diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/bpf-cgroup.h | 24 | ||||
| -rw-r--r-- | include/linux/bpf.h | 1 | ||||
| -rw-r--r-- | include/linux/bpf_lirc.h | 29 | ||||
| -rw-r--r-- | include/linux/bpf_types.h | 3 | ||||
| -rw-r--r-- | include/linux/filter.h | 44 | ||||
| -rw-r--r-- | include/linux/netdevice.h | 21 | ||||
| -rw-r--r-- | include/net/xdp.h | 14 | ||||
| -rw-r--r-- | include/net/xdp_sock.h | 44 | ||||
| -rw-r--r-- | include/uapi/linux/bpf.h | 136 | ||||
| -rw-r--r-- | include/uapi/linux/if_xdp.h | 16 |
10 files changed, 277 insertions, 55 deletions
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 30d15e64b993..975fb4cf1bb7 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -66,7 +66,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type); + enum bpf_attach_type type, + void *t_ctx); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, @@ -120,16 +121,18 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + NULL); \ __ret; \ }) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type) \ +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + t_ctx); \ release_sock(sk); \ } \ __ret; \ @@ -151,10 +154,16 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_CONNECT) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT, NULL) + +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_SENDMSG, t_ctx) + +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ @@ -185,6 +194,7 @@ struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } +#define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) @@ -197,6 +207,8 @@ static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) +#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; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bbe297436e5d..995c3b1e59bf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -746,6 +746,7 @@ extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; +extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/bpf_lirc.h b/include/linux/bpf_lirc.h new file mode 100644 index 000000000000..5f8a4283092d --- /dev/null +++ b/include/linux/bpf_lirc.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_LIRC_H +#define _BPF_LIRC_H + +#include <uapi/linux/bpf.h> + +#ifdef CONFIG_BPF_LIRC_MODE2 +int lirc_prog_attach(const union bpf_attr *attr); +int lirc_prog_detach(const union bpf_attr *attr); +int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +#else +static inline int lirc_prog_attach(const union bpf_attr *attr) +{ + return -EINVAL; +} + +static inline int lirc_prog_detach(const union bpf_attr *attr) +{ + return -EINVAL; +} + +static inline int lirc_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} +#endif + +#endif /* _BPF_LIRC_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index b161e506dcfc..c5700c2d5549 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -26,6 +26,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) #endif +#ifdef CONFIG_BPF_LIRC_MODE2 +BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/filter.h b/include/linux/filter.h index d358d1815c16..45fc0f5000d8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -289,8 +289,21 @@ struct xdp_buff; .off = OFF, \ .imm = 0 }) +/* Relative call */ + +#define BPF_CALL_REL(TGT) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_CALL, \ + .dst_reg = 0, \ + .src_reg = BPF_PSEUDO_CALL, \ + .off = 0, \ + .imm = TGT }) + /* Function call */ +#define BPF_CAST_CALL(x) \ + ((u64 (*)(u64, u64, u64, u64, u64))(x)) + #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ @@ -626,16 +639,34 @@ static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) return prog->type == BPF_PROG_TYPE_UNSPEC; } -static inline bool -bpf_ctx_narrow_access_ok(u32 off, u32 size, const u32 size_default) +static inline u32 bpf_ctx_off_adjust_machine(u32 size) +{ + const u32 size_machine = sizeof(unsigned long); + + if (size > size_machine && size % size_machine == 0) + size = size_machine; + + return size; +} + +static inline bool bpf_ctx_narrow_align_ok(u32 off, u32 size_access, + u32 size_default) { - bool off_ok; + size_default = bpf_ctx_off_adjust_machine(size_default); + size_access = bpf_ctx_off_adjust_machine(size_access); + #ifdef __LITTLE_ENDIAN - off_ok = (off & (size_default - 1)) == 0; + return (off & (size_default - 1)) == 0; #else - off_ok = (off & (size_default - 1)) + size == size_default; + return (off & (size_default - 1)) + size_access == size_default; #endif - return off_ok && size <= size_default && (size & (size - 1)) == 0; +} + +static inline bool +bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) +{ + return bpf_ctx_narrow_align_ok(off, size, size_default) && + size <= size_default && (size & (size - 1)) == 0; } #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) @@ -1010,6 +1041,7 @@ struct bpf_sock_addr_kern { * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; + void *t_ctx; /* Attach type specific context. */ }; struct bpf_sock_ops_kern { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6b863ed3174a..3ec9850c7936 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -818,10 +818,13 @@ enum bpf_netdev_command { BPF_OFFLOAD_DESTROY, BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, + XDP_QUERY_XSK_UMEM, + XDP_SETUP_XSK_UMEM, }; struct bpf_prog_offload_ops; struct netlink_ext_ack; +struct xdp_umem; struct netdev_bpf { enum bpf_netdev_command command; @@ -852,6 +855,11 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; + /* XDP_SETUP_XSK_UMEM */ + struct { + struct xdp_umem *umem; + u16 queue_id; + } xsk; }; }; @@ -1186,16 +1194,13 @@ struct dev_ifalias { * This function is used to set or query state related to XDP on the * netdevice and manage BPF offload. See definition of * enum bpf_netdev_command for details. - * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp); + * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, + * u32 flags); * This function is used to submit @n XDP packets for transmit on a * netdevice. Returns number of frames successfully transmitted, frames * 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. - * TODO: Consider add flag to allow sending flush operation. - * 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); @@ -1381,8 +1386,10 @@ struct net_device_ops { int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); int (*ndo_xdp_xmit)(struct net_device *dev, int n, - struct xdp_frame **xdp); - void (*ndo_xdp_flush)(struct net_device *dev); + struct xdp_frame **xdp, + u32 flags); + int (*ndo_xsk_async_xmit)(struct net_device *dev, + u32 queue_id); }; /** diff --git a/include/net/xdp.h b/include/net/xdp.h index 7ad779237ae8..2deea7166a34 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -37,9 +37,14 @@ enum xdp_mem_type { MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */ MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */ MEM_TYPE_PAGE_POOL, + MEM_TYPE_ZERO_COPY, MEM_TYPE_MAX, }; +/* XDP flags for ndo_xdp_xmit */ +#define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ +#define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH + struct xdp_mem_info { u32 type; /* enum xdp_mem_type, but known size type */ u32 id; @@ -47,6 +52,10 @@ struct xdp_mem_info { struct page_pool; +struct zero_copy_allocator { + void (*free)(struct zero_copy_allocator *zca, unsigned long handle); +}; + struct xdp_rxq_info { struct net_device *dev; u32 queue_index; @@ -59,6 +68,7 @@ struct xdp_buff { void *data_end; void *data_meta; void *data_hard_start; + unsigned long handle; struct xdp_rxq_info *rxq; }; @@ -82,6 +92,10 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) int metasize; int headroom; + /* TODO: implement clone, copy, use "native" MEM_TYPE */ + if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) + return NULL; + /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; metasize = xdp->data - xdp->data_meta; diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 7a647c56ec15..9fe472f2ac95 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -6,12 +6,46 @@ #ifndef _LINUX_XDP_SOCK_H #define _LINUX_XDP_SOCK_H +#include <linux/workqueue.h> +#include <linux/if_xdp.h> #include <linux/mutex.h> +#include <linux/spinlock.h> +#include <linux/mm.h> #include <net/sock.h> struct net_device; struct xsk_queue; -struct xdp_umem; + +struct xdp_umem_props { + u64 chunk_mask; + u64 size; +}; + +struct xdp_umem_page { + void *addr; + dma_addr_t dma; +}; + +struct xdp_umem { + struct xsk_queue *fq; + struct xsk_queue *cq; + struct xdp_umem_page *pages; + struct xdp_umem_props props; + u32 headroom; + u32 chunk_size_nohr; + struct user_struct *user; + struct pid *pid; + unsigned long address; + refcount_t users; + struct work_struct work; + struct page **pgs; + u32 npgs; + struct net_device *dev; + u16 queue_id; + bool zc; + spinlock_t xsk_list_lock; + struct list_head xsk_list; +}; struct xdp_sock { /* struct sock must be the first member of struct xdp_sock */ @@ -22,6 +56,8 @@ struct xdp_sock { struct list_head flush_node; u16 queue_id; struct xsk_queue *tx ____cacheline_aligned_in_smp; + struct list_head list; + bool zc; /* Protects multiple processes in the control path */ struct mutex mutex; u64 rx_dropped; @@ -33,6 +69,12 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); void xsk_flush(struct xdp_sock *xs); bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs); +/* Used from netdev driver */ +u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr); +void xsk_umem_discard_addr(struct xdp_umem *umem); +void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); +bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len); +void xsk_umem_consume_tx_done(struct xdp_umem *umem); #else static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 671486133988..59b19b6a40d7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -143,6 +143,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_RAW_TRACEPOINT, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_PROG_TYPE_LWT_SEG6LOCAL, + BPF_PROG_TYPE_LIRC_MODE2, }; enum bpf_attach_type { @@ -160,6 +161,9 @@ enum bpf_attach_type { BPF_CGROUP_INET6_CONNECT, BPF_CGROUP_INET4_POST_BIND, BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + BPF_LIRC_MODE2, __MAX_BPF_ATTACH_TYPE }; @@ -1008,7 +1012,6 @@ union bpf_attr { * :: * * # sysctl kernel.perf_event_max_stack=<new value> - * * Return * The positive or null stack id on success, or a negative error * in case of failure. @@ -1819,10 +1822,9 @@ union bpf_attr { * :: * * # sysctl kernel.perf_event_max_stack=<new value> - * * Return - * a non-negative value equal to or less than size on success, or - * a negative error in case of failure. + * A non-negative value equal to or less than *size* on success, + * or a negative error in case of failure. * * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) * Description @@ -1843,7 +1845,6 @@ union bpf_attr { * in socket filters where *skb*\ **->data** does not always point * to the start of the mac header and where "direct packet access" * is not available. - * * Return * 0 on success, or a negative error in case of failure. * @@ -1853,22 +1854,24 @@ union bpf_attr { * If lookup is successful and result shows packet is to be * forwarded, the neighbor tables are searched for the nexthop. * If successful (ie., FIB lookup shows forwarding and nexthop - * is resolved), the nexthop address is returned in ipv4_dst, - * ipv6_dst or mpls_out based on family, smac is set to mac - * address of egress device, dmac is set to nexthop mac address, - * rt_metric is set to metric from route. + * is resolved), the nexthop address is returned in ipv4_dst + * or ipv6_dst based on family, smac is set to mac address of + * egress device, dmac is set to nexthop mac address, rt_metric + * is set to metric from route (IPv4/IPv6 only). * * *plen* argument is the size of the passed in struct. - * *flags* argument can be one or more BPF_FIB_LOOKUP_ flags: + * *flags* argument can be a combination of one or more of the + * following values: * - * **BPF_FIB_LOOKUP_DIRECT** means do a direct table lookup vs - * full lookup using FIB rules - * **BPF_FIB_LOOKUP_OUTPUT** means do lookup from an egress - * perspective (default is ingress) + * **BPF_FIB_LOOKUP_DIRECT** + * Do a direct table lookup vs full lookup using FIB + * rules. + * **BPF_FIB_LOOKUP_OUTPUT** + * Perform lookup from an egress perspective (default is + * ingress). * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. - * * Return * Egress device index on success, 0 if packet needs to continue * up the stack for further processing or a negative error in case @@ -2004,6 +2007,74 @@ union bpf_attr { * direct packet access. * Return * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown** () again with the same values, or calling + * **bpf_rc_repeat** (). + * + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Return + * 0 + * + * int bpf_rc_repeat(void *ctx) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. + * + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Return + * 0 + * + * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb) + * Description + * Return the cgroup v2 id of the socket associated with the *skb*. + * This is roughly similar to the **bpf_get_cgroup_classid**\ () + * helper for cgroup v1 by providing a tag resp. identifier that + * can be matched on or used for map lookups e.g. to implement + * policy. The cgroup v2 id of a given path in the hierarchy is + * exposed in user space through the f_handle API in order to get + * to the same 64-bit id. + * + * This helper can be used on TC egress path, but not on ingress, + * and is available only if the kernel was compiled with the + * **CONFIG_SOCK_CGROUP_DATA** configuration option. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_get_current_cgroup_id(void) + * Return + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2082,7 +2153,11 @@ union bpf_attr { FN(lwt_push_encap), \ FN(lwt_seg6_store_bytes), \ FN(lwt_seg6_adjust_srh), \ - FN(lwt_seg6_action), + FN(lwt_seg6_action), \ + FN(rc_repeat), \ + FN(rc_keydown), \ + FN(skb_cgroup_id), \ + FN(get_current_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2199,7 +2274,7 @@ struct bpf_tunnel_key { }; __u8 tunnel_tos; __u8 tunnel_ttl; - __u16 tunnel_ext; + __u16 tunnel_ext; /* Padding, future use. */ __u32 tunnel_label; }; @@ -2210,6 +2285,7 @@ struct bpf_xfrm_state { __u32 reqid; __u32 spi; /* Stored in network byte order */ __u16 family; + __u16 ext; /* Padding, future use. */ union { __u32 remote_ipv4; /* Stored in network byte order */ __u32 remote_ipv6[4]; /* Stored in network byte order */ @@ -2364,6 +2440,12 @@ struct bpf_sock_addr { __u32 family; /* Allows 4-byte read, but no write */ __u32 type; /* Allows 4-byte read, but no write */ __u32 protocol; /* Allows 4-byte read, but no write */ + __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ }; /* User bpf_sock_ops struct to access socket values and specify request ops @@ -2531,8 +2613,10 @@ struct bpf_raw_tracepoint_args { #define BPF_FIB_LOOKUP_OUTPUT BIT(1) struct bpf_fib_lookup { - /* input */ - __u8 family; /* network family, AF_INET, AF_INET6, AF_MPLS */ + /* input: network family for lookup (AF_INET, AF_INET6) + * output: network family of egress nexthop + */ + __u8 family; /* set if lookup is to consider L4 data - e.g., FIB rules */ __u8 l4_protocol; @@ -2546,24 +2630,22 @@ struct bpf_fib_lookup { union { /* inputs to lookup */ __u8 tos; /* AF_INET */ - __be32 flowlabel; /* AF_INET6 */ + __be32 flowinfo; /* AF_INET6, flow_label + priority */ - /* output: metric of fib result */ - __u32 rt_metric; + /* output: metric of fib result (IPv4/IPv6 only) */ + __u32 rt_metric; }; union { - __be32 mpls_in; __be32 ipv4_src; __u32 ipv6_src[4]; /* in6_addr; network order */ }; - /* input to bpf_fib_lookup, *dst is destination address. - * output: bpf_fib_lookup sets to gateway address + /* input to bpf_fib_lookup, ipv{4,6}_dst is destination address in + * network header. output: bpf_fib_lookup sets to gateway address + * if FIB lookup returns gateway route */ union { - /* return for MPLS lookups */ - __be32 mpls_out[4]; /* support up to 4 labels */ __be32 ipv4_dst; __u32 ipv6_dst[4]; /* in6_addr; network order */ }; diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index 4737cfe222f5..1fa0e977ea8d 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -13,7 +13,9 @@ #include <linux/types.h> /* Options for the sxdp_flags field */ -#define XDP_SHARED_UMEM 1 +#define XDP_SHARED_UMEM (1 << 0) +#define XDP_COPY (1 << 1) /* Force copy-mode */ +#define XDP_ZEROCOPY (1 << 2) /* Force zero-copy mode */ struct sockaddr_xdp { __u16 sxdp_family; @@ -48,8 +50,8 @@ struct xdp_mmap_offsets { struct xdp_umem_reg { __u64 addr; /* Start of packet data area */ __u64 len; /* Length of packet data area */ - __u32 frame_size; /* Frame size */ - __u32 frame_headroom; /* Frame head room */ + __u32 chunk_size; + __u32 headroom; }; struct xdp_statistics { @@ -66,13 +68,11 @@ struct xdp_statistics { /* Rx/Tx descriptor */ struct xdp_desc { - __u32 idx; + __u64 addr; __u32 len; - __u16 offset; - __u8 flags; - __u8 padding[5]; + __u32 options; }; -/* UMEM descriptor is __u32 */ +/* UMEM descriptor is __u64 */ #endif /* _LINUX_IF_XDP_H */ |