diff options
Diffstat (limited to 'include/linux')
43 files changed, 1663 insertions, 169 deletions
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 2b038442c352..3ce61342fa31 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -135,6 +135,7 @@ enum virtchnl_ops { VIRTCHNL_OP_SET_RSS_HENA = 26, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28, + VIRTCHNL_OP_REQUEST_QUEUES = 29, }; /* This macro is used to generate a compilation error if a structure @@ -235,6 +236,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 #define VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 #define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 +#define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES 0x00000040 #define VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 #define VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 #define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 @@ -325,6 +327,21 @@ struct virtchnl_vsi_queue_config_info { struct virtchnl_queue_pair_info qpair[1]; }; +/* VIRTCHNL_OP_REQUEST_QUEUES + * VF sends this message to request the PF to allocate additional queues to + * this VF. Each VF gets a guaranteed number of queues on init but asking for + * additional queues must be negotiated. This is a best effort request as it + * is possible the PF does not have enough queues left to support the request. + * If the PF cannot support the number requested it will respond with the + * maximum number it is able to support. If the request is successful, PF will + * then reset the VF to institute required changes. + */ + +/* VF resource request */ +struct virtchnl_vf_res_request { + u16 num_queue_pairs; +}; + VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); /* VIRTCHNL_OP_CONFIG_IRQ_MAP @@ -691,6 +708,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: break; + case VIRTCHNL_OP_REQUEST_QUEUES: + valid_len = sizeof(struct virtchnl_vf_res_request); + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 44dfae288fcf..a7f16e0f8d68 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -15,27 +15,46 @@ struct bpf_sock_ops_kern; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +struct bpf_prog_list { + struct list_head node; + struct bpf_prog *prog; +}; + +struct bpf_prog_array; + struct cgroup_bpf { - /* - * Store two sets of bpf_prog pointers, one for programs that are - * pinned directly to this cgroup, and one for those that are effective - * when this cgroup is accessed. + /* array of effective progs in this cgroup */ + struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE]; + + /* attached progs to this cgroup and attach flags + * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will + * have either zero or one element + * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS */ - struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE]; - struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE]; - bool disallow_override[MAX_BPF_ATTACH_TYPE]; + struct list_head progs[MAX_BPF_ATTACH_TYPE]; + u32 flags[MAX_BPF_ATTACH_TYPE]; + + /* temp storage for effective prog array used by prog_attach/detach */ + struct bpf_prog_array __rcu *inactive; }; void cgroup_bpf_put(struct cgroup *cgrp); -void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent); - -int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, - struct bpf_prog *prog, enum bpf_attach_type type, - bool overridable); - -/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */ -int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, bool overridable); +int cgroup_bpf_inherit(struct cgroup *cgrp); + +int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr); + +/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ +int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, @@ -48,6 +67,9 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, enum bpf_attach_type type); +int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, + short access, enum bpf_attach_type type); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -93,17 +115,28 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, } \ __ret; \ }) + +#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_check_dev_permission(type, major, minor, \ + access, \ + BPF_CGROUP_DEVICE); \ + \ + __ret; \ +}) #else struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} -static inline void cgroup_bpf_inherit(struct cgroup *cgrp, - struct cgroup *parent) {} +static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) #endif /* CONFIG_CGROUP_BPF */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f1af7d63d678..c397934f91dd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -15,6 +15,7 @@ #include <linux/err.h> #include <linux/rbtree_latch.h> #include <linux/numa.h> +#include <linux/wait.h> struct perf_event; struct bpf_prog; @@ -56,6 +57,10 @@ struct bpf_map { struct work_struct work; atomic_t usercnt; struct bpf_map *inner_map_meta; + char name[BPF_OBJ_NAME_LEN]; +#ifdef CONFIG_SECURITY + void *security; +#endif }; /* function argument constraints */ @@ -137,6 +142,7 @@ enum bpf_reg_type { PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ PTR_TO_STACK, /* reg == frame_pointer + offset */ + PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ }; @@ -155,6 +161,11 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +struct bpf_prog_ops { + int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +}; + struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); @@ -170,8 +181,16 @@ struct bpf_verifier_ops { const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); - int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, - union bpf_attr __user *uattr); +}; + +struct bpf_dev_offload { + struct bpf_prog *prog; + struct net_device *netdev; + void *dev_priv; + struct list_head offloads; + bool dev_state; + bool verifier_running; + wait_queue_head_t verifier_done; }; struct bpf_prog_aux { @@ -182,10 +201,16 @@ struct bpf_prog_aux { u32 id; struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; - const struct bpf_verifier_ops *ops; + const struct bpf_prog_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; struct user_struct *user; + u64 load_time; /* ns since boottime */ + char name[BPF_OBJ_NAME_LEN]; +#ifdef CONFIG_SECURITY + void *security; +#endif + struct bpf_dev_offload *offload; union { struct work_struct work; struct rcu_head rcu; @@ -218,9 +243,6 @@ struct bpf_event_entry { struct rcu_head rcu; }; -u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); -u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); - bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); @@ -237,19 +259,84 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +/* an array of programs to be executed under rcu_lock. + * + * Typical usage: + * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN); + * + * the structure returned by bpf_prog_array_alloc() should be populated + * with program pointers and the last pointer must be NULL. + * The user has to keep refcnt on the program and make sure the program + * is removed from the array before bpf_prog_put(). + * The 'struct bpf_prog_array *' should only be replaced with xchg() + * since other cpus are walking the array of pointers in parallel. + */ +struct bpf_prog_array { + struct rcu_head rcu; + struct bpf_prog *progs[0]; +}; + +struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); +void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); +int bpf_prog_array_length(struct bpf_prog_array __rcu *progs); +int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, + __u32 __user *prog_ids, u32 cnt); + +void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs, + struct bpf_prog *old_prog); +int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, + struct bpf_prog *exclude_prog, + struct bpf_prog *include_prog, + struct bpf_prog_array **new_array); + +#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \ + ({ \ + struct bpf_prog **_prog, *__prog; \ + struct bpf_prog_array *_array; \ + u32 _ret = 1; \ + rcu_read_lock(); \ + _array = rcu_dereference(array); \ + if (unlikely(check_non_null && !_array))\ + goto _out; \ + _prog = _array->progs; \ + while ((__prog = READ_ONCE(*_prog))) { \ + _ret &= func(__prog, ctx); \ + _prog++; \ + } \ +_out: \ + rcu_read_unlock(); \ + _ret; \ + }) + +#define BPF_PROG_RUN_ARRAY(array, ctx, func) \ + __BPF_PROG_RUN_ARRAY(array, ctx, func, false) + +#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \ + __BPF_PROG_RUN_ARRAY(array, ctx, func, true) + #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); -#define BPF_PROG_TYPE(_id, _ops) \ - extern const struct bpf_verifier_ops _ops; +extern const struct file_operations bpf_map_fops; +extern const struct file_operations bpf_prog_fops; + +#define BPF_PROG_TYPE(_id, _name) \ + extern const struct bpf_prog_ops _name ## _prog_ops; \ + extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +extern const struct bpf_prog_ops bpf_offload_prog_ops; +extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; +extern const struct bpf_verifier_ops xdp_analyzer_ops; + struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); +struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, + struct net_device *netdev); struct bpf_prog * __must_check 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); @@ -269,11 +356,11 @@ void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; -int bpf_map_new_fd(struct bpf_map *map); +int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); -int bpf_obj_get_user(const char __user *pathname); +int bpf_obj_get_user(const char __user *pathname, int flags); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); @@ -292,6 +379,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); +int bpf_get_file_flag(int flags); + /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent @@ -316,6 +405,13 @@ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); +void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); +void __cpu_map_flush(struct bpf_map *map); +struct xdp_buff; +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, + struct net_device *dev_rx); + /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) { @@ -323,7 +419,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) attr->numa_node : NUMA_NO_NODE; } -#else +#else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); @@ -334,6 +430,14 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, { return ERR_PTR(-EOPNOTSUPP); } + +static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, + enum bpf_prog_type type, + struct net_device *netdev) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i) { @@ -368,7 +472,7 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } -static inline int bpf_obj_get_user(const char __user *pathname) +static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; } @@ -386,8 +490,54 @@ static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) static inline void __dev_map_flush(struct bpf_map *map) { } + +static inline +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) +{ + return NULL; +} + +static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index) +{ +} + +static inline void __cpu_map_flush(struct bpf_map *map) +{ +} + +struct xdp_buff; +static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, + struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + return 0; +} #endif /* CONFIG_BPF_SYSCALL */ +int bpf_prog_offload_compile(struct bpf_prog *prog); +void bpf_prog_offload_destroy(struct bpf_prog *prog); +u32 bpf_prog_offload_ifindex(struct bpf_prog *prog); + +#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) +int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); + +static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) +{ + return aux->offload; +} +#else +static inline int bpf_prog_offload_init(struct bpf_prog *prog, + union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} + +static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) +{ + return false; +} +#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ + #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index e1149327a0c0..978c1d9c9383 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -2,22 +2,25 @@ /* internal file - do not include directly */ #ifdef CONFIG_NET -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb_prog_ops) +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_CGROUP_SKB, cg_skb) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) #endif #ifdef CONFIG_BPF_EVENTS -BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event_prog_ops) +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) +#endif +#ifdef CONFIG_CGROUP_BPF +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) @@ -42,4 +45,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) #ifdef CONFIG_STREAM_PARSER BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b8d200f60a40..07b96aaca256 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -88,14 +88,19 @@ enum bpf_stack_slot_type { #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ +struct bpf_stack_state { + struct bpf_reg_state spilled_ptr; + u8 slot_type[BPF_REG_SIZE]; +}; + /* state of the program: * type of all registers and stack info */ struct bpf_verifier_state { struct bpf_reg_state regs[MAX_BPF_REG]; - u8 stack_slot_type[MAX_BPF_STACK]; - struct bpf_reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE]; struct bpf_verifier_state *parent; + int allocated_stack; + struct bpf_stack_state *stack; }; /* linked list of verifier states used to prune search */ @@ -115,6 +120,21 @@ struct bpf_insn_aux_data { #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ +#define BPF_VERIFIER_TMP_LOG_SIZE 1024 + +struct bpf_verifer_log { + u32 level; + char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; + char __user *ubuf; + u32 len_used; + u32 len_total; +}; + +static inline bool bpf_verifier_log_full(const struct bpf_verifer_log *log) +{ + return log->len_used >= log->len_total - 1; +} + struct bpf_verifier_env; struct bpf_ext_analyzer_ops { int (*insn_hook)(struct bpf_verifier_env *env, @@ -126,22 +146,35 @@ struct bpf_ext_analyzer_ops { */ struct bpf_verifier_env { struct bpf_prog *prog; /* eBPF program being verified */ + const struct bpf_verifier_ops *ops; struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ - struct bpf_verifier_state cur_state; /* current verifier state */ + struct bpf_verifier_state *cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ - const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */ - void *analyzer_priv; /* pointer to external analyzer's private data */ + const struct bpf_ext_analyzer_ops *dev_ops; /* device analyzer ops */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ u32 used_map_cnt; /* number of used maps */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ + + struct bpf_verifer_log log; }; -int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, - void *priv); +static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) +{ + return env->cur_state->regs; +} + +#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) +int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); +#else +int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env) +{ + return -EOPNOTSUPP; +} +#endif #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 4f087f86a741..8ff86b4c1b8a 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -64,6 +64,7 @@ #define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000 #define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 +#define PHY_BRCM_EN_MASTER_MODE 0x00010000 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h index 133b76d0d2c0..451aaa0786ae 100644 --- a/include/linux/byteorder/generic.h +++ b/include/linux/byteorder/generic.h @@ -171,4 +171,20 @@ static inline void be64_add_cpu(__be64 *var, u64 val) *var = cpu_to_be64(be64_to_cpu(*var) + val); } +static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) +{ + int i; + + for (i = 0; i < len; i++) + dst[i] = cpu_to_be32(src[i]); +} + +static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len) +{ + int i; + + for (i = 0; i < len; i++) + dst[i] = be32_to_cpu(src[i]); +} + #endif /* _LINUX_BYTEORDER_GENERIC_H */ diff --git a/include/linux/connector.h b/include/linux/connector.h index f8fe8637d771..032102b19645 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -22,7 +22,7 @@ #define __CONNECTOR_H -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/list.h> #include <linux/workqueue.h> @@ -49,7 +49,7 @@ struct cn_callback_id { struct cn_callback_entry { struct list_head callback_entry; - atomic_t refcnt; + refcount_t refcnt; struct cn_queue_dev *pdev; struct cn_callback_id id; diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index cdbc344a92e4..8557efe096dc 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -1,17 +1,76 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/fs.h> +#include <linux/bpf-cgroup.h> + +#define DEVCG_ACC_MKNOD 1 +#define DEVCG_ACC_READ 2 +#define DEVCG_ACC_WRITE 4 +#define DEVCG_ACC_MASK (DEVCG_ACC_MKNOD | DEVCG_ACC_READ | DEVCG_ACC_WRITE) + +#define DEVCG_DEV_BLOCK 1 +#define DEVCG_DEV_CHAR 2 +#define DEVCG_DEV_ALL 4 /* this represents all devices */ #ifdef CONFIG_CGROUP_DEVICE -extern int __devcgroup_inode_permission(struct inode *inode, int mask); -extern int devcgroup_inode_mknod(int mode, dev_t dev); +extern int __devcgroup_check_permission(short type, u32 major, u32 minor, + short access); +#else +static inline int __devcgroup_check_permission(short type, u32 major, u32 minor, + short access) +{ return 0; } +#endif + +#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) +static inline int devcgroup_check_permission(short type, u32 major, u32 minor, + short access) +{ + int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); + + if (rc) + return -EPERM; + + return __devcgroup_check_permission(type, major, minor, access); +} + static inline int devcgroup_inode_permission(struct inode *inode, int mask) { + short type, access = 0; + if (likely(!inode->i_rdev)) return 0; - if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode)) + + if (S_ISBLK(inode->i_mode)) + type = DEVCG_DEV_BLOCK; + else if (S_ISCHR(inode->i_mode)) + type = DEVCG_DEV_CHAR; + else + return 0; + + if (mask & MAY_WRITE) + access |= DEVCG_ACC_WRITE; + if (mask & MAY_READ) + access |= DEVCG_ACC_READ; + + return devcgroup_check_permission(type, imajor(inode), iminor(inode), + access); +} + +static inline int devcgroup_inode_mknod(int mode, dev_t dev) +{ + short type; + + if (!S_ISBLK(mode) && !S_ISCHR(mode)) return 0; - return __devcgroup_inode_permission(inode, mask); + + if (S_ISBLK(mode)) + type = DEVCG_DEV_BLOCK; + else + type = DEVCG_DEV_CHAR; + + return devcgroup_check_permission(type, MAJOR(dev), MINOR(dev), + DEVCG_ACC_MKNOD); } + #else static inline int devcgroup_inode_permission(struct inode *inode, int mask) { return 0; } diff --git a/include/linux/dsa/lan9303.h b/include/linux/dsa/lan9303.h new file mode 100644 index 000000000000..f48a85c377de --- /dev/null +++ b/include/linux/dsa/lan9303.h @@ -0,0 +1,38 @@ +/* Included by drivers/net/dsa/lan9303.h and net/dsa/tag_lan9303.c */ +#include <linux/if_ether.h> + +struct lan9303; + +struct lan9303_phy_ops { + /* PHY 1 and 2 access*/ + int (*phy_read)(struct lan9303 *chip, int port, int regnum); + int (*phy_write)(struct lan9303 *chip, int port, + int regnum, u16 val); +}; + +#define LAN9303_NUM_ALR_RECORDS 512 +struct lan9303_alr_cache_entry { + u8 mac_addr[ETH_ALEN]; + u8 port_map; /* Bitmap of ports. Zero if unused entry */ + u8 stp_override; /* non zero if set LAN9303_ALR_DAT1_AGE_OVERRID */ +}; + +struct lan9303 { + struct device *dev; + struct regmap *regmap; + struct regmap_irq_chip_data *irq_data; + struct gpio_desc *reset_gpio; + u32 reset_duration; /* in [ms] */ + bool phy_addr_sel_strap; + struct dsa_switch *ds; + struct mutex indirect_mutex; /* protect indexed register access */ + const struct lan9303_phy_ops *ops; + bool is_bridged; /* true if port 1 and 2 are bridged */ + + /* remember LAN9303_SWE_PORT_STATE while not bridged */ + u32 swe_port_state; + /* LAN9303 do not offer reading specific ALR entry. Cache all + * static entries in a flat table + **/ + struct lan9303_alr_cache_entry alr_cache[LAN9303_NUM_ALR_RECORDS]; +}; diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 34c0a5464c74..be1214731505 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -99,7 +99,7 @@ void dql_completed(struct dql *dql, unsigned int count); void dql_reset(struct dql *dql); /* Initialize dql state */ -int dql_init(struct dql *dql, unsigned hold_time); +void dql_init(struct dql *dql, unsigned int hold_time); #endif /* _KERNEL_ */ diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2d9f80848d4b..263dbcad22fc 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -66,6 +66,7 @@ int eth_gro_complete(struct sk_buff *skb, int nhoff); /* Reserved Ethernet Addresses per IEEE 802.1Q */ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; +#define eth_stp_addr eth_reserved_addr_base /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 0c0146e7e274..2ec41a7eb54f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -164,6 +164,16 @@ extern int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); +/** + * ethtool_intersect_link_masks - Given two link masks, AND them together + * @dst: first mask and where result is stored + * @src: second mask to intersect with + * + * Given two link mode masks, AND them together and save the result in dst. + */ +void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst, + struct ethtool_link_ksettings *src); + void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst, u32 legacy_u32); diff --git a/include/linux/filter.h b/include/linux/filter.h index 48ec57e70f9f..0cd02ff4ae30 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -482,30 +482,36 @@ struct sk_filter { struct bpf_prog *prog; }; -#define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) +#define BPF_PROG_RUN(filter, ctx) (*(filter)->bpf_func)(ctx, (filter)->insnsi) #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; + void *data_meta; void *data_end; }; struct xdp_buff { void *data; void *data_end; + void *data_meta; void *data_hard_start; }; -/* compute the linear packet data range [data, data_end) which - * will be accessed by cls_bpf, act_bpf and lwt programs +/* Compute the linear packet data range [data, data_end) which + * will be accessed by various program types (cls_bpf, act_bpf, + * lwt, ...). Subsystems allowing direct data access must (!) + * ensure that cb[] area can be written to when BPF program is + * invoked (otherwise cb[] save/restore is necessary). */ -static inline void bpf_compute_data_end(struct sk_buff *skb) +static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb)); - cb->data_end = skb->data + skb_headlen(skb); + cb->data_meta = skb->data - skb_metadata_len(skb); + cb->data_end = skb->data + skb_headlen(skb); } static inline u8 *bpf_skb_cb(struct sk_buff *skb) @@ -726,8 +732,22 @@ int xdp_do_redirect(struct net_device *dev, struct bpf_prog *prog); void xdp_do_flush_map(void); +/* Drivers not supporting XDP metadata can use this helper, which + * rejects any room expansion for metadata as a result. + */ +static __always_inline void +xdp_set_data_meta_invalid(struct xdp_buff *xdp) +{ + xdp->data_meta = xdp->data + 1; +} + +static __always_inline bool +xdp_data_meta_unsupported(const struct xdp_buff *xdp) +{ + return unlikely(xdp->data_meta > xdp->data); +} + void bpf_warn_invalid_xdp_action(u32 act); -void bpf_warn_invalid_xdp_redirect(u32 ifindex); struct sock *do_sk_redirect_map(struct sk_buff *skb); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 55a604ad459f..ee6657a0ed69 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2445,6 +2445,7 @@ enum ieee80211_sa_query_action { #define WLAN_OUI_TYPE_MICROSOFT_WPA 1 #define WLAN_OUI_TYPE_MICROSOFT_WMM 2 #define WLAN_OUI_TYPE_MICROSOFT_WPS 4 +#define WLAN_OUI_TYPE_MICROSOFT_TPC 8 /* * WMM/802.11e Tspec Element diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 3355efc89781..6756fea18b69 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -31,7 +31,7 @@ static inline struct arphdr *arp_hdr(const struct sk_buff *skb) return (struct arphdr *)skb_network_header(skb); } -static inline int arp_hdr_len(struct net_device *dev) +static inline unsigned int arp_hdr_len(const struct net_device *dev) { switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 3cd18ac0697f..02639ebea2f0 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -49,6 +49,7 @@ struct br_ip_list { #define BR_MULTICAST_TO_UNICAST BIT(12) #define BR_VLAN_TUNNEL BIT(13) #define BR_BCAST_FLOOD BIT(14) +#define BR_NEIGH_SUPPRESS BIT(15) #define BR_DEFAULT_AGEING_TIME (300 * HZ) @@ -63,6 +64,7 @@ int br_multicast_list_adjacent(struct net_device *dev, bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto); bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); +bool br_multicast_router(const struct net_device *dev); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -83,6 +85,10 @@ static inline bool br_multicast_enabled(const struct net_device *dev) { return false; } +static inline bool br_multicast_router(const struct net_device *dev) +{ + return false; +} #endif #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h index 46df7e565d6f..82a1b4e93570 100644 --- a/include/linux/if_frad.h +++ b/include/linux/if_frad.h @@ -83,6 +83,7 @@ struct frad_local /* fields that are used by the Sangoma SDLA cards */ struct timer_list timer; + struct net_device *dev; int type; /* adapter type */ int state; /* state of the S502/8 control latch */ int buffer; /* current buffer for S508 firmware */ diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 0e2c60efad2d..bedf54b6f943 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -11,13 +11,6 @@ #include <linux/u64_stats_sync.h> struct macvlan_port; -struct macvtap_queue; - -/* - * Maximum times a macvtap device can be opened. This can be used to - * configure the number of receive queue, e.g. for multiqueue virtio. - */ -#define MAX_TAP_QUEUES 256 #define MACVLAN_MC_FILTER_BITS 8 #define MACVLAN_MC_FILTER_SZ (1 << MACVLAN_MC_FILTER_BITS) @@ -36,14 +29,6 @@ struct macvlan_dev { netdev_features_t set_features; enum macvlan_mode mode; u16 flags; - /* This array tracks active taps. */ - struct tap_queue __rcu *taps[MAX_TAP_QUEUES]; - /* This list tracks all taps (both enabled and disabled) */ - struct list_head queue_list; - int numvtaps; - int numqueues; - netdev_features_t tap_features; - int minor; int nest_level; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; @@ -73,7 +58,8 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, extern void macvlan_common_setup(struct net_device *dev); extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]); + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack); extern void macvlan_count_rx(const struct macvlan_dev *vlan, unsigned int len, bool success, diff --git a/include/linux/if_phonet.h b/include/linux/if_phonet.h index 3b5c60da2e2a..2d8486168ec5 100644 --- a/include/linux/if_phonet.h +++ b/include/linux/if_phonet.h @@ -11,5 +11,5 @@ #include <uapi/linux/if_phonet.h> -extern struct header_ops phonet_header_ops; +extern const struct header_ops phonet_header_ops; #endif diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h index 13edf19ce9fb..3ecef57c31e3 100644 --- a/include/linux/if_tap.h +++ b/include/linux/if_tap.h @@ -23,6 +23,10 @@ static inline struct skb_array *tap_get_skb_array(struct file *f) #include <net/sock.h> #include <linux/skb_array.h> +/* + * Maximum times a tap device can be opened. This can be used to + * configure the number of receive queue, e.g. for multiqueue virtio. + */ #define MAX_TAP_QUEUES 256 struct tap_queue; diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 5058f061cb2b..1ac5bf95bfdd 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -155,6 +155,7 @@ struct in_ifaddr { struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; + struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); @@ -180,6 +181,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); +struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index c9258124e417..7161d8e7ee79 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1351,6 +1351,40 @@ * @inode we wish to get the security context of. * @ctx is a pointer in which to place the allocated security context. * @ctxlen points to the place to put the length of @ctx. + * + * Security hooks for using the eBPF maps and programs functionalities through + * eBPF syscalls. + * + * @bpf: + * Do a initial check for all bpf syscalls after the attribute is copied + * into the kernel. The actual security module can implement their own + * rules to check the specific cmd they need. + * + * @bpf_map: + * Do a check when the kernel generate and return a file descriptor for + * eBPF maps. + * + * @map: bpf map that we want to access + * @mask: the access flags + * + * @bpf_prog: + * Do a check when the kernel generate and return a file descriptor for + * eBPF programs. + * + * @prog: bpf prog that userspace want to use. + * + * @bpf_map_alloc_security: + * Initialize the security field inside bpf map. + * + * @bpf_map_free_security: + * Clean up the security information stored inside bpf map. + * + * @bpf_prog_alloc_security: + * Initialize the security field inside bpf program. + * + * @bpf_prog_free_security: + * Clean up the security information stored inside bpf prog. + * */ union security_list_options { int (*binder_set_context_mgr)(struct task_struct *mgr); @@ -1682,6 +1716,17 @@ union security_list_options { struct audit_context *actx); void (*audit_rule_free)(void *lsmrule); #endif /* CONFIG_AUDIT */ + +#ifdef CONFIG_BPF_SYSCALL + int (*bpf)(int cmd, union bpf_attr *attr, + unsigned int size); + int (*bpf_map)(struct bpf_map *map, fmode_t fmode); + int (*bpf_prog)(struct bpf_prog *prog); + int (*bpf_map_alloc_security)(struct bpf_map *map); + void (*bpf_map_free_security)(struct bpf_map *map); + int (*bpf_prog_alloc_security)(struct bpf_prog_aux *aux); + void (*bpf_prog_free_security)(struct bpf_prog_aux *aux); +#endif /* CONFIG_BPF_SYSCALL */ }; struct security_hook_heads { @@ -1901,6 +1946,15 @@ struct security_hook_heads { struct list_head audit_rule_match; struct list_head audit_rule_free; #endif /* CONFIG_AUDIT */ +#ifdef CONFIG_BPF_SYSCALL + struct list_head bpf; + struct list_head bpf_map; + struct list_head bpf_prog; + struct list_head bpf_map_alloc_security; + struct list_head bpf_map_free_security; + struct list_head bpf_prog_alloc_security; + struct list_head bpf_prog_free_security; +#endif /* CONFIG_BPF_SYSCALL */ } __randomize_layout; /* diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b0a57e043fa3..a9b5fed8f7c6 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -40,7 +40,7 @@ #include <linux/cpu_rmap.h> #include <linux/crash_dump.h> -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/timecounter.h> @@ -751,7 +751,7 @@ struct mlx4_cq { int cqn; unsigned vector; - atomic_t refcount; + refcount_t refcount; struct completion free; struct { struct list_head list; @@ -768,7 +768,7 @@ struct mlx4_qp { int qpn; - atomic_t refcount; + refcount_t refcount; struct completion free; u8 usage; }; @@ -781,7 +781,7 @@ struct mlx4_srq { int max_gs; int wqe_shift; - atomic_t refcount; + refcount_t refcount; struct completion free; }; diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 95898847c7d4..6a57ec2f1ef7 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -35,7 +35,7 @@ #include <rdma/ib_verbs.h> #include <linux/mlx5/driver.h> - +#include <linux/refcount.h> struct mlx5_core_cq { u32 cqn; @@ -43,7 +43,7 @@ struct mlx5_core_cq { __be32 *set_ci_db; __be32 *arm_db; struct mlx5_uars_page *uar; - atomic_t refcount; + refcount_t refcount; struct completion free; unsigned vector; unsigned int irqn; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index e32dbc4934db..409ffb14298a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -49,11 +49,15 @@ #define __mlx5_nullp(typ) ((struct mlx5_ifc_##typ##_bits *)0) #define __mlx5_bit_sz(typ, fld) sizeof(__mlx5_nullp(typ)->fld) #define __mlx5_bit_off(typ, fld) (offsetof(struct mlx5_ifc_##typ##_bits, fld)) +#define __mlx5_16_off(typ, fld) (__mlx5_bit_off(typ, fld) / 16) #define __mlx5_dw_off(typ, fld) (__mlx5_bit_off(typ, fld) / 32) #define __mlx5_64_off(typ, fld) (__mlx5_bit_off(typ, fld) / 64) +#define __mlx5_16_bit_off(typ, fld) (16 - __mlx5_bit_sz(typ, fld) - (__mlx5_bit_off(typ, fld) & 0xf)) #define __mlx5_dw_bit_off(typ, fld) (32 - __mlx5_bit_sz(typ, fld) - (__mlx5_bit_off(typ, fld) & 0x1f)) #define __mlx5_mask(typ, fld) ((u32)((1ull << __mlx5_bit_sz(typ, fld)) - 1)) #define __mlx5_dw_mask(typ, fld) (__mlx5_mask(typ, fld) << __mlx5_dw_bit_off(typ, fld)) +#define __mlx5_mask16(typ, fld) ((u16)((1ull << __mlx5_bit_sz(typ, fld)) - 1)) +#define __mlx5_16_mask(typ, fld) (__mlx5_mask16(typ, fld) << __mlx5_16_bit_off(typ, fld)) #define __mlx5_st_sz_bits(typ) sizeof(struct mlx5_ifc_##typ##_bits) #define MLX5_FLD_SZ_BYTES(typ, fld) (__mlx5_bit_sz(typ, fld) / 8) @@ -116,6 +120,19 @@ __mlx5_mask(typ, fld)) ___t; \ }) +#define MLX5_GET16(typ, p, fld) ((be16_to_cpu(*((__be16 *)(p) +\ +__mlx5_16_off(typ, fld))) >> __mlx5_16_bit_off(typ, fld)) & \ +__mlx5_mask16(typ, fld)) + +#define MLX5_SET16(typ, p, fld, v) do { \ + u16 _v = v; \ + BUILD_BUG_ON(__mlx5_st_sz_bits(typ) % 16); \ + *((__be16 *)(p) + __mlx5_16_off(typ, fld)) = \ + cpu_to_be16((be16_to_cpu(*((__be16 *)(p) + __mlx5_16_off(typ, fld))) & \ + (~__mlx5_16_mask(typ, fld))) | (((_v) & __mlx5_mask16(typ, fld)) \ + << __mlx5_16_bit_off(typ, fld))); \ +} while (0) + /* Big endian getters */ #define MLX5_GET64_BE(typ, p, fld) (*((__be64 *)(p) +\ __mlx5_64_off(typ, fld))) @@ -1000,6 +1017,14 @@ enum mlx5_mcam_feature_groups { MLX5_MCAM_FEATURE_ENHANCED_FEATURES = 0x0, }; +enum mlx5_qcam_reg_groups { + MLX5_QCAM_REGS_FIRST_128 = 0x0, +}; + +enum mlx5_qcam_feature_groups { + MLX5_QCAM_FEATURE_ENHANCED_FEATURES = 0x0, +}; + /* GET Dev Caps macros */ #define MLX5_CAP_GEN(mdev, cap) \ MLX5_GET(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap) @@ -1108,6 +1133,12 @@ enum mlx5_mcam_feature_groups { #define MLX5_CAP_MCAM_FEATURE(mdev, fld) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) +#define MLX5_CAP_QCAM_REG(mdev, fld) \ + MLX5_GET(qcam_reg, (mdev)->caps.qcam, qos_access_reg_cap_mask.reg_cap.fld) + +#define MLX5_CAP_QCAM_FEATURE(mdev, fld) \ + MLX5_GET(qcam_reg, (mdev)->caps.qcam, qos_feature_cap_mask.feature_cap.fld) + #define MLX5_CAP_FPGA(mdev, cap) \ MLX5_GET(fpga_cap, (mdev)->caps.fpga, cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 401c8972cc3a..a886b51511ab 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -49,6 +49,8 @@ #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> #include <linux/mlx5/srq.h> +#include <linux/timecounter.h> +#include <linux/ptp_clock_kernel.h> enum { MLX5_BOARD_ID_LEN = 64, @@ -105,8 +107,11 @@ enum { }; enum { + MLX5_REG_QPTS = 0x4002, MLX5_REG_QETCR = 0x4005, MLX5_REG_QTCT = 0x400a, + MLX5_REG_QPDPM = 0x4013, + MLX5_REG_QCAM = 0x4019, MLX5_REG_DCBX_PARAM = 0x4020, MLX5_REG_DCBX_APP = 0x4021, MLX5_REG_FPGA_CAP = 0x4022, @@ -139,6 +144,11 @@ enum { MLX5_REG_MCAM = 0x907f, }; +enum mlx5_qpts_trust_state { + MLX5_QPTS_TRUST_PCP = 1, + MLX5_QPTS_TRUST_DSCP = 2, +}; + enum mlx5_dcbx_oper_mode { MLX5E_DCBX_PARAM_VER_OPER_HOST = 0x0, MLX5E_DCBX_PARAM_VER_OPER_AUTO = 0x3, @@ -760,6 +770,27 @@ struct mlx5_rsvd_gids { struct ida ida; }; +#define MAX_PIN_NUM 8 +struct mlx5_pps { + u8 pin_caps[MAX_PIN_NUM]; + struct work_struct out_work; + u64 start[MAX_PIN_NUM]; + u8 enabled; +}; + +struct mlx5_clock { + rwlock_t lock; + struct cyclecounter cycles; + struct timecounter tc; + struct hwtstamp_config hwtstamp_config; + u32 nominal_c_mult; + unsigned long overflow_period; + struct delayed_work overflow_work; + struct ptp_clock *ptp; + struct ptp_clock_info ptp_info; + struct mlx5_pps pps_info; +}; + struct mlx5_core_dev { struct pci_dev *pdev; /* sync pci state */ @@ -775,6 +806,7 @@ struct mlx5_core_dev { u32 pcam[MLX5_ST_SZ_DW(pcam_reg)]; u32 mcam[MLX5_ST_SZ_DW(mcam_reg)]; u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; + u32 qcam[MLX5_ST_SZ_DW(qcam_reg)]; } caps; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; @@ -800,6 +832,7 @@ struct mlx5_core_dev { #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap; #endif + struct mlx5_clock clock; }; struct mlx5_db { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 69772347f866..3e5363f760dd 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -838,7 +838,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cc_modify_allowed[0x1]; u8 start_pad[0x1]; u8 cache_line_128byte[0x1]; - u8 reserved_at_165[0xb]; + u8 reserved_at_165[0xa]; + u8 qcam_reg[0x1]; u8 gid_table_size[0x10]; u8 out_of_seq_cnt[0x1]; @@ -7890,6 +7891,43 @@ struct mlx5_ifc_mcam_reg_bits { u8 reserved_at_1c0[0x80]; }; +struct mlx5_ifc_qcam_access_reg_cap_mask { + u8 qcam_access_reg_cap_mask_127_to_20[0x6C]; + u8 qpdpm[0x1]; + u8 qcam_access_reg_cap_mask_18_to_4[0x0F]; + u8 qdpm[0x1]; + u8 qpts[0x1]; + u8 qcap[0x1]; + u8 qcam_access_reg_cap_mask_0[0x1]; +}; + +struct mlx5_ifc_qcam_qos_feature_cap_mask { + u8 qcam_qos_feature_cap_mask_127_to_1[0x7F]; + u8 qpts_trust_both[0x1]; +}; + +struct mlx5_ifc_qcam_reg_bits { + u8 reserved_at_0[0x8]; + u8 feature_group[0x8]; + u8 reserved_at_10[0x8]; + u8 access_reg_group[0x8]; + u8 reserved_at_20[0x20]; + + union { + struct mlx5_ifc_qcam_access_reg_cap_mask reg_cap; + u8 reserved_at_0[0x80]; + } qos_access_reg_cap_mask; + + u8 reserved_at_c0[0x80]; + + union { + struct mlx5_ifc_qcam_qos_feature_cap_mask feature_cap; + u8 reserved_at_0[0x80]; + } qos_feature_cap_mask; + + u8 reserved_at_1c0[0x80]; +}; + struct mlx5_ifc_pcap_reg_bits { u8 reserved_at_0[0x8]; u8 local_port[0x8]; @@ -8540,6 +8578,26 @@ struct mlx5_ifc_qetc_reg_bits { struct mlx5_ifc_ets_global_config_reg_bits global_configuration; }; +struct mlx5_ifc_qpdpm_dscp_reg_bits { + u8 e[0x1]; + u8 reserved_at_01[0x0b]; + u8 prio[0x04]; +}; + +struct mlx5_ifc_qpdpm_reg_bits { + u8 reserved_at_0[0x8]; + u8 local_port[0x8]; + u8 reserved_at_10[0x10]; + struct mlx5_ifc_qpdpm_dscp_reg_bits dscp[64]; +}; + +struct mlx5_ifc_qpts_reg_bits { + u8 reserved_at_0[0x8]; + u8 local_port[0x8]; + u8 reserved_at_10[0x2d]; + u8 trust_state[0x3]; +}; + struct mlx5_ifc_qtct_reg_bits { u8 reserved_at_0[0x8]; u8 port_number[0x8]; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index c59af8ab753a..035f0d4dc9fe 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -179,4 +179,9 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out); int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in); + +int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state); +int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state); +int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio); +int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio); #endif /* __MLX5_PORT_H__ */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 1c2e8d6b7274..abb6dc2ebbf8 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -687,5 +687,31 @@ struct fsl_mc_device_id { const char obj_type[16]; }; +/** + * struct tb_service_id - Thunderbolt service identifiers + * @match_flags: Flags used to match the structure + * @protocol_key: Protocol key the service supports + * @protocol_id: Protocol id the service supports + * @protocol_version: Version of the protocol + * @protocol_revision: Revision of the protocol software + * @driver_data: Driver specific data + * + * Thunderbolt XDomain services are exposed as devices where each device + * carries the protocol information the service supports. Thunderbolt + * XDomain service drivers match against that information. + */ +struct tb_service_id { + __u32 match_flags; + char protocol_key[8 + 1]; + __u32 protocol_id; + __u32 protocol_version; + __u32 protocol_revision; + kernel_ulong_t driver_data; +}; + +#define TBSVC_MATCH_PROTOCOL_KEY 0x0001 +#define TBSVC_MATCH_PROTOCOL_ID 0x0002 +#define TBSVC_MATCH_PROTOCOL_VERSION 0x0004 +#define TBSVC_MATCH_PROTOCOL_REVISION 0x0008 #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 65a70a7c51c1..5396521a776a 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -6,6 +6,8 @@ #include <linux/pim.h> #include <linux/rhashtable.h> #include <net/sock.h> +#include <net/fib_rules.h> +#include <net/fib_notifier.h> #include <uapi/linux/mroute.h> #ifdef CONFIG_IP_MROUTE @@ -19,6 +21,7 @@ int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); int ip_mr_init(void); +bool ipmr_rule_default(const struct fib_rule *rule); #else static inline int ip_mroute_setsockopt(struct sock *sock, int optname, char __user *optval, unsigned int optlen) @@ -46,10 +49,16 @@ static inline int ip_mroute_opt(int opt) { return 0; } + +static inline bool ipmr_rule_default(const struct fib_rule *rule) +{ + return true; +} #endif struct vif_device { struct net_device *dev; /* Device we are using */ + struct netdev_phys_item_id dev_parent_id; /* Device parent ID */ unsigned long bytes_in,bytes_out; unsigned long pkt_in,pkt_out; /* Statistics */ unsigned long rate_limit; /* Traffic shaping (NI) */ @@ -59,6 +68,14 @@ struct vif_device { int link; /* Physical interface index */ }; +struct vif_entry_notifier_info { + struct fib_notifier_info info; + struct net_device *dev; + vifi_t vif_index; + unsigned short vif_flags; + u32 tb_id; +}; + #define VIFF_STATIC 0x8000 #define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL) @@ -82,9 +99,11 @@ struct mr_table { /* mfc_flags: * MFC_STATIC - the entry was added statically (not by a routing daemon) + * MFC_OFFLOAD - the entry was offloaded to the hardware */ enum { MFC_STATIC = BIT(0), + MFC_OFFLOAD = BIT(1), }; struct mfc_cache_cmp_arg { @@ -110,6 +129,7 @@ struct mfc_cache_cmp_arg { * @wrong_if: number of wrong source interface hits * @lastuse: time of last use of the group (traffic or update) * @ttls: OIF TTL threshold array + * @refcount: reference count for this entry * @list: global entry list * @rcu: used for entry destruction */ @@ -139,14 +159,40 @@ struct mfc_cache { unsigned long wrong_if; unsigned long lastuse; unsigned char ttls[MAXVIFS]; + refcount_t refcount; } res; } mfc_un; struct list_head list; struct rcu_head rcu; }; +struct mfc_entry_notifier_info { + struct fib_notifier_info info; + struct mfc_cache *mfc; + u32 tb_id; +}; + struct rtmsg; int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, struct rtmsg *rtm, u32 portid); + +#ifdef CONFIG_IP_MROUTE +void ipmr_cache_free(struct mfc_cache *mfc_cache); +#else +static inline void ipmr_cache_free(struct mfc_cache *mfc_cache) +{ +} +#endif + +static inline void ipmr_cache_put(struct mfc_cache *c) +{ + if (refcount_dec_and_test(&c->mfc_un.res.refcount)) + ipmr_cache_free(c); +} +static inline void ipmr_cache_hold(struct mfc_cache *c) +{ + refcount_inc(&c->mfc_un.res.refcount); +} + #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2eaac7d75af4..30f0f2928808 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -55,7 +55,7 @@ struct netpoll_info; struct device; struct phy_device; -struct dsa_switch_tree; +struct dsa_port; /* 802.11 specific */ struct wireless_dev; @@ -770,17 +770,20 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); enum tc_setup_type { - TC_SETUP_MQPRIO, + TC_SETUP_QDISC_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, TC_SETUP_CLSMATCHALL, TC_SETUP_CLSBPF, + TC_SETUP_BLOCK, + TC_SETUP_QDISC_CBS, + TC_SETUP_QDISC_RED, }; -/* These structures hold the attributes of xdp state that are being passed - * to the netdevice through the xdp op. +/* These structures hold the attributes of bpf state that are being passed + * to the netdevice through the bpf op. */ -enum xdp_netdev_command { +enum bpf_netdev_command { /* Set or clear a bpf program used in the earliest stages of packet * rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee * is responsible for calling bpf_prog_put on any old progs that are @@ -795,12 +798,17 @@ enum xdp_netdev_command { * is equivalent to XDP_ATTACHED_DRV. */ XDP_QUERY_PROG, + /* BPF program for offload callbacks, invoked at program load time. */ + BPF_OFFLOAD_VERIFIER_PREP, + BPF_OFFLOAD_TRANSLATE, + BPF_OFFLOAD_DESTROY, }; +struct bpf_ext_analyzer_ops; struct netlink_ext_ack; -struct netdev_xdp { - enum xdp_netdev_command command; +struct netdev_bpf { + enum bpf_netdev_command command; union { /* XDP_SETUP_PROG */ struct { @@ -813,6 +821,15 @@ struct netdev_xdp { u8 prog_attached; u32 prog_id; }; + /* BPF_OFFLOAD_VERIFIER_PREP */ + struct { + struct bpf_prog *prog; + const struct bpf_ext_analyzer_ops *ops; /* callee set */ + } verifier; + /* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */ + struct { + struct bpf_prog *prog; + } offload; }; }; @@ -826,6 +843,11 @@ struct xfrmdev_ops { }; #endif +struct dev_ifalias { + struct rcu_head rcuhead; + char ifalias[]; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1117,9 +1139,10 @@ struct xfrmdev_ops { * appropriate rx headroom value allows avoiding skb head copy on * forward. Setting a negative value resets the rx headroom to the * default value. - * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); + * int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); * This function is used to set or query state related to XDP on the - * netdevice. See definition of enum xdp_netdev_command for details. + * netdevice and manage BPF offload. See definition of + * enum bpf_netdev_command for details. * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); * This function is used to submit a XDP packet for transmit on a * netdevice. @@ -1241,7 +1264,8 @@ struct net_device_ops { u32 flow_id); #endif int (*ndo_add_slave)(struct net_device *dev, - struct net_device *slave_dev); + struct net_device *slave_dev, + struct netlink_ext_ack *extack); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); netdev_features_t (*ndo_fix_features)(struct net_device *dev, @@ -1307,8 +1331,8 @@ struct net_device_ops { struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); - int (*ndo_xdp)(struct net_device *dev, - struct netdev_xdp *xdp); + int (*ndo_bpf)(struct net_device *dev, + struct netdev_bpf *bpf); int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); void (*ndo_xdp_flush)(struct net_device *dev); @@ -1551,6 +1575,8 @@ enum netdev_priv_flags { * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one + * @miniq_ingress: ingress/clsact qdisc specific data for + * ingress processing * @ingress_queue: XXX: need comments on this one * @broadcast: hw bcast address * @@ -1568,7 +1594,8 @@ enum netdev_priv_flags { * @tx_global_lock: XXX: need comments on this one * * @xps_maps: XXX: need comments on this one - * + * @miniq_egress: clsact qdisc specific data for + * egress processing * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers @@ -1632,7 +1659,7 @@ enum netdev_priv_flags { struct net_device { char name[IFNAMSIZ]; struct hlist_node name_hlist; - char *ifalias; + struct dev_ifalias __rcu *ifalias; /* * I/O specific fields * FIXME: Merge these and struct ifmap into one @@ -1752,7 +1779,7 @@ struct net_device { struct vlan_info __rcu *vlan_info; #endif #if IS_ENABLED(CONFIG_NET_DSA) - struct dsa_switch_tree *dsa_ptr; + struct dsa_port *dsa_ptr; #endif #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; @@ -1787,7 +1814,7 @@ struct net_device { void __rcu *rx_handler_data; #ifdef CONFIG_NET_CLS_ACT - struct tcf_proto __rcu *ingress_cl_list; + struct mini_Qdisc __rcu *miniq_ingress; #endif struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS @@ -1818,7 +1845,7 @@ struct net_device { struct xps_dev_maps __rcu *xps_maps; #endif #ifdef CONFIG_NET_CLS_ACT - struct tcf_proto __rcu *egress_cl_list; + struct mini_Qdisc __rcu *miniq_egress; #endif /* These may be needed for future network-power-down code. */ @@ -2304,7 +2331,8 @@ int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); struct netdev_notifier_info { - struct net_device *dev; + struct net_device *dev; + struct netlink_ext_ack *extack; }; struct netdev_notifier_change_info { @@ -2329,6 +2357,7 @@ static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { info->dev = dev; + info->extack = NULL; } static inline struct net_device * @@ -2337,6 +2366,12 @@ netdev_notifier_info_to_dev(const struct netdev_notifier_info *info) return info->dev; } +static inline struct netlink_ext_ack * +netdev_notifier_info_to_extack(const struct netdev_notifier_info *info) +{ + return info->extack; +} + int call_netdevice_notifiers(unsigned long val, struct net_device *dev); @@ -3246,6 +3281,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); +int netif_receive_skb_core(struct sk_buff *skb); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); @@ -3275,6 +3311,7 @@ void __dev_notify_flags(struct net_device *, unsigned int old_flags, unsigned int gchanges); int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); +int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); int dev_set_mtu(struct net_device *, int); @@ -3290,10 +3327,10 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp); +typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags); -u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id); +u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t xdp_op, u32 *prog_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); @@ -3907,10 +3944,12 @@ void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); -int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); +int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, + struct netlink_ext_ack *extack); int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, - void *upper_priv, void *upper_info); + void *upper_priv, void *upper_info, + struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); diff --git a/include/linux/of.h b/include/linux/of.h index b240ed69dc96..b32d418d011a 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -675,12 +675,6 @@ static inline int of_property_count_elems_of_size(const struct device_node *np, return -ENOSYS; } -static inline int of_property_read_u32_index(const struct device_node *np, - const char *propname, u32 index, u32 *out_value) -{ - return -ENOSYS; -} - static inline int of_property_read_u8_array(const struct device_node *np, const char *propname, u8 *out_values, size_t sz) { @@ -707,16 +701,14 @@ static inline int of_property_read_u64_array(const struct device_node *np, return -ENOSYS; } -static inline int of_property_read_string(const struct device_node *np, - const char *propname, - const char **out_string) +static inline int of_property_read_u32_index(const struct device_node *np, + const char *propname, u32 index, u32 *out_value) { return -ENOSYS; } -static inline int of_property_read_string_helper(const struct device_node *np, - const char *propname, - const char **out_strs, size_t sz, int index) +static inline int of_property_read_u64_index(const struct device_node *np, + const char *propname, u32 index, u64 *out_value) { return -ENOSYS; } @@ -744,12 +736,51 @@ static inline int of_n_size_cells(struct device_node *np) return 0; } +static inline int of_property_read_variable_u8_array(const struct device_node *np, + const char *propname, u8 *out_values, + size_t sz_min, size_t sz_max) +{ + return -ENOSYS; +} + +static inline int of_property_read_variable_u16_array(const struct device_node *np, + const char *propname, u16 *out_values, + size_t sz_min, size_t sz_max) +{ + return -ENOSYS; +} + +static inline int of_property_read_variable_u32_array(const struct device_node *np, + const char *propname, + u32 *out_values, + size_t sz_min, + size_t sz_max) +{ + return -ENOSYS; +} + static inline int of_property_read_u64(const struct device_node *np, const char *propname, u64 *out_value) { return -ENOSYS; } +static inline int of_property_read_variable_u64_array(const struct device_node *np, + const char *propname, + u64 *out_values, + size_t sz_min, + size_t sz_max) +{ + return -ENOSYS; +} + +static inline int of_property_read_string(const struct device_node *np, + const char *propname, + const char **out_string) +{ + return -ENOSYS; +} + static inline int of_property_match_string(const struct device_node *np, const char *propname, const char *string) @@ -757,6 +788,13 @@ static inline int of_property_match_string(const struct device_node *np, return -ENOSYS; } +static inline int of_property_read_string_helper(const struct device_node *np, + const char *propname, + const char **out_strs, size_t sz, int index) +{ + return -ENOSYS; +} + static inline struct device_node *of_parse_phandle(const struct device_node *np, const char *phandle_name, int index) diff --git a/include/linux/once.h b/include/linux/once.h index 6790884d3c57..9225ee6d96c7 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -6,7 +6,7 @@ #include <linux/jump_label.h> bool __do_once_start(bool *done, unsigned long *flags); -void __do_once_done(bool *done, struct static_key *once_key, +void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags); /* Call a function exactly once. The idea of DO_ONCE() is to perform @@ -39,8 +39,8 @@ void __do_once_done(bool *done, struct static_key *once_key, ({ \ bool ___ret = false; \ static bool ___done = false; \ - static struct static_key ___once_key = STATIC_KEY_INIT_TRUE; \ - if (static_key_true(&___once_key)) { \ + static DEFINE_STATIC_KEY_TRUE(___once_key); \ + if (static_branch_unlikely(&___once_key)) { \ unsigned long ___flags; \ ___ret = __do_once_start(&___done, &___flags); \ if (unlikely(___ret)) { \ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8e22f24ded6a..79b18a20cf5d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -806,6 +806,7 @@ struct perf_output_handle { struct bpf_perf_event_data_kern { struct pt_regs *regs; struct perf_sample_data *data; + struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF @@ -884,7 +885,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); -int perf_event_read_local(struct perf_event *event, u64 *value); +int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -1286,7 +1288,8 @@ static inline const struct perf_event_attr *perf_event_attrs(struct perf_event * { return ERR_PTR(-EINVAL); } -static inline int perf_event_read_local(struct perf_event *event, u64 *value) +static inline int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running) { return -EINVAL; } diff --git a/include/linux/phy.h b/include/linux/phy.h index d78cd01ea513..dc82a07cb4fd 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -451,6 +451,8 @@ struct phy_device { struct phy_led_trigger *phy_led_triggers; unsigned int phy_num_led_triggers; struct phy_led_trigger *last_triggered; + + struct phy_led_trigger *led_link_trigger; #endif /* diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index dd7a3b86bb9e..e755954d85fd 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -64,6 +64,7 @@ enum qed_ll2_roce_flavor_type { enum qed_ll2_tx_dest { QED_LL2_TX_DEST_NW, /* Light L2 TX Destination to the Network */ QED_LL2_TX_DEST_LB, /* Light L2 TX Destination to the Loopback */ + QED_LL2_TX_DEST_DROP, /* Light L2 Drop the TX packet */ QED_LL2_TX_DEST_MAX }; @@ -101,6 +102,7 @@ struct qed_ll2_comp_rx_data { void *cookie; dma_addr_t rx_buf_addr; u16 parse_flags; + u16 err_flags; u16 vlan; bool b_last_packet; u8 connection_handle; @@ -149,11 +151,16 @@ void (*qed_ll2_release_tx_packet_cb)(void *cxt, dma_addr_t first_frag_addr, bool b_last_fragment, bool b_last_packet); +typedef +void (*qed_ll2_slowpath_cb)(void *cxt, u8 connection_handle, + u32 opaque_data_0, u32 opaque_data_1); + struct qed_ll2_cbs { qed_ll2_complete_rx_packet_cb rx_comp_cb; qed_ll2_release_rx_packet_cb rx_release_cb; qed_ll2_complete_tx_packet_cb tx_comp_cb; qed_ll2_release_tx_packet_cb tx_release_cb; + qed_ll2_slowpath_cb slowpath_cb; void *cookie; }; @@ -170,6 +177,7 @@ struct qed_ll2_acquire_data_inputs { enum qed_ll2_tx_dest tx_dest; enum qed_ll2_error_handle ai_err_packet_too_big; enum qed_ll2_error_handle ai_err_no_buf; + bool secondary_queue; u8 gsi_enable; }; diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index ff3dd2ec44b4..d090d466cd0b 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -18,9 +18,11 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error); void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags); +void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, + gfp_t flags, int *new_nsid); struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, - gfp_t flags); + gfp_t flags, int *new_nsid); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags); diff --git a/include/linux/security.h b/include/linux/security.h index ce6265960d6c..73f1ef625d40 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1730,6 +1730,54 @@ static inline void securityfs_remove(struct dentry *dentry) #endif +#ifdef CONFIG_BPF_SYSCALL +union bpf_attr; +struct bpf_map; +struct bpf_prog; +struct bpf_prog_aux; +#ifdef CONFIG_SECURITY +extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); +extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); +extern int security_bpf_prog(struct bpf_prog *prog); +extern int security_bpf_map_alloc(struct bpf_map *map); +extern void security_bpf_map_free(struct bpf_map *map); +extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux); +extern void security_bpf_prog_free(struct bpf_prog_aux *aux); +#else +static inline int security_bpf(int cmd, union bpf_attr *attr, + unsigned int size) +{ + return 0; +} + +static inline int security_bpf_map(struct bpf_map *map, fmode_t fmode) +{ + return 0; +} + +static inline int security_bpf_prog(struct bpf_prog *prog) +{ + return 0; +} + +static inline int security_bpf_map_alloc(struct bpf_map *map) +{ + return 0; +} + +static inline void security_bpf_map_free(struct bpf_map *map) +{ } + +static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +{ + return 0; +} + +static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) +{ } +#endif /* CONFIG_SECURITY */ +#endif /* CONFIG_BPF_SYSCALL */ + #ifdef CONFIG_SECURITY static inline char *alloc_secdata(void) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d448a4804aea..57d712671081 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -489,8 +489,9 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, * the end of the header data, ie. at skb->end. */ struct skb_shared_info { - unsigned short _unused; - unsigned char nr_frags; + __u8 __unused; + __u8 meta_len; + __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ @@ -616,6 +617,7 @@ typedef unsigned char *sk_buff_data_t; * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function + * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_nfct: Associated connection, if any (with nfctinfo bits) * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on @@ -661,8 +663,12 @@ struct sk_buff { struct sk_buff *prev; union { - ktime_t tstamp; - u64 skb_mstamp; + struct net_device *dev; + /* Some protocols might use this space to store information, + * while device pointer would be NULL. + * UDP receive path is one user. + */ + unsigned long dev_scratch; }; }; struct rb_node rbnode; /* used in netem & tcp stack */ @@ -670,12 +676,8 @@ struct sk_buff { struct sock *sk; union { - struct net_device *dev; - /* Some protocols might use this space to store information, - * while device pointer would be NULL. - * UDP receive path is one user. - */ - unsigned long dev_scratch; + ktime_t tstamp; + u64 skb_mstamp; }; /* * This is the control buffer. It is free to use for every @@ -685,8 +687,14 @@ struct sk_buff { */ char cb[48] __aligned(8); - unsigned long _skb_refdst; - void (*destructor)(struct sk_buff *skb); + union { + struct { + unsigned long _skb_refdst; + void (*destructor)(struct sk_buff *skb); + }; + struct list_head tcp_tsorted_anchor; + }; + #ifdef CONFIG_XFRM struct sec_path *sp; #endif @@ -771,6 +779,7 @@ struct sk_buff { __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; + __u8 offload_mr_fwd_mark:1; #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; @@ -1457,27 +1466,8 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) } /** - * skb_header_release - release reference to header - * @skb: buffer to operate on - * - * Drop a reference to the header part of the buffer. This is done - * by acquiring a payload reference. You must not read from the header - * part of skb->data after this. - * Note : Check if you can use __skb_header_release() instead. - */ -static inline void skb_header_release(struct sk_buff *skb) -{ - BUG_ON(skb->nohdr); - skb->nohdr = 1; - atomic_add(1 << SKB_DATAREF_SHIFT, &skb_shinfo(skb)->dataref); -} - -/** * __skb_header_release - release reference to header * @skb: buffer to operate on - * - * Variant of skb_header_release() assuming skb is private to caller. - * We can avoid one atomic operation. */ static inline void __skb_header_release(struct sk_buff *skb) { @@ -3168,6 +3158,12 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) return __skb_grow(skb, len); } +#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) +#define skb_rb_first(root) rb_to_skb(rb_first(root)) +#define skb_rb_last(root) rb_to_skb(rb_last(root)) +#define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) +#define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) + #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ @@ -3182,6 +3178,18 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) +#define skb_rbtree_walk(skb, root) \ + for (skb = skb_rb_first(root); skb != NULL; \ + skb = skb_rb_next(skb)) + +#define skb_rbtree_walk_from(skb) \ + for (; skb != NULL; \ + skb = skb_rb_next(skb)) + +#define skb_rbtree_walk_from_safe(skb, tmp) \ + for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ + skb = tmp) + #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ @@ -3419,6 +3427,69 @@ static inline ktime_t net_invalid_timestamp(void) return 0; } +static inline u8 skb_metadata_len(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->meta_len; +} + +static inline void *skb_metadata_end(const struct sk_buff *skb) +{ + return skb_mac_header(skb); +} + +static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b, + u8 meta_len) +{ + const void *a = skb_metadata_end(skb_a); + const void *b = skb_metadata_end(skb_b); + /* Using more efficient varaiant than plain call to memcmp(). */ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + u64 diffs = 0; + + switch (meta_len) { +#define __it(x, op) (x -= sizeof(u##op)) +#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) + case 32: diffs |= __it_diff(a, b, 64); + case 24: diffs |= __it_diff(a, b, 64); + case 16: diffs |= __it_diff(a, b, 64); + case 8: diffs |= __it_diff(a, b, 64); + break; + case 28: diffs |= __it_diff(a, b, 64); + case 20: diffs |= __it_diff(a, b, 64); + case 12: diffs |= __it_diff(a, b, 64); + case 4: diffs |= __it_diff(a, b, 32); + break; + } + return diffs; +#else + return memcmp(a - meta_len, b - meta_len, meta_len); +#endif +} + +static inline bool skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b) +{ + u8 len_a = skb_metadata_len(skb_a); + u8 len_b = skb_metadata_len(skb_b); + + if (!(len_a | len_b)) + return false; + + return len_a != len_b ? + true : __skb_metadata_differs(skb_a, skb_b, len_a); +} + +static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) +{ + skb_shinfo(skb)->meta_len = meta_len; +} + +static inline void skb_metadata_clear(struct sk_buff *skb) +{ + skb_metadata_set(skb, 0); +} + struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4aa40ef02d32..22f40c96a15b 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -98,7 +98,8 @@ struct tcp_options_received { tstamp_ok : 1, /* TIMESTAMP seen on SYN packet */ dsack : 1, /* D-SACK is scheduled */ wscale_ok : 1, /* Wscale seen on SYN packet */ - sack_ok : 4, /* SACK seen on SYN packet */ + sack_ok : 3, /* SACK seen on SYN packet */ + smc_ok : 1, /* SMC seen on SYN packet */ snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ u8 num_sacks; /* Number of SACK blocks */ @@ -110,6 +111,9 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) { rx_opt->tstamp_ok = rx_opt->sack_ok = 0; rx_opt->wscale_ok = rx_opt->snd_wscale = 0; +#if IS_ENABLED(CONFIG_SMC) + rx_opt->smc_ok = 0; +#endif } /* This is the max number of SACKS that we'll generate and process. It's safe @@ -191,6 +195,7 @@ struct tcp_sock { u32 tsoffset; /* timestamp offset */ struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ + struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ u32 snd_wl1; /* Sequence for window update */ u32 snd_wnd; /* The window we expect to receive */ @@ -205,8 +210,13 @@ struct tcp_sock { u64 mstamp; /* (Re)sent time of the skb */ u32 rtt_us; /* Associated RTT */ u32 end_seq; /* Ending TCP sequence of the skb */ - u8 advanced; /* mstamp advanced since last lost marking */ - u8 reord; /* reordering detected */ + u32 last_delivered; /* tp->delivered at last reo_wnd adj */ + u8 reo_wnd_steps; /* Allowed reordering window */ +#define TCP_RACK_RECOVERY_THRESH 16 + u8 reo_wnd_persist:5, /* No. of recovery since last adj */ + dsack_seen:1, /* Whether DSACK seen after last adj */ + advanced:1, /* mstamp advanced since last lost marking */ + reord:1; /* reordering detected */ } rack; u16 advmss; /* Advertised MSS */ u32 chrono_start; /* Start time in jiffies of a TCP chrono */ @@ -214,7 +224,8 @@ struct tcp_sock { u8 chrono_type:2, /* current chronograph type */ rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ - unused:4; + fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ + unused:3; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ unused1 : 1, @@ -227,7 +238,8 @@ struct tcp_sock { syn_fastopen_ch:1, /* Active TFO re-enabling probe */ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ save_syn:1, /* Save headers of SYN packet */ - is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ + is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ + syn_smc:1; /* SYN includes SMC */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ /* RTT measurement */ diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h new file mode 100644 index 000000000000..7b69853188b1 --- /dev/null +++ b/include/linux/thunderbolt.h @@ -0,0 +1,598 @@ +/* + * Thunderbolt service API + * + * Copyright (C) 2014 Andreas Noever <andreas.noever@gmail.com> + * Copyright (C) 2017, Intel Corporation + * Authors: Michael Jamet <michael.jamet@intel.com> + * Mika Westerberg <mika.westerberg@linux.intel.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef THUNDERBOLT_H_ +#define THUNDERBOLT_H_ + +#include <linux/device.h> +#include <linux/idr.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/mod_devicetable.h> +#include <linux/pci.h> +#include <linux/uuid.h> +#include <linux/workqueue.h> + +enum tb_cfg_pkg_type { + TB_CFG_PKG_READ = 1, + TB_CFG_PKG_WRITE = 2, + TB_CFG_PKG_ERROR = 3, + TB_CFG_PKG_NOTIFY_ACK = 4, + TB_CFG_PKG_EVENT = 5, + TB_CFG_PKG_XDOMAIN_REQ = 6, + TB_CFG_PKG_XDOMAIN_RESP = 7, + TB_CFG_PKG_OVERRIDE = 8, + TB_CFG_PKG_RESET = 9, + TB_CFG_PKG_ICM_EVENT = 10, + TB_CFG_PKG_ICM_CMD = 11, + TB_CFG_PKG_ICM_RESP = 12, + TB_CFG_PKG_PREPARE_TO_SLEEP = 13, +}; + +/** + * enum tb_security_level - Thunderbolt security level + * @TB_SECURITY_NONE: No security, legacy mode + * @TB_SECURITY_USER: User approval required at minimum + * @TB_SECURITY_SECURE: One time saved key required at minimum + * @TB_SECURITY_DPONLY: Only tunnel Display port (and USB) + */ +enum tb_security_level { + TB_SECURITY_NONE, + TB_SECURITY_USER, + TB_SECURITY_SECURE, + TB_SECURITY_DPONLY, +}; + +/** + * struct tb - main thunderbolt bus structure + * @dev: Domain device + * @lock: Big lock. Must be held when accessing any struct + * tb_switch / struct tb_port. + * @nhi: Pointer to the NHI structure + * @ctl: Control channel for this domain + * @wq: Ordered workqueue for all domain specific work + * @root_switch: Root switch of this domain + * @cm_ops: Connection manager specific operations vector + * @index: Linux assigned domain number + * @security_level: Current security level + * @privdata: Private connection manager specific data + */ +struct tb { + struct device dev; + struct mutex lock; + struct tb_nhi *nhi; + struct tb_ctl *ctl; + struct workqueue_struct *wq; + struct tb_switch *root_switch; + const struct tb_cm_ops *cm_ops; + int index; + enum tb_security_level security_level; + unsigned long privdata[0]; +}; + +extern struct bus_type tb_bus_type; +extern struct device_type tb_service_type; +extern struct device_type tb_xdomain_type; + +#define TB_LINKS_PER_PHY_PORT 2 + +static inline unsigned int tb_phy_port_from_link(unsigned int link) +{ + return (link - 1) / TB_LINKS_PER_PHY_PORT; +} + +/** + * struct tb_property_dir - XDomain property directory + * @uuid: Directory UUID or %NULL if root directory + * @properties: List of properties in this directory + * + * User needs to provide serialization if needed. + */ +struct tb_property_dir { + const uuid_t *uuid; + struct list_head properties; +}; + +enum tb_property_type { + TB_PROPERTY_TYPE_UNKNOWN = 0x00, + TB_PROPERTY_TYPE_DIRECTORY = 0x44, + TB_PROPERTY_TYPE_DATA = 0x64, + TB_PROPERTY_TYPE_TEXT = 0x74, + TB_PROPERTY_TYPE_VALUE = 0x76, +}; + +#define TB_PROPERTY_KEY_SIZE 8 + +/** + * struct tb_property - XDomain property + * @list: Used to link properties together in a directory + * @key: Key for the property (always terminated). + * @type: Type of the property + * @length: Length of the property data in dwords + * @value: Property value + * + * Users use @type to determine which field in @value is filled. + */ +struct tb_property { + struct list_head list; + char key[TB_PROPERTY_KEY_SIZE + 1]; + enum tb_property_type type; + size_t length; + union { + struct tb_property_dir *dir; + u8 *data; + char *text; + u32 immediate; + } value; +}; + +struct tb_property_dir *tb_property_parse_dir(const u32 *block, + size_t block_len); +ssize_t tb_property_format_dir(const struct tb_property_dir *dir, u32 *block, + size_t block_len); +struct tb_property_dir *tb_property_create_dir(const uuid_t *uuid); +void tb_property_free_dir(struct tb_property_dir *dir); +int tb_property_add_immediate(struct tb_property_dir *parent, const char *key, + u32 value); +int tb_property_add_data(struct tb_property_dir *parent, const char *key, + const void *buf, size_t buflen); +int tb_property_add_text(struct tb_property_dir *parent, const char *key, + const char *text); +int tb_property_add_dir(struct tb_property_dir *parent, const char *key, + struct tb_property_dir *dir); +void tb_property_remove(struct tb_property *tb_property); +struct tb_property *tb_property_find(struct tb_property_dir *dir, + const char *key, enum tb_property_type type); +struct tb_property *tb_property_get_next(struct tb_property_dir *dir, + struct tb_property *prev); + +#define tb_property_for_each(dir, property) \ + for (property = tb_property_get_next(dir, NULL); \ + property; \ + property = tb_property_get_next(dir, property)) + +int tb_register_property_dir(const char *key, struct tb_property_dir *dir); +void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir); + +/** + * struct tb_xdomain - Cross-domain (XDomain) connection + * @dev: XDomain device + * @tb: Pointer to the domain + * @remote_uuid: UUID of the remote domain (host) + * @local_uuid: Cached local UUID + * @route: Route string the other domain can be reached + * @vendor: Vendor ID of the remote domain + * @device: Device ID of the demote domain + * @lock: Lock to serialize access to the following fields of this structure + * @vendor_name: Name of the vendor (or %NULL if not known) + * @device_name: Name of the device (or %NULL if not known) + * @is_unplugged: The XDomain is unplugged + * @resume: The XDomain is being resumed + * @transmit_path: HopID which the remote end expects us to transmit + * @transmit_ring: Local ring (hop) where outgoing packets are pushed + * @receive_path: HopID which we expect the remote end to transmit + * @receive_ring: Local ring (hop) where incoming packets arrive + * @service_ids: Used to generate IDs for the services + * @properties: Properties exported by the remote domain + * @property_block_gen: Generation of @properties + * @properties_lock: Lock protecting @properties. + * @get_properties_work: Work used to get remote domain properties + * @properties_retries: Number of times left to read properties + * @properties_changed_work: Work used to notify the remote domain that + * our properties have changed + * @properties_changed_retries: Number of times left to send properties + * changed notification + * @link: Root switch link the remote domain is connected (ICM only) + * @depth: Depth in the chain the remote domain is connected (ICM only) + * + * This structure represents connection across two domains (hosts). + * Each XDomain contains zero or more services which are exposed as + * &struct tb_service objects. + * + * Service drivers may access this structure if they need to enumerate + * non-standard properties but they need hold @lock when doing so + * because properties can be changed asynchronously in response to + * changes in the remote domain. + */ +struct tb_xdomain { + struct device dev; + struct tb *tb; + uuid_t *remote_uuid; + const uuid_t *local_uuid; + u64 route; + u16 vendor; + u16 device; + struct mutex lock; + const char *vendor_name; + const char *device_name; + bool is_unplugged; + bool resume; + u16 transmit_path; + u16 transmit_ring; + u16 receive_path; + u16 receive_ring; + struct ida service_ids; + struct tb_property_dir *properties; + u32 property_block_gen; + struct delayed_work get_properties_work; + int properties_retries; + struct delayed_work properties_changed_work; + int properties_changed_retries; + u8 link; + u8 depth; +}; + +int tb_xdomain_enable_paths(struct tb_xdomain *xd, u16 transmit_path, + u16 transmit_ring, u16 receive_path, + u16 receive_ring); +int tb_xdomain_disable_paths(struct tb_xdomain *xd); +struct tb_xdomain *tb_xdomain_find_by_uuid(struct tb *tb, const uuid_t *uuid); + +static inline struct tb_xdomain * +tb_xdomain_find_by_uuid_locked(struct tb *tb, const uuid_t *uuid) +{ + struct tb_xdomain *xd; + + mutex_lock(&tb->lock); + xd = tb_xdomain_find_by_uuid(tb, uuid); + mutex_unlock(&tb->lock); + + return xd; +} + +static inline struct tb_xdomain *tb_xdomain_get(struct tb_xdomain *xd) +{ + if (xd) + get_device(&xd->dev); + return xd; +} + +static inline void tb_xdomain_put(struct tb_xdomain *xd) +{ + if (xd) + put_device(&xd->dev); +} + +static inline bool tb_is_xdomain(const struct device *dev) +{ + return dev->type == &tb_xdomain_type; +} + +static inline struct tb_xdomain *tb_to_xdomain(struct device *dev) +{ + if (tb_is_xdomain(dev)) + return container_of(dev, struct tb_xdomain, dev); + return NULL; +} + +int tb_xdomain_response(struct tb_xdomain *xd, const void *response, + size_t size, enum tb_cfg_pkg_type type); +int tb_xdomain_request(struct tb_xdomain *xd, const void *request, + size_t request_size, enum tb_cfg_pkg_type request_type, + void *response, size_t response_size, + enum tb_cfg_pkg_type response_type, + unsigned int timeout_msec); + +/** + * tb_protocol_handler - Protocol specific handler + * @uuid: XDomain messages with this UUID are dispatched to this handler + * @callback: Callback called with the XDomain message. Returning %1 + * here tells the XDomain core that the message was handled + * by this handler and should not be forwared to other + * handlers. + * @data: Data passed with the callback + * @list: Handlers are linked using this + * + * Thunderbolt services can hook into incoming XDomain requests by + * registering protocol handler. Only limitation is that the XDomain + * discovery protocol UUID cannot be registered since it is handled by + * the core XDomain code. + * + * The @callback must check that the message is really directed to the + * service the driver implements. + */ +struct tb_protocol_handler { + const uuid_t *uuid; + int (*callback)(const void *buf, size_t size, void *data); + void *data; + struct list_head list; +}; + +int tb_register_protocol_handler(struct tb_protocol_handler *handler); +void tb_unregister_protocol_handler(struct tb_protocol_handler *handler); + +/** + * struct tb_service - Thunderbolt service + * @dev: XDomain device + * @id: ID of the service (shown in sysfs) + * @key: Protocol key from the properties directory + * @prtcid: Protocol ID from the properties directory + * @prtcvers: Protocol version from the properties directory + * @prtcrevs: Protocol software revision from the properties directory + * @prtcstns: Protocol settings mask from the properties directory + * + * Each domain exposes set of services it supports as collection of + * properties. For each service there will be one corresponding + * &struct tb_service. Service drivers are bound to these. + */ +struct tb_service { + struct device dev; + int id; + const char *key; + u32 prtcid; + u32 prtcvers; + u32 prtcrevs; + u32 prtcstns; +}; + +static inline struct tb_service *tb_service_get(struct tb_service *svc) +{ + if (svc) + get_device(&svc->dev); + return svc; +} + +static inline void tb_service_put(struct tb_service *svc) +{ + if (svc) + put_device(&svc->dev); +} + +static inline bool tb_is_service(const struct device *dev) +{ + return dev->type == &tb_service_type; +} + +static inline struct tb_service *tb_to_service(struct device *dev) +{ + if (tb_is_service(dev)) + return container_of(dev, struct tb_service, dev); + return NULL; +} + +/** + * tb_service_driver - Thunderbolt service driver + * @driver: Driver structure + * @probe: Called when the driver is probed + * @remove: Called when the driver is removed (optional) + * @shutdown: Called at shutdown time to stop the service (optional) + * @id_table: Table of service identifiers the driver supports + */ +struct tb_service_driver { + struct device_driver driver; + int (*probe)(struct tb_service *svc, const struct tb_service_id *id); + void (*remove)(struct tb_service *svc); + void (*shutdown)(struct tb_service *svc); + const struct tb_service_id *id_table; +}; + +#define TB_SERVICE(key, id) \ + .match_flags = TBSVC_MATCH_PROTOCOL_KEY | \ + TBSVC_MATCH_PROTOCOL_ID, \ + .protocol_key = (key), \ + .protocol_id = (id) + +int tb_register_service_driver(struct tb_service_driver *drv); +void tb_unregister_service_driver(struct tb_service_driver *drv); + +static inline void *tb_service_get_drvdata(const struct tb_service *svc) +{ + return dev_get_drvdata(&svc->dev); +} + +static inline void tb_service_set_drvdata(struct tb_service *svc, void *data) +{ + dev_set_drvdata(&svc->dev, data); +} + +static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc) +{ + return tb_to_xdomain(svc->dev.parent); +} + +/** + * struct tb_nhi - thunderbolt native host interface + * @lock: Must be held during ring creation/destruction. Is acquired by + * interrupt_work when dispatching interrupts to individual rings. + * @pdev: Pointer to the PCI device + * @iobase: MMIO space of the NHI + * @tx_rings: All Tx rings available on this host controller + * @rx_rings: All Rx rings available on this host controller + * @msix_ida: Used to allocate MSI-X vectors for rings + * @going_away: The host controller device is about to disappear so when + * this flag is set, avoid touching the hardware anymore. + * @interrupt_work: Work scheduled to handle ring interrupt when no + * MSI-X is used. + * @hop_count: Number of rings (end point hops) supported by NHI. + */ +struct tb_nhi { + spinlock_t lock; + struct pci_dev *pdev; + void __iomem *iobase; + struct tb_ring **tx_rings; + struct tb_ring **rx_rings; + struct ida msix_ida; + bool going_away; + struct work_struct interrupt_work; + u32 hop_count; +}; + +/** + * struct tb_ring - thunderbolt TX or RX ring associated with a NHI + * @lock: Lock serializing actions to this ring. Must be acquired after + * nhi->lock. + * @nhi: Pointer to the native host controller interface + * @size: Size of the ring + * @hop: Hop (DMA channel) associated with this ring + * @head: Head of the ring (write next descriptor here) + * @tail: Tail of the ring (complete next descriptor here) + * @descriptors: Allocated descriptors for this ring + * @queue: Queue holding frames to be transferred over this ring + * @in_flight: Queue holding frames that are currently in flight + * @work: Interrupt work structure + * @is_tx: Is the ring Tx or Rx + * @running: Is the ring running + * @irq: MSI-X irq number if the ring uses MSI-X. %0 otherwise. + * @vector: MSI-X vector number the ring uses (only set if @irq is > 0) + * @flags: Ring specific flags + * @sof_mask: Bit mask used to detect start of frame PDF + * @eof_mask: Bit mask used to detect end of frame PDF + * @start_poll: Called when ring interrupt is triggered to start + * polling. Passing %NULL keeps the ring in interrupt mode. + * @poll_data: Data passed to @start_poll + */ +struct tb_ring { + spinlock_t lock; + struct tb_nhi *nhi; + int size; + int hop; + int head; + int tail; + struct ring_desc *descriptors; + dma_addr_t descriptors_dma; + struct list_head queue; + struct list_head in_flight; + struct work_struct work; + bool is_tx:1; + bool running:1; + int irq; + u8 vector; + unsigned int flags; + u16 sof_mask; + u16 eof_mask; + void (*start_poll)(void *data); + void *poll_data; +}; + +/* Leave ring interrupt enabled on suspend */ +#define RING_FLAG_NO_SUSPEND BIT(0) +/* Configure the ring to be in frame mode */ +#define RING_FLAG_FRAME BIT(1) +/* Enable end-to-end flow control */ +#define RING_FLAG_E2E BIT(2) + +struct ring_frame; +typedef void (*ring_cb)(struct tb_ring *, struct ring_frame *, bool canceled); + +/** + * enum ring_desc_flags - Flags for DMA ring descriptor + * %RING_DESC_ISOCH: Enable isonchronous DMA (Tx only) + * %RING_DESC_CRC_ERROR: In frame mode CRC check failed for the frame (Rx only) + * %RING_DESC_COMPLETED: Descriptor completed (set by NHI) + * %RING_DESC_POSTED: Always set this + * %RING_DESC_BUFFER_OVERRUN: RX buffer overrun + * %RING_DESC_INTERRUPT: Request an interrupt on completion + */ +enum ring_desc_flags { + RING_DESC_ISOCH = 0x1, + RING_DESC_CRC_ERROR = 0x1, + RING_DESC_COMPLETED = 0x2, + RING_DESC_POSTED = 0x4, + RING_DESC_BUFFER_OVERRUN = 0x04, + RING_DESC_INTERRUPT = 0x8, +}; + +/** + * struct ring_frame - For use with ring_rx/ring_tx + * @buffer_phy: DMA mapped address of the frame + * @callback: Callback called when the frame is finished (optional) + * @list: Frame is linked to a queue using this + * @size: Size of the frame in bytes (%0 means %4096) + * @flags: Flags for the frame (see &enum ring_desc_flags) + * @eof: End of frame protocol defined field + * @sof: Start of frame protocol defined field + */ +struct ring_frame { + dma_addr_t buffer_phy; + ring_cb callback; + struct list_head list; + u32 size:12; + u32 flags:12; + u32 eof:4; + u32 sof:4; +}; + +/* Minimum size for ring_rx */ +#define TB_FRAME_SIZE 0x100 + +struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size, + unsigned int flags); +struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, + unsigned int flags, u16 sof_mask, u16 eof_mask, + void (*start_poll)(void *), void *poll_data); +void tb_ring_start(struct tb_ring *ring); +void tb_ring_stop(struct tb_ring *ring); +void tb_ring_free(struct tb_ring *ring); + +int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame); + +/** + * tb_ring_rx() - enqueue a frame on an RX ring + * @ring: Ring to enqueue the frame + * @frame: Frame to enqueue + * + * @frame->buffer, @frame->buffer_phy have to be set. The buffer must + * contain at least %TB_FRAME_SIZE bytes. + * + * @frame->callback will be invoked with @frame->size, @frame->flags, + * @frame->eof, @frame->sof set once the frame has been received. + * + * If ring_stop() is called after the packet has been enqueued + * @frame->callback will be called with canceled set to true. + * + * Return: Returns %-ESHUTDOWN if ring_stop has been called. Zero otherwise. + */ +static inline int tb_ring_rx(struct tb_ring *ring, struct ring_frame *frame) +{ + WARN_ON(ring->is_tx); + return __tb_ring_enqueue(ring, frame); +} + +/** + * tb_ring_tx() - enqueue a frame on an TX ring + * @ring: Ring the enqueue the frame + * @frame: Frame to enqueue + * + * @frame->buffer, @frame->buffer_phy, @frame->size, @frame->eof and + * @frame->sof have to be set. + * + * @frame->callback will be invoked with once the frame has been transmitted. + * + * If ring_stop() is called after the packet has been enqueued @frame->callback + * will be called with canceled set to true. + * + * Return: Returns %-ESHUTDOWN if ring_stop has been called. Zero otherwise. + */ +static inline int tb_ring_tx(struct tb_ring *ring, struct ring_frame *frame) +{ + WARN_ON(!ring->is_tx); + return __tb_ring_enqueue(ring, frame); +} + +/* Used only when the ring is in polling mode */ +struct ring_frame *tb_ring_poll(struct tb_ring *ring); +void tb_ring_poll_complete(struct tb_ring *ring); + +/** + * tb_ring_dma_device() - Return device used for DMA mapping + * @ring: Ring whose DMA device is retrieved + * + * Use this function when you are mapping DMA for buffers that are + * passed to the ring for sending/receiving. + */ +static inline struct device *tb_ring_dma_device(struct tb_ring *ring) +{ + return &ring->nhi->pdev->dev; +} + +#endif /* THUNDERBOLT_H_ */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2bcb4dc6df1a..84014ecfa67f 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -272,14 +272,37 @@ struct trace_event_call { #ifdef CONFIG_PERF_EVENTS int perf_refcount; struct hlist_head __percpu *perf_events; - struct bpf_prog *prog; - struct perf_event *bpf_prog_owner; + struct bpf_prog_array __rcu *prog_array; int (*perf_perm)(struct trace_event_call *, struct perf_event *); #endif }; +#ifdef CONFIG_PERF_EVENTS +static inline bool bpf_prog_array_valid(struct trace_event_call *call) +{ + /* + * This inline function checks whether call->prog_array + * is valid or not. The function is called in various places, + * outside rcu_read_lock/unlock, as a heuristic to speed up execution. + * + * If this function returns true, and later call->prog_array + * becomes false inside rcu_read_lock/unlock region, + * we bail out then. If this function return false, + * there is a risk that we might miss a few events if the checking + * were delayed until inside rcu_read_lock/unlock region and + * call->prog_array happened to become non-NULL then. + * + * Here, READ_ONCE() is used instead of rcu_access_pointer(). + * rcu_access_pointer() requires the actual definition of + * "struct bpf_prog_array" while READ_ONCE() only needs + * a declaration of the same type. + */ + return !!READ_ONCE(call->prog_array); +} +#endif + static inline const char * trace_event_name(struct trace_event_call *call) { @@ -436,12 +459,23 @@ trace_trigger_soft_disabled(struct trace_event_file *file) } #ifdef CONFIG_BPF_EVENTS -unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx); +unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); +int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog); +void perf_event_detach_bpf_prog(struct perf_event *event); #else -static inline unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx) +static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { return 1; } + +static inline int +perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} + +static inline void perf_event_detach_bpf_prog(struct perf_event *event) { } + #endif enum { @@ -512,6 +546,7 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type, { perf_tp_event(type, count, raw_data, size, regs, head, rctx, task, event); } + #endif #endif /* _LINUX_TRACE_EVENT_H */ |