diff options
Diffstat (limited to 'include/linux')
42 files changed, 873 insertions, 386 deletions
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/cgroup-defs.h b/include/linux/cgroup-defs.h index 1bfcfb1af352..d4427d0a0e18 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -264,7 +264,8 @@ struct css_set { * List of csets participating in the on-going migration either as * source or destination. Protected by cgroup_mutex. */ - struct list_head mg_preload_node; + struct list_head mg_src_preload_node; + struct list_head mg_dst_preload_node; struct list_head mg_node; /* diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 2c7477354744..314802f98b9d 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -68,6 +68,8 @@ extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, extern ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, 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/highmem.h b/include/linux/highmem.h index 3af34de54330..56d6a0196534 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -149,19 +149,19 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they - * can be used in a manner similar to the following: + * can be used in a manner similar to the following:: * - * -- Find the page of interest. -- - * struct page *page = find_get_page(mapping, offset); + * // Find the page of interest. + * struct page *page = find_get_page(mapping, offset); * - * -- Gain access to the contents of that page. -- - * void *vaddr = kmap_atomic(page); + * // Gain access to the contents of that page. + * void *vaddr = kmap_atomic(page); * - * -- Do something to the contents of that page. -- - * memset(vaddr, 0, PAGE_SIZE); + * // Do something to the contents of that page. + * memset(vaddr, 0, PAGE_SIZE); * - * -- Unmap that page. -- - * kunmap_atomic(vaddr); + * // Unmap that page. + * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. 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/inetdevice.h b/include/linux/inetdevice.h index ead323243e7b..ddb27fc0ee8c 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -131,7 +131,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) -#define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_ORCONF((in_dev), ARP_ACCEPT) +#define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) diff --git a/include/linux/kexec.h b/include/linux/kexec.h index ce6536f1d269..475683cd67f1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -452,6 +452,12 @@ static inline int kexec_crash_loaded(void) { return 0; } #define kexec_in_progress false #endif /* CONFIG_KEXEC_CORE */ +#ifdef CONFIG_KEXEC_SIG +void set_kexec_sig_enforced(void); +#else +static inline void set_kexec_sig_enforced(void) {} +#endif + #endif /* !defined(__ASSEBMLY__) */ #endif /* LINUX_KEXEC_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c20f2d55840c..83cf7fd842e0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1513,7 +1513,7 @@ static inline void kvm_arch_end_assignment(struct kvm *kvm) { } -static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; } 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..ecda6e63d5f2 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 { @@ -606,6 +610,7 @@ struct mlx5_priv { spinlock_t ctx_lock; struct mlx5_adev **adev; int adev_idx; + int sw_vhca_id; struct mlx5_events *events; struct mlx5_flow_steering *steering; @@ -676,6 +681,7 @@ 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..254cc22f5eec 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]; @@ -1804,7 +1826,14 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 max_reformat_remove_size[0x8]; u8 max_reformat_remove_offset[0x8]; - u8 reserved_at_c0[0x740]; + u8 reserved_at_c0[0x160]; + + u8 reserved_at_220[0x1]; + u8 sw_vhca_id_valid[0x1]; + u8 sw_vhca_id[0xe]; + u8 reserved_at_230[0x10]; + + u8 reserved_at_240[0x5c0]; }; enum mlx5_ifc_flow_destination_type { @@ -3277,6 +3306,7 @@ 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 +3322,38 @@ 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 +3385,9 @@ 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 +3455,21 @@ 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 { @@ -3715,6 +3789,11 @@ struct mlx5_ifc_rmpc_bits { struct mlx5_ifc_wq_bits wq; }; +enum { + VHCA_ID_TYPE_HW = 0, + VHCA_ID_TYPE_SW = 1, +}; + struct mlx5_ifc_nic_vport_context_bits { u8 reserved_at_0[0x5]; u8 min_wqe_inline_mode[0x3]; @@ -3731,8 +3810,8 @@ struct mlx5_ifc_nic_vport_context_bits { u8 event_on_mc_address_change[0x1]; u8 event_on_uc_address_change[0x1]; - u8 reserved_at_40[0xc]; - + u8 vhca_id_type[0x1]; + u8 reserved_at_41[0xb]; u8 affiliation_criteria[0x4]; u8 affiliated_vhca_id[0x10]; @@ -4074,7 +4153,8 @@ 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 +6050,9 @@ 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 { @@ -7189,7 +7271,12 @@ struct mlx5_ifc_init_hca_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x2]; + u8 sw_vhca_id[0xe]; + u8 reserved_at_70[0x10]; + u8 sw_owner_id[4][0x20]; }; @@ -11370,12 +11457,14 @@ 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 +11537,61 @@ 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/objtool.h b/include/linux/objtool.h index 15b940ec1eac..10bc88cc3bf6 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -32,11 +32,16 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 #ifdef CONFIG_OBJTOOL @@ -124,7 +129,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -177,7 +182,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm 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/sched/task.h b/include/linux/sched/task.h index 505aaf9fe477..81cab4b01edc 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -85,7 +85,7 @@ static inline void exit_thread(struct task_struct *tsk) extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); -extern void exit_itimers(struct signal_struct *); +extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1111adefd906..5d7ff8850eb2 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. @@ -2567,6 +2390,18 @@ static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, } /** + * 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 @@ -2968,8 +2803,14 @@ 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; } @@ -2980,14 +2821,10 @@ 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 3c11ef18a9cf..d2f5c4d5a906 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -433,10 +433,6 @@ 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) |