diff options
Diffstat (limited to 'include/linux')
40 files changed, 704 insertions, 430 deletions
diff --git a/include/linux/audit.h b/include/linux/audit.h index aee3dc9eb378..18925d924c73 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -358,6 +358,8 @@ static inline void audit_ptrace(struct task_struct *t) __audit_ptrace(t); } +extern void audit_log_task(struct audit_buffer *ab); + /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); @@ -645,6 +647,9 @@ static inline void audit_ntp_log(const struct audit_ntp_data *ad) static inline void audit_ptrace(struct task_struct *t) { } + +static inline void audit_log_task(struct audit_buffer *ab) +{ } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3bf3835d0e86..e89e86122233 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -12,10 +12,14 @@ #include <linux/err.h> #include <linux/rbtree_latch.h> #include <linux/numa.h> +#include <linux/mm_types.h> #include <linux/wait.h> #include <linux/u64_stats_sync.h> +#include <linux/refcount.h> +#include <linux/mutex.h> struct bpf_verifier_env; +struct bpf_verifier_log; struct perf_event; struct bpf_prog; struct bpf_map; @@ -23,6 +27,7 @@ struct sock; struct seq_file; struct btf; struct btf_type; +struct exception_table_entry; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -64,6 +69,7 @@ struct bpf_map_ops { u64 *imm, u32 off); int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); + int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); }; struct bpf_map_memory { @@ -92,17 +98,19 @@ struct bpf_map { u32 btf_value_type_id; struct btf *btf; struct bpf_map_memory memory; + char name[BPF_OBJ_NAME_LEN]; bool unpriv_array; - bool frozen; /* write-once */ - /* 48 bytes hole */ + bool frozen; /* write-once; write-protected by freeze_mutex */ + /* 22 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ - atomic_t refcnt ____cacheline_aligned; - atomic_t usercnt; + atomic64_t refcnt ____cacheline_aligned; + atomic64_t usercnt; struct work_struct work; - char name[BPF_OBJ_NAME_LEN]; + struct mutex freeze_mutex; + u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */ }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -211,6 +219,7 @@ enum bpf_arg_type { ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ + ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ }; /* type of values returned from helper functions */ @@ -233,11 +242,17 @@ struct bpf_func_proto { bool gpl_only; bool pkt_access; enum bpf_return_type ret_type; - enum bpf_arg_type arg1_type; - enum bpf_arg_type arg2_type; - enum bpf_arg_type arg3_type; - enum bpf_arg_type arg4_type; - enum bpf_arg_type arg5_type; + union { + struct { + enum bpf_arg_type arg1_type; + enum bpf_arg_type arg2_type; + enum bpf_arg_type arg3_type; + enum bpf_arg_type arg4_type; + enum bpf_arg_type arg5_type; + }; + enum bpf_arg_type arg_type[5]; + }; + int *btf_id; /* BTF ids of arguments */ }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is @@ -281,6 +296,7 @@ enum bpf_reg_type { PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ + PTR_TO_BTF_ID, /* reg points to kernel struct */ }; /* The information passed from prog-specific *_is_valid_access @@ -288,7 +304,11 @@ enum bpf_reg_type { */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; - int ctx_field_size; + union { + int ctx_field_size; + u32 btf_id; + }; + struct bpf_verifier_log *log; /* for verbose logs */ }; static inline void @@ -359,14 +379,117 @@ enum bpf_cgroup_storage_type { #define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX +/* The longest tracepoint has 12 args. + * See include/trace/bpf_probe.h + */ +#define MAX_BPF_FUNC_ARGS 12 + struct bpf_prog_stats { u64 cnt; u64 nsecs; struct u64_stats_sync syncp; +} __aligned(2 * sizeof(u64)); + +struct btf_func_model { + u8 ret_size; + u8 nr_args; + u8 arg_size[MAX_BPF_FUNC_ARGS]; +}; + +/* Restore arguments before returning from trampoline to let original function + * continue executing. This flag is used for fentry progs when there are no + * fexit progs. + */ +#define BPF_TRAMP_F_RESTORE_REGS BIT(0) +/* Call original function after fentry progs, but before fexit progs. + * Makes sense for fentry/fexit, normal calls and indirect calls. + */ +#define BPF_TRAMP_F_CALL_ORIG BIT(1) +/* Skip current frame and return to parent. Makes sense for fentry/fexit + * programs only. Should not be used with normal calls and indirect calls. + */ +#define BPF_TRAMP_F_SKIP_FRAME BIT(2) + +/* Different use cases for BPF trampoline: + * 1. replace nop at the function entry (kprobe equivalent) + * flags = BPF_TRAMP_F_RESTORE_REGS + * fentry = a set of programs to run before returning from trampoline + * + * 2. replace nop at the function entry (kprobe + kretprobe equivalent) + * flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME + * orig_call = fentry_ip + MCOUNT_INSN_SIZE + * fentry = a set of program to run before calling original function + * fexit = a set of program to run after original function + * + * 3. replace direct call instruction anywhere in the function body + * or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid) + * With flags = 0 + * fentry = a set of programs to run before returning from trampoline + * With flags = BPF_TRAMP_F_CALL_ORIG + * orig_call = original callback addr or direct function addr + * fentry = a set of program to run before calling original function + * fexit = a set of program to run after original function + */ +int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags, + struct bpf_prog **fentry_progs, int fentry_cnt, + struct bpf_prog **fexit_progs, int fexit_cnt, + void *orig_call); +/* these two functions are called from generated trampoline */ +u64 notrace __bpf_prog_enter(void); +void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); + +enum bpf_tramp_prog_type { + BPF_TRAMP_FENTRY, + BPF_TRAMP_FEXIT, + BPF_TRAMP_MAX +}; + +struct bpf_trampoline { + /* hlist for trampoline_table */ + struct hlist_node hlist; + /* serializes access to fields of this trampoline */ + struct mutex mutex; + refcount_t refcnt; + u64 key; + struct { + struct btf_func_model model; + void *addr; + } func; + /* list of BPF programs using this trampoline */ + struct hlist_head progs_hlist[BPF_TRAMP_MAX]; + /* Number of attached programs. A counter per kind. */ + int progs_cnt[BPF_TRAMP_MAX]; + /* Executable image of trampoline */ + void *image; + u64 selector; +}; +#ifdef CONFIG_BPF_JIT +struct bpf_trampoline *bpf_trampoline_lookup(u64 key); +int bpf_trampoline_link_prog(struct bpf_prog *prog); +int bpf_trampoline_unlink_prog(struct bpf_prog *prog); +void bpf_trampoline_put(struct bpf_trampoline *tr); +#else +static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key) +{ + return NULL; +} +static inline int bpf_trampoline_link_prog(struct bpf_prog *prog) +{ + return -ENOTSUPP; +} +static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog) +{ + return -ENOTSUPP; +} +static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} +#endif + +struct bpf_func_info_aux { + bool unreliable; }; struct bpf_prog_aux { - atomic_t refcnt; + atomic64_t refcnt; u32 used_map_cnt; u32 max_ctx_offset; u32 max_pkt_offset; @@ -375,8 +498,19 @@ struct bpf_prog_aux { u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ + u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + struct bpf_prog *linked_prog; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; + bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ + bool func_proto_unreliable; + enum bpf_tramp_prog_type trampoline_prog_type; + struct bpf_trampoline *trampoline; + struct hlist_node tramp_hlist; + /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ + const struct btf_type *attach_func_proto; + /* function name for valid attach_btf_id */ + const char *attach_func_name; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ struct latch_tree_node ksym_tnode; @@ -394,6 +528,7 @@ struct bpf_prog_aux { struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; + struct bpf_func_info_aux *func_info_aux; /* bpf_line_info loaded from userspace. linfo->insn_off * has the xlated insn offset. * Both the main and sub prog share the same linfo. @@ -416,6 +551,8 @@ struct bpf_prog_aux { * main prog always has linfo_idx == 0 */ u32 linfo_idx; + u32 num_exentries; + struct exception_table_entry *extable; struct bpf_prog_stats __percpu *stats; union { struct work_struct work; @@ -482,6 +619,7 @@ struct bpf_event_entry { bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); +const char *kernel_type_name(u32 btf_type_id); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -620,7 +758,7 @@ DECLARE_PER_CPU(int, bpf_prog_active); extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; -#define BPF_PROG_TYPE(_id, _name) \ +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ @@ -636,9 +774,9 @@ extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv); -struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); +void bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); -struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); +void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); @@ -649,9 +787,9 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); -struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); -struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map, - bool uref); +void bpf_map_inc(struct bpf_map *map); +void bpf_map_inc_with_uref(struct bpf_map *map); +struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); @@ -661,6 +799,7 @@ void bpf_map_charge_finish(struct bpf_map_memory *mem); void bpf_map_charge_move(struct bpf_map_memory *dst, struct bpf_map_memory *src); void *bpf_map_area_alloc(u64 size, int numa_node); +void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); @@ -747,6 +886,24 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +bool btf_ctx_access(int off, int size, enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info); +int btf_struct_access(struct bpf_verifier_log *log, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, + u32 *next_btf_id); +int btf_resolve_helper_id(struct bpf_verifier_log *log, + const struct bpf_func_proto *fn, int); + +int btf_distill_func_proto(struct bpf_verifier_log *log, + struct btf *btf, + const struct btf_type *func_proto, + const char *func_name, + struct btf_func_model *m); + +int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -760,10 +917,8 @@ static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, return ERR_PTR(-EOPNOTSUPP); } -static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, - int i) +static inline void bpf_prog_add(struct bpf_prog *prog, int i) { - return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_prog_sub(struct bpf_prog *prog, int i) @@ -774,9 +929,8 @@ static inline void bpf_prog_put(struct bpf_prog *prog) { } -static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog) +static inline void bpf_prog_inc(struct bpf_prog *prog) { - return ERR_PTR(-EOPNOTSUPP); } static inline struct bpf_prog *__must_check @@ -972,31 +1126,6 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr, } #endif -#if defined(CONFIG_XDP_SOCKETS) -struct xdp_sock; -struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key); -int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, - struct xdp_sock *xs); -void __xsk_map_flush(struct bpf_map *map); -#else -struct xdp_sock; -static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, - u32 key) -{ - return NULL; -} - -static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, - struct xdp_sock *xs) -{ - return -EOPNOTSUPP; -} - -static inline void __xsk_map_flush(struct bpf_map *map) -{ -} -#endif - #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, @@ -1095,6 +1224,15 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, #endif #ifdef CONFIG_INET +struct sk_reuseport_kern { + struct sk_buff *skb; + struct sock *sk; + struct sock *selected_sk; + void *data_end; + u32 hash; + u32 reuseport_id; + bool bind_inany; +}; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); @@ -1145,4 +1283,12 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, } #endif /* CONFIG_INET */ +enum bpf_text_poke_type { + BPF_MOD_NOP_TO_CALL, + BPF_MOD_CALL_TO_CALL, + BPF_MOD_CALL_TO_NOP, +}; +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, + void *addr1, void *addr2); + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 36a9c2325176..93740b3614d7 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -2,41 +2,68 @@ /* internal file - do not include directly */ #ifdef CONFIG_NET -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act) -BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp, + struct xdp_md, struct xdp_buff) #ifdef CONFIG_CGROUP_BPF -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock, + struct bpf_sock, struct sock) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr, + struct bpf_sock_addr, struct bpf_sock_addr_kern) #endif -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local) -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg) -BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops, + struct bpf_sock_ops, struct bpf_sock_ops_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg, + struct sk_msg_md, struct sk_msg) +BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector, + struct __sk_buff, struct bpf_flow_dissector) #endif #ifdef CONFIG_BPF_EVENTS -BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) -BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) -BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) -BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) -BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) +BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe, + bpf_user_pt_regs_t, struct pt_regs) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint, + __u64, u64) +BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event, + struct bpf_perf_event_data, struct bpf_perf_event_data_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint, + struct bpf_raw_tracepoint_args, u64) +BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable, + struct bpf_raw_tracepoint_args, u64) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing, + void *, void *) #endif #ifdef CONFIG_CGROUP_BPF -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev, + struct bpf_cgroup_dev_ctx, struct bpf_cgroup_dev_ctx) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl, + struct bpf_sysctl, struct bpf_sysctl_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt, + struct bpf_sockopt, struct bpf_sockopt_kern) #endif #ifdef CONFIG_BPF_LIRC_MODE2 -BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) +BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2, + __u32, u32) #endif #ifdef CONFIG_INET -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport, + struct sk_reuseport_md, struct sk_reuseport_kern) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 26a6d58ca78c..cdd08bf0ec06 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -52,6 +52,8 @@ struct bpf_reg_state { */ struct bpf_map *map_ptr; + u32 btf_id; /* for PTR_TO_BTF_ID */ + /* Max size from any of the above. */ unsigned long raw; }; @@ -330,15 +332,18 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) #define BPF_LOG_STATS 4 #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) #define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) +#define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { - return log->level && log->ubuf && !bpf_verifier_log_full(log); + return (log->level && log->ubuf && !bpf_verifier_log_full(log)) || + log->level == BPF_LOG_KERNEL; } #define BPF_MAX_SUBPROGS 256 struct bpf_subprog_info { + /* 'start' has to be the first field otherwise find_subprog() won't work */ u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ @@ -397,6 +402,8 @@ __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); +__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, + const char *fmt, ...); static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6db2d9a6e503..b475e7f20d28 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -200,9 +200,15 @@ #define BCM5482_SHD_SSD 0x14 /* 10100: Secondary SerDes control */ #define BCM5482_SHD_SSD_LEDM 0x0008 /* SSD LED Mode enable */ #define BCM5482_SHD_SSD_EN 0x0001 /* SSD enable */ -#define BCM5482_SHD_MODE 0x1f /* 11111: Mode Control Register */ -#define BCM5482_SHD_MODE_1000BX 0x0001 /* Enable 1000BASE-X registers */ +/* 10011: SerDes 100-FX Control Register */ +#define BCM54616S_SHD_100FX_CTRL 0x13 +#define BCM54616S_100FX_MODE BIT(0) /* 100-FX SerDes Enable */ + +/* 11111: Mode Control Register */ +#define BCM54XX_SHD_MODE 0x1f +#define BCM54XX_SHD_INTF_SEL_MASK GENMASK(2, 1) /* INTERF_SEL[1:0] */ +#define BCM54XX_SHD_MODE_1000BX BIT(0) /* Enable 1000-X registers */ /* * EXPANSION SHADOW ACCESS REGISTERS. (PHY REG 0x15, 0x16, and 0x17) diff --git a/include/linux/btf.h b/include/linux/btf.h index 64cdf2a23d42..79d4abc2556a 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -5,6 +5,7 @@ #define _LINUX_BTF_H 1 #include <linux/types.h> +#include <uapi/linux/btf.h> struct btf; struct btf_member; @@ -53,9 +54,41 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); +static inline bool btf_type_is_ptr(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; +} + +static inline bool btf_type_is_int(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_INT; +} + +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_type_is_typedef(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; +} + +static inline bool btf_type_is_func(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; +} + +static inline bool btf_type_is_func_proto(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; +} + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); +struct btf *btf_parse_vmlinux(void); +struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h deleted file mode 100644 index 9e5ac27fb6c1..000000000000 --- a/include/linux/can/platform/mcp251x.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CAN_PLATFORM_MCP251X_H -#define _CAN_PLATFORM_MCP251X_H - -/* - * - * CAN bus driver for Microchip 251x CAN Controller with SPI Interface - * - */ - -#include <linux/spi/spi.h> - -/* - * struct mcp251x_platform_data - MCP251X SPI CAN controller platform data - * @oscillator_frequency: - oscillator frequency in Hz - */ - -struct mcp251x_platform_data { - unsigned long oscillator_frequency; -}; - -#endif /* !_CAN_PLATFORM_MCP251X_H */ diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 01219f2902bf..1b78a0cfb615 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -15,9 +15,9 @@ struct can_rx_offload { struct net_device *dev; - unsigned int (*mailbox_read)(struct can_rx_offload *offload, - struct can_frame *cf, - u32 *timestamp, unsigned int mb); + struct sk_buff *(*mailbox_read)(struct can_rx_offload *offload, + unsigned int mb, u32 *timestamp, + bool drop); struct sk_buff_head skb_queue; u32 skb_queue_len_max; @@ -44,7 +44,6 @@ unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int idx, u32 timestamp); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb); -void can_rx_offload_reset(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); void can_rx_offload_enable(struct can_rx_offload *offload); diff --git a/include/linux/dim.h b/include/linux/dim.h index 9fa4b3f88c39..b698266d0035 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -4,22 +4,26 @@ #ifndef DIM_H #define DIM_H +#include <linux/bits.h> +#include <linux/kernel.h> #include <linux/module.h> +#include <linux/types.h> +#include <linux/workqueue.h> -/** +/* * Number of events between DIM iterations. * Causes a moderation of the algorithm run. */ #define DIM_NEVENTS 64 -/** +/* * Is a difference between values justifies taking an action. * We consider 10% difference as significant. */ #define IS_SIGNIFICANT_DIFF(val, ref) \ (((100UL * abs((val) - (ref))) / (ref)) > 10) -/** +/* * Calculate the gap between two values. * Take wrap-around and variable size into consideration. */ @@ -27,12 +31,13 @@ & (BIT_ULL(bits) - 1)) /** - * Structure for CQ moderation values. + * struct dim_cq_moder - Structure for CQ moderation values. * Used for communications between DIM and its consumer. * * @usec: CQ timer suggestion (by DIM) * @pkts: CQ packet counter suggestion (by DIM) - * @cq_period_mode: CQ priod count mode (from CQE/EQE) + * @comps: Completion counter + * @cq_period_mode: CQ period count mode (from CQE/EQE) */ struct dim_cq_moder { u16 usec; @@ -42,13 +47,14 @@ struct dim_cq_moder { }; /** - * Structure for DIM sample data. + * struct dim_sample - Structure for DIM sample data. * Used for communications between DIM and its consumer. * * @time: Sample timestamp * @pkt_ctr: Number of packets * @byte_ctr: Number of bytes * @event_ctr: Number of events + * @comp_ctr: Current completion counter */ struct dim_sample { ktime_t time; @@ -59,12 +65,14 @@ struct dim_sample { }; /** - * Structure for DIM stats. + * struct dim_stats - Structure for DIM stats. * Used for holding current measured rates. * * @ppms: Packets per msec * @bpms: Bytes per msec * @epms: Events per msec + * @cpms: Completions per msec + * @cpe_ratio: Ratio of completions to events */ struct dim_stats { int ppms; /* packets per msec */ @@ -75,12 +83,13 @@ struct dim_stats { }; /** - * Main structure for dynamic interrupt moderation (DIM). + * struct dim - Main structure for dynamic interrupt moderation (DIM). * Used for holding all information about a specific DIM instance. * * @state: Algorithm state (see below) * @prev_stats: Measured rates from previous iteration (for comparison) * @start_sample: Sampled data at start of current iteration + * @measuring_sample: A &dim_sample that is used to update the current events * @work: Work to perform on action required * @priv: A pointer to the struct that points to dim * @profile_ix: Current moderation profile @@ -106,24 +115,21 @@ struct dim { }; /** - * enum dim_cq_period_mode - * - * These are the modes for CQ period count. + * enum dim_cq_period_mode - Modes for CQ period count * * @DIM_CQ_PERIOD_MODE_START_FROM_EQE: Start counting from EQE * @DIM_CQ_PERIOD_MODE_START_FROM_CQE: Start counting from CQE (implies timer reset) * @DIM_CQ_PERIOD_NUM_MODES: Number of modes */ -enum { +enum dim_cq_period_mode { DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, DIM_CQ_PERIOD_NUM_MODES }; /** - * enum dim_state + * enum dim_state - DIM algorithm states * - * These are the DIM algorithm states. * These will determine if the algorithm is in a valid state to start an iteration. * * @DIM_START_MEASURE: This is the first iteration (also after applying a new profile) @@ -131,16 +137,15 @@ enum { * need to perform an action * @DIM_APPLY_NEW_PROFILE: DIM consumer is currently applying a profile - no need to measure */ -enum { +enum dim_state { DIM_START_MEASURE, DIM_MEASURE_IN_PROGRESS, DIM_APPLY_NEW_PROFILE, }; /** - * enum dim_tune_state + * enum dim_tune_state - DIM algorithm tune states * - * These are the DIM algorithm tune states. * These will determine which action the algorithm should perform. * * @DIM_PARKING_ON_TOP: Algorithm found a local top point - exit on significant difference @@ -148,7 +153,7 @@ enum { * @DIM_GOING_RIGHT: Algorithm is currently trying higher moderation levels * @DIM_GOING_LEFT: Algorithm is currently trying lower moderation levels */ -enum { +enum dim_tune_state { DIM_PARKING_ON_TOP, DIM_PARKING_TIRED, DIM_GOING_RIGHT, @@ -156,25 +161,23 @@ enum { }; /** - * enum dim_stats_state + * enum dim_stats_state - DIM algorithm statistics states * - * These are the DIM algorithm statistics states. * These will determine the verdict of current iteration. * * @DIM_STATS_WORSE: Current iteration shows worse performance than before - * @DIM_STATS_WORSE: Current iteration shows same performance than before - * @DIM_STATS_WORSE: Current iteration shows better performance than before + * @DIM_STATS_SAME: Current iteration shows same performance than before + * @DIM_STATS_BETTER: Current iteration shows better performance than before */ -enum { +enum dim_stats_state { DIM_STATS_WORSE, DIM_STATS_SAME, DIM_STATS_BETTER, }; /** - * enum dim_step_result + * enum dim_step_result - DIM algorithm step results * - * These are the DIM algorithm step results. * These describe the result of a step. * * @DIM_STEPPED: Performed a regular step @@ -182,7 +185,7 @@ enum { * tired parking * @DIM_ON_EDGE: Stepped to the most left/right profile */ -enum { +enum dim_step_result { DIM_STEPPED, DIM_TOO_TIRED, DIM_ON_EDGE, @@ -199,7 +202,7 @@ enum { bool dim_on_top(struct dim *dim); /** - * dim_turn - change profile alterning direction + * dim_turn - change profile altering direction * @dim: DIM context * * Go left if we were going right and vice-versa. @@ -238,7 +241,7 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, struct dim_stats *curr_stats); /** - * dim_update_sample - set a sample's fields with give values + * dim_update_sample - set a sample's fields with given values * @event_ctr: number of events to set * @packets: number of packets to set * @bytes: number of bytes to set @@ -304,8 +307,8 @@ struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode); * @end_sample: Current data measurement * * Called by the consumer. - * This is the main logic of the algorithm, where data is processed in order to decide on next - * required action. + * This is the main logic of the algorithm, where data is processed in order + * to decide on next required action. */ void net_dim(struct dim *dim, struct dim_sample end_sample); diff --git a/include/linux/extable.h b/include/linux/extable.h index 81ecfaa83ad3..4ab9e78f313b 100644 --- a/include/linux/extable.h +++ b/include/linux/extable.h @@ -33,4 +33,14 @@ search_module_extables(unsigned long addr) } #endif /*CONFIG_MODULES*/ +#ifdef CONFIG_BPF_JIT +const struct exception_table_entry *search_bpf_extables(unsigned long addr); +#else +static inline const struct exception_table_entry * +search_bpf_extables(unsigned long addr) +{ + return NULL; +} +#endif + #endif /* _LINUX_EXTABLE_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 0367a75f873b..ad80e9c6111c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -65,6 +65,9 @@ struct ctl_table_header; /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 +/* unused opcode to mark special load instruction. Same as BPF_ABS */ +#define BPF_PROBE_MEM 0x20 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 @@ -464,10 +467,11 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) #define BPF_CALL_x(x, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ + typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ - return ____##name(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ + return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) @@ -511,10 +515,12 @@ struct sock_fprog_kern { struct sock_filter *filter; }; +/* Some arches need doubleword alignment for their instructions and/or data */ +#define BPF_IMAGE_ALIGNMENT 8 + struct bpf_binary_header { u32 pages; - /* Some arches need word alignment for their instructions */ - u8 image[] __aligned(4); + u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; struct bpf_prog { diff --git a/include/linux/firmware/broadcom/tee_bnxt_fw.h b/include/linux/firmware/broadcom/tee_bnxt_fw.h new file mode 100644 index 000000000000..f24c82d6ef73 --- /dev/null +++ b/include/linux/firmware/broadcom/tee_bnxt_fw.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: BSD-2-Clause */ +/* + * Copyright 2019 Broadcom. + */ + +#ifndef _BROADCOM_TEE_BNXT_FW_H +#define _BROADCOM_TEE_BNXT_FW_H + +#include <linux/types.h> + +int tee_bnxt_fw_load(void); +int tee_bnxt_copy_coredump(void *buf, u32 offset, u32 size); + +#endif /* _BROADCOM_TEE_BNXT_FW_H */ diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 975553a9f75d..54d9436600c7 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -403,6 +403,8 @@ int __must_check fsl_mc_allocate_irqs(struct fsl_mc_device *mc_dev); void fsl_mc_free_irqs(struct fsl_mc_device *mc_dev); +struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev); + extern struct bus_type fsl_mc_bus_type; extern struct device_type fsl_mc_bus_dprc_type; diff --git a/include/linux/icmp.h b/include/linux/icmp.h index 2d8aaf7d4b9e..81ca84ce3119 100644 --- a/include/linux/icmp.h +++ b/include/linux/icmp.h @@ -20,4 +20,19 @@ static inline struct icmphdr *icmp_hdr(const struct sk_buff *skb) { return (struct icmphdr *)skb_transport_header(skb); } + +static inline bool icmp_is_err(int type) +{ + switch (type) { + case ICMP_DEST_UNREACH: + case ICMP_SOURCE_QUENCH: + case ICMP_REDIRECT: + case ICMP_TIME_EXCEEDED: + case ICMP_PARAMETERPROB: + return true; + } + + return false; +} + #endif /* _LINUX_ICMP_H */ diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index a8f888976137..ef1cbb5f454f 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -46,4 +46,18 @@ extern void icmpv6_flow_init(struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif); + +static inline bool icmpv6_is_err(int type) +{ + switch (type) { + case ICMPV6_DEST_UNREACH: + case ICMPV6_PKT_TOOBIG: + case ICMPV6_TIME_EXCEED: + case ICMPV6_PARAMPROB: + return true; + } + + return false; +} + #endif diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index a99c58866860..fe740031339d 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -82,4 +82,10 @@ static inline int linkmode_equal(const unsigned long *src1, return bitmap_equal(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } +static inline int linkmode_subset(const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_subset(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + #endif /* __LINKMODE_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3e80f03a387f..1884513aac90 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1121,6 +1121,11 @@ static inline bool mlx5_core_is_pf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_PF; } +static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) +{ + return dev->coredev_type == MLX5_COREDEV_VF; +} + static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; @@ -1186,4 +1191,15 @@ enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; +static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(dev); + union devlink_param_value val; + + devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + &val); + return val.vbool; +} + #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 724d276ea133..4e5b84e66822 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -80,7 +80,8 @@ enum mlx5_flow_namespace_type { enum { FDB_BYPASS_PATH, - FDB_FAST_PATH, + FDB_TC_OFFLOAD, + FDB_FT_OFFLOAD, FDB_SLOW_PATH, }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 0836fe232f97..4f912d4e67bc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1153,7 +1153,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_srq[0x5]; u8 reserved_at_b0[0x10]; - u8 reserved_at_c0[0x8]; + u8 max_sgl_for_optimized_performance[0x8]; u8 log_max_cq_sz[0x8]; u8 reserved_at_d0[0xb]; u8 log_max_cq[0x5]; diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 34de06b426ef..8071148f29a6 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -47,16 +47,16 @@ struct vif_entry_notifier_info { }; static inline int mr_call_vif_notifier(struct notifier_block *nb, - struct net *net, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, - unsigned short vif_index, u32 tb_id) + unsigned short vif_index, u32 tb_id, + struct netlink_ext_ack *extack) { struct vif_entry_notifier_info info = { .info = { .family = family, - .net = net, + .extack = extack, }, .dev = vif->dev, .vif_index = vif_index, @@ -64,7 +64,7 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, .tb_id = tb_id, }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_vif_notifiers(struct net *net, @@ -77,7 +77,6 @@ static inline int mr_call_vif_notifiers(struct net *net, struct vif_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .dev = vif->dev, .vif_index = vif_index, @@ -173,21 +172,21 @@ struct mfc_entry_notifier_info { }; static inline int mr_call_mfc_notifier(struct notifier_block *nb, - struct net *net, unsigned short family, enum fib_event_type event_type, - struct mr_mfc *mfc, u32 tb_id) + struct mr_mfc *mfc, u32 tb_id, + struct netlink_ext_ack *extack) { struct mfc_entry_notifier_info info = { .info = { .family = family, - .net = net, + .extack = extack, }, .mfc = mfc, .tb_id = tb_id }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_mfc_notifiers(struct net *net, @@ -199,7 +198,6 @@ static inline int mr_call_mfc_notifiers(struct net *net, struct mfc_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .mfc = mfc, .tb_id = tb_id @@ -301,10 +299,11 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + 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); + rwlock_t *mrt_lock, struct netlink_ext_ack *extack); #else static inline void vif_device_init(struct vif_device *v, struct net_device *dev, @@ -355,10 +354,11 @@ mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, static inline int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + 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) + rwlock_t *mrt_lock, struct netlink_ext_ack *extack) { return -EINVAL; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c20f190b4c18..9e6fb8524d91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -848,6 +848,7 @@ enum tc_setup_type { TC_SETUP_ROOT_QDISC, TC_SETUP_QDISC_GRED, TC_SETUP_QDISC_TAPRIO, + TC_SETUP_FT, }; /* These structures hold the attributes of bpf state that are being passed @@ -925,6 +926,15 @@ struct dev_ifalias { struct devlink; struct tlsdev_ops; +struct netdev_name_node { + struct hlist_node hlist; + struct list_head list; + struct net_device *dev; + const char *name; +}; + +int netdev_name_node_alt_create(struct net_device *dev, const char *name); +int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); /* * This structure defines the management hooks for network devices. @@ -1564,7 +1574,7 @@ enum netdev_priv_flags { * (i.e. as seen by users in the "Space.c" file). It is the name * of the interface. * - * @name_hlist: Device name hash chain, please keep it close to name[] + * @name_node: Name hashlist node * @ifalias: SNMP alias * @mem_end: Shared memory end * @mem_start: Shared memory start @@ -1780,7 +1790,7 @@ enum netdev_priv_flags { struct net_device { char name[IFNAMSIZ]; - struct hlist_node name_hlist; + struct netdev_name_node *name_node; struct dev_ifalias __rcu *ifalias; /* * I/O specific fields @@ -2387,11 +2397,23 @@ struct pcpu_sw_netstats { } __aligned(4 * sizeof(u64)); struct pcpu_lstats { - u64 packets; - u64 bytes; + u64_stats_t packets; + u64_stats_t bytes; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); +void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes); + +static inline void dev_lstats_add(struct net_device *dev, unsigned int len) +{ + struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); + + u64_stats_update_begin(&lstats->syncp); + u64_stats_add(&lstats->bytes, len); + u64_stats_inc(&lstats->packets); + u64_stats_update_end(&lstats->syncp); +} + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ @@ -2487,6 +2509,9 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd); int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); +int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); +int unregister_netdevice_notifier_net(struct net *net, + struct notifier_block *nb); struct netdev_notifier_info { struct net_device *dev; @@ -2557,6 +2582,9 @@ extern rwlock_t dev_base_lock; /* Device list lock */ list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue(net, d) \ list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list) +#define for_each_netdev_continue_reverse(net, d) \ + list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \ + dev_list) #define for_each_netdev_continue_rcu(net, d) \ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_in_bond_rcu(bond, slave) \ @@ -4081,9 +4109,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs); -int dev_get_valid_name(struct net *net, struct net_device *dev, - const char *name); - #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 77ebb61faf48..eb312e7ca36e 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -199,6 +199,8 @@ extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int i); +void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, + const struct nf_hook_entries *e); /** * nf_hook - call a netfilter hook * @@ -311,17 +313,36 @@ NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct list_head *head, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - struct sk_buff *skb, *next; - struct list_head sublist; - - INIT_LIST_HEAD(&sublist); - list_for_each_entry_safe(skb, next, head, list) { - list_del(&skb->list); - if (nf_hook(pf, hook, net, sk, skb, in, out, okfn) == 1) - list_add_tail(&skb->list, &sublist); + struct nf_hook_entries *hook_head = NULL; + +#ifdef CONFIG_JUMP_LABEL + if (__builtin_constant_p(pf) && + __builtin_constant_p(hook) && + !static_key_false(&nf_hooks_needed[pf][hook])) + return; +#endif + + rcu_read_lock(); + switch (pf) { + case NFPROTO_IPV4: + hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); + break; + case NFPROTO_IPV6: + hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); + break; + default: + WARN_ON_ONCE(1); + break; } - /* Put passed packets back on main list */ - list_splice(&sublist, head); + + if (hook_head) { + struct nf_hook_state state; + + nf_hook_state_init(&state, hook, pf, in, out, sk, net, okfn); + + nf_hook_slow_list(head, &state, hook_head); + } + rcu_read_unlock(); } /* Call setsockopt() */ diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 9bc255a8461b..4d8b1eaf7708 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -269,34 +269,15 @@ ip_set_ext_destroy(struct ip_set *set, void *data) /* Check that the extension is enabled for the set and * call it's destroy function for its extension part in data. */ - if (SET_WITH_COMMENT(set)) - ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy( - set, ext_comment(data, set)); -} + if (SET_WITH_COMMENT(set)) { + struct ip_set_comment *c = ext_comment(data, set); -static inline int -ip_set_put_flags(struct sk_buff *skb, struct ip_set *set) -{ - u32 cadt_flags = 0; - - if (SET_WITH_TIMEOUT(set)) - if (unlikely(nla_put_net32(skb, IPSET_ATTR_TIMEOUT, - htonl(set->timeout)))) - return -EMSGSIZE; - if (SET_WITH_COUNTER(set)) - cadt_flags |= IPSET_FLAG_WITH_COUNTERS; - if (SET_WITH_COMMENT(set)) - cadt_flags |= IPSET_FLAG_WITH_COMMENT; - if (SET_WITH_SKBINFO(set)) - cadt_flags |= IPSET_FLAG_WITH_SKBINFO; - if (SET_WITH_FORCEADD(set)) - cadt_flags |= IPSET_FLAG_WITH_FORCEADD; - - if (!cadt_flags) - return 0; - return nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(cadt_flags)); + ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy(set, c); + } } +int ip_set_put_flags(struct sk_buff *skb, struct ip_set *set); + /* Netlink CB args */ enum { IPSET_CB_NET = 0, /* net namespace */ @@ -506,144 +487,8 @@ ip_set_timeout_set(unsigned long *timeout, u32 value) *timeout = t; } -static inline u32 -ip_set_timeout_get(const unsigned long *timeout) -{ - u32 t; - - if (*timeout == IPSET_ELEM_PERMANENT) - return 0; - - t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; - /* Zero value in userspace means no timeout */ - return t == 0 ? 1 : t; -} - -static inline char* -ip_set_comment_uget(struct nlattr *tb) -{ - return nla_data(tb); -} - -/* Called from uadd only, protected by the set spinlock. - * The kadt functions don't use the comment extensions in any way. - */ -static inline void -ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, - const struct ip_set_ext *ext) -{ - struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); - size_t len = ext->comment ? strlen(ext->comment) : 0; - - if (unlikely(c)) { - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; - kfree_rcu(c, rcu); - rcu_assign_pointer(comment->c, NULL); - } - if (!len) - return; - if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) - len = IPSET_MAX_COMMENT_SIZE; - c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC); - if (unlikely(!c)) - return; - strlcpy(c->str, ext->comment, len + 1); - set->ext_size += sizeof(*c) + strlen(c->str) + 1; - rcu_assign_pointer(comment->c, c); -} - -/* Used only when dumping a set, protected by rcu_read_lock() */ -static inline int -ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) -{ - struct ip_set_comment_rcu *c = rcu_dereference(comment->c); - - if (!c) - return 0; - return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str); -} - -/* Called from uadd/udel, flush or the garbage collectors protected - * by the set spinlock. - * Called when the set is destroyed and when there can't be any user - * of the set data anymore. - */ -static inline void -ip_set_comment_free(struct ip_set *set, struct ip_set_comment *comment) -{ - struct ip_set_comment_rcu *c; - - c = rcu_dereference_protected(comment->c, 1); - if (unlikely(!c)) - return; - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; - kfree_rcu(c, rcu); - rcu_assign_pointer(comment->c, NULL); -} - -static inline void -ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) -{ - atomic64_add((long long)bytes, &(counter)->bytes); -} - -static inline void -ip_set_add_packets(u64 packets, struct ip_set_counter *counter) -{ - atomic64_add((long long)packets, &(counter)->packets); -} - -static inline u64 -ip_set_get_bytes(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->bytes); -} - -static inline u64 -ip_set_get_packets(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->packets); -} - -static inline bool -ip_set_match_counter(u64 counter, u64 match, u8 op) -{ - switch (op) { - case IPSET_COUNTER_NONE: - return true; - case IPSET_COUNTER_EQ: - return counter == match; - case IPSET_COUNTER_NE: - return counter != match; - case IPSET_COUNTER_LT: - return counter < match; - case IPSET_COUNTER_GT: - return counter > match; - } - return false; -} - -static inline void -ip_set_update_counter(struct ip_set_counter *counter, - const struct ip_set_ext *ext, u32 flags) -{ - if (ext->packets != ULLONG_MAX && - !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { - ip_set_add_bytes(ext->bytes, counter); - ip_set_add_packets(ext->packets, counter); - } -} - -static inline bool -ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) -{ - return nla_put_net64(skb, IPSET_ATTR_BYTES, - cpu_to_be64(ip_set_get_bytes(counter)), - IPSET_ATTR_PAD) || - nla_put_net64(skb, IPSET_ATTR_PACKETS, - cpu_to_be64(ip_set_get_packets(counter)), - IPSET_ATTR_PAD); -} +void ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, + const struct ip_set_ext *ext); static inline void ip_set_init_counter(struct ip_set_counter *counter, @@ -656,31 +501,6 @@ ip_set_init_counter(struct ip_set_counter *counter, } static inline void -ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, - const struct ip_set_ext *ext, - struct ip_set_ext *mext, u32 flags) -{ - mext->skbinfo = *skbinfo; -} - -static inline bool -ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) -{ - /* Send nonzero parameters only */ - return ((skbinfo->skbmark || skbinfo->skbmarkmask) && - nla_put_net64(skb, IPSET_ATTR_SKBMARK, - cpu_to_be64((u64)skbinfo->skbmark << 32 | - skbinfo->skbmarkmask), - IPSET_ATTR_PAD)) || - (skbinfo->skbprio && - nla_put_net32(skb, IPSET_ATTR_SKBPRIO, - cpu_to_be32(skbinfo->skbprio))) || - (skbinfo->skbqueue && - nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, - cpu_to_be16(skbinfo->skbqueue))); -} - -static inline void ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, const struct ip_set_ext *ext) { diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h index 2dddbc6dcac7..fcc4d214a788 100644 --- a/include/linux/netfilter/ipset/ip_set_bitmap.h +++ b/include/linux/netfilter/ipset/ip_set_bitmap.h @@ -12,18 +12,4 @@ enum { IPSET_ADD_START_STORED_TIMEOUT, }; -/* Common functions */ - -static inline u32 -range_to_mask(u32 from, u32 to, u8 *bits) -{ - u32 mask = 0xFFFFFFFE; - - *bits = 32; - while (--(*bits) > 0 && mask && (to & mask) != from) - mask <<= 1; - - return mask; -} - #endif /* __IP_SET_BITMAP_H */ diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h index d74cd112b88a..1ecaabd9a048 100644 --- a/include/linux/netfilter/ipset/ip_set_getport.h +++ b/include/linux/netfilter/ipset/ip_set_getport.h @@ -20,9 +20,6 @@ static inline bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src, } #endif -extern bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, - __be16 *port); - static inline bool ip_set_proto_with_ports(u8 proto) { switch (proto) { diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 6aeaea1775e6..71bbfcf3adcd 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -6,15 +6,18 @@ #ifndef __LINUX_OF_NET_H #define __LINUX_OF_NET_H +#include <linux/phy.h> + #ifdef CONFIG_OF_NET #include <linux/of.h> struct net_device; -extern int of_get_phy_mode(struct device_node *np); +extern int of_get_phy_mode(struct device_node *np, phy_interface_t *interface); extern const void *of_get_mac_address(struct device_node *np); extern struct net_device *of_find_net_device_by_node(struct device_node *np); #else -static inline int of_get_phy_mode(struct device_node *np) +static inline int of_get_phy_mode(struct device_node *np, + phy_interface_t *interface) { return -ENODEV; } diff --git a/include/linux/phy.h b/include/linux/phy.h index 9a0e981df502..124516fe2763 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -203,6 +203,8 @@ static inline const char *phy_modes(phy_interface_t interface) struct device; struct phylink; +struct sfp_bus; +struct sfp_upstream_ops; struct sk_buff; /* @@ -342,6 +344,8 @@ struct phy_c45_device_ids { * dev_flags: Device-specific flags used by the PHY driver. * irq: IRQ number of the PHY's interrupt (-1 if none) * phy_timer: The timer for handling the state machine + * sfp_bus_attached: flag indicating whether the SFP bus has been attached + * sfp_bus: SFP bus attached to this PHY's fiber port * attached_dev: The attached enet driver's device instance ptr * adjust_link: Callback for the enet controller to respond to * changes in the link state. @@ -432,6 +436,9 @@ struct phy_device { struct mutex lock; + /* This may be modified under the rtnl lock */ + bool sfp_bus_attached; + struct sfp_bus *sfp_bus; struct phylink *phylink; struct net_device *attached_dev; @@ -1020,6 +1027,10 @@ int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); +void phy_sfp_attach(void *upstream, struct sfp_bus *bus); +void phy_sfp_detach(void *upstream, struct sfp_bus *bus); +int phy_sfp_probe(struct phy_device *phydev, + const struct sfp_upstream_ops *ops); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); @@ -1106,6 +1117,10 @@ int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, u16 regnum, u16 val); +/* Clause 37 */ +int genphy_c37_config_aneg(struct phy_device *phydev); +int genphy_c37_read_status(struct phy_device *phydev); + /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart); diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 1c35428e98bc..487fd9412d10 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -428,6 +428,10 @@ enum { SFP_TEC_CUR = 0x6c, SFP_STATUS = 0x6e, + SFP_STATUS_TX_DISABLE = BIT(7), + SFP_STATUS_TX_DISABLE_FORCE = BIT(6), + SFP_STATUS_TX_FAULT = BIT(2), + SFP_STATUS_RX_LOS = BIT(1), SFP_ALARM0 = 0x70, SFP_ALARM0_TEMP_HIGH = BIT(7), SFP_ALARM0_TEMP_LOW = BIT(6), @@ -508,10 +512,11 @@ int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, u8 *data); void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); -struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode, - void *upstream, - const struct sfp_upstream_ops *ops); -void sfp_unregister_upstream(struct sfp_bus *bus); +void sfp_bus_put(struct sfp_bus *bus); +struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode); +int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, + const struct sfp_upstream_ops *ops); +void sfp_bus_del_upstream(struct sfp_bus *bus); #else static inline int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, @@ -553,14 +558,22 @@ static inline void sfp_upstream_stop(struct sfp_bus *bus) { } -static inline struct sfp_bus *sfp_register_upstream( - struct fwnode_handle *fwnode, void *upstream, - const struct sfp_upstream_ops *ops) +static inline void sfp_bus_put(struct sfp_bus *bus) { - return (struct sfp_bus *)-1; } -static inline void sfp_unregister_upstream(struct sfp_bus *bus) +static inline struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, + const struct sfp_upstream_ops *ops) +{ + return 0; +} + +static inline void sfp_bus_del_upstream(struct sfp_bus *bus) { } #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8688f7adfda7..eceb3607864b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1795,7 +1795,7 @@ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { - struct sk_buff *skb = list_->prev; + struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; @@ -1861,7 +1861,9 @@ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { - /* see skb_queue_empty_lockless() for the opposite READ_ONCE() */ + /* See skb_queue_empty_lockless() and skb_peek_tail() + * for the opposite READ_ONCE() + */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(next->prev, newsk); @@ -2277,12 +2279,12 @@ static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len); } -static inline int pskb_may_pull(struct sk_buff *skb, unsigned int len) +static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { if (likely(len <= skb_headlen(skb))) - return 1; + return true; if (unlikely(len > skb->len)) - return 0; + return false; return __pskb_pull_tail(skb, len - skb_headlen(skb)) != NULL; } diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index ce7055259877..6cb077b646a5 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -28,13 +28,14 @@ struct sk_msg_sg { u32 end; u32 size; u32 copybreak; - bool copy[MAX_MSG_FRAGS]; + unsigned long copy; /* The extra element is used for chaining the front and sections when * the list becomes partitioned (e.g. end < start). The crypto APIs * require the chaining. */ struct scatterlist data[MAX_MSG_FRAGS + 1]; }; +static_assert(BITS_PER_LONG >= MAX_MSG_FRAGS); /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { @@ -230,7 +231,7 @@ static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); - if (msg->sg.copy[msg->sg.start]) { + if (test_bit(msg->sg.start, &msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { @@ -249,7 +250,7 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sg_set_page(sge, page, len, offset); sg_unmark_end(sge); - msg->sg.copy[msg->sg.end] = true; + __set_bit(msg->sg.end, &msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } @@ -257,7 +258,10 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { - msg->sg.copy[i] = copy_state; + if (copy_state) + __set_bit(i, &msg->sg.copy); + else + __clear_bit(i, &msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index af4f265d0f67..27f6b046cf92 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -13,6 +13,7 @@ #include <linux/completion.h> #include <linux/scatterlist.h> #include <linux/gpio/consumer.h> +#include <linux/ptp_clock_kernel.h> struct dma_chan; struct property_entry; @@ -409,6 +410,12 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @fw_translate_cs: If the boot firmware uses different numbering scheme * what Linux expects, this optional hook can be used to translate * between the two. + * @ptp_sts_supported: If the driver sets this to true, it must provide a + * time snapshot in @spi_transfer->ptp_sts as close as possible to the + * moment in time when @spi_transfer->ptp_sts_word_pre and + * @spi_transfer->ptp_sts_word_post were transmitted. + * If the driver does not set this, the SPI core takes the snapshot as + * close to the driver hand-over as possible. * * Each SPI controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals @@ -604,6 +611,15 @@ struct spi_controller { void *dummy_tx; int (*fw_translate_cs)(struct spi_controller *ctlr, unsigned cs); + + /* + * Driver sets this field to indicate it is able to snapshot SPI + * transfers (needed e.g. for reading the time of POSIX clocks) + */ + bool ptp_sts_supported; + + /* Interrupt enable state during PTP system timestamping */ + unsigned long irq_flags; }; static inline void *spi_controller_get_devdata(struct spi_controller *ctlr) @@ -644,6 +660,14 @@ extern struct spi_message *spi_get_next_queued_message(struct spi_controller *ct extern void spi_finalize_current_message(struct spi_controller *ctlr); extern void spi_finalize_current_transfer(struct spi_controller *ctlr); +/* Helper calls for driver to timestamp transfer */ +void spi_take_timestamp_pre(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off); +void spi_take_timestamp_post(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off); + /* the spi driver core manages memory for the spi_controller classdev */ extern struct spi_controller *__spi_alloc_controller(struct device *host, unsigned int size, bool slave); @@ -753,6 +777,35 @@ extern void spi_res_release(struct spi_controller *ctlr, * @transfer_list: transfers are sequenced through @spi_message.transfers * @tx_sg: Scatterlist for transmit, currently not for client use * @rx_sg: Scatterlist for receive, currently not for client use + * @ptp_sts_word_pre: The word (subject to bits_per_word semantics) offset + * within @tx_buf for which the SPI device is requesting that the time + * snapshot for this transfer begins. Upon completing the SPI transfer, + * this value may have changed compared to what was requested, depending + * on the available snapshotting resolution (DMA transfer, + * @ptp_sts_supported is false, etc). + * @ptp_sts_word_post: See @ptp_sts_word_post. The two can be equal (meaning + * that a single byte should be snapshotted). + * If the core takes care of the timestamp (if @ptp_sts_supported is false + * for this controller), it will set @ptp_sts_word_pre to 0, and + * @ptp_sts_word_post to the length of the transfer. This is done + * purposefully (instead of setting to spi_transfer->len - 1) to denote + * that a transfer-level snapshot taken from within the driver may still + * be of higher quality. + * @ptp_sts: Pointer to a memory location held by the SPI slave device where a + * PTP system timestamp structure may lie. If drivers use PIO or their + * hardware has some sort of assist for retrieving exact transfer timing, + * they can (and should) assert @ptp_sts_supported and populate this + * structure using the ptp_read_system_*ts helper functions. + * The timestamp must represent the time at which the SPI slave device has + * processed the word, i.e. the "pre" timestamp should be taken before + * transmitting the "pre" word, and the "post" timestamp after receiving + * transmit confirmation from the controller for the "post" word. + * @timestamped_pre: Set by the SPI controller driver to denote it has acted + * upon the @ptp_sts request. Not set when the SPI core has taken care of + * the task. SPI device drivers are free to print a warning if this comes + * back unset and they need the better resolution. + * @timestamped_post: See above. The reason why both exist is that these + * booleans are also used to keep state in the core SPI logic. * * SPI transfers always write the same number of bytes as they read. * Protocol drivers should always provide @rx_buf and/or @tx_buf. @@ -842,6 +895,14 @@ struct spi_transfer { u32 effective_speed_hz; + unsigned int ptp_sts_word_pre; + unsigned int ptp_sts_word_post; + + struct ptp_system_timestamp *ptp_sts; + + bool timestamped_pre; + bool timestamped_post; + struct list_head transfer_list; }; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dc60d03c4b60..d4bcd9387136 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -13,6 +13,7 @@ #define __STMMAC_PLATFORM_DATA #include <linux/platform_device.h> +#include <linux/phy.h> #define MTL_MAX_RX_QUEUES 8 #define MTL_MAX_TX_QUEUES 8 @@ -92,6 +93,7 @@ struct stmmac_dma_cfg { int fixed_burst; int mixed_burst; bool aal; + bool eame; }; #define AXI_BLEN 7 @@ -131,7 +133,7 @@ struct plat_stmmacenet_data { int bus_id; int phy_addr; int interface; - int phy_interface; + phy_interface_t phy_interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; struct device_node *phylink_node; diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h index 267369110584..85ec745767bd 100644 --- a/include/linux/sxgbe_platform.h +++ b/include/linux/sxgbe_platform.h @@ -10,6 +10,8 @@ #ifndef __SXGBE_PLATFORM_H__ #define __SXGBE_PLATFORM_H__ +#include <linux/phy.h> + /* MDC Clock Selection define*/ #define SXGBE_CSR_100_150M 0x0 /* MDC = clk_scr_i/62 */ #define SXGBE_CSR_150_250M 0x1 /* MDC = clk_scr_i/102 */ @@ -38,7 +40,7 @@ struct sxgbe_plat_data { char *phy_bus_name; int bus_id; int phy_addr; - int interface; + phy_interface_t interface; struct sxgbe_mdio_bus_data *mdio_bus_data; struct sxgbe_dma_cfg *dma_cfg; int clk_csr; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 668e25a76d69..ca6f01531e64 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -223,7 +223,7 @@ struct tcp_sock { fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ - unused:2; + fastopen_client_fail:2; /* reason why fastopen failed */ u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index a27604f99ed0..9de5c10293f5 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -40,8 +40,8 @@ * spin_lock_bh(...) or other synchronization to get exclusive access * ... * u64_stats_update_begin(&stats->syncp); - * stats->bytes64 += len; // non atomic operation - * stats->packets64++; // non atomic operation + * u64_stats_add(&stats->bytes64, len); // non atomic operation + * u64_stats_inc(&stats->packets64); // non atomic operation * u64_stats_update_end(&stats->syncp); * * While a consumer (reader) should use following template to get consistent @@ -52,8 +52,8 @@ * * do { * start = u64_stats_fetch_begin(&stats->syncp); - * tbytes = stats->bytes64; // non atomic operation - * tpackets = stats->packets64; // non atomic operation + * tbytes = u64_stats_read(&stats->bytes64); // non atomic operation + * tpackets = u64_stats_read(&stats->packets64); // non atomic operation * } while (u64_stats_fetch_retry(&stats->syncp, start)); * * @@ -68,6 +68,49 @@ struct u64_stats_sync { #endif }; +#if BITS_PER_LONG == 64 +#include <asm/local64.h> + +typedef struct { + local64_t v; +} u64_stats_t ; + +static inline u64 u64_stats_read(const u64_stats_t *p) +{ + return local64_read(&p->v); +} + +static inline void u64_stats_add(u64_stats_t *p, unsigned long val) +{ + local64_add(val, &p->v); +} + +static inline void u64_stats_inc(u64_stats_t *p) +{ + local64_inc(&p->v); +} + +#else + +typedef struct { + u64 v; +} u64_stats_t; + +static inline u64 u64_stats_read(const u64_stats_t *p) +{ + return p->v; +} + +static inline void u64_stats_add(u64_stats_t *p, unsigned long val) +{ + p->v += val; +} + +static inline void u64_stats_inc(u64_stats_t *p) +{ + p->v++; +} +#endif static inline void u64_stats_init(struct u64_stats_sync *syncp) { diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index d4ee6e942562..67f016010aad 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -311,6 +311,7 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, * happens, handle that and return -EFAULT. */ extern long probe_kernel_read(void *dst, const void *src, size_t size); +extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); extern long __probe_kernel_read(void *dst, const void *src, size_t size); /* @@ -337,7 +338,22 @@ extern long __probe_user_read(void *dst, const void __user *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); +/* + * probe_user_write(): safely attempt to write to a location in user space + * @dst: address to write to + * @src: pointer to the data that shall be written + * @size: size of the data chunk + * + * Safely write to address @dst from the buffer at @src. If a kernel fault + * happens, handle that and return -EFAULT. + */ +extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); +extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size); + extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); +extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, + long count); +extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, long count); extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 07875ccc7bb5..71c81e0dc8f2 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -7,9 +7,6 @@ #include <net/sock.h> #include <net/af_vsock.h> -#define VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE 128 -#define VIRTIO_VSOCK_DEFAULT_BUF_SIZE (1024 * 256) -#define VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE (1024 * 256) #define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE (1024 * 4) #define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL #define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64) @@ -25,11 +22,6 @@ enum { struct virtio_vsock_sock { struct vsock_sock *vsk; - /* Protected by lock_sock(sk_vsock(trans->vsk)) */ - u32 buf_size; - u32 buf_size_min; - u32 buf_size_max; - spinlock_t tx_lock; spinlock_t rx_lock; @@ -92,12 +84,6 @@ s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); -u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk); -u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk); -u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk); -void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val); -void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val); -void virtio_transport_set_max_buffer_size(struct vsock_sock *vs, u64 val); int virtio_transport_notify_poll_in(struct vsock_sock *vsk, size_t target, @@ -124,6 +110,7 @@ int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, struct vsock_transport_send_notify_data *data); int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written, struct vsock_transport_send_notify_data *data); +void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val); u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk); bool virtio_transport_stream_is_active(struct vsock_sock *vsk); @@ -150,7 +137,8 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk, void virtio_transport_destruct(struct vsock_sock *vsk); -void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt); +void virtio_transport_recv_pkt(struct virtio_transport *t, + struct virtio_vsock_pkt *pkt); void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt); void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt); u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); diff --git a/include/linux/vm_sockets.h b/include/linux/vm_sockets.h deleted file mode 100644 index 33f1a2ecd905..000000000000 --- a/include/linux/vm_sockets.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * VMware vSockets Driver - * - * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. - */ - -#ifndef _VM_SOCKETS_H -#define _VM_SOCKETS_H - -#include <uapi/linux/vm_sockets.h> - -int vm_sockets_get_local_cid(void); - -#endif /* _VM_SOCKETS_H */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 4e7809408073..b4c58a191eb1 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -93,6 +93,7 @@ extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); extern void *vzalloc_node(unsigned long size, int node); +extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h index acd9fafe4fc6..f28907345c80 100644 --- a/include/linux/vmw_vmci_api.h +++ b/include/linux/vmw_vmci_api.h @@ -19,6 +19,7 @@ struct msghdr; typedef void (vmci_device_shutdown_fn) (void *device_registration, void *user_data); +typedef void (*vmci_vsock_cb) (bool is_host); int vmci_datagram_create_handle(u32 resource_id, u32 flags, vmci_datagram_recv_cb recv_cb, @@ -37,6 +38,7 @@ int vmci_doorbell_destroy(struct vmci_handle handle); int vmci_doorbell_notify(struct vmci_handle handle, u32 priv_flags); u32 vmci_get_context_id(void); bool vmci_is_context_owner(u32 context_id, kuid_t uid); +int vmci_register_vsock_callback(vmci_vsock_cb callback); int vmci_event_subscribe(u32 event, vmci_event_cb callback, void *callback_data, |