2149,12 +2153,11 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define __I_DIRTY_TIME_EXPIRED 12 -#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) +#define I_SYNC_QUEUED (1 << 17) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 2eab6d5f6736..aab0ffc6bac6 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -120,7 +120,7 @@ static inline bool fs_validate_description(const char *name, #define fsparam_u32oct(NAME, OPT) \ __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) #define fsparam_u32hex(NAME, OPT) \ - __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *16)) + __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16) #define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0, NULL) #define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0, NULL) #define fsparam_enum(NAME, OPT, array) __fsparam(fs_param_is_enum, NAME, OPT, 0, array) diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index 884b8f8ca06d..01acebe37fab 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -136,6 +136,7 @@ struct ptp_qoriq_registers { #define DEFAULT_TMR_PRSC 2 #define DEFAULT_FIPER1_PERIOD 1000000000 #define DEFAULT_FIPER2_PERIOD 1000000000 +#define DEFAULT_FIPER3_PERIOD 1000000000 struct ptp_qoriq { void __iomem *base; @@ -147,6 +148,7 @@ struct ptp_qoriq { struct dentry *debugfs_root; struct device *dev; bool extts_fifo_support; + bool fiper3_support; int irq; int phc_index; u32 tclk_period; /* nanoseconds */ @@ -155,6 +157,7 @@ struct ptp_qoriq { u32 cksel; u32 tmr_fiper1; u32 tmr_fiper2; + u32 tmr_fiper3; u32 (*read)(unsigned __iomem *addr); void (*write)(unsigned __iomem *addr, u32 val); }; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ce2c06f72e86..e5c2d5cc6e6a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -85,8 +85,7 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val extern int ftrace_enabled; extern int ftrace_enable_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); struct ftrace_ops; diff --git a/include/linux/hid.h b/include/linux/hid.h index 875f71132b14..c7044a14200e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -959,34 +959,49 @@ static inline void hid_device_io_stop(struct hid_device *hid) { * @max: maximal valid usage->code to consider later (out parameter) * @type: input event type (EV_KEY, EV_REL, ...) * @c: code which corresponds to this usage and type + * + * The value pointed to by @bit will be set to NULL if either @type is + * an unhandled event type, or if @c is out of range for @type. This + * can be used as an error condition. */ static inline void hid_map_usage(struct hid_input *hidinput, struct hid_usage *usage, unsigned long **bit, int *max, - __u8 type, __u16 c) + __u8 type, unsigned int c) { struct input_dev *input = hidinput->input; - - usage->type = type; - usage->code = c; + unsigned long *bmap = NULL; + unsigned int limit = 0; switch (type) { case EV_ABS: - *bit = input->absbit; - *max = ABS_MAX; + bmap = input->absbit; + limit = ABS_MAX; break; case EV_REL: - *bit = input->relbit; - *max = REL_MAX; + bmap = input->relbit; + limit = REL_MAX; break; case EV_KEY: - *bit = input->keybit; - *max = KEY_MAX; + bmap = input->keybit; + limit = KEY_MAX; break; case EV_LED: - *bit = input->ledbit; - *max = LED_MAX; + bmap = input->ledbit; + limit = LED_MAX; break; } + + if (unlikely(c > limit || !bmap)) { + pr_warn_ratelimited("%s: Invalid code %d type %d\n", + input->name, c, type); + *bit = NULL; + return; + } + + usage->type = type; + usage->code = c; + *max = limit; + *bit = bmap; } /** @@ -1000,7 +1015,8 @@ static inline void hid_map_usage_clear(struct hid_input *hidinput, __u8 type, __u16 c) { hid_map_usage(hidinput, usage, bit, max, type, c); - clear_bit(c, *bit); + if (*bit) + clear_bit(usage->code, *bit); } /** diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h index d03071732db4..7c522fdd9ea7 100644 --- a/include/linux/i2c-algo-pca.h +++ b/include/linux/i2c-algo-pca.h @@ -53,6 +53,20 @@ #define I2C_PCA_CON_SI 0x08 /* Serial Interrupt */ #define I2C_PCA_CON_CR 0x07 /* Clock Rate (MASK) */ +/** + * struct pca_i2c_bus_settings - The configured PCA i2c bus settings + * @mode: Configured i2c bus mode + * @tlow: Configured SCL LOW period + * @thi: Configured SCL HIGH period + * @clock_freq: The configured clock frequency + */ +struct pca_i2c_bus_settings { + int mode; + int tlow; + int thi; + int clock_freq; +}; + struct i2c_algo_pca_data { void *data; /* private low level data */ void (*write_byte) (void *data, int reg, int val); @@ -64,6 +78,7 @@ struct i2c_algo_pca_data { * For PCA9665, use the frequency you want here. */ unsigned int i2c_clock; unsigned int chip; + struct pca_i2c_bus_settings bus_settings; }; int i2c_pca_add_bus(struct i2c_adapter *); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index c47f43e65a2f..53fba39d4ba6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2330,84 +2330,84 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) } /* S1G Capabilities Information field */ -#define S1G_CAPAB_B0_S1G_LONG BIT(0) -#define S1G_CAPAB_B0_SGI_1MHZ BIT(1) -#define S1G_CAPAB_B0_SGI_2MHZ BIT(2) -#define S1G_CAPAB_B0_SGI_4MHZ BIT(3) -#define S1G_CAPAB_B0_SGI_8MHZ BIT(4) -#define S1G_CAPAB_B0_SGI_16MHZ BIT(5) -#define S1G_CAPAB_B0_SUPP_CH_WIDTH_MASK (BIT(6) | BIT(7)) -#define S1G_CAPAB_B0_SUPP_CH_WIDTH_SHIFT 6 - -#define S1G_CAPAB_B1_RX_LDPC BIT(0) -#define S1G_CAPAB_B1_TX_STBC BIT(1) -#define S1G_CAPAB_B1_RX_STBC BIT(2) -#define S1G_CAPAB_B1_SU_BFER BIT(3) -#define S1G_CAPAB_B1_SU_BFEE BIT(4) -#define S1G_CAPAB_B1_BFEE_STS_MASK (BIT(5) | BIT(6) | BIT(7)) -#define S1G_CAPAB_B1_BFEE_STS_SHIFT 5 - -#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_MASK (BIT(0) | BIT(1) | BIT(2)) -#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_SHIFT 0 -#define S1G_CAPAB_B2_MU_BFER BIT(3) -#define S1G_CAPAB_B2_MU_BFEE BIT(4) -#define S1G_CAPAB_B2_PLUS_HTC_VHT BIT(5) -#define S1G_CAPAB_B2_TRAVELING_PILOT_MASK (BIT(6) | BIT(7)) -#define S1G_CAPAB_B2_TRAVELING_PILOT_SHIFT 6 - -#define S1G_CAPAB_B3_RD_RESPONDER BIT(0) -#define S1G_CAPAB_B3_HT_DELAYED_BA BIT(1) -#define S1G_CAPAB_B3_MAX_MPDU_LEN BIT(2) -#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_MASK (BIT(3) | BIT(4)) -#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_SHIFT 3 -#define S1G_CAPAB_B3_MIN_MPDU_START_MASK (BIT(5) | BIT(6) | BIT(7)) -#define S1G_CAPAB_B3_MIN_MPDU_START_SHIFT 5 - -#define S1G_CAPAB_B4_UPLINK_SYNC BIT(0) -#define S1G_CAPAB_B4_DYNAMIC_AID BIT(1) -#define S1G_CAPAB_B4_BAT BIT(2) -#define S1G_CAPAB_B4_TIME_ADE BIT(3) -#define S1G_CAPAB_B4_NON_TIM BIT(4) -#define S1G_CAPAB_B4_GROUP_AID BIT(5) -#define S1G_CAPAB_B4_STA_TYPE_MASK (BIT(6) | BIT(7)) -#define S1G_CAPAB_B4_STA_TYPE_SHIFT 6 - -#define S1G_CAPAB_B5_CENT_AUTH_CONTROL BIT(0) -#define S1G_CAPAB_B5_DIST_AUTH_CONTROL BIT(1) -#define S1G_CAPAB_B5_AMSDU BIT(2) -#define S1G_CAPAB_B5_AMPDU BIT(3) -#define S1G_CAPAB_B5_ASYMMETRIC_BA BIT(4) -#define S1G_CAPAB_B5_FLOW_CONTROL BIT(5) -#define S1G_CAPAB_B5_SECTORIZED_BEAM_MASK (BIT(6) | BIT(7)) -#define S1G_CAPAB_B5_SECTORIZED_BEAM_SHIFT 6 - -#define S1G_CAPAB_B6_OBSS_MITIGATION BIT(0) -#define S1G_CAPAB_B6_FRAGMENT_BA BIT(1) -#define S1G_CAPAB_B6_NDP_PS_POLL BIT(2) -#define S1G_CAPAB_B6_RAW_OPERATION BIT(3) -#define S1G_CAPAB_B6_PAGE_SLICING BIT(4) -#define S1G_CAPAB_B6_TXOP_SHARING_IMP_ACK BIT(5) -#define S1G_CAPAB_B6_VHT_LINK_ADAPT_MASK (BIT(6) | BIT(7)) -#define S1G_CAPAB_B6_VHT_LINK_ADAPT_SHIFT 6 - -#define S1G_CAPAB_B7_TACK_AS_PS_POLL BIT(0) -#define S1G_CAPAB_B7_DUP_1MHZ BIT(1) -#define S1G_CAPAB_B7_MCS_NEGOTIATION BIT(2) -#define S1G_CAPAB_B7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3) -#define S1G_CAPAB_B7_NDP_BFING_REPORT_POLL BIT(4) -#define S1G_CAPAB_B7_UNSOLICITED_DYN_AID BIT(5) -#define S1G_CAPAB_B7_SECTOR_TRAINING_OPERATION BIT(6) -#define S1G_CAPAB_B7_TEMP_PS_MODE_SWITCH BIT(7) - -#define S1G_CAPAB_B8_TWT_GROUPING BIT(0) -#define S1G_CAPAB_B8_BDT BIT(1) -#define S1G_CAPAB_B8_COLOR_MASK (BIT(2) | BIT(3) | BIT(4)) -#define S1G_CAPAB_B8_COLOR_SHIFT 2 -#define S1G_CAPAB_B8_TWT_REQUEST BIT(5) -#define S1G_CAPAB_B8_TWT_RESPOND BIT(6) -#define S1G_CAPAB_B8_PV1_FRAME BIT(7) - -#define S1G_CAPAB_B9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0) +#define S1G_CAP0_S1G_LONG BIT(0) +#define S1G_CAP0_SGI_1MHZ BIT(1) +#define S1G_CAP0_SGI_2MHZ BIT(2) +#define S1G_CAP0_SGI_4MHZ BIT(3) +#define S1G_CAP0_SGI_8MHZ BIT(4) +#define S1G_CAP0_SGI_16MHZ BIT(5) +#define S1G_CAP0_SUPP_CH_WIDTH GENMASK(7, 6) + +#define S1G_SUPP_CH_WIDTH_2 0 +#define S1G_SUPP_CH_WIDTH_4 1 +#define S1G_SUPP_CH_WIDTH_8 2 +#define S1G_SUPP_CH_WIDTH_16 3 +#define S1G_SUPP_CH_WIDTH_MAX(cap) ((1 << FIELD_GET(S1G_CAP0_SUPP_CH_WIDTH, \ + cap[0])) << 1) + +#define S1G_CAP1_RX_LDPC BIT(0) +#define S1G_CAP1_TX_STBC BIT(1) +#define S1G_CAP1_RX_STBC BIT(2) +#define S1G_CAP1_SU_BFER BIT(3) +#define S1G_CAP1_SU_BFEE BIT(4) +#define S1G_CAP1_BFEE_STS GENMASK(7, 5) + +#define S1G_CAP2_SOUNDING_DIMENSIONS GENMASK(2, 0) +#define S1G_CAP2_MU_BFER BIT(3) +#define S1G_CAP2_MU_BFEE BIT(4) +#define S1G_CAP2_PLUS_HTC_VHT BIT(5) +#define S1G_CAP2_TRAVELING_PILOT GENMASK(7, 6) + +#define S1G_CAP3_RD_RESPONDER BIT(0) +#define S1G_CAP3_HT_DELAYED_BA BIT(1) +#define S1G_CAP3_MAX_MPDU_LEN BIT(2) +#define S1G_CAP3_MAX_AMPDU_LEN_EXP GENMASK(4, 3) +#define S1G_CAP3_MIN_MPDU_START GENMASK(7, 5) + +#define S1G_CAP4_UPLINK_SYNC BIT(0) +#define S1G_CAP4_DYNAMIC_AID BIT(1) +#define S1G_CAP4_BAT BIT(2) +#define S1G_CAP4_TIME_ADE BIT(3) +#define S1G_CAP4_NON_TIM BIT(4) +#define S1G_CAP4_GROUP_AID BIT(5) +#define S1G_CAP4_STA_TYPE GENMASK(7, 6) + +#define S1G_CAP5_CENT_AUTH_CONTROL BIT(0) +#define S1G_CAP5_DIST_AUTH_CONTROL BIT(1) +#define S1G_CAP5_AMSDU BIT(2) +#define S1G_CAP5_AMPDU BIT(3) +#define S1G_CAP5_ASYMMETRIC_BA BIT(4) +#define S1G_CAP5_FLOW_CONTROL BIT(5) +#define S1G_CAP5_SECTORIZED_BEAM GENMASK(7, 6) + +#define S1G_CAP6_OBSS_MITIGATION BIT(0) +#define S1G_CAP6_FRAGMENT_BA BIT(1) +#define S1G_CAP6_NDP_PS_POLL BIT(2) +#define S1G_CAP6_RAW_OPERATION BIT(3) +#define S1G_CAP6_PAGE_SLICING BIT(4) +#define S1G_CAP6_TXOP_SHARING_IMP_ACK BIT(5) +#define S1G_CAP6_VHT_LINK_ADAPT GENMASK(7, 6) + +#define S1G_CAP7_TACK_AS_PS_POLL BIT(0) +#define S1G_CAP7_DUP_1MHZ BIT(1) +#define S1G_CAP7_MCS_NEGOTIATION BIT(2) +#define S1G_CAP7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3) +#define S1G_CAP7_NDP_BFING_REPORT_POLL BIT(4) +#define S1G_CAP7_UNSOLICITED_DYN_AID BIT(5) +#define S1G_CAP7_SECTOR_TRAINING_OPERATION BIT(6) +#define S1G_CAP7_TEMP_PS_MODE_SWITCH BIT(7) + +#define S1G_CAP8_TWT_GROUPING BIT(0) +#define S1G_CAP8_BDT BIT(1) +#define S1G_CAP8_COLOR GENMASK(4, 2) +#define S1G_CAP8_TWT_REQUEST BIT(5) +#define S1G_CAP8_TWT_RESPOND BIT(6) +#define S1G_CAP8_PV1_FRAME BIT(7) + +#define S1G_CAP9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0) + +#define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ BIT(0) +#define S1G_OPER_CH_WIDTH_OPER GENMASK(4, 1) /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 6479a38e52fa..556caed00258 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -19,7 +19,13 @@ struct br_ip { #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ip6; #endif - } u; + } src; + union { + __be32 ip4; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr ip6; +#endif + } dst; __be16 proto; __u16 vid; }; diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 5bda8cf457b6..2a7660843444 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -27,9 +27,18 @@ struct tun_xdp_hdr { #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); -bool tun_is_xdp_frame(void *ptr); -void *tun_xdp_to_ptr(void *ptr); -void *tun_ptr_to_xdp(void *ptr); +static inline bool tun_is_xdp_frame(void *ptr) +{ + return (unsigned long)ptr & TUN_XDP_FLAG; +} +static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp) +{ + return (void *)((unsigned long)xdp | TUN_XDP_FLAG); +} +static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr) +{ + return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG); +} void tun_ptr_free(void *ptr); #else #include <linux/err.h> @@ -48,11 +57,11 @@ static inline bool tun_is_xdp_frame(void *ptr) { return false; } -static inline void *tun_xdp_to_ptr(void *ptr) +static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp) { return NULL; } -static inline void *tun_ptr_to_xdp(void *ptr) +static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr) { return NULL; } diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 0ef2d800fda7..84abb30a3fbb 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -75,6 +75,8 @@ static inline size_t inet_diag_msg_attrs_size(void) #ifdef CONFIG_SOCK_CGROUP_DATA + nla_total_size_64bit(sizeof(u64)) /* INET_DIAG_CGROUP_ID */ #endif + + nla_total_size(sizeof(struct inet_diag_sockopt)) + /* INET_DIAG_SOCKOPT */ ; } int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a44789d027cc..dda61d150a13 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -177,17 +177,6 @@ static inline int inet6_sdif(const struct sk_buff *skb) return 0; } -/* can not be used in TCP layer after tcp_v6_fill_cb */ -static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb) -{ -#if defined(CONFIG_NET_L3_MASTER_DEV) - if (!net->ipv4.sysctl_tcp_l3mdev_accept && - skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) - return true; -#endif - return false; -} - struct tcp6_request_sock { struct tcp_request_sock tcp6rsk_tcp; }; @@ -345,17 +334,6 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) return (struct raw6_sock *)sk; } -static inline void inet_sk_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - int ancestor_size = sizeof(struct inet_sock); - - if (sk_from->sk_family == PF_INET6) - ancestor_size += sizeof(struct ipv6_pinfo); - - __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); -} - #define __ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_only_sock(sk) (__ipv6_only_sock(sk)) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index bd5c55755447..3ed4e8771b64 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -49,17 +49,18 @@ struct irqtrace_events { DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); - extern void trace_hardirqs_on_prepare(void); - extern void trace_hardirqs_off_finish(void); - extern void trace_hardirqs_on(void); - extern void trace_hardirqs_off(void); -# define lockdep_hardirq_context() (this_cpu_read(hardirq_context)) +extern void trace_hardirqs_on_prepare(void); +extern void trace_hardirqs_off_finish(void); +extern void trace_hardirqs_on(void); +extern void trace_hardirqs_off(void); + +# define lockdep_hardirq_context() (raw_cpu_read(hardirq_context)) # define lockdep_softirq_context(p) ((p)->softirq_context) # define lockdep_hardirqs_enabled() (this_cpu_read(hardirqs_enabled)) # define lockdep_softirqs_enabled(p) ((p)->softirqs_enabled) # define lockdep_hardirq_enter() \ do { \ - if (this_cpu_inc_return(hardirq_context) == 1) \ + if (__this_cpu_inc_return(hardirq_context) == 1)\ current->hardirq_threaded = 0; \ } while (0) # define lockdep_hardirq_threaded() \ @@ -68,7 +69,7 @@ do { \ } while (0) # define lockdep_hardirq_exit() \ do { \ - this_cpu_dec(hardirq_context); \ + __this_cpu_dec(hardirq_context); \ } while (0) # define lockdep_softirq_enter() \ do { \ @@ -120,17 +121,17 @@ do { \ #else # define trace_hardirqs_on_prepare() do { } while (0) # define trace_hardirqs_off_finish() do { } while (0) -# define trace_hardirqs_on() do { } while (0) -# define trace_hardirqs_off() do { } while (0) -# define lockdep_hardirq_context() 0 -# define lockdep_softirq_context(p) 0 -# define lockdep_hardirqs_enabled() 0 -# define lockdep_softirqs_enabled(p) 0 -# define lockdep_hardirq_enter() do { } while (0) -# define lockdep_hardirq_threaded() do { } while (0) -# define lockdep_hardirq_exit() do { } while (0) -# define lockdep_softirq_enter() do { } while (0) -# define lockdep_softirq_exit() do { } while (0) +# define trace_hardirqs_on() do { } while (0) +# define trace_hardirqs_off() do { } while (0) +# define lockdep_hardirq_context() 0 +# define lockdep_softirq_context(p) 0 +# define lockdep_hardirqs_enabled() 0 +# define lockdep_softirqs_enabled(p) 0 +# define lockdep_hardirq_enter() do { } while (0) +# define lockdep_hardirq_threaded() do { } while (0) +# define lockdep_hardirq_exit() do { } while (0) +# define lockdep_softirq_enter() do { } while (0) +# define lockdep_softirq_exit() do { } while (0) # define lockdep_hrtimer_enter(__hrtimer) false # define lockdep_hrtimer_exit(__context) do { } while (0) # define lockdep_posixtimer_enter() do { } while (0) @@ -181,26 +182,33 @@ do { \ * if !TRACE_IRQFLAGS. */ #ifdef CONFIG_TRACE_IRQFLAGS -#define local_irq_enable() \ - do { trace_hardirqs_on(); raw_local_irq_enable(); } while (0) -#define local_irq_disable() \ - do { raw_local_irq_disable(); trace_hardirqs_off(); } while (0) + +#define local_irq_enable() \ + do { \ + trace_hardirqs_on(); \ + raw_local_irq_enable(); \ + } while (0) + +#define local_irq_disable() \ + do { \ + bool was_disabled = raw_irqs_disabled();\ + raw_local_irq_disable(); \ + if (!was_disabled) \ + trace_hardirqs_off(); \ + } while (0) + #define local_irq_save(flags) \ do { \ raw_local_irq_save(flags); \ - trace_hardirqs_off(); \ + if (!raw_irqs_disabled_flags(flags)) \ + trace_hardirqs_off(); \ } while (0) - #define local_irq_restore(flags) \ do { \ - if (raw_irqs_disabled_flags(flags)) { \ - raw_local_irq_restore(flags); \ - trace_hardirqs_off(); \ - } else { \ + if (!raw_irqs_disabled_flags(flags)) \ trace_hardirqs_on(); \ - raw_local_irq_restore(flags); \ - } \ + raw_local_irq_restore(flags); \ } while (0) #define safe_halt() \ @@ -214,10 +222,7 @@ do { \ #define local_irq_enable() do { raw_local_irq_enable(); } while (0) #define local_irq_disable() do { raw_local_irq_disable(); } while (0) -#define local_irq_save(flags) \ - do { \ - raw_local_irq_save(flags); \ - } while (0) +#define local_irq_save(flags) do { raw_local_irq_save(flags); } while (0) #define local_irq_restore(flags) do { raw_local_irq_restore(flags); } while (0) #define safe_halt() do { raw_safe_halt(); } while (0) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 4aaa29772bb0..08f904943ab2 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1381,7 +1381,7 @@ extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); -extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); +extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush (journal_t *); extern void jbd2_journal_lock_updates (journal_t *); diff --git a/include/linux/jhash.h b/include/linux/jhash.h index 19ddd43aee68..cfb62e9f37be 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -86,17 +86,17 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) } /* Last block: affect all 32 bits of (c) */ switch (length) { - case 12: c += (u32)k[11]<<24; /* fall through */ - case 11: c += (u32)k[10]<<16; /* fall through */ - case 10: c += (u32)k[9]<<8; /* fall through */ - case 9: c += k[8]; /* fall through */ - case 8: b += (u32)k[7]<<24; /* fall through */ - case 7: b += (u32)k[6]<<16; /* fall through */ - case 6: b += (u32)k[5]<<8; /* fall through */ - case 5: b += k[4]; /* fall through */ - case 4: a += (u32)k[3]<<24; /* fall through */ - case 3: a += (u32)k[2]<<16; /* fall through */ - case 2: a += (u32)k[1]<<8; /* fall through */ + case 12: c += (u32)k[11]<<24; fallthrough; + case 11: c += (u32)k[10]<<16; fallthrough; + case 10: c += (u32)k[9]<<8; fallthrough; + case 9: c += k[8]; fallthrough; + case 8: b += (u32)k[7]<<24; fallthrough; + case 7: b += (u32)k[6]<<16; fallthrough; + case 6: b += (u32)k[5]<<8; fallthrough; + case 5: b += k[4]; fallthrough; + case 4: a += (u32)k[3]<<24; fallthrough; + case 3: a += (u32)k[2]<<16; fallthrough; + case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ @@ -132,8 +132,8 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) /* Handle the last 3 u32's */ switch (length) { - case 3: c += k[2]; /* fall through */ - case 2: b += k[1]; /* fall through */ + case 3: c += k[2]; fallthrough; + case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 500def620d8f..c25b8e41c0ea 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -186,7 +186,7 @@ * lower_32_bits - return bits 0-31 of a number * @n: the number we're accessing */ -#define lower_32_bits(n) ((u32)(n)) +#define lower_32_bits(n) ((u32)((n) & 0xffffffff)) struct completion; struct pt_regs; diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9be1bff4f586..8aab327b5539 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -373,6 +373,8 @@ void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); +void kprobe_free_init_mem(void); + int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); @@ -435,6 +437,9 @@ static inline void unregister_kretprobes(struct kretprobe **rps, int num) static inline void kprobe_flush_task(struct task_struct *tk) { } +static inline void kprobe_free_init_mem(void) +{ +} static inline int disable_kprobe(struct kprobe *kp) { return -ENOSYS; diff --git a/include/linux/ksm.h b/include/linux/ksm.h index e48b1e453ff5..161e8164abcf 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -53,8 +53,6 @@ struct page *ksm_might_need_to_copy(struct page *page, void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); void ksm_migrate_page(struct page *newpage, struct page *oldpage); -bool reuse_ksm_page(struct page *page, - struct vm_area_struct *vma, unsigned long address); #else /* !CONFIG_KSM */ @@ -88,11 +86,6 @@ static inline void rmap_walk_ksm(struct page *page, static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage) { } -static inline bool reuse_ksm_page(struct page *page, - struct vm_area_struct *vma, unsigned long address) -{ - return false; -} #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a23076765b4c..05e3c2fb3ef7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -749,25 +749,46 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); -#define __kvm_put_guest(kvm, gfn, offset, value, type) \ +#define __kvm_get_guest(kvm, gfn, offset, v) \ ({ \ unsigned long __addr = gfn_to_hva(kvm, gfn); \ - type __user *__uaddr = (type __user *)(__addr + offset); \ + typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ int __ret = -EFAULT; \ \ if (!kvm_is_error_hva(__addr)) \ - __ret = put_user(value, __uaddr); \ + __ret = get_user(v, __uaddr); \ + __ret; \ +}) + +#define kvm_get_guest(kvm, gpa, v) \ +({ \ + gpa_t __gpa = gpa; \ + struct kvm *__kvm = kvm; \ + \ + __kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT, \ + offset_in_page(__gpa), v); \ +}) + +#define __kvm_put_guest(kvm, gfn, offset, v) \ +({ \ + unsigned long __addr = gfn_to_hva(kvm, gfn); \ + typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ + int __ret = -EFAULT; \ + \ + if (!kvm_is_error_hva(__addr)) \ + __ret = put_user(v, __uaddr); \ if (!__ret) \ mark_page_dirty(kvm, gfn); \ __ret; \ }) -#define kvm_put_guest(kvm, gpa, value, type) \ +#define kvm_put_guest(kvm, gpa, v) \ ({ \ gpa_t __gpa = gpa; \ struct kvm *__kvm = kvm; \ + \ __kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \ - offset_in_page(__gpa), (value), type); \ + offset_in_page(__gpa), v); \ }) int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); diff --git a/include/linux/libata.h b/include/linux/libata.h index 77ccf040a128..5f550eb27f81 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -421,6 +421,7 @@ enum { ATA_HORKAGE_NO_DMA_LOG = (1 << 23), /* don't use DMA for log read */ ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ + ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 62a382d1845b..6a584b3e5c74 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -535,19 +535,27 @@ do { \ DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); +/* + * The below lockdep_assert_*() macros use raw_cpu_read() to access the above + * per-cpu variables. This is required because this_cpu_read() will potentially + * call into preempt/irq-disable and that obviously isn't right. This is also + * correct because when IRQs are enabled, it doesn't matter if we accidentally + * read the value from our previous CPU. + */ + #define lockdep_assert_irqs_enabled() \ do { \ - WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirqs_enabled)); \ + WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_irqs_disabled() \ do { \ - WARN_ON_ONCE(debug_locks && this_cpu_read(hardirqs_enabled)); \ + WARN_ON_ONCE(debug_locks && raw_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_in_irq() \ do { \ - WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirq_context)); \ + WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirq_context)); \ } while (0) #define lockdep_assert_preemption_enabled() \ @@ -555,7 +563,7 @@ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ debug_locks && \ (preempt_count() != 0 || \ - !this_cpu_read(hardirqs_enabled))); \ + !raw_cpu_read(hardirqs_enabled))); \ } while (0) #define lockdep_assert_preemption_disabled() \ @@ -563,7 +571,7 @@ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ debug_locks && \ (preempt_count() == 0 && \ - this_cpu_read(hardirqs_enabled))); \ + raw_cpu_read(hardirqs_enabled))); \ } while (0) #else diff --git a/include/linux/log2.h b/include/linux/log2.h index 83a4a3ca3e8a..c619ec6eff4a 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -173,7 +173,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) #define roundup_pow_of_two(n) \ ( \ __builtin_constant_p(n) ? ( \ - (n == 1) ? 1 : \ + ((n) == 1) ? 1 : \ (1UL << (ilog2((n) - 1) + 1)) \ ) : \ __roundup_pow_of_two(n) \ diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 898cbf00332a..3a88b699b758 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -358,6 +358,12 @@ static inline int mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, return mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum)); } +static inline int mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad, + u16 regnum, u16 val) +{ + return mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), val); +} + int mdiobus_register_device(struct mdio_device *mdiodev); int mdiobus_unregister_device(struct mdio_device *mdiodev); bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); diff --git a/include/linux/mdio/mdio-i2c.h b/include/linux/mdio/mdio-i2c.h new file mode 100644 index 000000000000..b1d27f7cd23f --- /dev/null +++ b/include/linux/mdio/mdio-i2c.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * MDIO I2C bridge + * + * Copyright (C) 2015 Russell King + */ +#ifndef MDIO_I2C_H +#define MDIO_I2C_H + +struct device; +struct i2c_adapter; +struct mii_bus; + +struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c); + +#endif diff --git a/include/linux/mdio/mdio-xgene.h b/include/linux/mdio/mdio-xgene.h new file mode 100644 index 000000000000..8af93ada8b64 --- /dev/null +++ b/include/linux/mdio/mdio-xgene.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Applied Micro X-Gene SoC MDIO Driver + * + * Copyright (c) 2016, Applied Micro Circuits Corporation + * Author: Iyappan Subramanian <isubramanian@apm.com> + */ + +#ifndef __MDIO_XGENE_H__ +#define __MDIO_XGENE_H__ + +#define BLOCK_XG_MDIO_CSR_OFFSET 0x5000 +#define BLOCK_DIAG_CSR_OFFSET 0xd000 +#define XGENET_CONFIG_REG_ADDR 0x20 + +#define MAC_ADDR_REG_OFFSET 0x00 +#define MAC_COMMAND_REG_OFFSET 0x04 +#define MAC_WRITE_REG_OFFSET 0x08 +#define MAC_READ_REG_OFFSET 0x0c +#define MAC_COMMAND_DONE_REG_OFFSET 0x10 + +#define CLKEN_OFFSET 0x08 +#define SRST_OFFSET 0x00 + +#define MENET_CFG_MEM_RAM_SHUTDOWN_ADDR 0x70 +#define MENET_BLOCK_MEM_RDY_ADDR 0x74 + +#define MAC_CONFIG_1_ADDR 0x00 +#define MII_MGMT_COMMAND_ADDR 0x24 +#define MII_MGMT_ADDRESS_ADDR 0x28 +#define MII_MGMT_CONTROL_ADDR 0x2c +#define MII_MGMT_STATUS_ADDR 0x30 +#define MII_MGMT_INDICATORS_ADDR 0x34 +#define SOFT_RESET BIT(31) + +#define MII_MGMT_CONFIG_ADDR 0x20 +#define MII_MGMT_COMMAND_ADDR 0x24 +#define MII_MGMT_ADDRESS_ADDR 0x28 +#define MII_MGMT_CONTROL_ADDR 0x2c +#define MII_MGMT_STATUS_ADDR 0x30 +#define MII_MGMT_INDICATORS_ADDR 0x34 + +#define MIIM_COMMAND_ADDR 0x20 +#define MIIM_FIELD_ADDR 0x24 +#define MIIM_CONFIGURATION_ADDR 0x28 +#define MIIM_LINKFAILVECTOR_ADDR 0x2c +#define MIIM_INDICATOR_ADDR 0x30 +#define MIIMRD_FIELD_ADDR 0x34 + +#define MDIO_CSR_OFFSET 0x5000 + +#define REG_ADDR_POS 0 +#define REG_ADDR_LEN 5 +#define PHY_ADDR_POS 8 +#define PHY_ADDR_LEN 5 + +#define HSTMIIMWRDAT_POS 0 +#define HSTMIIMWRDAT_LEN 16 +#define HSTPHYADX_POS 23 +#define HSTPHYADX_LEN 5 +#define HSTREGADX_POS 18 +#define HSTREGADX_LEN 5 +#define HSTLDCMD BIT(3) +#define HSTMIIMCMD_POS 0 +#define HSTMIIMCMD_LEN 3 + +#define BUSY_MASK BIT(0) +#define READ_CYCLE_MASK BIT(0) + +enum xgene_enet_cmd { + XGENE_ENET_WR_CMD = BIT(31), + XGENE_ENET_RD_CMD = BIT(30) +}; + +enum { + MIIM_CMD_IDLE, + MIIM_CMD_LEGACY_WRITE, + MIIM_CMD_LEGACY_READ, +}; + +enum xgene_mdio_id { + XGENE_MDIO_RGMII = 1, + XGENE_MDIO_XFI +}; + +struct xgene_mdio_pdata { + struct clk *clk; + struct device *dev; + void __iomem *mac_csr_addr; + void __iomem *diag_csr_addr; + void __iomem *mdio_csr_addr; + struct mii_bus *mdio_bus; + int mdio_id; + spinlock_t mac_lock; /* mac lock */ +}; + +/* Set the specified value into a bit-field defined by its starting position + * and length within a single u64. + */ +static inline u64 xgene_enet_set_field_value(int pos, int len, u64 val) +{ + return (val & ((1ULL << len) - 1)) << pos; +} + +#define SET_VAL(field, val) \ + xgene_enet_set_field_value(field ## _POS, field ## _LEN, val) + +#define SET_BIT(field) \ + xgene_enet_set_field_value(field ## _POS, 1, 1) + +/* Get the value from a bit-field defined by its starting position + * and length within the specified u64. + */ +static inline u64 xgene_enet_get_field_value(int pos, int len, u64 src) +{ + return (src >> pos) & ((1ULL << len) - 1); +} + +#define GET_VAL(field, src) \ + xgene_enet_get_field_value(field ## _POS, field ## _LEN, src) + +#define GET_BIT(field, src) \ + xgene_enet_get_field_value(field ## _POS, 1, src) + +u32 xgene_mdio_rd_mac(struct xgene_mdio_pdata *pdata, u32 rd_addr); +void xgene_mdio_wr_mac(struct xgene_mdio_pdata *pdata, u32 wr_addr, u32 data); +int xgene_mdio_rgmii_read(struct mii_bus *bus, int phy_id, int reg); +int xgene_mdio_rgmii_write(struct mii_bus *bus, int phy_id, int reg, u16 data); +struct phy_device *xgene_enet_phy_register(struct mii_bus *bus, int phy_addr); + +#endif /* __MDIO_XGENE_H__ */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 5f5b2df06e61..e5862746751b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -46,11 +46,10 @@ struct vmem_altmap { * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * - * MEMORY_DEVICE_DEVDAX: + * MEMORY_DEVICE_GENERIC: * Host memory that has similar access semantics as System RAM i.e. DMA - * coherent and supports page pinning. In contrast to - * MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax - * character device. + * coherent and supports page pinning. This is for example used by DAX devices + * that expose memory using a character device. * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer @@ -60,7 +59,7 @@ enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_FS_DAX, - MEMORY_DEVICE_DEVDAX, + MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, }; diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 75f880c25bb8..416ee6dd2574 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -27,6 +27,7 @@ #define PHY_ID_KSZ8061 0x00221570 #define PHY_ID_KSZ9031 0x00221620 #define PHY_ID_KSZ9131 0x00221640 +#define PHY_ID_LAN8814 0x00221660 #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 4d3376e20f5e..81ca5989009b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -816,7 +816,7 @@ struct mlx5_mini_cqe8 { __be32 rx_hash_result; struct { __be16 checksum; - __be16 rsvd; + __be16 stridx; }; struct { __be16 wqe_counter; @@ -836,6 +836,7 @@ enum { enum { MLX5_CQE_FORMAT_CSUM = 0x1, + MLX5_CQE_FORMAT_CSUM_STRIDX = 0x3, }; #define MLX5_MINI_CQE_ARRAY_SIZE 8 diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c145de0473bc..8dc3da6e6480 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -643,7 +643,6 @@ struct mlx5_pps { }; struct mlx5_clock { - struct mlx5_core_dev *mdev; struct mlx5_nb pps_nb; seqlock_t lock; struct cyclecounter cycles; diff --git a/include/linux/mm.h b/include/linux/mm.h index 1983e08f5906..b2f370f0b420 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -41,6 +41,8 @@ struct writeback_control; struct bdi_writeback; struct pt_regs; +extern int sysctl_page_lock_unfairness; + void init_mm_internals(void); #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ @@ -157,11 +159,14 @@ static inline void __mm_zero_struct_page(struct page *page) switch (sizeof(struct page)) { case 80: - _pp[9] = 0; /* fallthrough */ + _pp[9] = 0; + fallthrough; case 72: - _pp[8] = 0; /* fallthrough */ + _pp[8] = 0; + fallthrough; case 64: - _pp[7] = 0; /* fallthrough */ + _pp[7] = 0; + fallthrough; case 56: _pp[6] = 0; _pp[5] = 0; @@ -321,6 +326,8 @@ extern unsigned int kobjsize(const void *objp); #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ +#elif defined(CONFIG_PPC) +# define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_IA64) diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index c51a84132d7c..03dee12d2b61 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -3,10 +3,15 @@ #define _LINUX_MMU_CONTEXT_H #include <asm/mmu_context.h> +#include <asm/mmu.h> /* Architectures that care about IRQ state in switch_mm can override this. */ #ifndef switch_mm_irqs_off # define switch_mm_irqs_off switch_mm #endif +#ifndef leave_mm +static inline void leave_mm(int cpu) { } +#endif + #endif diff --git a/include/linux/net.h b/include/linux/net.h index d48ff1180879..7657c6432a69 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -41,6 +41,8 @@ struct net; #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 +#define PROTO_CMSG_DATA_ONLY 0x0001 + #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types @@ -135,6 +137,7 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, struct proto_ops { int family; + unsigned int flags; struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2cc3cf80b49a..0b17c4322b09 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -193,7 +193,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) #define NETIF_F_GSO_MASK (__NETIF_F_BIT(NETIF_F_GSO_LAST + 1) - \ __NETIF_F_BIT(NETIF_F_GSO_SHIFT)) -/* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be +/* List of IP checksum features. Note that NETIF_F_HW_CSUM should not be * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set-- * this would be contradictory */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0e303f6603f..a431c3229cbf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -70,6 +70,7 @@ struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; +void synchronize_net(void); void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -354,7 +355,7 @@ enum { NAPI_STATE_MISSED, /* reschedule a napi */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ - NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ + NAPI_STATE_LISTED, /* NAPI added to system lists */ NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */ }; @@ -364,7 +365,7 @@ enum { NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), - NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED), + NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED), NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), }; @@ -489,20 +490,6 @@ static inline bool napi_complete(struct napi_struct *n) } /** - * napi_hash_del - remove a NAPI from global table - * @napi: NAPI context - * - * Warning: caller must observe RCU grace period - * before freeing memory containing @napi, if - * this function returns true. - * Note: core networking stack automatically calls it - * from netif_napi_del(). - * Drivers might want to call this helper to combine all - * the needed RCU grace periods into a single one. - */ -bool napi_hash_del(struct napi_struct *napi); - -/** * napi_disable - prevent NAPI from scheduling * @n: NAPI context * @@ -618,7 +605,7 @@ struct netdev_queue { /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; #ifdef CONFIG_XDP_SOCKETS - struct xdp_umem *umem; + struct xsk_buff_pool *pool; #endif /* * write-mostly part @@ -640,11 +627,16 @@ struct netdev_queue { extern int sysctl_fb_tunnels_only_for_init_net; extern int sysctl_devconf_inherit_init_net; +/* + * sysctl_fb_tunnels_only_for_init_net == 0 : For all netns + * == 1 : For initns only + * == 2 : For none. + */ static inline bool net_has_fallback_tunnels(const struct net *net) { - return net == &init_net || - !IS_ENABLED(CONFIG_SYSCTL) || - !sysctl_fb_tunnels_only_for_init_net; + return !IS_ENABLED(CONFIG_SYSCTL) || + !sysctl_fb_tunnels_only_for_init_net || + (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1); } static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) @@ -751,7 +743,7 @@ struct netdev_rx_queue { struct net_device *dev; struct xdp_rxq_info xdp_rxq; #ifdef CONFIG_XDP_SOCKETS - struct xdp_umem *umem; + struct xsk_buff_pool *pool; #endif } ____cacheline_aligned_in_smp; @@ -879,7 +871,7 @@ enum bpf_netdev_command { /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, - XDP_SETUP_XSK_UMEM, + XDP_SETUP_XSK_POOL, }; struct bpf_prog_offload_ops; @@ -913,9 +905,9 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; - /* XDP_SETUP_XSK_UMEM */ + /* XDP_SETUP_XSK_POOL */ struct { - struct xdp_umem *umem; + struct xsk_buff_pool *pool; u16 queue_id; } xsk; }; @@ -1784,6 +1776,7 @@ enum netdev_priv_flags { * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers * + * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one @@ -1848,6 +1841,7 @@ enum netdev_priv_flags { * @udp_tunnel_nic_info: static structure describing the UDP tunnel * offload capabilities of the device * @udp_tunnel_nic: UDP tunnel offload state + * @xdp_state: stores info on attached XDP BPF programs * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -2193,6 +2187,22 @@ int netdev_get_num_tc(struct net_device *dev) return dev->num_tc; } +static inline void net_prefetch(void *p) +{ + prefetch(p); +#if L1_CACHE_BYTES < 128 + prefetch((u8 *)p + L1_CACHE_BYTES); +#endif +} + +static inline void net_prefetchw(void *p) +{ + prefetchw(p); +#if L1_CACHE_BYTES < 128 + prefetchw((u8 *)p + L1_CACHE_BYTES); +#endif +} + void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev); int netdev_bind_sb_channel_queue(struct net_device *dev, @@ -2348,12 +2358,26 @@ static inline void netif_tx_napi_add(struct net_device *dev, } /** + * __netif_napi_del - remove a NAPI context + * @napi: NAPI context + * + * Warning: caller must observe RCU grace period before freeing memory + * containing @napi. Drivers might want to call this helper to combine + * all the needed RCU grace periods into a single one. + */ +void __netif_napi_del(struct napi_struct *napi); + +/** * netif_napi_del - remove a NAPI context * @napi: NAPI context * * netif_napi_del() removes a NAPI context from the network device NAPI list */ -void netif_napi_del(struct napi_struct *napi); +static inline void netif_napi_del(struct napi_struct *napi) +{ + __netif_napi_del(napi); + synchronize_net(); +} struct napi_gro_cb { /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ @@ -2777,7 +2801,6 @@ static inline void unregister_netdevice(struct net_device *dev) int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); void netdev_freemem(struct net_device *dev); -void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, @@ -4657,16 +4680,6 @@ int netdev_class_create_file_ns(const struct class_attribute *class_attr, void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns); -static inline int netdev_class_create_file(const struct class_attribute *class_attr) -{ - return netdev_class_create_file_ns(class_attr, NULL); -} - -static inline void netdev_class_remove_file(const struct class_attribute *class_attr) -{ - netdev_class_remove_file_ns(class_attr, NULL); -} - extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 1db83c931d9c..0c7d8d1e945d 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -8,9 +8,9 @@ struct ip_conntrack_stat { unsigned int found; unsigned int invalid; - unsigned int ignore; unsigned int insert; unsigned int insert_failed; + unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index 9a33f171aa82..625f491b95de 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -9,6 +9,8 @@ struct ip_ct_sctp { enum sctp_conntrack state; __be32 vtag[IP_CT_DIR_MAX]; + u8 last_dir; + u8 flags; }; #endif /* _NF_CONNTRACK_SCTP_H */ diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 851425c3178f..89016d08f6a2 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -43,8 +43,7 @@ int nfnetlink_has_listeners(struct net *net, unsigned int group); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); -int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, - int flags); +int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid); static inline u16 nfnl_msg_type(u8 subsys, u8 msg_type) { diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index aac42c28fe62..9b67394471e1 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -58,7 +58,6 @@ struct nf_ipv6_ops { int (*output)(struct net *, struct sock *, struct sk_buff *)); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); #if IS_MODULE(CONFIG_IPV6) - int (*br_defrag)(struct net *net, struct sk_buff *skb, u32 user); int (*br_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, @@ -117,23 +116,6 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, #include <net/netfilter/ipv6/nf_defrag_ipv6.h> -static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, - u32 user) -{ -#if IS_MODULE(CONFIG_IPV6) - const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); - - if (!v6_ops) - return 1; - - return v6_ops->br_defrag(net, skb, user); -#elif IS_BUILTIN(CONFIG_IPV6) - return nf_ct_frag6_gather(net, skb, user); -#else - return 1; -#endif -} - int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, diff --git a/include/linux/of.h b/include/linux/of.h index 5cf7ae0465d1..481ec0467285 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -929,6 +929,11 @@ static inline int of_machine_is_compatible(const char *compat) return 0; } +static inline int of_remove_property(struct device_node *np, struct property *prop) +{ + return 0; +} + static inline bool of_console_check(const struct device_node *dn, const char *name, int index) { return false; diff --git a/include/linux/pcs-lynx.h b/include/linux/pcs-lynx.h new file mode 100644 index 000000000000..a6440d6ebe95 --- /dev/null +++ b/include/linux/pcs-lynx.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* Copyright 2020 NXP + * Lynx PCS helpers + */ + +#ifndef __LINUX_PCS_LYNX_H +#define __LINUX_PCS_LYNX_H + +#include <linux/mdio.h> +#include <linux/phylink.h> + +struct lynx_pcs { + struct phylink_pcs pcs; + struct mdio_device *mdio; +}; + +struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio); + +void lynx_pcs_destroy(struct lynx_pcs *pcs); + +#endif /* __LINUX_PCS_LYNX_H */ diff --git a/include/linux/mdio-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 9a841aa5982d..351c1c9aedc5 100644 --- a/include/linux/mdio-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -4,8 +4,8 @@ * Synopsys DesignWare XPCS helpers */ -#ifndef __LINUX_MDIO_XPCS_H -#define __LINUX_MDIO_XPCS_H +#ifndef __LINUX_PCS_XPCS_H +#define __LINUX_PCS_XPCS_H #include <linux/phy.h> #include <linux/phylink.h> @@ -29,7 +29,7 @@ struct mdio_xpcs_ops { int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); }; -#if IS_ENABLED(CONFIG_MDIO_XPCS) +#if IS_ENABLED(CONFIG_PCS_XPCS) struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); #else static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) @@ -38,4 +38,4 @@ static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) } #endif -#endif /* __LINUX_MDIO_XPCS_H */ +#endif /* __LINUX_PCS_XPCS_H */ diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 5e033fe1ff4e..5fda40f97fe9 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -60,7 +60,7 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem) * anything we did within this RCU-sched read-size critical section. */ if (likely(rcu_sync_is_idle(&sem->rss))) - __this_cpu_inc(*sem->read_count); + this_cpu_inc(*sem->read_count); else __percpu_down_read(sem, false); /* Unconditional memory barrier */ /* @@ -79,7 +79,7 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) - __this_cpu_inc(*sem->read_count); + this_cpu_inc(*sem->read_count); else ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ preempt_enable(); @@ -103,7 +103,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) { - __this_cpu_dec(*sem->read_count); + this_cpu_dec(*sem->read_count); } else { /* * slowpath; reader will only ever wake a single blocked @@ -115,7 +115,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) * aggregate zero, as that is the only time it matters) they * will also see our critical section. */ - __this_cpu_dec(*sem->read_count); + this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } preempt_enable(); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index a124c21e3204..e8cbc2e795d5 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -117,7 +117,9 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ +#ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) +#endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE diff --git a/include/linux/phylink.h b/include/linux/phylink.h index a8e876317e25..d81a714cfbbd 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -402,7 +402,8 @@ void pcs_get_state(struct phylink_pcs *pcs, * For most 10GBASE-R, there is no advertisement. */ int pcs_config(struct phylink_pcs *pcs, unsigned int mode, - phy_interface_t interface, const unsigned long *advertising); + phy_interface_t interface, const unsigned long *advertising, + bool permit_pause_to_mac); /** * pcs_an_restart() - restart 802.3z BaseX autonegotiation @@ -489,4 +490,7 @@ void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs); void phylink_mii_c45_pcs_get_state(struct mdio_device *pcs, struct phylink_link_state *state); + +void phylink_decode_usxgmii_word(struct phylink_link_state *state, + uint16_t lpa); #endif diff --git a/include/linux/powercap.h b/include/linux/powercap.h index 4537f57f9e42..3d557bbcd2c7 100644 --- a/include/linux/powercap.h +++ b/include/linux/powercap.h @@ -44,19 +44,18 @@ struct powercap_control_type_ops { }; /** - * struct powercap_control_type- Defines a powercap control_type - * @name: name of control_type + * struct powercap_control_type - Defines a powercap control_type * @dev: device for this control_type * @idr: idr to have unique id for its child - * @root_node: Root holding power zones for this control_type + * @nr_zones: counter for number of zones of this type * @ops: Pointer to callback struct - * @node_lock: mutex for control type + * @lock: mutex for control type * @allocated: This is possible that client owns the memory * used by this structure. In this case * this flag is set to false by framework to * prevent deallocation during release process. * Otherwise this flag is set to true. - * @ctrl_inst: link to the control_type list + * @node: linked-list node * * Defines powercap control_type. This acts as a container for power * zones, which use same method to control power. E.g. RAPL, RAPL-PCI etc. @@ -129,7 +128,7 @@ struct powercap_zone_ops { * this flag is set to false by framework to * prevent deallocation during release process. * Otherwise this flag is set to true. - * @constraint_ptr: List of constraints for this zone. + * @constraints: List of constraints for this zone. * * This defines a power zone instance. The fields of this structure are * private, and should not be used by client drivers. diff --git a/include/linux/prefetch.h b/include/linux/prefetch.h index 13eafebf3549..b83a3f944f28 100644 --- a/include/linux/prefetch.h +++ b/include/linux/prefetch.h @@ -15,6 +15,7 @@ #include <asm/processor.h> #include <asm/cache.h> +struct page; /* prefetch(x) attempts to pre-emptively get the memory pointed to by address "x" into the CPU L1 cache. @@ -62,4 +63,11 @@ static inline void prefetch_range(void *addr, size_t len) #endif } +static inline void prefetch_page_address(struct page *page) +{ +#if defined(WANT_PAGE_VIRTUAL) || defined(HASHED_PAGE_VIRTUAL) + prefetch(page); +#endif +} + #endif diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index dd00fa41f7e7..8437307cca8c 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -36,7 +36,6 @@ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ #define OFF_PTP_SEQUENCE_ID 30 -#define OFF_PTP_CONTROL 32 /* PTPv1 only */ /* Below defines should actually be removed at some point in time. */ #define IP6_HLEN 40 @@ -44,6 +43,30 @@ #define OFF_IHL 14 #define IPV4_HLEN(data) (((struct iphdr *)(data + OFF_IHL))->ihl << 2) +struct clock_identity { + u8 id[8]; +} __packed; + +struct port_identity { + struct clock_identity clock_identity; + __be16 port_number; +} __packed; + +struct ptp_header { + u8 tsmt; /* transportSpecific | messageType */ + u8 ver; /* reserved | versionPTP */ + __be16 message_length; + u8 domain_number; + u8 reserved1; + u8 flag_field[2]; + __be64 correction; + __be32 reserved2; + struct port_identity source_port_identity; + __be16 sequence_id; + u8 control; + u8 log_message_interval; +} __packed; + #if defined(CONFIG_NET_PTP_CLASSIFY) /** * ptp_classify_raw - classify a PTP packet @@ -57,6 +80,46 @@ */ unsigned int ptp_classify_raw(const struct sk_buff *skb); +/** + * ptp_parse_header - Get pointer to the PTP v2 header + * @skb: packet buffer + * @type: type of the packet (see ptp_classify_raw()) + * + * This function takes care of the VLAN, UDP, IPv4 and IPv6 headers. The length + * is checked. + * + * Note, internally skb_mac_header() is used. Make sure that the @skb is + * initialized accordingly. + * + * Return: Pointer to the ptp v2 header or NULL if not found + */ +struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type); + +/** + * ptp_get_msgtype - Extract ptp message type from given header + * @hdr: ptp header + * @type: type of the packet (see ptp_classify_raw()) + * + * This function returns the message type for a given ptp header. It takes care + * of the different ptp header versions (v1 or v2). + * + * Return: The message type + */ +static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, + unsigned int type) +{ + u8 msgtype; + + if (unlikely(type & PTP_CLASS_V1)) { + /* msg type is located at the control field for ptp v1 */ + msgtype = hdr->control; + } else { + msgtype = hdr->tsmt & 0x0f; + } + + return msgtype; +} + void __init ptp_classifier_init(void); #else static inline void ptp_classifier_init(void) @@ -66,5 +129,10 @@ static inline unsigned int ptp_classify_raw(struct sk_buff *skb) { return PTP_CLASS_NONE; } +static inline struct ptp_header *ptp_parse_header(struct sk_buff *skb, + unsigned int type) +{ + return NULL; +} #endif #endif /* _PTP_CLASSIFY_H_ */ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index cd6a5c7e56eb..57fb295ea41a 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -21,6 +21,7 @@ #include <linux/qed/common_hsi.h> #include <linux/qed/qed_chain.h> #include <linux/io-64-nonatomic-lo-hi.h> +#include <net/devlink.h> enum dcbx_protocol_type { DCBX_PROTOCOL_ISCSI, @@ -623,6 +624,7 @@ struct qed_dev_info { #define QED_MFW_VERSION_3_OFFSET 24 u32 flash_size; + bool b_arfs_capable; bool b_inter_pf_switch; bool tx_switching; bool rdma_supported; @@ -779,6 +781,11 @@ enum qed_nvm_flash_cmd { QED_NVM_FLASH_CMD_NVM_MAX, }; +struct qed_devlink { + struct qed_dev *cdev; + struct devlink_health_reporter *fw_reporter; +}; + struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); @@ -844,10 +851,9 @@ struct qed_common_ops { struct qed_dev* (*probe)(struct pci_dev *dev, struct qed_probe_params *params); - void (*remove)(struct qed_dev *cdev); + void (*remove)(struct qed_dev *cdev); - int (*set_power_state)(struct qed_dev *cdev, - pci_power_t state); + int (*set_power_state)(struct qed_dev *cdev, pci_power_t state); void (*set_name) (struct qed_dev *cdev, char name[]); @@ -855,50 +861,51 @@ struct qed_common_ops { * PF params required for the call before slowpath_start is * documented within the qed_pf_params structure definition. */ - void (*update_pf_params)(struct qed_dev *cdev, - struct qed_pf_params *params); - int (*slowpath_start)(struct qed_dev *cdev, - struct qed_slowpath_params *params); + void (*update_pf_params)(struct qed_dev *cdev, + struct qed_pf_params *params); - int (*slowpath_stop)(struct qed_dev *cdev); + int (*slowpath_start)(struct qed_dev *cdev, + struct qed_slowpath_params *params); + + int (*slowpath_stop)(struct qed_dev *cdev); /* Requests to use `cnt' interrupts for fastpath. * upon success, returns number of interrupts allocated for fastpath. */ - int (*set_fp_int)(struct qed_dev *cdev, - u16 cnt); + int (*set_fp_int)(struct qed_dev *cdev, u16 cnt); /* Fills `info' with pointers required for utilizing interrupts */ - int (*get_fp_int)(struct qed_dev *cdev, - struct qed_int_info *info); - - u32 (*sb_init)(struct qed_dev *cdev, - struct qed_sb_info *sb_info, - void *sb_virt_addr, - dma_addr_t sb_phy_addr, - u16 sb_id, - enum qed_sb_type type); - - u32 (*sb_release)(struct qed_dev *cdev, - struct qed_sb_info *sb_info, - u16 sb_id, - enum qed_sb_type type); - - void (*simd_handler_config)(struct qed_dev *cdev, - void *token, - int index, - void (*handler)(void *)); - - void (*simd_handler_clean)(struct qed_dev *cdev, - int index); - int (*dbg_grc)(struct qed_dev *cdev, - void *buffer, u32 *num_dumped_bytes); + int (*get_fp_int)(struct qed_dev *cdev, struct qed_int_info *info); + + u32 (*sb_init)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + void *sb_virt_addr, + dma_addr_t sb_phy_addr, + u16 sb_id, + enum qed_sb_type type); + + u32 (*sb_release)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + u16 sb_id, + enum qed_sb_type type); + + void (*simd_handler_config)(struct qed_dev *cdev, + void *token, + int index, + void (*handler)(void *)); + + void (*simd_handler_clean)(struct qed_dev *cdev, int index); + + int (*dbg_grc)(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes); int (*dbg_grc_size)(struct qed_dev *cdev); - int (*dbg_all_data) (struct qed_dev *cdev, void *buffer); + int (*dbg_all_data)(struct qed_dev *cdev, void *buffer); - int (*dbg_all_data_size) (struct qed_dev *cdev); + int (*dbg_all_data_size)(struct qed_dev *cdev); + + int (*report_fatal_error)(struct devlink *devlink, + enum qed_hw_err_type err_type); /** * @brief can_link_change - can the instance change the link or not @@ -1137,6 +1144,10 @@ struct qed_common_ops { * */ int (*set_grc_config)(struct qed_dev *cdev, u32 cfg_id, u32 val); + + struct devlink* (*devlink_register)(struct qed_dev *cdev); + + void (*devlink_unregister)(struct devlink *devlink); }; #define MASK_FIELD(_name, _value) \ diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index a6a6a3acab5a..3e7919fc5f34 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -86,7 +86,14 @@ static inline void rcu_read_unlock_trace(void) void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); void synchronize_rcu_tasks_trace(void); void rcu_barrier_tasks_trace(void); - +#else +/* + * The BPF JIT forms these addresses even when it doesn't call these + * functions, so provide definitions that result in runtime errors. + */ +static inline void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func) { BUG(); } +static inline void rcu_read_lock_trace(void) { BUG(); } +static inline void rcu_read_unlock_trace(void) { BUG(); } #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ #endif /* __LINUX_RCUPDATE_TRACE_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 93ecd930efd3..afe01e232935 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1666,7 +1666,7 @@ extern struct task_struct *idle_task(int cpu); * * Return: 1 if @p is an idle task. 0 otherwise. */ -static inline bool is_idle_task(const struct task_struct *p) +static __always_inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 917d88edb7b9..a8ec3b6093fc 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -36,6 +36,9 @@ struct user_struct { defined(CONFIG_NET) || defined(CONFIG_IO_URING) atomic_long_t locked_vm; #endif +#ifdef CONFIG_WATCH_QUEUE + atomic_t nr_watches; /* The number of watches this user currently has */ +#endif /* Miscellaneous per-user rate limit */ struct ratelimit_state ratelimit; diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 01fc4d9c9c54..8a99279a579b 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -248,6 +248,7 @@ struct uart_port { unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; + unsigned char console_reinit; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ diff --git a/include/linux/signal.h b/include/linux/signal.h index 6bb1a3f0258c..7bbc0e9cf084 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -137,11 +137,11 @@ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ b3 = b->sig[3]; b2 = b->sig[2]; \ r->sig[3] = op(a3, b3); \ r->sig[2] = op(a2, b2); \ - /* fall through */ \ + fallthrough; \ case 2: \ a1 = a->sig[1]; b1 = b->sig[1]; \ r->sig[1] = op(a1, b1); \ - /* fall through */ \ + fallthrough; \ case 1: \ a0 = a->sig[0]; b0 = b->sig[0]; \ r->sig[0] = op(a0, b0); \ @@ -171,9 +171,9 @@ static inline void name(sigset_t *set) \ switch (_NSIG_WORDS) { \ case 4: set->sig[3] = op(set->sig[3]); \ set->sig[2] = op(set->sig[2]); \ - /* fall through */ \ + fallthrough; \ case 2: set->sig[1] = op(set->sig[1]); \ - /* fall through */ \ + fallthrough; \ case 1: set->sig[0] = op(set->sig[0]); \ break; \ default: \ @@ -194,7 +194,7 @@ static inline void sigemptyset(sigset_t *set) memset(set, 0, sizeof(sigset_t)); break; case 2: set->sig[1] = 0; - /* fall through */ + fallthrough; case 1: set->sig[0] = 0; break; } @@ -207,7 +207,7 @@ static inline void sigfillset(sigset_t *set) memset(set, -1, sizeof(sigset_t)); break; case 2: set->sig[1] = -1; - /* fall through */ + fallthrough; case 1: set->sig[0] = -1; break; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 46881d902124..04a18e01b362 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -71,7 +71,7 @@ * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or - * IPv4|UDP where the Next Header field in the IPv6 + * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with @@ -1056,7 +1056,16 @@ void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); + +#ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); +#else +static inline void consume_skb(struct sk_buff *skb) +{ + return kfree_skb(skb); +} +#endif + void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); extern struct kmem_cache *skbuff_head_cache; @@ -2658,7 +2667,7 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. - * get_rps_cpus() for example only access one 64 bytes aligned block : + * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD @@ -3214,8 +3223,9 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ -static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, - bool free_on_error) +static inline int __must_check __skb_put_padto(struct sk_buff *skb, + unsigned int len, + bool free_on_error) { unsigned int size = skb->len; @@ -3238,7 +3248,7 @@ static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ -static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } @@ -3745,19 +3755,19 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 24: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 16: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 20: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 12: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; } diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 1e9ed840b9fc..3119928fc103 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -340,23 +340,6 @@ static inline void sk_psock_update_proto(struct sock *sk, struct sk_psock *psock, struct proto *ops) { - /* Initialize saved callbacks and original proto only once, since this - * function may be called multiple times for a psock, e.g. when - * psock->progs.msg_parser is updated. - * - * Since we've not installed the new proto, psock is not yet in use and - * we can initialize it without synchronization. - */ - if (!psock->sk_proto) { - struct proto *orig = READ_ONCE(sk->sk_prot); - - psock->saved_unhash = orig->unhash; - psock->saved_close = orig->close; - psock->saved_write_space = sk->sk_write_space; - - psock->sk_proto = orig; - } - /* Pairs with lockless read in sk_clone_lock() */ WRITE_ONCE(sk->sk_prot, ops); } diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 49c5d29cd33c..cf27b080e148 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -220,6 +220,9 @@ struct ti_sci_rm_core_ops { u16 *range_start, u16 *range_num); }; +#define TI_SCI_RESASG_SUBTYPE_IR_OUTPUT 0 +#define TI_SCI_RESASG_SUBTYPE_IA_VINT 0xa +#define TI_SCI_RESASG_SUBTYPE_GLOBAL_EVENT_SEVT 0xd /** * struct ti_sci_rm_irq_ops: IRQ management operations * @set_irq: Set an IRQ route between the requested source @@ -556,6 +559,9 @@ u32 ti_sci_get_num_resources(struct ti_sci_resource *res); struct ti_sci_resource * devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, struct device *dev, u32 dev_id, char *of_prop); +struct ti_sci_resource * +devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev, + u32 dev_id, u32 sub_type); #else /* CONFIG_TI_SCI_PROTOCOL */ @@ -609,6 +615,13 @@ devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, { return ERR_PTR(-EINVAL); } + +static inline struct ti_sci_resource * +devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev, + u32 dev_id, u32 sub_type); +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_TI_SCI_PROTOCOL */ #endif /* __TISCI_PROTOCOL_H */ diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 3d5c3271a9a8..a59db2f08e76 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -25,7 +25,7 @@ static inline void stackleak_task_init(struct task_struct *t) #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE int stack_erasing_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); #endif #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 14b62d7df942..2f87377e9af7 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -92,6 +92,8 @@ struct tcp_options_received { smc_ok : 1, /* SMC seen on SYN packet */ snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ + u8 saw_unknown:1, /* Received unknown option */ + unused:7; u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ @@ -132,6 +134,7 @@ struct tcp_request_sock { * FastOpen it's the seq# * after data-in-SYN. */ + u8 syn_tos; }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) @@ -237,14 +240,13 @@ struct tcp_sock { repair : 1, frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; - u8 syn_data:1, /* SYN includes data */ + u8 save_syn:2, /* Save headers of SYN packet */ + syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ syn_fastopen_ch:1, /* Active TFO re-enabling probe */ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ - save_syn:1, /* Save headers of SYN packet */ - is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ - syn_smc:1; /* SYN includes SMC */ + is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ u32 tlp_high_seq; /* snd_nxt at the time of TLP */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ @@ -391,6 +393,9 @@ struct tcp_sock { #if IS_ENABLED(CONFIG_MPTCP) bool is_mptcp; #endif +#if IS_ENABLED(CONFIG_SMC) + bool syn_smc; /* SYN includes SMC */ +#endif #ifdef CONFIG_TCP_MD5SIG /* TCP AF-Specific parts; only used by MD5 Signature support so far */ @@ -406,7 +411,7 @@ struct tcp_sock { * socket. Used to retransmit SYNACKs etc. */ struct request_sock __rcu *fastopen_rsk; - u32 *saved_syn; + struct saved_syn *saved_syn; }; enum tsq_enum { @@ -484,6 +489,12 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) tp->saved_syn = NULL; } +static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn) +{ + return saved_syn->mac_hdrlen + saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; +} + struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, const struct sk_buff *orig_skb); diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 2e6ca53b9bbd..18e75974d4e3 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -30,6 +30,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGFAULT, PGMAJFAULT, PGLAZYFREED, PGREFILL, + PGREUSE, PGSTEAL_KSWAPD, PGSTEAL_DIRECT, PGSCAN_KSWAPD, diff --git a/include/linux/wait.h b/include/linux/wait.h index 898c890fc153..27fb99cfeb02 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -21,6 +21,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int #define WQ_FLAG_WOKEN 0x02 #define WQ_FLAG_BOOKMARK 0x04 #define WQ_FLAG_CUSTOM 0x08 +#define WQ_FLAG_DONE 0x10 /* * A single wait-queue entry structure: diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h index adcc6a97db61..143568d64b20 100644 --- a/include/math-emu/op-common.h +++ b/include/math-emu/op-common.h @@ -308,7 +308,7 @@ do { \ \ case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO): \ R##_e = X##_e; \ - /* Fall through */ \ + fallthrough; \ case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NORMAL): \ case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF): \ case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO): \ @@ -319,7 +319,7 @@ do { \ \ case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NORMAL): \ R##_e = Y##_e; \ - /* Fall through */ \ + fallthrough; \ case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NAN): \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN): \ case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN): \ @@ -417,7 +417,7 @@ do { \ case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF): \ case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO): \ R##_s = X##_s; \ - /* Fall through */ \ + fallthrough; \ \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF): \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL): \ @@ -431,7 +431,7 @@ do { \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN): \ case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN): \ R##_s = Y##_s; \ - /* Fall through */ \ + fallthrough; \ \ case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_INF): \ case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO): \ @@ -497,7 +497,7 @@ do { \ \ case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO): \ FP_SET_EXCEPTION(FP_EX_DIVZERO); \ - /* Fall through */ \ + fallthrough; \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO): \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL): \ R##_c = FP_CLS_INF; \ diff --git a/include/net/addrconf.h b/include/net/addrconf.h index ba3f6c15ad2b..18f783dcd55f 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -97,7 +97,8 @@ bool ipv6_chk_custom_prefix(const struct in6_addr *addr, int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev); -struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr); +struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, + struct net_device *dev); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 91eacbdcf33d..f6abcc0bbd6e 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -59,7 +59,7 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *); -u32 rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *); +bool rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *, u32 *); int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 5036c94c0503..119f4c9c3a9c 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -3,13 +3,27 @@ #ifndef _BPF_SK_STORAGE_H #define _BPF_SK_STORAGE_H +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/bpf.h> +#include <net/sock.h> +#include <uapi/linux/sock_diag.h> +#include <uapi/linux/btf.h> +#include <linux/bpf_local_storage.h> + struct sock; void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; +extern const struct bpf_func_proto sk_storage_get_btf_proto; +extern const struct bpf_func_proto sk_storage_delete_btf_proto; +struct bpf_local_storage_elem; struct bpf_sk_storage_diag; struct sk_buff; struct nlattr; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d9e6b9fbd95b..10c2cc8f0efc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -96,6 +96,16 @@ struct wiphy; * @IEEE80211_CHAN_NO_10MHZ: 10 MHz bandwidth is not permitted * on this channel. * @IEEE80211_CHAN_NO_HE: HE operation is not permitted on this channel. + * @IEEE80211_CHAN_1MHZ: 1 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_2MHZ: 2 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_4MHZ: 4 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_8MHZ: 8 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_16MHZ: 16 MHz bandwidth is permitted + * on this channel. * */ enum ieee80211_channel_flags { @@ -113,6 +123,11 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_NO_20MHZ = 1<<11, IEEE80211_CHAN_NO_10MHZ = 1<<12, IEEE80211_CHAN_NO_HE = 1<<13, + IEEE80211_CHAN_1MHZ = 1<<14, + IEEE80211_CHAN_2MHZ = 1<<15, + IEEE80211_CHAN_4MHZ = 1<<16, + IEEE80211_CHAN_8MHZ = 1<<17, + IEEE80211_CHAN_16MHZ = 1<<18, }; #define IEEE80211_CHAN_NO_HT40 \ @@ -450,6 +465,7 @@ struct ieee80211_sta_s1g_cap { * @ht_cap: HT capabilities in this band * @vht_cap: VHT capabilities in this band * @edmg_cap: EDMG capabilities in this band + * @s1g_cap: S1G capabilities in this band (S1B band only, of course) * @n_iftype_data: number of iftype data entries * @iftype_data: interface type data entries. Note that the bits in * @types_mask inside this structure cannot overlap (i.e. only @@ -678,7 +694,10 @@ struct cfg80211_bitrate_mask { u32 legacy; u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; u16 vht_mcs[NL80211_VHT_NSS_MAX]; + u16 he_mcs[NL80211_HE_NSS_MAX]; enum nl80211_txrate_gi gi; + enum nl80211_he_gi he_gi; + enum nl80211_he_ltf he_ltf; } control[NUM_NL80211_BANDS]; }; @@ -1065,6 +1084,39 @@ struct cfg80211_acl_data { }; /** + * struct cfg80211_fils_discovery - FILS discovery parameters from + * IEEE Std 802.11ai-2016, Annex C.3 MIB detail. + * + * @min_interval: Minimum packet interval in TUs (0 - 10000) + * @max_interval: Maximum packet interval in TUs (0 - 10000) + * @tmpl_len: Template length + * @tmpl: Template data for FILS discovery frame including the action + * frame headers. + */ +struct cfg80211_fils_discovery { + u32 min_interval; + u32 max_interval; + size_t tmpl_len; + const u8 *tmpl; +}; + +/** + * struct cfg80211_unsol_bcast_probe_resp - Unsolicited broadcast probe + * response parameters in 6GHz. + * + * @interval: Packet interval in TUs. Maximum allowed is 20 TU, as mentioned + * in IEEE P802.11ax/D6.0 26.17.2.3.2 - AP behavior for fast passive + * scanning + * @tmpl_len: Template length + * @tmpl: Template data for probe response + */ +struct cfg80211_unsol_bcast_probe_resp { + u32 interval; + size_t tmpl_len; + const u8 *tmpl; +}; + +/** * enum cfg80211_ap_settings_flags - AP settings flags * * Used by cfg80211_ap_settings @@ -1111,6 +1163,8 @@ enum cfg80211_ap_settings_flags { * @he_obss_pd: OBSS Packet Detection settings * @he_bss_color: BSS Color settings * @he_oper: HE operation IE (or %NULL if HE isn't enabled) + * @fils_discovery: FILS discovery transmission parameters + * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1141,6 +1195,8 @@ struct cfg80211_ap_settings { u32 flags; struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; + struct cfg80211_fils_discovery fils_discovery; + struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; }; /** @@ -1784,6 +1840,7 @@ struct mpath_info { * (or NULL for no change) * @basic_rates_len: number of basic rates * @ap_isolate: do not forward packets between connected stations + * (0 = no, 1 = yes, -1 = do not change) * @ht_opmode: HT Operation mode * (u16 = opmode, -1 = do not change) * @p2p_ctwindow: P2P CT Window (-1 = no change) @@ -5276,6 +5333,16 @@ ieee80211_channel_to_khz(const struct ieee80211_channel *chan) } /** + * ieee80211_s1g_channel_width - get allowed channel width from @chan + * + * Only allowed for band NL80211_BAND_S1GHZ + * @chan: channel + * Return: The allowed channel width for this center_freq + */ +enum nl80211_chan_width +ieee80211_s1g_channel_width(const struct ieee80211_channel *chan); + +/** * ieee80211_channel_to_freq_khz - convert channel number to frequency * @chan: channel number * @band: band, necessary due to channel number overlap diff --git a/include/net/devlink.h b/include/net/devlink.h index 8f3c8a443238..4883dbae7faf 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -57,13 +57,30 @@ struct devlink_port_phys_attrs { u32 split_subport_number; /* If the port is split, this is the number of subport. */ }; +/** + * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes + * @controller: Associated controller number + * @pf: Associated PCI PF number for this port. + * @external: when set, indicates if a port is for an external controller + */ struct devlink_port_pci_pf_attrs { - u16 pf; /* Associated PCI PF for this port. */ + u32 controller; + u16 pf; + u8 external:1; }; +/** + * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes + * @controller: Associated controller number + * @pf: Associated PCI PF number for this port. + * @vf: Associated PCI VF for of the PCI PF for this port. + * @external: when set, indicates if a port is for an external controller + */ struct devlink_port_pci_vf_attrs { - u16 pf; /* Associated PCI PF for this port. */ - u16 vf; /* Associated PCI VF for of the PCI PF for this port. */ + u32 controller; + u16 pf; + u16 vf; + u8 external:1; }; /** @@ -73,6 +90,9 @@ struct devlink_port_pci_vf_attrs { * @splittable: indicates if the port can be split. * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink. * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL + * @phys: physical port attributes + * @pci_pf: PCI PF port attributes + * @pci_vf: PCI VF port attributes */ struct devlink_port_attrs { u8 split:1, @@ -372,6 +392,25 @@ struct devlink_param_gset_ctx { }; /** + * struct devlink_flash_notify - devlink dev flash notify data + * @status_msg: current status string + * @component: firmware component being updated + * @done: amount of work completed of total amount + * @total: amount of work expected to be done + * @timeout: expected max timeout in seconds + * + * These are values to be given to userland to be displayed in order + * to show current activity in a firmware update process. + */ +struct devlink_flash_notify { + const char *status_msg; + const char *component; + unsigned long done; + unsigned long total; + unsigned long timeout; +}; + +/** * struct devlink_param - devlink configuration parameter data * @name: name of the parameter * @generic: indicates if the parameter is generic or driver specific @@ -522,12 +561,16 @@ struct devlink_info_req; * the data variable must be updated to point to the snapshot data. * The function will be called while the devlink instance lock is * held. + * @priv: Pointer to driver private data for the region operation */ struct devlink_region_ops { const char *name; void (*destructor)(const void *data); - int (*snapshot)(struct devlink *devlink, struct netlink_ext_ack *extack, + int (*snapshot)(struct devlink *devlink, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, u8 **data); + void *priv; }; struct devlink_fmsg; @@ -546,6 +589,7 @@ enum devlink_health_reporter_state { * @dump: callback to dump an object * if priv_ctx is NULL, run a full dump * @diagnose: callback to diagnose the current status + * @test: callback to trigger a test event */ struct devlink_health_reporter_ops { @@ -558,6 +602,8 @@ struct devlink_health_reporter_ops { int (*diagnose)(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, struct netlink_ext_ack *extack); + int (*test)(struct devlink_health_reporter *reporter, + struct netlink_ext_ack *extack); }; /** @@ -1203,9 +1249,10 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port, void devlink_port_type_clear(struct devlink_port *devlink_port); void devlink_port_attrs_set(struct devlink_port *devlink_port, struct devlink_port_attrs *devlink_port_attrs); -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf); -void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, - u16 pf, u16 vf); +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, bool external); +void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u16 vf, bool external); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, @@ -1379,6 +1426,10 @@ void devlink_flash_update_status_notify(struct devlink *devlink, const char *component, unsigned long done, unsigned long total); +void devlink_flash_update_timeout_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long timeout); int devlink_traps_register(struct devlink *devlink, const struct devlink_trap *traps, diff --git a/include/net/dsa.h b/include/net/dsa.h index 75c8fac82017..d16057c5987a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -612,11 +612,14 @@ struct dsa_switch_ops { bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); - /* Devlink parameters */ + /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); + int (*devlink_info_get)(struct dsa_switch *ds, + struct devlink_info_req *req, + struct netlink_ext_ack *extack); /* * MTU change functionality. Switches can also adjust their MRU through @@ -658,12 +661,25 @@ void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); +struct devlink_region * +dsa_devlink_region_create(struct dsa_switch *ds, + const struct devlink_region_ops *ops, + u32 region_max_snapshots, u64 region_size); +void dsa_devlink_region_destroy(struct devlink_region *region); + struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; +static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) +{ + struct dsa_devlink_priv *dl_priv = devlink_priv(dl); + + return dl_priv->ds; +} + struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; diff --git a/include/net/dst.h b/include/net/dst.h index 6ae2e625050d..8ea8812b0b41 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -214,7 +214,7 @@ dst_allfrag(const struct dst_entry *dst) static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { - return dst_metric(dst, RTAX_LOCK) & (1<<metric); + return dst_metric(dst, RTAX_LOCK) & (1 << metric); } static inline void dst_hold(struct dst_entry *dst) diff --git a/include/net/flow.h b/include/net/flow.h index 929d3ca614d0..b2531df3f65f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -116,6 +116,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = sport; + fl4->flowi4_multipath_hash = 0; } /* Reset some input parameters after previous lookup */ diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 6e5f1e1aa822..b9eb92f3fe86 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -101,14 +101,6 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) -static inline int genl_err_attr(struct genl_info *info, int err, - const struct nlattr *attr) -{ - info->extack->bad_attr = attr; - - return err; -} - enum genl_validate_flags { GENL_DONT_VALIDATE_STRICT = BIT(0), GENL_DONT_VALIDATE_DUMP = BIT(1), diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index aa8893c68c50..dc763ca9413c 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -86,6 +86,8 @@ struct inet_connection_sock { struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; + __u32 icsk_rto_min; + __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; @@ -94,7 +96,8 @@ struct inet_connection_sock { void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); - __u8 icsk_ca_state:6, + __u8 icsk_ca_state:5, + icsk_ca_initialized:1, icsk_ca_setsockopt:1, icsk_ca_dst_locked:1; __u8 icsk_retransmits; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index a3702d1d4875..89163ef8cf4b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -296,13 +296,6 @@ static inline void __inet_sk_copy_descendant(struct sock *sk_to, memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, sk_from->sk_prot->obj_size - ancestor_size); } -#if !(IS_ENABLED(CONFIG_IPV6)) -static inline void inet_sk_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - __inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock)); -} -#endif int inet_sk_rebuild_header(struct sock *sk); diff --git a/include/net/ip.h b/include/net/ip.h index b09c48d862cc..0f72bf8c0cbf 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -151,7 +151,7 @@ int igmp_mc_init(void); int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, - struct ip_options_rcu *opt); + struct ip_options_rcu *opt, u8 tos); int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ip_list_rcv(struct list_head *head, struct packet_type *pt, diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9a59a33787cb..d609e957a3ec 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -25,9 +25,6 @@ #include <linux/ip.h> #include <linux/ipv6.h> /* for struct ipv6hdr */ #include <net/ipv6.h> -#if IS_ENABLED(CONFIG_IP_VS_IPV6) -#include <linux/netfilter_ipv6/ip6_tables.h> -#endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index d7a7f7c81e7b..8fce558b5fea 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -63,6 +63,9 @@ struct ipv6_stub { int encap_type); #endif struct neigh_table *nd_tbl; + + int (*ipv6_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); }; extern const struct ipv6_stub *ipv6_stub __read_mostly; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 66e2bfd165e8..e90089d104b0 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -317,6 +317,9 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_TWT: TWT status changed * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed. * @BSS_CHANGED_HE_BSS_COLOR: BSS Color has changed + * @BSS_CHANGED_FILS_DISCOVERY: FILS discovery status changed. + * @BSS_CHANGED_UNSOL_BCAST_PROBE_RESP: Unsolicited broadcast probe response + * status changed. * */ enum ieee80211_bss_change { @@ -350,6 +353,8 @@ enum ieee80211_bss_change { BSS_CHANGED_TWT = 1<<27, BSS_CHANGED_HE_OBSS_PD = 1<<28, BSS_CHANGED_HE_BSS_COLOR = 1<<29, + BSS_CHANGED_FILS_DISCOVERY = 1<<30, + BSS_CHANGED_UNSOL_BCAST_PROBE_RESP = 1<<31, /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -491,6 +496,18 @@ struct ieee80211_ftm_responder_params { }; /** + * struct ieee80211_fils_discovery - FILS discovery parameters from + * IEEE Std 802.11ai-2016, Annex C.3 MIB detail. + * + * @min_interval: Minimum packet interval in TUs (0 - 10000) + * @max_interval: Maximum packet interval in TUs (0 - 10000) + */ +struct ieee80211_fils_discovery { + u32 min_interval; + u32 max_interval; +}; + +/** * struct ieee80211_bss_conf - holds the BSS's changing parameters * * This structure keeps information about a BSS (and an association @@ -607,6 +624,9 @@ struct ieee80211_ftm_responder_params { * @he_oper: HE operation information of the AP we are connected to * @he_obss_pd: OBSS Packet Detection parameters. * @he_bss_color: BSS coloring settings, if BSS supports HE + * @fils_discovery: FILS discovery configuration + * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response + * interval. */ struct ieee80211_bss_conf { const u8 *bssid; @@ -674,6 +694,8 @@ struct ieee80211_bss_conf { } he_oper; struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; + struct ieee80211_fils_discovery fils_discovery; + u32 unsol_bcast_probe_resp_interval; }; /** @@ -720,9 +742,8 @@ struct ieee80211_bss_conf { * @IEEE80211_TX_INTFL_OFFCHAN_TX_OK: Internal to mac80211. Used to indicate * that a frame can be transmitted while the queues are stopped for * off-channel operation. - * @IEEE80211_TX_INTFL_NEED_TXPROCESSING: completely internal to mac80211, - * used to indicate that a pending frame requires TX processing before - * it can be sent out. + * @IEEE80211_TX_CTL_HW_80211_ENCAP: This frame uses hardware encapsulation + * (header conversion) * @IEEE80211_TX_INTFL_RETRIED: completely internal to mac80211, * used to indicate that a frame was already retried due to PS * @IEEE80211_TX_INTFL_DONT_ENCRYPT: completely internal to mac80211, @@ -791,7 +812,7 @@ enum mac80211_tx_info_flags { IEEE80211_TX_STAT_AMPDU_NO_BACK = BIT(11), IEEE80211_TX_CTL_RATE_CTRL_PROBE = BIT(12), IEEE80211_TX_INTFL_OFFCHAN_TX_OK = BIT(13), - IEEE80211_TX_INTFL_NEED_TXPROCESSING = BIT(14), + IEEE80211_TX_CTL_HW_80211_ENCAP = BIT(14), IEEE80211_TX_INTFL_RETRIED = BIT(15), IEEE80211_TX_INTFL_DONT_ENCRYPT = BIT(16), IEEE80211_TX_CTL_NO_PS_BUFFER = BIT(17), @@ -823,8 +844,9 @@ enum mac80211_tx_info_flags { * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path * @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup - * @IEEE80211_TX_CTRL_HW_80211_ENCAP: This frame uses hardware encapsulation - * (header conversion) + * @IEEE80211_TX_INTCFL_NEED_TXPROCESSING: completely internal to mac80211, + * used to indicate that a pending frame requires TX processing before + * it can be sent out. * @IEEE80211_TX_CTRL_NO_SEQNO: Do not overwrite the sequence number that * has already been assigned to this frame. * @@ -837,7 +859,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_AMSDU = BIT(3), IEEE80211_TX_CTRL_FAST_XMIT = BIT(4), IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5), - IEEE80211_TX_CTRL_HW_80211_ENCAP = BIT(6), + IEEE80211_TX_INTCFL_NEED_TXPROCESSING = BIT(6), IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), }; @@ -1002,7 +1024,8 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * @status.ampdu_ack_len: AMPDU ack length * @status.ampdu_len: AMPDU length * @status.antenna: (legacy, kept only for iwlegacy) - * @status.tx_time: airtime consumed for transmission + * @status.tx_time: airtime consumed for transmission; note this is only + * used for WMM AC, not for airtime fairness * @status.is_valid_ack_signal: ACK signal is valid * @status.status_driver_data: driver use area * @ack: union part for pure ACK data @@ -1095,12 +1118,14 @@ ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info) * @info: Basic tx status information * @skb: Packet skb (can be NULL if not provided by the driver) * @rate: The TX rate that was used when sending the packet + * @free_list: list where processed skbs are stored to be free'd by the driver */ struct ieee80211_tx_status { struct ieee80211_sta *sta; struct ieee80211_tx_info *info; struct sk_buff *skb; struct rate_info *rate; + struct list_head *free_list; }; /** @@ -1606,6 +1631,21 @@ enum ieee80211_vif_flags { IEEE80211_VIF_GET_NOA_UPDATE = BIT(3), }; + +/** + * enum ieee80211_offload_flags - virtual interface offload flags + * + * @IEEE80211_OFFLOAD_ENCAP_ENABLED: tx encapsulation offload is enabled + * The driver supports sending frames passed as 802.3 frames by mac80211. + * It must also support sending 802.11 packets for the same interface. + * @IEEE80211_OFFLOAD_ENCAP_4ADDR: support 4-address mode encapsulation offload + */ + +enum ieee80211_offload_flags { + IEEE80211_OFFLOAD_ENCAP_ENABLED = BIT(0), + IEEE80211_OFFLOAD_ENCAP_4ADDR = BIT(1), +}; + /** * struct ieee80211_vif - per-interface data * @@ -1626,6 +1666,11 @@ enum ieee80211_vif_flags { * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed * at runtime, mac80211 will never touch this field + * @offloaad_flags: hardware offload capabilities/flags for this interface. + * These are initialized by mac80211 before calling .add_interface, + * .change_interface or .update_vif_offload and updated by the driver + * within these ops, based on supported features or runtime change + * restrictions. * @hw_queue: hardware queue for each AC * @cab_queue: content-after-beacon (DTIM beacon really) queue, AP mode only * @chanctx_conf: The channel context this interface is assigned to, or %NULL @@ -1645,6 +1690,8 @@ enum ieee80211_vif_flags { * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped, * protected by fq->lock. + * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see + * &enum ieee80211_offload_flags. */ struct ieee80211_vif { enum nl80211_iftype type; @@ -1662,6 +1709,7 @@ struct ieee80211_vif { struct ieee80211_chanctx_conf __rcu *chanctx_conf; u32 driver_flags; + u32 offload_flags; #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *debugfs_dir; @@ -2328,6 +2376,9 @@ struct ieee80211_txq { * aggregating MPDUs with the same keyid, allowing mac80211 to keep Tx * A-MPDU sessions active while rekeying with Extended Key ID. * + * @IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD: Hardware supports tx encapsulation + * offload + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2380,6 +2431,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_MULTI_BSSID, IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID, IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT, + IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -3736,7 +3788,7 @@ enum ieee80211_reconfig_type { * decremented, and when they reach 1 the driver must call * ieee80211_csa_finish(). Drivers which use ieee80211_beacon_get() * get the csa counter decremented by mac80211, but must check if it is - * 1 using ieee80211_csa_is_complete() after the beacon has been + * 1 using ieee80211_beacon_counter_is_complete() after the beacon has been * transmitted and then call ieee80211_csa_finish(). * If the CSA count starts as zero or 1, this function will not be called, * since there won't be any time to beacon before the switch anyway. @@ -3814,6 +3866,10 @@ enum ieee80211_reconfig_type { * @set_tid_config: Apply TID specific configurations. This callback may sleep. * @reset_tid_config: Reset TID specific configuration for the peer. * This callback may sleep. + * @update_vif_offload: Update virtual interface offload flags + * This callback may sleep. + * @sta_set_4addr: Called to notify the driver when a station starts/stops using + * 4-address mode */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4125,6 +4181,10 @@ struct ieee80211_ops { int (*reset_tid_config)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u8 tids); + void (*update_vif_offload)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); + void (*sta_set_4addr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_sta *sta, bool enabled); }; /** @@ -4763,21 +4823,21 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw, */ void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets); -#define IEEE80211_MAX_CSA_COUNTERS_NUM 2 +#define IEEE80211_MAX_CNTDWN_COUNTERS_NUM 2 /** * struct ieee80211_mutable_offsets - mutable beacon offsets * @tim_offset: position of TIM element * @tim_length: size of TIM element - * @csa_counter_offs: array of IEEE80211_MAX_CSA_COUNTERS_NUM offsets - * to CSA counters. This array can contain zero values which + * @cntdwn_counter_offs: array of IEEE80211_MAX_CNTDWN_COUNTERS_NUM offsets + * to countdown counters. This array can contain zero values which * should be ignored. */ struct ieee80211_mutable_offsets { u16 tim_offset; u16 tim_length; - u16 csa_counter_offs[IEEE80211_MAX_CSA_COUNTERS_NUM]; + u16 cntdwn_counter_offs[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; }; /** @@ -4846,31 +4906,31 @@ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, } /** - * ieee80211_csa_update_counter - request mac80211 to decrement the csa counter + * ieee80211_beacon_update_cntdwn - request mac80211 to decrement the beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * The csa counter should be updated after each beacon transmission. + * The beacon counter should be updated after each beacon transmission. * This function is called implicitly when * ieee80211_beacon_get/ieee80211_beacon_get_tim are called, however if the * beacon frames are generated by the device, the driver should call this - * function after each beacon transmission to sync mac80211's csa counters. + * function after each beacon transmission to sync mac80211's beacon countdown. * - * Return: new csa counter value + * Return: new countdown value */ -u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif); +u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif); /** - * ieee80211_csa_set_counter - request mac80211 to set csa counter + * ieee80211_beacon_set_cntdwn - request mac80211 to set beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @counter: the new value for the counter * - * The csa counter can be changed by the device, this API should be + * The beacon countdown can be changed by the device, this API should be * used by the device driver to update csa counter in mac80211. * - * It should never be used together with ieee80211_csa_update_counter(), + * It should never be used together with ieee80211_beacon_update_cntdwn(), * as it will cause a race condition around the counter value. */ -void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter); +void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter); /** * ieee80211_csa_finish - notify mac80211 about channel switch @@ -4883,13 +4943,12 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter); void ieee80211_csa_finish(struct ieee80211_vif *vif); /** - * ieee80211_csa_is_complete - find out if counters reached 1 + * ieee80211_beacon_cntdwn_is_complete - find out if countdown reached 1 * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * This function returns whether the channel switch counters reached zero. + * This function returns whether the countdown reached zero. */ -bool ieee80211_csa_is_complete(struct ieee80211_vif *vif); - +bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif); /** * ieee80211_proberesp_get - retrieve a Probe Response template @@ -5648,7 +5707,7 @@ void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid); /** * ieee80211_sta_register_airtime - register airtime usage for a sta/tid * - * Register airtime usage for a given sta on a given tid. The driver can call + * Register airtime usage for a given sta on a given tid. The driver must call * this function to notify mac80211 that a station used a certain amount of * airtime. This information will be used by the TXQ scheduler to schedule * stations in a way that ensures airtime fairness. @@ -6594,4 +6653,29 @@ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, */ bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable); +/** + * ieee80211_get_fils_discovery_tmpl - Get FILS discovery template. + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * The driver is responsible for freeing the returned skb. + * + * Return: FILS discovery template. %NULL on error. + */ +struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); + +/** + * ieee80211_get_unsol_bcast_probe_resp_tmpl - Get unsolicited broadcast + * probe response template. + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * The driver is responsible for freeing the returned skb. + * + * Return: Unsolicited broadcast probe response template. %NULL on error. + */ +struct sk_buff * +ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); #endif /* MAC80211_H */ diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 9205a76d967a..38e4094960ce 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -494,7 +494,7 @@ int igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index bf9491b77d16..8ceca0e419b3 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -143,6 +143,8 @@ static inline u64 nft_reg_load64(const u32 *sreg) static inline void nft_data_copy(u32 *dst, const struct nft_data *src, unsigned int len) { + if (len % NFT_REG32_SIZE) + dst[len / NFT_REG32_SIZE] = 0; memcpy(dst, src, len); } @@ -1080,6 +1082,8 @@ struct nft_table { flags:8, genmask:2; char *name; + u16 udlen; + u8 *udata; }; void nft_register_chain_type(const struct nft_chain_type *); @@ -1121,6 +1125,8 @@ struct nft_object { u32 genmask:2, use:30; u64 handle; + u16 udlen; + u8 *udata; /* runtime data below here */ const struct nft_object_ops *ops ____cacheline_aligned; unsigned char data[] diff --git a/include/net/netlink.h b/include/net/netlink.h index c0411f14fb53..b2cf34f53e55 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -181,8 +181,6 @@ enum { NLA_S64, NLA_BITFIELD32, NLA_REJECT, - NLA_EXACT_LEN, - NLA_MIN_LEN, __NLA_TYPE_MAX, }; @@ -199,11 +197,11 @@ struct netlink_range_validation_signed { enum nla_policy_validation { NLA_VALIDATE_NONE, NLA_VALIDATE_RANGE, + NLA_VALIDATE_RANGE_WARN_TOO_LONG, NLA_VALIDATE_MIN, NLA_VALIDATE_MAX, NLA_VALIDATE_RANGE_PTR, NLA_VALIDATE_FUNCTION, - NLA_VALIDATE_WARN_TOO_LONG, }; /** @@ -222,7 +220,7 @@ enum nla_policy_validation { * NLA_NUL_STRING Maximum length of string (excluding NUL) * NLA_FLAG Unused * NLA_BINARY Maximum length of attribute payload - * NLA_MIN_LEN Minimum length of attribute payload + * (but see also below with the validation type) * NLA_NESTED, * NLA_NESTED_ARRAY Length verification is done by checking len of * nested header (or empty); len field is used if @@ -237,11 +235,6 @@ enum nla_policy_validation { * just like "All other" * NLA_BITFIELD32 Unused * NLA_REJECT Unused - * NLA_EXACT_LEN Attribute should have exactly this length, otherwise - * it is rejected or warned about, the latter happening - * if and only if the `validation_type' is set to - * NLA_VALIDATE_WARN_TOO_LONG. - * NLA_MIN_LEN Minimum length of attribute payload * All other Minimum length of attribute payload * * Meaning of validation union: @@ -296,6 +289,11 @@ enum nla_policy_validation { * pointer to a struct netlink_range_validation_signed * that indicates the min/max values. * Use NLA_POLICY_FULL_RANGE_SIGNED(). + * + * NLA_BINARY If the validation type is like the ones for integers + * above, then the min/max length (not value like for + * integers) of the attribute is enforced. + * * All other Unused - but note that it's a union * * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: @@ -309,7 +307,7 @@ enum nla_policy_validation { * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, - * [ATTR_BAZ] = { .type = NLA_EXACT_LEN, .len = sizeof(struct mystruct) }, + * [ATTR_BAZ] = NLA_POLICY_EXACT_LEN(sizeof(struct mystruct)), * [ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags), * }; */ @@ -335,9 +333,10 @@ struct nla_policy { * nesting validation starts here. * * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT - * for any types >= this, so need to use NLA_MIN_LEN to get the - * previous pure { .len = xyz } behaviour. The advantage of this - * is that types not specified in the policy will be rejected. + * for any types >= this, so need to use NLA_POLICY_MIN_LEN() to + * get the previous pure { .len = xyz } behaviour. The advantage + * of this is that types not specified in the policy will be + * rejected. * * For completely new families it should be set to 1 so that the * validation is enforced for all attributes. For existing ones @@ -349,12 +348,6 @@ struct nla_policy { }; }; -#define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len } -#define NLA_POLICY_EXACT_LEN_WARN(_len) \ - { .type = NLA_EXACT_LEN, .len = _len, \ - .validation_type = NLA_VALIDATE_WARN_TOO_LONG, } -#define NLA_POLICY_MIN_LEN(_len) { .type = NLA_MIN_LEN, .len = _len } - #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) @@ -370,19 +363,21 @@ struct nla_policy { { .type = NLA_BITFIELD32, .bitfield32_valid = valid } #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) -#define NLA_ENSURE_UINT_TYPE(tp) \ +#define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_U8 || tp == NLA_U16 || \ tp == NLA_U32 || tp == NLA_U64 || \ - tp == NLA_MSECS) + tp) + tp == NLA_MSECS || \ + tp == NLA_BINARY) + tp) #define NLA_ENSURE_SINT_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_S16 || \ tp == NLA_S32 || tp == NLA_S64) + tp) -#define NLA_ENSURE_INT_TYPE(tp) \ +#define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 || \ tp == NLA_S16 || tp == NLA_U16 || \ tp == NLA_S32 || tp == NLA_U32 || \ tp == NLA_S64 || tp == NLA_U64 || \ - tp == NLA_MSECS) + tp) + tp == NLA_MSECS || \ + tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ (__NLA_ENSURE(tp != NLA_BITFIELD32 && \ tp != NLA_REJECT && \ @@ -390,14 +385,14 @@ struct nla_policy { tp != NLA_NESTED_ARRAY) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE, \ .min = _min, \ .max = _max \ } #define NLA_POLICY_FULL_RANGE(tp, _range) { \ - .type = NLA_ENSURE_UINT_TYPE(tp), \ + .type = NLA_ENSURE_UINT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE_PTR, \ .range = _range, \ } @@ -409,13 +404,13 @@ struct nla_policy { } #define NLA_POLICY_MIN(tp, _min) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MIN, \ .min = _min, \ } #define NLA_POLICY_MAX(tp, _max) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ } @@ -427,6 +422,15 @@ struct nla_policy { .len = __VA_ARGS__ + 0, \ } +#define NLA_POLICY_EXACT_LEN(_len) NLA_POLICY_RANGE(NLA_BINARY, _len, _len) +#define NLA_POLICY_EXACT_LEN_WARN(_len) { \ + .type = NLA_BINARY, \ + .validation_type = NLA_VALIDATE_RANGE_WARN_TOO_LONG, \ + .min = _len, \ + .max = _len \ +} +#define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len) + /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request @@ -726,7 +730,6 @@ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected - * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() @@ -824,7 +827,6 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy - * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 9e36738c1fe1..8e4fcac4df72 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -183,6 +183,7 @@ struct netns_ipv4 { unsigned int sysctl_tcp_fastopen_blackhole_timeout; atomic_t tfo_active_disable_times; unsigned long tfo_active_disable_stamp; + int sysctl_tcp_reflect_tos; int sysctl_udp_wmem_min; int sysctl_udp_rmem_min; diff --git a/include/net/netns/nexthop.h b/include/net/netns/nexthop.h index 1937476c94a0..1849e77eb68a 100644 --- a/include/net/netns/nexthop.h +++ b/include/net/netns/nexthop.h @@ -14,6 +14,6 @@ struct netns_nexthop { unsigned int seq; /* protected by rtnl_mutex */ u32 last_id_allocated; - struct atomic_notifier_head notifier_chain; + struct blocking_notifier_head notifier_chain; }; #endif diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index a1a8d45adb42..6c0806bd8d1e 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -8,6 +8,7 @@ struct netns_nftables { struct list_head tables; struct list_head commit_list; struct list_head module_list; + struct list_head notify_list; struct mutex commit_mutex; unsigned int base_seq; u8 gencursor; diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 3a4f9e3b91a5..2fd76a9b6dc8 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -105,13 +105,9 @@ struct nexthop { }; enum nexthop_event_type { - NEXTHOP_EVENT_ADD, NEXTHOP_EVENT_DEL }; -int call_nexthop_notifier(struct notifier_block *nb, struct net *net, - enum nexthop_event_type event_type, - struct nexthop *nh); int register_nexthop_notifier(struct net *net, struct notifier_block *nb); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index b2eb8b4ba697..29e41ff3ec93 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -41,6 +41,13 @@ struct request_sock_ops { int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); +struct saved_syn { + u32 mac_hdrlen; + u32 network_hdrlen; + u32 tcp_hdrlen; + u8 data[]; +}; + /* struct request_sock - mini sock to represent a connection request */ struct request_sock { @@ -60,7 +67,7 @@ struct request_sock { struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; struct sock *sk; - u32 *saved_syn; + struct saved_syn *saved_syn; u32 secid; u32 peer_secid; }; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d60e7c39d60c..6c762457122f 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1047,12 +1047,6 @@ static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, return 0; } -static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch, - struct sk_buff **to_free) -{ - return __qdisc_queue_drop_head(sch, &sch->q, to_free); -} - static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) { const struct qdisc_skb_head *qh = &sch->q; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index b33f1aefad09..0bdff38eb4bb 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -226,12 +226,14 @@ struct sctp_sock { data_ready_signalled:1; atomic_t pd_mode; + + /* Fields after this point will be skipped on copies, like on accept + * and peeloff operations + */ + /* Receive to here while partial delivery is in effect. */ struct sk_buff_head pd_lobby; - /* These must be the last fields, as they will skipped on copies, - * like on accept and peeloff operations - */ struct list_head auto_asconf_list; int do_auto_asconf; }; diff --git a/include/net/sock.h b/include/net/sock.h index 064637d1ddf6..eaa5cac5e836 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -246,7 +246,7 @@ struct sock_common { /* public: */ }; -struct bpf_sk_storage; +struct bpf_local_storage; /** * struct sock - network layer representation of sockets @@ -517,7 +517,7 @@ struct sock { void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL - struct bpf_sk_storage __rcu *sk_bpf_storage; + struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; }; @@ -845,7 +845,6 @@ enum sock_flags { SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ - SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */ SOCK_MEMALLOC, /* VM depends on this socket for swapping */ SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ SOCK_FASYNC, /* fasync() active */ @@ -1478,7 +1477,7 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { if (!sk_has_account(sk)) return true; - return size<= sk->sk_forward_alloc || + return size <= sk->sk_forward_alloc || __sk_mem_schedule(sk, size, SK_MEM_RECV) || skb_pfmemalloc(skb); } @@ -1526,7 +1525,6 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { - sock_set_flag(sk, SOCK_QUEUE_SHRUNK); sk_wmem_queued_add(sk, -skb->truesize); sk_mem_uncharge(sk, skb->truesize); if (static_branch_unlikely(&tcp_tx_skb_cache_key) && diff --git a/include/net/switchdev.h b/include/net/switchdev.h index ff2246914301..53e8b4994296 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -203,6 +203,7 @@ enum switchdev_notifier_type { SWITCHDEV_FDB_ADD_TO_DEVICE, SWITCHDEV_FDB_DEL_TO_DEVICE, SWITCHDEV_FDB_OFFLOADED, + SWITCHDEV_FDB_FLUSH_TO_BRIDGE, SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */ SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */ diff --git a/include/net/tcp.h b/include/net/tcp.h index eab6c7510b5b..3601dea931a6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -394,7 +394,7 @@ void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); -void tcp_init_transfer(struct sock *sk, int bpf_op); +void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, @@ -455,7 +455,8 @@ enum tcp_synack_type { struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type); + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); @@ -699,7 +700,7 @@ static inline void tcp_fast_path_check(struct sock *sk) static inline u32 tcp_rto_min(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); - u32 rto_min = TCP_RTO_MIN; + u32 rto_min = inet_csk(sk)->icsk_rto_min; if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); @@ -941,16 +942,6 @@ INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb)); #endif -static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb) -{ -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - if (!net->ipv4.sysctl_tcp_l3mdev_accept && - skb && ipv4_l3mdev_skb(IPCB(skb)->flags)) - return true; -#endif - return false; -} - /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { @@ -1113,7 +1104,7 @@ void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, - bool reinit, bool cap_net_admin); + bool cap_net_admin); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); @@ -1423,6 +1414,8 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } +void tcp_cleanup_rbuf(struct sock *sk, int copied); + /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override * SO_RCVLOWAT constraint, since we are receiving skbs with too small @@ -2035,7 +2028,8 @@ struct tcp_request_sock_ops { int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type); + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb); }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; @@ -2233,6 +2227,55 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ +#ifdef CONFIG_CGROUP_BPF +/* Copy the listen sk's HDR_OPT_CB flags to its child. + * + * During 3-Way-HandShake, the synack is usually sent from + * the listen sk with the HDR_OPT_CB flags set so that + * bpf-prog will be called to write the BPF hdr option. + * + * In fastopen, the child sk is used to send synack instead + * of the listen sk. Thus, inheriting the HDR_OPT_CB flags + * from the listen sk gives the bpf-prog a chance to write + * BPF hdr option in the synack pkt during fastopen. + * + * Both fastopen and non-fastopen child will inherit the + * HDR_OPT_CB flags to keep the bpf-prog having a consistent + * behavior when deciding to clear this cb flags (or not) + * during the PASSIVE_ESTABLISHED_CB. + * + * In the future, other cb flags could be inherited here also. + */ +static inline void bpf_skops_init_child(const struct sock *sk, + struct sock *child) +{ + tcp_sk(child)->bpf_sock_ops_cb_flags = + tcp_sk(sk)->bpf_sock_ops_cb_flags & + (BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG | + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG); +} + +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ + skops->skb = skb; + skops->skb_data_end = skb->data + end_offset; +} +#else +static inline void bpf_skops_init_child(const struct sock *sk, + struct sock *child) +{ +} + +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ +} +#endif + /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 3a41627cbdfe..08537aa14f7c 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -121,6 +121,9 @@ struct vxlanhdr_gbp { #define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16) #define VXLAN_GBP_ID_MASK (0xFFFF) +#define VXLAN_GBP_MASK (VXLAN_GBP_DONT_LEARN | VXLAN_GBP_POLICY_APPLIED | \ + VXLAN_GBP_ID_MASK) + /* * VXLAN Generic Protocol Extension (VXLAN_F_GPE): * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index c9d87cc40c11..1a9559c0cbdd 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -18,25 +18,19 @@ struct xsk_queue; struct xdp_buff; struct xdp_umem { - struct xsk_queue *fq; - struct xsk_queue *cq; - struct xsk_buff_pool *pool; + void *addrs; u64 size; u32 headroom; u32 chunk_size; + u32 chunks; + u32 npgs; struct user_struct *user; refcount_t users; - struct work_struct work; - struct page **pgs; - u32 npgs; - u16 queue_id; - u8 need_wakeup; u8 flags; - int id; - struct net_device *dev; bool zc; - spinlock_t xsk_tx_list_lock; - struct list_head xsk_tx_list; + struct page **pgs; + int id; + struct list_head xsk_dma_list; }; struct xsk_map { @@ -48,10 +42,11 @@ struct xsk_map { struct xdp_sock { /* struct sock must be the first member of struct xdp_sock */ struct sock sk; - struct xsk_queue *rx; + struct xsk_queue *rx ____cacheline_aligned_in_smp; struct net_device *dev; struct xdp_umem *umem; struct list_head flush_node; + struct xsk_buff_pool *pool; u16 queue_id; bool zc; enum { @@ -59,10 +54,9 @@ struct xdp_sock { XSK_BOUND, XSK_UNBOUND, } state; - /* Protects multiple processes in the control path */ - struct mutex mutex; + struct xsk_queue *tx ____cacheline_aligned_in_smp; - struct list_head list; + struct list_head tx_list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths * in the SKB destructor callback. */ @@ -77,6 +71,10 @@ struct xdp_sock { struct list_head map_list; /* Protects map_list */ spinlock_t map_list_lock; + /* Protects multiple processes in the control path */ + struct mutex mutex; + struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */ + struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */ }; #ifdef CONFIG_XDP_SOCKETS diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index ccf848f7efa4..5b1ee8a9976d 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -11,47 +11,50 @@ #ifdef CONFIG_XDP_SOCKETS -void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); -bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); -void xsk_umem_consume_tx_done(struct xdp_umem *umem); -struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id); -void xsk_set_rx_need_wakeup(struct xdp_umem *umem); -void xsk_set_tx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_rx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_tx_need_wakeup(struct xdp_umem *umem); -bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem); +void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); +bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc); +void xsk_tx_release(struct xsk_buff_pool *pool); +struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, + u16 queue_id); +void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool); +bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool); -static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool) { - return XDP_PACKET_HEADROOM + umem->headroom; + return XDP_PACKET_HEADROOM + pool->headroom; } -static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool) { - return umem->chunk_size; + return pool->chunk_size; } -static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) { - return xsk_umem_get_chunk_size(umem) - xsk_umem_get_headroom(umem); + return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool); } -static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, +static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { - xp_set_rxq_info(umem->pool, rxq); + xp_set_rxq_info(pool, rxq); } -static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, +static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { - xp_dma_unmap(umem->pool, attrs); + xp_dma_unmap(pool, attrs); } -static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, - unsigned long attrs) +static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool, + struct device *dev, unsigned long attrs) { - return xp_dma_map(umem->pool, dev, attrs, umem->pgs, umem->npgs); + struct xdp_umem *umem = pool->umem; + + return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs); } static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp) @@ -68,14 +71,14 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) return xp_get_frame_dma(xskb); } -static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) { - return xp_alloc(umem->pool); + return xp_alloc(pool); } -static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { - return xp_can_alloc(umem->pool, count); + return xp_can_alloc(pool, count); } static inline void xsk_buff_free(struct xdp_buff *xdp) @@ -85,100 +88,104 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) xp_free(xskb); } -static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, + u64 addr) { - return xp_raw_get_dma(umem->pool, addr); + return xp_raw_get_dma(pool, addr); } -static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { - return xp_raw_get_data(umem->pool, addr); + return xp_raw_get_data(pool, addr); } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + if (!pool->dma_need_sync) + return; + xp_dma_sync_for_cpu(xskb); } -static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, +static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { - xp_dma_sync_for_device(umem->pool, dma, size); + xp_dma_sync_for_device(pool, dma, size); } #else -static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { } -static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, - struct xdp_desc *desc) +static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, + struct xdp_desc *desc) { return false; } -static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) +static inline void xsk_tx_release(struct xsk_buff_pool *pool) { } -static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, - u16 queue_id) +static inline struct xsk_buff_pool * +xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id) { return NULL; } -static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) +static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) { return false; } -static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool) { return 0; } -static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool) { return 0; } -static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) { return 0; } -static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, +static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { } -static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, +static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { } -static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, - unsigned long attrs) +static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool, + struct device *dev, unsigned long attrs) { return 0; } @@ -193,12 +200,12 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) return 0; } -static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) { return NULL; } -static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { return false; } @@ -207,21 +214,22 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) { } -static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, + u64 addr) { return 0; } -static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { return NULL; } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { } -static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, +static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 6842990e2712..0140d086dc84 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -13,6 +13,8 @@ struct xsk_buff_pool; struct xdp_rxq_info; struct xsk_queue; struct xdp_desc; +struct xdp_umem; +struct xdp_sock; struct device; struct page; @@ -26,34 +28,68 @@ struct xdp_buff_xsk { struct list_head free_list_node; }; +struct xsk_dma_map { + dma_addr_t *dma_pages; + struct device *dev; + struct net_device *netdev; + refcount_t users; + struct list_head list; /* Protected by the RTNL_LOCK */ + u32 dma_pages_cnt; + bool dma_need_sync; +}; + struct xsk_buff_pool { - struct xsk_queue *fq; + /* Members only used in the control path first. */ + struct device *dev; + struct net_device *netdev; + struct list_head xsk_tx_list; + /* Protects modifications to the xsk_tx_list */ + spinlock_t xsk_tx_list_lock; + refcount_t users; + struct xdp_umem *umem; + struct work_struct work; struct list_head free_list; + u32 heads_cnt; + u16 queue_id; + + /* Data path members as close to free_heads at the end as possible. */ + struct xsk_queue *fq ____cacheline_aligned_in_smp; + struct xsk_queue *cq; + /* For performance reasons, each buff pool has its own array of dma_pages + * even when they are identical. + */ dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; u64 chunk_mask; u64 addrs_cnt; u32 free_list_cnt; u32 dma_pages_cnt; - u32 heads_cnt; u32 free_heads_cnt; u32 headroom; u32 chunk_size; u32 frame_len; + u8 cached_need_wakeup; + bool uses_need_wakeup; bool dma_need_sync; bool unaligned; void *addrs; - struct device *dev; struct xdp_buff_xsk *free_heads[]; }; /* AF_XDP core. */ -struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, - u32 chunk_size, u32 headroom, u64 size, - bool unaligned); -void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq); +struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, + struct xdp_umem *umem); +int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, + u16 queue_id, u16 flags); +int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, + struct net_device *dev, u16 queue_id); void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); +void xp_get_pool(struct xsk_buff_pool *pool); +void xp_put_pool(struct xsk_buff_pool *pool); +void xp_clear_dev(struct xsk_buff_pool *pool); +void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); +void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); /* AF_XDP, and XDP core. */ void xp_free(struct xdp_buff_xsk *xskb); @@ -80,9 +116,6 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb); static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { - if (!xskb->pool->dma_need_sync) - return; - xp_dma_sync_for_cpu_slow(xskb); } diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index da369b12005f..0ac4e7fba086 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -566,6 +566,7 @@ struct ocelot_port { u8 ptp_cmd; struct sk_buff_head tx_skbs; u8 ts_id; + spinlock_t ts_id_lock; phy_interface_t phy_mode; @@ -677,6 +678,7 @@ void ocelot_configure_cpu(struct ocelot *ocelot, int npi, int ocelot_init(struct ocelot *ocelot); void ocelot_deinit(struct ocelot *ocelot); void ocelot_init_port(struct ocelot *ocelot, int port); +void ocelot_deinit_port(struct ocelot *ocelot, int port); /* DSA callbacks */ void ocelot_port_enable(struct ocelot *ocelot, int port, diff --git a/include/soc/mscc/ocelot_ptp.h b/include/soc/mscc/ocelot_ptp.h index 4a6b2f71b6b2..6a7388fa7cc5 100644 --- a/include/soc/mscc/ocelot_ptp.h +++ b/include/soc/mscc/ocelot_ptp.h @@ -53,6 +53,7 @@ int ocelot_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, enum ptp_pin_function func, unsigned int chan); int ocelot_ptp_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on); -int ocelot_init_timestamp(struct ocelot *ocelot, struct ptp_clock_info *info); +int ocelot_init_timestamp(struct ocelot *ocelot, + const struct ptp_clock_info *info); int ocelot_deinit_timestamp(struct ocelot *ocelot); #endif diff --git a/include/soc/nps/common.h b/include/soc/nps/common.h index 9b1d43d671a3..8c18dc6d3fde 100644 --- a/include/soc/nps/common.h +++ b/include/soc/nps/common.h @@ -45,6 +45,12 @@ #define CTOP_INST_MOV2B_FLIP_R3_B1_B2_INST 0x5B60 #define CTOP_INST_MOV2B_FLIP_R3_B1_B2_LIMM 0x00010422 +#ifndef AUX_IENABLE +#define AUX_IENABLE 0x40c +#endif + +#define CTOP_AUX_IACK (0xFFFFF800 + 0x088) + #ifndef __ASSEMBLY__ /* In order to increase compilation test coverage */ diff --git a/include/sound/soc.h b/include/sound/soc.h index 5e3919ffb00c..fc4fcac72cf7 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1193,6 +1193,8 @@ struct snd_soc_pcm_runtime { ((i) < (rtd)->num_cpus + (rtd)->num_codecs) && \ ((dai) = (rtd)->dais[i]); \ (i)++) +#define for_each_rtd_dais_rollback(rtd, i, dai) \ + for (; (--(i) >= 0) && ((dai) = (rtd)->dais[i]);) void snd_soc_close_delayed_work(struct snd_soc_pcm_runtime *rtd); @@ -1361,6 +1363,8 @@ void snd_soc_unregister_dai(struct snd_soc_dai *dai); struct snd_soc_dai *snd_soc_find_dai( const struct snd_soc_dai_link_component *dlc); +struct snd_soc_dai *snd_soc_find_dai_with_mutex( + const struct snd_soc_dai_link_component *dlc); #include <sound/soc-dai.h> diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index cc41d692ae8e..4c8b99ec8606 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -746,24 +746,29 @@ TRACE_EVENT(ext4_mb_release_group_pa, ); TRACE_EVENT(ext4_discard_preallocations, - TP_PROTO(struct inode *inode), + TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed), - TP_ARGS(inode), + TP_ARGS(inode, len, needed), TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( unsigned int, len ) + __field( unsigned int, needed ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; + __entry->len = len; + __entry->needed = needed; ), - TP_printk("dev %d,%d ino %lu", + TP_printk("dev %d,%d ino %lu len: %u needed %u", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino) + (unsigned long) __entry->ino, __entry->len, + __entry->needed) ); TRACE_EVENT(ext4_mb_discard_preallocations, @@ -1312,18 +1317,34 @@ DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load, TP_ARGS(sb, group) ); -DEFINE_EVENT(ext4__bitmap_load, ext4_read_block_bitmap_load, +DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); -DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, +TRACE_EVENT(ext4_read_block_bitmap_load, + TP_PROTO(struct super_block *sb, unsigned long group, bool prefetch), - TP_PROTO(struct super_block *sb, unsigned long group), + TP_ARGS(sb, group, prefetch), - TP_ARGS(sb, group) + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + __field( bool, prefetch ) + + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + __entry->prefetch = prefetch; + ), + + TP_printk("dev %d,%d group %u prefetch %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->group, __entry->prefetch) ); TRACE_EVENT(ext4_direct_IO_enter, @@ -2726,6 +2747,50 @@ TRACE_EVENT(ext4_error, __entry->function, __entry->line) ); +TRACE_EVENT(ext4_prefetch_bitmaps, + TP_PROTO(struct super_block *sb, ext4_group_t group, + ext4_group_t next, unsigned int prefetch_ios), + + TP_ARGS(sb, group, next, prefetch_ios), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + __field( __u32, next ) + __field( __u32, ios ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + __entry->next = next; + __entry->ios = prefetch_ios; + ), + + TP_printk("dev %d,%d group %u next %u ios %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->group, __entry->next, __entry->ios) +); + +TRACE_EVENT(ext4_lazy_itable_init, + TP_PROTO(struct super_block *sb, ext4_group_t group), + + TP_ARGS(sb, group), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + ), + + TP_printk("dev %d,%d group %u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 939092dbcb8b..5fb752034386 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -114,6 +114,8 @@ IF_HAVE_PG_IDLE(PG_idle, "idle" ) #if defined(CONFIG_X86) #define __VM_ARCH_SPECIFIC_1 {VM_PAT, "pat" } +#elif defined(CONFIG_PPC) +#define __VM_ARCH_SPECIFIC_1 {VM_SAO, "sao" } #elif defined(CONFIG_PARISC) || defined(CONFIG_IA64) #define __VM_ARCH_SPECIFIC_1 {VM_GROWSUP, "growsup" } #elif !defined(CONFIG_MMU) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 059b6e45a028..e70c90116eda 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -68,21 +68,14 @@ enum rxrpc_client_trace { rxrpc_client_chan_activate, rxrpc_client_chan_disconnect, rxrpc_client_chan_pass, - rxrpc_client_chan_unstarted, rxrpc_client_chan_wait_failed, rxrpc_client_cleanup, - rxrpc_client_count, rxrpc_client_discard, rxrpc_client_duplicate, rxrpc_client_exposed, rxrpc_client_replace, rxrpc_client_to_active, - rxrpc_client_to_culled, rxrpc_client_to_idle, - rxrpc_client_to_inactive, - rxrpc_client_to_upgrade, - rxrpc_client_to_waiting, - rxrpc_client_uncount, }; enum rxrpc_call_trace { @@ -138,11 +131,16 @@ enum rxrpc_recvmsg_trace { }; enum rxrpc_rtt_tx_trace { + rxrpc_rtt_tx_cancel, rxrpc_rtt_tx_data, + rxrpc_rtt_tx_no_slot, rxrpc_rtt_tx_ping, }; enum rxrpc_rtt_rx_trace { + rxrpc_rtt_rx_cancel, + rxrpc_rtt_rx_lost, + rxrpc_rtt_rx_obsolete, rxrpc_rtt_rx_ping_response, rxrpc_rtt_rx_requested_ack, }; @@ -266,29 +264,14 @@ enum rxrpc_tx_point { EM(rxrpc_client_chan_activate, "ChActv") \ EM(rxrpc_client_chan_disconnect, "ChDisc") \ EM(rxrpc_client_chan_pass, "ChPass") \ - EM(rxrpc_client_chan_unstarted, "ChUnst") \ EM(rxrpc_client_chan_wait_failed, "ChWtFl") \ EM(rxrpc_client_cleanup, "Clean ") \ - EM(rxrpc_client_count, "Count ") \ EM(rxrpc_client_discard, "Discar") \ EM(rxrpc_client_duplicate, "Duplic") \ EM(rxrpc_client_exposed, "Expose") \ EM(rxrpc_client_replace, "Replac") \ EM(rxrpc_client_to_active, "->Actv") \ - EM(rxrpc_client_to_culled, "->Cull") \ - EM(rxrpc_client_to_idle, "->Idle") \ - EM(rxrpc_client_to_inactive, "->Inac") \ - EM(rxrpc_client_to_upgrade, "->Upgd") \ - EM(rxrpc_client_to_waiting, "->Wait") \ - E_(rxrpc_client_uncount, "Uncoun") - -#define rxrpc_conn_cache_states \ - EM(RXRPC_CONN_CLIENT_INACTIVE, "Inac") \ - EM(RXRPC_CONN_CLIENT_WAITING, "Wait") \ - EM(RXRPC_CONN_CLIENT_ACTIVE, "Actv") \ - EM(RXRPC_CONN_CLIENT_UPGRADE, "Upgd") \ - EM(RXRPC_CONN_CLIENT_CULLED, "Cull") \ - E_(RXRPC_CONN_CLIENT_IDLE, "Idle") \ + E_(rxrpc_client_to_idle, "->Idle") #define rxrpc_call_traces \ EM(rxrpc_call_connected, "CON") \ @@ -339,10 +322,15 @@ enum rxrpc_tx_point { E_(rxrpc_recvmsg_wait, "WAIT") #define rxrpc_rtt_tx_traces \ + EM(rxrpc_rtt_tx_cancel, "CNCE") \ EM(rxrpc_rtt_tx_data, "DATA") \ + EM(rxrpc_rtt_tx_no_slot, "FULL") \ E_(rxrpc_rtt_tx_ping, "PING") #define rxrpc_rtt_rx_traces \ + EM(rxrpc_rtt_rx_cancel, "CNCL") \ + EM(rxrpc_rtt_rx_obsolete, "OBSL") \ + EM(rxrpc_rtt_rx_lost, "LOST") \ EM(rxrpc_rtt_rx_ping_response, "PONG") \ E_(rxrpc_rtt_rx_requested_ack, "RACK") @@ -584,23 +572,20 @@ TRACE_EVENT(rxrpc_client, __field(int, channel ) __field(int, usage ) __field(enum rxrpc_client_trace, op ) - __field(enum rxrpc_conn_cache_state, cs ) ), TP_fast_assign( - __entry->conn = conn->debug_id; + __entry->conn = conn ? conn->debug_id : 0; __entry->channel = channel; - __entry->usage = atomic_read(&conn->usage); + __entry->usage = conn ? atomic_read(&conn->usage) : -2; __entry->op = op; - __entry->cid = conn->proto.cid; - __entry->cs = conn->cache_state; + __entry->cid = conn ? conn->proto.cid : 0; ), - TP_printk("C=%08x h=%2d %s %s i=%08x u=%d", + TP_printk("C=%08x h=%2d %s i=%08x u=%d", __entry->conn, __entry->channel, __print_symbolic(__entry->op, rxrpc_client_traces), - __print_symbolic(__entry->cs, rxrpc_conn_cache_states), __entry->cid, __entry->usage) ); @@ -1087,38 +1072,43 @@ TRACE_EVENT(rxrpc_recvmsg, TRACE_EVENT(rxrpc_rtt_tx, TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_tx_trace why, - rxrpc_serial_t send_serial), + int slot, rxrpc_serial_t send_serial), - TP_ARGS(call, why, send_serial), + TP_ARGS(call, why, slot, send_serial), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_rtt_tx_trace, why ) + __field(int, slot ) __field(rxrpc_serial_t, send_serial ) ), TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; + __entry->slot = slot; __entry->send_serial = send_serial; ), - TP_printk("c=%08x %s sr=%08x", + TP_printk("c=%08x [%d] %s sr=%08x", __entry->call, + __entry->slot, __print_symbolic(__entry->why, rxrpc_rtt_tx_traces), __entry->send_serial) ); TRACE_EVENT(rxrpc_rtt_rx, TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + int slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, u32 rtt, u32 rto), - TP_ARGS(call, why, send_serial, resp_serial, rtt, rto), + TP_ARGS(call, why, slot, send_serial, resp_serial, rtt, rto), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_rtt_rx_trace, why ) + __field(int, slot ) __field(rxrpc_serial_t, send_serial ) __field(rxrpc_serial_t, resp_serial ) __field(u32, rtt ) @@ -1128,14 +1118,16 @@ TRACE_EVENT(rxrpc_rtt_rx, TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; + __entry->slot = slot; __entry->send_serial = send_serial; __entry->resp_serial = resp_serial; __entry->rtt = rtt; __entry->rto = rto; ), - TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%u rto=%u", + TP_printk("c=%08x [%d] %s sr=%08x rr=%08x rtt=%u rto=%u", __entry->call, + __entry->slot, __print_symbolic(__entry->why, rxrpc_rtt_rx_traces), __entry->send_serial, __entry->resp_serial, diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 10f5d1fa7347..e7cbccc7c14c 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -20,7 +20,6 @@ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ - {I_DIRTY_TIME_EXPIRED, "I_DIRTY_TIME_EXPIRED"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) @@ -498,8 +497,9 @@ DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, + unsigned long dirtied_before, int moved), - TP_ARGS(wb, work, moved), + TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) @@ -509,19 +509,17 @@ TRACE_EVENT(writeback_queue_io, __field(ino_t, cgroup_ino) ), TP_fast_assign( - unsigned long *older_than_this = work->older_than_this; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); - __entry->older = older_than_this ? *older_than_this : 0; - __entry->age = older_than_this ? - (jiffies - *older_than_this) * 1000 / HZ : -1; + __entry->older = dirtied_before; + __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu", __entry->name, - __entry->older, /* older_than_this in jiffies */ - __entry->age, /* older_than_this in relative milliseconds */ + __entry->older, /* dirtied_before in jiffies */ + __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0480f893facd..a22812561064 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -124,6 +124,7 @@ enum bpf_cmd { BPF_ENABLE_STATS, BPF_ITER_CREATE, BPF_LINK_DETACH, + BPF_PROG_BIND_MAP, }; enum bpf_map_type { @@ -155,6 +156,7 @@ enum bpf_map_type { BPF_MAP_TYPE_DEVMAP_HASH, BPF_MAP_TYPE_STRUCT_OPS, BPF_MAP_TYPE_RINGBUF, + BPF_MAP_TYPE_INODE_STORAGE, }; /* Note that tracing related programs such as @@ -345,6 +347,14 @@ enum bpf_link_type { /* The verifier internal test flag. Behavior is undefined */ #define BPF_F_TEST_STATE_FREQ (1U << 3) +/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will + * restrict map and helper usage for such programs. Sleepable BPF programs can + * only be attached to hooks where kernel execution context allows sleeping. + * Such programs are allowed to use helpers that may sleep like + * bpf_copy_from_user(). + */ +#define BPF_F_SLEEPABLE (1U << 4) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * @@ -649,6 +659,12 @@ union bpf_attr { __u32 flags; } iter_create; + struct { /* struct used by BPF_PROG_BIND_MAP command */ + __u32 prog_fd; + __u32 map_fd; + __u32 flags; /* extra flags */ + } prog_bind_map; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -767,7 +783,7 @@ union bpf_attr { * * Also, note that **bpf_trace_printk**\ () is slow, and should * only be used for debugging purposes. For this reason, a notice - * bloc (spanning several lines) is printed to kernel logs and + * block (spanning several lines) is printed to kernel logs and * states that the helper should not be used "for production use" * the first time this helper is used (or more precisely, when * **trace_printk**\ () buffers are allocated). For passing values @@ -1033,14 +1049,14 @@ union bpf_attr { * * int ret; * struct bpf_tunnel_key key = {}; - * + * * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); * if (ret < 0) * return TC_ACT_SHOT; // drop packet - * + * * if (key.remote_ipv4 != 0x0a000001) * return TC_ACT_SHOT; // drop packet - * + * * return TC_ACT_OK; // accept packet * * This interface can also be used with all encapsulation devices @@ -1147,7 +1163,7 @@ union bpf_attr { * Description * Retrieve the realm or the route, that is to say the * **tclassid** field of the destination for the *skb*. The - * indentifier retrieved is a user-provided tag, similar to the + * identifier retrieved is a user-provided tag, similar to the * one used with the net_cls cgroup (see description for * **bpf_get_cgroup_classid**\ () helper), but here this tag is * held by a route (a destination entry), not by a task. @@ -1438,8 +1454,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if the *skb* task belongs to the cgroup2. - * * 1, if the *skb* task does not belong to the cgroup2. + * * 0, if current task belongs to the cgroup2. + * * 1, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) @@ -2807,7 +2823,7 @@ union bpf_attr { * * **-ERANGE** if resulting value was out of range. * - * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags) * Description * Get a bpf-local-storage from a *sk*. * @@ -2823,6 +2839,9 @@ union bpf_attr { * "type". The bpf-local-storage "type" (i.e. the *map*) is * searched against all bpf-local-storages residing at *sk*. * + * *sk* is a kernel **struct sock** pointer for LSM program. + * *sk* is a **struct bpf_sock** pointer for other program types. + * * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be * used such that a new bpf-local-storage will be * created if one does not exist. *value* can be used @@ -2835,7 +2854,7 @@ union bpf_attr { * **NULL** if not found or there was an error in adding * a new bpf-local-storage. * - * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * long bpf_sk_storage_delete(struct bpf_map *map, void *sk) * Description * Delete a bpf-local-storage from a *sk*. * Return @@ -3337,38 +3356,38 @@ union bpf_attr { * Description * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer. * Return - * *sk* if casting is valid, or NULL otherwise. + * *sk* if casting is valid, or **NULL** otherwise. * * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk) * Description * Dynamically cast a *sk* pointer to a *tcp_sock* pointer. * Return - * *sk* if casting is valid, or NULL otherwise. + * *sk* if casting is valid, or **NULL** otherwise. * * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk) * Description * Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer. * Return - * *sk* if casting is valid, or NULL otherwise. + * *sk* if casting is valid, or **NULL** otherwise. * * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk) * Description * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer. * Return - * *sk* if casting is valid, or NULL otherwise. + * *sk* if casting is valid, or **NULL** otherwise. * * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk) * Description * Dynamically cast a *sk* pointer to a *udp6_sock* pointer. * Return - * *sk* if casting is valid, or NULL otherwise. + * *sk* if casting is valid, or **NULL** otherwise. * * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags) * Description * Return a user or a kernel stack in bpf program provided buffer. * To achieve this, the helper needs *task*, which is a valid - * pointer to struct task_struct. To store the stacktrace, the - * bpf program provides *buf* with a nonnegative *size*. + * pointer to **struct task_struct**. To store the stacktrace, the + * bpf program provides *buf* with a nonnegative *size*. * * The last argument, *flags*, holds the number of stack frames to * skip (from 0 to 255), masked with @@ -3395,6 +3414,178 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * + * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) + * Description + * Load header option. Support reading a particular TCP header + * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**). + * + * If *flags* is 0, it will search the option from the + * *skops*\ **->skb_data**. The comment in **struct bpf_sock_ops** + * has details on what skb_data contains under different + * *skops*\ **->op**. + * + * The first byte of the *searchby_res* specifies the + * kind that it wants to search. + * + * If the searching kind is an experimental kind + * (i.e. 253 or 254 according to RFC6994). It also + * needs to specify the "magic" which is either + * 2 bytes or 4 bytes. It then also needs to + * specify the size of the magic by using + * the 2nd byte which is "kind-length" of a TCP + * header option and the "kind-length" also + * includes the first 2 bytes "kind" and "kind-length" + * itself as a normal TCP header option also does. + * + * For example, to search experimental kind 254 with + * 2 byte magic 0xeB9F, the searchby_res should be + * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. + * + * To search for the standard window scale option (3), + * the *searchby_res* should be [ 3, 0, 0, .... 0 ]. + * Note, kind-length must be 0 for regular option. + * + * Searching for No-Op (0) and End-of-Option-List (1) are + * not supported. + * + * *len* must be at least 2 bytes which is the minimal size + * of a header option. + * + * Supported flags: + * + * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the + * saved_syn packet or the just-received syn packet. + * + * Return + * > 0 when found, the header option is copied to *searchby_res*. + * The return value is the total length copied. On failure, a + * negative error code is returned: + * + * **-EINVAL** if a parameter is invalid. + * + * **-ENOMSG** if the option is not found. + * + * **-ENOENT** if no syn packet is available when + * **BPF_LOAD_HDR_OPT_TCP_SYN** is used. + * + * **-ENOSPC** if there is not enough space. Only *len* number of + * bytes are copied. + * + * **-EFAULT** on failure to parse the header options in the + * packet. + * + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. + * + * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags) + * Description + * Store header option. The data will be copied + * from buffer *from* with length *len* to the TCP header. + * + * The buffer *from* should have the whole option that + * includes the kind, kind-length, and the actual + * option data. The *len* must be at least kind-length + * long. The kind-length does not have to be 4 byte + * aligned. The kernel will take care of the padding + * and setting the 4 bytes aligned value to th->doff. + * + * This helper will check for duplicated option + * by searching the same option in the outgoing skb. + * + * This helper can only be called during + * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** If param is invalid. + * + * **-ENOSPC** if there is not enough space in the header. + * Nothing has been written + * + * **-EEXIST** if the option already exists. + * + * **-EFAULT** on failrue to parse the existing header options. + * + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. + * + * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags) + * Description + * Reserve *len* bytes for the bpf header option. The + * space will be used by **bpf_store_hdr_opt**\ () later in + * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. + * + * If **bpf_reserve_hdr_opt**\ () is called multiple times, + * the total number of bytes will be reserved. + * + * This helper can only be called during + * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** if a parameter is invalid. + * + * **-ENOSPC** if there is not enough space in the header. + * + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. + * + * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags) + * Description + * Get a bpf_local_storage from an *inode*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *inode* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this + * helper enforces the key must be an inode and the map must also + * be a **BPF_MAP_TYPE_INODE_STORAGE**. + * + * Underneath, the value is stored locally at *inode* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *inode*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * int bpf_inode_storage_delete(struct bpf_map *map, void *inode) + * Description + * Delete a bpf_local_storage from an *inode*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. + * + * long bpf_d_path(struct path *path, char *buf, u32 sz) + * Description + * Return full path for given **struct path** object, which + * needs to be the kernel BTF *path* object. The path is + * returned in the provided buffer *buf* of size *sz* and + * is zero terminated. + * + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr) + * Description + * Read *size* bytes from user space address *user_ptr* and store + * the data in *dst*. This is a wrapper of **copy_from_user**\ (). + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3539,6 +3730,13 @@ union bpf_attr { FN(skc_to_tcp_request_sock), \ FN(skc_to_udp6_sock), \ FN(get_task_stack), \ + FN(load_hdr_opt), \ + FN(store_hdr_opt), \ + FN(reserve_hdr_opt), \ + FN(inode_storage_get), \ + FN(inode_storage_delete), \ + FN(d_path), \ + FN(copy_from_user), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -3648,9 +3846,13 @@ enum { BPF_F_SYSCTL_BASE_NAME = (1ULL << 0), }; -/* BPF_FUNC_sk_storage_get flags */ +/* BPF_FUNC_<kernel_obj>_storage_get flags */ enum { - BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0), + BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0), + /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility + * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead. + */ + BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE, }; /* BPF_FUNC_read_branch_records flags. */ @@ -4071,6 +4273,15 @@ struct bpf_link_info { __u64 cgroup_id; __u32 attach_type; } cgroup; + struct { + __aligned_u64 target_name; /* in/out: target_name buffer ptr */ + __u32 target_name_len; /* in/out: target_name buffer len */ + union { + struct { + __u32 map_id; + } map; + }; + } iter; struct { __u32 netns_ino; __u32 attach_type; @@ -4158,6 +4369,36 @@ struct bpf_sock_ops { __u64 bytes_received; __u64 bytes_acked; __bpf_md_ptr(struct bpf_sock *, sk); + /* [skb_data, skb_data_end) covers the whole TCP header. + * + * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received + * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the + * header has not been written. + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have + * been written so far. + * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes + * the 3WHS. + * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes + * the 3WHS. + * + * bpf_load_hdr_opt() can also be used to read a particular option. + */ + __bpf_md_ptr(void *, skb_data); + __bpf_md_ptr(void *, skb_data_end); + __u32 skb_len; /* The total length of a packet. + * It includes the header, options, + * and payload. + */ + __u32 skb_tcp_flags; /* tcp_flags of the header. It provides + * an easy way to check for tcp_flags + * without parsing skb_data. + * + * In particular, the skb_tcp_flags + * will still be available in + * BPF_SOCK_OPS_HDR_OPT_LEN even though + * the outgoing header has not + * been written yet. + */ }; /* Definitions for bpf_sock_ops_cb_flags */ @@ -4166,8 +4407,51 @@ enum { BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), + /* Call bpf for all received TCP headers. The bpf prog will be + * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + * + * It could be used at the client/active side (i.e. connect() side) + * when the server told it that the server was in syncookie + * mode and required the active side to resend the bpf-written + * options. The active side can keep writing the bpf-options until + * it received a valid packet from the server side to confirm + * the earlier packet (and options) has been received. The later + * example patch is using it like this at the active side when the + * server is in syncookie mode. + * + * The bpf prog will usually turn this off in the common cases. + */ + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf when kernel has received a header option that + * the kernel cannot handle. The bpf prog will be called under + * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + */ + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + /* Call bpf when the kernel is writing header options for the + * outgoing packet. The bpf prog will first be called + * to reserve space in a skb under + * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then + * the bpf prog will be called to write the header option(s) + * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB + * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option + * related helpers that will be useful to the bpf programs. + * + * The kernel gets its chance to reserve space and write + * options first before the BPF program does. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), /* Mask of all currently supported cb flags */ - BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF, + BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, }; /* List of known BPF sock_ops operators. @@ -4223,6 +4507,63 @@ enum { */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. */ + BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. + * It will be called to handle + * the packets received at + * an already established + * connection. + * + * sock_ops->skb_data: + * Referring to the received skb. + * It covers the TCP header only. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option. + */ + BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the + * header option later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Not available because no header has + * been written yet. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the + * outgoing skb. (e.g. SYN, ACK, FIN). + * + * bpf_reserve_hdr_opt() should + * be used to reserve space. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Referring to the outgoing skb. + * It covers the TCP header + * that has already been written + * by the kernel and the + * earlier bpf-progs. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the outgoing + * skb. (e.g. SYN, ACK, FIN). + * + * bpf_store_hdr_opt() should + * be used to write the + * option. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option that + * has already been written + * by the kernel or the + * earlier bpf-progs. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -4250,6 +4591,63 @@ enum { enum { TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ + TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ + TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ + /* Copy the SYN pkt to optval + * + * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the + * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit + * to only getting from the saved_syn. It can either get the + * syn packet from: + * + * 1. the just-received SYN packet (only available when writing the + * SYNACK). It will be useful when it is not necessary to + * save the SYN packet for latter use. It is also the only way + * to get the SYN during syncookie mode because the syn + * packet cannot be saved during syncookie. + * + * OR + * + * 2. the earlier saved syn which was done by + * bpf_setsockopt(TCP_SAVE_SYN). + * + * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the + * SYN packet is obtained. + * + * If the bpf-prog does not need the IP[46] header, the + * bpf-prog can avoid parsing the IP header by using + * TCP_BPF_SYN. Otherwise, the bpf-prog can get both + * IP[46] and TCP header by using TCP_BPF_SYN_IP. + * + * >0: Total number of bytes copied + * -ENOSPC: Not enough space in optval. Only optlen number of + * bytes is copied. + * -ENOENT: The SYN skb is not available now and the earlier SYN pkt + * is not saved by setsockopt(TCP_SAVE_SYN). + */ + TCP_BPF_SYN = 1005, /* Copy the TCP header */ + TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ + TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ +}; + +enum { + BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0), +}; + +/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + */ +enum { + BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the + * total option spaces + * required for an established + * sk in order to calculate the + * MSS. No skb is actually + * sent. + */ + BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode + * when sending a SYN. + */ }; struct bpf_perf_event_value { diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cfef4245ea5a..a2ecc8b00611 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -122,6 +122,8 @@ enum devlink_command { DEVLINK_CMD_TRAP_POLICER_NEW, DEVLINK_CMD_TRAP_POLICER_DEL, + DEVLINK_CMD_HEALTH_REPORTER_TEST, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -458,6 +460,11 @@ enum devlink_attr { DEVLINK_ATTR_PORT_LANES, /* u32 */ DEVLINK_ATTR_PORT_SPLITTABLE, /* u8 */ + DEVLINK_ATTR_PORT_EXTERNAL, /* u8 */ + DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, /* u32 */ + + DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, /* u64 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index b4f2d134e713..9ca87bc73c44 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1617,6 +1617,8 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT = 87, ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT = 88, ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT = 89, + ETHTOOL_LINK_MODE_100baseFX_Half_BIT = 90, + ETHTOOL_LINK_MODE_100baseFX_Full_BIT = 91, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS }; diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 5dcd24cb33ea..e2bf36e6964b 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -79,6 +79,7 @@ enum { ETHTOOL_MSG_TSINFO_GET_REPLY, ETHTOOL_MSG_CABLE_TEST_NTF, ETHTOOL_MSG_CABLE_TEST_TDR_NTF, + ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -91,9 +92,12 @@ enum { #define ETHTOOL_FLAG_COMPACT_BITSETS (1 << 0) /* provide optional reply for SET or ACT requests */ #define ETHTOOL_FLAG_OMIT_REPLY (1 << 1) +/* request statistics, if supported by the driver */ +#define ETHTOOL_FLAG_STATS (1 << 2) #define ETHTOOL_FLAG_ALL (ETHTOOL_FLAG_COMPACT_BITSETS | \ - ETHTOOL_FLAG_OMIT_REPLY) + ETHTOOL_FLAG_OMIT_REPLY | \ + ETHTOOL_FLAG_STATS) enum { ETHTOOL_A_HEADER_UNSPEC, @@ -376,12 +380,25 @@ enum { ETHTOOL_A_PAUSE_AUTONEG, /* u8 */ ETHTOOL_A_PAUSE_RX, /* u8 */ ETHTOOL_A_PAUSE_TX, /* u8 */ + ETHTOOL_A_PAUSE_STATS, /* nest - _PAUSE_STAT_* */ /* add new constants above here */ __ETHTOOL_A_PAUSE_CNT, ETHTOOL_A_PAUSE_MAX = (__ETHTOOL_A_PAUSE_CNT - 1) }; +enum { + ETHTOOL_A_PAUSE_STAT_UNSPEC, + ETHTOOL_A_PAUSE_STAT_PAD, + + ETHTOOL_A_PAUSE_STAT_TX_FRAMES, + ETHTOOL_A_PAUSE_STAT_RX_FRAMES, + + /* add new constants above here */ + __ETHTOOL_A_PAUSE_STAT_CNT, + ETHTOOL_A_PAUSE_STAT_MAX = (__ETHTOOL_A_PAUSE_STAT_CNT - 1) +}; + /* EEE */ enum { diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index c7d66755d212..79f9191bbb24 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ +#define GTP_GENL_MCGRP_NAME "gtp" + enum gtp_genl_cmds { GTP_CMD_NEWPDP, GTP_CMD_DELPDP, diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index c1227aecd38f..4c687686aa8f 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -455,10 +455,33 @@ enum { enum { MDBA_MDB_EATTR_UNSPEC, MDBA_MDB_EATTR_TIMER, + MDBA_MDB_EATTR_SRC_LIST, + MDBA_MDB_EATTR_GROUP_MODE, + MDBA_MDB_EATTR_SOURCE, + MDBA_MDB_EATTR_RTPROT, __MDBA_MDB_EATTR_MAX }; #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1) +/* per mdb entry source */ +enum { + MDBA_MDB_SRCLIST_UNSPEC, + MDBA_MDB_SRCLIST_ENTRY, + __MDBA_MDB_SRCLIST_MAX +}; +#define MDBA_MDB_SRCLIST_MAX (__MDBA_MDB_SRCLIST_MAX - 1) + +/* per mdb entry per source attributes + * these are embedded in MDBA_MDB_SRCLIST_ENTRY + */ +enum { + MDBA_MDB_SRCATTR_UNSPEC, + MDBA_MDB_SRCATTR_ADDRESS, + MDBA_MDB_SRCATTR_TIMER, + __MDBA_MDB_SRCATTR_MAX +}; +#define MDBA_MDB_SRCATTR_MAX (__MDBA_MDB_SRCATTR_MAX - 1) + /* multicast router types */ enum { MDB_RTR_TYPE_DISABLED, @@ -495,6 +518,8 @@ struct br_mdb_entry { __u8 state; #define MDB_FLAGS_OFFLOAD (1 << 0) #define MDB_FLAGS_FAST_LEAVE (1 << 1) +#define MDB_FLAGS_STAR_EXCL (1 << 2) +#define MDB_FLAGS_BLOCKED (1 << 3) __u8 flags; __u16 vid; struct { @@ -509,10 +534,23 @@ struct br_mdb_entry { enum { MDBA_SET_ENTRY_UNSPEC, MDBA_SET_ENTRY, + MDBA_SET_ENTRY_ATTRS, __MDBA_SET_ENTRY_MAX, }; #define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1) +/* [MDBA_SET_ENTRY_ATTRS] = { + * [MDBE_ATTR_xxx] + * ... + * } + */ +enum { + MDBE_ATTR_UNSPEC, + MDBE_ATTR_SOURCE, + __MDBE_ATTR_MAX, +}; +#define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1) + /* Embedded inside LINK_XSTATS_TYPE_BRIDGE */ enum { BRIDGE_XSTATS_UNSPEC, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7fba4de511de..c4b23f06f69e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -7,24 +7,23 @@ /* This struct should be in sync with struct rtnl_link_stats64 */ struct rtnl_link_stats { - __u32 rx_packets; /* total packets received */ - __u32 tx_packets; /* total packets transmitted */ - __u32 rx_bytes; /* total bytes received */ - __u32 tx_bytes; /* total bytes transmitted */ - __u32 rx_errors; /* bad packets received */ - __u32 tx_errors; /* packet transmit problems */ - __u32 rx_dropped; /* no space in linux buffers */ - __u32 tx_dropped; /* no space available in linux */ - __u32 multicast; /* multicast packets received */ + __u32 rx_packets; + __u32 tx_packets; + __u32 rx_bytes; + __u32 tx_bytes; + __u32 rx_errors; + __u32 tx_errors; + __u32 rx_dropped; + __u32 tx_dropped; + __u32 multicast; __u32 collisions; - /* detailed rx_errors: */ __u32 rx_length_errors; - __u32 rx_over_errors; /* receiver ring buff overflow */ - __u32 rx_crc_errors; /* recved pkt with crc error */ - __u32 rx_frame_errors; /* recv'd frame alignment error */ - __u32 rx_fifo_errors; /* recv'r fifo overrun */ - __u32 rx_missed_errors; /* receiver missed packet */ + __u32 rx_over_errors; + __u32 rx_crc_errors; + __u32 rx_frame_errors; + __u32 rx_fifo_errors; + __u32 rx_missed_errors; /* detailed tx_errors */ __u32 tx_aborted_errors; @@ -37,29 +36,200 @@ struct rtnl_link_stats { __u32 rx_compressed; __u32 tx_compressed; - __u32 rx_nohandler; /* dropped, no handler found */ + __u32 rx_nohandler; }; -/* The main device statistics structure */ +/** + * struct rtnl_link_stats64 - The main device statistics structure. + * + * @rx_packets: Number of good packets received by the interface. + * For hardware interfaces counts all good packets received from the device + * by the host, including packets which host had to drop at various stages + * of processing (even in the driver). + * + * @tx_packets: Number of packets successfully transmitted. + * For hardware interfaces counts packets which host was able to successfully + * hand over to the device, which does not necessarily mean that packets + * had been successfully transmitted out of the device, only that device + * acknowledged it copied them out of host memory. + * + * @rx_bytes: Number of good received bytes, corresponding to @rx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @rx_errors: Total number of bad packets received on this network device. + * This counter must include events counted by @rx_length_errors, + * @rx_crc_errors, @rx_frame_errors and other errors not otherwise + * counted. + * + * @tx_errors: Total number of transmit problems. + * This counter must include events counter by @tx_aborted_errors, + * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors, + * @tx_window_errors and other errors not otherwise counted. + * + * @rx_dropped: Number of packets received but not processed, + * e.g. due to lack of resources or unsupported protocol. + * For hardware interfaces this counter should not include packets + * dropped by the device which are counted separately in + * @rx_missed_errors (since procfs folds those two counters together). + * + * @tx_dropped: Number of packets dropped on their way to transmission, + * e.g. due to lack of resources. + * + * @multicast: Multicast packets received. + * For hardware interfaces this statistic is commonly calculated + * at the device level (unlike @rx_packets) and therefore may include + * packets which did not reach the host. + * + * For IEEE 802.3 devices this counter may be equivalent to: + * + * - 30.3.1.1.21 aMulticastFramesReceivedOK + * + * @collisions: Number of collisions during packet transmissions. + * + * @rx_length_errors: Number of packets dropped due to invalid length. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to a sum + * of the following attributes: + * + * - 30.3.1.1.23 aInRangeLengthErrors + * - 30.3.1.1.24 aOutOfRangeLengthField + * - 30.3.1.1.25 aFrameTooLongErrors + * + * @rx_over_errors: Receiver FIFO overflow event counter. + * + * Historically the count of overflow events. Such events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * The recommended interpretation for high speed interfaces is - + * number of packets dropped because they did not fit into buffers + * provided by the host, e.g. packets larger than MTU or next buffer + * in the ring was not available for a scatter transfer. + * + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * This statistics was historically used interchangeably with + * @rx_fifo_errors. + * + * This statistic corresponds to hardware events and is not commonly used + * on software devices. + * + * @rx_crc_errors: Number of packets received with a CRC error. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.6 aFrameCheckSequenceErrors + * + * @rx_frame_errors: Receiver frame alignment errors. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to: + * + * - 30.3.1.1.7 aAlignmentErrors + * + * @rx_fifo_errors: Receiver FIFO error counter. + * + * Historically the count of overflow events. Those events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * This statistics was used interchangeably with @rx_over_errors. + * Not recommended for use in drivers for high speed interfaces. + * + * This statistic is used on software devices, e.g. to count software + * packet queue overflow (can) or sequencing errors (GRE). + * + * @rx_missed_errors: Count of packets missed by the host. + * Folded into the "drop" counter in `/proc/net/dev`. + * + * Counts number of packets dropped by the device due to lack + * of buffer space. This usually indicates that the host interface + * is slower than the network interface, or host is not keeping up + * with the receive packet rate. + * + * This statistic corresponds to hardware events and is not used + * on software devices. + * + * @tx_aborted_errors: + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * For IEEE 802.3 devices capable of half-duplex operation this counter + * must be equivalent to: + * + * - 30.3.1.1.11 aFramesAbortedDueToXSColls + * + * High speed interfaces may use this counter as a general device + * discard counter. + * + * @tx_carrier_errors: Number of frame transmission errors due to loss + * of carrier during transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.13 aCarrierSenseErrors + * + * @tx_fifo_errors: Number of frame transmission errors due to device + * FIFO underrun / underflow. This condition occurs when the device + * begins transmission of a frame but is unable to deliver the + * entire frame to the transmitter in time for transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for + * old half-duplex Ethernet. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices possibly equivalent to: + * + * - 30.3.2.1.4 aSQETestErrors + * + * @tx_window_errors: Number of frame transmission errors due + * to late collisions (for Ethernet - after the first 64B of transmission). + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.10 aLateCollisions + * + * @rx_compressed: Number of correctly received compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @tx_compressed: Number of transmitted compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @rx_nohandler: Number of packets received on the interface + * but dropped by the networking stack because the device is + * not designated to receive packets (e.g. backup link in a bond). + */ struct rtnl_link_stats64 { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ - __u64 multicast; /* multicast packets received */ + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; __u64 collisions; /* detailed rx_errors: */ __u64 rx_length_errors; - __u64 rx_over_errors; /* receiver ring buff overflow */ - __u64 rx_crc_errors; /* recved pkt with crc error */ - __u64 rx_frame_errors; /* recv'd frame alignment error */ - __u64 rx_fifo_errors; /* recv'r fifo overrun */ - __u64 rx_missed_errors; /* receiver missed packet */ + __u64 rx_over_errors; + __u64 rx_crc_errors; + __u64 rx_frame_errors; + __u64 rx_fifo_errors; + __u64 rx_missed_errors; /* detailed tx_errors */ __u64 tx_aborted_errors; @@ -71,8 +241,7 @@ struct rtnl_link_stats64 { /* for cslip etc */ __u64 rx_compressed; __u64 tx_compressed; - - __u64 rx_nohandler; /* dropped, no handler found */ + __u64 rx_nohandler; }; /* The struct should be in sync with struct ifmap */ diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h index 060b4d1f3129..a91044328bc9 100644 --- a/include/uapi/linux/if_pppol2tp.h +++ b/include/uapi/linux/if_pppol2tp.h @@ -75,7 +75,7 @@ struct pppol2tpv3in6_addr { }; /* Socket options: - * DEBUG - bitmask of debug message categories + * DEBUG - bitmask of debug message categories (not used) * SENDSEQ - 0 => don't send packets with sequence numbers * 1 => send packets with sequence numbers * RECVSEQ - 0 => receive packet sequence numbers are optional diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 3d0d8231dc19..7d6687618d80 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -135,7 +135,7 @@ struct in_addr { * this socket to prevent accepting spoofed ones. */ #define IP_PMTUDISC_INTERFACE 4 -/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get +/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get * fragmented if they exeed the interface mtu */ #define IP_PMTUDISC_OMIT 5 diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 5ba122c1949a..20ee93f0f876 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -160,6 +160,7 @@ enum { INET_DIAG_ULP_INFO, INET_DIAG_SK_BPF_STORAGES, INET_DIAG_CGROUP_ID, + INET_DIAG_SOCKOPT, __INET_DIAG_MAX, }; @@ -183,6 +184,23 @@ struct inet_diag_meminfo { __u32 idiag_tmem; }; +/* INET_DIAG_SOCKOPT */ + +struct inet_diag_sockopt { + __u8 recverr:1, + is_icsk:1, + freebind:1, + hdrincl:1, + mc_loop:1, + transparent:1, + mc_all:1, + nodefrag:1; + __u8 bind_address_no_port:1, + recverr_rfc4884:1, + defer_connect:1, + unused:5; +}; + /* INET_DIAG_VEGASINFO */ struct tcpvegas_info { diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index f6d86033c4fa..7d8eced6f459 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -790,9 +790,10 @@ struct kvm_ppc_resize_hpt { #define KVM_VM_PPC_HV 1 #define KVM_VM_PPC_PR 2 -/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */ -#define KVM_VM_MIPS_TE 0 +/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */ +#define KVM_VM_MIPS_AUTO 0 #define KVM_VM_MIPS_VZ 1 +#define KVM_VM_MIPS_TE 2 #define KVM_S390_SIE_PAGE_OFFSET 1 @@ -1035,6 +1036,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_LAST_CPU 184 #define KVM_CAP_SMALLER_MAXPHYADDR 185 #define KVM_CAP_S390_DIAG318 186 +#define KVM_CAP_STEAL_TIME 187 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 61158f5a1a5b..88a0d32b8c07 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -108,7 +108,7 @@ enum { L2TP_ATTR_VLAN_ID, /* u16 (not used) */ L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */ L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */ - L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags */ + L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags (not used) */ L2TP_ATTR_RECV_SEQ, /* u8 */ L2TP_ATTR_SEND_SEQ, /* u8 */ L2TP_ATTR_LNS_MODE, /* u8 */ @@ -177,7 +177,9 @@ enum l2tp_seqmode { }; /** - * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions + * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions. + * + * Unused. * * @L2TP_MSG_DEBUG: verbose debug (if compiled in) * @L2TP_MSG_CONTROL: userspace - kernel interface diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h index 11c8c1fc1124..1a42f5f9b31b 100644 --- a/include/uapi/linux/mroute.h +++ b/include/uapi/linux/mroute.h @@ -113,8 +113,8 @@ struct igmpmsg { __u32 unused1,unused2; unsigned char im_msgtype; /* What is this */ unsigned char im_mbz; /* Must be zero */ - unsigned char im_vif; /* Interface (this ought to be a vifi_t!) */ - unsigned char unused3; + unsigned char im_vif; /* Low 8 bits of Interface */ + unsigned char im_vif_hi; /* High 8 bits of Interface */ struct in_addr im_src,im_dst; }; @@ -169,6 +169,7 @@ enum { IPMRA_CREPORT_SRC_ADDR, IPMRA_CREPORT_DST_ADDR, IPMRA_CREPORT_PKT, + IPMRA_CREPORT_TABLE, __IPMRA_CREPORT_MAX }; #define IPMRA_CREPORT_MAX (__IPMRA_CREPORT_MAX - 1) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 42f351c1f5c5..3c2469b43742 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -133,7 +133,7 @@ enum nf_tables_msg_types { * @NFTA_LIST_ELEM: list element (NLA_NESTED) */ enum nft_list_attributes { - NFTA_LIST_UNPEC, + NFTA_LIST_UNSPEC, NFTA_LIST_ELEM, __NFTA_LIST_MAX }; @@ -172,6 +172,7 @@ enum nft_table_flags { * @NFTA_TABLE_NAME: name of the table (NLA_STRING) * @NFTA_TABLE_FLAGS: bitmask of enum nft_table_flags (NLA_U32) * @NFTA_TABLE_USE: number of chains in this table (NLA_U32) + * @NFTA_TABLE_USERDATA: user data (NLA_BINARY) */ enum nft_table_attributes { NFTA_TABLE_UNSPEC, @@ -180,6 +181,7 @@ enum nft_table_attributes { NFTA_TABLE_USE, NFTA_TABLE_HANDLE, NFTA_TABLE_PAD, + NFTA_TABLE_USERDATA, __NFTA_TABLE_MAX }; #define NFTA_TABLE_MAX (__NFTA_TABLE_MAX - 1) @@ -1008,10 +1010,12 @@ enum nft_socket_attributes { * * @NFT_SOCKET_TRANSPARENT: Value of the IP(V6)_TRANSPARENT socket option * @NFT_SOCKET_MARK: Value of the socket mark + * @NFT_SOCKET_WILDCARD: Whether the socket is zero-bound (e.g. 0.0.0.0 or ::0) */ enum nft_socket_keys { NFT_SOCKET_TRANSPARENT, NFT_SOCKET_MARK, + NFT_SOCKET_WILDCARD, __NFT_SOCKET_MAX }; #define NFT_SOCKET_MAX (__NFT_SOCKET_MAX - 1) @@ -1555,6 +1559,7 @@ enum nft_ct_expectation_attributes { * @NFTA_OBJ_DATA: stateful object data (NLA_NESTED) * @NFTA_OBJ_USE: number of references to this expression (NLA_U32) * @NFTA_OBJ_HANDLE: object handle (NLA_U64) + * @NFTA_OBJ_USERDATA: user data (NLA_BINARY) */ enum nft_object_attributes { NFTA_OBJ_UNSPEC, @@ -1565,6 +1570,7 @@ enum nft_object_attributes { NFTA_OBJ_USE, NFTA_OBJ_HANDLE, NFTA_OBJ_PAD, + NFTA_OBJ_USERDATA, __NFTA_OBJ_MAX }; #define NFTA_OBJ_MAX (__NFTA_OBJ_MAX - 1) diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index 262881792671..d8484be72fdc 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -247,7 +247,7 @@ enum ctattr_stats_cpu { CTA_STATS_FOUND, CTA_STATS_NEW, /* no longer used */ CTA_STATS_INVALID, - CTA_STATS_IGNORE, + CTA_STATS_IGNORE, /* no longer used */ CTA_STATS_DELETE, /* no longer used */ CTA_STATS_DELETE_LIST, /* no longer used */ CTA_STATS_INSERT, @@ -256,6 +256,7 @@ enum ctattr_stats_cpu { CTA_STATS_EARLY_DROP, CTA_STATS_ERROR, CTA_STATS_SEARCH_RESTART, + CTA_STATS_CLASH_RESOLVE, __CTA_STATS_MAX, }; #define CTA_STATS_MAX (__CTA_STATS_MAX - 1) diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 631f3a997b3c..bdc90b8dfd24 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -252,9 +252,13 @@ * DOC: SAE authentication offload * * By setting @NL80211_EXT_FEATURE_SAE_OFFLOAD flag drivers can indicate they - * support offloading SAE authentication for WPA3-Personal networks. In - * %NL80211_CMD_CONNECT the password for SAE should be specified using - * %NL80211_ATTR_SAE_PASSWORD. + * support offloading SAE authentication for WPA3-Personal networks in station + * mode. Similarly @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP flag can be set by + * drivers indicating the offload support in AP mode. + * + * The password for SAE should be specified using %NL80211_ATTR_SAE_PASSWORD in + * %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP for station and AP mode + * respectively. */ /** @@ -647,13 +651,9 @@ * authentication/association or not receiving a response from the AP. * Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as * well to remain backwards compatible. - * When establishing a security association, drivers that support 4 way - * handshake offload should send %NL80211_CMD_PORT_AUTHORIZED event when - * the 4 way handshake is completed successfully. * @NL80211_CMD_ROAM: Notification indicating the card/driver roamed by itself. - * When a security association was established with the new AP (e.g. if - * the FT protocol was used for roaming or the driver completed the 4 way - * handshake), this event should be followed by an + * When a security association was established on an 802.1X network using + * fast transition, this event should be followed by an * %NL80211_CMD_PORT_AUTHORIZED event. * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify * userspace that a connection was dropped by the AP or due to other @@ -1067,13 +1067,11 @@ * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously * configured PMK for the authenticator address identified by * %NL80211_ATTR_MAC. - * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way - * handshake was completed successfully by the driver. The BSSID is - * specified with %NL80211_ATTR_MAC. Drivers that support 4 way handshake - * offload should send this event after indicating 802.11 association with - * %NL80211_CMD_CONNECT or %NL80211_CMD_ROAM. If the 4 way handshake failed - * %NL80211_CMD_DISCONNECT should be indicated instead. - * + * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates an 802.1X FT roam was + * completed successfully. Drivers that support 4 way handshake offload + * should send this event after indicating 802.1X FT assocation with + * %NL80211_CMD_ROAM. If the 4 way handshake failed %NL80211_CMD_DISCONNECT + * should be indicated instead. * @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request * and RX notification. This command is used both as a request to transmit * a control port frame and as a notification that a control port frame @@ -2082,10 +2080,10 @@ enum nl80211_commands { * operation). * @NL80211_ATTR_CSA_IES: Nested set of attributes containing the IE information * for the time while performing a channel switch. - * @NL80211_ATTR_CSA_C_OFF_BEACON: An array of offsets (u16) to the channel - * switch counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL). - * @NL80211_ATTR_CSA_C_OFF_PRESP: An array of offsets (u16) to the channel - * switch counters in the probe response (%NL80211_ATTR_PROBE_RESP). + * @NL80211_ATTR_CNTDWN_OFFS_BEACON: An array of offsets (u16) to the channel + * switch or color change counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL). + * @NL80211_ATTR_CNTDWN_OFFS_PRESP: An array of offsets (u16) to the channel + * switch or color change counters in the probe response (%NL80211_ATTR_PROBE_RESP). * * @NL80211_ATTR_RXMGMT_FLAGS: flags for nl80211_send_mgmt(), u32. * As specified in the &enum nl80211_rxmgmt_flags. @@ -2515,6 +2513,14 @@ enum nl80211_commands { * @NL80211_ATTR_HE_6GHZ_CAPABILITY: HE 6 GHz Band Capability element (from * association request when used with NL80211_CMD_NEW_STATION). * + * @NL80211_ATTR_FILS_DISCOVERY: Optional parameter to configure FILS + * discovery. It is a nested attribute, see + * &enum nl80211_fils_discovery_attributes. + * + * @NL80211_ATTR_UNSOL_BCAST_PROBE_RESP: Optional parameter to configure + * unsolicited broadcast probe response. It is a nested attribute, see + * &enum nl80211_unsol_bcast_probe_resp_attributes. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2821,8 +2827,8 @@ enum nl80211_attrs { NL80211_ATTR_CH_SWITCH_COUNT, NL80211_ATTR_CH_SWITCH_BLOCK_TX, NL80211_ATTR_CSA_IES, - NL80211_ATTR_CSA_C_OFF_BEACON, - NL80211_ATTR_CSA_C_OFF_PRESP, + NL80211_ATTR_CNTDWN_OFFS_BEACON, + NL80211_ATTR_CNTDWN_OFFS_PRESP, NL80211_ATTR_RXMGMT_FLAGS, @@ -2997,6 +3003,10 @@ enum nl80211_attrs { NL80211_ATTR_HE_6GHZ_CAPABILITY, + NL80211_ATTR_FILS_DISCOVERY, + + NL80211_ATTR_UNSOL_BCAST_PROBE_RESP, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3009,6 +3019,8 @@ enum nl80211_attrs { #define NL80211_ATTR_MESH_PARAMS NL80211_ATTR_MESH_CONFIG #define NL80211_ATTR_IFACE_SOCKET_OWNER NL80211_ATTR_SOCKET_OWNER #define NL80211_ATTR_SAE_DATA NL80211_ATTR_AUTH_DATA +#define NL80211_ATTR_CSA_C_OFF_BEACON NL80211_ATTR_CNTDWN_OFFS_BEACON +#define NL80211_ATTR_CSA_C_OFF_PRESP NL80211_ATTR_CNTDWN_OFFS_PRESP /* * Allow user space programs to use #ifdef on new attributes by defining them @@ -3187,6 +3199,18 @@ enum nl80211_he_gi { }; /** + * enum nl80211_he_ltf - HE long training field + * @NL80211_RATE_INFO_HE_1xLTF: 3.2 usec + * @NL80211_RATE_INFO_HE_2xLTF: 6.4 usec + * @NL80211_RATE_INFO_HE_4xLTF: 12.8 usec + */ +enum nl80211_he_ltf { + NL80211_RATE_INFO_HE_1XLTF, + NL80211_RATE_INFO_HE_2XLTF, + NL80211_RATE_INFO_HE_4XLTF, +}; + +/** * enum nl80211_he_ru_alloc - HE RU allocation values * @NL80211_RATE_INFO_HE_RU_ALLOC_26: 26-tone RU allocation * @NL80211_RATE_INFO_HE_RU_ALLOC_52: 52-tone RU allocation @@ -3725,6 +3749,16 @@ enum nl80211_wmm_rule { * @NL80211_FREQUENCY_ATTR_NO_HE: HE operation is not allowed on this channel * in current regulatory domain. * @NL80211_FREQUENCY_ATTR_OFFSET: frequency offset in KHz + * @NL80211_FREQUENCY_ATTR_1MHZ: 1 MHz operation is allowed + * on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_2MHZ: 2 MHz operation is allowed + * on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_4MHZ: 4 MHz operation is allowed + * on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_8MHZ: 8 MHz operation is allowed + * on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_16MHZ: 16 MHz operation is allowed + * on this channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -3756,6 +3790,11 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_WMM, NL80211_FREQUENCY_ATTR_NO_HE, NL80211_FREQUENCY_ATTR_OFFSET, + NL80211_FREQUENCY_ATTR_1MHZ, + NL80211_FREQUENCY_ATTR_2MHZ, + NL80211_FREQUENCY_ATTR_4MHZ, + NL80211_FREQUENCY_ATTR_8MHZ, + NL80211_FREQUENCY_ATTR_16MHZ, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4741,6 +4780,10 @@ enum nl80211_key_attributes { * @NL80211_TXRATE_VHT: VHT rates allowed for TX rate selection, * see &struct nl80211_txrate_vht * @NL80211_TXRATE_GI: configure GI, see &enum nl80211_txrate_gi + * @NL80211_TXRATE_HE: HE rates allowed for TX rate selection, + * see &struct nl80211_txrate_he + * @NL80211_TXRATE_HE_GI: configure HE GI, 0.8us, 1.6us and 3.2us. + * @NL80211_TXRATE_HE_LTF: configure HE LTF, 1XLTF, 2XLTF and 4XLTF. * @__NL80211_TXRATE_AFTER_LAST: internal * @NL80211_TXRATE_MAX: highest TX rate attribute */ @@ -4750,6 +4793,9 @@ enum nl80211_tx_rate_attributes { NL80211_TXRATE_HT, NL80211_TXRATE_VHT, NL80211_TXRATE_GI, + NL80211_TXRATE_HE, + NL80211_TXRATE_HE_GI, + NL80211_TXRATE_HE_LTF, /* keep last */ __NL80211_TXRATE_AFTER_LAST, @@ -4767,6 +4813,15 @@ struct nl80211_txrate_vht { __u16 mcs[NL80211_VHT_NSS_MAX]; }; +#define NL80211_HE_NSS_MAX 8 +/** + * struct nl80211_txrate_he - HE MCS/NSS txrate bitmap + * @mcs: MCS bitmap table for each NSS (array index 0 for 1 stream, etc.) + */ +struct nl80211_txrate_he { + __u16 mcs[NL80211_HE_NSS_MAX]; +}; + enum nl80211_txrate_gi { NL80211_TXRATE_DEFAULT_GI, NL80211_TXRATE_FORCE_SGI, @@ -5821,6 +5876,15 @@ enum nl80211_feature_flags { * handshake with PSK in AP mode (PSK is passed as part of the start AP * command). * + * @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP: Device wants to do SAE authentication + * in AP mode (SAE password is passed as part of the start AP command). + * + * @NL80211_EXT_FEATURE_FILS_DISCOVERY: Driver/device supports FILS discovery + * frames transmission + * + * @NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP: Driver/device supports + * unsolicited broadcast probe response transmission + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5878,6 +5942,9 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS, NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK, + NL80211_EXT_FEATURE_SAE_OFFLOAD_AP, + NL80211_EXT_FEATURE_FILS_DISCOVERY, + NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -6972,4 +7039,64 @@ enum nl80211_iftype_akm_attributes { NL80211_IFTYPE_AKM_ATTR_MAX = __NL80211_IFTYPE_AKM_ATTR_LAST - 1, }; +/** + * enum nl80211_fils_discovery_attributes - FILS discovery configuration + * from IEEE Std 802.11ai-2016, Annex C.3 MIB detail. + * + * @__NL80211_FILS_DISCOVERY_ATTR_INVALID: Invalid + * + * @NL80211_FILS_DISCOVERY_ATTR_INT_MIN: Minimum packet interval (u32, TU). + * Allowed range: 0..10000 (TU = Time Unit) + * @NL80211_FILS_DISCOVERY_ATTR_INT_MAX: Maximum packet interval (u32, TU). + * Allowed range: 0..10000 (TU = Time Unit) + * @NL80211_FILS_DISCOVERY_ATTR_TMPL: Template data for FILS discovery action + * frame including the headers. + * + * @__NL80211_FILS_DISCOVERY_ATTR_LAST: Internal + * @NL80211_FILS_DISCOVERY_ATTR_MAX: highest attribute + */ +enum nl80211_fils_discovery_attributes { + __NL80211_FILS_DISCOVERY_ATTR_INVALID, + + NL80211_FILS_DISCOVERY_ATTR_INT_MIN, + NL80211_FILS_DISCOVERY_ATTR_INT_MAX, + NL80211_FILS_DISCOVERY_ATTR_TMPL, + + /* keep last */ + __NL80211_FILS_DISCOVERY_ATTR_LAST, + NL80211_FILS_DISCOVERY_ATTR_MAX = __NL80211_FILS_DISCOVERY_ATTR_LAST - 1 +}; + +/* + * FILS discovery template minimum length with action frame headers and + * mandatory fields. + */ +#define NL80211_FILS_DISCOVERY_TMPL_MIN_LEN 42 + +/** + * enum nl80211_unsol_bcast_probe_resp_attributes - Unsolicited broadcast probe + * response configuration. Applicable only in 6GHz. + * + * @__NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INVALID: Invalid + * + * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT: Maximum packet interval (u32, TU). + * Allowed range: 0..20 (TU = Time Unit). IEEE P802.11ax/D6.0 + * 26.17.2.3.2 (AP behavior for fast passive scanning). + * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL: Unsolicited broadcast probe response + * frame template (binary). + * + * @__NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST: Internal + * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX: highest attribute + */ +enum nl80211_unsol_bcast_probe_resp_attributes { + __NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INVALID, + + NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT, + NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL, + + /* keep last */ + __NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST, + NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX = + __NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST - 1 +}; #endif /* __LINUX_NL80211_H */ diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index add01db1daef..80ea15e12113 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -254,6 +254,8 @@ static inline int tipc_aead_key_size(struct tipc_aead_key *key) return sizeof(*key) + key->keylen; } +#define TIPC_REKEYING_NOW (~0U) + /* The macros and functions below are deprecated: */ diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index dc0d23a50e69..d847dd671d79 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -165,6 +165,8 @@ enum { TIPC_NLA_NODE_UP, /* flag */ TIPC_NLA_NODE_ID, /* data */ TIPC_NLA_NODE_KEY, /* data */ + TIPC_NLA_NODE_KEY_MASTER, /* flag */ + TIPC_NLA_NODE_REKEYING, /* u32 */ __TIPC_NLA_NODE_MAX, TIPC_NLA_NODE_MAX = __TIPC_NLA_NODE_MAX - 1 diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index d7f6af50e200..39df751d0dc4 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -76,7 +76,11 @@ static inline unsigned long bfn_to_pfn(unsigned long bfn) #define bfn_to_local_pfn(bfn) bfn_to_pfn(bfn) /* VIRT <-> GUEST conversion */ -#define virt_to_gfn(v) (pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT)) +#define virt_to_gfn(v) \ + ({ \ + WARN_ON_ONCE(!virt_addr_valid(v)); \ + pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT); \ + }) #define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT)) /* Only used in PV code. But ARM guests are always HVM. */ diff --git a/include/xen/balloon.h b/include/xen/balloon.h index 6fb95aa19405..6dbdb0b3fd03 100644 --- a/include/xen/balloon.h +++ b/include/xen/balloon.h @@ -2,6 +2,8 @@ /****************************************************************************** * Xen balloon functionality */ +#ifndef _XEN_BALLOON_H +#define _XEN_BALLOON_H #define RETRY_UNLIMITED 0 @@ -34,3 +36,5 @@ static inline void xen_balloon_init(void) { } #endif + +#endif /* _XEN_BALLOON_H */ diff --git a/include/xen/xen.h b/include/xen/xen.h index 19a72f591e2b..43efba045acc 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -52,4 +52,13 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, extern u64 xen_saved_max_mem_size; #endif +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC +int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages); +void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages); +#else +#define xen_alloc_unpopulated_pages alloc_xenballooned_pages +#define xen_free_unpopulated_pages free_xenballooned_pages +#include <xen/balloon.h> +#endif + #endif /* _XEN_XEN_H */ |