diff options
Diffstat (limited to 'include')
78 files changed, 1861 insertions, 1019 deletions
diff --git a/include/dt-bindings/net/pcs-rzn1-miic.h b/include/dt-bindings/net/pcs-rzn1-miic.h new file mode 100644 index 000000000000..784782eaec9e --- /dev/null +++ b/include/dt-bindings/net/pcs-rzn1-miic.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2022 Schneider-Electric + * + * Clément Léger <clement.leger@bootlin.com> + */ + +#ifndef _DT_BINDINGS_PCS_RZN1_MIIC +#define _DT_BINDINGS_PCS_RZN1_MIIC + +/* + * Reefer to the datasheet [1] section 8.2.1, Internal Connection of Ethernet + * Ports to check the available combination + * + * [1] REN_r01uh0750ej0140-rzn1-introduction_MAT_20210228.pdf + */ + +#define MIIC_GMAC1_PORT 0 +#define MIIC_GMAC2_PORT 1 +#define MIIC_RTOS_PORT 2 +#define MIIC_SERCOS_PORTA 3 +#define MIIC_SERCOS_PORTB 4 +#define MIIC_ETHERCAT_PORTA 5 +#define MIIC_ETHERCAT_PORTB 6 +#define MIIC_ETHERCAT_PORTC 7 +#define MIIC_SWITCH_PORTA 8 +#define MIIC_SWITCH_PORTB 9 +#define MIIC_SWITCH_PORTC 10 +#define MIIC_SWITCH_PORTD 11 +#define MIIC_HSR_PORTA 12 +#define MIIC_HSR_PORTB 13 + +#endif diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h index 695d1224a71b..7b121bd780eb 100644 --- a/include/linux/bpf-cgroup-defs.h +++ b/include/linux/bpf-cgroup-defs.h @@ -10,6 +10,13 @@ struct bpf_prog_array; +#ifdef CONFIG_BPF_LSM +/* Maximum number of concurrently attachable per-cgroup LSM hooks. */ +#define CGROUP_LSM_NUM 10 +#else +#define CGROUP_LSM_NUM 0 +#endif + enum cgroup_bpf_attach_type { CGROUP_BPF_ATTACH_TYPE_INVALID = -1, CGROUP_INET_INGRESS = 0, @@ -35,6 +42,8 @@ enum cgroup_bpf_attach_type { CGROUP_INET4_GETSOCKNAME, CGROUP_INET6_GETSOCKNAME, CGROUP_INET_SOCK_RELEASE, + CGROUP_LSM_START, + CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1, MAX_CGROUP_BPF_ATTACH_TYPE }; @@ -47,8 +56,8 @@ struct cgroup_bpf { * have either zero or one element * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS */ - struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; - u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; + struct hlist_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; + u8 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; /* list of cgroup shared storages */ struct list_head storages; diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 669d96d074ad..2bd1b5f8de9b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,6 +23,13 @@ struct ctl_table; struct ctl_table_header; struct task_struct; +unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx, + const struct bpf_insn *insn); +unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx, + const struct bpf_insn *insn); +unsigned int __cgroup_bpf_run_lsm_current(const void *ctx, + const struct bpf_insn *insn); + #ifdef CONFIG_CGROUP_BPF #define CGROUP_ATYPE(type) \ @@ -95,7 +102,7 @@ struct bpf_cgroup_link { }; struct bpf_prog_list { - struct list_head node; + struct hlist_node node; struct bpf_prog *prog; struct bpf_cgroup_link *link; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2b914a56a2c5..2b21f2a3452f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -5,6 +5,7 @@ #define _LINUX_BPF_H 1 #include <uapi/linux/bpf.h> +#include <uapi/linux/filter.h> #include <linux/workqueue.h> #include <linux/file.h> @@ -22,8 +23,10 @@ #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> +#include <linux/stddef.h> #include <linux/bpfptr.h> #include <linux/btf.h> +#include <linux/rcupdate_trace.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -53,6 +56,8 @@ typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); +typedef unsigned int (*bpf_func_t)(const void *, + const struct bpf_insn *); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; @@ -398,6 +403,9 @@ enum bpf_type_flag { /* DYNPTR points to a ringbuf record. */ DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), + /* Size is known at compile time. */ + MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -461,6 +469,8 @@ enum bpf_arg_type { * all bytes or clear them in error case. */ ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, + /* Pointer to valid memory of size known at compile time. */ + ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. @@ -526,6 +536,14 @@ struct bpf_func_proto { u32 *arg5_btf_id; }; u32 *arg_btf_id[5]; + struct { + size_t arg1_size; + size_t arg2_size; + size_t arg3_size; + size_t arg4_size; + size_t arg5_size; + }; + size_t arg_size[5]; }; int *ret_btf_id; /* return value btf_id */ bool (*allowed)(const struct bpf_prog *prog); @@ -776,6 +794,10 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_ u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); @@ -863,8 +885,7 @@ struct bpf_dispatcher { static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, - unsigned int (*bpf_func)(const void *, - const struct bpf_insn *)) + bpf_func_t bpf_func) { return bpf_func(ctx, insnsi); } @@ -893,8 +914,7 @@ int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs); noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ - unsigned int (*bpf_func)(const void *, \ - const struct bpf_insn *)) \ + bpf_func_t bpf_func) \ { \ return bpf_func(ctx, insnsi); \ } \ @@ -905,8 +925,7 @@ int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs); unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ - unsigned int (*bpf_func)(const void *, \ - const struct bpf_insn *)); \ + bpf_func_t bpf_func); \ extern struct bpf_dispatcher bpf_dispatcher_##name; #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) @@ -1045,6 +1064,7 @@ struct bpf_prog_aux { struct user_struct *user; u64 load_time; /* ns since boottime */ u32 verified_insns; + int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY @@ -1084,6 +1104,40 @@ struct bpf_prog_aux { }; }; +struct bpf_prog { + u16 pages; /* Number of allocated pages */ + u16 jited:1, /* Is our filter JIT'ed? */ + jit_requested:1,/* archs need to JIT the prog */ + gpl_compatible:1, /* Is filter GPL compatible? */ + cb_access:1, /* Is control block accessed? */ + dst_needed:1, /* Do we need dst entry? */ + blinding_requested:1, /* needs constant blinding */ + blinded:1, /* Was blinded */ + is_func:1, /* program is a bpf function */ + kprobe_override:1, /* Do we override a kprobe? */ + has_callchain_buf:1, /* callchain buffer allocated? */ + enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ + call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ + call_get_func_ip:1, /* Do we call get_func_ip() */ + tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ + enum bpf_prog_type type; /* Type of BPF program */ + enum bpf_attach_type expected_attach_type; /* For some prog types */ + u32 len; /* Number of filter blocks */ + u32 jited_len; /* Size of jited insns in bytes */ + u8 tag[BPF_TAG_SIZE]; + struct bpf_prog_stats __percpu *stats; + int __percpu *active; + unsigned int (*bpf_func)(const void *ctx, + const struct bpf_insn *insn); + struct bpf_prog_aux *aux; /* Auxiliary fields */ + struct sock_fprog_kern *orig_prog; /* Original BPF program */ + /* Instructions for interpreter */ + union { + DECLARE_FLEX_ARRAY(struct sock_filter, insns); + DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); + }; +}; + struct bpf_array_aux { /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; @@ -1118,6 +1172,11 @@ struct bpf_tramp_link { u64 cookie; }; +struct bpf_shim_tramp_link { + struct bpf_tramp_link link; + struct bpf_trampoline *trampoline; +}; + struct bpf_tracing_link { struct bpf_tramp_link link; enum bpf_attach_type attach_type; @@ -1196,6 +1255,9 @@ struct bpf_dummy_ops { int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif +int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, + int cgroup_atype); +void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog); #else static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { @@ -1219,6 +1281,14 @@ static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, { return -EINVAL; } +static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, + int cgroup_atype) +{ + return -EOPNOTSUPP; +} +static inline void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog) +{ +} #endif struct bpf_array { @@ -1236,6 +1306,9 @@ struct bpf_array { #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 33 +/* Maximum number of loops for bpf_loop */ +#define BPF_MAX_LOOPS BIT(23) + #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ BPF_F_WRONLY | \ @@ -1336,6 +1409,8 @@ extern struct bpf_empty_prog_array bpf_empty_prog_array; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); +/* Use when traversal over the bpf_prog_array uses tasks_trace rcu */ +void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); bool bpf_prog_array_is_empty(struct bpf_prog_array *array); int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, @@ -1427,6 +1502,55 @@ bpf_prog_run_array(const struct bpf_prog_array *array, return ret; } +/* Notes on RCU design for bpf_prog_arrays containing sleepable programs: + * + * We use the tasks_trace rcu flavor read section to protect the bpf_prog_array + * overall. As a result, we must use the bpf_prog_array_free_sleepable + * in order to use the tasks_trace rcu grace period. + * + * When a non-sleepable program is inside the array, we take the rcu read + * section and disable preemption for that program alone, so it can access + * rcu-protected dynamically sized maps. + */ +static __always_inline u32 +bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const struct bpf_prog_array *array; + struct bpf_run_ctx *old_run_ctx; + struct bpf_trace_run_ctx run_ctx; + u32 ret = 1; + + might_fault(); + + rcu_read_lock_trace(); + migrate_disable(); + + array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); + if (unlikely(!array)) + goto out; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + item = &array->items[0]; + while ((prog = READ_ONCE(item->prog))) { + if (!prog->aux->sleepable) + rcu_read_lock(); + + run_ctx.bpf_cookie = item->bpf_cookie; + ret &= run_prog(prog, ctx); + item++; + + if (!prog->aux->sleepable) + rcu_read_unlock(); + } + bpf_reset_run_ctx(old_run_ctx); +out: + migrate_enable(); + rcu_read_unlock_trace(); + return ret; +} + #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; @@ -2104,6 +2228,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); void sock_map_unhash(struct sock *sk); +void sock_map_destroy(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, @@ -2261,12 +2386,13 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; -extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; +extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto; +extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; -extern const struct bpf_func_proto bpf_strncmp_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; -extern const struct bpf_func_proto bpf_kptr_xchg_proto; +extern const struct bpf_func_proto bpf_set_retval_proto; +extern const struct bpf_func_proto bpf_get_retval_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -2420,4 +2546,12 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); int bpf_dynptr_check_size(u32 size); +#ifdef CONFIG_BPF_LSM +void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); +void bpf_cgroup_atype_put(int cgroup_atype); +#else +static inline void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) {} +static inline void bpf_cgroup_atype_put(int cgroup_atype) {} +#endif /* CONFIG_BPF_LSM */ + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index 479c101546ad..4bcf76a9bb06 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -42,6 +42,8 @@ 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); +void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func); + #else /* !CONFIG_BPF_LSM */ static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id) @@ -65,6 +67,11 @@ static inline void bpf_inode_storage_free(struct inode *inode) { } +static inline void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, + bpf_func_t *bpf_func) +{ +} + #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e8439f6cbe57..81b19669efba 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -299,7 +299,7 @@ struct bpf_verifier_state { * If is_state_visited() sees a state with branches > 0 it means * there is a loop. If such state is exactly equal to the current state * it's an infinite loop. Note states_equal() checks for states - * equvalency, so two states being 'states_equal' does not mean + * equivalency, so two states being 'states_equal' does not mean * infinite loop. The exact comparison is provided by * states_maybe_looping() function. It's a stronger pre-check and * much faster than states_equal(). @@ -344,6 +344,14 @@ struct bpf_verifier_state_list { int miss_cnt, hit_cnt; }; +struct bpf_loop_inline_state { + int initialized:1; /* set to true upon first entry */ + int fit_for_inline:1; /* true if callback function is the same + * at each call and flags are always zero + */ + u32 callback_subprogno; /* valid when fit_for_inline is true */ +}; + /* Possible states for alu_state member. */ #define BPF_ALU_SANITIZE_SRC (1U << 0) #define BPF_ALU_SANITIZE_DST (1U << 1) @@ -373,6 +381,10 @@ struct bpf_insn_aux_data { u32 mem_size; /* mem_size for non-struct typed var */ }; } btf_var; + /* if instruction is a call to bpf_loop this field tracks + * the state of the relevant registers to make decision about inlining + */ + struct bpf_loop_inline_state loop_inline_state; }; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 747fad264033..6ff567ece34a 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -16,6 +16,7 @@ #define PHY_ID_BCM5481 0x0143bca0 #define PHY_ID_BCM5395 0x0143bcf0 #define PHY_ID_BCM53125 0x03625f20 +#define PHY_ID_BCM53128 0x03625e10 #define PHY_ID_BCM54810 0x03625d00 #define PHY_ID_BCM54811 0x03625cc0 #define PHY_ID_BCM5482 0x0143bcb0 diff --git a/include/linux/btf.h b/include/linux/btf.h index 2611cea2c2b6..1bfed7fa0428 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -177,6 +177,19 @@ static inline bool btf_type_is_enum(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } +static inline bool btf_is_any_enum(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM || + BTF_INFO_KIND(t->info) == BTF_KIND_ENUM64; +} + +static inline bool btf_kind_core_compat(const struct btf_type *t1, + const struct btf_type *t2) +{ + return BTF_INFO_KIND(t1->info) == BTF_INFO_KIND(t2->info) || + (btf_is_any_enum(t1) && btf_is_any_enum(t2)); +} + static inline bool str_is_empty(const char *s) { return !s || !s[0]; @@ -192,6 +205,16 @@ static inline bool btf_is_enum(const struct btf_type *t) return btf_kind(t) == BTF_KIND_ENUM; } +static inline bool btf_is_enum64(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM64; +} + +static inline u64 btf_enum64_value(const struct btf_enum64 *e) +{ + return ((u64)e->val_hi32 << 32) | e->val_lo32; +} + static inline bool btf_is_composite(const struct btf_type *t) { u16 kind = btf_kind(t); @@ -332,6 +355,11 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t) return (struct btf_enum *)(t + 1); } +static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) +{ + return (struct btf_enum64 *)(t + 1); +} + static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 335a19092368..252a4befeab1 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -179,7 +179,8 @@ extern struct btf_id_set name; BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) \ - BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock) + BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCKET, socket) enum { #define BTF_SOCK_TYPE(name, str) name, diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index 7ae21c0f7f23..ef0a77173e3c 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -11,6 +11,8 @@ #define CAN_SYNC_SEG 1 +#define CAN_BITRATE_UNSET 0 +#define CAN_BITRATE_UNKNOWN (-1U) #define CAN_CTRLMODE_TDC_MASK \ (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index fdb22b00674a..182749e858b3 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -31,6 +31,7 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev, struct canfd_frame **cfd); struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf); +bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb); /* * The struct can_skb_priv is used to transport additional information along @@ -96,64 +97,6 @@ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) return nskb; } -/* Check for outgoing skbs that have not been created by the CAN subsystem */ -static inline bool can_skb_headroom_valid(struct net_device *dev, - struct sk_buff *skb) -{ - /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ - if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) - return false; - - /* af_packet does not apply CAN skb specific settings */ - if (skb->ip_summed == CHECKSUM_NONE) { - /* init headroom */ - can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - - /* perform proper loopback on capable devices */ - if (dev->flags & IFF_ECHO) - skb->pkt_type = PACKET_LOOPBACK; - else - skb->pkt_type = PACKET_HOST; - - skb_reset_mac_header(skb); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - } - - return true; -} - -/* Drop a given socketbuffer if it does not contain a valid CAN frame. */ -static inline bool can_dropped_invalid_skb(struct net_device *dev, - struct sk_buff *skb) -{ - const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - - if (skb->protocol == htons(ETH_P_CAN)) { - if (unlikely(skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN)) - goto inval_skb; - } else if (skb->protocol == htons(ETH_P_CANFD)) { - if (unlikely(skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN)) - goto inval_skb; - } else - goto inval_skb; - - if (!can_skb_headroom_valid(dev, skb)) - goto inval_skb; - - return false; - -inval_skb: - kfree_skb(skb); - dev->stats.tx_dropped++; - return true; -} - static inline bool can_is_canfd_skb(const struct sk_buff *skb) { /* the CAN specific type of skb is identified by its data length */ diff --git a/include/linux/filter.h b/include/linux/filter.h index ed0c0ff42ad5..4c1a8b247545 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -559,40 +559,6 @@ struct bpf_prog_stats { struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); -struct bpf_prog { - u16 pages; /* Number of allocated pages */ - u16 jited:1, /* Is our filter JIT'ed? */ - jit_requested:1,/* archs need to JIT the prog */ - gpl_compatible:1, /* Is filter GPL compatible? */ - cb_access:1, /* Is control block accessed? */ - dst_needed:1, /* Do we need dst entry? */ - blinding_requested:1, /* needs constant blinding */ - blinded:1, /* Was blinded */ - is_func:1, /* program is a bpf function */ - kprobe_override:1, /* Do we override a kprobe? */ - has_callchain_buf:1, /* callchain buffer allocated? */ - enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ - call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ - call_get_func_ip:1, /* Do we call get_func_ip() */ - tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ - enum bpf_prog_type type; /* Type of BPF program */ - enum bpf_attach_type expected_attach_type; /* For some prog types */ - u32 len; /* Number of filter blocks */ - u32 jited_len; /* Size of jited insns in bytes */ - u8 tag[BPF_TAG_SIZE]; - struct bpf_prog_stats __percpu *stats; - int __percpu *active; - unsigned int (*bpf_func)(const void *ctx, - const struct bpf_insn *insn); - struct bpf_prog_aux *aux; /* Auxiliary fields */ - struct sock_fprog_kern *orig_prog; /* Original BPF program */ - /* Instructions for interpreter */ - union { - DECLARE_FLEX_ARRAY(struct sock_filter, insns); - DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); - }; -}; - struct sk_filter { refcount_t refcnt; struct rcu_head rcu; @@ -948,6 +914,7 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); +bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_helper_changes_pkt_data(void *func); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 75d40acb60c1..f386f9ed41f3 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -76,6 +76,7 @@ #define IEEE80211_STYPE_ACTION 0x00D0 /* control */ +#define IEEE80211_STYPE_TRIGGER 0x0020 #define IEEE80211_STYPE_CTL_EXT 0x0060 #define IEEE80211_STYPE_BACK_REQ 0x0080 #define IEEE80211_STYPE_BACK 0x0090 @@ -295,6 +296,17 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_HT_CTL_LEN 4 +/* trigger type within common_info of trigger frame */ +#define IEEE80211_TRIGGER_TYPE_MASK 0xf +#define IEEE80211_TRIGGER_TYPE_BASIC 0x0 +#define IEEE80211_TRIGGER_TYPE_BFRP 0x1 +#define IEEE80211_TRIGGER_TYPE_MU_BAR 0x2 +#define IEEE80211_TRIGGER_TYPE_MU_RTS 0x3 +#define IEEE80211_TRIGGER_TYPE_BSRP 0x4 +#define IEEE80211_TRIGGER_TYPE_GCR_MU_BAR 0x5 +#define IEEE80211_TRIGGER_TYPE_BQRP 0x6 +#define IEEE80211_TRIGGER_TYPE_NFRP 0x7 + struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; @@ -324,6 +336,15 @@ struct ieee80211_qos_hdr { __le16 qos_ctrl; } __packed __aligned(2); +struct ieee80211_trigger { + __le16 frame_control; + __le16 duration; + u8 ra[ETH_ALEN]; + u8 ta[ETH_ALEN]; + __le64 common_info; + u8 variable[]; +} __packed __aligned(2); + /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder @@ -730,6 +751,16 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) } /** + * ieee80211_is_trigger - check if frame is trigger frame + * @fc: frame control field in little-endian byteorder + */ +static inline bool ieee80211_is_trigger(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == + cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_TRIGGER); +} + +/** * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder */ @@ -4063,6 +4094,7 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) *category != WLAN_CATEGORY_SELF_PROTECTED && *category != WLAN_CATEGORY_UNPROT_DMG && *category != WLAN_CATEGORY_VHT && + *category != WLAN_CATEGORY_S1G && *category != WLAN_CATEGORY_VENDOR_SPECIFIC; } @@ -4345,4 +4377,229 @@ enum ieee80211_range_params_max_total_ltf { IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_UNSPECIFIED, }; +/* multi-link device */ +#define IEEE80211_MLD_MAX_NUM_LINKS 15 + +#define IEEE80211_ML_CONTROL_TYPE 0x0007 +#define IEEE80211_ML_CONTROL_TYPE_BASIC 0 +#define IEEE80211_ML_CONTROL_TYPE_PREQ 1 +#define IEEE80211_ML_CONTROL_TYPE_RECONF 2 +#define IEEE80211_ML_CONTROL_TYPE_TDLS 3 +#define IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS 4 +#define IEEE80211_ML_CONTROL_PRESENCE_MASK 0xfff0 + +struct ieee80211_multi_link_elem { + __le16 control; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_BASIC_PRES_LINK_ID 0x0010 +#define IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT 0x0020 +#define IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY 0x0040 +#define IEEE80211_MLC_BASIC_PRES_EML_CAPA 0x0080 +#define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP 0x0100 +#define IEEE80211_MLC_BASIC_PRES_MLD_ID 0x0200 + +#define IEEE80211_MED_SYNC_DELAY_DURATION 0x00ff +#define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH 0x0f00 +#define IEEE80211_MED_SYNC_DELAY_SYNC_MAX_NUM_TXOPS 0xf000 + +#define IEEE80211_EML_CAP_EMLSR_SUPP 0x0001 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY 0x000e +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_32US 1 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_64US 2 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_128US 3 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US 4 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY 0x0070 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_16US 1 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_32US 2 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US 3 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_128US 4 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US 5 +#define IEEE80211_EML_CAP_EMLMR_SUPPORT 0x0080 +#define IEEE80211_EML_CAP_EMLMR_DELAY 0x0700 +#define IEEE80211_EML_CAP_EMLMR_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLMR_DELAY_32US 1 +#define IEEE80211_EML_CAP_EMLMR_DELAY_64US 2 +#define IEEE80211_EML_CAP_EMLMR_DELAY_128US 3 +#define IEEE80211_EML_CAP_EMLMR_DELAY_256US 4 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT 0x7800 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_0 0 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128US 1 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_256US 2 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_512US 3 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_1TU 4 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_2TU 5 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_4TU 6 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_8TU 7 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_16TU 8 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_32TU 9 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_64TU 10 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU 11 + +#define IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS 0x000f +#define IEEE80211_MLD_CAP_OP_SRS_SUPPORT 0x0010 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP 0x0060 +#define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND 0x0f80 +#define IEEE80211_MLD_CAP_OP_AAR_SUPPORT 0x1000 + +struct ieee80211_mle_basic_common_info { + u8 len; + u8 mld_mac_addr[ETH_ALEN]; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_PREQ_PRES_MLD_ID 0x0010 + +struct ieee80211_mle_preq_common_info { + u8 len; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR 0x0010 + +/* no fixed fields in RECONF */ + +struct ieee80211_mle_tdls_common_info { + u8 len; + u8 ap_mld_mac_addr[ETH_ALEN]; +} __packed; + +#define IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR 0x0010 + +/* no fixed fields in PRIO_ACCESS */ + +/** + * ieee80211_mle_common_size - check multi-link element common size + * @data: multi-link element, must already be checked for size using + * ieee80211_mle_size_ok() + */ +static inline u8 ieee80211_mle_common_size(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + u8 common = 0; + + switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { + case IEEE80211_ML_CONTROL_TYPE_BASIC: + common += sizeof(struct ieee80211_mle_basic_common_info); + break; + case IEEE80211_ML_CONTROL_TYPE_PREQ: + common += sizeof(struct ieee80211_mle_preq_common_info); + break; + case IEEE80211_ML_CONTROL_TYPE_RECONF: + if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) + common += ETH_ALEN; + return common; + case IEEE80211_ML_CONTROL_TYPE_TDLS: + common += sizeof(struct ieee80211_mle_tdls_common_info); + break; + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: + if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) + common += ETH_ALEN; + return common; + default: + WARN_ON(1); + return 0; + } + + return common + mle->variable[0]; +} + +/** + * ieee80211_mle_size_ok - validate multi-link element size + * @data: pointer to the element data + * @len: length of the containing element + */ +static inline bool ieee80211_mle_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u8 fixed = sizeof(*mle); + u8 common = 0; + bool check_common_len = false; + u16 control; + + if (len < fixed) + return false; + + control = le16_to_cpu(mle->control); + + switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { + case IEEE80211_ML_CONTROL_TYPE_BASIC: + common += sizeof(struct ieee80211_mle_basic_common_info); + check_common_len = true; + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) + common += 1; + break; + case IEEE80211_ML_CONTROL_TYPE_PREQ: + common += sizeof(struct ieee80211_mle_preq_common_info); + if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID) + common += 1; + check_common_len = true; + break; + case IEEE80211_ML_CONTROL_TYPE_RECONF: + if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) + common += ETH_ALEN; + break; + case IEEE80211_ML_CONTROL_TYPE_TDLS: + common += sizeof(struct ieee80211_mle_tdls_common_info); + check_common_len = true; + break; + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: + if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) + common += ETH_ALEN; + break; + default: + /* we don't know this type */ + return true; + } + + if (len < fixed + common) + return false; + + if (!check_common_len) + return true; + + /* if present, common length is the first octet there */ + return mle->variable[0] >= common; +} + +enum ieee80211_mle_subelems { + IEEE80211_MLE_SUBELEM_PER_STA_PROFILE = 0, +}; + +#define IEEE80211_MLE_STA_CONTROL_LINK_ID 0x000f +#define IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE 0x0010 +#define IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 +#define IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT 0x0040 +#define IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT 0x0080 +#define IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT 0x0100 +#define IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT 0x0200 +#define IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE 0x0400 +#define IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT 0x0800 + +struct ieee80211_mle_per_sta_profile { + __le16 control; + u8 sta_info_len; + u8 variable[]; +} __packed; + +#define for_each_mle_subelement(_elem, _data, _len) \ + if (ieee80211_mle_size_ok(_data, _len)) \ + for_each_element(_elem, \ + _data + ieee80211_mle_common_size(_data),\ + _len - ieee80211_mle_common_size(_data)) + #endif /* LINUX_IEEE80211_H */ diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index b42294739063..523025106a64 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -46,10 +46,10 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, pcpu_stats = get_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->rx_packets++; - pcpu_stats->rx_bytes += len; + u64_stats_inc(&pcpu_stats->rx_packets); + u64_stats_add(&pcpu_stats->rx_bytes, len); if (multicast) - pcpu_stats->rx_multicast++; + u64_stats_inc(&pcpu_stats->rx_multicast); u64_stats_update_end(&pcpu_stats->syncp); put_cpu_ptr(vlan->pcpu_stats); } else { diff --git a/include/linux/if_team.h b/include/linux/if_team.h index add607943c95..fc985e5c739d 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -12,11 +12,11 @@ #include <uapi/linux/if_team.h> struct team_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_multicast; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_dropped; u32 tx_dropped; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 2be4dd7e90a9..e00c4ee81ff7 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -118,11 +118,11 @@ static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev) * @tx_dropped: number of tx drops */ struct vlan_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_multicast; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errors; u32 tx_dropped; diff --git a/include/linux/mii.h b/include/linux/mii.h index 5ee13083cec7..d5a959ce4877 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -545,4 +545,39 @@ static inline u8 mii_resolve_flowctrl_fdx(u16 lcladv, u16 rmtadv) return cap; } +/** + * mii_bmcr_encode_fixed - encode fixed speed/duplex settings to a BMCR value + * @speed: a SPEED_* value + * @duplex: a DUPLEX_* value + * + * Encode the speed and duplex to a BMCR value. 2500, 1000, 100 and 10 Mbps are + * supported. 2500Mbps is encoded to 1000Mbps. Other speeds are encoded as 10 + * Mbps. Unknown duplex values are encoded to half-duplex. + */ +static inline u16 mii_bmcr_encode_fixed(int speed, int duplex) +{ + u16 bmcr; + + switch (speed) { + case SPEED_2500: + case SPEED_1000: + bmcr = BMCR_SPEED1000; + break; + + case SPEED_100: + bmcr = BMCR_SPEED100; + break; + + case SPEED_10: + default: + bmcr = BMCR_SPEED10; + break; + } + + if (duplex == DUPLEX_FULL) + bmcr |= BMCR_FULLDPLX; + + return bmcr; +} + #endif /* __LINUX_MII_H__ */ diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 604b85dd770a..b5f58fd37a0f 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -387,21 +387,6 @@ enum { }; enum { - MLX5_DEV_CAP_FLAG_XRC = 1LL << 3, - MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR = 1LL << 8, - MLX5_DEV_CAP_FLAG_BAD_QKEY_CNTR = 1LL << 9, - MLX5_DEV_CAP_FLAG_APM = 1LL << 17, - MLX5_DEV_CAP_FLAG_ATOMIC = 1LL << 18, - MLX5_DEV_CAP_FLAG_BLOCK_MCAST = 1LL << 23, - MLX5_DEV_CAP_FLAG_ON_DMND_PG = 1LL << 24, - MLX5_DEV_CAP_FLAG_CQ_MODER = 1LL << 29, - MLX5_DEV_CAP_FLAG_RESIZE_CQ = 1LL << 30, - MLX5_DEV_CAP_FLAG_DCT = 1LL << 37, - MLX5_DEV_CAP_FLAG_SIG_HAND_OVER = 1LL << 40, - MLX5_DEV_CAP_FLAG_CMDIF_CSUM = 3LL << 46, -}; - -enum { MLX5_ROCE_VERSION_1 = 0, MLX5_ROCE_VERSION_2 = 2, }; @@ -455,6 +440,7 @@ enum { MLX5_OPCODE_UMR = 0x25, + MLX5_OPCODE_ACCESS_ASO = 0x2d, }; enum { @@ -496,10 +482,6 @@ enum { }; enum { - MLX5_CAP_OFF_CMDIF_CSUM = 46, -}; - -enum { /* * Max wqe size for rdma read is 512 bytes, so this * limits our max_sge_rd as the wqe needs to fit: @@ -840,7 +822,10 @@ struct mlx5_cqe64 { __be32 timestamp_l; __be32 sop_drop_qpn; __be16 wqe_counter; - u8 signature; + union { + u8 signature; + u8 validity_iteration_count; + }; u8 op_own; }; @@ -872,6 +857,11 @@ enum { MLX5_CQE_FORMAT_CSUM_STRIDX = 0x3, }; +enum { + MLX5_CQE_COMPRESS_LAYOUT_BASIC = 0, + MLX5_CQE_COMPRESS_LAYOUT_ENHANCED = 1, +}; + #define MLX5_MINI_CQE_ARRAY_SIZE 8 static inline u8 mlx5_get_cqe_format(struct mlx5_cqe64 *cqe) @@ -884,6 +874,12 @@ static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe) return cqe->op_own >> 4; } +static inline u8 get_cqe_enhanced_num_mini_cqes(struct mlx5_cqe64 *cqe) +{ + /* num_of_mini_cqes is zero based */ + return get_cqe_opcode(cqe) + 1; +} + static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) { return (cqe->lro.tcppsh_abort_dupack >> 6) & 1; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5040cd774c5a..bd882884b23c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -551,6 +551,10 @@ enum { * creation/deletion on drivers rescan. Unset during device attach. */ MLX5_PRIV_FLAGS_DETACH = 1 << 2, + /* Distinguish between mlx5e_probe/remove called by module init/cleanup + * and called by other flows which can already hold devlink lock + */ + MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW = 1 << 3, }; struct mlx5_adev { @@ -676,6 +680,7 @@ struct mlx5e_resources { enum mlx5_sw_icm_type { MLX5_SW_ICM_TYPE_STEERING, MLX5_SW_ICM_TYPE_HEADER_MODIFY, + MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN, }; #define MLX5_MAX_RESERVED_GIDS 8 diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 8b18fe9771f9..e2701ed0200e 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -12,7 +12,6 @@ #define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) enum { - MLX5_ESWITCH_NONE, MLX5_ESWITCH_LEGACY, MLX5_ESWITCH_OFFLOADS }; @@ -153,7 +152,7 @@ struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); static inline u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { - return MLX5_ESWITCH_NONE; + return MLX5_ESWITCH_LEGACY; } static inline enum devlink_eswitch_encap_mode @@ -198,6 +197,11 @@ static inline struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitc #endif /* CONFIG_MLX5_ESWITCH */ +static inline bool is_mdev_legacy_mode(struct mlx5_core_dev *dev) +{ + return mlx5_eswitch_mode(dev) == MLX5_ESWITCH_LEGACY; +} + static inline bool is_mdev_switchdev_mode(struct mlx5_core_dev *dev) { return mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 8135713b0d2d..ece3e35622d7 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -212,6 +212,19 @@ struct mlx5_flow_group * mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *in); void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); +struct mlx5_exe_aso { + u32 object_id; + u8 type; + u8 return_reg_id; + union { + u32 ctrl_data; + struct { + u8 meter_idx; + u8 init_color; + } flow_meter; + }; +}; + struct mlx5_fs_vlan { u16 ethtype; u16 vid; @@ -237,6 +250,7 @@ struct mlx5_flow_act { struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; struct mlx5_flow_group *fg; + struct mlx5_exe_aso exe_aso; }; #define MLX5_DECLARE_FLOW_ACT(name) \ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fd7d083a34d3..8e87eb47f9dc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -442,7 +442,9 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 max_modify_header_actions[0x8]; u8 max_ft_level[0x8]; - u8 reserved_at_40[0x20]; + u8 reserved_at_40[0x6]; + u8 execute_aso[0x1]; + u8 reserved_at_47[0x19]; u8 reserved_at_60[0x2]; u8 reformat_insert[0x1]; @@ -940,7 +942,17 @@ struct mlx5_ifc_qos_cap_bits { u8 max_tsar_bw_share[0x20]; - u8 reserved_at_100[0x700]; + u8 reserved_at_100[0x20]; + + u8 reserved_at_120[0x3]; + u8 log_meter_aso_granularity[0x5]; + u8 reserved_at_128[0x3]; + u8 log_meter_aso_max_alloc[0x5]; + u8 reserved_at_130[0x3]; + u8 log_max_num_meter_aso[0x5]; + u8 reserved_at_138[0x8]; + + u8 reserved_at_140[0x6c0]; }; struct mlx5_ifc_debug_cap_bits { @@ -1086,11 +1098,14 @@ struct mlx5_ifc_device_mem_cap_bits { u8 log_sw_icm_alloc_granularity[0x6]; u8 log_steering_sw_icm_size[0x8]; - u8 reserved_at_120[0x20]; + u8 reserved_at_120[0x18]; + u8 log_header_modify_pattern_sw_icm_size[0x8]; u8 header_modify_sw_icm_start_address[0x40]; - u8 reserved_at_180[0x80]; + u8 reserved_at_180[0x40]; + + u8 header_modify_pattern_sw_icm_start_address[0x40]; u8 memic_operations[0x20]; @@ -1426,7 +1441,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_120[0xa]; u8 log_max_ra_req_dc[0x6]; - u8 reserved_at_130[0xa]; + u8 reserved_at_130[0x9]; + u8 vnic_env_cq_overrun[0x1]; u8 log_max_ra_res_dc[0x6]; u8 reserved_at_140[0x5]; @@ -1621,7 +1637,11 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 nic_receive_steering_discard[0x1]; u8 receive_discard_vport_down[0x1]; u8 transmit_discard_vport_down[0x1]; - u8 reserved_at_343[0x5]; + u8 eq_overrun_count[0x1]; + u8 reserved_at_344[0x1]; + u8 invalid_command_count[0x1]; + u8 quota_exceeded_count[0x1]; + u8 reserved_at_347[0x1]; u8 log_max_flow_counter_bulk[0x8]; u8 max_flow_counter_15_0[0x10]; @@ -1719,7 +1739,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_dci_errored_streams[0x5]; u8 reserved_at_598[0x8]; - u8 reserved_at_5a0[0x13]; + u8 reserved_at_5a0[0x10]; + u8 enhanced_cqe_compression[0x1]; + u8 reserved_at_5b1[0x2]; u8 log_max_dek[0x5]; u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; @@ -3277,6 +3299,7 @@ enum { MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, MLX5_FLOW_CONTEXT_ACTION_IPSEC_DECRYPT = 0x1000, MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT = 0x2000, + MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO = 0x4000, }; enum { @@ -3292,6 +3315,38 @@ struct mlx5_ifc_vlan_bits { u8 vid[0xc]; }; +enum { + MLX5_FLOW_METER_COLOR_RED = 0x0, + MLX5_FLOW_METER_COLOR_YELLOW = 0x1, + MLX5_FLOW_METER_COLOR_GREEN = 0x2, + MLX5_FLOW_METER_COLOR_UNDEFINED = 0x3, +}; + +enum { + MLX5_EXE_ASO_FLOW_METER = 0x2, +}; + +struct mlx5_ifc_exe_aso_ctrl_flow_meter_bits { + u8 return_reg_id[0x4]; + u8 aso_type[0x4]; + u8 reserved_at_8[0x14]; + u8 action[0x1]; + u8 init_color[0x2]; + u8 meter_id[0x1]; +}; + +union mlx5_ifc_exe_aso_ctrl { + struct mlx5_ifc_exe_aso_ctrl_flow_meter_bits exe_aso_ctrl_flow_meter; +}; + +struct mlx5_ifc_execute_aso_bits { + u8 valid[0x1]; + u8 reserved_at_1[0x7]; + u8 aso_object_id[0x18]; + + union mlx5_ifc_exe_aso_ctrl exe_aso_ctrl; +}; + struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_vlan_bits push_vlan; @@ -3323,7 +3378,9 @@ struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_fte_match_param_bits match_value; - u8 reserved_at_1200[0x600]; + struct mlx5_ifc_execute_aso_bits execute_aso[4]; + + u8 reserved_at_1300[0x500]; union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[]; }; @@ -3391,11 +3448,21 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits { u8 transmit_discard_vport_down[0x40]; - u8 reserved_at_140[0xa0]; + u8 async_eq_overrun[0x20]; + + u8 comp_eq_overrun[0x20]; + + u8 reserved_at_180[0x20]; + + u8 invalid_command[0x20]; + + u8 quota_exceeded_command[0x20]; u8 internal_rq_out_of_buffer[0x20]; - u8 reserved_at_200[0xe00]; + u8 cq_overrun[0x20]; + + u8 reserved_at_220[0xde0]; }; struct mlx5_ifc_traffic_counter_bits { @@ -4074,7 +4141,8 @@ struct mlx5_ifc_cqc_bits { u8 cqe_comp_en[0x1]; u8 mini_cqe_res_format[0x2]; u8 st[0x4]; - u8 reserved_at_18[0x8]; + u8 reserved_at_18[0x6]; + u8 cqe_compression_layout[0x2]; u8 reserved_at_20[0x20]; @@ -5970,7 +6038,9 @@ struct mlx5_ifc_general_obj_in_cmd_hdr_bits { u8 obj_id[0x20]; - u8 reserved_at_60[0x20]; + u8 reserved_at_60[0x3]; + u8 log_obj_range[0x5]; + u8 reserved_at_68[0x18]; }; struct mlx5_ifc_general_obj_out_cmd_hdr_bits { @@ -11370,12 +11440,14 @@ enum { MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT_ULL(0xc), MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT_ULL(0x13), MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT_ULL(0x20), + MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = BIT_ULL(0x24), }; enum { MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13, MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20, + MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24, }; enum { @@ -11448,6 +11520,61 @@ struct mlx5_ifc_create_encryption_key_in_bits { struct mlx5_ifc_encryption_key_obj_bits encryption_key_object; }; +enum { + MLX5_FLOW_METER_MODE_BYTES_IP_LENGTH = 0x0, + MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2 = 0x1, + MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2_IPG = 0x2, + MLX5_FLOW_METER_MODE_NUM_PACKETS = 0x3, +}; + +struct mlx5_ifc_flow_meter_parameters_bits { + u8 valid[0x1]; + u8 bucket_overflow[0x1]; + u8 start_color[0x2]; + u8 both_buckets_on_green[0x1]; + u8 reserved_at_5[0x1]; + u8 meter_mode[0x2]; + u8 reserved_at_8[0x18]; + + u8 reserved_at_20[0x20]; + + u8 reserved_at_40[0x3]; + u8 cbs_exponent[0x5]; + u8 cbs_mantissa[0x8]; + u8 reserved_at_50[0x3]; + u8 cir_exponent[0x5]; + u8 cir_mantissa[0x8]; + + u8 reserved_at_60[0x20]; + + u8 reserved_at_80[0x3]; + u8 ebs_exponent[0x5]; + u8 ebs_mantissa[0x8]; + u8 reserved_at_90[0x3]; + u8 eir_exponent[0x5]; + u8 eir_mantissa[0x8]; + + u8 reserved_at_a0[0x60]; +}; + +struct mlx5_ifc_flow_meter_aso_obj_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x40]; + + u8 reserved_at_80[0x8]; + u8 meter_aso_access_pd[0x18]; + + u8 reserved_at_a0[0x160]; + + struct mlx5_ifc_flow_meter_parameters_bits flow_meter_parameters[2]; +}; + +struct mlx5_ifc_create_flow_meter_aso_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_flow_meter_aso_obj_bits flow_meter_aso_obj; +}; + struct mlx5_ifc_sampler_obj_bits { u8 modify_field_select[0x40]; diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index e05ee9f001ff..9dd4bf157255 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -26,7 +26,7 @@ * @remote: Remote address for tunnels */ struct vif_device { - struct net_device *dev; + struct net_device __rcu *dev; netdevice_tracker dev_tracker; unsigned long bytes_in, bytes_out; unsigned long pkt_in, pkt_out; @@ -52,6 +52,7 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, + struct net_device *vif_dev, unsigned short vif_index, u32 tb_id, struct netlink_ext_ack *extack) { @@ -60,7 +61,7 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, .family = family, .extack = extack, }, - .dev = vif->dev, + .dev = vif_dev, .vif_index = vif_index, .vif_flags = vif->flags, .tb_id = tb_id, @@ -73,6 +74,7 @@ static inline int mr_call_vif_notifiers(struct net *net, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, + struct net_device *vif_dev, unsigned short vif_index, u32 tb_id, unsigned int *ipmr_seq) { @@ -80,7 +82,7 @@ static inline int mr_call_vif_notifiers(struct net *net, .info = { .family = family, }, - .dev = vif->dev, + .dev = vif_dev, .vif_index = vif_index, .vif_flags = vif->flags, .tb_id = tb_id, @@ -98,7 +100,8 @@ static inline int mr_call_vif_notifiers(struct net *net, #define MAXVIFS 32 #endif -#define VIF_EXISTS(_mrt, _idx) (!!((_mrt)->vif_table[_idx].dev)) +/* Note: This helper is deprecated. */ +#define VIF_EXISTS(_mrt, _idx) (!!rcu_access_pointer((_mrt)->vif_table[_idx].dev)) /* mfc_flags: * MFC_STATIC - the entry was added statically (not by a routing daemon) @@ -305,7 +308,7 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock, struct netlink_ext_ack *extack); + struct netlink_ext_ack *extack); #else static inline void vif_device_init(struct vif_device *v, struct net_device *dev, @@ -360,7 +363,7 @@ static inline int mr_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock, struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack) { return -EINVAL; } diff --git a/include/linux/net.h b/include/linux/net.h index 12093f4db50c..a03485e8cbb2 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -152,6 +152,8 @@ struct module; struct sk_buff; typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, unsigned int, size_t); +typedef int (*skb_read_actor_t)(struct sock *, struct sk_buff *); + struct proto_ops { int family; @@ -214,6 +216,8 @@ struct proto_ops { */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); + /* This is different from read_sock(), it reads an entire skb at a time. */ + int (*read_skb)(struct sock *sk, skb_read_actor_t recv_actor); int (*sendpage_locked)(struct sock *sk, struct page *page, int offset, size_t size, int flags); int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2563d30736e9..1a3cb93c3dcc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2636,10 +2636,10 @@ struct packet_offload { /* often modified stats are per-CPU, other are shared (netdev->stats) */ struct pcpu_sw_netstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); @@ -2656,8 +2656,8 @@ static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int l struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->rx_bytes += len; - tstats->rx_packets++; + u64_stats_add(&tstats->rx_bytes, len); + u64_stats_inc(&tstats->rx_packets); u64_stats_update_end(&tstats->syncp); } @@ -2668,8 +2668,8 @@ static inline void dev_sw_netstats_tx_add(struct net_device *dev, struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += len; - tstats->tx_packets += packets; + u64_stats_add(&tstats->tx_bytes, len); + u64_stats_add(&tstats->tx_packets, packets); u64_stats_update_end(&tstats->syncp); } @@ -3981,8 +3981,8 @@ static inline void netdev_tracker_free(struct net_device *dev, #endif } -static inline void dev_hold_track(struct net_device *dev, - netdevice_tracker *tracker, gfp_t gfp) +static inline void netdev_hold(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) { if (dev) { __dev_hold(dev); @@ -3990,8 +3990,8 @@ static inline void dev_hold_track(struct net_device *dev, } } -static inline void dev_put_track(struct net_device *dev, - netdevice_tracker *tracker) +static inline void netdev_put(struct net_device *dev, + netdevice_tracker *tracker) { if (dev) { netdev_tracker_free(dev, tracker); @@ -4004,11 +4004,11 @@ static inline void dev_put_track(struct net_device *dev, * @dev: network device * * Hold reference to device to keep it from being freed. - * Try using dev_hold_track() instead. + * Try using netdev_hold() instead. */ static inline void dev_hold(struct net_device *dev) { - dev_hold_track(dev, NULL, GFP_ATOMIC); + netdev_hold(dev, NULL, GFP_ATOMIC); } /** @@ -4016,17 +4016,17 @@ static inline void dev_hold(struct net_device *dev) * @dev: network device * * Release reference to device to allow it to be freed. - * Try using dev_put_track() instead. + * Try using netdev_put() instead. */ static inline void dev_put(struct net_device *dev) { - dev_put_track(dev, NULL); + netdev_put(dev, NULL); } -static inline void dev_replace_track(struct net_device *odev, - struct net_device *ndev, - netdevice_tracker *tracker, - gfp_t gfp) +static inline void netdev_ref_replace(struct net_device *odev, + struct net_device *ndev, + netdevice_tracker *tracker, + gfp_t gfp) { if (odev) netdev_tracker_free(odev, tracker); diff --git a/include/linux/pcs-rzn1-miic.h b/include/linux/pcs-rzn1-miic.h new file mode 100644 index 000000000000..56d12b21365d --- /dev/null +++ b/include/linux/pcs-rzn1-miic.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Schneider Electric + * + * Clément Léger <clement.leger@bootlin.com> + */ + +#ifndef __LINUX_PCS_MIIC_H +#define __LINUX_PCS_MIIC_H + +struct phylink; +struct device_node; + +struct phylink_pcs *miic_create(struct device *dev, struct device_node *np); + +void miic_destroy(struct phylink_pcs *pcs); + +#endif /* __LINUX_PCS_MIIC_H */ diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 266eb26fb029..d2da1e0b4a92 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -17,6 +17,7 @@ #define DW_AN_C73 1 #define DW_AN_C37_SGMII 2 #define DW_2500BASEX 3 +#define DW_AN_C37_1000BASEX 4 struct xpcs_id; @@ -30,7 +31,7 @@ int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, - unsigned int mode); + unsigned int mode, const unsigned long *advertising); void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); diff --git a/include/linux/phy.h b/include/linux/phy.h index b09f7d36cff2..87638c55d844 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1545,6 +1545,9 @@ static inline void phy_device_reset(struct phy_device *phydev, int value) #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) +#define phydev_err_probe(_phydev, err, format, args...) \ + dev_err_probe(&_phydev->mdio.dev, err, format, ##args) + #define phydev_info(_phydev, format, args...) \ dev_info(&_phydev->mdio.dev, format, ##args) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d3d10556f0fa..f6a27ab19202 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -43,6 +43,7 @@ #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> +#include <net/dropreason.h> /** * DOC: skb checksums @@ -337,184 +338,6 @@ struct sk_buff_head { struct sk_buff; -/* The reason of skb drop, which is used in kfree_skb_reason(). - * en...maybe they should be splited by group? - * - * Each item here should also be in 'TRACE_SKB_DROP_REASON', which is - * used to translate the reason to string. - */ -enum skb_drop_reason { - SKB_NOT_DROPPED_YET = 0, - SKB_DROP_REASON_NOT_SPECIFIED, /* drop reason is not specified */ - SKB_DROP_REASON_NO_SOCKET, /* socket not found */ - SKB_DROP_REASON_PKT_TOO_SMALL, /* packet size is too small */ - SKB_DROP_REASON_TCP_CSUM, /* TCP checksum error */ - SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ - SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ - SKB_DROP_REASON_NETFILTER_DROP, /* dropped by netfilter */ - SKB_DROP_REASON_OTHERHOST, /* packet don't belong to current - * host (interface is in promisc - * mode) - */ - SKB_DROP_REASON_IP_CSUM, /* IP checksum error */ - SKB_DROP_REASON_IP_INHDR, /* there is something wrong with - * IP header (see - * IPSTATS_MIB_INHDRERRORS) - */ - SKB_DROP_REASON_IP_RPFILTER, /* IP rpfilter validate failed. - * see the document for rp_filter - * in ip-sysctl.rst for more - * information - */ - SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2 - * is multicast, but L3 is - * unicast. - */ - SKB_DROP_REASON_XFRM_POLICY, /* xfrm policy check failed */ - SKB_DROP_REASON_IP_NOPROTO, /* no support for IP protocol */ - SKB_DROP_REASON_SOCKET_RCVBUFF, /* socket receive buff is full */ - SKB_DROP_REASON_PROTO_MEM, /* proto memory limition, such as - * udp packet drop out of - * udp_memory_allocated. - */ - SKB_DROP_REASON_TCP_MD5NOTFOUND, /* no MD5 hash and one - * expected, corresponding - * to LINUX_MIB_TCPMD5NOTFOUND - */ - SKB_DROP_REASON_TCP_MD5UNEXPECTED, /* MD5 hash and we're not - * expecting one, corresponding - * to LINUX_MIB_TCPMD5UNEXPECTED - */ - SKB_DROP_REASON_TCP_MD5FAILURE, /* MD5 hash and its wrong, - * corresponding to - * LINUX_MIB_TCPMD5FAILURE - */ - SKB_DROP_REASON_SOCKET_BACKLOG, /* failed to add skb to socket - * backlog (see - * LINUX_MIB_TCPBACKLOGDROP) - */ - SKB_DROP_REASON_TCP_FLAGS, /* TCP flags invalid */ - SKB_DROP_REASON_TCP_ZEROWINDOW, /* TCP receive window size is zero, - * see LINUX_MIB_TCPZEROWINDOWDROP - */ - SKB_DROP_REASON_TCP_OLD_DATA, /* the TCP data reveived is already - * received before (spurious retrans - * may happened), see - * LINUX_MIB_DELAYEDACKLOST - */ - SKB_DROP_REASON_TCP_OVERWINDOW, /* the TCP data is out of window, - * the seq of the first byte exceed - * the right edges of receive - * window - */ - SKB_DROP_REASON_TCP_OFOMERGE, /* the data of skb is already in - * the ofo queue, corresponding to - * LINUX_MIB_TCPOFOMERGE - */ - SKB_DROP_REASON_TCP_RFC7323_PAWS, /* PAWS check, corresponding to - * LINUX_MIB_PAWSESTABREJECTED - */ - SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ - SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ - SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ - SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ - SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ - SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ - SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ - SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ - SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ - SKB_DROP_REASON_TCP_OFO_DROP, /* data already in receive queue */ - SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ - SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by - * BPF_PROG_TYPE_CGROUP_SKB - * eBPF program - */ - SKB_DROP_REASON_IPV6DISABLED, /* IPv6 is disabled on the device */ - SKB_DROP_REASON_NEIGH_CREATEFAIL, /* failed to create neigh - * entry - */ - SKB_DROP_REASON_NEIGH_FAILED, /* neigh entry in failed state */ - SKB_DROP_REASON_NEIGH_QUEUEFULL, /* arp_queue for neigh - * entry is full - */ - SKB_DROP_REASON_NEIGH_DEAD, /* neigh entry is dead */ - SKB_DROP_REASON_TC_EGRESS, /* dropped in TC egress HOOK */ - SKB_DROP_REASON_QDISC_DROP, /* dropped by qdisc when packet - * outputting (failed to enqueue to - * current qdisc) - */ - SKB_DROP_REASON_CPU_BACKLOG, /* failed to enqueue the skb to - * the per CPU backlog queue. This - * can be caused by backlog queue - * full (see netdev_max_backlog in - * net.rst) or RPS flow limit - */ - SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ - SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ - SKB_DROP_REASON_UNHANDLED_PROTO, /* protocol not implemented - * or not supported - */ - SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation - * error - */ - SKB_DROP_REASON_SKB_GSO_SEG, /* gso segmentation error */ - SKB_DROP_REASON_SKB_UCOPY_FAULT, /* failed to copy data from - * user space, e.g., via - * zerocopy_sg_from_iter() - * or skb_orphan_frags_rx() - */ - SKB_DROP_REASON_DEV_HDR, /* device driver specific - * header/metadata is invalid - */ - /* the device is not ready to xmit/recv due to any of its data - * structure that is not up/ready/initialized, e.g., the IFF_UP is - * not set, or driver specific tun->tfiles[txq] is not initialized - */ - SKB_DROP_REASON_DEV_READY, - SKB_DROP_REASON_FULL_RING, /* ring buffer is full */ - SKB_DROP_REASON_NOMEM, /* error due to OOM */ - SKB_DROP_REASON_HDR_TRUNC, /* failed to trunc/extract the header - * from networking data, e.g., failed - * to pull the protocol header from - * frags via pskb_may_pull() - */ - SKB_DROP_REASON_TAP_FILTER, /* dropped by (ebpf) filter directly - * attached to tun/tap, e.g., via - * TUNSETFILTEREBPF - */ - SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented - * at tun/tap, e.g., check_filter() - */ - SKB_DROP_REASON_ICMP_CSUM, /* ICMP checksum error */ - SKB_DROP_REASON_INVALID_PROTO, /* the packet doesn't follow RFC - * 2211, such as a broadcasts - * ICMP_TIMESTAMP - */ - SKB_DROP_REASON_IP_INADDRERRORS, /* host unreachable, corresponding - * to IPSTATS_MIB_INADDRERRORS - */ - SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding - * to IPSTATS_MIB_INADDRERRORS - */ - SKB_DROP_REASON_PKT_TOO_BIG, /* packet size is too big (maybe exceed - * the MTU) - */ - SKB_DROP_REASON_MAX, -}; - -#define SKB_DR_INIT(name, reason) \ - enum skb_drop_reason name = SKB_DROP_REASON_##reason -#define SKB_DR(name) \ - SKB_DR_INIT(name, NOT_SPECIFIED) -#define SKB_DR_SET(name, reason) \ - (name = SKB_DROP_REASON_##reason) -#define SKB_DR_OR(name, reason) \ - do { \ - if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ - name == SKB_NOT_DROPPED_YET) \ - SKB_DR_SET(name, reason); \ - } while (0) - /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. @@ -2529,6 +2352,18 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) } /** + * skb_len_add - adds a number to len fields of skb + * @skb: buffer to add len to + * @delta: number of bytes to add + */ +static inline void skb_len_add(struct sk_buff *skb, int delta) +{ + skb->len += delta; + skb->data_len += delta; + skb->truesize += delta; +} + +/** * __skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise @@ -2940,8 +2775,14 @@ static inline void skb_set_network_header(struct sk_buff *skb, const int offset) skb->network_header += offset; } +static inline int skb_mac_header_was_set(const struct sk_buff *skb) +{ + return skb->mac_header != (typeof(skb->mac_header))~0U; +} + static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->head + skb->mac_header; } @@ -2952,14 +2793,10 @@ static inline int skb_mac_offset(const struct sk_buff *skb) static inline u32 skb_mac_header_len(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->network_header - skb->mac_header; } -static inline int skb_mac_header_was_set(const struct sk_buff *skb) -{ - return skb->mac_header != (typeof(skb->mac_header))~0U; -} - static inline void skb_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c5a2d6f50f25..153b6dec9b6a 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -95,6 +95,7 @@ struct sk_psock { spinlock_t link_lock; refcount_t refcnt; void (*saved_unhash)(struct sock *sk); + void (*saved_destroy)(struct sock *sk); void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); void (*saved_data_ready)(struct sock *sk); diff --git a/include/linux/socket.h b/include/linux/socket.h index 17311ad9f9af..414b8c7bb8f7 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -428,10 +428,6 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); -extern int __sys_accept4_file(struct file *file, unsigned file_flags, - struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile); extern struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index ea193414298b..d45902fb4cad 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -102,4 +102,12 @@ static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) return strncpy_from_user(dst, src.user, count); } +static inline int check_zeroed_sockptr(sockptr_t src, size_t offset, + size_t size) +{ + if (!sockptr_is_kernel(src)) + return check_zeroed_user(src.user + offset, size); + return memchr_inv(src.kernel + offset, 0, size) == NULL; +} + #endif /* _LINUX_SOCKPTR_H */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 80263f7cdb77..17b42ce89d3e 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -75,6 +75,8 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer, int proc_dou8vec_minmax(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); int proc_dointvec_ms_jiffies(struct ctl_table *, int, void *, size_t *, diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 1168302b7927..a9fbe22732c3 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -46,6 +46,36 @@ static inline unsigned int inner_tcp_hdrlen(const struct sk_buff *skb) return inner_tcp_hdr(skb)->doff * 4; } +/** + * skb_tcp_all_headers - Returns size of all headers for a TCP packet + * @skb: buffer + * + * Used in TX path, for a packet known to be a TCP one. + * + * if (skb_is_gso(skb)) { + * int hlen = skb_tcp_all_headers(skb); + * ... + */ +static inline int skb_tcp_all_headers(const struct sk_buff *skb) +{ + return skb_transport_offset(skb) + tcp_hdrlen(skb); +} + +/** + * skb_inner_tcp_all_headers - Returns size of all headers for an encap TCP packet + * @skb: buffer + * + * Used in TX path, for a packet known to be a TCP one. + * + * if (skb_is_gso(skb) && skb->encapsulation) { + * int hlen = skb_inner_tcp_all_headers(skb); + * ... + */ +static inline int skb_inner_tcp_all_headers(const struct sk_buff *skb) +{ + return skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb); +} + static inline unsigned int tcp_optlen(const struct sk_buff *skb) { return (tcp_hdr(skb)->doff - 5) * 4; diff --git a/include/linux/time64.h b/include/linux/time64.h index 81b9686a2079..2fb8232cff1d 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -20,6 +20,9 @@ struct itimerspec64 { struct timespec64 it_value; }; +/* Parameters used to convert the timespec values: */ +#define PSEC_PER_NSEC 1000L + /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) diff --git a/include/net/af_unix.h b/include/net/af_unix.h index a7ef624ed726..480fa579787e 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -16,12 +16,11 @@ void wait_for_unix_gc(void); struct sock *unix_get_socket(struct file *filp); struct sock *unix_peer_get(struct sock *sk); -#define UNIX_HASH_SIZE 256 +#define UNIX_HASH_MOD (256 - 1) +#define UNIX_HASH_SIZE (256 * 2) #define UNIX_HASH_BITS 8 extern unsigned int unix_tot_inflight; -extern spinlock_t unix_table_locks[2 * UNIX_HASH_SIZE]; -extern struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; struct unix_address { refcount_t refcnt; diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 61b49063791c..d2aea5cf1e41 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -67,6 +67,7 @@ enum { BOND_OPT_LACP_ACTIVE, BOND_OPT_MISSED_MAX, BOND_OPT_NS_TARGETS, + BOND_OPT_PRIO, BOND_OPT_LAST }; @@ -83,7 +84,10 @@ struct bond_opt_value { char *string; u64 value; u32 flags; - char extra[BOND_OPT_EXTRA_MAXLEN]; + union { + char extra[BOND_OPT_EXTRA_MAXLEN]; + struct net_device *slave_dev; + }; }; struct bonding; @@ -107,7 +111,8 @@ struct bond_option { }; int __bond_opt_set(struct bonding *bond, unsigned int option, - struct bond_opt_value *val); + struct bond_opt_value *val, + struct nlattr *bad_attr, struct netlink_ext_ack *extack); int __bond_opt_set_notify(struct bonding *bond, unsigned int option, struct bond_opt_value *val); int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); @@ -132,13 +137,16 @@ static inline void __bond_opt_init(struct bond_opt_value *optval, optval->value = value; else if (string) optval->string = string; - else if (extra_len <= BOND_OPT_EXTRA_MAXLEN) + + if (extra && extra_len <= BOND_OPT_EXTRA_MAXLEN) memcpy(optval->extra, extra, extra_len); } #define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value, NULL, 0) #define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX, NULL, 0) #define bond_opt_initextra(optval, extra, extra_len) \ __bond_opt_init(optval, NULL, ULLONG_MAX, extra, extra_len) +#define bond_opt_slave_initval(optval, slave_dev, value) \ + __bond_opt_init(optval, NULL, value, slave_dev, sizeof(struct net_device *)) void bond_option_arp_ip_targets_clear(struct bonding *bond); #if IS_ENABLED(CONFIG_IPV6) diff --git a/include/net/bonding.h b/include/net/bonding.h index cb904d356e31..6e78d657aa05 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -178,6 +178,7 @@ struct slave { u32 speed; u16 queue_id; u8 perm_hwaddr[MAX_ADDR_LEN]; + int prio; struct ad_slave_info *ad_info; struct tlb_slave_info tlb_info; #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 80f41446b1f0..3bcdd20ace66 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -374,6 +374,7 @@ struct ieee80211_sta_he_cap { * and NSS Set field" * * @only_20mhz: MCS/NSS support for 20 MHz-only STA. + * @bw: MCS/NSS support for 80, 160 and 320 MHz * @bw._80: MCS/NSS support for BW <= 80 MHz * @bw._160: MCS/NSS support for BW = 160 MHz * @bw._320: MCS/NSS support for BW = 320 MHz @@ -420,6 +421,7 @@ struct ieee80211_sta_eht_cap { * @he_cap: holds the HE capabilities * @he_6ghz_capa: HE 6 GHz capabilities, must be filled in for a * 6 GHz band channel (and 0 may be valid value). + * @eht_cap: STA's EHT capabilities * @vendor_elems: vendor element(s) to advertise * @vendor_elems.data: vendor element(s) data * @vendor_elems.len: vendor element(s) length @@ -495,7 +497,7 @@ struct ieee80211_edmg { * This structure describes most essential parameters needed * to describe 802.11ah S1G capabilities for a STA. * - * @s1g_supported: is STA an S1G STA + * @s1g: is STA an S1G STA * @cap: S1G capabilities information * @nss_mcs: Supported NSS MCS set */ @@ -1061,6 +1063,7 @@ struct survey_info { }; #define CFG80211_MAX_WEP_KEYS 4 +#define CFG80211_MAX_NUM_AKM_SUITES 10 /** * struct cfg80211_crypto_settings - Crypto settings @@ -1112,7 +1115,7 @@ struct cfg80211_crypto_settings { int n_ciphers_pairwise; u32 ciphers_pairwise[NL80211_MAX_NR_CIPHER_SUITES]; int n_akm_suites; - u32 akm_suites[NL80211_MAX_NR_AKM_SUITES]; + u32 akm_suites[CFG80211_MAX_NUM_AKM_SUITES]; bool control_port; __be16 control_port_ethertype; bool control_port_no_encrypt; @@ -1158,6 +1161,7 @@ struct cfg80211_mbssid_elems { /** * struct cfg80211_beacon_data - beacon data + * @link_id: the link ID for the AP MLD link sending this beacon * @head: head portion of beacon (before TIM IE) * or %NULL if not changed * @tail: tail portion of beacon (after TIM IE) @@ -1188,6 +1192,8 @@ struct cfg80211_mbssid_elems { * attribute is present in beacon data or not. */ struct cfg80211_beacon_data { + unsigned int link_id; + const u8 *head, *tail; const u8 *beacon_ies; const u8 *proberesp_ies; @@ -1290,6 +1296,8 @@ struct cfg80211_unsol_bcast_probe_resp { * @ht_cap: HT capabilities (or %NULL if HT isn't enabled) * @vht_cap: VHT capabilities (or %NULL if VHT isn't enabled) * @he_cap: HE capabilities (or %NULL if HE isn't enabled) + * @eht_cap: EHT capabilities (or %NULL if EHT isn't enabled) + * @eht_oper: EHT operation IE (or %NULL if EHT isn't enabled) * @ht_required: stations must support HT * @vht_required: stations must support VHT * @twt_responder: Enable Target Wait Time @@ -1326,6 +1334,8 @@ struct cfg80211_ap_settings { const struct ieee80211_vht_cap *vht_cap; const struct ieee80211_he_cap_elem *he_cap; const struct ieee80211_he_operation *he_oper; + const struct ieee80211_eht_cap_elem *eht_cap; + const struct ieee80211_eht_operation *eht_oper; bool ht_required, vht_required, he_required, sae_h2e_required; bool twt_responder; u32 flags; @@ -1370,8 +1380,8 @@ struct cfg80211_csa_settings { * Used for bss color change * * @beacon_color_change: beacon data while performing the color countdown - * @counter_offsets_beacon: offsets of the counters within the beacon (tail) - * @counter_offsets_presp: offsets of the counters within the probe response + * @counter_offset_beacon: offsets of the counters within the beacon (tail) + * @counter_offset_presp: offsets of the counters within the probe response * @beacon_next: beacon data to be used after the color change * @count: number of beacons until the color change * @color: the color used after the change @@ -1414,6 +1424,7 @@ struct iface_combination_params { * @STATION_PARAM_APPLY_UAPSD: apply new uAPSD parameters (uapsd_queues, max_sp) * @STATION_PARAM_APPLY_CAPABILITY: apply new capability * @STATION_PARAM_APPLY_PLINK_STATE: apply new plink state + * @STATION_PARAM_APPLY_STA_TXPOWER: apply tx power for STA * * Not all station parameters have in-band "no change" signalling, * for those that don't these flags will are used. @@ -2146,6 +2157,9 @@ struct bss_parameters { * @plink_timeout: If no tx activity is seen from a STA we've established * peering with for longer than this time (in seconds), then remove it * from the STA's list of peers. Default is 30 minutes. + * @dot11MeshConnectedToAuthServer: if set to true then this mesh STA + * will advertise that it is connected to a authentication server + * in the mesh formation field. * @dot11MeshConnectedToMeshGate: if set to true, advertise that this STA is * connected to a mesh gate in mesh formation info. If false, the * value in mesh formation is determined by the presence of root paths @@ -2318,12 +2332,12 @@ struct cfg80211_scan_info { /** * struct cfg80211_scan_6ghz_params - relevant for 6 GHz only * - * @short_bssid: short ssid to scan for + * @short_ssid: short ssid to scan for * @bssid: bssid to scan for * @channel_idx: idx of the channel in the channel array in the scan request * which the above info relvant to * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU - * @short_ssid_valid: short_ssid is valid and can be used + * @short_ssid_valid: @short_ssid is valid and can be used * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait * 20 TUs before starting to send probe requests. */ @@ -2715,6 +2729,12 @@ static inline const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 id) * Authentication algorithm number, i.e., starting at the Authentication * transaction sequence number field. * @auth_data_len: Length of auth_data buffer in octets + * @link_id: if >= 0, indicates authentication should be done as an MLD, + * the interface address is included as the MLD address and the + * necessary link (with the given link_id) will be created (and + * given an MLD address) by the driver + * @ap_mld_addr: AP MLD address in case of authentication request with + * an AP MLD, valid iff @link_id >= 0 */ struct cfg80211_auth_request { struct cfg80211_bss *bss; @@ -2725,6 +2745,21 @@ struct cfg80211_auth_request { u8 key_len, key_idx; const u8 *auth_data; size_t auth_data_len; + s8 link_id; + const u8 *ap_mld_addr; +}; + +/** + * struct cfg80211_assoc_link - per-link information for MLO association + * @bss: the BSS pointer, see also &struct cfg80211_assoc_request::bss; + * if this is %NULL for a link, that link is not requested + * @elems: extra elements for the per-STA profile for this link + * @elems_len: length of the elements + */ +struct cfg80211_assoc_link { + struct cfg80211_bss *bss; + const u8 *elems; + size_t elems_len; }; /** @@ -2739,6 +2774,9 @@ struct cfg80211_auth_request { * request (connect callback). * @ASSOC_REQ_DISABLE_HE: Disable HE * @ASSOC_REQ_DISABLE_EHT: Disable EHT + * @CONNECT_REQ_MLO_SUPPORT: Userspace indicates support for handling MLD links. + * Drivers shall disable MLO features for the current association if this + * flag is not set. */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), @@ -2747,6 +2785,7 @@ enum cfg80211_assoc_req_flags { CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), ASSOC_REQ_DISABLE_HE = BIT(4), ASSOC_REQ_DISABLE_EHT = BIT(5), + CONNECT_REQ_MLO_SUPPORT = BIT(6), }; /** @@ -2758,6 +2797,8 @@ enum cfg80211_assoc_req_flags { * given a reference that it must give back to cfg80211_send_rx_assoc() * or to cfg80211_assoc_timeout(). To ensure proper refcounting, new * association requests while already associating must be rejected. + * This also applies to the @links.bss parameter, which is used instead + * of this one (it is %NULL) for MLO associations. * @ie: Extra IEs to add to (Re)Association Request frame or %NULL * @ie_len: Length of ie buffer in octets * @use_mfp: Use management frame protection (IEEE 802.11w) in this association @@ -2782,6 +2823,11 @@ enum cfg80211_assoc_req_flags { * with 16 octets of STA Nonce followed by 16 octets of AP Nonce. * @s1g_capa: S1G capability override * @s1g_capa_mask: S1G capability override mask + * @links: per-link information for MLO connections + * @link_id: >= 0 for MLO connections, where links are given, and indicates + * the link on which the association request should be sent + * @ap_mld_addr: AP MLD address in case of MLO association request, + * valid iff @link_id >= 0 */ struct cfg80211_assoc_request { struct cfg80211_bss *bss; @@ -2797,6 +2843,9 @@ struct cfg80211_assoc_request { size_t fils_kek_len; const u8 *fils_nonces; struct ieee80211_s1g_cap s1g_capa, s1g_capa_mask; + struct cfg80211_assoc_link links[IEEE80211_MLD_MAX_NUM_LINKS]; + const u8 *ap_mld_addr; + s8 link_id; }; /** @@ -3279,7 +3328,7 @@ struct cfg80211_wowlan_wakeup { * @kck: key confirmation key (@kck_len bytes) * @replay_ctr: replay counter (NL80211_REPLAY_CTR_LEN bytes) * @kek_len: length of kek - * @kck_len length of kck + * @kck_len: length of kck * @akm: akm (oui, id) */ struct cfg80211_gtk_rekey_data { @@ -3641,6 +3690,7 @@ struct cfg80211_pmsr_ftm_result { * @type: type of the measurement reported, note that we only support reporting * one type at a time, but you can report multiple results separately and * they're all aggregated for userspace. + * @ftm: FTM result */ struct cfg80211_pmsr_result { u64 host_time, ap_tsf; @@ -3779,7 +3829,7 @@ struct cfg80211_update_owe_info { * for the entire device * @interface_stypes: bitmap of management frame subtypes registered * for the given interface - * @global_mcast_rx: mcast RX is needed globally for these subtypes + * @global_mcast_stypes: mcast RX is needed globally for these subtypes * @interface_mcast_stypes: mcast RX is needed on this interface * for these subtypes */ @@ -3824,6 +3874,11 @@ struct mgmt_frame_regs { * keep the struct wireless_dev's iftype updated. * This additionally holds the RTNL to be able to do netdev changes. * + * @add_intf_link: Add a new MLO link to the given interface. Note that + * the wdev->link[] data structure has been updated, so the new link + * address is available. + * @del_intf_link: Remove an MLO link from the given interface. + * * @add_key: add a key with the given parameters. @mac_addr will be %NULL * when adding a group key. * @@ -4178,6 +4233,13 @@ struct cfg80211_ops { enum nl80211_iftype type, struct vif_params *params); + int (*add_intf_link)(struct wiphy *wiphy, + struct wireless_dev *wdev, + unsigned int link_id); + void (*del_intf_link)(struct wiphy *wiphy, + struct wireless_dev *wdev, + unsigned int link_id); + int (*add_key)(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, bool pairwise, const u8 *mac_addr, struct key_params *params); @@ -4201,7 +4263,8 @@ struct cfg80211_ops { struct cfg80211_ap_settings *settings); int (*change_beacon)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_beacon_data *info); - int (*stop_ap)(struct wiphy *wiphy, struct net_device *dev); + int (*stop_ap)(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id); int (*add_station)(struct wiphy *wiphy, struct net_device *dev, @@ -4309,6 +4372,7 @@ struct cfg80211_ops { int (*set_bitrate_mask)(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id, const u8 *peer, const struct cfg80211_bitrate_mask *mask); @@ -4384,6 +4448,7 @@ struct cfg80211_ops { int (*get_channel)(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id, struct cfg80211_chan_def *chandef); int (*start_p2p_device)(struct wiphy *wiphy, @@ -4420,6 +4485,7 @@ struct cfg80211_ops { struct cfg80211_qos_map *qos_map); int (*set_ap_chanwidth)(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id, struct cfg80211_chan_def *chandef); int (*add_tx_ts)(struct wiphy *wiphy, struct net_device *dev, @@ -4545,10 +4611,14 @@ struct cfg80211_ops { * @WIPHY_FLAG_HAS_STATIC_WEP: The device supports static WEP key installation * before connection. * @WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK: The device supports bigger kek and kck keys + * @WIPHY_FLAG_SUPPORTS_MLO: This is a temporary flag gating the MLO APIs, + * in order to not have them reachable in normal drivers, until we have + * complete feature/interface combinations/etc. advertisement. No driver + * should set this flag for now. */ enum wiphy_flags { WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), - /* use hole at 1 */ + WIPHY_FLAG_SUPPORTS_MLO = BIT(1), WIPHY_FLAG_SPLIT_SCAN_6GHZ = BIT(2), WIPHY_FLAG_NETNS_OK = BIT(3), WIPHY_FLAG_PS_ON_BY_DEFAULT = BIT(4), @@ -4882,6 +4952,7 @@ struct wiphy_iftype_ext_capab { * @max_peers: maximum number of peers in a single measurement * @report_ap_tsf: can report assoc AP's TSF for radio resource measurement * @randomize_mac_addr: can randomize MAC address for measurement + * @ftm: FTM measurement data * @ftm.supported: FTM measurement is supported * @ftm.asap: ASAP-mode is supported * @ftm.non_asap: non-ASAP-mode is supported @@ -5134,6 +5205,13 @@ struct wiphy_iftype_akm_suites { * @ema_max_profile_periodicity: maximum profile periodicity supported by * the driver. Setting this field to a non-zero value indicates that the * driver supports enhanced multi-BSSID advertisements (EMA AP). + * @max_num_akm_suites: maximum number of AKM suites allowed for + * configuration through %NL80211_CMD_CONNECT, %NL80211_CMD_ASSOCIATE and + * %NL80211_CMD_START_AP. Set to NL80211_MAX_NR_AKM_SUITES if not set by + * driver. If set by driver minimum allowed value is + * NL80211_MAX_NR_AKM_SUITES in order to avoid compatibility issues with + * legacy userspace and maximum allowed value is + * CFG80211_MAX_NUM_AKM_SUITES. */ struct wiphy { struct mutex mtx; @@ -5280,6 +5358,7 @@ struct wiphy { u8 mbssid_max_interfaces; u8 ema_max_profile_periodicity; + u16 max_num_akm_suites; char priv[] __aligned(NETDEV_ALIGN); }; @@ -5505,16 +5584,9 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * @netdev: (private) Used to reference back to the netdev, may be %NULL * @identifier: (private) Identifier used in nl80211 to identify this * wireless device if it has no netdev - * @current_bss: (private) Used by the internal configuration code - * @chandef: (private) Used by the internal configuration code to track - * the user-set channel definition. - * @preset_chandef: (private) Used by the internal configuration code to - * track the channel to be used for AP later + * @u: union containing data specific to @iftype + * @connected: indicates if connected or not (STA mode) * @bssid: (private) Used by the internal configuration code - * @ssid: (private) Used by the internal configuration code - * @ssid_len: (private) Used by the internal configuration code - * @mesh_id_len: (private) Used by the internal configuration code - * @mesh_id_up_len: (private) Used by the internal configuration code * @wext: (private) Used by the internal wireless extensions compat code * @wext.ibss: (private) IBSS data part of wext handling * @wext.connect: (private) connection handling data @@ -5564,6 +5636,9 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * @pmsr_free_wk: (private) peer measurements cleanup work * @unprot_beacon_reported: (private) timestamp of last * unprotected beacon report + * @links: array of %IEEE80211_MLD_MAX_NUM_LINKS elements containing @addr + * @ap and @client for each link + * @valid_links: bitmap describing what elements of @links are valid */ struct wireless_dev { struct wiphy *wiphy; @@ -5585,8 +5660,6 @@ struct wireless_dev { u8 address[ETH_ALEN] __aligned(sizeof(u16)); /* currently used for IBSS and SME - might be rearranged later */ - u8 ssid[IEEE80211_MAX_SSID_LEN]; - u8 ssid_len, mesh_id_len, mesh_id_up_len; struct cfg80211_conn *conn; struct cfg80211_cached_keys *connect_keys; enum ieee80211_bss_type conn_bss_type; @@ -5598,20 +5671,17 @@ struct wireless_dev { struct list_head event_list; spinlock_t event_lock; - struct cfg80211_internal_bss *current_bss; /* associated / joined */ - struct cfg80211_chan_def preset_chandef; - struct cfg80211_chan_def chandef; + u8 connected:1; bool ps; int ps_timeout; - int beacon_interval; - u32 ap_unexpected_nlportid; u32 owner_nlportid; bool nl_owner_dead; + /* FIXME: need to rework radar detection for MLO */ bool cac_started; unsigned long cac_start_time; unsigned int cac_time_ms; @@ -5639,6 +5709,50 @@ struct wireless_dev { struct work_struct pmsr_free_wk; unsigned long unprot_beacon_reported; + + union { + struct { + u8 connected_addr[ETH_ALEN] __aligned(2); + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + } client; + struct { + int beacon_interval; + struct cfg80211_chan_def preset_chandef; + struct cfg80211_chan_def chandef; + u8 id[IEEE80211_MAX_SSID_LEN]; + u8 id_len, id_up_len; + } mesh; + struct { + struct cfg80211_chan_def preset_chandef; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + } ap; + struct { + struct cfg80211_internal_bss *current_bss; + struct cfg80211_chan_def chandef; + int beacon_interval; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + } ibss; + struct { + struct cfg80211_chan_def chandef; + } ocb; + } u; + + struct { + u8 addr[ETH_ALEN] __aligned(2); + union { + struct { + unsigned int beacon_interval; + struct cfg80211_chan_def chandef; + } ap; + struct { + struct cfg80211_internal_bss *current_bss; + } client; + }; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; + u16 valid_links; }; static inline const u8 *wdev_address(struct wireless_dev *wdev) @@ -5668,6 +5782,32 @@ static inline void *wdev_priv(struct wireless_dev *wdev) } /** + * wdev_chandef - return chandef pointer from wireless_dev + * @wdev: the wdev + * @link_id: the link ID for MLO + * + * Return: The chandef depending on the mode, or %NULL. + */ +struct cfg80211_chan_def *wdev_chandef(struct wireless_dev *wdev, + unsigned int link_id); + +static inline void WARN_INVALID_LINK_ID(struct wireless_dev *wdev, + unsigned int link_id) +{ + WARN_ON(link_id && !wdev->valid_links); + WARN_ON(wdev->valid_links && + !(wdev->valid_links & BIT(link_id))); +} + +#define for_each_valid_link(link_info, link_id) \ + for (link_id = 0; \ + link_id < ((link_info)->valid_links ? \ + ARRAY_SIZE((link_info)->links) : 1); \ + link_id++) \ + if (!(link_info)->valid_links || \ + ((link_info)->valid_links & BIT(link_id))) + +/** * DOC: Utility functions * * cfg80211 offers a number of utility functions that can be useful. @@ -5943,6 +6083,7 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr); * @addr: the device MAC address * @iftype: the virtual interface type * @data_offset: offset of payload after the 802.11 header + * @is_amsdu: true if the 802.11 header is A-MSDU * Return: 0 on success. Non-zero on error. */ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, @@ -6812,6 +6953,7 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, * @macaddr: the MAC address of the new candidate * @ie: information elements advertised by the peer candidate * @ie_len: length of the information elements buffer + * @sig_dbm: signal level in dBm * @gfp: allocation flags * * This function notifies cfg80211 that the mesh peer candidate has been @@ -7176,13 +7318,6 @@ struct cfg80211_fils_resp_params { * indicate that this is a failure, but without a status code. * @timeout_reason is used to report the reason for the timeout in that * case. - * @bssid: The BSSID of the AP (may be %NULL) - * @bss: Entry of bss to which STA got connected to, can be obtained through - * cfg80211_get_bss() (may be %NULL). But it is recommended to store the - * bss from the connect_request and hold a reference to it and return - * through this param to avoid a warning if the bss is expired during the - * connection, esp. for those drivers implementing connect op. - * Only one parameter among @bssid and @bss needs to be specified. * @req_ie: Association request IEs (may be %NULL) * @req_ie_len: Association request IEs length * @resp_ie: Association response IEs (may be %NULL) @@ -7194,17 +7329,41 @@ struct cfg80211_fils_resp_params { * not known. This value is used only if @status < 0 to indicate that the * failure is due to a timeout and not due to explicit rejection by the AP. * This value is ignored in other cases (@status >= 0). + * @valid_links: For MLO connection, BIT mask of the valid link ids. Otherwise + * zero. + * @ap_mld_addr: For MLO connection, MLD address of the AP. Otherwise %NULL. + * @links : For MLO connection, contains link info for the valid links indicated + * using @valid_links. For non-MLO connection, links[0] contains the + * connected AP info. + * @links.addr: For MLO connection, MAC address of the STA link. Otherwise + * %NULL. + * @links.bssid: For MLO connection, MAC address of the AP link. For non-MLO + * connection, links[0].bssid points to the BSSID of the AP (may be %NULL). + * @links.bss: For MLO connection, entry of bss to which STA link is connected. + * For non-MLO connection, links[0].bss points to entry of bss to which STA + * is connected. It can be obtained through cfg80211_get_bss() (may be + * %NULL). It is recommended to store the bss from the connect_request and + * hold a reference to it and return through this param to avoid a warning + * if the bss is expired during the connection, esp. for those drivers + * implementing connect op. Only one parameter among @bssid and @bss needs + * to be specified. */ struct cfg80211_connect_resp_params { int status; - const u8 *bssid; - struct cfg80211_bss *bss; const u8 *req_ie; size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; struct cfg80211_fils_resp_params fils; enum nl80211_timeout_reason timeout_reason; + + const u8 *ap_mld_addr; + u16 valid_links; + struct { + const u8 *addr; + const u8 *bssid; + struct cfg80211_bss *bss; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** @@ -7274,8 +7433,8 @@ cfg80211_connect_bss(struct net_device *dev, const u8 *bssid, memset(¶ms, 0, sizeof(params)); params.status = status; - params.bssid = bssid; - params.bss = bss; + params.links[0].bssid = bssid; + params.links[0].bss = bss; params.req_ie = req_ie; params.req_ie_len = req_ie_len; params.resp_ie = resp_ie; @@ -7346,24 +7505,40 @@ cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, /** * struct cfg80211_roam_info - driver initiated roaming information * - * @channel: the channel of the new AP - * @bss: entry of bss to which STA got roamed (may be %NULL if %bssid is set) - * @bssid: the BSSID of the new AP (may be %NULL if %bss is set) * @req_ie: association request IEs (maybe be %NULL) * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) * @resp_ie_len: assoc response IEs length * @fils: FILS related roaming information. + * @valid_links: For MLO roaming, BIT mask of the new valid links is set. + * Otherwise zero. + * @ap_mld_addr: For MLO roaming, MLD address of the new AP. Otherwise %NULL. + * @links : For MLO roaming, contains new link info for the valid links set in + * @valid_links. For non-MLO roaming, links[0] contains the new AP info. + * @links.addr: For MLO roaming, MAC address of the STA link. Otherwise %NULL. + * @links.bssid: For MLO roaming, MAC address of the new AP link. For non-MLO + * roaming, links[0].bssid points to the BSSID of the new AP. May be + * %NULL if %links.bss is set. + * @links.channel: the channel of the new AP. + * @links.bss: For MLO roaming, entry of new bss to which STA link got + * roamed. For non-MLO roaming, links[0].bss points to entry of bss to + * which STA got roamed (may be %NULL if %links.bssid is set) */ struct cfg80211_roam_info { - struct ieee80211_channel *channel; - struct cfg80211_bss *bss; - const u8 *bssid; const u8 *req_ie; size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; struct cfg80211_fils_resp_params fils; + + const u8 *ap_mld_addr; + u16 valid_links; + struct { + const u8 *addr; + const u8 *bssid; + struct ieee80211_channel *channel; + struct cfg80211_bss *bss; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** @@ -7882,12 +8057,14 @@ bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, * cfg80211_ch_switch_notify - update wdev channel and notify userspace * @dev: the device which switched channels * @chandef: the new channel definition + * @link_id: the link ID for MLO, must be 0 for non-MLO * * Caller must acquire wdev_lock, therefore must only be called from sleepable * driver context! */ void cfg80211_ch_switch_notify(struct net_device *dev, - struct cfg80211_chan_def *chandef); + struct cfg80211_chan_def *chandef, + unsigned int link_id); /* * cfg80211_ch_switch_started_notify - notify channel switch start diff --git a/include/net/devlink.h b/include/net/devlink.h index 2a2a2a0c93f7..b1b5c19a8316 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1521,15 +1521,6 @@ void devl_unlock(struct devlink *devlink); void devl_assert_locked(struct devlink *devlink); bool devl_lock_is_held(struct devlink *devlink); -int devl_port_register(struct devlink *devlink, - struct devlink_port *devlink_port, - unsigned int port_index); -void devl_port_unregister(struct devlink_port *devlink_port); - -int devl_rate_leaf_create(struct devlink_port *port, void *priv); -void devl_rate_leaf_destroy(struct devlink_port *devlink_port); -void devl_rate_nodes_destroy(struct devlink *devlink); - struct ib_device; struct net *devlink_net(const struct devlink *devlink); @@ -1551,9 +1542,13 @@ void devlink_set_features(struct devlink *devlink, u64 features); void devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); void devlink_free(struct devlink *devlink); +int devl_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index); int devlink_port_register(struct devlink *devlink, struct devlink_port *devlink_port, unsigned int port_index); +void devl_port_unregister(struct devlink_port *devlink_port); void devlink_port_unregister(struct devlink_port *devlink_port); void devlink_port_type_eth_set(struct devlink_port *devlink_port, struct net_device *netdev); @@ -1569,9 +1564,9 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u32 sf, bool external); -int devlink_rate_leaf_create(struct devlink_port *port, void *priv); -void devlink_rate_leaf_destroy(struct devlink_port *devlink_port); -void devlink_rate_nodes_destroy(struct devlink *devlink); +int devl_rate_leaf_create(struct devlink_port *port, void *priv); +void devl_rate_leaf_destroy(struct devlink_port *devlink_port); +void devl_rate_nodes_destroy(struct devlink *devlink); void devlink_port_linecard_set(struct devlink_port *devlink_port, struct devlink_linecard *linecard); struct devlink_linecard * diff --git a/include/net/dropreason.h b/include/net/dropreason.h new file mode 100644 index 000000000000..fae9b40e54fa --- /dev/null +++ b/include/net/dropreason.h @@ -0,0 +1,256 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _LINUX_DROPREASON_H +#define _LINUX_DROPREASON_H + +/** + * enum skb_drop_reason - the reasons of skb drops + * + * The reason of skb drop, which is used in kfree_skb_reason(). + */ +enum skb_drop_reason { + /** + * @SKB_NOT_DROPPED_YET: skb is not dropped yet (used for no-drop case) + */ + SKB_NOT_DROPPED_YET = 0, + /** @SKB_DROP_REASON_NOT_SPECIFIED: drop reason is not specified */ + SKB_DROP_REASON_NOT_SPECIFIED, + /** @SKB_DROP_REASON_NO_SOCKET: socket not found */ + SKB_DROP_REASON_NO_SOCKET, + /** @SKB_DROP_REASON_PKT_TOO_SMALL: packet size is too small */ + SKB_DROP_REASON_PKT_TOO_SMALL, + /** @SKB_DROP_REASON_TCP_CSUM: TCP checksum error */ + SKB_DROP_REASON_TCP_CSUM, + /** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */ + SKB_DROP_REASON_SOCKET_FILTER, + /** @SKB_DROP_REASON_UDP_CSUM: UDP checksum error */ + SKB_DROP_REASON_UDP_CSUM, + /** @SKB_DROP_REASON_NETFILTER_DROP: dropped by netfilter */ + SKB_DROP_REASON_NETFILTER_DROP, + /** + * @SKB_DROP_REASON_OTHERHOST: packet don't belong to current host + * (interface is in promisc mode) + */ + SKB_DROP_REASON_OTHERHOST, + /** @SKB_DROP_REASON_IP_CSUM: IP checksum error */ + SKB_DROP_REASON_IP_CSUM, + /** + * @SKB_DROP_REASON_IP_INHDR: there is something wrong with IP header (see + * IPSTATS_MIB_INHDRERRORS) + */ + SKB_DROP_REASON_IP_INHDR, + /** + * @SKB_DROP_REASON_IP_RPFILTER: IP rpfilter validate failed. see the + * document for rp_filter in ip-sysctl.rst for more information + */ + SKB_DROP_REASON_IP_RPFILTER, + /** + * @SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST: destination address of L2 is + * multicast, but L3 is unicast. + */ + SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, + /** @SKB_DROP_REASON_XFRM_POLICY: xfrm policy check failed */ + SKB_DROP_REASON_XFRM_POLICY, + /** @SKB_DROP_REASON_IP_NOPROTO: no support for IP protocol */ + SKB_DROP_REASON_IP_NOPROTO, + /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ + SKB_DROP_REASON_SOCKET_RCVBUFF, + /** + * @SKB_DROP_REASON_PROTO_MEM: proto memory limition, such as udp packet + * drop out of udp_memory_allocated. + */ + SKB_DROP_REASON_PROTO_MEM, + /** + * @SKB_DROP_REASON_TCP_MD5NOTFOUND: no MD5 hash and one expected, + * corresponding to LINUX_MIB_TCPMD5NOTFOUND + */ + SKB_DROP_REASON_TCP_MD5NOTFOUND, + /** + * @SKB_DROP_REASON_TCP_MD5UNEXPECTED: MD5 hash and we're not expecting + * one, corresponding to LINUX_MIB_TCPMD5UNEXPECTED + */ + SKB_DROP_REASON_TCP_MD5UNEXPECTED, + /** + * @SKB_DROP_REASON_TCP_MD5FAILURE: MD5 hash and its wrong, corresponding + * to LINUX_MIB_TCPMD5FAILURE + */ + SKB_DROP_REASON_TCP_MD5FAILURE, + /** + * @SKB_DROP_REASON_SOCKET_BACKLOG: failed to add skb to socket backlog ( + * see LINUX_MIB_TCPBACKLOGDROP) + */ + SKB_DROP_REASON_SOCKET_BACKLOG, + /** @SKB_DROP_REASON_TCP_FLAGS: TCP flags invalid */ + SKB_DROP_REASON_TCP_FLAGS, + /** + * @SKB_DROP_REASON_TCP_ZEROWINDOW: TCP receive window size is zero, + * see LINUX_MIB_TCPZEROWINDOWDROP + */ + SKB_DROP_REASON_TCP_ZEROWINDOW, + /** + * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already + * received before (spurious retrans may happened), see + * LINUX_MIB_DELAYEDACKLOST + */ + SKB_DROP_REASON_TCP_OLD_DATA, + /** + * @SKB_DROP_REASON_TCP_OVERWINDOW: the TCP data is out of window, + * the seq of the first byte exceed the right edges of receive + * window + */ + SKB_DROP_REASON_TCP_OVERWINDOW, + /** + * @SKB_DROP_REASON_TCP_OFOMERGE: the data of skb is already in the ofo + * queue, corresponding to LINUX_MIB_TCPOFOMERGE + */ + SKB_DROP_REASON_TCP_OFOMERGE, + /** + * @SKB_DROP_REASON_TCP_RFC7323_PAWS: PAWS check, corresponding to + * LINUX_MIB_PAWSESTABREJECTED + */ + SKB_DROP_REASON_TCP_RFC7323_PAWS, + /** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */ + SKB_DROP_REASON_TCP_INVALID_SEQUENCE, + /** @SKB_DROP_REASON_TCP_RESET: Invalid RST packet */ + SKB_DROP_REASON_TCP_RESET, + /** + * @SKB_DROP_REASON_TCP_INVALID_SYN: Incoming packet has unexpected + * SYN flag + */ + SKB_DROP_REASON_TCP_INVALID_SYN, + /** @SKB_DROP_REASON_TCP_CLOSE: TCP socket in CLOSE state */ + SKB_DROP_REASON_TCP_CLOSE, + /** @SKB_DROP_REASON_TCP_FASTOPEN: dropped by FASTOPEN request socket */ + SKB_DROP_REASON_TCP_FASTOPEN, + /** @SKB_DROP_REASON_TCP_OLD_ACK: TCP ACK is old, but in window */ + SKB_DROP_REASON_TCP_OLD_ACK, + /** @SKB_DROP_REASON_TCP_TOO_OLD_ACK: TCP ACK is too old */ + SKB_DROP_REASON_TCP_TOO_OLD_ACK, + /** + * @SKB_DROP_REASON_TCP_ACK_UNSENT_DATA: TCP ACK for data we haven't + * sent yet + */ + SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, + /** @SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE: pruned from TCP OFO queue */ + SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, + /** @SKB_DROP_REASON_TCP_OFO_DROP: data already in receive queue */ + SKB_DROP_REASON_TCP_OFO_DROP, + /** @SKB_DROP_REASON_IP_OUTNOROUTES: route lookup failed */ + SKB_DROP_REASON_IP_OUTNOROUTES, + /** + * @SKB_DROP_REASON_BPF_CGROUP_EGRESS: dropped by BPF_PROG_TYPE_CGROUP_SKB + * eBPF program + */ + SKB_DROP_REASON_BPF_CGROUP_EGRESS, + /** @SKB_DROP_REASON_IPV6DISABLED: IPv6 is disabled on the device */ + SKB_DROP_REASON_IPV6DISABLED, + /** @SKB_DROP_REASON_NEIGH_CREATEFAIL: failed to create neigh entry */ + SKB_DROP_REASON_NEIGH_CREATEFAIL, + /** @SKB_DROP_REASON_NEIGH_FAILED: neigh entry in failed state */ + SKB_DROP_REASON_NEIGH_FAILED, + /** @SKB_DROP_REASON_NEIGH_QUEUEFULL: arp_queue for neigh entry is full */ + SKB_DROP_REASON_NEIGH_QUEUEFULL, + /** @SKB_DROP_REASON_NEIGH_DEAD: neigh entry is dead */ + SKB_DROP_REASON_NEIGH_DEAD, + /** @SKB_DROP_REASON_TC_EGRESS: dropped in TC egress HOOK */ + SKB_DROP_REASON_TC_EGRESS, + /** + * @SKB_DROP_REASON_QDISC_DROP: dropped by qdisc when packet outputting ( + * failed to enqueue to current qdisc) + */ + SKB_DROP_REASON_QDISC_DROP, + /** + * @SKB_DROP_REASON_CPU_BACKLOG: failed to enqueue the skb to the per CPU + * backlog queue. This can be caused by backlog queue full (see + * netdev_max_backlog in net.rst) or RPS flow limit + */ + SKB_DROP_REASON_CPU_BACKLOG, + /** @SKB_DROP_REASON_XDP: dropped by XDP in input path */ + SKB_DROP_REASON_XDP, + /** @SKB_DROP_REASON_TC_INGRESS: dropped in TC ingress HOOK */ + SKB_DROP_REASON_TC_INGRESS, + /** @SKB_DROP_REASON_UNHANDLED_PROTO: protocol not implemented or not supported */ + SKB_DROP_REASON_UNHANDLED_PROTO, + /** @SKB_DROP_REASON_SKB_CSUM: sk_buff checksum computation error */ + SKB_DROP_REASON_SKB_CSUM, + /** @SKB_DROP_REASON_SKB_GSO_SEG: gso segmentation error */ + SKB_DROP_REASON_SKB_GSO_SEG, + /** + * @SKB_DROP_REASON_SKB_UCOPY_FAULT: failed to copy data from user space, + * e.g., via zerocopy_sg_from_iter() or skb_orphan_frags_rx() + */ + SKB_DROP_REASON_SKB_UCOPY_FAULT, + /** @SKB_DROP_REASON_DEV_HDR: device driver specific header/metadata is invalid */ + SKB_DROP_REASON_DEV_HDR, + /** + * @SKB_DROP_REASON_DEV_READY: the device is not ready to xmit/recv due to + * any of its data structure that is not up/ready/initialized, + * e.g., the IFF_UP is not set, or driver specific tun->tfiles[txq] + * is not initialized + */ + SKB_DROP_REASON_DEV_READY, + /** @SKB_DROP_REASON_FULL_RING: ring buffer is full */ + SKB_DROP_REASON_FULL_RING, + /** @SKB_DROP_REASON_NOMEM: error due to OOM */ + SKB_DROP_REASON_NOMEM, + /** + * @SKB_DROP_REASON_HDR_TRUNC: failed to trunc/extract the header from + * networking data, e.g., failed to pull the protocol header from + * frags via pskb_may_pull() + */ + SKB_DROP_REASON_HDR_TRUNC, + /** + * @SKB_DROP_REASON_TAP_FILTER: dropped by (ebpf) filter directly attached + * to tun/tap, e.g., via TUNSETFILTEREBPF + */ + SKB_DROP_REASON_TAP_FILTER, + /** + * @SKB_DROP_REASON_TAP_TXFILTER: dropped by tx filter implemented at + * tun/tap, e.g., check_filter() + */ + SKB_DROP_REASON_TAP_TXFILTER, + /** @SKB_DROP_REASON_ICMP_CSUM: ICMP checksum error */ + SKB_DROP_REASON_ICMP_CSUM, + /** + * @SKB_DROP_REASON_INVALID_PROTO: the packet doesn't follow RFC 2211, + * such as a broadcasts ICMP_TIMESTAMP + */ + SKB_DROP_REASON_INVALID_PROTO, + /** + * @SKB_DROP_REASON_IP_INADDRERRORS: host unreachable, corresponding to + * IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INADDRERRORS, + /** + * @SKB_DROP_REASON_IP_INNOROUTES: network unreachable, corresponding to + * IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INNOROUTES, + /** + * @SKB_DROP_REASON_PKT_TOO_BIG: packet size is too big (maybe exceed the + * MTU) + */ + SKB_DROP_REASON_PKT_TOO_BIG, + /** + * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be + * used as a real 'reason' + */ + SKB_DROP_REASON_MAX, +}; + +#define SKB_DR_INIT(name, reason) \ + enum skb_drop_reason name = SKB_DROP_REASON_##reason +#define SKB_DR(name) \ + SKB_DR_INIT(name, NOT_SPECIFIED) +#define SKB_DR_SET(name, reason) \ + (name = SKB_DROP_REASON_##reason) +#define SKB_DR_OR(name, reason) \ + do { \ + if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ + name == SKB_NOT_DROPPED_YET) \ + SKB_DR_SET(name, reason); \ + } while (0) + +extern const char * const drop_reasons[]; + +#endif diff --git a/include/net/dsa.h b/include/net/dsa.h index 14f07275852b..b902b31bebce 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -53,6 +53,8 @@ struct phylink_link_state; #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 +#define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 +#define DSA_TAG_PROTO_LAN937X_VALUE 27 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -81,6 +83,8 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, + DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, + DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, }; struct dsa_switch; @@ -888,8 +892,13 @@ struct dsa_switch_ops { struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); + void (*get_rmon_stats)(struct dsa_switch *ds, int port, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); + void (*get_pause_stats)(struct dsa_switch *ds, int port, + struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index a4c6057c7097..0f9544a9bb9e 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -179,6 +179,22 @@ struct flow_dissector_key_ports { }; /** + * struct flow_dissector_key_ports_range + * @tp: port number from packet + * @tp_min: min port number in range + * @tp_max: max port number in range + */ +struct flow_dissector_key_ports_range { + union { + struct flow_dissector_key_ports tp; + struct { + struct flow_dissector_key_ports tp_min; + struct flow_dissector_key_ports tp_max; + }; + }; +}; + +/** * flow_dissector_key_icmp: * type: ICMP type * code: ICMP code diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 7ac313858037..a8d8512b7059 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -48,6 +48,10 @@ struct flow_match_ports { struct flow_dissector_key_ports *key, *mask; }; +struct flow_match_ports_range { + struct flow_dissector_key_ports_range *key, *mask; +}; + struct flow_match_icmp { struct flow_dissector_key_icmp *key, *mask; }; @@ -94,6 +98,8 @@ void flow_rule_match_ip(const struct flow_rule *rule, struct flow_match_ip *out); void flow_rule_match_ports(const struct flow_rule *rule, struct flow_match_ports *out); +void flow_rule_match_ports_range(const struct flow_rule *rule, + struct flow_match_ports_range *out); void flow_rule_match_tcp(const struct flow_rule *rule, struct flow_match_tcp *out); void flow_rule_match_icmp(const struct flow_rule *rule, diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index a5f67a2c0c73..524b510f1c68 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -358,8 +358,7 @@ static int fq_init(struct fq *fq, int flows_cnt) if (!fq->flows) return -ENOMEM; - fq->flows_bitmap = kcalloc(BITS_TO_LONGS(fq->flows_cnt), sizeof(long), - GFP_KERNEL); + fq->flows_bitmap = bitmap_zalloc(fq->flows_cnt, GFP_KERNEL); if (!fq->flows_bitmap) { kvfree(fq->flows); fq->flows = NULL; @@ -383,7 +382,7 @@ static void fq_reset(struct fq *fq, kvfree(fq->flows); fq->flows = NULL; - kfree(fq->flows_bitmap); + bitmap_free(fq->flows_bitmap); fq->flows_bitmap = NULL; } diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index c24fa934221d..70cbc4a72669 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -456,8 +456,8 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += pkt_len; - tstats->tx_packets++; + u64_stats_add(&tstats->tx_bytes, pkt_len); + u64_stats_inc(&tstats->tx_packets); u64_stats_update_end(&tstats->syncp); put_cpu_ptr(tstats); } else { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 47642b020706..1c005a30313f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -261,11 +261,13 @@ enum ieee80211_chanctx_switch_mode { * done. * * @vif: the vif that should be switched from old_ctx to new_ctx + * @link_id: the link ID that's switching * @old_ctx: the old context to which the vif was assigned * @new_ctx: the new context to which the vif must be assigned */ struct ieee80211_vif_chanctx_switch { struct ieee80211_vif *vif; + unsigned int link_id; struct ieee80211_chanctx_conf *old_ctx; struct ieee80211_chanctx_conf *new_ctx; }; @@ -273,8 +275,8 @@ struct ieee80211_vif_chanctx_switch { /** * enum ieee80211_bss_change - BSS change notification flags * - * These flags are used with the bss_info_changed() callback - * to indicate which BSS parameter changed. + * These flags are used with the bss_info_changed(), link_info_changed() + * and vif_cfg_changed() callbacks to indicate which parameter(s) changed. * * @BSS_CHANGED_ASSOC: association status changed (associated/disassociated), * also implies a change in the AID. @@ -513,6 +515,7 @@ struct ieee80211_fils_discovery { * This structure keeps information about a BSS (and an association * to that BSS) that can change during the lifetime of the BSS. * + * @addr: (link) address used locally * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE * @uora_exists: is the UORA element advertised by AP * @ack_enabled: indicates support to receive a multi-TID that solicits either @@ -526,11 +529,6 @@ struct ieee80211_fils_discovery { * mode only, set if the AP advertises TWT responder role) * @twt_protected: does this BSS support protected TWT frames * @twt_broadcast: does this BSS support broadcast TWT - * @assoc: association status - * @ibss_joined: indicates whether this station is part of an IBSS - * or not - * @ibss_creator: indicates if a new IBSS network is being created - * @aid: association ID number, valid only when @assoc is true * @use_cts_prot: use CTS protection * @use_short_preamble: use 802.11b short preamble * @use_short_slot: use short slot time (only relevant for ERP) @@ -551,6 +549,8 @@ struct ieee80211_fils_discovery { * IMPORTANT: These three sync_* parameters would possibly be out of sync * by the time the driver will use them. The synchronized view is currently * guaranteed only in certain callbacks. + * Note also that this is not used with MLD associations, mac80211 doesn't + * know how to track beacons for all of the links for this. * @beacon_int: beacon interval * @assoc_capability: capabilities taken from assoc resp * @basic_rates: bitmap of basic rates, each bit stands for an @@ -576,21 +576,9 @@ struct ieee80211_fils_discovery { * threshold event and can't be enabled simultaneously with it. * @cqm_rssi_high: Connection quality monitor RSSI upper threshold. * @cqm_rssi_hyst: Connection quality monitor RSSI hysteresis - * @arp_addr_list: List of IPv4 addresses for hardware ARP filtering. The - * may filter ARP queries targeted for other addresses than listed here. - * The driver must allow ARP queries targeted for all address listed here - * to pass through. An empty list implies no ARP queries need to pass. - * @arp_addr_cnt: Number of addresses currently on the list. Note that this - * may be larger than %IEEE80211_BSS_ARP_ADDR_LIST_LEN (the arp_addr_list - * array size), it's up to the driver what to do in that case. * @qos: This is a QoS-enabled BSS. - * @idle: This interface is idle. There's also a global idle flag in the - * hardware config which may be more appropriate depending on what - * your driver/device needs to do. * @ps: power-save mode (STA only). This flag is NOT affected by * offchannel/dynamic_ps operations. - * @ssid: The SSID of the current vif. Valid in AP and IBSS mode. - * @ssid_len: Length of SSID given in @ssid. * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode. * @txpower: TX power in dBm. INT_MIN means not configured. * @txpower_type: TX power adjustment used to control per packet Transmit @@ -628,7 +616,6 @@ struct ieee80211_fils_discovery { * @fils_discovery: FILS discovery configuration * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response * interval. - * @s1g: BSS is S1G BSS (affects Association Request format). * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed * to driver when rate control is offloaded to firmware. * @power_type: power type of BSS for 6 GHz @@ -636,9 +623,23 @@ struct ieee80211_fils_discovery { * @tx_pwr_env_num: number of @tx_pwr_env. * @pwr_reduction: power constraint of BSS. * @eht_support: does this BSS support EHT + * @csa_active: marks whether a channel switch is going on. Internally it is + * write-protected by sdata_lock and local->mtx so holding either is fine + * for read access. + * @mu_mimo_owner: indicates interface owns MU-MIMO capability + * @chanctx_conf: The channel context this interface is assigned to, or %NULL + * when it is not assigned. This pointer is RCU-protected due to the TX + * path needing to access it; even though the netdev carrier will always + * be off when it is %NULL there can still be races and packets could be + * processed after it switches back to %NULL. + * @color_change_active: marks whether a color change is ongoing. Internally it is + * write-protected by sdata_lock and local->mtx so holding either is fine + * for read access. + * @color_change_color: the bss color that will be used after the change. */ struct ieee80211_bss_conf { const u8 *bssid; + u8 addr[ETH_ALEN] __aligned(2); u8 htc_trig_based_pkt_ext; bool uora_exists; u8 uora_ocw_range; @@ -648,10 +649,6 @@ struct ieee80211_bss_conf { bool twt_responder; bool twt_protected; bool twt_broadcast; - /* association related data */ - bool assoc, ibss_joined; - bool ibss_creator; - u16 aid; /* erp related data */ bool use_cts_prot; bool use_short_preamble; @@ -673,13 +670,8 @@ struct ieee80211_bss_conf { s32 cqm_rssi_high; struct cfg80211_chan_def chandef; struct ieee80211_mu_group_data mu_group; - __be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; - int arp_addr_cnt; bool qos; - bool idle; bool ps; - u8 ssid[IEEE80211_MAX_SSID_LEN]; - size_t ssid_len; bool hidden_ssid; int txpower; enum nl80211_tx_power_setting txpower_type; @@ -704,13 +696,19 @@ struct ieee80211_bss_conf { struct cfg80211_he_bss_color he_bss_color; struct ieee80211_fils_discovery fils_discovery; u32 unsol_bcast_probe_resp_interval; - bool s1g; struct cfg80211_bitrate_mask beacon_tx_rate; enum ieee80211_ap_reg_power power_type; struct ieee80211_tx_pwr_env tx_pwr_env[IEEE80211_TPE_MAX_IE_COUNT]; u8 tx_pwr_env_num; u8 pwr_reduction; bool eht_support; + + bool csa_active; + bool mu_mimo_owner; + struct ieee80211_chanctx_conf __rcu *chanctx_conf; + + bool color_change_active; + u8 color_change_color; }; /** @@ -869,6 +867,10 @@ enum mac80211_tx_info_flags { * @IEEE80211_TX_CTRL_DONT_REORDER: This frame should not be reordered * relative to other frames that have this flag set, independent * of their QoS TID or other priority field values. + * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this + * frame should be transmitted on the specific link. This really is + * only relevant for frames that do not have data present, and is + * also not used for 802.3 format frames. * * These flags are used in tx_info->control.flags. */ @@ -882,8 +884,11 @@ enum mac80211_tx_control_flags { IEEE80211_TX_INTCFL_NEED_TXPROCESSING = BIT(6), IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), + IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000, }; +#define IEEE80211_LINK_UNSPECIFIED 0xf + /** * enum mac80211_tx_status_flags - flags to describe transmit status * @@ -1031,7 +1036,9 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * (3) TX status information - driver tells mac80211 what happened * * @flags: transmit info flags, defined above - * @band: the band to transmit on (use for checking for races) + * @band: the band to transmit on (use e.g. for checking for races), + * not valid if the interface is an MLD since we won't know which + * link the frame will be transmitted on * @hw_queue: HW queue to put the frame on, skb_get_queue_mapping() gives the AC * @ack_frame_id: internal frame ID for TX status, used internally * @tx_time_est: TX time estimate in units of 4us, used internally @@ -1702,21 +1709,55 @@ enum ieee80211_offload_flags { }; /** + * struct ieee80211_vif_cfg - interface configuration + * @assoc: association status + * @ibss_joined: indicates whether this station is part of an IBSS or not + * @ibss_creator: indicates if a new IBSS network is being created + * @aid: association ID number, valid only when @assoc is true + * @arp_addr_list: List of IPv4 addresses for hardware ARP filtering. The + * may filter ARP queries targeted for other addresses than listed here. + * The driver must allow ARP queries targeted for all address listed here + * to pass through. An empty list implies no ARP queries need to pass. + * @arp_addr_cnt: Number of addresses currently on the list. Note that this + * may be larger than %IEEE80211_BSS_ARP_ADDR_LIST_LEN (the arp_addr_list + * array size), it's up to the driver what to do in that case. + * @ssid: The SSID of the current vif. Valid in AP and IBSS mode. + * @ssid_len: Length of SSID given in @ssid. + * @s1g: BSS is S1G BSS (affects Association Request format). + * @idle: This interface is idle. There's also a global idle flag in the + * hardware config which may be more appropriate depending on what + * your driver/device needs to do. + */ +struct ieee80211_vif_cfg { + /* association related data */ + bool assoc, ibss_joined; + bool ibss_creator; + u16 aid; + + __be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; + int arp_addr_cnt; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + size_t ssid_len; + bool s1g; + bool idle; +}; + +/** * struct ieee80211_vif - per-interface data * * Data in this structure is continually present for driver * use during the life of a virtual interface. * * @type: type of this virtual interface + * @cfg: vif configuration, see &struct ieee80211_vif_cfg * @bss_conf: BSS configuration for this interface, either our own * or the BSS we're associated to + * @link_conf: in case of MLD, the per-link BSS configuration, + * indexed by link ID + * @valid_links: bitmap of valid links, or 0 for non-MLO. * @addr: address of this interface * @p2p: indicates whether this AP or STA interface is a p2p * interface, i.e. a GO or p2p-sta respectively - * @csa_active: marks whether a channel switch is going on. Internally it is - * write-protected by sdata_lock and local->mtx so holding either is fine - * for read access. - * @mu_mimo_owner: indicates interface owns MU-MIMO capability * @driver_flags: flags/capabilities the driver has for this interface, * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed @@ -1728,11 +1769,6 @@ enum ieee80211_offload_flags { * 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 - * when it is not assigned. This pointer is RCU-protected due to the TX - * path needing to access it; even though the netdev carrier will always - * be off when it is %NULL there can still be races and packets could be - * processed after it switches back to %NULL. * @debugfs_dir: debugfs dentry, can be used by drivers to create own per * interface debug files. Note that it will be NULL for the virtual * monitor interface (if that is requested.) @@ -1747,27 +1783,22 @@ enum ieee80211_offload_flags { * protected by fq->lock. * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see * &enum ieee80211_offload_flags. - * @color_change_active: marks whether a color change is ongoing. Internally it is - * write-protected by sdata_lock and local->mtx so holding either is fine - * for read access. - * @color_change_color: the bss color that will be used after the change. * @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled. */ struct ieee80211_vif { enum nl80211_iftype type; + struct ieee80211_vif_cfg cfg; struct ieee80211_bss_conf bss_conf; + struct ieee80211_bss_conf *link_conf[IEEE80211_MLD_MAX_NUM_LINKS]; + u16 valid_links; u8 addr[ETH_ALEN] __aligned(2); bool p2p; - bool csa_active; - bool mu_mimo_owner; u8 cab_queue; u8 hw_queue[IEEE80211_NUM_ACS]; struct ieee80211_txq *txq; - struct ieee80211_chanctx_conf __rcu *chanctx_conf; - u32 driver_flags; u32 offload_flags; @@ -1780,9 +1811,6 @@ struct ieee80211_vif { bool txqs_stopped[IEEE80211_NUM_ACS]; - bool color_change_active; - u8 color_change_color; - struct ieee80211_vif *mbssid_tx_vif; /* must be last */ @@ -1959,36 +1987,6 @@ struct ieee80211_key_seq { }; /** - * struct ieee80211_cipher_scheme - cipher scheme - * - * This structure contains a cipher scheme information defining - * the secure packet crypto handling. - * - * @cipher: a cipher suite selector - * @iftype: a cipher iftype bit mask indicating an allowed cipher usage - * @hdr_len: a length of a security header used the cipher - * @pn_len: a length of a packet number in the security header - * @pn_off: an offset of pn from the beginning of the security header - * @key_idx_off: an offset of key index byte in the security header - * @key_idx_mask: a bit mask of key_idx bits - * @key_idx_shift: a bit shift needed to get key_idx - * key_idx value calculation: - * (sec_header_base[key_idx_off] & key_idx_mask) >> key_idx_shift - * @mic_len: a mic length in bytes - */ -struct ieee80211_cipher_scheme { - u32 cipher; - u16 iftype; - u8 hdr_len; - u8 pn_len; - u8 pn_off; - u8 key_idx_off; - u8 key_idx_mask; - u8 key_idx_shift; - u8 mic_len; -}; - -/** * enum set_key_cmd - key command * * Used with the set_key() callback in &struct ieee80211_ops, this @@ -2076,8 +2074,6 @@ struct ieee80211_sta_txpwr { enum nl80211_tx_power_setting type; }; -#define MAX_STA_LINKS 15 - /** * struct ieee80211_link_sta - station Link specific info * All link specific info for a STA link for a non MLD STA(single) @@ -2154,7 +2150,6 @@ struct ieee80211_link_sta { * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID * @txq: per-TID data TX queues (if driver uses the TXQ abstraction); note that * the last entry (%IEEE80211_NUM_TIDS) is used for non-data frames - * @multi_link_sta: Identifies if this sta is a MLD STA * @deflink: This holds the default link STA information, for non MLO STA all link * specific STA information is accessed through @deflink or through * link[0] which points to address of @deflink. For MLO Link STA @@ -2166,6 +2161,7 @@ struct ieee80211_link_sta { * @deflink address and remaining would be allocated and the address * would be assigned to link[link_id] where link_id is the id assigned * by the AP. + * @valid_links: bitmap of valid links, or 0 for non-MLO */ struct ieee80211_sta { u8 addr[ETH_ALEN]; @@ -2203,9 +2199,9 @@ struct ieee80211_sta { struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; - bool multi_link_sta; + u16 valid_links; struct ieee80211_link_sta deflink; - struct ieee80211_link_sta *link[MAX_STA_LINKS]; + struct ieee80211_link_sta __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); @@ -2664,9 +2660,6 @@ enum ieee80211_hw_flags { * deliver to a WMM STA during any Service Period triggered by the WMM STA. * Use IEEE80211_WMM_IE_STA_QOSINFO_SP_* for correct values. * - * @n_cipher_schemes: a size of an array of cipher schemes definitions. - * @cipher_schemes: a pointer to an array of cipher scheme definitions - * supported by HW. * @max_nan_de_entries: maximum number of NAN DE functions supported by the * device. * @@ -2716,8 +2709,6 @@ struct ieee80211_hw { netdev_features_t netdev_features; u8 uapsd_queues; u8 uapsd_max_sp_len; - u8 n_cipher_schemes; - const struct ieee80211_cipher_scheme *cipher_schemes; u8 max_nan_de_entries; u8 tx_sk_pacing_shift; u8 weight_multiplier; @@ -3549,6 +3540,22 @@ struct ieee80211_prep_tx_info { * for association indication. The @changed parameter indicates which * of the bss parameters has changed when a call is made. The callback * can sleep. + * Note: this callback is called if @vif_cfg_changed or @link_info_changed + * are not implemented. + * + * @vif_cfg_changed: Handler for configuration requests related to interface + * (MLD) parameters from &struct ieee80211_vif_cfg that vary during the + * lifetime of the interface (e.g. assoc status, IP addresses, etc.) + * The @changed parameter indicates which value changed. + * The callback can sleep. + * + * @link_info_changed: Handler for configuration requests related to link + * parameters from &struct ieee80211_bss_conf that are related to an + * individual link. e.g. legacy/HT/VHT/... rate information. + * The @changed parameter indicates which value changed, and the @link_id + * parameter indicates the link ID. Note that the @link_id will be 0 for + * non-MLO connections. + * The callback can sleep. * * @prepare_multicast: Prepare for multicast filter configuration. * This callback is optional, and its return value is passed @@ -4034,6 +4041,18 @@ struct ieee80211_prep_tx_info { * disable background CAC/radar detection. * @net_fill_forward_path: Called from .ndo_fill_forward_path in order to * resolve a path for hardware flow offloading + * @change_vif_links: Change the valid links on an interface, note that while + * removing the old link information is still valid (link_conf pointer), + * but may immediately disappear after the function returns. The old or + * new links bitmaps may be 0 if going from/to a non-MLO situation. + * The @old array contains pointers to the old bss_conf structures + * that were already removed, in case they're needed. + * This callback can sleep. + * @change_sta_links: Change the valid links of a station, similar to + * @change_vif_links. This callback can sleep. + * Note that a sta can also be inserted or removed with valid links, + * i.e. passed to @sta_add/@sta_state with sta->valid_links not zero. + * In fact, cannot change from having valid_links and not having them. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4057,10 +4076,18 @@ struct ieee80211_ops { void (*bss_info_changed)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *info, - u32 changed); + u64 changed); + void (*vif_cfg_changed)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u64 changed); + void (*link_info_changed)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + unsigned int link_id, u64 changed); - int (*start_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); - void (*stop_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); + int (*start_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id); + void (*stop_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id); u64 (*prepare_multicast)(struct ieee80211_hw *hw, struct netdev_hw_addr_list *mc_list); @@ -4262,9 +4289,11 @@ struct ieee80211_ops { u32 changed); int (*assign_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id, struct ieee80211_chanctx_conf *ctx); void (*unassign_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id, struct ieee80211_chanctx_conf *ctx); int (*switch_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif_chanctx_switch *vifs, @@ -4369,6 +4398,14 @@ struct ieee80211_ops { struct ieee80211_sta *sta, struct net_device_path_ctx *ctx, struct net_device_path *path); + int (*change_vif_links)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u16 old_links, u16 new_links, + struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS]); + int (*change_sta_links)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + u16 old_links, u16 new_links); }; /** @@ -5032,6 +5069,7 @@ struct ieee80211_mutable_offsets { * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @offs: &struct ieee80211_mutable_offsets pointer to struct that will * receive the offsets that may be updated by the driver. + * @link_id: the link id to which the beacon belongs (or 0 for a non-MLD AP) * * If the driver implements beaconing modes, it must use this function to * obtain the beacon template. @@ -5048,7 +5086,8 @@ struct ieee80211_mutable_offsets { struct sk_buff * ieee80211_beacon_get_template(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - struct ieee80211_mutable_offsets *offs); + struct ieee80211_mutable_offsets *offs, + unsigned int link_id); /** * ieee80211_beacon_get_tim - beacon generation function @@ -5059,6 +5098,7 @@ ieee80211_beacon_get_template(struct ieee80211_hw *hw, * @tim_length: pointer to variable that will receive the TIM IE length, * (including the ID and length bytes!). * Set to 0 if invalid (in non-AP modes). + * @link_id: the link id to which the beacon belongs (or 0 for a non-MLD AP) * * If the driver implements beaconing modes, it must use this function to * obtain the beacon frame. @@ -5074,21 +5114,24 @@ ieee80211_beacon_get_template(struct ieee80211_hw *hw, */ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - u16 *tim_offset, u16 *tim_length); + u16 *tim_offset, u16 *tim_length, + unsigned int link_id); /** * ieee80211_beacon_get - beacon generation function * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @link_id: the link id to which the beacon belongs (or 0 for a non-MLD AP) * * See ieee80211_beacon_get_tim(). * * Return: See ieee80211_beacon_get_tim(). */ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, - struct ieee80211_vif *vif) + struct ieee80211_vif *vif, + unsigned int link_id) { - return ieee80211_beacon_get_tim(hw, vif, NULL, NULL); + return ieee80211_beacon_get_tim(hw, vif, NULL, NULL, link_id); } /** @@ -6195,7 +6238,7 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success); /** * ieee80211_channel_switch_disconnect - disconnect due to channel switch error - * @vif &struct ieee80211_vif pointer from the add_interface callback. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @block_tx: if %true, do not send deauth frame. * * Instruct mac80211 to disconnect due to a channel switch error. The channel @@ -6208,13 +6251,14 @@ void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, /** * ieee80211_request_smps - request SM PS transition * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @link_id: link ID for MLO, or 0 * @smps_mode: new SM PS mode * * This allows the driver to request an SM PS transition in managed * mode. This is useful when the driver has more information than * the stack about possible interference, for example by bluetooth. */ -void ieee80211_request_smps(struct ieee80211_vif *vif, +void ieee80211_request_smps(struct ieee80211_vif *vif, unsigned int link_id, enum ieee80211_smps_mode smps_mode); /** @@ -6546,6 +6590,7 @@ ieee80211_vif_type_p2p(struct ieee80211_vif *vif) * ieee80211_update_mu_groups - set the VHT MU-MIMO groud data * * @vif: the specified virtual interface + * @link_id: the link ID for MLO, otherwise 0 * @membership: 64 bits array - a bit is set if station is member of the group * @position: 2 bits per group id indicating the position in the group * @@ -6554,7 +6599,7 @@ ieee80211_vif_type_p2p(struct ieee80211_vif *vif) * matching GroupId management frame. * Calls to this function need to be serialized with RX path. */ -void ieee80211_update_mu_groups(struct ieee80211_vif *vif, +void ieee80211_update_mu_groups(struct ieee80211_vif *vif, unsigned int link_id, const u8 *membership, const u8 *position); void ieee80211_enable_rssi_reports(struct ieee80211_vif *vif, @@ -6787,6 +6832,9 @@ static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) { } +void __ieee80211_schedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, bool force); + /** * ieee80211_schedule_txq - schedule a TXQ for transmission * @@ -6799,7 +6847,11 @@ static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) * The driver may call this function if it has buffered packets for * this TXQ internally. */ -void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq); +static inline void +ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) +{ + __ieee80211_schedule_txq(hw, txq, true); +} /** * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() @@ -6811,8 +6863,12 @@ void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq); * The driver may set force=true if it has buffered packets for this TXQ * internally. */ -void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, - bool force); +static inline void +ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, + bool force) +{ + __ieee80211_schedule_txq(hw, txq, force); +} /** * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 4d761ad530c9..ac9cf7271d46 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -39,6 +39,7 @@ struct mptcp_ext { infinite_map:1; }; +#define MPTCPOPT_HMAC_LEN 20 #define MPTCP_RM_IDS_MAX 8 struct mptcp_rm_list { @@ -89,7 +90,7 @@ struct mptcp_out_options { u32 nonce; u32 token; u64 thmac; - u8 hmac[20]; + u8 hmac[MPTCPOPT_HMAC_LEN]; }; }; #endif diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 87419f7f5421..9f0bab0589d9 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -48,6 +48,7 @@ enum { NEIGH_VAR_RETRANS_TIME, NEIGH_VAR_BASE_REACHABLE_TIME, NEIGH_VAR_DELAY_PROBE_TIME, + NEIGH_VAR_INTERVAL_PROBE_TIME_MS, NEIGH_VAR_GC_STALETIME, NEIGH_VAR_QUEUE_LEN_BYTES, NEIGH_VAR_PROXY_QLEN, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index c4f5601f6e32..20a2992901c2 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -120,7 +120,9 @@ struct net { struct netns_core core; struct netns_mib mib; struct netns_packet packet; +#if IS_ENABLED(CONFIG_UNIX) struct netns_unix unx; +#endif struct netns_nexthop nexthop; struct netns_ipv4 ipv4; #if IS_ENABLED(CONFIG_IPV6) diff --git a/include/net/netns/unix.h b/include/net/netns/unix.h index 91a3d7e39198..6f1a33df061d 100644 --- a/include/net/netns/unix.h +++ b/include/net/netns/unix.h @@ -5,8 +5,14 @@ #ifndef __NETNS_UNIX_H__ #define __NETNS_UNIX_H__ +struct unix_table { + spinlock_t *locks; + struct hlist_head *buckets; +}; + struct ctl_table_header; struct netns_unix { + struct unix_table table; int sysctl_max_dgram_qlen; struct ctl_table_header *ctl; }; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 8cf001aed858..d9d90e6925e1 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -23,7 +23,7 @@ struct tcf_walker { }; int register_tcf_proto_ops(struct tcf_proto_ops *ops); -int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); +void unregister_tcf_proto_ops(struct tcf_proto_ops *ops); struct tcf_block_ext_info { enum flow_block_binder_type binder_type; diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 44a35531952e..3372a1f67cf4 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -173,11 +173,28 @@ struct tc_taprio_qopt_offload { struct tc_taprio_sched_entry entries[]; }; +#if IS_ENABLED(CONFIG_NET_SCH_TAPRIO) + /* Reference counting */ struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload *offload); void taprio_offload_free(struct tc_taprio_qopt_offload *offload); +#else + +/* Reference counting */ +static inline struct tc_taprio_qopt_offload * +taprio_offload_get(struct tc_taprio_qopt_offload *offload) +{ + return NULL; +} + +static inline void taprio_offload_free(struct tc_taprio_qopt_offload *offload) +{ +} + +#endif + /* Ensure skb_mstamp_ns, which might have been populated with the txtime, is * not mistaken for a software timestamp, because this will otherwise prevent * the dispatch of hardware timestamps to the socket. diff --git a/include/net/raw.h b/include/net/raw.h index c51a635671a7..5e665934ebc7 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -20,9 +20,8 @@ extern struct proto raw_prot; extern struct raw_hashinfo raw_v4_hashinfo; -struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, - unsigned short num, __be32 raddr, - __be32 laddr, int dif, int sdif); +bool raw_v4_match(struct net *net, struct sock *sk, unsigned short num, + __be32 raddr, __be32 laddr, int dif, int sdif); int raw_abort(struct sock *sk, int err); void raw_icmp_error(struct sk_buff *, int, u32); @@ -33,10 +32,19 @@ int raw_rcv(struct sock *, struct sk_buff *); #define RAW_HTABLE_SIZE MAX_INET_PROTOS struct raw_hashinfo { - rwlock_t lock; - struct hlist_head ht[RAW_HTABLE_SIZE]; + spinlock_t lock; + struct hlist_nulls_head ht[RAW_HTABLE_SIZE]; }; +static inline void raw_hashinfo_init(struct raw_hashinfo *hashinfo) +{ + int i; + + spin_lock_init(&hashinfo->lock); + for (i = 0; i < RAW_HTABLE_SIZE; i++) + INIT_HLIST_NULLS_HEAD(&hashinfo->ht[i], i); +} + #ifdef CONFIG_PROC_FS int raw_proc_init(void); void raw_proc_exit(void); diff --git a/include/net/rawv6.h b/include/net/rawv6.h index 53d86b6055e8..bc70909625f6 100644 --- a/include/net/rawv6.h +++ b/include/net/rawv6.h @@ -3,11 +3,12 @@ #define _NET_RAWV6_H #include <net/protocol.h> +#include <net/raw.h> extern struct raw_hashinfo raw_v6_hashinfo; -struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, - unsigned short num, const struct in6_addr *loc_addr, - const struct in6_addr *rmt_addr, int dif, int sdif); +bool raw_v6_match(struct net *net, struct sock *sk, unsigned short num, + const struct in6_addr *loc_addr, + const struct in6_addr *rmt_addr, int dif, int sdif); int raw_abort(struct sock *sk, int err); diff --git a/include/net/route.h b/include/net/route.h index 991a3985712d..651424ef09c9 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -201,10 +201,6 @@ int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct in_device *in_dev, u32 *itag); int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin); -int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src, - u8 tos, struct net_device *devin, - struct fib_result *res); - int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin, const struct sk_buff *hint); diff --git a/include/net/sock.h b/include/net/sock.h index 9fa54762e077..f7ad1a7705e9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -609,7 +609,7 @@ void sock_net_set(struct sock *sk, struct net *net) int sk_set_peek_off(struct sock *sk, int val); -static inline int sk_peek_offset(struct sock *sk, int flags) +static inline int sk_peek_offset(const struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { return READ_ONCE(sk->sk_peek_off); @@ -849,7 +849,7 @@ static inline void sk_add_bind_node(struct sock *sk, ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ pos = rcu_dereference(hlist_next_rcu(pos))) -static inline struct user_namespace *sk_user_ns(struct sock *sk) +static inline struct user_namespace *sk_user_ns(const struct sock *sk) { /* Careful only use this in a context where these parameters * can not change and must all be valid, such as recvmsg from @@ -895,7 +895,7 @@ enum sock_flags { #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) -static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) +static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { nsk->sk_flags = osk->sk_flags; } @@ -1240,6 +1240,7 @@ struct proto { void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ + int __percpu *per_cpu_fw_alloc; struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* @@ -1383,21 +1384,46 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) } static inline long -sk_memory_allocated(const struct sock *sk) +proto_memory_allocated(const struct proto *prot) { - return atomic_long_read(sk->sk_prot->memory_allocated); + return max(0L, atomic_long_read(prot->memory_allocated)); } static inline long +sk_memory_allocated(const struct sock *sk) +{ + return proto_memory_allocated(sk->sk_prot); +} + +/* 1 MB per cpu, in page units */ +#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) + +static inline void sk_memory_allocated_add(struct sock *sk, int amt) { - return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve >= SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { - atomic_long_sub(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 @@ -1426,12 +1452,6 @@ proto_sockets_allocated_sum_positive(struct proto *prot) return percpu_counter_sum_positive(prot->sockets_allocated); } -static inline long -proto_memory_allocated(struct proto *prot) -{ - return atomic_long_read(prot->memory_allocated); -} - static inline bool proto_memory_pressure(struct proto *prot) { @@ -1518,30 +1538,18 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); -/* We used to have PAGE_SIZE here, but systems with 64KB pages - * do not necessarily have 16x time more memory than 4KB ones. - */ -#define SK_MEM_QUANTUM 4096 -#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 -/* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ +/* sysctl_mem values are in pages */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long val = READ_ONCE(sk->sk_prot->sysctl_mem[index]); - -#if PAGE_SIZE > SK_MEM_QUANTUM - val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; -#elif PAGE_SIZE < SK_MEM_QUANTUM - val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT; -#endif - return val; + return READ_ONCE(sk->sk_prot->sysctl_mem[index]); } static inline int sk_mem_pages(int amt) { - return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT; + return (amt + PAGE_SIZE - 1) >> PAGE_SHIFT; } static inline bool sk_has_account(struct sock *sk) @@ -1552,19 +1560,23 @@ static inline bool sk_has_account(struct sock *sk) static inline bool sk_wmem_schedule(struct sock *sk, int size) { + int delta; + if (!sk_has_account(sk)) return true; - return size <= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_SEND); + delta = size - sk->sk_forward_alloc; + return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_SEND); } static inline bool sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { + int delta; + if (!sk_has_account(sk)) return true; - return size <= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_RECV) || + delta = size - sk->sk_forward_alloc; + return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || skb_pfmemalloc(skb); } @@ -1590,7 +1602,7 @@ static inline void sk_mem_reclaim(struct sock *sk) reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - if (reclaimable >= SK_MEM_QUANTUM) + if (reclaimable >= (int)PAGE_SIZE) __sk_mem_reclaim(sk, reclaimable); } @@ -1600,19 +1612,6 @@ static inline void sk_mem_reclaim_final(struct sock *sk) sk_mem_reclaim(sk); } -static inline void sk_mem_reclaim_partial(struct sock *sk) -{ - int reclaimable; - - if (!sk_has_account(sk)) - return; - - reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - - if (reclaimable > SK_MEM_QUANTUM) - __sk_mem_reclaim(sk, reclaimable - 1); -} - static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) @@ -1620,29 +1619,12 @@ static inline void sk_mem_charge(struct sock *sk, int size) sk->sk_forward_alloc -= size; } -/* the following macros control memory reclaiming in sk_mem_uncharge() - */ -#define SK_RECLAIM_THRESHOLD (1 << 21) -#define SK_RECLAIM_CHUNK (1 << 20) - static inline void sk_mem_uncharge(struct sock *sk, int size) { - int reclaimable; - if (!sk_has_account(sk)) return; sk->sk_forward_alloc += size; - reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - - /* Avoid a possible overflow. - * TCP send queues can make this happen, if sk_mem_reclaim() - * is not called and more than 2 GBytes are released at once. - * - * If we reach 2 MBytes, reclaim 1 MBytes right now, there is - * no need to hold that much forward allocation anyway. - */ - if (unlikely(reclaimable >= SK_RECLAIM_THRESHOLD)) - __sk_mem_reclaim(sk, SK_RECLAIM_CHUNK); + sk_mem_reclaim(sk); } /* @@ -2232,9 +2214,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro if (err) return err; - skb->len += copy; - skb->data_len += copy; - skb->truesize += copy; + skb_len_add(skb, copy); sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; diff --git a/include/net/strparser.h b/include/net/strparser.h index a191486eb1e4..88900b05443e 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -65,15 +65,19 @@ struct _strp_msg { struct sk_skb_cb { #define SK_SKB_CB_PRIV_LEN 20 unsigned char data[SK_SKB_CB_PRIV_LEN]; + /* align strp on cache line boundary within skb->cb[] */ + unsigned char pad[4]; struct _strp_msg strp; - /* temp_reg is a temporary register used for bpf_convert_data_end_access - * when dst_reg == src_reg. - */ - u64 temp_reg; + + /* strp users' data follows */ struct tls_msg { u8 control; u8 decrypted; } tls; + /* temp_reg is a temporary register used for bpf_convert_data_end_access + * when dst_reg == src_reg. + */ + u64 temp_reg; }; static inline struct strp_msg *strp_msg(struct sk_buff *skb) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index aa0171d5786d..7dcdc97c0bc3 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -239,6 +239,9 @@ struct switchdev_notifier_info { const void *ctx; }; +/* Remember to update br_switchdev_fdb_populate() when adding + * new members to this structure + */ struct switchdev_notifier_fdb_info { struct switchdev_notifier_info info; /* must be first */ const unsigned char *addr; diff --git a/include/net/tcp.h b/include/net/tcp.h index 1e99f5c61f84..8e48dc56837b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -253,6 +253,8 @@ extern long sysctl_tcp_mem[3]; #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; +DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); + extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; @@ -432,6 +434,7 @@ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie); +u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss); u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th); @@ -669,6 +672,7 @@ void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); +int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); void tcp_initialize_rcv_mss(struct sock *sk); diff --git a/include/net/tls.h b/include/net/tls.h index 8bd938f98bdd..8742e13bc362 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -39,7 +39,6 @@ #include <linux/crypto.h> #include <linux/socket.h> #include <linux/tcp.h> -#include <linux/skmsg.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> @@ -50,6 +49,7 @@ #include <crypto/aead.h> #include <uapi/linux/tls.h> +struct tls_rec; /* Maximum data size carried in a TLS record */ #define TLS_MAX_PAYLOAD_SIZE ((size_t)1 << 14) @@ -66,6 +66,7 @@ #define MAX_IV_SIZE 16 #define TLS_TAG_SIZE 16 #define TLS_MAX_REC_SEQ_SIZE 8 +#define TLS_MAX_AAD_SIZE TLS_AAD_SPACE_SIZE /* For CCM mode, the full 16-bytes of IV is made of '4' fields of given sizes. * @@ -77,13 +78,6 @@ #define TLS_AES_CCM_IV_B0_BYTE 2 #define TLS_SM4_CCM_IV_B0_BYTE 2 -#define __TLS_INC_STATS(net, field) \ - __SNMP_INC_STATS((net)->mib.tls_statistics, field) -#define TLS_INC_STATS(net, field) \ - SNMP_INC_STATS((net)->mib.tls_statistics, field) -#define TLS_DEC_STATS(net, field) \ - SNMP_DEC_STATS((net)->mib.tls_statistics, field) - enum { TLS_BASE, TLS_SW, @@ -92,32 +86,6 @@ enum { TLS_NUM_CONFIG, }; -/* TLS records are maintained in 'struct tls_rec'. It stores the memory pages - * allocated or mapped for each TLS record. After encryption, the records are - * stores in a linked list. - */ -struct tls_rec { - struct list_head list; - int tx_ready; - int tx_flags; - - struct sk_msg msg_plaintext; - struct sk_msg msg_encrypted; - - /* AAD | msg_plaintext.sg.data | sg_tag */ - struct scatterlist sg_aead_in[2]; - /* AAD | msg_encrypted.sg.data (data contains overhead for hdr & iv & tag) */ - struct scatterlist sg_aead_out[2]; - - char content_type; - struct scatterlist sg_content_type; - - char aad_space[TLS_AAD_SPACE_SIZE]; - u8 iv_data[MAX_IV_SIZE]; - struct aead_request aead_req; - u8 aead_req_ctx[]; -}; - struct tx_work { struct delayed_work work; struct sock *sk; @@ -149,6 +117,7 @@ struct tls_sw_context_rx { struct sk_buff *recv_pkt; u8 async_capable:1; + u8 zc_capable:1; atomic_t decrypt_pending; /* protect crypto_wait with decrypt_pending*/ spinlock_t decrypt_compl_lock; @@ -239,6 +208,7 @@ struct tls_context { u8 tx_conf:3; u8 rx_conf:3; u8 zerocopy_sendfile:1; + u8 rx_no_pad:1; int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); @@ -346,43 +316,6 @@ struct tls_offload_context_rx { #define TLS_OFFLOAD_CONTEXT_SIZE_RX \ (sizeof(struct tls_offload_context_rx) + TLS_DRIVER_STATE_SIZE_RX) -struct tls_context *tls_ctx_create(struct sock *sk); -void tls_ctx_free(struct sock *sk, struct tls_context *ctx); -void update_sk_prot(struct sock *sk, struct tls_context *ctx); - -int wait_on_pending_writer(struct sock *sk, long *timeo); -int tls_sk_query(struct sock *sk, int optname, char __user *optval, - int __user *optlen); -int tls_sk_attach(struct sock *sk, int optname, char __user *optval, - unsigned int optlen); -void tls_err_abort(struct sock *sk, int err); - -int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); -void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); -void tls_sw_strparser_done(struct tls_context *tls_ctx); -int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); -int tls_sw_sendpage_locked(struct sock *sk, struct page *page, - int offset, size_t size, int flags); -int tls_sw_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags); -void tls_sw_cancel_work_tx(struct tls_context *tls_ctx); -void tls_sw_release_resources_tx(struct sock *sk); -void tls_sw_free_ctx_tx(struct tls_context *tls_ctx); -void tls_sw_free_resources_rx(struct sock *sk); -void tls_sw_release_resources_rx(struct sock *sk); -void tls_sw_free_ctx_rx(struct tls_context *tls_ctx); -int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int flags, int *addr_len); -bool tls_sw_sock_is_readable(struct sock *sk); -ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, - struct pipe_inode_info *pipe, - size_t len, unsigned int flags); - -int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); -int tls_device_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags); -int tls_tx_records(struct sock *sk, int flags); - struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn); @@ -396,58 +329,6 @@ static inline u32 tls_record_start_seq(struct tls_record_info *rec) return rec->end_seq - rec->len; } -int tls_push_sg(struct sock *sk, struct tls_context *ctx, - struct scatterlist *sg, u16 first_offset, - int flags); -int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, - int flags); -void tls_free_partial_record(struct sock *sk, struct tls_context *ctx); - -static inline struct tls_msg *tls_msg(struct sk_buff *skb) -{ - struct sk_skb_cb *scb = (struct sk_skb_cb *)skb->cb; - - return &scb->tls; -} - -static inline bool tls_is_partially_sent_record(struct tls_context *ctx) -{ - return !!ctx->partially_sent_record; -} - -static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) -{ - return tls_ctx->pending_open_record_frags; -} - -static inline bool is_tx_ready(struct tls_sw_context_tx *ctx) -{ - struct tls_rec *rec; - - rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); - if (!rec) - return false; - - return READ_ONCE(rec->tx_ready); -} - -static inline u16 tls_user_config(struct tls_context *ctx, bool tx) -{ - u16 config = tx ? ctx->tx_conf : ctx->rx_conf; - - switch (config) { - case TLS_BASE: - return TLS_CONF_BASE; - case TLS_SW: - return TLS_CONF_SW; - case TLS_HW: - return TLS_CONF_HW; - case TLS_HW_RECORD: - return TLS_CONF_HW_RECORD; - } - return 0; -} - struct sk_buff * tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, struct sk_buff *skb); @@ -466,31 +347,6 @@ static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) #endif } -static inline bool tls_bigint_increment(unsigned char *seq, int len) -{ - int i; - - for (i = len - 1; i >= 0; i--) { - ++seq[i]; - if (seq[i] != 0) - break; - } - - return (i == -1); -} - -static inline void tls_bigint_subtract(unsigned char *seq, int n) -{ - u64 rcd_sn; - __be64 *p; - - BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8); - - p = (__be64 *)seq; - rcd_sn = be64_to_cpu(*p); - *p = cpu_to_be64(rcd_sn - n); -} - static inline struct tls_context *tls_get_ctx(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -501,82 +357,6 @@ static inline struct tls_context *tls_get_ctx(const struct sock *sk) return (__force void *)icsk->icsk_ulp_data; } -static inline void tls_advance_record_sn(struct sock *sk, - struct tls_prot_info *prot, - struct cipher_context *ctx) -{ - if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size)) - tls_err_abort(sk, -EBADMSG); - - if (prot->version != TLS_1_3_VERSION && - prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) - tls_bigint_increment(ctx->iv + prot->salt_size, - prot->iv_size); -} - -static inline void tls_fill_prepend(struct tls_context *ctx, - char *buf, - size_t plaintext_len, - unsigned char record_type) -{ - struct tls_prot_info *prot = &ctx->prot_info; - size_t pkt_len, iv_size = prot->iv_size; - - pkt_len = plaintext_len + prot->tag_size; - if (prot->version != TLS_1_3_VERSION && - prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) { - pkt_len += iv_size; - - memcpy(buf + TLS_NONCE_OFFSET, - ctx->tx.iv + prot->salt_size, iv_size); - } - - /* we cover nonce explicit here as well, so buf should be of - * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE - */ - buf[0] = prot->version == TLS_1_3_VERSION ? - TLS_RECORD_TYPE_DATA : record_type; - /* Note that VERSION must be TLS_1_2 for both TLS1.2 and TLS1.3 */ - buf[1] = TLS_1_2_VERSION_MINOR; - buf[2] = TLS_1_2_VERSION_MAJOR; - /* we can use IV for nonce explicit according to spec */ - buf[3] = pkt_len >> 8; - buf[4] = pkt_len & 0xFF; -} - -static inline void tls_make_aad(char *buf, - size_t size, - char *record_sequence, - unsigned char record_type, - struct tls_prot_info *prot) -{ - if (prot->version != TLS_1_3_VERSION) { - memcpy(buf, record_sequence, prot->rec_seq_size); - buf += 8; - } else { - size += prot->tag_size; - } - - buf[0] = prot->version == TLS_1_3_VERSION ? - TLS_RECORD_TYPE_DATA : record_type; - buf[1] = TLS_1_2_VERSION_MAJOR; - buf[2] = TLS_1_2_VERSION_MINOR; - buf[3] = size >> 8; - buf[4] = size & 0xFF; -} - -static inline void xor_iv_with_seq(struct tls_prot_info *prot, char *iv, char *seq) -{ - int i; - - if (prot->version == TLS_1_3_VERSION || - prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) { - for (i = 0; i < 8; i++) - iv[i + 4] ^= seq[i]; - } -} - - static inline struct tls_sw_context_rx *tls_sw_ctx_rx( const struct tls_context *tls_ctx) { @@ -613,9 +393,6 @@ static inline bool tls_sw_has_ctx_rx(const struct sock *sk) return !!tls_sw_ctx_rx(ctx); } -void tls_sw_write_space(struct sock *sk, struct tls_context *ctx); -void tls_device_write_space(struct sock *sk, struct tls_context *ctx); - static inline struct tls_offload_context_rx * tls_offload_ctx_rx(const struct tls_context *tls_ctx) { @@ -690,31 +467,11 @@ static inline bool tls_offload_tx_resync_pending(struct sock *sk) return ret; } -int __net_init tls_proc_init(struct net *net); -void __net_exit tls_proc_fini(struct net *net); - -int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, - unsigned char *record_type); -int decrypt_skb(struct sock *sk, struct sk_buff *skb, - struct scatterlist *sgout); struct sk_buff *tls_encrypt_skb(struct sk_buff *skb); -int tls_sw_fallback_init(struct sock *sk, - struct tls_offload_context_tx *offload_ctx, - struct tls_crypto_info *crypto_info); - #ifdef CONFIG_TLS_DEVICE -int tls_device_init(void); -void tls_device_cleanup(void); void tls_device_sk_destruct(struct sock *sk); -int tls_set_device_offload(struct sock *sk, struct tls_context *ctx); -void tls_device_free_resources_tx(struct sock *sk); -int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx); -void tls_device_offload_cleanup_rx(struct sock *sk); -void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq); void tls_offload_tx_resync_request(struct sock *sk, u32 got_seq, u32 exp_seq); -int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx, - struct sk_buff *skb, struct strp_msg *rxm); static inline bool tls_is_sk_rx_device_offloaded(struct sock *sk) { @@ -723,33 +480,5 @@ static inline bool tls_is_sk_rx_device_offloaded(struct sock *sk) return false; return tls_get_ctx(sk)->rx_conf == TLS_HW; } -#else -static inline int tls_device_init(void) { return 0; } -static inline void tls_device_cleanup(void) {} - -static inline int -tls_set_device_offload(struct sock *sk, struct tls_context *ctx) -{ - return -EOPNOTSUPP; -} - -static inline void tls_device_free_resources_tx(struct sock *sk) {} - -static inline int -tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) -{ - return -EOPNOTSUPP; -} - -static inline void tls_device_offload_cleanup_rx(struct sock *sk) {} -static inline void -tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) {} - -static inline int -tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx, - struct sk_buff *skb, struct strp_msg *rxm) -{ - return 0; -} #endif #endif /* _TLS_OFFLOAD_H */ diff --git a/include/net/udp.h b/include/net/udp.h index b83a00330566..987f7fc7c0aa 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -95,6 +95,7 @@ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, extern struct proto udp_prot; extern atomic_long_t udp_memory_allocated; +DECLARE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); /* sysctl variables for udp */ extern long sysctl_udp_mem[3]; @@ -305,8 +306,7 @@ struct sock *__udp6_lib_lookup(struct net *net, struct sk_buff *skb); struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); -int udp_read_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor); +int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); /* UDP uses skb->dev_scratch to cache as much information as possible and avoid * possibly multiple cache miss on dequeue() diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c39d910d4b45..67b799ef5f67 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1195,6 +1195,8 @@ int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk); static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { + if (!sk_fullsock(osk)) + return 0; sk->sk_policy[0] = NULL; sk->sk_policy[1] = NULL; if (unlikely(osk->sk_policy[0] || osk->sk_policy[1])) @@ -1923,7 +1925,7 @@ static inline void xfrm_dev_state_free(struct xfrm_state *x) if (dev->xfrmdev_ops->xdo_dev_state_free) dev->xfrmdev_ops->xdo_dev_state_free(x); xso->dev = NULL; - dev_put_track(dev, &xso->dev_tracker); + netdev_put(dev, &xso->dev_tracker); } } #else diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 5f88385a7748..ac151ecc7f19 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -575,6 +575,7 @@ struct ocelot_ops { int (*psfp_stats_get)(struct ocelot *ocelot, struct flow_cls_offload *f, struct flow_stats *stats); void (*cut_through_fwd)(struct ocelot *ocelot); + void (*tas_clock_adjust)(struct ocelot *ocelot); }; struct ocelot_vcap_policer { @@ -669,6 +670,8 @@ struct ocelot_port { /* VLAN that untagged frames are classified to, on ingress */ const struct ocelot_bridge_vlan *pvid_vlan; + struct tc_taprio_qopt_offload *taprio; + phy_interface_t phy_mode; unsigned int ptp_skbs_in_flight; @@ -757,6 +760,9 @@ struct ocelot { /* Lock for serializing forwarding domain changes */ struct mutex fwd_domain_lock; + /* Lock for serializing Time-Aware Shaper changes */ + struct mutex tas_lock; + struct workqueue_struct *owq; u8 ptp:1; diff --git a/include/trace/events/net.h b/include/trace/events/net.h index 032b431b987b..da611a7aaf97 100644 --- a/include/trace/events/net.h +++ b/include/trace/events/net.h @@ -136,7 +136,7 @@ DECLARE_EVENT_CLASS(net_dev_template, __assign_str(name, skb->dev->name); ), - TP_printk("dev=%s skbaddr=%px len=%u", + TP_printk("dev=%s skbaddr=%p len=%u", __get_str(name), __entry->skbaddr, __entry->len) ) diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index 59c945b66f9c..a3995925cb05 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -41,7 +41,7 @@ TRACE_EVENT(qdisc_dequeue, __entry->txq_state = txq->state; ), - TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%px", + TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%p", __entry->ifindex, __entry->handle, __entry->parent, __entry->txq_state, __entry->packets, __entry->skbaddr ) ); @@ -70,7 +70,7 @@ TRACE_EVENT(qdisc_enqueue, __entry->parent = qdisc->parent; ), - TP_printk("enqueue ifindex=%d qdisc handle=0x%X parent=0x%X skbaddr=%px", + TP_printk("enqueue ifindex=%d qdisc handle=0x%X parent=0x%X skbaddr=%p", __entry->ifindex, __entry->handle, __entry->parent, __entry->skbaddr) ); diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index a477bf907498..45264e4bb254 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -9,92 +9,6 @@ #include <linux/netdevice.h> #include <linux/tracepoint.h> -#define TRACE_SKB_DROP_REASON \ - EM(SKB_DROP_REASON_NOT_SPECIFIED, NOT_SPECIFIED) \ - EM(SKB_DROP_REASON_NO_SOCKET, NO_SOCKET) \ - EM(SKB_DROP_REASON_PKT_TOO_SMALL, PKT_TOO_SMALL) \ - EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \ - EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER) \ - EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \ - EM(SKB_DROP_REASON_NETFILTER_DROP, NETFILTER_DROP) \ - EM(SKB_DROP_REASON_OTHERHOST, OTHERHOST) \ - EM(SKB_DROP_REASON_IP_CSUM, IP_CSUM) \ - EM(SKB_DROP_REASON_IP_INHDR, IP_INHDR) \ - EM(SKB_DROP_REASON_IP_RPFILTER, IP_RPFILTER) \ - EM(SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, \ - UNICAST_IN_L2_MULTICAST) \ - EM(SKB_DROP_REASON_XFRM_POLICY, XFRM_POLICY) \ - EM(SKB_DROP_REASON_IP_NOPROTO, IP_NOPROTO) \ - EM(SKB_DROP_REASON_SOCKET_RCVBUFF, SOCKET_RCVBUFF) \ - EM(SKB_DROP_REASON_PROTO_MEM, PROTO_MEM) \ - EM(SKB_DROP_REASON_TCP_MD5NOTFOUND, TCP_MD5NOTFOUND) \ - EM(SKB_DROP_REASON_TCP_MD5UNEXPECTED, \ - TCP_MD5UNEXPECTED) \ - EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ - EM(SKB_DROP_REASON_SOCKET_BACKLOG, SOCKET_BACKLOG) \ - EM(SKB_DROP_REASON_TCP_FLAGS, TCP_FLAGS) \ - EM(SKB_DROP_REASON_TCP_ZEROWINDOW, TCP_ZEROWINDOW) \ - EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ - EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ - EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ - EM(SKB_DROP_REASON_TCP_OFO_DROP, TCP_OFO_DROP) \ - EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ - EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ - TCP_INVALID_SEQUENCE) \ - EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ - EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ - EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ - EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ - EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ - EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ - EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ - TCP_ACK_UNSENT_DATA) \ - EM(SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, \ - TCP_OFO_QUEUE_PRUNE) \ - EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ - EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ - BPF_CGROUP_EGRESS) \ - EM(SKB_DROP_REASON_IPV6DISABLED, IPV6DISABLED) \ - EM(SKB_DROP_REASON_NEIGH_CREATEFAIL, NEIGH_CREATEFAIL) \ - EM(SKB_DROP_REASON_NEIGH_FAILED, NEIGH_FAILED) \ - EM(SKB_DROP_REASON_NEIGH_QUEUEFULL, NEIGH_QUEUEFULL) \ - EM(SKB_DROP_REASON_NEIGH_DEAD, NEIGH_DEAD) \ - EM(SKB_DROP_REASON_TC_EGRESS, TC_EGRESS) \ - EM(SKB_DROP_REASON_QDISC_DROP, QDISC_DROP) \ - EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ - EM(SKB_DROP_REASON_XDP, XDP) \ - EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \ - EM(SKB_DROP_REASON_UNHANDLED_PROTO, UNHANDLED_PROTO) \ - EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \ - EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \ - EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \ - EM(SKB_DROP_REASON_DEV_HDR, DEV_HDR) \ - EM(SKB_DROP_REASON_DEV_READY, DEV_READY) \ - EM(SKB_DROP_REASON_FULL_RING, FULL_RING) \ - EM(SKB_DROP_REASON_NOMEM, NOMEM) \ - EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC) \ - EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER) \ - EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ - EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ - EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ - EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ - EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ - EM(SKB_DROP_REASON_PKT_TOO_BIG, PKT_TOO_BIG) \ - EMe(SKB_DROP_REASON_MAX, MAX) - -#undef EM -#undef EMe - -#define EM(a, b) TRACE_DEFINE_ENUM(a); -#define EMe(a, b) TRACE_DEFINE_ENUM(a); - -TRACE_SKB_DROP_REASON - -#undef EM -#undef EMe -#define EM(a, b) { a, #b }, -#define EMe(a, b) { a, #b } - /* * Tracepoint for free an sk_buff: */ @@ -121,8 +35,7 @@ TRACE_EVENT(kfree_skb, TP_printk("skbaddr=%p protocol=%u location=%p reason: %s", __entry->skbaddr, __entry->protocol, __entry->location, - __print_symbolic(__entry->reason, - TRACE_SKB_DROP_REASON)) + drop_reasons[__entry->reason]) ); TRACE_EVENT(consume_skb, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ef78e0e1a754..3dd13fe738b9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -998,6 +998,7 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, BPF_TRACE_KPROBE_MULTI, + BPF_LSM_CGROUP, __MAX_BPF_ATTACH_TYPE }; @@ -1431,6 +1432,7 @@ union bpf_attr { __u32 attach_flags; __aligned_u64 prog_ids; __u32 prog_cnt; + __aligned_u64 prog_attach_flags; /* output: per-program attach_flags */ } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ @@ -3597,10 +3599,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains **sizeof**\ (**struct tcphdr**). + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). * Return * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. @@ -3783,10 +3786,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains the length of the TCP header. + * contains the length of the TCP header with options (at least + * **sizeof**\ (**struct tcphdr**)). * Return * On success, lower 32 bits hold the generated SYN cookie in * followed by 16 bits which hold the MSS value for that cookie, @@ -5252,6 +5256,80 @@ union bpf_attr { * Pointer to the underlying dynptr data, NULL if the dynptr is * read-only, if the dynptr is invalid, or if the offset and length * is out of bounds. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv4/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv6/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5458,6 +5536,10 @@ union bpf_attr { FN(dynptr_read), \ FN(dynptr_write), \ FN(dynptr_data), \ + FN(tcp_raw_gen_syncookie_ipv4), \ + FN(tcp_raw_gen_syncookie_ipv6), \ + FN(tcp_raw_check_syncookie_ipv4), \ + FN(tcp_raw_check_syncookie_ipv6), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5998,6 +6080,8 @@ struct bpf_prog_info { __u64 run_cnt; __u64 recursion_misses; __u32 verified_insns; + __u32 attach_btf_obj_id; + __u32 attach_btf_id; } __attribute__((aligned(8))); struct bpf_map_info { @@ -6705,6 +6789,7 @@ enum bpf_core_relo_kind { BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ + BPF_CORE_TYPE_MATCHES = 12, /* type match in target kernel */ }; /* diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index a9162a6c0284..ec1798b6d3ff 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -36,10 +36,10 @@ struct btf_type { * bits 24-28: kind (e.g. int, ptr, array...etc) * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union and fwd + * struct, union, enum, fwd and enum64 */ __u32 info; - /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. + /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, @@ -63,7 +63,7 @@ enum { BTF_KIND_ARRAY = 3, /* Array */ BTF_KIND_STRUCT = 4, /* Struct */ BTF_KIND_UNION = 5, /* Union */ - BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_ENUM = 6, /* Enumeration up to 32-bit values */ BTF_KIND_FWD = 7, /* Forward */ BTF_KIND_TYPEDEF = 8, /* Typedef */ BTF_KIND_VOLATILE = 9, /* Volatile */ @@ -76,6 +76,7 @@ enum { BTF_KIND_FLOAT = 16, /* Floating point */ BTF_KIND_DECL_TAG = 17, /* Decl Tag */ BTF_KIND_TYPE_TAG = 18, /* Type Tag */ + BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -186,4 +187,14 @@ struct btf_decl_tag { __s32 component_idx; }; +/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64". + * The exact number of btf_enum64 is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum64 { + __u32 name_off; + __u32 val_lo32; + __u32 val_hi32; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 1d0bccc3fa54..d370165bc621 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -116,6 +116,7 @@ #define ETH_P_QINQ3 0x9300 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_EDSA 0xDADA /* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_DSA_8021Q 0xDADB /* Fake VLAN Header for DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_DSA_A5PSW 0xE001 /* A5PSW Tag Value [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_IFE 0xED3E /* ForCES inter-FE LFB type */ #define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5f58dcfe2787..e36d9d2c65a7 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -963,6 +963,7 @@ enum { IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, + IFLA_BOND_SLAVE_PRIO, __IFLA_BOND_SLAVE_MAX, }; diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 39c565e460c7..a998bf761635 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -154,6 +154,7 @@ enum { NDTPA_QUEUE_LENBYTES, /* u32 */ NDTPA_MCAST_REPROBES, /* u32 */ NDTPA_PAD, + NDTPA_INTERVAL_PROBE_TIME_MS, /* u64, msecs */ __NDTPA_MAX }; #define NDTPA_MAX (__NDTPA_MAX - 1) diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d9490e3062a7..7bb1ae59f3a5 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -324,6 +324,17 @@ */ /** + * DOC: Multi-Link Operation + * + * In Multi-Link Operation, a connection between to MLDs utilizes multiple + * links. To use this in nl80211, various commands and responses now need + * to or will include the new %NL80211_ATTR_MLO_LINKS attribute. + * Additionally, various commands that need to operate on a specific link + * now need to be given the %NL80211_ATTR_MLO_LINK_ID attribute, e.g. to + * use %NL80211_CMD_START_AP or similar functions. + */ + +/** * enum nl80211_commands - supported nl80211 commands * * @NL80211_CMD_UNSPEC: unspecified command to catch errors @@ -1237,6 +1248,12 @@ * to describe the BSSID address of the AP and %NL80211_ATTR_TIMEOUT to * specify the timeout value. * + * @NL80211_CMD_ADD_LINK: Add a new link to an interface. The + * %NL80211_ATTR_MLO_LINK_ID attribute is used for the new link. + * @NL80211_CMD_REMOVE_LINK: Remove a link from an interface. This may come + * without %NL80211_ATTR_MLO_LINK_ID as an easy way to remove all links + * in preparation for e.g. roaming to a regular (non-MLO) AP. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1481,6 +1498,9 @@ enum nl80211_commands { NL80211_CMD_ASSOC_COMEBACK, + NL80211_CMD_ADD_LINK, + NL80211_CMD_REMOVE_LINK, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2663,6 +2683,24 @@ enum nl80211_commands { * association request when used with NL80211_CMD_NEW_STATION). Can be set * only if %NL80211_STA_FLAG_WME is set. * + * @NL80211_ATTR_MLO_LINK_ID: A (u8) link ID for use with MLO, to be used with + * various commands that need a link ID to operate. + * @NL80211_ATTR_MLO_LINKS: A nested array of links, each containing some + * per-link information and a link ID. + * @NL80211_ATTR_MLD_ADDR: An MLD address, used with various commands such as + * authenticate/associate. + * + * @NL80211_ATTR_MLO_SUPPORT: Flag attribute to indicate user space supports MLO + * connection. Used with %NL80211_CMD_CONNECT. If this attribute is not + * included in NL80211_CMD_CONNECT drivers must not perform MLO connection. + * + * @NL80211_ATTR_MAX_NUM_AKM_SUITES: U16 attribute. Indicates maximum number of + * AKM suites allowed for %NL80211_CMD_CONNECT, %NL80211_CMD_ASSOCIATE and + * %NL80211_CMD_START_AP in %NL80211_CMD_GET_WIPHY response. If this + * attribute is not present userspace shall consider maximum number of AKM + * suites allowed as %NL80211_MAX_NR_AKM_SUITES which is the legacy maximum + * number prior to the introduction of this attribute. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3177,6 +3215,14 @@ enum nl80211_attrs { NL80211_ATTR_DISABLE_EHT, + NL80211_ATTR_MLO_LINKS, + NL80211_ATTR_MLO_LINK_ID, + NL80211_ATTR_MLD_ADDR, + + NL80211_ATTR_MLO_SUPPORT, + + NL80211_ATTR_MAX_NUM_AKM_SUITES, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3231,6 +3277,11 @@ enum nl80211_attrs { #define NL80211_HE_MIN_CAPABILITY_LEN 16 #define NL80211_HE_MAX_CAPABILITY_LEN 54 #define NL80211_MAX_NR_CIPHER_SUITES 5 + +/* + * NL80211_MAX_NR_AKM_SUITES is obsolete when %NL80211_ATTR_MAX_NUM_AKM_SUITES + * present in %NL80211_CMD_GET_WIPHY response. + */ #define NL80211_MAX_NR_AKM_SUITES 2 #define NL80211_EHT_MIN_CAPABILITY_LEN 13 #define NL80211_EHT_MAX_CAPABILITY_LEN 51 @@ -4853,6 +4904,7 @@ enum nl80211_bss_scan_width { * Contains a nested array of signal strength attributes (u8, dBm), * using the nesting index as the antenna number. * @NL80211_BSS_FREQUENCY_OFFSET: frequency offset in KHz + * @NL80211_BSS_MLO_LINK_ID: MLO link ID of the BSS (u8). * @__NL80211_BSS_AFTER_LAST: internal * @NL80211_BSS_MAX: highest BSS attribute */ @@ -4878,6 +4930,7 @@ enum nl80211_bss { NL80211_BSS_PARENT_BSSID, NL80211_BSS_CHAIN_SIGNAL, NL80211_BSS_FREQUENCY_OFFSET, + NL80211_BSS_MLO_LINK_ID, /* keep last */ __NL80211_BSS_AFTER_LAST, @@ -5874,7 +5927,7 @@ enum nl80211_ap_sme_features { * @NL80211_FEATURE_INACTIVITY_TIMER: This driver takes care of freeing up * the connected inactive stations in AP mode. * @NL80211_FEATURE_CELL_BASE_REG_HINTS: This driver has been tested - * to work properly to suppport receiving regulatory hints from + * to work properly to support receiving regulatory hints from * cellular base stations. * @NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL: (no longer available, only * here to reserve the value for API/ABI compatibility) diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 904909d020e2..4d7470036a8b 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -344,6 +344,8 @@ enum LINUX_MIB_TLSRXDEVICE, /* TlsRxDevice */ LINUX_MIB_TLSDECRYPTERROR, /* TlsDecryptError */ LINUX_MIB_TLSRXDEVICERESYNC, /* TlsRxDeviceResync */ + LINUX_MIB_TLSDECRYPTRETRY, /* TlsDecryptRetry */ + LINUX_MIB_TLSRXNOPADVIOL, /* TlsRxNoPadViolation */ __LINUX_MIB_TLSMAX }; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 6a3b194c50fe..8981f00204db 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -584,24 +584,25 @@ enum { /* /proc/sys/net/<protocol>/neigh/<dev> */ enum { - NET_NEIGH_MCAST_SOLICIT=1, - NET_NEIGH_UCAST_SOLICIT=2, - NET_NEIGH_APP_SOLICIT=3, - NET_NEIGH_RETRANS_TIME=4, - NET_NEIGH_REACHABLE_TIME=5, - NET_NEIGH_DELAY_PROBE_TIME=6, - NET_NEIGH_GC_STALE_TIME=7, - NET_NEIGH_UNRES_QLEN=8, - NET_NEIGH_PROXY_QLEN=9, - NET_NEIGH_ANYCAST_DELAY=10, - NET_NEIGH_PROXY_DELAY=11, - NET_NEIGH_LOCKTIME=12, - NET_NEIGH_GC_INTERVAL=13, - NET_NEIGH_GC_THRESH1=14, - NET_NEIGH_GC_THRESH2=15, - NET_NEIGH_GC_THRESH3=16, - NET_NEIGH_RETRANS_TIME_MS=17, - NET_NEIGH_REACHABLE_TIME_MS=18, + NET_NEIGH_MCAST_SOLICIT = 1, + NET_NEIGH_UCAST_SOLICIT = 2, + NET_NEIGH_APP_SOLICIT = 3, + NET_NEIGH_RETRANS_TIME = 4, + NET_NEIGH_REACHABLE_TIME = 5, + NET_NEIGH_DELAY_PROBE_TIME = 6, + NET_NEIGH_GC_STALE_TIME = 7, + NET_NEIGH_UNRES_QLEN = 8, + NET_NEIGH_PROXY_QLEN = 9, + NET_NEIGH_ANYCAST_DELAY = 10, + NET_NEIGH_PROXY_DELAY = 11, + NET_NEIGH_LOCKTIME = 12, + NET_NEIGH_GC_INTERVAL = 13, + NET_NEIGH_GC_THRESH1 = 14, + NET_NEIGH_GC_THRESH2 = 15, + NET_NEIGH_GC_THRESH3 = 16, + NET_NEIGH_RETRANS_TIME_MS = 17, + NET_NEIGH_REACHABLE_TIME_MS = 18, + NET_NEIGH_INTERVAL_PROBE_TIME_MS = 19, }; /* /proc/sys/net/dccp */ diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index bb8f80812b0b..f1157d8f4acd 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -40,6 +40,7 @@ #define TLS_TX 1 /* Set transmit parameters */ #define TLS_RX 2 /* Set receive parameters */ #define TLS_TX_ZEROCOPY_RO 3 /* TX zerocopy (only sendfile now) */ +#define TLS_RX_EXPECT_NO_PAD 4 /* Attempt opportunistic zero-copy */ /* Supported versions */ #define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) @@ -162,6 +163,7 @@ enum { TLS_INFO_TXCONF, TLS_INFO_RXCONF, TLS_INFO_ZC_RO_TX, + TLS_INFO_RX_NO_PAD, __TLS_INFO_MAX, }; #define TLS_INFO_MAX (__TLS_INFO_MAX - 1) diff --git a/include/uapi/linux/tty.h b/include/uapi/linux/tty.h index 9d0f06bfbac3..68aeae2addec 100644 --- a/include/uapi/linux/tty.h +++ b/include/uapi/linux/tty.h @@ -38,8 +38,9 @@ #define N_NULL 27 /* Null ldisc used for error handling */ #define N_MCTP 28 /* MCTP-over-serial */ #define N_DEVELOPMENT 29 /* Manual out-of-tree testing */ +#define N_CAN327 30 /* ELM327 based OBD-II interfaces */ /* Always the newest line discipline + 1 */ -#define NR_LDISCS 30 +#define NR_LDISCS 31 #endif /* _UAPI_LINUX_TTY_H */ diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h index a21ca8ece8db..7af9e09ea556 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h +++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h @@ -63,6 +63,7 @@ enum mlx5_ib_uapi_dm_type { MLX5_IB_UAPI_DM_TYPE_MEMIC, MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM, MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM, + MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM, }; enum mlx5_ib_uapi_devx_create_event_channel_flags { |