diff options
Diffstat (limited to 'include/linux')
36 files changed, 1348 insertions, 382 deletions
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index c893b9520a67..2b038442c352 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -133,6 +133,8 @@ enum virtchnl_ops { VIRTCHNL_OP_CONFIG_RSS_LUT = 24, VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25, VIRTCHNL_OP_SET_RSS_HENA = 26, + VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27, + VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28, }; /* This macro is used to generate a compilation error if a structure @@ -223,7 +225,7 @@ struct virtchnl_vsi_resource { VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); -/* VF offload flags +/* VF capability flags * VIRTCHNL_VF_OFFLOAD_L2 flag is inclusive of base mode L2 offloads including * TX/RX Checksum offloading and TSO for non-tunnelled packets. */ @@ -251,7 +253,7 @@ struct virtchnl_vf_resource { u16 max_vectors; u16 max_mtu; - u32 vf_offload_flags; + u32 vf_cap_flags; u32 rss_key_size; u32 rss_lut_size; @@ -686,6 +688,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_SET_RSS_HENA: valid_len = sizeof(struct virtchnl_rss_hena); break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b69e7a5869ff..c2cb1b5c094e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -14,8 +14,10 @@ #include <linux/percpu.h> #include <linux/err.h> #include <linux/rbtree_latch.h> +#include <linux/numa.h> struct perf_event; +struct bpf_prog; struct bpf_map; /* map is generic key/value storage optionally accesible by eBPF programs */ @@ -48,6 +50,7 @@ struct bpf_map { u32 map_flags; u32 pages; u32 id; + int numa_node; struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; @@ -117,39 +120,27 @@ enum bpf_access_type { }; /* types of values stored in eBPF registers */ +/* Pointer types represent: + * pointer + * pointer + imm + * pointer + (u16) var + * pointer + (u16) var + imm + * if (range > 0) then [ptr, ptr + range - off) is safe to access + * if (id > 0) means that some 'var' was added + * if (off > 0) means that 'imm' was added + */ enum bpf_reg_type { NOT_INIT = 0, /* nothing was written into register */ - UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ + SCALAR_VALUE, /* reg doesn't contain a valid pointer */ PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ - FRAME_PTR, /* reg == frame_pointer */ - PTR_TO_STACK, /* reg == frame_pointer + imm */ - CONST_IMM, /* constant integer value */ - - /* PTR_TO_PACKET represents: - * skb->data - * skb->data + imm - * skb->data + (u16) var - * skb->data + (u16) var + imm - * if (range > 0) then [ptr, ptr + range - off) is safe to access - * if (id > 0) means that some 'var' was added - * if (off > 0) menas that 'imm' was added - */ - PTR_TO_PACKET, + PTR_TO_STACK, /* reg == frame_pointer + offset */ + PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ - - /* PTR_TO_MAP_VALUE_ADJ is used for doing pointer math inside of a map - * elem value. We only allow this if we can statically verify that - * access from this register are going to fall within the size of the - * map element. - */ - PTR_TO_MAP_VALUE_ADJ, }; -struct bpf_prog; - /* The information passed from prog-specific *_is_valid_access * back to the verifier. */ @@ -262,6 +253,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); 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); +struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); @@ -272,7 +264,7 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); -void *bpf_map_area_alloc(size_t size); +void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; @@ -318,6 +310,19 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); + +/* Map specifics */ +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); + +/* Return map's numa specified by userspace */ +static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) +{ + return (attr->map_flags & BPF_F_NUMA_NODE) ? + attr->numa_node : NUMA_NO_NODE; +} + #else static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -348,6 +353,12 @@ static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog) return ERR_PTR(-EOPNOTSUPP); } +static inline struct bpf_prog *__must_check +bpf_prog_inc_not_zero(struct bpf_prog *prog) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) { return 0; @@ -356,8 +367,39 @@ static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } + +static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} + +static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) +{ +} + +static inline void __dev_map_flush(struct bpf_map *map) +{ +} #endif /* 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_attach_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); +#else +static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) +{ + return NULL; +} + +static inline int sock_map_attach_prog(struct bpf_map *map, + struct bpf_prog *prog, + u32 type) +{ + return -EOPNOTSUPP; +} +#endif + /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; @@ -374,6 +416,7 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; +extern const struct bpf_func_proto bpf_sock_map_update_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 3d137c33d664..6f1a567667b8 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -11,6 +11,7 @@ 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) #endif #ifdef CONFIG_BPF_EVENTS BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) @@ -35,3 +36,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops) #endif 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) +#ifdef CONFIG_STREAM_PARSER +BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) +#endif +#endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 8e5d31f6faef..b8d200f60a40 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -9,41 +9,75 @@ #include <linux/bpf.h> /* for enum bpf_reg_type */ #include <linux/filter.h> /* for MAX_BPF_STACK */ +#include <linux/tnum.h> - /* Just some arbitrary values so we can safely do math without overflowing and - * are obviously wrong for any sort of memory access. - */ -#define BPF_REGISTER_MAX_RANGE (1024 * 1024 * 1024) -#define BPF_REGISTER_MIN_RANGE -1 +/* Maximum variable offset umax_value permitted when resolving memory accesses. + * In practice this is far bigger than any realistic pointer offset; this limit + * ensures that umax_value + (int)off + (int)size cannot overflow a u64. + */ +#define BPF_MAX_VAR_OFF (1ULL << 31) +/* Maximum variable size permitted for ARG_CONST_SIZE[_OR_ZERO]. This ensures + * that converting umax_value to int cannot overflow. + */ +#define BPF_MAX_VAR_SIZ INT_MAX + +/* Liveness marks, used for registers and spilled-regs (in stack slots). + * Read marks propagate upwards until they find a write mark; they record that + * "one of this state's descendants read this reg" (and therefore the reg is + * relevant for states_equal() checks). + * Write marks collect downwards and do not propagate; they record that "the + * straight-line code that reached this state (from its parent) wrote this reg" + * (and therefore that reads propagated from this state or its descendants + * should not propagate to its parent). + * A state with a write mark can receive read marks; it just won't propagate + * them to its parent, since the write mark is a property, not of the state, + * but of the link between it and its parent. See mark_reg_read() and + * mark_stack_slot_read() in kernel/bpf/verifier.c. + */ +enum bpf_reg_liveness { + REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */ + REG_LIVE_READ, /* reg was read, so we're sensitive to initial value */ + REG_LIVE_WRITTEN, /* reg was written first, screening off later reads */ +}; struct bpf_reg_state { enum bpf_reg_type type; union { - /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ - s64 imm; - - /* valid when type == PTR_TO_PACKET* */ - struct { - u16 off; - u16 range; - }; + /* valid when type == PTR_TO_PACKET */ + u16 range; /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL */ struct bpf_map *map_ptr; }; + /* Fixed part of pointer offset, pointer types only */ + s32 off; + /* For PTR_TO_PACKET, used to find other pointers with the same variable + * offset, so they can share range knowledge. + * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we + * came from, when one is tested for != NULL. + */ u32 id; + /* Ordering of fields matters. See states_equal() */ + /* For scalar types (SCALAR_VALUE), this represents our knowledge of + * the actual value. + * For pointer types, this represents the variable part of the offset + * from the pointed-to object, and is shared with all bpf_reg_states + * with the same id as us. + */ + struct tnum var_off; /* Used to determine if any memory access using this register will - * result in a bad access. These two fields must be last. - * See states_equal() + * result in a bad access. + * These refer to the same value as var_off, not necessarily the actual + * contents of the register. */ - s64 min_value; - u64 max_value; - u32 min_align; - u32 aux_off; - u32 aux_off_align; - bool value_from_signed; + s64 smin_value; /* minimum possible (s64)value */ + s64 smax_value; /* maximum possible (s64)value */ + u64 umin_value; /* minimum possible (u64)value */ + u64 umax_value; /* maximum possible (u64)value */ + /* This field must be last, for states_equal() reasons. */ + enum bpf_reg_liveness live; }; enum bpf_stack_slot_type { @@ -61,6 +95,7 @@ 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; }; /* linked list of verifier states used to prune search */ @@ -103,7 +138,6 @@ struct bpf_verifier_env { u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; bool seen_direct_write; - bool varlen_map_value_access; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ }; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 83cc9863444b..4587a4c36923 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -137,6 +137,17 @@ struct ethtool_link_ksettings { __set_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) /** + * ethtool_link_ksettings_del_link_mode - clear bit in link_ksettings + * link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + */ +#define ethtool_link_ksettings_del_link_mode(ptr, name, mode) \ + __clear_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + +/** * ethtool_link_ksettings_test_link_mode - test bit in ksettings link mode mask * @ptr : pointer to struct ethtool_link_ksettings * @name : one of supported/advertising/lp_advertising @@ -374,5 +385,9 @@ struct ethtool_ops { struct ethtool_link_ksettings *); int (*set_link_ksettings)(struct net_device *, const struct ethtool_link_ksettings *); + int (*get_fecparam)(struct net_device *, + struct ethtool_fecparam *); + int (*set_fecparam)(struct net_device *, + struct ethtool_fecparam *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index bfef1e5734f8..d29e58fde364 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -711,7 +711,24 @@ bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); + +/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the + * same cpu context. Further for best results no more than a single map + * for the do_redirect/do_flush pair should be used. This limitation is + * because we only track one map and force a flush when the map changes. + * This does not appear to be a real limitation for existing software. + */ +int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *prog); +int xdp_do_redirect(struct net_device *dev, + struct xdp_buff *xdp, + struct bpf_prog *prog); +void xdp_do_flush_map(void); + void bpf_warn_invalid_xdp_action(u32 act); +void bpf_warn_invalid_xdp_redirect(u32 ifindex); + +struct sock *do_sk_redirect_map(void); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b7d7bbec74e0..a5f961c4149e 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1030,13 +1030,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel, enum vmbus_packet_type type, u32 flags); -extern int vmbus_sendpacket_ctl(struct vmbus_channel *channel, - void *buffer, - u32 bufferLen, - u64 requestid, - enum vmbus_packet_type type, - u32 flags); - extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, struct hv_page_buffer pagebuffers[], u32 pagecount, @@ -1044,20 +1037,6 @@ extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, u32 bufferlen, u64 requestid); -extern int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, - void *buffer, - u32 bufferlen, - u64 requestid, - u32 flags); - -extern int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel, - struct hv_multipage_buffer *mpb, - void *buffer, - u32 bufferlen, - u64 requestid); - extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *mpb, u32 desc_size, diff --git a/include/linux/idr.h b/include/linux/idr.h index bf70b3ef0a07..7c3a365f7e12 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -80,19 +80,75 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val) */ void idr_preload(gfp_t gfp_mask); -int idr_alloc(struct idr *, void *entry, int start, int end, gfp_t); + +int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index, + unsigned long start, unsigned long end, gfp_t gfp, + bool ext); + +/** + * idr_alloc - allocate an id + * @idr: idr handle + * @ptr: pointer to be associated with the new id + * @start: the minimum id (inclusive) + * @end: the maximum id (exclusive) + * @gfp: memory allocation flags + * + * Allocates an unused ID in the range [start, end). Returns -ENOSPC + * if there are no unused IDs in that range. + * + * Note that @end is treated as max when <= 0. This is to always allow + * using @start + N as @end as long as N is inside integer range. + * + * Simultaneous modifications to the @idr are not allowed and should be + * prevented by the user, usually with a lock. idr_alloc() may be called + * concurrently with read-only accesses to the @idr, such as idr_find() and + * idr_for_each_entry(). + */ +static inline int idr_alloc(struct idr *idr, void *ptr, + int start, int end, gfp_t gfp) +{ + unsigned long id; + int ret; + + if (WARN_ON_ONCE(start < 0)) + return -EINVAL; + + ret = idr_alloc_cmn(idr, ptr, &id, start, end, gfp, false); + + if (ret) + return ret; + + return id; +} + +static inline int idr_alloc_ext(struct idr *idr, void *ptr, + unsigned long *index, + unsigned long start, + unsigned long end, + gfp_t gfp) +{ + return idr_alloc_cmn(idr, ptr, index, start, end, gfp, true); +} + int idr_alloc_cyclic(struct idr *, void *entry, int start, int end, gfp_t); int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *, int *nextid); +void *idr_get_next_ext(struct idr *idr, unsigned long *nextid); void *idr_replace(struct idr *, void *, int id); +void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id); void idr_destroy(struct idr *); -static inline void *idr_remove(struct idr *idr, int id) +static inline void *idr_remove_ext(struct idr *idr, unsigned long id) { return radix_tree_delete_item(&idr->idr_rt, id, NULL); } +static inline void *idr_remove(struct idr *idr, int id) +{ + return idr_remove_ext(idr, id); +} + static inline void idr_init(struct idr *idr) { INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); @@ -128,11 +184,16 @@ static inline void idr_preload_end(void) * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. */ -static inline void *idr_find(const struct idr *idr, int id) +static inline void *idr_find_ext(const struct idr *idr, unsigned long id) { return radix_tree_lookup(&idr->idr_rt, id); } +static inline void *idr_find(const struct idr *idr, int id) +{ + return idr_find_ext(idr, id); +} + /** * idr_for_each_entry - iterate over an idr's elements of a given type * @idr: idr handle @@ -145,6 +206,8 @@ static inline void *idr_find(const struct idr *idr, int id) */ #define idr_for_each_entry(idr, entry, id) \ for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) +#define idr_for_each_entry_ext(idr, entry, id) \ + for (id = 0; ((entry) = idr_get_next_ext(idr, &(id))) != NULL; ++id) /** * idr_for_each_entry_continue - continue iteration over an idr's elements of a given type diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 97caf1821de8..f8231854b5d6 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -118,7 +118,8 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct ip_msfilter __user *optval, int __user *optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, struct group_filter __user *optval, int __user *optlen); -extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif); +extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, + int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 474d6bbc158c..ac2da4e11d5e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -159,6 +159,16 @@ static inline bool inet6_is_jumbogram(const struct sk_buff *skb) } /* can not be used in TCP layer after tcp_v6_fill_cb */ +static inline int inet6_sdif(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) + return IP6CB(skb)->iif; +#endif + return 0; +} + +/* can not be used in TCP layer after tcp_v6_fill_cb */ static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb) { #if defined(CONFIG_NET_L3_MASTER_DEV) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b54517c05e9a..89c0e7f7cd9b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -224,6 +224,7 @@ enum { MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT = 1ULL << 35, MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP = 1ULL << 36, MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT = 1ULL << 37, + MLX4_DEV_CAP_FLAG2_USER_MAC_EN = 1ULL << 38, }; enum { @@ -518,6 +519,14 @@ struct mlx4_phys_caps { u32 base_tunnel_sqpn; }; +struct mlx4_spec_qps { + u32 qp0_qkey; + u32 qp0_proxy; + u32 qp0_tunnel; + u32 qp1_proxy; + u32 qp1_tunnel; +}; + struct mlx4_caps { u64 fw_ver; u32 function; @@ -547,11 +556,7 @@ struct mlx4_caps { int max_qp_init_rdma; int max_qp_dest_rdma; int max_tc_eth; - u32 *qp0_qkey; - u32 *qp0_proxy; - u32 *qp1_proxy; - u32 *qp0_tunnel; - u32 *qp1_tunnel; + struct mlx4_spec_qps *spec_qps; int num_srqs; int max_srq_wqes; int max_srq_sge; @@ -1373,6 +1378,7 @@ int mlx4_get_base_qpn(struct mlx4_dev *dev, u8 port); int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac); int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu, u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx); +int mlx4_SET_PORT_user_mac(struct mlx4_dev *dev, u8 port, u8 *user_mac); int mlx4_SET_PORT_user_mtu(struct mlx4_dev *dev, u8 port, u16 user_mtu); int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, u8 promisc); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f31a0b5377e1..3c7442b56460 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -48,7 +48,7 @@ /* helper macros */ #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) ((unsigned)(unsigned long)(&(__mlx5_nullp(typ)->fld))) +#define __mlx5_bit_off(typ, fld) (offsetof(struct mlx5_ifc_##typ##_bits, fld)) #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_dw_bit_off(typ, fld) (32 - __mlx5_bit_sz(typ, fld) - (__mlx5_bit_off(typ, fld) & 0x1f)) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 205d82d4c468..023b29d973e6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -550,6 +550,7 @@ struct mlx5_fc_stats { unsigned long sampling_interval; /* jiffies */ }; +struct mlx5_mpfs; struct mlx5_eswitch; struct mlx5_lag; struct mlx5_pagefault; @@ -646,7 +647,11 @@ struct mlx5_priv { struct list_head ctx_list; spinlock_t ctx_lock; + struct list_head waiting_events_list; + bool is_accum_events; + struct mlx5_flow_steering *steering; + struct mlx5_mpfs *mpfs; struct mlx5_eswitch *eswitch; struct mlx5_core_sriov sriov; struct mlx5_lag *lag; @@ -883,8 +888,6 @@ static inline void *mlx5_buf_offset(struct mlx5_buf *buf, int offset) return buf->direct.buf + offset; } -extern struct workqueue_struct *mlx5_core_wq; - #define STRUCT_FIELD(header, field) \ .struct_offset_bytes = offsetof(struct ib_unpacked_ ## header, field), \ .struct_size_bytes = sizeof((struct ib_unpacked_ ## header *)0)->field diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3030121b4746..3d5d32e5446c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -602,7 +602,7 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 reserved_at_1a[0x1]; u8 tunnel_lso_const_out_ip_id[0x1]; u8 reserved_at_1c[0x2]; - u8 tunnel_statless_gre[0x1]; + u8 tunnel_stateless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; u8 swp[0x1]; @@ -963,7 +963,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_2a0[0x10]; u8 max_wqe_sz_rq[0x10]; - u8 reserved_at_2c0[0x10]; + u8 max_flow_counter_31_16[0x10]; u8 max_wqe_sz_sq_dc[0x10]; u8 reserved_at_2e0[0x7]; @@ -981,7 +981,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_340[0x8]; u8 log_max_flow_counter_bulk[0x8]; - u8 max_flow_counter[0x10]; + u8 max_flow_counter_15_0[0x10]; u8 reserved_at_360[0x3]; @@ -1071,9 +1071,7 @@ struct mlx5_ifc_dest_format_struct_bits { }; struct mlx5_ifc_flow_counter_list_bits { - u8 clear[0x1]; - u8 num_of_counters[0xf]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_20[0x20]; }; @@ -1540,7 +1538,17 @@ struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { u8 port_transmit_wait_low[0x20]; - u8 reserved_at_40[0x780]; + u8 reserved_at_40[0x100]; + + u8 rx_buffer_almost_full_high[0x20]; + + u8 rx_buffer_almost_full_low[0x20]; + + u8 rx_buffer_full_high[0x20]; + + u8 rx_buffer_full_low[0x20]; + + u8 reserved_at_1c0[0x600]; }; struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { @@ -1856,7 +1864,19 @@ struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits { u8 crc_error_tlp[0x20]; - u8 reserved_at_140[0x680]; + u8 tx_overflow_buffer_pkt_high[0x20]; + + u8 tx_overflow_buffer_pkt_low[0x20]; + + u8 outbound_stalled_reads[0x20]; + + u8 outbound_stalled_writes[0x20]; + + u8 outbound_stalled_reads_events[0x20]; + + u8 outbound_stalled_writes_events[0x20]; + + u8 reserved_at_200[0x5c0]; }; struct mlx5_ifc_cmd_inter_comp_event_bits { @@ -4403,8 +4423,7 @@ struct mlx5_ifc_query_flow_counter_in_bits { u8 reserved_at_c1[0xf]; u8 num_of_counters[0x10]; - u8 reserved_at_e0[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; }; struct mlx5_ifc_query_esw_vport_context_out_bits { @@ -6272,8 +6291,7 @@ struct mlx5_ifc_dealloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_60[0x20]; }; @@ -7098,8 +7116,7 @@ struct mlx5_ifc_alloc_flow_counter_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_60[0x20]; }; @@ -7718,8 +7735,9 @@ struct mlx5_ifc_peir_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x7c]; + u8 reserved_at_0[0x7b]; + u8 rx_buffer_fullness_counters[0x1]; u8 ptys_connector_type[0x1]; u8 reserved_at_7d[0x1]; u8 ppcnt_discard_group[0x1]; @@ -7749,8 +7767,9 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x7d]; - + u8 reserved_at_0[0x7b]; + u8 pcie_outbound_stalled[0x1]; + u8 tx_overflow_buffer_pkt[0x1]; u8 mtpps_enh_out_per_adj[0x1]; u8 mtpps_fs[0x1]; u8 pcie_performance_group[0x1]; diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index b733eb404ffc..abacd5484bc0 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -39,6 +39,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 #define SDIO_DEVICE_ID_BROADCOM_4356 0x4356 +#define SDIO_DEVICE_ID_CYPRESS_4373 0x4373 #define SDIO_VENDOR_ID_INTEL 0x0089 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 diff --git a/include/linux/net.h b/include/linux/net.h index ebeb48c92005..d97d80d7fdf8 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -190,8 +190,16 @@ struct proto_ops { struct pipe_inode_info *pipe, size_t len, unsigned int flags); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); + + /* The following functions are called internally by kernel with + * sock lock already held. + */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); + int (*sendpage_locked)(struct sock *sk, struct page *page, + int offset, size_t size, int flags); + int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, + size_t size); }; #define DECLARE_SOCKADDR(type, dst, src) \ @@ -279,6 +287,8 @@ do { \ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); +int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, + struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); @@ -297,6 +307,8 @@ int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); +int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, + size_t size, int flags); int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 1d4737cffc71..dc8b4896b77b 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -36,7 +36,6 @@ enum { /**/NETIF_F_GSO_SHIFT, /* keep the order of SKB_GSO_* bits */ NETIF_F_TSO_BIT /* ... TCPv4 segmentation */ = NETIF_F_GSO_SHIFT, - NETIF_F_UFO_BIT, /* ... UDPv4 fragmentation */ NETIF_F_GSO_ROBUST_BIT, /* ... ->SKB_GSO_DODGY */ NETIF_F_TSO_ECN_BIT, /* ... TCP ECN support */ NETIF_F_TSO_MANGLEID_BIT, /* ... IPV4 ID mangling allowed */ @@ -76,6 +75,7 @@ enum { NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */ NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */ NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ + NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */ /* * Add your fresh new feature above and remember to update @@ -118,7 +118,6 @@ enum { #define NETIF_F_TSO6 __NETIF_F(TSO6) #define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN) #define NETIF_F_TSO __NETIF_F(TSO) -#define NETIF_F_UFO __NETIF_F(UFO) #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) @@ -140,6 +139,7 @@ enum { #define NETIF_F_HW_TC __NETIF_F(HW_TC) #define NETIF_F_HW_ESP __NETIF_F(HW_ESP) #define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM) +#define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) @@ -172,7 +172,7 @@ enum { NETIF_F_FSO) /* List of features with software fallbacks. */ -#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_UFO | \ +#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | \ NETIF_F_GSO_SCTP) /* diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c99ba7914c0a..8aba119bb005 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -35,7 +35,6 @@ #include <linux/percpu.h> #include <linux/rculist.h> -#include <linux/dmaengine.h> #include <linux/workqueue.h> #include <linux/dynamic_queue_limits.h> @@ -66,6 +65,7 @@ struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; struct bpf_prog; +struct xdp_buff; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -693,10 +693,9 @@ struct netdev_rx_queue { */ struct rx_queue_attribute { struct attribute attr; - ssize_t (*show)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, char *buf); + ssize_t (*show)(struct netdev_rx_queue *queue, char *buf); ssize_t (*store)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, const char *buf, size_t len); + const char *buf, size_t len); }; #ifdef CONFIG_XPS @@ -770,31 +769,14 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); -/* These structures hold the attributes of qdisc and classifiers - * that are being passed to the netdevice through the setup_tc op. - */ -enum { +enum tc_setup_type { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, - TC_SETUP_MATCHALL, + TC_SETUP_CLSMATCHALL, TC_SETUP_CLSBPF, }; -struct tc_cls_u32_offload; - -struct tc_to_netdev { - unsigned int type; - union { - struct tc_cls_u32_offload *cls_u32; - struct tc_cls_flower_offload *cls_flower; - struct tc_cls_matchall_offload *cls_mall; - struct tc_cls_bpf_offload *cls_bpf; - struct tc_mqprio_qopt *mqprio; - }; - bool egress_dev; -}; - /* These structures hold the attributes of xdp state that are being passed * to the netdevice through the xdp op. */ @@ -977,8 +959,8 @@ struct xfrmdev_ops { * with PF and querying it may introduce a theoretical security risk. * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); - * int (*ndo_setup_tc)(struct net_device *dev, u32 handle, u32 chain_index, - * __be16 protocol, struct tc_to_netdev *tc); + * int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, + * void *type_data); * Called to setup any 'tc' scheduler, classifier or action on @dev. * This is always called from the stack with the rtnl lock held and netif * tx queues stopped. This allows the netdevice to perform queue @@ -1138,7 +1120,12 @@ struct xfrmdev_ops { * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); * This function is used to set or query state related to XDP on the * netdevice. See definition of enum xdp_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. + * void (*ndo_xdp_flush)(struct net_device *dev); + * This function is used to inform the driver to flush a particular + * xdp tx queue. Must be called on same CPU as xdp_xmit. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1221,9 +1208,8 @@ struct net_device_ops { struct net_device *dev, int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, - u32 handle, u32 chain_index, - __be16 protocol, - struct tc_to_netdev *tc); + enum tc_setup_type type, + void *type_data); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); @@ -1323,6 +1309,9 @@ struct net_device_ops { int needed_headroom); int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); + int (*ndo_xdp_xmit)(struct net_device *dev, + struct xdp_buff *xdp); + void (*ndo_xdp_flush)(struct net_device *dev); }; /** @@ -2308,6 +2297,7 @@ struct netdev_lag_lower_state_info { #define NETDEV_PRECHANGEUPPER 0x001A #define NETDEV_CHANGELOWERSTATE 0x001B #define NETDEV_UDP_TUNNEL_PUSH_INFO 0x001C +#define NETDEV_UDP_TUNNEL_DROP_INFO 0x001D #define NETDEV_CHANGE_TX_QUEUE_LEN 0x001E int register_netdevice_notifier(struct notifier_block *nb); @@ -2423,8 +2413,8 @@ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev); -int dev_close(struct net_device *dev); -int dev_close_many(struct list_head *head, bool unlink); +void dev_close(struct net_device *dev); +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); int dev_queue_xmit(struct sk_buff *skb); @@ -3251,6 +3241,8 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); } +void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); +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); @@ -4021,22 +4013,22 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi return rc; } -int netdev_class_create_file_ns(struct class_attribute *class_attr, +int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns); -void netdev_class_remove_file_ns(struct class_attribute *class_attr, +void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns); -static inline int netdev_class_create_file(struct class_attribute *class_attr) +static inline int netdev_class_create_file(const struct class_attribute *class_attr) { return netdev_class_create_file_ns(class_attr, NULL); } -static inline void netdev_class_remove_file(struct class_attribute *class_attr) +static inline void netdev_class_remove_file(const struct class_attribute *class_attr) { netdev_class_remove_file_ns(class_attr, NULL); } -extern struct kobj_ns_type_operations net_ns_type_operations; +extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); @@ -4091,7 +4083,6 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); - BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); diff --git a/include/linux/phy.h b/include/linux/phy.h index 0bb5b212ab42..d78cd01ea513 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -182,6 +182,7 @@ static inline const char *phy_modes(phy_interface_t interface) #define MII_ADDR_C45 (1<<30) struct device; +struct phylink; struct sk_buff; /* @@ -469,11 +470,13 @@ struct phy_device { struct mutex lock; + struct phylink *phylink; struct net_device *attached_dev; u8 mdix; u8 mdix_ctrl; + void (*phy_link_change)(struct phy_device *, bool up, bool do_carrier); void (*adjust_link)(struct net_device *dev); }; #define to_phy_device(d) container_of(to_mdio_device(d), \ @@ -667,6 +670,24 @@ struct phy_fixup { int (*run)(struct phy_device *phydev); }; +const char *phy_speed_to_str(int speed); +const char *phy_duplex_to_str(unsigned int duplex); + +/* A structure for mapping a particular speed and duplex + * combination to a particular SUPPORTED and ADVERTISED value + */ +struct phy_setting { + u32 speed; + u8 duplex; + u8 bit; +}; + +const struct phy_setting * +phy_lookup_setting(int speed, int duplex, const unsigned long *mask, + size_t maxbit, bool exact); +size_t phy_speeds(unsigned int *speeds, size_t size, + unsigned long *mask, size_t maxbit); + /** * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 78bb0d7f6b11..e694d4008c4a 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -27,6 +27,8 @@ enum phy_mode { PHY_MODE_USB_HOST, PHY_MODE_USB_DEVICE, PHY_MODE_USB_OTG, + PHY_MODE_SGMII, + PHY_MODE_10GKR, }; /** diff --git a/include/linux/phylink.h b/include/linux/phylink.h new file mode 100644 index 000000000000..af67edd4ae38 --- /dev/null +++ b/include/linux/phylink.h @@ -0,0 +1,148 @@ +#ifndef NETDEV_PCS_H +#define NETDEV_PCS_H + +#include <linux/phy.h> +#include <linux/spinlock.h> +#include <linux/workqueue.h> + +struct device_node; +struct ethtool_cmd; +struct net_device; + +enum { + MLO_PAUSE_NONE, + MLO_PAUSE_ASYM = BIT(0), + MLO_PAUSE_SYM = BIT(1), + MLO_PAUSE_RX = BIT(2), + MLO_PAUSE_TX = BIT(3), + MLO_PAUSE_TXRX_MASK = MLO_PAUSE_TX | MLO_PAUSE_RX, + MLO_PAUSE_AN = BIT(4), + + MLO_AN_PHY = 0, /* Conventional PHY */ + MLO_AN_FIXED, /* Fixed-link mode */ + MLO_AN_SGMII, /* Cisco SGMII protocol */ + MLO_AN_8023Z, /* 1000base-X protocol */ +}; + +static inline bool phylink_autoneg_inband(unsigned int mode) +{ + return mode == MLO_AN_SGMII || mode == MLO_AN_8023Z; +} + +struct phylink_link_state { + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + phy_interface_t interface; /* PHY_INTERFACE_xxx */ + int speed; + int duplex; + int pause; + unsigned int link:1; + unsigned int an_enabled:1; + unsigned int an_complete:1; +}; + +struct phylink_mac_ops { + /** + * validate: validate and update the link configuration + * @ndev: net_device structure associated with MAC + * @config: configuration to validate + * + * Update the %config->supported and %config->advertised masks + * clearing bits that can not be supported. + * + * Note: the PHY may be able to transform from one connection + * technology to another, so, eg, don't clear 1000BaseX just + * because the MAC is unable to support it. This is more about + * clearing unsupported speeds and duplex settings. + * + * If the %config->interface mode is %PHY_INTERFACE_MODE_1000BASEX + * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode + * based on %config->advertised and/or %config->speed. + */ + void (*validate)(struct net_device *ndev, unsigned long *supported, + struct phylink_link_state *state); + + /* Read the current link state from the hardware */ + int (*mac_link_state)(struct net_device *, struct phylink_link_state *); + + /* Configure the MAC */ + /** + * mac_config: configure the MAC for the selected mode and state + * @ndev: net_device structure for the MAC + * @mode: one of MLO_AN_FIXED, MLO_AN_PHY, MLO_AN_8023Z, MLO_AN_SGMII + * @state: state structure + * + * The action performed depends on the currently selected mode: + * + * %MLO_AN_FIXED, %MLO_AN_PHY: + * set the specified speed, duplex, pause mode, and phy interface + * mode in the provided @state. + * %MLO_AN_8023Z: + * place the link in 1000base-X mode, advertising the parameters + * given in advertising in @state. + * %MLO_AN_SGMII: + * place the link in Cisco SGMII mode - there is no advertisment + * to make as the PHY communicates the speed and duplex to the + * MAC over the in-band control word. Configuration of the pause + * mode is as per MLO_AN_PHY since this is not included. + */ + void (*mac_config)(struct net_device *ndev, unsigned int mode, + const struct phylink_link_state *state); + + /** + * mac_an_restart: restart 802.3z BaseX autonegotiation + * @ndev: net_device structure for the MAC + */ + void (*mac_an_restart)(struct net_device *ndev); + + void (*mac_link_down)(struct net_device *, unsigned int mode); + void (*mac_link_up)(struct net_device *, unsigned int mode, + struct phy_device *); +}; + +struct phylink *phylink_create(struct net_device *, struct device_node *, + phy_interface_t iface, const struct phylink_mac_ops *ops); +void phylink_destroy(struct phylink *); + +int phylink_connect_phy(struct phylink *, struct phy_device *); +int phylink_of_phy_connect(struct phylink *, struct device_node *); +void phylink_disconnect_phy(struct phylink *); + +void phylink_mac_change(struct phylink *, bool up); + +void phylink_start(struct phylink *); +void phylink_stop(struct phylink *); + +void phylink_ethtool_get_wol(struct phylink *, struct ethtool_wolinfo *); +int phylink_ethtool_set_wol(struct phylink *, struct ethtool_wolinfo *); + +int phylink_ethtool_ksettings_get(struct phylink *, + struct ethtool_link_ksettings *); +int phylink_ethtool_ksettings_set(struct phylink *, + const struct ethtool_link_ksettings *); +int phylink_ethtool_nway_reset(struct phylink *); +void phylink_ethtool_get_pauseparam(struct phylink *, + struct ethtool_pauseparam *); +int phylink_ethtool_set_pauseparam(struct phylink *, + struct ethtool_pauseparam *); +int phylink_ethtool_get_module_info(struct phylink *, struct ethtool_modinfo *); +int phylink_ethtool_get_module_eeprom(struct phylink *, + struct ethtool_eeprom *, u8 *); +int phylink_init_eee(struct phylink *, bool); +int phylink_get_eee_err(struct phylink *); +int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *); +int phylink_ethtool_set_eee(struct phylink *, struct ethtool_eee *); +int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); + +#define phylink_zero(bm) \ + bitmap_zero(bm, __ETHTOOL_LINK_MODE_MASK_NBITS) +#define __phylink_do_bit(op, bm, mode) \ + op(ETHTOOL_LINK_MODE_ ## mode ## _BIT, bm) + +#define phylink_set(bm, mode) __phylink_do_bit(__set_bit, bm, mode) +#define phylink_clear(bm, mode) __phylink_do_bit(__clear_bit, bm, mode) +#define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) + +void phylink_set_port_modes(unsigned long *bits); + +#endif diff --git a/include/linux/platform_data/mdio-bcm-unimac.h b/include/linux/platform_data/mdio-bcm-unimac.h new file mode 100644 index 000000000000..8a5f9f0b2c52 --- /dev/null +++ b/include/linux/platform_data/mdio-bcm-unimac.h @@ -0,0 +1,13 @@ +#ifndef __MDIO_BCM_UNIMAC_PDATA_H +#define __MDIO_BCM_UNIMAC_PDATA_H + +struct unimac_mdio_pdata { + u32 phy_mask; + int (*wait_func)(void *data); + void *wait_func_data; + const char *bus_name; +}; + +#define UNIMAC_MDIO_DRV_NAME "unimac-mdio" + +#endif /* __MDIO_BCM_UNIMAC_PDATA_H */ diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 0eef0a2b1901..d60de4a39810 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -323,6 +323,7 @@ struct qed_eth_ops { int (*configure_arfs_searcher)(struct qed_dev *cdev, bool en_searcher); + int (*get_coalesce)(struct qed_dev *cdev, u16 *coal, void *handle); }; const struct qed_eth_ops *qed_get_eth_ops(void); diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index ef39c7f40ae6..cc646ca97974 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -161,6 +161,18 @@ enum qed_nvm_images { QED_NVM_IMAGE_FCOE_CFG, }; +struct qed_link_eee_params { + u32 tx_lpi_timer; +#define QED_EEE_1G_ADV BIT(0) +#define QED_EEE_10G_ADV BIT(1) + + /* Capabilities are represented using QED_EEE_*_ADV values */ + u8 adv_caps; + u8 lp_adv_caps; + bool enable; + bool tx_lpi_enable; +}; + enum qed_led_mode { QED_LED_MODE_OFF, QED_LED_MODE_ON, @@ -172,8 +184,9 @@ enum qed_led_mode { #define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr)) -#define QED_COALESCE_MAX 0xFF +#define QED_COALESCE_MAX 0x1FF #define QED_DEFAULT_RX_USECS 12 +#define QED_DEFAULT_TX_USECS 48 /* forward */ struct qed_dev; @@ -408,6 +421,7 @@ struct qed_link_params { #define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED BIT(2) #define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) #define QED_LINK_OVERRIDE_LOOPBACK_MODE BIT(4) +#define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) u32 override_flags; bool autoneg; u32 adv_speeds; @@ -422,6 +436,7 @@ struct qed_link_params { #define QED_LINK_LOOPBACK_EXT BIT(3) #define QED_LINK_LOOPBACK_MAC BIT(4) u32 loopback_mode; + struct qed_link_eee_params eee; }; struct qed_link_output { @@ -437,6 +452,12 @@ struct qed_link_output { u8 port; /* In PORT defs */ bool autoneg; u32 pause_config; + + /* EEE - capability & param */ + bool eee_supported; + bool eee_active; + u8 sup_caps; + struct qed_link_eee_params eee; }; struct qed_probe_params { @@ -654,16 +675,6 @@ struct qed_common_ops { enum qed_nvm_images type, u8 *buf, u16 len); /** - * @brief get_coalesce - Get coalesce parameters in usec - * - * @param cdev - * @param rx_coal - Rx coalesce value in usec - * @param tx_coal - Tx coalesce value in usec - * - */ - void (*get_coalesce)(struct qed_dev *cdev, u16 *rx_coal, u16 *tx_coal); - -/** * @brief set_coalesce - Configure Rx coalesce value in usec * * @param cdev @@ -674,8 +685,8 @@ struct qed_common_ops { * * @return 0 on success, error otherwise. */ - int (*set_coalesce)(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal, - u16 qid, u16 sb_id); + int (*set_coalesce)(struct qed_dev *cdev, + u16 rx_coal, u16 tx_coal, void *handle); /** * @brief set_led - Configure LED mode diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 3e5735064b71..567ebb5eaab0 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -357,8 +357,25 @@ int radix_tree_split(struct radix_tree_root *, unsigned long index, unsigned new_order); int radix_tree_join(struct radix_tree_root *, unsigned long index, unsigned new_order, void *); -void __rcu **idr_get_free(struct radix_tree_root *, struct radix_tree_iter *, - gfp_t, int end); + +void __rcu **idr_get_free_cmn(struct radix_tree_root *root, + struct radix_tree_iter *iter, gfp_t gfp, + unsigned long max); +static inline void __rcu **idr_get_free(struct radix_tree_root *root, + struct radix_tree_iter *iter, + gfp_t gfp, + int end) +{ + return idr_get_free_cmn(root, iter, gfp, end > 0 ? end - 1 : INT_MAX); +} + +static inline void __rcu **idr_get_free_ext(struct radix_tree_root *root, + struct radix_tree_iter *iter, + gfp_t gfp, + unsigned long end) +{ + return idr_get_free_cmn(root, iter, gfp, end - 1); +} enum { RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h deleted file mode 100644 index 7343f71783dc..000000000000 --- a/include/linux/rxrpc.h +++ /dev/null @@ -1,79 +0,0 @@ -/* AF_RXRPC parameters - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef _LINUX_RXRPC_H -#define _LINUX_RXRPC_H - -#include <linux/in.h> -#include <linux/in6.h> - -/* - * RxRPC socket address - */ -struct sockaddr_rxrpc { - sa_family_t srx_family; /* address family */ - u16 srx_service; /* service desired */ - u16 transport_type; /* type of transport socket (SOCK_DGRAM) */ - u16 transport_len; /* length of transport address */ - union { - sa_family_t family; /* transport address family */ - struct sockaddr_in sin; /* IPv4 transport address */ - struct sockaddr_in6 sin6; /* IPv6 transport address */ - } transport; -}; - -/* - * RxRPC socket options - */ -#define RXRPC_SECURITY_KEY 1 /* [clnt] set client security key */ -#define RXRPC_SECURITY_KEYRING 2 /* [srvr] set ring of server security keys */ -#define RXRPC_EXCLUSIVE_CONNECTION 3 /* Deprecated; use RXRPC_EXCLUSIVE_CALL instead */ -#define RXRPC_MIN_SECURITY_LEVEL 4 /* minimum security level */ -#define RXRPC_UPGRADEABLE_SERVICE 5 /* Upgrade service[0] -> service[1] */ -#define RXRPC_SUPPORTED_CMSG 6 /* Get highest supported control message type */ - -/* - * RxRPC control messages - * - If neither abort or accept are specified, the message is a data message. - * - terminal messages mean that a user call ID tag can be recycled - * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg() - */ -enum rxrpc_cmsg_type { - RXRPC_USER_CALL_ID = 1, /* sr: user call ID specifier */ - RXRPC_ABORT = 2, /* sr: abort request / notification [terminal] */ - RXRPC_ACK = 3, /* -r: [Service] RPC op final ACK received [terminal] */ - RXRPC_NET_ERROR = 5, /* -r: network error received [terminal] */ - RXRPC_BUSY = 6, /* -r: server busy received [terminal] */ - RXRPC_LOCAL_ERROR = 7, /* -r: local error generated [terminal] */ - RXRPC_NEW_CALL = 8, /* -r: [Service] new incoming call notification */ - RXRPC_ACCEPT = 9, /* s-: [Service] accept request */ - RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */ - RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */ - RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */ - RXRPC__SUPPORTED -}; - -/* - * RxRPC security levels - */ -#define RXRPC_SECURITY_PLAIN 0 /* plain secure-checksummed packets only */ -#define RXRPC_SECURITY_AUTH 1 /* authenticated packets */ -#define RXRPC_SECURITY_ENCRYPT 2 /* encrypted packets */ - -/* - * RxRPC security indices - */ -#define RXRPC_SECURITY_NONE 0 /* no security protocol */ -#define RXRPC_SECURITY_RXKAD 2 /* kaserver or kerberos 4 */ -#define RXRPC_SECURITY_RXGK 4 /* gssapi-based */ -#define RXRPC_SECURITY_RXK5 5 /* kerberos 5 */ - -#endif /* _LINUX_RXRPC_H */ diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 5d5415e129d4..3c07e4135127 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -36,7 +36,8 @@ struct user_struct { struct hlist_node uidhash_node; kuid_t uid; -#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ + defined(CONFIG_NET) atomic_long_t locked_vm; #endif }; diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 99e866487e2f..82b171e1aa0b 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -273,87 +273,85 @@ struct sctp_init_chunk { /* Section 3.3.2.1. IPv4 Address Parameter (5) */ -typedef struct sctp_ipv4addr_param { +struct sctp_ipv4addr_param { struct sctp_paramhdr param_hdr; - struct in_addr addr; -} sctp_ipv4addr_param_t; + struct in_addr addr; +}; /* Section 3.3.2.1. IPv6 Address Parameter (6) */ -typedef struct sctp_ipv6addr_param { +struct sctp_ipv6addr_param { struct sctp_paramhdr param_hdr; struct in6_addr addr; -} sctp_ipv6addr_param_t; +}; /* Section 3.3.2.1 Cookie Preservative (9) */ -typedef struct sctp_cookie_preserve_param { +struct sctp_cookie_preserve_param { struct sctp_paramhdr param_hdr; - __be32 lifespan_increment; -} sctp_cookie_preserve_param_t; + __be32 lifespan_increment; +}; /* Section 3.3.2.1 Host Name Address (11) */ -typedef struct sctp_hostname_param { +struct sctp_hostname_param { struct sctp_paramhdr param_hdr; uint8_t hostname[0]; -} sctp_hostname_param_t; +}; /* Section 3.3.2.1 Supported Address Types (12) */ -typedef struct sctp_supported_addrs_param { +struct sctp_supported_addrs_param { struct sctp_paramhdr param_hdr; __be16 types[0]; -} sctp_supported_addrs_param_t; - -/* Appendix A. ECN Capable (32768) */ -typedef struct sctp_ecn_capable_param { - struct sctp_paramhdr param_hdr; -} sctp_ecn_capable_param_t; +}; /* ADDIP Section 3.2.6 Adaptation Layer Indication */ -typedef struct sctp_adaptation_ind_param { +struct sctp_adaptation_ind_param { struct sctp_paramhdr param_hdr; __be32 adaptation_ind; -} sctp_adaptation_ind_param_t; +}; /* ADDIP Section 4.2.7 Supported Extensions Parameter */ -typedef struct sctp_supported_ext_param { +struct sctp_supported_ext_param { struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} sctp_supported_ext_param_t; +}; /* AUTH Section 3.1 Random */ -typedef struct sctp_random_param { +struct sctp_random_param { struct sctp_paramhdr param_hdr; __u8 random_val[0]; -} sctp_random_param_t; +}; /* AUTH Section 3.2 Chunk List */ -typedef struct sctp_chunks_param { +struct sctp_chunks_param { struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} sctp_chunks_param_t; +}; /* AUTH Section 3.3 HMAC Algorithm */ -typedef struct sctp_hmac_algo_param { +struct sctp_hmac_algo_param { struct sctp_paramhdr param_hdr; __be16 hmac_ids[0]; -} sctp_hmac_algo_param_t; +}; /* RFC 2960. Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2): * The INIT ACK chunk is used to acknowledge the initiation of an SCTP * association. */ -typedef struct sctp_init_chunk sctp_initack_chunk_t; +struct sctp_initack_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_inithdr init_hdr; +}; /* Section 3.3.3.1 State Cookie (7) */ -typedef struct sctp_cookie_param { +struct sctp_cookie_param { struct sctp_paramhdr p; __u8 body[0]; -} sctp_cookie_param_t; +}; /* Section 3.3.3.1 Unrecognized Parameters (8) */ -typedef struct sctp_unrecognized_param { +struct sctp_unrecognized_param { struct sctp_paramhdr param_hdr; struct sctp_paramhdr unrecognized; -} sctp_unrecognized_param_t; +}; @@ -365,30 +363,28 @@ typedef struct sctp_unrecognized_param { * subsequences of DATA chunks as represented by their TSNs. */ -typedef struct sctp_gap_ack_block { +struct sctp_gap_ack_block { __be16 start; __be16 end; -} sctp_gap_ack_block_t; - -typedef __be32 sctp_dup_tsn_t; +}; -typedef union { - sctp_gap_ack_block_t gab; - sctp_dup_tsn_t dup; -} sctp_sack_variable_t; +union sctp_sack_variable { + struct sctp_gap_ack_block gab; + __be32 dup; +}; -typedef struct sctp_sackhdr { +struct sctp_sackhdr { __be32 cum_tsn_ack; __be32 a_rwnd; __be16 num_gap_ack_blocks; __be16 num_dup_tsns; - sctp_sack_variable_t variable[0]; -} sctp_sackhdr_t; + union sctp_sack_variable variable[0]; +}; -typedef struct sctp_sack_chunk { +struct sctp_sack_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_sackhdr_t sack_hdr; -} sctp_sack_chunk_t; + struct sctp_sackhdr sack_hdr; +}; /* RFC 2960. Section 3.3.5 Heartbeat Request (HEARTBEAT) (4): @@ -398,49 +394,49 @@ typedef struct sctp_sack_chunk { * the present association. */ -typedef struct sctp_heartbeathdr { +struct sctp_heartbeathdr { struct sctp_paramhdr info; -} sctp_heartbeathdr_t; +}; -typedef struct sctp_heartbeat_chunk { +struct sctp_heartbeat_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_heartbeathdr_t hb_hdr; -} sctp_heartbeat_chunk_t; + struct sctp_heartbeathdr hb_hdr; +}; /* For the abort and shutdown ACK we must carry the init tag in the * common header. Just the common header is all that is needed with a * chunk descriptor. */ -typedef struct sctp_abort_chunk { +struct sctp_abort_chunk { struct sctp_chunkhdr uh; -} sctp_abort_chunk_t; +}; /* For the graceful shutdown we must carry the tag (in common header) * and the highest consecutive acking value. */ -typedef struct sctp_shutdownhdr { +struct sctp_shutdownhdr { __be32 cum_tsn_ack; -} sctp_shutdownhdr_t; +}; -struct sctp_shutdown_chunk_t { +struct sctp_shutdown_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_shutdownhdr_t shutdown_hdr; + struct sctp_shutdownhdr shutdown_hdr; }; /* RFC 2960. Section 3.3.10 Operation Error (ERROR) (9) */ -typedef struct sctp_errhdr { +struct sctp_errhdr { __be16 cause; __be16 length; __u8 variable[0]; -} sctp_errhdr_t; +}; -typedef struct sctp_operr_chunk { +struct sctp_operr_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_errhdr_t err_hdr; -} sctp_operr_chunk_t; + struct sctp_errhdr err_hdr; +}; /* RFC 2960 3.3.10 - Operation Error * @@ -461,7 +457,7 @@ typedef struct sctp_operr_chunk { * 9 No User Data * 10 Cookie Received While Shutting Down */ -typedef enum { +enum sctp_error { SCTP_ERROR_NO_ERROR = cpu_to_be16(0x00), SCTP_ERROR_INV_STRM = cpu_to_be16(0x01), @@ -516,33 +512,28 @@ typedef enum { * 0x0105 Unsupported HMAC Identifier */ SCTP_ERROR_UNSUP_HMAC = cpu_to_be16(0x0105) -} sctp_error_t; +}; /* RFC 2960. Appendix A. Explicit Congestion Notification. * Explicit Congestion Notification Echo (ECNE) (12) */ -typedef struct sctp_ecnehdr { +struct sctp_ecnehdr { __be32 lowest_tsn; -} sctp_ecnehdr_t; +}; -typedef struct sctp_ecne_chunk { +struct sctp_ecne_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_ecnehdr_t ence_hdr; -} sctp_ecne_chunk_t; + struct sctp_ecnehdr ence_hdr; +}; /* RFC 2960. Appendix A. Explicit Congestion Notification. * Congestion Window Reduced (CWR) (13) */ -typedef struct sctp_cwrhdr { +struct sctp_cwrhdr { __be32 lowest_tsn; -} sctp_cwrhdr_t; - -typedef struct sctp_cwr_chunk { - struct sctp_chunkhdr chunk_hdr; - sctp_cwrhdr_t cwr_hdr; -} sctp_cwr_chunk_t; +}; /* PR-SCTP * 3.2 Forward Cumulative TSN Chunk Definition (FORWARD TSN) @@ -638,20 +629,20 @@ struct sctp_fwdtsn_chunk { * The ASCONF Parameter Response is used in the ASCONF-ACK to * report status of ASCONF processing. */ -typedef struct sctp_addip_param { - struct sctp_paramhdr param_hdr; - __be32 crr_id; -} sctp_addip_param_t; +struct sctp_addip_param { + struct sctp_paramhdr param_hdr; + __be32 crr_id; +}; -typedef struct sctp_addiphdr { +struct sctp_addiphdr { __be32 serial; __u8 params[0]; -} sctp_addiphdr_t; +}; -typedef struct sctp_addip_chunk { +struct sctp_addip_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_addiphdr_t addip_hdr; -} sctp_addip_chunk_t; + struct sctp_addiphdr addip_hdr; +}; /* AUTH * Section 4.1 Authentication Chunk (AUTH) @@ -702,16 +693,16 @@ typedef struct sctp_addip_chunk { * HMAC: n bytes (unsigned integer) This hold the result of the HMAC * calculation. */ -typedef struct sctp_authhdr { +struct sctp_authhdr { __be16 shkey_id; __be16 hmac_id; __u8 hmac[0]; -} sctp_authhdr_t; +}; -typedef struct sctp_auth_chunk { +struct sctp_auth_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_authhdr_t auth_hdr; -} sctp_auth_chunk_t; + struct sctp_authhdr auth_hdr; +}; struct sctp_infox { struct sctp_info *sctpinfo; diff --git a/include/linux/seg6_local.h b/include/linux/seg6_local.h new file mode 100644 index 000000000000..ee63e76fe0c7 --- /dev/null +++ b/include/linux/seg6_local.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_LOCAL_H +#define _LINUX_SEG6_LOCAL_H + +#include <uapi/linux/seg6_local.h> + +#endif diff --git a/include/linux/sfp.h b/include/linux/sfp.h new file mode 100644 index 000000000000..4a906f560817 --- /dev/null +++ b/include/linux/sfp.h @@ -0,0 +1,434 @@ +#ifndef LINUX_SFP_H +#define LINUX_SFP_H + +#include <linux/phy.h> + +struct __packed sfp_eeprom_base { + u8 phys_id; + u8 phys_ext_id; + u8 connector; +#if defined __BIG_ENDIAN_BITFIELD + u8 e10g_base_er:1; + u8 e10g_base_lrm:1; + u8 e10g_base_lr:1; + u8 e10g_base_sr:1; + u8 if_1x_sx:1; + u8 if_1x_lx:1; + u8 if_1x_copper_active:1; + u8 if_1x_copper_passive:1; + + u8 escon_mmf_1310_led:1; + u8 escon_smf_1310_laser:1; + u8 sonet_oc192_short_reach:1; + u8 sonet_reach_bit1:1; + u8 sonet_reach_bit2:1; + u8 sonet_oc48_long_reach:1; + u8 sonet_oc48_intermediate_reach:1; + u8 sonet_oc48_short_reach:1; + + u8 unallocated_5_7:1; + u8 sonet_oc12_smf_long_reach:1; + u8 sonet_oc12_smf_intermediate_reach:1; + u8 sonet_oc12_short_reach:1; + u8 unallocated_5_3:1; + u8 sonet_oc3_smf_long_reach:1; + u8 sonet_oc3_smf_intermediate_reach:1; + u8 sonet_oc3_short_reach:1; + + u8 e_base_px:1; + u8 e_base_bx10:1; + u8 e100_base_fx:1; + u8 e100_base_lx:1; + u8 e1000_base_t:1; + u8 e1000_base_cx:1; + u8 e1000_base_lx:1; + u8 e1000_base_sx:1; + + u8 fc_ll_v:1; + u8 fc_ll_s:1; + u8 fc_ll_i:1; + u8 fc_ll_l:1; + u8 fc_ll_m:1; + u8 fc_tech_sa:1; + u8 fc_tech_lc:1; + u8 fc_tech_electrical_inter_enclosure:1; + + u8 fc_tech_electrical_intra_enclosure:1; + u8 fc_tech_sn:1; + u8 fc_tech_sl:1; + u8 fc_tech_ll:1; + u8 sfp_ct_active:1; + u8 sfp_ct_passive:1; + u8 unallocated_8_1:1; + u8 unallocated_8_0:1; + + u8 fc_media_tw:1; + u8 fc_media_tp:1; + u8 fc_media_mi:1; + u8 fc_media_tv:1; + u8 fc_media_m6:1; + u8 fc_media_m5:1; + u8 unallocated_9_1:1; + u8 fc_media_sm:1; + + u8 fc_speed_1200:1; + u8 fc_speed_800:1; + u8 fc_speed_1600:1; + u8 fc_speed_400:1; + u8 fc_speed_3200:1; + u8 fc_speed_200:1; + u8 unallocated_10_1:1; + u8 fc_speed_100:1; +#elif defined __LITTLE_ENDIAN_BITFIELD + u8 if_1x_copper_passive:1; + u8 if_1x_copper_active:1; + u8 if_1x_lx:1; + u8 if_1x_sx:1; + u8 e10g_base_sr:1; + u8 e10g_base_lr:1; + u8 e10g_base_lrm:1; + u8 e10g_base_er:1; + + u8 sonet_oc3_short_reach:1; + u8 sonet_oc3_smf_intermediate_reach:1; + u8 sonet_oc3_smf_long_reach:1; + u8 unallocated_5_3:1; + u8 sonet_oc12_short_reach:1; + u8 sonet_oc12_smf_intermediate_reach:1; + u8 sonet_oc12_smf_long_reach:1; + u8 unallocated_5_7:1; + + u8 sonet_oc48_short_reach:1; + u8 sonet_oc48_intermediate_reach:1; + u8 sonet_oc48_long_reach:1; + u8 sonet_reach_bit2:1; + u8 sonet_reach_bit1:1; + u8 sonet_oc192_short_reach:1; + u8 escon_smf_1310_laser:1; + u8 escon_mmf_1310_led:1; + + u8 e1000_base_sx:1; + u8 e1000_base_lx:1; + u8 e1000_base_cx:1; + u8 e1000_base_t:1; + u8 e100_base_lx:1; + u8 e100_base_fx:1; + u8 e_base_bx10:1; + u8 e_base_px:1; + + u8 fc_tech_electrical_inter_enclosure:1; + u8 fc_tech_lc:1; + u8 fc_tech_sa:1; + u8 fc_ll_m:1; + u8 fc_ll_l:1; + u8 fc_ll_i:1; + u8 fc_ll_s:1; + u8 fc_ll_v:1; + + u8 unallocated_8_0:1; + u8 unallocated_8_1:1; + u8 sfp_ct_passive:1; + u8 sfp_ct_active:1; + u8 fc_tech_ll:1; + u8 fc_tech_sl:1; + u8 fc_tech_sn:1; + u8 fc_tech_electrical_intra_enclosure:1; + + u8 fc_media_sm:1; + u8 unallocated_9_1:1; + u8 fc_media_m5:1; + u8 fc_media_m6:1; + u8 fc_media_tv:1; + u8 fc_media_mi:1; + u8 fc_media_tp:1; + u8 fc_media_tw:1; + + u8 fc_speed_100:1; + u8 unallocated_10_1:1; + u8 fc_speed_200:1; + u8 fc_speed_3200:1; + u8 fc_speed_400:1; + u8 fc_speed_1600:1; + u8 fc_speed_800:1; + u8 fc_speed_1200:1; +#else +#error Unknown Endian +#endif + u8 encoding; + u8 br_nominal; + u8 rate_id; + u8 link_len[6]; + char vendor_name[16]; + u8 extended_cc; + char vendor_oui[3]; + char vendor_pn[16]; + char vendor_rev[4]; + union { + __be16 optical_wavelength; + u8 cable_spec; + }; + u8 reserved62; + u8 cc_base; +}; + +struct __packed sfp_eeprom_ext { + __be16 options; + u8 br_max; + u8 br_min; + char vendor_sn[16]; + char datecode[8]; + u8 diagmon; + u8 enhopts; + u8 sff8472_compliance; + u8 cc_ext; +}; + +struct __packed sfp_eeprom_id { + struct sfp_eeprom_base base; + struct sfp_eeprom_ext ext; +}; + +/* SFP EEPROM registers */ +enum { + SFP_PHYS_ID = 0x00, + SFP_PHYS_EXT_ID = 0x01, + SFP_CONNECTOR = 0x02, + SFP_COMPLIANCE = 0x03, + SFP_ENCODING = 0x0b, + SFP_BR_NOMINAL = 0x0c, + SFP_RATE_ID = 0x0d, + SFP_LINK_LEN_SM_KM = 0x0e, + SFP_LINK_LEN_SM_100M = 0x0f, + SFP_LINK_LEN_50UM_OM2_10M = 0x10, + SFP_LINK_LEN_62_5UM_OM1_10M = 0x11, + SFP_LINK_LEN_COPPER_1M = 0x12, + SFP_LINK_LEN_50UM_OM4_10M = 0x12, + SFP_LINK_LEN_50UM_OM3_10M = 0x13, + SFP_VENDOR_NAME = 0x14, + SFP_VENDOR_OUI = 0x25, + SFP_VENDOR_PN = 0x28, + SFP_VENDOR_REV = 0x38, + SFP_OPTICAL_WAVELENGTH_MSB = 0x3c, + SFP_OPTICAL_WAVELENGTH_LSB = 0x3d, + SFP_CABLE_SPEC = 0x3c, + SFP_CC_BASE = 0x3f, + SFP_OPTIONS = 0x40, /* 2 bytes, MSB, LSB */ + SFP_BR_MAX = 0x42, + SFP_BR_MIN = 0x43, + SFP_VENDOR_SN = 0x44, + SFP_DATECODE = 0x54, + SFP_DIAGMON = 0x5c, + SFP_ENHOPTS = 0x5d, + SFP_SFF8472_COMPLIANCE = 0x5e, + SFP_CC_EXT = 0x5f, + + SFP_PHYS_ID_SFP = 0x03, + SFP_PHYS_EXT_ID_SFP = 0x04, + SFP_CONNECTOR_UNSPEC = 0x00, + /* codes 01-05 not supportable on SFP, but some modules have single SC */ + SFP_CONNECTOR_SC = 0x01, + SFP_CONNECTOR_FIBERJACK = 0x06, + SFP_CONNECTOR_LC = 0x07, + SFP_CONNECTOR_MT_RJ = 0x08, + SFP_CONNECTOR_MU = 0x09, + SFP_CONNECTOR_SG = 0x0a, + SFP_CONNECTOR_OPTICAL_PIGTAIL = 0x0b, + SFP_CONNECTOR_MPO_1X12 = 0x0c, + SFP_CONNECTOR_MPO_2X16 = 0x0d, + SFP_CONNECTOR_HSSDC_II = 0x20, + SFP_CONNECTOR_COPPER_PIGTAIL = 0x21, + SFP_CONNECTOR_RJ45 = 0x22, + SFP_CONNECTOR_NOSEPARATE = 0x23, + SFP_CONNECTOR_MXC_2X16 = 0x24, + SFP_ENCODING_UNSPEC = 0x00, + SFP_ENCODING_8B10B = 0x01, + SFP_ENCODING_4B5B = 0x02, + SFP_ENCODING_NRZ = 0x03, + SFP_ENCODING_8472_MANCHESTER = 0x04, + SFP_ENCODING_8472_SONET = 0x05, + SFP_ENCODING_8472_64B66B = 0x06, + SFP_ENCODING_256B257B = 0x07, + SFP_ENCODING_PAM4 = 0x08, + SFP_OPTIONS_HIGH_POWER_LEVEL = BIT(13), + SFP_OPTIONS_PAGING_A2 = BIT(12), + SFP_OPTIONS_RETIMER = BIT(11), + SFP_OPTIONS_COOLED_XCVR = BIT(10), + SFP_OPTIONS_POWER_DECL = BIT(9), + SFP_OPTIONS_RX_LINEAR_OUT = BIT(8), + SFP_OPTIONS_RX_DECISION_THRESH = BIT(7), + SFP_OPTIONS_TUNABLE_TX = BIT(6), + SFP_OPTIONS_RATE_SELECT = BIT(5), + SFP_OPTIONS_TX_DISABLE = BIT(4), + SFP_OPTIONS_TX_FAULT = BIT(3), + SFP_OPTIONS_LOS_INVERTED = BIT(2), + SFP_OPTIONS_LOS_NORMAL = BIT(1), + SFP_DIAGMON_DDM = BIT(6), + SFP_DIAGMON_INT_CAL = BIT(5), + SFP_DIAGMON_EXT_CAL = BIT(4), + SFP_DIAGMON_RXPWR_AVG = BIT(3), + SFP_DIAGMON_ADDRMODE = BIT(2), + SFP_ENHOPTS_ALARMWARN = BIT(7), + SFP_ENHOPTS_SOFT_TX_DISABLE = BIT(6), + SFP_ENHOPTS_SOFT_TX_FAULT = BIT(5), + SFP_ENHOPTS_SOFT_RX_LOS = BIT(4), + SFP_ENHOPTS_SOFT_RATE_SELECT = BIT(3), + SFP_ENHOPTS_APP_SELECT_SFF8079 = BIT(2), + SFP_ENHOPTS_SOFT_RATE_SFF8431 = BIT(1), + SFP_SFF8472_COMPLIANCE_NONE = 0x00, + SFP_SFF8472_COMPLIANCE_REV9_3 = 0x01, + SFP_SFF8472_COMPLIANCE_REV9_5 = 0x02, + SFP_SFF8472_COMPLIANCE_REV10_2 = 0x03, + SFP_SFF8472_COMPLIANCE_REV10_4 = 0x04, + SFP_SFF8472_COMPLIANCE_REV11_0 = 0x05, + SFP_SFF8472_COMPLIANCE_REV11_3 = 0x06, + SFP_SFF8472_COMPLIANCE_REV11_4 = 0x07, + SFP_SFF8472_COMPLIANCE_REV12_0 = 0x08, +}; + +/* SFP Diagnostics */ +enum { + /* Alarm and warnings stored MSB at lower address then LSB */ + SFP_TEMP_HIGH_ALARM = 0x00, + SFP_TEMP_LOW_ALARM = 0x02, + SFP_TEMP_HIGH_WARN = 0x04, + SFP_TEMP_LOW_WARN = 0x06, + SFP_VOLT_HIGH_ALARM = 0x08, + SFP_VOLT_LOW_ALARM = 0x0a, + SFP_VOLT_HIGH_WARN = 0x0c, + SFP_VOLT_LOW_WARN = 0x0e, + SFP_BIAS_HIGH_ALARM = 0x10, + SFP_BIAS_LOW_ALARM = 0x12, + SFP_BIAS_HIGH_WARN = 0x14, + SFP_BIAS_LOW_WARN = 0x16, + SFP_TXPWR_HIGH_ALARM = 0x18, + SFP_TXPWR_LOW_ALARM = 0x1a, + SFP_TXPWR_HIGH_WARN = 0x1c, + SFP_TXPWR_LOW_WARN = 0x1e, + SFP_RXPWR_HIGH_ALARM = 0x20, + SFP_RXPWR_LOW_ALARM = 0x22, + SFP_RXPWR_HIGH_WARN = 0x24, + SFP_RXPWR_LOW_WARN = 0x26, + SFP_LASER_TEMP_HIGH_ALARM = 0x28, + SFP_LASER_TEMP_LOW_ALARM = 0x2a, + SFP_LASER_TEMP_HIGH_WARN = 0x2c, + SFP_LASER_TEMP_LOW_WARN = 0x2e, + SFP_TEC_CUR_HIGH_ALARM = 0x30, + SFP_TEC_CUR_LOW_ALARM = 0x32, + SFP_TEC_CUR_HIGH_WARN = 0x34, + SFP_TEC_CUR_LOW_WARN = 0x36, + SFP_CAL_RXPWR4 = 0x38, + SFP_CAL_RXPWR3 = 0x3c, + SFP_CAL_RXPWR2 = 0x40, + SFP_CAL_RXPWR1 = 0x44, + SFP_CAL_RXPWR0 = 0x48, + SFP_CAL_TXI_SLOPE = 0x4c, + SFP_CAL_TXI_OFFSET = 0x4e, + SFP_CAL_TXPWR_SLOPE = 0x50, + SFP_CAL_TXPWR_OFFSET = 0x52, + SFP_CAL_T_SLOPE = 0x54, + SFP_CAL_T_OFFSET = 0x56, + SFP_CAL_V_SLOPE = 0x58, + SFP_CAL_V_OFFSET = 0x5a, + SFP_CHKSUM = 0x5f, + + SFP_TEMP = 0x60, + SFP_VCC = 0x62, + SFP_TX_BIAS = 0x64, + SFP_TX_POWER = 0x66, + SFP_RX_POWER = 0x68, + SFP_LASER_TEMP = 0x6a, + SFP_TEC_CUR = 0x6c, + + SFP_STATUS = 0x6e, + SFP_ALARM = 0x70, + + SFP_EXT_STATUS = 0x76, + SFP_VSL = 0x78, + SFP_PAGE = 0x7f, +}; + +struct device_node; +struct ethtool_eeprom; +struct ethtool_modinfo; +struct net_device; +struct sfp_bus; + +struct sfp_upstream_ops { + int (*module_insert)(void *, const struct sfp_eeprom_id *id); + void (*module_remove)(void *); + void (*link_down)(void *); + void (*link_up)(void *); + int (*connect_phy)(void *, struct phy_device *); + void (*disconnect_phy)(void *); +}; + +#if IS_ENABLED(CONFIG_SFP) +int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, + unsigned long *support); +phy_interface_t sfp_parse_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id); +void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, + unsigned long *support); + +int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo); +int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, + u8 *data); +void sfp_upstream_start(struct sfp_bus *bus); +void sfp_upstream_stop(struct sfp_bus *bus); +struct sfp_bus *sfp_register_upstream(struct device_node *np, + struct net_device *ndev, void *upstream, + const struct sfp_upstream_ops *ops); +void sfp_unregister_upstream(struct sfp_bus *bus); +#else +static inline int sfp_parse_port(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *support) +{ + return PORT_OTHER; +} + +static inline phy_interface_t sfp_parse_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id) +{ + return PHY_INTERFACE_MODE_NA; +} + +static inline void sfp_parse_support(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *support) +{ +} + +static inline int sfp_get_module_info(struct sfp_bus *bus, + struct ethtool_modinfo *modinfo) +{ + return -EOPNOTSUPP; +} + +static inline int sfp_get_module_eeprom(struct sfp_bus *bus, + struct ethtool_eeprom *ee, u8 *data) +{ + return -EOPNOTSUPP; +} + +static inline void sfp_upstream_start(struct sfp_bus *bus) +{ +} + +static inline void sfp_upstream_stop(struct sfp_bus *bus) +{ +} + +static inline struct sfp_bus *sfp_register_upstream(struct device_node *np, + struct net_device *ndev, void *upstream, + const struct sfp_upstream_ops *ops) +{ + return (struct sfp_bus *)-1; +} + +static inline void sfp_unregister_upstream(struct sfp_bus *bus) +{ +} +#endif + +#endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d67a8182e5eb..f93cc01064cb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -345,6 +345,42 @@ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) frag->size -= delta; } +static inline bool skb_frag_must_loop(struct page *p) +{ +#if defined(CONFIG_HIGHMEM) + if (PageHighMem(p)) + return true; +#endif + return false; +} + +/** + * skb_frag_foreach_page - loop over pages in a fragment + * + * @f: skb frag to operate on + * @f_off: offset from start of f->page.p + * @f_len: length from f_off to loop over + * @p: (temp var) current page + * @p_off: (temp var) offset from start of current page, + * non-zero only on first page. + * @p_len: (temp var) length in current page, + * < PAGE_SIZE only on first and last page. + * @copied: (temp var) length so far, excluding current p_len. + * + * A fragment can hold a compound page, in which case per-page + * operations, notably kmap_atomic, must be called for each + * regular page. + */ +#define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ + for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ + p_off = (f_off) & (PAGE_SIZE - 1), \ + p_len = skb_frag_must_loop(p) ? \ + min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ + copied = 0; \ + copied < f_len; \ + copied += p_len, p++, p_off = 0, \ + p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ + #define HAVE_HW_TIME_STAMP /** @@ -393,6 +429,7 @@ enum { SKBTX_SCHED_TSTAMP = 1 << 6, }; +#define SKBTX_ZEROCOPY_FRAG (SKBTX_DEV_ZEROCOPY | SKBTX_SHARED_FRAG) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) @@ -407,10 +444,46 @@ enum { */ struct ubuf_info { void (*callback)(struct ubuf_info *, bool zerocopy_success); - void *ctx; - unsigned long desc; + union { + struct { + unsigned long desc; + void *ctx; + }; + struct { + u32 id; + u16 len; + u16 zerocopy:1; + u32 bytelen; + }; + }; + atomic_t refcnt; + + struct mmpin { + struct user_struct *user; + unsigned int num_pg; + } mmp; }; +#define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) + +struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); +struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg); + +static inline void sock_zerocopy_get(struct ubuf_info *uarg) +{ + atomic_inc(&uarg->refcnt); +} + +void sock_zerocopy_put(struct ubuf_info *uarg); +void sock_zerocopy_put_abort(struct ubuf_info *uarg); + +void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg); + /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -463,39 +536,38 @@ enum { enum { SKB_GSO_TCPV4 = 1 << 0, - SKB_GSO_UDP = 1 << 1, /* This indicates the skb is from an untrusted source. */ - SKB_GSO_DODGY = 1 << 2, + SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ - SKB_GSO_TCP_ECN = 1 << 3, + SKB_GSO_TCP_ECN = 1 << 2, - SKB_GSO_TCP_FIXEDID = 1 << 4, + SKB_GSO_TCP_FIXEDID = 1 << 3, - SKB_GSO_TCPV6 = 1 << 5, + SKB_GSO_TCPV6 = 1 << 4, - SKB_GSO_FCOE = 1 << 6, + SKB_GSO_FCOE = 1 << 5, - SKB_GSO_GRE = 1 << 7, + SKB_GSO_GRE = 1 << 6, - SKB_GSO_GRE_CSUM = 1 << 8, + SKB_GSO_GRE_CSUM = 1 << 7, - SKB_GSO_IPXIP4 = 1 << 9, + SKB_GSO_IPXIP4 = 1 << 8, - SKB_GSO_IPXIP6 = 1 << 10, + SKB_GSO_IPXIP6 = 1 << 9, - SKB_GSO_UDP_TUNNEL = 1 << 11, + SKB_GSO_UDP_TUNNEL = 1 << 10, - SKB_GSO_UDP_TUNNEL_CSUM = 1 << 12, + SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, - SKB_GSO_PARTIAL = 1 << 13, + SKB_GSO_PARTIAL = 1 << 12, - SKB_GSO_TUNNEL_REMCSUM = 1 << 14, + SKB_GSO_TUNNEL_REMCSUM = 1 << 13, - SKB_GSO_SCTP = 1 << 15, + SKB_GSO_SCTP = 1 << 14, - SKB_GSO_ESP = 1 << 16, + SKB_GSO_ESP = 1 << 15, }; #if BITS_PER_LONG > 32 @@ -945,12 +1017,6 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } -struct sk_buff *__alloc_skb_head(gfp_t priority, int node); -static inline struct sk_buff *alloc_skb_head(gfp_t priority) -{ - return __alloc_skb_head(priority, -1); -} - struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); @@ -1145,8 +1211,6 @@ static inline __u32 skb_get_hash(struct sk_buff *skb) return skb->hash; } -__u32 __skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6); - static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { @@ -1159,20 +1223,6 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 return skb->hash; } -__u32 __skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl); - -static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl4) -{ - if (!skb->l4_hash && !skb->sw_hash) { - struct flow_keys keys; - __u32 hash = __get_hash_from_flowi4(fl4, &keys); - - __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); - } - - return skb->hash; -} - __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) @@ -1217,6 +1267,50 @@ static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) return &skb_shinfo(skb)->hwtstamps; } +static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) +{ + bool is_zcopy = skb && skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY; + + return is_zcopy ? skb_uarg(skb) : NULL; +} + +static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) +{ + if (skb && uarg && !skb_zcopy(skb)) { + sock_zerocopy_get(uarg); + skb_shinfo(skb)->destructor_arg = uarg; + skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; + } +} + +/* Release a reference on a zerocopy structure */ +static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) +{ + struct ubuf_info *uarg = skb_zcopy(skb); + + if (uarg) { + if (uarg->callback == sock_zerocopy_callback) { + uarg->zerocopy = uarg->zerocopy && zerocopy; + sock_zerocopy_put(uarg); + } else { + uarg->callback(uarg, zerocopy); + } + + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + } +} + +/* Abort a zerocopy operation and revert zckey on error in send syscall */ +static inline void skb_zcopy_abort(struct sk_buff *skb) +{ + struct ubuf_info *uarg = skb_zcopy(skb); + + if (uarg) { + sock_zerocopy_put_abort(uarg); + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + } +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head @@ -1799,13 +1893,18 @@ static inline unsigned int skb_headlen(const struct sk_buff *skb) return skb->len - skb->data_len; } -static inline unsigned int skb_pagelen(const struct sk_buff *skb) +static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); - return len + skb_headlen(skb); + return len; +} + +static inline unsigned int skb_pagelen(const struct sk_buff *skb) +{ + return skb_headlen(skb) + __skb_pagelen(skb); } /** @@ -2450,7 +2549,17 @@ static inline void skb_orphan(struct sk_buff *skb) */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { - if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY))) + if (likely(!skb_zcopy(skb))) + return 0; + if (skb_uarg(skb)->callback == sock_zerocopy_callback) + return 0; + return skb_copy_ubufs(skb, gfp_mask); +} + +/* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ +static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) +{ + if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } @@ -2899,6 +3008,8 @@ static inline int skb_add_data(struct sk_buff *skb, static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { + if (skb_zcopy(skb)) + return false; if (i) { const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; @@ -3153,6 +3264,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); +int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, + int len); +int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, diff --git a/include/linux/socket.h b/include/linux/socket.h index 8b13db5163cc..8ad963cdc88c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -287,6 +287,7 @@ struct ucred { #define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN +#define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file descriptor received through diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3cb15ea48aee..c9170218e9e6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -172,8 +172,20 @@ extern struct trace_event_functions exit_syscall_print_funcs; static struct syscall_metadata __used \ __attribute__((section("__syscalls_metadata"))) \ *__p_syscall_meta_##sname = &__syscall_meta_##sname; + +static inline int is_syscall_trace_event(struct trace_event_call *tp_event) +{ + return tp_event->class == &event_class_syscall_enter || + tp_event->class == &event_class_syscall_exit; +} + #else #define SYSCALL_METADATA(sname, nb, ...) + +static inline int is_syscall_trace_event(struct trace_event_call *tp_event) +{ + return 0; +} #endif #define SYSCALL_DEFINE0(sname) \ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 542ca1ae02c4..4aa40ef02d32 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -192,15 +192,6 @@ struct tcp_sock { struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ - /* Data for direct copy to user */ - struct { - struct sk_buff_head prequeue; - struct task_struct *task; - struct msghdr *msg; - int memory; - int len; - } ucopy; - u32 snd_wl1; /* Sequence for window update */ u32 snd_wnd; /* The window we expect to receive */ u32 max_window; /* Maximal window ever seen from peer */ @@ -273,7 +264,7 @@ struct tcp_sock { u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; u32 snd_cwnd_stamp; - u32 prior_cwnd; /* Congestion window at start of Recovery. */ + u32 prior_cwnd; /* cwnd right before starting loss recovery */ u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ diff --git a/include/linux/tnum.h b/include/linux/tnum.h new file mode 100644 index 000000000000..0d2d3da46139 --- /dev/null +++ b/include/linux/tnum.h @@ -0,0 +1,81 @@ +/* tnum: tracked (or tristate) numbers + * + * A tnum tracks knowledge about the bits of a value. Each bit can be either + * known (0 or 1), or unknown (x). Arithmetic operations on tnums will + * propagate the unknown bits such that the tnum result represents all the + * possible results for possible values of the operands. + */ +#include <linux/types.h> + +struct tnum { + u64 value; + u64 mask; +}; + +/* Constructors */ +/* Represent a known constant as a tnum. */ +struct tnum tnum_const(u64 value); +/* A completely unknown value */ +extern const struct tnum tnum_unknown; +/* A value that's unknown except that @min <= value <= @max */ +struct tnum tnum_range(u64 min, u64 max); + +/* Arithmetic and logical ops */ +/* Shift a tnum left (by a fixed shift) */ +struct tnum tnum_lshift(struct tnum a, u8 shift); +/* Shift a tnum right (by a fixed shift) */ +struct tnum tnum_rshift(struct tnum a, u8 shift); +/* Add two tnums, return @a + @b */ +struct tnum tnum_add(struct tnum a, struct tnum b); +/* Subtract two tnums, return @a - @b */ +struct tnum tnum_sub(struct tnum a, struct tnum b); +/* Bitwise-AND, return @a & @b */ +struct tnum tnum_and(struct tnum a, struct tnum b); +/* Bitwise-OR, return @a | @b */ +struct tnum tnum_or(struct tnum a, struct tnum b); +/* Bitwise-XOR, return @a ^ @b */ +struct tnum tnum_xor(struct tnum a, struct tnum b); +/* Multiply two tnums, return @a * @b */ +struct tnum tnum_mul(struct tnum a, struct tnum b); + +/* Return a tnum representing numbers satisfying both @a and @b */ +struct tnum tnum_intersect(struct tnum a, struct tnum b); + +/* Return @a with all but the lowest @size bytes cleared */ +struct tnum tnum_cast(struct tnum a, u8 size); + +/* Returns true if @a is a known constant */ +static inline bool tnum_is_const(struct tnum a) +{ + return !a.mask; +} + +/* Returns true if @a == tnum_const(@b) */ +static inline bool tnum_equals_const(struct tnum a, u64 b) +{ + return tnum_is_const(a) && a.value == b; +} + +/* Returns true if @a is completely unknown */ +static inline bool tnum_is_unknown(struct tnum a) +{ + return !~a.mask; +} + +/* Returns true if @a is known to be a multiple of @size. + * @size must be a power of two. + */ +bool tnum_is_aligned(struct tnum a, u64 size); + +/* Returns true if @b represents a subset of @a. */ +bool tnum_in(struct tnum a, struct tnum b); + +/* Formatting functions. These have snprintf-like semantics: they will write + * up to @size bytes (including the terminating NUL byte), and return the number + * of bytes (excluding the terminating NUL) which would have been written had + * sufficient space been available. (Thus tnum_sbin always returns 64.) + */ +/* Format a tnum as a pair of hex numbers (value; mask) */ +int tnum_strn(char *str, size_t size, struct tnum a); +/* Format a tnum as tristate binary expansion */ +int tnum_sbin(char *str, size_t size, struct tnum a); diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 5209b5ed2a64..32fb046f2173 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -18,9 +18,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; break; - case VIRTIO_NET_HDR_GSO_UDP: - gso_type = SKB_GSO_UDP; - break; default: return -EINVAL; } @@ -73,8 +70,6 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; - else if (sinfo->gso_type & SKB_GSO_UDP) - hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) |