diff options
Diffstat (limited to 'include/linux')
37 files changed, 654 insertions, 257 deletions
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a4c644c1c091..cb3c6b3b89c8 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -17,6 +17,8 @@ struct bpf_map; struct bpf_prog; struct bpf_sock_ops_kern; struct bpf_cgroup_storage; +struct ctl_table; +struct ctl_table_header; #ifdef CONFIG_CGROUP_BPF @@ -109,6 +111,12 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum bpf_attach_type type); +int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, + struct ctl_table *table, int write, + void __user *buf, size_t *pcount, + loff_t *ppos, void **new_buf, + enum bpf_attach_type type); + static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -253,6 +261,18 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, \ __ret; \ }) + + +#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos, nbuf) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ + buf, count, pos, nbuf, \ + BPF_CGROUP_SYSCTL); \ + __ret; \ +}) + int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog); int cgroup_bpf_prog_detach(const union bpf_attr *attr, @@ -321,6 +341,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; }) #define for_each_cgroup_storage_type(stype) for (; false; ) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 944ccc310201..59631dd0777c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -57,6 +57,12 @@ struct bpf_map_ops { const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); + + /* Direct value access helpers. */ + int (*map_direct_value_addr)(const struct bpf_map *map, + u64 *imm, u32 off); + int (*map_direct_value_meta)(const struct bpf_map *map, + u64 imm, u32 *off); }; struct bpf_map { @@ -81,7 +87,8 @@ struct bpf_map { struct btf *btf; u32 pages; bool unpriv_array; - /* 51 bytes hole */ + bool frozen; /* write-once */ + /* 48 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. @@ -177,6 +184,7 @@ enum bpf_arg_type { ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ + ARG_PTR_TO_MAP_VALUE_OR_NULL, /* pointer to stack used as map value or NULL */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack @@ -195,6 +203,9 @@ enum bpf_arg_type { ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ + ARG_PTR_TO_INT, /* pointer to int */ + ARG_PTR_TO_LONG, /* pointer to long */ + ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ }; /* type of values returned from helper functions */ @@ -205,6 +216,7 @@ enum bpf_return_type { RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ + RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -262,6 +274,7 @@ enum bpf_reg_type { PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ + PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ }; /* The information passed from prog-specific *_is_valid_access @@ -351,6 +364,7 @@ struct bpf_prog_aux { u32 used_map_cnt; u32 max_ctx_offset; u32 max_pkt_offset; + u32 max_tp_access; u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ @@ -420,8 +434,38 @@ struct bpf_array { }; }; +#define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 32 +#define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ + BPF_F_RDONLY_PROG | \ + BPF_F_WRONLY | \ + BPF_F_WRONLY_PROG) + +#define BPF_MAP_CAN_READ BIT(0) +#define BPF_MAP_CAN_WRITE BIT(1) + +static inline u32 bpf_map_flags_to_cap(struct bpf_map *map) +{ + u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); + + /* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is + * not possible. + */ + if (access_flags & BPF_F_RDONLY_PROG) + return BPF_MAP_CAN_READ; + else if (access_flags & BPF_F_WRONLY_PROG) + return BPF_MAP_CAN_WRITE; + else + return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE; +} + +static inline bool bpf_map_flags_access_ok(u32 access_flags) +{ + return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) != + (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); +} + struct bpf_event_entry { struct perf_event *event; struct file *perf_file; @@ -445,14 +489,6 @@ typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); -int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, - union bpf_attr __user *uattr); -int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, - union bpf_attr __user *uattr); -int bpf_prog_test_run_flow_dissector(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: @@ -643,6 +679,13 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); int array_map_alloc_check(union bpf_attr *attr); +int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -754,6 +797,27 @@ static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, { return ERR_PTR(-EOPNOTSUPP); } + +static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} + +static inline int bpf_prog_test_run_skb(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} + +static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, @@ -929,6 +993,8 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_spin_lock_proto; extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; +extern const struct bpf_func_proto bpf_strtol_proto; +extern const struct bpf_func_proto bpf_strtoul_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 08bf2f1fe553..5a9975678d6f 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -25,9 +25,11 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) +BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) #endif #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl) #endif #ifdef CONFIG_BPF_LIRC_MODE2 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) @@ -59,6 +61,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) #if defined(CONFIG_BPF_STREAM_PARSER) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7d8228d1c898..1305ccbd8fe6 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -207,6 +207,7 @@ struct bpf_verifier_state { struct bpf_verifier_state_list { struct bpf_verifier_state state; struct bpf_verifier_state_list *next; + int miss_cnt, hit_cnt; }; /* Possible states for alu_state member. */ @@ -223,6 +224,10 @@ struct bpf_insn_aux_data { unsigned long map_state; /* pointer/poison value for maps */ s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ + struct { + u32 map_index; /* index into used_maps[] */ + u32 map_off; /* offset from value base address */ + }; }; int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ int sanitize_stack_off; /* stack slot to be cleared */ @@ -248,6 +253,12 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) return log->len_used >= log->len_total - 1; } +#define BPF_LOG_LEVEL1 1 +#define BPF_LOG_LEVEL2 2 +#define BPF_LOG_STATS 4 +#define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) +#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) + static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { return log->level && log->ubuf && !bpf_verifier_log_full(log); @@ -274,6 +285,7 @@ struct bpf_verifier_env { bool strict_alignment; /* perform strict pointer alignment checks */ struct bpf_verifier_state *cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ + struct bpf_verifier_state_list *free_list; 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 */ @@ -283,7 +295,27 @@ struct bpf_verifier_env { const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; + struct { + int *insn_state; + int *insn_stack; + int cur_stack; + } cfg; u32 subprog_cnt; + /* number of instructions analyzed by the verifier */ + u32 insn_processed; + /* total verification time */ + u64 verification_time; + /* maximum number of verifier states kept in 'branching' instructions */ + u32 max_states_per_insn; + /* total number of allocated verifier states */ + u32 total_states; + /* some states are freed during program analysis. + * this is peak number of states. this number dominates kernel + * memory consumption during verification + */ + u32 peak_states; + /* longest register parentage chain walked for liveness marking */ + u32 longest_mark_read_walk; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, diff --git a/include/linux/btf.h b/include/linux/btf.h index 455d31b55828..64cdf2a23d42 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -51,6 +51,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); +bool btf_type_is_void(const struct btf_type *t); #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index aa8bfd6f738c..25c0d049336f 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -33,7 +33,7 @@ struct device; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); -u32 eth_get_headlen(void *data, unsigned int max_len); +u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; diff --git a/include/linux/filter.h b/include/linux/filter.h index 6074aa064b54..fb0edad75971 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -33,6 +33,8 @@ struct bpf_prog_aux; struct xdp_rxq_info; struct xdp_buff; struct sock_reuseport; +struct ctl_table; +struct ctl_table_header; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function @@ -1177,4 +1179,18 @@ struct bpf_sock_ops_kern { */ }; +struct bpf_sysctl_kern { + struct ctl_table_header *head; + struct ctl_table *table; + void *cur_val; + size_t cur_len; + void *new_val; + size_t new_len; + int new_updated; + int write; + loff_t *ppos; + /* Temporary "register" for indirect stores to ppos. */ + u64 tmp_reg; +}; + #endif /* __LINUX_FILTER_H__ */ diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 83f81ac53282..6cb82301d8e9 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -233,7 +233,6 @@ const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd) { \ handler \ .cmd = op_name, \ - .policy = CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy), \ }, #define ZZZ_genl_ops CONCAT_(GENL_MAGIC_FAMILY, _genl_ops) @@ -290,7 +289,8 @@ static struct genl_family ZZZ_genl_family __ro_after_init = { #ifdef GENL_MAGIC_FAMILY_HDRSZ .hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ), #endif - .maxattr = ARRAY_SIZE(drbd_tla_nl_policy)-1, + .maxattr = ARRAY_SIZE(CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy))-1, + .policy = CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy), .ops = ZZZ_genl_ops, .n_ops = ARRAY_SIZE(ZZZ_genl_ops), .mcgrps = ZZZ_genl_mcgrps, diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 48703ec60d06..61f0a316c6ac 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1557,7 +1557,7 @@ struct ieee80211_vht_operation { * struct ieee80211_he_cap_elem - HE capabilities element * * This structure is the "HE capabilities element" fixed fields as - * described in P802.11ax_D3.0 section 9.4.2.237.2 and 9.4.2.237.3 + * described in P802.11ax_D4.0 section 9.4.2.242.2 and 9.4.2.242.3 */ struct ieee80211_he_cap_elem { u8 mac_cap_info[6]; @@ -1619,12 +1619,12 @@ struct ieee80211_he_mcs_nss_supp { * struct ieee80211_he_operation - HE capabilities element * * This structure is the "HE operation element" fields as - * described in P802.11ax_D3.0 section 9.4.2.238 + * described in P802.11ax_D4.0 section 9.4.2.243 */ struct ieee80211_he_operation { __le32 he_oper_params; __le16 he_mcs_nss_set; - /* Optional 0,1,3 or 4 bytes: depends on @he_oper_params */ + /* Optional 0,1,3,4,5,7 or 8 bytes: depends on @he_oper_params */ u8 optional[0]; } __packed; @@ -1632,7 +1632,7 @@ struct ieee80211_he_operation { * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field * * This structure is the "MU AC Parameter Record" fields as - * described in P802.11ax_D2.0 section 9.4.2.240 + * described in P802.11ax_D4.0 section 9.4.2.245 */ struct ieee80211_he_mu_edca_param_ac_rec { u8 aifsn; @@ -1644,7 +1644,7 @@ struct ieee80211_he_mu_edca_param_ac_rec { * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element * * This structure is the "MU EDCA Parameter Set element" fields as - * described in P802.11ax_D2.0 section 9.4.2.240 + * described in P802.11ax_D4.0 section 9.4.2.245 */ struct ieee80211_mu_edca_param_set { u8 mu_qos_info; @@ -2026,6 +2026,7 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00004000 #define IEEE80211_HE_OPERATION_CO_HOSTED_BSS 0x00008000 #define IEEE80211_HE_OPERATION_ER_SU_DISABLE 0x00010000 +#define IEEE80211_HE_OPERATION_6GHZ_OP_INFO 0x00020000 #define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x3f000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 @@ -2056,6 +2057,8 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) oper_len += 3; if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) oper_len++; + if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO) + oper_len += 4; /* Add the first byte (extension ID) to the total length */ oper_len++; @@ -2487,6 +2490,7 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_HE_MU_EDCA = 38, WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME = 52, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION = 55, + WLAN_EID_EXT_NON_INHERITANCE = 56, }; /* Action category code */ diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 627b788ba0ff..ef0819ced0fc 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -56,9 +56,6 @@ struct br_ip_list { extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); -typedef int br_should_route_hook_t(struct sk_buff *skb); -extern br_should_route_hook_t __rcu *br_should_route_hook; - #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING) int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list); diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index a64f21a97369..367dc2a0f84a 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -237,6 +237,20 @@ static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) return rtnl_dereference(dev->ip_ptr); } +/* called with rcu_read_lock or rtnl held */ +static inline bool ip_ignore_linkdown(const struct net_device *dev) +{ + struct in_device *in_dev; + bool rc = false; + + in_dev = rcu_dereference_rtnl(dev->ip_ptr); + if (in_dev && + IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) + rc = true; + + return rc; +} + static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index fa928242567d..1b6d31da7cbc 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -297,6 +297,7 @@ static inline u64 jiffies_to_nsecs(const unsigned long j) } extern u64 jiffies64_to_nsecs(u64 j); +extern u64 jiffies64_to_msecs(u64 j); extern unsigned long __msecs_to_jiffies(const unsigned int m); #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 73d04743a2bb..af6b11d4d673 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -34,5 +34,6 @@ /* struct phy_device dev_flags definitions */ #define MARVELL_PHY_M1145_FLAGS_RESISTANCE 0x00000001 #define MARVELL_PHY_M1118_DNS323_LEDS 0x00000002 +#define MARVELL_PHY_LED0_LINK_LED1_ACTIVE 0x00000004 #endif /* _MARVELL_PHY_H */ diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 3e99ae3ed87f..9dc16d5705a1 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -39,7 +39,8 @@ struct mdio_device { /* Bus address of the MDIO device (0-31) */ int addr; int flags; - struct gpio_desc *reset; + struct gpio_desc *reset_gpio; + struct reset_control *reset_ctrl; unsigned int reset_assert_delay; unsigned int reset_deassert_delay; }; diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 612c8c2f2466..769326ea1d9b 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -170,7 +170,7 @@ static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd, doorbell[0] = cpu_to_be32(sn << 28 | cmd | ci); doorbell[1] = cpu_to_be32(cq->cqn); - mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, NULL); + mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL); } static inline void mlx5_cq_hold(struct mlx5_core_cq *cq) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f93a5598b942..db7dca75d726 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -361,6 +361,7 @@ enum { enum { MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1, + MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT = 0x5, }; enum { diff --git a/include/linux/mlx5/doorbell.h b/include/linux/mlx5/doorbell.h index 0787de28f2fc..5c267707e1df 100644 --- a/include/linux/mlx5/doorbell.h +++ b/include/linux/mlx5/doorbell.h @@ -36,46 +36,25 @@ #define MLX5_BF_OFFSET 0x800 #define MLX5_CQ_DOORBELL 0x20 -#if BITS_PER_LONG == 64 /* Assume that we can just write a 64-bit doorbell atomically. s390 * actually doesn't have writeq() but S/390 systems don't even have * PCI so we won't worry about it. + * + * Note that the write is not atomic on 32-bit systems! In contrast to 64-bit + * ones, it requires proper locking. mlx5_write64 doesn't do any locking, so use + * it at your own discretion, protected by some kind of lock on 32 bits. + * + * TODO: use write{q,l}_relaxed() */ -#define MLX5_DECLARE_DOORBELL_LOCK(name) -#define MLX5_INIT_DOORBELL_LOCK(ptr) do { } while (0) -#define MLX5_GET_DOORBELL_LOCK(ptr) (NULL) - -static inline void mlx5_write64(__be32 val[2], void __iomem *dest, - spinlock_t *doorbell_lock) +static inline void mlx5_write64(__be32 val[2], void __iomem *dest) { +#if BITS_PER_LONG == 64 __raw_writeq(*(u64 *)val, dest); -} - #else - -/* Just fall back to a spinlock to protect the doorbell if - * BITS_PER_LONG is 32 -- there's no portable way to do atomic 64-bit - * MMIO writes. - */ - -#define MLX5_DECLARE_DOORBELL_LOCK(name) spinlock_t name; -#define MLX5_INIT_DOORBELL_LOCK(ptr) spin_lock_init(ptr) -#define MLX5_GET_DOORBELL_LOCK(ptr) (ptr) - -static inline void mlx5_write64(__be32 val[2], void __iomem *dest, - spinlock_t *doorbell_lock) -{ - unsigned long flags; - - if (doorbell_lock) - spin_lock_irqsave(doorbell_lock, flags); __raw_writel((__force u32) val[0], dest); __raw_writel((__force u32) val[1], dest + 4); - if (doorbell_lock) - spin_unlock_irqrestore(doorbell_lock, flags); -} - #endif +} #endif /* MLX5_DOORBELL_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 0d0729648844..d2d380d5e415 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -133,6 +133,7 @@ enum { MLX5_REG_MTRC_CONF = 0x9041, MLX5_REG_MTRC_STDB = 0x9042, MLX5_REG_MTRC_CTRL = 0x9043, + MLX5_REG_MPEIN = 0x9050, MLX5_REG_MPCNT = 0x9051, MLX5_REG_MTPPS = 0x9053, MLX5_REG_MTPPSE = 0x9054, @@ -662,6 +663,7 @@ struct mlx5_core_dev { u64 sys_image_guid; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; + phys_addr_t bar_addr; enum mlx5_device_state state; /* sync interface state */ struct mutex intf_state_mutex; @@ -887,6 +889,7 @@ void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); +void mlx5_health_flush(struct mlx5_core_dev *dev); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 9df51da04621..fd91df3a4e09 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -75,6 +75,12 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_EGRESS, }; +enum { + FDB_BYPASS_PATH, + FDB_FAST_PATH, + FDB_SLOW_PATH, +}; + struct mlx5_flow_table; struct mlx5_flow_group; struct mlx5_flow_namespace; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3b83288749c6..0e0e63d4d7aa 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5110,6 +5110,7 @@ enum { MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0 = 0x14, MLX5_ACTION_IN_FIELD_OUT_SIPV4 = 0x15, MLX5_ACTION_IN_FIELD_OUT_DIPV4 = 0x16, + MLX5_ACTION_IN_FIELD_OUT_FIRST_VID = 0x17, MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47, }; @@ -8026,6 +8027,52 @@ struct mlx5_ifc_ppcnt_reg_bits { union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; }; +struct mlx5_ifc_mpein_reg_bits { + u8 reserved_at_0[0x2]; + u8 depth[0x6]; + u8 pcie_index[0x8]; + u8 node[0x8]; + u8 reserved_at_18[0x8]; + + u8 capability_mask[0x20]; + + u8 reserved_at_40[0x8]; + u8 link_width_enabled[0x8]; + u8 link_speed_enabled[0x10]; + + u8 lane0_physical_position[0x8]; + u8 link_width_active[0x8]; + u8 link_speed_active[0x10]; + + u8 num_of_pfs[0x10]; + u8 num_of_vfs[0x10]; + + u8 bdf0[0x10]; + u8 reserved_at_b0[0x10]; + + u8 max_read_request_size[0x4]; + u8 max_payload_size[0x4]; + u8 reserved_at_c8[0x5]; + u8 pwr_status[0x3]; + u8 port_type[0x4]; + u8 reserved_at_d4[0xb]; + u8 lane_reversal[0x1]; + + u8 reserved_at_e0[0x14]; + u8 pci_power[0xc]; + + u8 reserved_at_100[0x20]; + + u8 device_status[0x10]; + u8 port_state[0x8]; + u8 reserved_at_138[0x8]; + + u8 reserved_at_140[0x10]; + u8 receiver_detect_result[0x10]; + + u8 reserved_at_160[0x20]; +}; + struct mlx5_ifc_mpcnt_reg_bits { u8 reserved_at_0[0x8]; u8 pcie_index[0x8]; @@ -8345,7 +8392,9 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x74]; + u8 reserved_at_0[0x6e]; + u8 pci_status_and_power[0x1]; + u8 reserved_at_6f[0x5]; u8 mark_tx_action_cnp[0x1]; u8 mark_tx_action_cqe[0x1]; u8 dynamic_tx_overflow[0x1]; @@ -8953,6 +9002,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_pmtu_reg_bits pmtu_reg; struct mlx5_ifc_ppad_reg_bits ppad_reg; struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg; + struct mlx5_ifc_mpein_reg_bits mpein_reg; struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg; struct mlx5_ifc_pplm_reg_bits pplm_reg; struct mlx5_ifc_pplr_reg_bits pplr_reg; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 0343c81d4c5f..3ba4edbd17a6 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -395,6 +395,7 @@ struct mlx5_wqe_signature_seg { struct mlx5_wqe_inline_seg { __be32 byte_count; + __be32 data[0]; }; enum mlx5_sig_type { diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index 97ca105347a6..5685805533b5 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -111,6 +111,18 @@ struct sdio_driver { extern int sdio_register_driver(struct sdio_driver *); extern void sdio_unregister_driver(struct sdio_driver *); +/** + * module_sdio_driver() - Helper macro for registering a SDIO driver + * @__sdio_driver: sdio_driver struct + * + * Helper macro for SDIO drivers which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only + * use this macro once, and calling it replaces module_init() and module_exit() + */ +#define module_sdio_driver(__sdio_driver) \ + module_driver(__sdio_driver, sdio_register_driver, \ + sdio_unregister_driver) + /* * SDIO I/O operations */ diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 4332199c71c2..d1a5d5df02f5 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -59,6 +59,8 @@ #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 #define SDIO_DEVICE_ID_MARVELL_8887WLAN 0x9134 +#define SDIO_VENDOR_ID_MEDIATEK 0x037a + #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 #define SDIO_DEVICE_ID_SIANO_NICE 0x0202 diff --git a/include/linux/net.h b/include/linux/net.h index c606c72311d0..50bf5206ead6 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -161,6 +161,8 @@ struct proto_ops { int (*compat_ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); #endif + int (*gettstamp) (struct socket *sock, void __user *userstamp, + bool timeval, bool time32); int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 324e872c91d1..44b47e9df94a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -194,8 +194,8 @@ struct net_device_stats { #ifdef CONFIG_RPS #include <linux/static_key.h> -extern struct static_key rps_needed; -extern struct static_key rfs_needed; +extern struct static_key_false rps_needed; +extern struct static_key_false rfs_needed; #endif struct neighbour; @@ -914,34 +914,13 @@ struct xfrmdev_ops { }; #endif -#if IS_ENABLED(CONFIG_TLS_DEVICE) -enum tls_offload_ctx_dir { - TLS_OFFLOAD_CTX_DIR_RX, - TLS_OFFLOAD_CTX_DIR_TX, -}; - -struct tls_crypto_info; -struct tls_context; - -struct tlsdev_ops { - int (*tls_dev_add)(struct net_device *netdev, struct sock *sk, - enum tls_offload_ctx_dir direction, - struct tls_crypto_info *crypto_info, - u32 start_offload_tcp_sn); - void (*tls_dev_del)(struct net_device *netdev, - struct tls_context *ctx, - enum tls_offload_ctx_dir direction); - void (*tls_dev_resync_rx)(struct net_device *netdev, - struct sock *sk, u32 seq, u64 rcd_sn); -}; -#endif - struct dev_ifalias { struct rcu_head rcuhead; char ifalias[]; }; struct devlink; +struct tlsdev_ops; /* * This structure defines the management hooks for network devices. @@ -986,8 +965,7 @@ struct devlink; * those the driver believes to be appropriate. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - * struct net_device *sb_dev, - * select_queue_fallback_t fallback); + * struct net_device *sb_dev); * Called to decide which queue to use when device supports multiple * transmit queues. * @@ -1251,8 +1229,8 @@ struct devlink; * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. - * struct devlink *(*ndo_get_devlink)(struct net_device *dev); - * Get devlink instance associated with a given netdev. + * struct devlink_port *(*ndo_get_devlink_port)(struct net_device *dev); + * Get devlink port instance associated with a given netdev. * Called with a reference on the netdevice and devlink locks only, * rtnl_lock is not held. */ @@ -1268,8 +1246,7 @@ struct net_device_ops { netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -1453,7 +1430,7 @@ struct net_device_ops { u32 flags); int (*ndo_xsk_async_xmit)(struct net_device *dev, u32 queue_id); - struct devlink * (*ndo_get_devlink)(struct net_device *dev); + struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); }; /** @@ -2155,9 +2132,11 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, &qdisc_xmit_lock_key); \ } -struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb, - struct net_device *sb_dev); +u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev); +struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, + struct sk_buff *skb, + struct net_device *sb_dev); /* returns the headroom that the master device needs to take in account * when forwarding to this dev @@ -2642,11 +2621,9 @@ void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback); + struct net_device *sb_dev); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); @@ -2664,14 +2641,6 @@ void netdev_freemem(struct net_device *dev); void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); -DECLARE_PER_CPU(int, xmit_recursion); -#define XMIT_RECURSION_LIMIT 10 - -static inline int dev_recursion_level(void) -{ - return this_cpu_read(xmit_recursion); -} - struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); @@ -3020,6 +2989,11 @@ struct softnet_data { #ifdef CONFIG_XFRM_OFFLOAD struct sk_buff_head xfrm_backlog; #endif + /* written and read only by owning cpu: */ + struct { + u16 recursion; + u8 more; + } xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, * and only read by other cpus. Worth using a cache line. @@ -3055,6 +3029,28 @@ static inline void input_queue_tail_incr_save(struct softnet_data *sd, DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +static inline int dev_recursion_level(void) +{ + return this_cpu_read(softnet_data.xmit.recursion); +} + +#define XMIT_RECURSION_LIMIT 10 +static inline bool dev_xmit_recursion(void) +{ + return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > + XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + __this_cpu_inc(softnet_data.xmit.recursion); +} + +static inline void dev_xmit_recursion_dec(void) +{ + __this_cpu_dec(softnet_data.xmit.recursion); +} + void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); @@ -4410,10 +4406,15 @@ static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) { - skb->xmit_more = more ? 1 : 0; + __this_cpu_write(softnet_data.xmit.more, more); return ops->ndo_start_xmit(skb, dev); } +static inline bool netdev_xmit_more(void) +{ + return __this_cpu_read(softnet_data.xmit.more); +} + static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) { diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 72cb19c3db6a..a7252f3baeb0 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -24,10 +24,17 @@ static inline int NF_DROP_GETERR(int verdict) static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) { +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + const unsigned long *ul1 = (const unsigned long *)a1; + const unsigned long *ul2 = (const unsigned long *)a2; + + return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; +#else return a1->all[0] == a2->all[0] && a1->all[1] == a2->all[1] && a1->all[2] == a2->all[2] && a1->all[3] == a2->all[3]; +#endif } static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, @@ -360,7 +367,7 @@ extern struct nf_nat_hook __rcu *nf_nat_hook; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) struct nf_nat_hook *nat_hook; rcu_read_lock(); diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index f2e1e6b13ca4..e499d170f12d 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -401,33 +401,30 @@ ip_set_get_h16(const struct nlattr *attr) return ntohs(nla_get_be16(attr)); } -#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr | NLA_F_NESTED) -#define ipset_nest_end(skb, start) nla_nest_end(skb, start) - static inline int nla_put_ipaddr4(struct sk_buff *skb, int type, __be32 ipaddr) { - struct nlattr *__nested = ipset_nest_start(skb, type); + struct nlattr *__nested = nla_nest_start(skb, type); int ret; if (!__nested) return -EMSGSIZE; ret = nla_put_in_addr(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr); if (!ret) - ipset_nest_end(skb, __nested); + nla_nest_end(skb, __nested); return ret; } static inline int nla_put_ipaddr6(struct sk_buff *skb, int type, const struct in6_addr *ipaddrptr) { - struct nlattr *__nested = ipset_nest_start(skb, type); + struct nlattr *__nested = nla_nest_start(skb, type); int ret; if (!__nested) return -EMSGSIZE; ret = nla_put_in6_addr(skb, IPSET_ATTR_IPADDR_IPV6, ipaddrptr); if (!ret) - ipset_nest_end(skb, __nested); + nla_nest_end(skb, __nested); return ret; } diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h index c6000046c966..788613f36935 100644 --- a/include/linux/netfilter/nfnetlink_osf.h +++ b/include/linux/netfilter/nfnetlink_osf.h @@ -21,13 +21,18 @@ struct nf_osf_finger { struct nf_osf_user_finger finger; }; +struct nf_osf_data { + const char *genre; + const char *version; +}; + bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, int hooknum, struct net_device *in, struct net_device *out, const struct nf_osf_info *info, struct net *net, const struct list_head *nf_osf_fingers); -const char *nf_osf_find(const struct sk_buff *skb, - const struct list_head *nf_osf_fingers, - const int ttl_check); +bool nf_osf_find(const struct sk_buff *skb, + const struct list_head *nf_osf_fingers, + const int ttl_check, struct nf_osf_data *data); #endif /* _NFOSF_H */ diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index bf384b3eedb8..1f852ef7b098 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -317,7 +317,6 @@ struct xt_table_info *xt_replace_table(struct xt_table *table, int *error); struct xt_match *xt_find_match(u8 af, const char *name, u8 revision); -struct xt_target *xt_find_target(u8 af, const char *name, u8 revision); struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision); struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision); int xt_find_revision(u8 af, const char *name, u8 revision, int target, diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 471e9467105b..12113e502656 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -87,6 +87,21 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, } int ip6_route_me_harder(struct net *net, struct sk_buff *skb); + +static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return -EHOSTUNREACH; + + return v6_ops->route_me_harder(net, skb); +#else + return ip6_route_me_harder(net, skb); +#endif +} + __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); diff --git a/include/linux/phy.h b/include/linux/phy.h index 34084892a466..0f9552b17ee7 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -345,6 +345,7 @@ struct phy_c45_device_ids { * is_c45: Set to true if this phy uses clause 45 addressing. * is_internal: Set to true if this phy is internal to a MAC. * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc. + * is_gigabit_capable: Set to true if PHY supports 1000Mbps * has_fixups: Set to true if this phy has fixups/quirks. * suspended: Set to true if this phy has been suspended successfully. * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. @@ -382,6 +383,7 @@ struct phy_device { unsigned is_c45:1; unsigned is_internal:1; unsigned is_pseudo_fixed_link:1; + unsigned is_gigabit_capable:1; unsigned has_fixups:1; unsigned suspended:1; unsigned sysfs_links:1; @@ -390,6 +392,7 @@ struct phy_device { unsigned autoneg:1; /* The most recently read link state */ unsigned link:1; + unsigned autoneg_complete:1; /* Interrupts are enabled */ unsigned interrupts:1; @@ -1075,6 +1078,7 @@ void phy_attached_info(struct phy_device *phydev); /* Clause 22 PHY */ int genphy_config_init(struct phy_device *phydev); +int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_eee_advert(struct phy_device *phydev); diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h new file mode 100644 index 000000000000..368530f98176 --- /dev/null +++ b/include/linux/platform_data/xilinx-ll-temac.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_XILINX_LL_TEMAC_H +#define __LINUX_XILINX_LL_TEMAC_H + +#include <linux/if_ether.h> +#include <linux/phy.h> + +struct ll_temac_platform_data { + bool txcsum; /* Enable/disable TX checksum */ + bool rxcsum; /* Enable/disable RX checksum */ + u8 mac_addr[ETH_ALEN]; /* MAC address (6 bytes) */ + /* Clock frequency for input to MDIO clock generator */ + u32 mdio_clk_freq; + unsigned long long mdio_bus_id; /* Unique id for MDIO bus */ + int phy_addr; /* Address of the PHY to connect to */ + phy_interface_t phy_interface; /* PHY interface mode */ + bool reg_little_endian; /* Little endian TEMAC register access */ + bool dma_little_endian; /* Little endian DMA register access */ + /* Pre-initialized mutex to use for synchronizing indirect + * register access. When using both interfaces of a single + * TEMAC IP block, the same mutex should be passed here, as + * they share the same DCR bus bridge. + */ + struct mutex *indirect_mutex; + /* DMA channel control setup */ + u8 tx_irq_timeout; /* TX Interrupt Delay Time-out */ + u8 tx_irq_count; /* TX Interrupt Coalescing Threshold Count */ + u8 rx_irq_timeout; /* RX Interrupt Delay Time-out */ + u8 rx_irq_count; /* RX Interrupt Coalescing Threshold Count */ +}; + +#endif /* __LINUX_XILINX_LL_TEMAC_H */ diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index 763d613ce2c2..57467cbf4c5b 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -48,7 +48,6 @@ typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, * @head_offset: Offset of rhash_head in struct to be hashed * @max_size: Maximum size while expanding * @min_size: Minimum size while shrinking - * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) * @automatic_shrinking: Enable automatic shrinking of tables * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) * @obj_hashfn: Function to hash object @@ -62,7 +61,6 @@ struct rhashtable_params { unsigned int max_size; u16 min_size; bool automatic_shrinking; - u8 locks_mul; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; rht_obj_cmpfn_t obj_cmpfn; diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index ae9c0f71f311..f7714d3b46bd 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -24,12 +24,27 @@ #include <linux/list_nulls.h> #include <linux/workqueue.h> #include <linux/rculist.h> +#include <linux/bit_spinlock.h> #include <linux/rhashtable-types.h> /* + * Objects in an rhashtable have an embedded struct rhash_head + * which is linked into as hash chain from the hash table - or one + * of two or more hash tables when the rhashtable is being resized. * The end of the chain is marked with a special nulls marks which has - * the least significant bit set. + * the least significant bit set but otherwise stores the address of + * the hash bucket. This allows us to be be sure we've found the end + * of the right list. + * The value stored in the hash bucket has BIT(0) used as a lock bit. + * This bit must be atomically set before any changes are made to + * the chain. To avoid dereferencing this pointer without clearing + * the bit first, we use an opaque 'struct rhash_lock_head *' for the + * pointer stored in the bucket. This struct needs to be defined so + * that rcu_dereference() works on it, but it has no content so a + * cast is needed for it to be useful. This ensures it isn't + * used by mistake with clearing the lock bit first. */ +struct rhash_lock_head {}; /* Maximum chain length before rehash * @@ -52,8 +67,6 @@ * @nest: Number of bits of first-level nested table. * @rehash: Current bucket being rehashed * @hash_rnd: Random seed to fold into hash - * @locks_mask: Mask to apply before accessing locks[] - * @locks: Array of spinlocks protecting individual buckets * @walkers: List of active walkers * @rcu: RCU structure for freeing the table * @future_tbl: Table under construction during rehashing @@ -63,31 +76,34 @@ struct bucket_table { unsigned int size; unsigned int nest; - unsigned int rehash; u32 hash_rnd; - unsigned int locks_mask; - spinlock_t *locks; struct list_head walkers; struct rcu_head rcu; struct bucket_table __rcu *future_tbl; - struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; + struct lockdep_map dep_map; + + struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; /* * NULLS_MARKER() expects a hash value with the low * bits mostly likely to be significant, and it discards * the msb. - * We git it an address, in which the bottom 2 bits are + * We give it an address, in which the bottom bit is * always 0, and the msb might be significant. * So we shift the address down one bit to align with * expectations and avoid losing a significant bit. + * + * We never store the NULLS_MARKER in the hash table + * itself as we need the lsb for locking. + * Instead we store a NULL */ #define RHT_NULLS_MARKER(ptr) \ ((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1)) #define INIT_RHT_NULLS_HEAD(ptr) \ - ((ptr) = RHT_NULLS_MARKER(&(ptr))) + ((ptr) = NULL) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) { @@ -207,25 +223,6 @@ static inline bool rht_grow_above_max(const struct rhashtable *ht, return atomic_read(&ht->nelems) >= ht->max_elems; } -/* The bucket lock is selected based on the hash and protects mutations - * on a group of hash buckets. - * - * A maximum of tbl->size/2 bucket locks is allocated. This ensures that - * a single lock always covers both buckets which may both contains - * entries which link to the same bucket of the old table during resizing. - * This allows to simplify the locking as locking the bucket in both - * tables during resize always guarantee protection. - * - * IMPORTANT: When holding the bucket lock of both the old and new table - * during expansions and shrinking, the old bucket lock must always be - * acquired first. - */ -static inline spinlock_t *rht_bucket_lock(const struct bucket_table *tbl, - unsigned int hash) -{ - return &tbl->locks[hash & tbl->locks_mask]; -} - #ifdef CONFIG_PROVE_LOCKING int lockdep_rht_mutex_is_held(struct rhashtable *ht); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash); @@ -264,11 +261,13 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, void *arg); void rhashtable_destroy(struct rhashtable *ht); -struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, - struct bucket_table *tbl, +struct rhash_lock_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, + unsigned int hash); +struct rhash_lock_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, + struct bucket_table *tbl, + unsigned int hash); #define rht_dereference(p, ht) \ rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht)) @@ -285,37 +284,136 @@ struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, #define rht_entry(tpos, pos, member) \ ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) -static inline struct rhash_head __rcu *const *rht_bucket( +static inline struct rhash_lock_head __rcu *const *rht_bucket( const struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_head __rcu **rht_bucket_var( +static inline struct rhash_lock_head __rcu **rht_bucket_var( struct bucket_table *tbl, unsigned int hash) { - return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : + return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_head __rcu **rht_bucket_insert( +static inline struct rhash_lock_head __rcu **rht_bucket_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) : &tbl->buckets[hash]; } +/* + * We lock a bucket by setting BIT(0) in the pointer - this is always + * zero in real pointers. The NULLS mark is never stored in the bucket, + * rather we store NULL if the bucket is empty. + * bit_spin_locks do not handle contention well, but the whole point + * of the hashtable design is to achieve minimum per-bucket contention. + * A nested hash table might not have a bucket pointer. In that case + * we cannot get a lock. For remove and replace the bucket cannot be + * interesting and doesn't need locking. + * For insert we allocate the bucket if this is the last bucket_table, + * and then take the lock. + * Sometimes we unlock a bucket by writing a new pointer there. In that + * case we don't need to unlock, but we do need to reset state such as + * local_bh. For that we have rht_assign_unlock(). As rcu_assign_pointer() + * provides the same release semantics that bit_spin_unlock() provides, + * this is safe. + * When we write to a bucket without unlocking, we use rht_assign_locked(). + */ + +static inline void rht_lock(struct bucket_table *tbl, + struct rhash_lock_head **bkt) +{ + local_bh_disable(); + bit_spin_lock(0, (unsigned long *)bkt); + lock_map_acquire(&tbl->dep_map); +} + +static inline void rht_lock_nested(struct bucket_table *tbl, + struct rhash_lock_head **bucket, + unsigned int subclass) +{ + local_bh_disable(); + bit_spin_lock(0, (unsigned long *)bucket); + lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_); +} + +static inline void rht_unlock(struct bucket_table *tbl, + struct rhash_lock_head **bkt) +{ + lock_map_release(&tbl->dep_map); + bit_spin_unlock(0, (unsigned long *)bkt); + local_bh_enable(); +} + +/* + * Where 'bkt' is a bucket and might be locked: + * rht_ptr() dereferences that pointer and clears the lock bit. + * rht_ptr_exclusive() dereferences in a context where exclusive + * access is guaranteed, such as when destroying the table. + */ +static inline struct rhash_head *rht_ptr( + struct rhash_lock_head __rcu * const *bkt, + struct bucket_table *tbl, + unsigned int hash) +{ + const struct rhash_lock_head *p = + rht_dereference_bucket_rcu(*bkt, tbl, hash); + + if ((((unsigned long)p) & ~BIT(0)) == 0) + return RHT_NULLS_MARKER(bkt); + return (void *)(((unsigned long)p) & ~BIT(0)); +} + +static inline struct rhash_head *rht_ptr_exclusive( + struct rhash_lock_head __rcu * const *bkt) +{ + const struct rhash_lock_head *p = + rcu_dereference_protected(*bkt, 1); + + if (!p) + return RHT_NULLS_MARKER(bkt); + return (void *)(((unsigned long)p) & ~BIT(0)); +} + +static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, + struct rhash_head *obj) +{ + struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; + + if (rht_is_a_nulls(obj)) + obj = NULL; + rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(0))); +} + +static inline void rht_assign_unlock(struct bucket_table *tbl, + struct rhash_lock_head __rcu **bkt, + struct rhash_head *obj) +{ + struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; + + if (rht_is_a_nulls(obj)) + obj = NULL; + lock_map_release(&tbl->dep_map); + rcu_assign_pointer(*p, obj); + preempt_enable(); + __release(bitlock); + local_bh_enable(); +} + /** - * rht_for_each_continue - continue iterating over hash chain + * rht_for_each_from - iterate over hash chain from given head * @pos: the &struct rhash_head to use as a loop cursor. - * @head: the previous &struct rhash_head to continue from + * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index */ -#define rht_for_each_continue(pos, head, tbl, hash) \ - for (pos = rht_dereference_bucket(head, tbl, hash); \ - !rht_is_a_nulls(pos); \ +#define rht_for_each_from(pos, head, tbl, hash) \ + for (pos = head; \ + !rht_is_a_nulls(pos); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) /** @@ -325,19 +423,20 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * @hash: the hash value / bucket index */ #define rht_for_each(pos, tbl, hash) \ - rht_for_each_continue(pos, *rht_bucket(tbl, hash), tbl, hash) + rht_for_each_from(pos, rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ + tbl, hash) /** - * rht_for_each_entry_continue - continue iterating over hash chain + * rht_for_each_entry_from - iterate over hash chain from given head * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. - * @head: the previous &struct rhash_head to continue from + * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. */ -#define rht_for_each_entry_continue(tpos, pos, head, tbl, hash, member) \ - for (pos = rht_dereference_bucket(head, tbl, hash); \ +#define rht_for_each_entry_from(tpos, pos, head, tbl, hash, member) \ + for (pos = head; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) @@ -350,8 +449,9 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * @member: name of the &struct rhash_head within the hashable struct. */ #define rht_for_each_entry(tpos, pos, tbl, hash, member) \ - rht_for_each_entry_continue(tpos, pos, *rht_bucket(tbl, hash), \ - tbl, hash, member) + rht_for_each_entry_from(tpos, pos, \ + rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ + tbl, hash, member) /** * rht_for_each_entry_safe - safely iterate over hash chain of given type @@ -366,7 +466,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * remove the loop cursor from the list. */ #define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \ - for (pos = rht_dereference_bucket(*rht_bucket(tbl, hash), tbl, hash), \ + for (pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ next = !rht_is_a_nulls(pos) ? \ rht_dereference_bucket(pos->next, tbl, hash) : NULL; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ @@ -375,9 +475,9 @@ static inline struct rhash_head __rcu **rht_bucket_insert( rht_dereference_bucket(pos->next, tbl, hash) : NULL) /** - * rht_for_each_rcu_continue - continue iterating over rcu hash chain + * rht_for_each_rcu_from - iterate over rcu hash chain from given head * @pos: the &struct rhash_head to use as a loop cursor. - * @head: the previous &struct rhash_head to continue from + * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @@ -385,9 +485,9 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ -#define rht_for_each_rcu_continue(pos, head, tbl, hash) \ +#define rht_for_each_rcu_from(pos, head, tbl, hash) \ for (({barrier(); }), \ - pos = rht_dereference_bucket_rcu(head, tbl, hash); \ + pos = head; \ !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) @@ -401,14 +501,17 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ -#define rht_for_each_rcu(pos, tbl, hash) \ - rht_for_each_rcu_continue(pos, *rht_bucket(tbl, hash), tbl, hash) +#define rht_for_each_rcu(pos, tbl, hash) \ + for (({barrier(); }), \ + pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash); \ + !rht_is_a_nulls(pos); \ + pos = rcu_dereference_raw(pos->next)) /** - * rht_for_each_entry_rcu_continue - continue iterating over rcu hash chain + * rht_for_each_entry_rcu_from - iterated over rcu hash chain from given head * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. - * @head: the previous &struct rhash_head to continue from + * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. @@ -417,9 +520,9 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ -#define rht_for_each_entry_rcu_continue(tpos, pos, head, tbl, hash, member) \ +#define rht_for_each_entry_rcu_from(tpos, pos, head, tbl, hash, member) \ for (({barrier(); }), \ - pos = rht_dereference_bucket_rcu(head, tbl, hash); \ + pos = head; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket_rcu(pos->next, tbl, hash)) @@ -436,8 +539,10 @@ static inline struct rhash_head __rcu **rht_bucket_insert( * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ - rht_for_each_entry_rcu_continue(tpos, pos, *rht_bucket(tbl, hash), \ - tbl, hash, member) + rht_for_each_entry_rcu_from(tpos, pos, \ + rht_ptr(rht_bucket(tbl, hash), \ + tbl, hash), \ + tbl, hash, member) /** * rhl_for_each_rcu - iterate over rcu hash table list @@ -482,7 +587,7 @@ static inline struct rhash_head *__rhashtable_lookup( .ht = ht, .key = key, }; - struct rhash_head __rcu * const *head; + struct rhash_lock_head __rcu * const *bkt; struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; @@ -490,9 +595,9 @@ static inline struct rhash_head *__rhashtable_lookup( tbl = rht_dereference_rcu(ht->tbl, ht); restart: hash = rht_key_hashfn(ht, tbl, key, params); - head = rht_bucket(tbl, hash); + bkt = rht_bucket(tbl, hash); do { - rht_for_each_rcu_continue(he, *head, tbl, hash) { + rht_for_each_rcu_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { if (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) @@ -502,7 +607,7 @@ restart: /* An object might have been moved to a different hash chain, * while we walk along it - better check and retry. */ - } while (he != RHT_NULLS_MARKER(head)); + } while (he != RHT_NULLS_MARKER(bkt)); /* Ensure we see any new tables. */ smp_rmb(); @@ -598,10 +703,10 @@ static inline void *__rhashtable_insert_fast( .ht = ht, .key = key, }; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct bucket_table *tbl; struct rhash_head *head; - spinlock_t *lock; unsigned int hash; int elasticity; void *data; @@ -610,23 +715,22 @@ static inline void *__rhashtable_insert_fast( tbl = rht_dereference_rcu(ht->tbl, ht); hash = rht_head_hashfn(ht, tbl, obj, params); - lock = rht_bucket_lock(tbl, hash); - spin_lock_bh(lock); + elasticity = RHT_ELASTICITY; + bkt = rht_bucket_insert(ht, tbl, hash); + data = ERR_PTR(-ENOMEM); + if (!bkt) + goto out; + pprev = NULL; + rht_lock(tbl, bkt); if (unlikely(rcu_access_pointer(tbl->future_tbl))) { slow_path: - spin_unlock_bh(lock); + rht_unlock(tbl, bkt); rcu_read_unlock(); return rhashtable_insert_slow(ht, key, obj); } - elasticity = RHT_ELASTICITY; - pprev = rht_bucket_insert(ht, tbl, hash); - data = ERR_PTR(-ENOMEM); - if (!pprev) - goto out; - - rht_for_each_continue(head, *pprev, tbl, hash) { + rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *plist; struct rhlist_head *list; @@ -642,7 +746,7 @@ slow_path: data = rht_obj(ht, head); if (!rhlist) - goto out; + goto out_unlock; list = container_of(obj, struct rhlist_head, rhead); @@ -651,9 +755,13 @@ slow_path: RCU_INIT_POINTER(list->next, plist); head = rht_dereference_bucket(head->next, tbl, hash); RCU_INIT_POINTER(list->rhead.next, head); - rcu_assign_pointer(*pprev, obj); - - goto good; + if (pprev) { + rcu_assign_pointer(*pprev, obj); + rht_unlock(tbl, bkt); + } else + rht_assign_unlock(tbl, bkt, obj); + data = NULL; + goto out; } if (elasticity <= 0) @@ -661,12 +769,13 @@ slow_path: data = ERR_PTR(-E2BIG); if (unlikely(rht_grow_above_max(ht, tbl))) - goto out; + goto out_unlock; if (unlikely(rht_grow_above_100(ht, tbl))) goto slow_path; - head = rht_dereference_bucket(*pprev, tbl, hash); + /* Inserting at head of list makes unlocking free. */ + head = rht_ptr(bkt, tbl, hash); RCU_INIT_POINTER(obj->next, head); if (rhlist) { @@ -676,20 +785,21 @@ slow_path: RCU_INIT_POINTER(list->next, NULL); } - rcu_assign_pointer(*pprev, obj); - atomic_inc(&ht->nelems); + rht_assign_unlock(tbl, bkt, obj); + if (rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); -good: data = NULL; - out: - spin_unlock_bh(lock); rcu_read_unlock(); return data; + +out_unlock: + rht_unlock(tbl, bkt); + goto out; } /** @@ -698,9 +808,9 @@ out: * @obj: pointer to hash head inside object * @params: hash table parameters * - * Will take a per bucket spinlock to protect against mutual mutations + * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless - * they map to the same bucket lock. + * they map to the same bucket. * * It is safe to call this function from atomic context. * @@ -727,9 +837,9 @@ static inline int rhashtable_insert_fast( * @list: pointer to hash list head inside object * @params: hash table parameters * - * Will take a per bucket spinlock to protect against mutual mutations + * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless - * they map to the same bucket lock. + * they map to the same bucket. * * It is safe to call this function from atomic context. * @@ -750,9 +860,9 @@ static inline int rhltable_insert_key( * @list: pointer to hash list head inside object * @params: hash table parameters * - * Will take a per bucket spinlock to protect against mutual mutations + * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless - * they map to the same bucket lock. + * they map to the same bucket. * * It is safe to call this function from atomic context. * @@ -776,12 +886,6 @@ static inline int rhltable_insert( * @obj: pointer to hash head inside object * @params: hash table parameters * - * Locks down the bucket chain in both the old and new table if a resize - * is in progress to ensure that writers can't remove from the old table - * and can't insert to the new table during the atomic operation of search - * and insertion. Searches for duplicates in both the old and new table if - * a resize is in progress. - * * This lookup function may only be used for fixed key hash table (key_len * parameter set). It will BUG() if used inappropriately. * @@ -837,12 +941,6 @@ static inline void *rhashtable_lookup_get_insert_fast( * @obj: pointer to hash head inside object * @params: hash table parameters * - * Locks down the bucket chain in both the old and new table if a resize - * is in progress to ensure that writers can't remove from the old table - * and can't insert to the new table during the atomic operation of search - * and insertion. Searches for duplicates in both the old and new table if - * a resize is in progress. - * * Lookups may occur in parallel with hashtable mutations and resizing. * * Will trigger an automatic deferred table resizing if residency in the @@ -891,19 +989,20 @@ static inline int __rhashtable_remove_fast_one( struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; - spinlock_t * lock; unsigned int hash; int err = -ENOENT; hash = rht_head_hashfn(ht, tbl, obj, params); - lock = rht_bucket_lock(tbl, hash); - - spin_lock_bh(lock); + bkt = rht_bucket_var(tbl, hash); + if (!bkt) + return -ENOENT; + pprev = NULL; + rht_lock(tbl, bkt); - pprev = rht_bucket_var(tbl, hash); - rht_for_each_continue(he, *pprev, tbl, hash) { + rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *list; list = container_of(he, struct rhlist_head, rhead); @@ -943,12 +1042,17 @@ static inline int __rhashtable_remove_fast_one( } } - rcu_assign_pointer(*pprev, obj); - break; + if (pprev) { + rcu_assign_pointer(*pprev, obj); + rht_unlock(tbl, bkt); + } else { + rht_assign_unlock(tbl, bkt, obj); + } + goto unlocked; } - spin_unlock_bh(lock); - + rht_unlock(tbl, bkt); +unlocked: if (err > 0) { atomic_dec(&ht->nelems); if (unlikely(ht->p.automatic_shrinking && @@ -1037,9 +1141,9 @@ static inline int __rhashtable_replace_fast( struct rhash_head *obj_old, struct rhash_head *obj_new, const struct rhashtable_params params) { + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; - spinlock_t *lock; unsigned int hash; int err = -ENOENT; @@ -1050,25 +1154,33 @@ static inline int __rhashtable_replace_fast( if (hash != rht_head_hashfn(ht, tbl, obj_new, params)) return -EINVAL; - lock = rht_bucket_lock(tbl, hash); + bkt = rht_bucket_var(tbl, hash); + if (!bkt) + return -ENOENT; - spin_lock_bh(lock); + pprev = NULL; + rht_lock(tbl, bkt); - pprev = rht_bucket_var(tbl, hash); - rht_for_each_continue(he, *pprev, tbl, hash) { + rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { if (he != obj_old) { pprev = &he->next; continue; } rcu_assign_pointer(obj_new->next, obj_old->next); - rcu_assign_pointer(*pprev, obj_new); + if (pprev) { + rcu_assign_pointer(*pprev, obj_new); + rht_unlock(tbl, bkt); + } else { + rht_assign_unlock(tbl, bkt, obj_new); + } err = 0; - break; + goto unlocked; } - spin_unlock_bh(lock); + rht_unlock(tbl, bkt); +unlocked: return err; } diff --git a/include/linux/siphash.h b/include/linux/siphash.h index fa7a6b9cedbf..bf21591a9e5e 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -21,6 +21,11 @@ typedef struct { u64 key[2]; } siphash_key_t; +static inline bool siphash_key_is_zero(const siphash_key_t *key) +{ + return !(key->key[0] | key->key[1]); +} + u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key); #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9027a8c4219f..6d58fa8a65fd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -657,7 +657,6 @@ typedef unsigned char *sk_buff_data_t; * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices - * @xmit_more: More SKBs are pending for this queue * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) @@ -764,7 +763,6 @@ struct sk_buff { fclone:2, peeked:1, head_frag:1, - xmit_more:1, pfmemalloc:1; #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; @@ -1044,6 +1042,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); +struct sk_buff *build_skb_around(struct sk_buff *skb, + void *data, unsigned int frag_size); /** * alloc_skb - allocate a network buffer @@ -1258,11 +1258,19 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, unsigned int key_count); #ifdef CONFIG_NET +int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); #else +static inline int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EOPNOTSUPP; +} + static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { @@ -1275,12 +1283,12 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) } #endif -struct bpf_flow_keys; -bool __skb_flow_bpf_dissect(struct bpf_prog *prog, - const struct sk_buff *skb, - struct flow_dissector *flow_dissector, - struct bpf_flow_keys *flow_keys); -bool __skb_flow_dissect(const struct sk_buff *skb, +struct bpf_flow_dissector; +bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, + __be16 proto, int nhoff, int hlen); + +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, void *data, __be16 proto, int nhoff, int hlen, @@ -1290,8 +1298,8 @@ static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { - return __skb_flow_dissect(skb, flow_dissector, target_container, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, flow_dissector, + target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, @@ -1299,18 +1307,19 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, unsigned int flags) { memset(flow, 0, sizeof(*flow)); - return __skb_flow_dissect(skb, &flow_keys_dissector, flow, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, + flow, NULL, 0, 0, 0, flags); } static inline bool -skb_flow_dissect_flow_keys_basic(const struct sk_buff *skb, +skb_flow_dissect_flow_keys_basic(const struct net *net, + const struct sk_buff *skb, struct flow_keys_basic *flow, void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); - return __skb_flow_dissect(skb, &flow_keys_basic_dissector, flow, + return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } @@ -2102,8 +2111,6 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); -#define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags) -#define SKB_FRAG_ASSERT(skb) BUG_ON(skb_has_frag_list(skb)) #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET @@ -2490,7 +2497,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb) if (skb_transport_header_was_set(skb)) return; - if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) + if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } @@ -3372,17 +3380,17 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err, + int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err, + int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), - int *peeked, int *off, int *err); + int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index 49ba9cde7e4b..b29950a19205 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -45,6 +45,7 @@ struct bpf_raw_event_map { struct tracepoint *tp; void *bpf_func; u32 num_args; + u32 writable_size; } __aligned(32); #endif |