diff options
author | David S. Miller <davem@davemloft.net> | 2018-05-24 22:20:51 -0400 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2018-05-24 22:20:51 -0400 |
commit | 90fed9c94625718a3a10db7d1e8e4efe093bbf5f (patch) | |
tree | 09b3bc9ea679316372b139338179a230105306dc /include | |
parent | 49a473f5b5f54f33e0bd8618158d33f83153c921 (diff) | |
parent | 10f678683e4026e43524b0492068a371d00fdeed (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2018-05-24
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Björn Töpel cleans up AF_XDP (removes rebind, explicit cache alignment from uapi, etc).
2) David Ahern adds mtu checks to bpf_ipv{4,6}_fib_lookup() helpers.
3) Jesper Dangaard Brouer adds bulking support to ndo_xdp_xmit.
4) Jiong Wang adds support for indirect and arithmetic shifts to NFP
5) Martin KaFai Lau cleans up BTF uapi and makes the btf_header extensible.
6) Mathieu Xhonneux adds an End.BPF action to seg6local with BPF helpers allowing
to edit/grow/shrink a SRH and apply on a packet generic SRv6 actions.
7) Sandipan Das adds support for bpf2bpf function calls in ppc64 JIT.
8) Yonghong Song adds BPF_TASK_FD_QUERY command for introspection of tracing events.
9) other misc fixes from Gustavo A. R. Silva, Sirio Balmelli, John Fastabend, and Magnus Karlsson
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/bpf.h | 24 | ||||
-rw-r--r-- | include/linux/bpf_types.h | 5 | ||||
-rw-r--r-- | include/linux/filter.h | 1 | ||||
-rw-r--r-- | include/linux/netdevice.h | 14 | ||||
-rw-r--r-- | include/linux/perf_event.h | 5 | ||||
-rw-r--r-- | include/linux/trace_events.h | 17 | ||||
-rw-r--r-- | include/net/addrconf.h | 2 | ||||
-rw-r--r-- | include/net/ip6_fib.h | 6 | ||||
-rw-r--r-- | include/net/ip6_route.h | 3 | ||||
-rw-r--r-- | include/net/ip_fib.h | 2 | ||||
-rw-r--r-- | include/net/page_pool.h | 5 | ||||
-rw-r--r-- | include/net/seg6.h | 7 | ||||
-rw-r--r-- | include/net/seg6_local.h | 32 | ||||
-rw-r--r-- | include/net/xdp.h | 1 | ||||
-rw-r--r-- | include/net/xdp_sock.h | 13 | ||||
-rw-r--r-- | include/trace/events/xdp.h | 50 | ||||
-rw-r--r-- | include/uapi/linux/bpf.h | 143 | ||||
-rw-r--r-- | include/uapi/linux/btf.h | 37 | ||||
-rw-r--r-- | include/uapi/linux/if_xdp.h | 59 | ||||
-rw-r--r-- | include/uapi/linux/seg6_local.h | 12 |
20 files changed, 346 insertions, 92 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ed0122b45b63..bbe297436e5d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -69,8 +69,8 @@ struct bpf_map { u32 pages; u32 id; int numa_node; - u32 btf_key_id; - u32 btf_value_id; + u32 btf_key_type_id; + u32 btf_value_type_id; struct btf *btf; bool unpriv_array; /* 55 bytes hole */ @@ -463,6 +463,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); +int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size, + size_t actual_size); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. @@ -485,14 +487,17 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); /* Map specifics */ -struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); +struct xdp_buff; + +struct bpf_dtab_netdev *__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); +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, + struct net_device *dev_rx); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); void __cpu_map_flush(struct bpf_map *map); -struct xdp_buff; int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -571,6 +576,16 @@ static inline void __dev_map_flush(struct bpf_map *map) { } +struct xdp_buff; +struct bpf_dtab_netdev; + +static inline +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + return 0; +} + static inline struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) { @@ -585,7 +600,6 @@ static inline void __cpu_map_flush(struct bpf_map *map) { } -struct xdp_buff; static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx) diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index b67f8793de0d..b161e506dcfc 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -9,9 +9,10 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local) BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg) diff --git a/include/linux/filter.h b/include/linux/filter.h index 9dbcb9d55921..d358d1815c16 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -517,6 +517,7 @@ struct sk_msg_buff { bool sg_copy[MAX_SKB_FRAGS]; __u32 flags; struct sock *sk_redir; + struct sock *sk; struct sk_buff *skb; struct list_head list; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 03ed492c4e14..debdb6286170 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1185,9 +1185,13 @@ 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, struct xdp_frame *xdp); - * This function is used to submit a XDP packet for transmit on a - * netdevice. + * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp); + * 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. @@ -1375,8 +1379,8 @@ struct net_device_ops { int needed_headroom); int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); - int (*ndo_xdp_xmit)(struct net_device *dev, - struct xdp_frame *xdp); + int (*ndo_xdp_xmit)(struct net_device *dev, int n, + struct xdp_frame **xdp); void (*ndo_xdp_flush)(struct net_device *dev); }; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e71e99eb9a4e..eec302b61cfe 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -868,6 +868,7 @@ extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); +extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); @@ -1289,6 +1290,10 @@ static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } +static inline const struct perf_event *perf_get_event(struct file *file) +{ + return ERR_PTR(-EINVAL); +} static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2bde3eff564c..d34144a3c5b5 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -473,6 +473,9 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info); int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog); int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog); struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name); +int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, + u32 *fd_type, const char **buf, + u64 *probe_offset, u64 *probe_addr); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { @@ -504,6 +507,13 @@ static inline struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name { return NULL; } +static inline int bpf_get_perf_event_info(const struct perf_event *event, + u32 *prog_id, u32 *fd_type, + const char **buf, u64 *probe_offset, + u64 *probe_addr) +{ + return -EOPNOTSUPP; +} #endif enum { @@ -560,10 +570,17 @@ extern void perf_trace_del(struct perf_event *event, int flags); #ifdef CONFIG_KPROBE_EVENTS extern int perf_kprobe_init(struct perf_event *event, bool is_retprobe); extern void perf_kprobe_destroy(struct perf_event *event); +extern int bpf_get_kprobe_info(const struct perf_event *event, + u32 *fd_type, const char **symbol, + u64 *probe_offset, u64 *probe_addr, + bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS extern int perf_uprobe_init(struct perf_event *event, bool is_retprobe); extern void perf_uprobe_destroy(struct perf_event *event); +extern int bpf_get_uprobe_info(const struct perf_event *event, + u32 *fd_type, const char **filename, + u64 *probe_offset, bool perf_type_tracepoint); #endif extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index ff766ab207e0..c07d4dd09361 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -236,6 +236,8 @@ struct ipv6_stub { struct flowi6 *fl6, int oif, const struct sk_buff *skb, int strict); + u32 (*ip6_mtu_from_fib6)(struct fib6_info *f6i, struct in6_addr *daddr, + struct in6_addr *saddr); void (*udpv6_encap_enable)(void); void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index cc70f6da8462..7897efe80727 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -412,6 +412,12 @@ static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i) return f6i->fib6_nh.nh_dev; } +static inline +struct lwtunnel_state *fib6_info_nh_lwt(const struct fib6_info *f6i) +{ + return f6i->fib6_nh.nh_lwtstate; +} + void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 9e4d0f0aeb6d..59656fc580df 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -294,6 +294,9 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) return mtu; } +u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr, + struct in6_addr *saddr); + struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, const void *daddr); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 81d0f2107ff1..69c91d1934c1 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -449,4 +449,6 @@ static inline void fib_proc_exit(struct net *net) } #endif +u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr); + #endif /* _NET_FIB_H */ diff --git a/include/net/page_pool.h b/include/net/page_pool.h index c79087153148..694d055e01ef 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -115,13 +115,14 @@ void page_pool_destroy(struct page_pool *pool); void __page_pool_put_page(struct page_pool *pool, struct page *page, bool allow_direct); -static inline void page_pool_put_page(struct page_pool *pool, struct page *page) +static inline void page_pool_put_page(struct page_pool *pool, + struct page *page, bool allow_direct) { /* When page_pool isn't compiled-in, net/core/xdp.c doesn't * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - __page_pool_put_page(pool, page, false); + __page_pool_put_page(pool, page, allow_direct); #endif } /* Very limited use-cases allow recycle direct */ diff --git a/include/net/seg6.h b/include/net/seg6.h index 099bad59dc90..e029e301faa5 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -49,7 +49,11 @@ struct seg6_pernet_data { static inline struct seg6_pernet_data *seg6_pernet(struct net *net) { +#if IS_ENABLED(CONFIG_IPV6) return net->ipv6.seg6_data; +#else + return NULL; +#endif } extern int seg6_init(void); @@ -63,5 +67,6 @@ extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len); extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto); extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); - +extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, + u32 tbl_id); #endif diff --git a/include/net/seg6_local.h b/include/net/seg6_local.h new file mode 100644 index 000000000000..661fd5b4d3e0 --- /dev/null +++ b/include/net/seg6_local.h @@ -0,0 +1,32 @@ +/* + * SR-IPv6 implementation + * + * Authors: + * David Lebrun <david.lebrun@uclouvain.be> + * eBPF support: Mathieu Xhonneux <m.xhonneux@gmail.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 _NET_SEG6_LOCAL_H +#define _NET_SEG6_LOCAL_H + +#include <linux/percpu.h> +#include <linux/net.h> +#include <linux/ipv6.h> + +extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, + u32 tbl_id); + +struct seg6_bpf_srh_state { + bool valid; + u16 hdrlen; +}; + +DECLARE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states); + +#endif diff --git a/include/net/xdp.h b/include/net/xdp.h index 0b689cf561c7..7ad779237ae8 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -104,6 +104,7 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) } void xdp_return_frame(struct xdp_frame *xdpf); +void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 185f4928fbda..7a647c56ec15 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -1,15 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 - * AF_XDP internal functions +/* SPDX-License-Identifier: GPL-2.0 */ +/* AF_XDP internal functions * Copyright(c) 2018 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #ifndef _LINUX_XDP_SOCK_H diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 8989a92c571a..1ecf4c67fcf7 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -138,11 +138,18 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err, __entry->map_id, __entry->map_index) ); +#ifndef __DEVMAP_OBJ_TYPE +#define __DEVMAP_OBJ_TYPE +struct _bpf_dtab_netdev { + struct net_device *dev; +}; +#endif /* __DEVMAP_OBJ_TYPE */ + #define devmap_ifindex(fwd, map) \ (!fwd ? 0 : \ (!map ? 0 : \ ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ - ((struct net_device *)fwd)->ifindex : 0))) + ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0))) #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \ @@ -222,6 +229,47 @@ TRACE_EVENT(xdp_cpumap_enqueue, __entry->to_cpu) ); +TRACE_EVENT(xdp_devmap_xmit, + + TP_PROTO(const struct bpf_map *map, u32 map_index, + int sent, int drops, + const struct net_device *from_dev, + const struct net_device *to_dev, int err), + + TP_ARGS(map, map_index, sent, drops, from_dev, to_dev, err), + + TP_STRUCT__entry( + __field(int, map_id) + __field(u32, act) + __field(u32, map_index) + __field(int, drops) + __field(int, sent) + __field(int, from_ifindex) + __field(int, to_ifindex) + __field(int, err) + ), + + TP_fast_assign( + __entry->map_id = map->id; + __entry->act = XDP_REDIRECT; + __entry->map_index = map_index; + __entry->drops = drops; + __entry->sent = sent; + __entry->from_ifindex = from_dev->ifindex; + __entry->to_ifindex = to_dev->ifindex; + __entry->err = err; + ), + + TP_printk("ndo_xdp_xmit" + " map_id=%d map_index=%d action=%s" + " sent=%d drops=%d" + " from_ifindex=%d to_ifindex=%d err=%d", + __entry->map_id, __entry->map_index, + __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), + __entry->sent, __entry->drops, + __entry->from_ifindex, __entry->to_ifindex, __entry->err) +); + #endif /* _TRACE_XDP_H */ #include <trace/define_trace.h> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d94d333a8225..9b8c6e310e9a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -97,6 +97,7 @@ enum bpf_cmd { BPF_RAW_TRACEPOINT_OPEN, BPF_BTF_LOAD, BPF_BTF_GET_FD_BY_ID, + BPF_TASK_FD_QUERY, }; enum bpf_map_type { @@ -141,6 +142,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_MSG, BPF_PROG_TYPE_RAW_TRACEPOINT, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_PROG_TYPE_LWT_SEG6LOCAL, }; enum bpf_attach_type { @@ -284,8 +286,8 @@ union bpf_attr { char map_name[BPF_OBJ_NAME_LEN]; __u32 map_ifindex; /* ifindex of netdev to create on */ __u32 btf_fd; /* fd pointing to a BTF type data */ - __u32 btf_key_id; /* BTF type_id of the key */ - __u32 btf_value_id; /* BTF type_id of the value */ + __u32 btf_key_type_id; /* BTF type_id of the key */ + __u32 btf_value_type_id; /* BTF type_id of the value */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -379,6 +381,22 @@ union bpf_attr { __u32 btf_log_size; __u32 btf_log_level; }; + + struct { + __u32 pid; /* input: pid */ + __u32 fd; /* input: fd */ + __u32 flags; /* input: flags */ + __u32 buf_len; /* input/output: buf len */ + __aligned_u64 buf; /* input/output: + * tp_name for tracepoint + * symbol for kprobe + * filename for uprobe + */ + __u32 prog_id; /* output: prod_id */ + __u32 fd_type; /* output: BPF_FD_TYPE_* */ + __u64 probe_offset; /* output: probe_offset */ + __u64 probe_addr; /* output: probe_addr */ + } task_fd_query; } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -1902,6 +1920,90 @@ union bpf_attr { * egress otherwise). This is the only flag supported for now. * Return * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) + * Description + * Encapsulate the packet associated to *skb* within a Layer 3 + * protocol header. This header is provided in the buffer at + * address *hdr*, with *len* its size in bytes. *type* indicates + * the protocol of the header and can be one of: + * + * **BPF_LWT_ENCAP_SEG6** + * IPv6 encapsulation with Segment Routing Header + * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH, + * the IPv6 header is computed by the kernel. + * **BPF_LWT_ENCAP_SEG6_INLINE** + * Only works if *skb* contains an IPv6 packet. Insert a + * Segment Routing Header (**struct ipv6_sr_hdr**) inside + * the IPv6 header. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. Only the flags, tag and TLVs + * inside the outermost IPv6 Segment Routing Header can be + * modified through this helper. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) + * Description + * Adjust the size allocated to TLVs in the outermost IPv6 + * Segment Routing Header contained in the packet associated to + * *skb*, at position *offset* by *delta* bytes. Only offsets + * after the segments are accepted. *delta* can be as well + * positive (growing) as negative (shrinking). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) + * Description + * Apply an IPv6 Segment Routing action of type *action* to the + * packet associated to *skb*. Each action takes a parameter + * contained at address *param*, and of length *param_len* bytes. + * *action* can be one of: + * + * **SEG6_LOCAL_ACTION_END_X** + * End.X action: Endpoint with Layer-3 cross-connect. + * Type of *param*: **struct in6_addr**. + * **SEG6_LOCAL_ACTION_END_T** + * End.T action: Endpoint with specific IPv6 table lookup. + * Type of *param*: **int**. + * **SEG6_LOCAL_ACTION_END_B6** + * End.B6 action: Endpoint bound to an SRv6 policy. + * Type of param: **struct ipv6_sr_hdr**. + * **SEG6_LOCAL_ACTION_END_B6_ENCAP** + * End.B6.Encap action: Endpoint bound to an SRv6 + * encapsulation policy. + * Type of param: **struct ipv6_sr_hdr**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -1976,7 +2078,11 @@ union bpf_attr { FN(fib_lookup), \ FN(sock_hash_update), \ FN(msg_redirect_hash), \ - FN(sk_redirect_hash), + FN(sk_redirect_hash), \ + FN(lwt_push_encap), \ + FN(lwt_seg6_store_bytes), \ + FN(lwt_seg6_adjust_srh), \ + FN(lwt_seg6_action), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2043,6 +2149,12 @@ enum bpf_hdr_start_off { BPF_HDR_START_NET, }; +/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */ +enum bpf_lwt_encap_mode { + BPF_LWT_ENCAP_SEG6, + BPF_LWT_ENCAP_SEG6_INLINE +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -2176,6 +2288,14 @@ enum sk_action { struct sk_msg_md { void *data; void *data_end; + + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ }; #define BPF_TAG_SIZE 8 @@ -2197,6 +2317,10 @@ struct bpf_prog_info { __u32 gpl_compatible:1; __u64 netns_dev; __u64 netns_ino; + __u32 nr_jited_ksyms; + __u32 nr_jited_func_lens; + __aligned_u64 jited_ksyms; + __aligned_u64 jited_func_lens; } __attribute__((aligned(8))); struct bpf_map_info { @@ -2211,8 +2335,8 @@ struct bpf_map_info { __u64 netns_dev; __u64 netns_ino; __u32 btf_id; - __u32 btf_key_id; - __u32 btf_value_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; } __attribute__((aligned(8))); struct bpf_btf_info { @@ -2450,4 +2574,13 @@ struct bpf_fib_lookup { __u8 dmac[6]; /* ETH_ALEN */ }; +enum bpf_task_fd_type { + BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_UPROBE, /* filename + offset */ + BPF_FD_TYPE_URETPROBE, /* filename + offset */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index bcb56ee47014..0b5ddbe135a4 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -12,42 +12,29 @@ struct btf_header { __u16 magic; __u8 version; __u8 flags; - - __u32 parent_label; - __u32 parent_name; + __u32 hdr_len; /* All offsets are in bytes relative to the end of this header */ - __u32 label_off; /* offset of label section */ - __u32 object_off; /* offset of data object section*/ - __u32 func_off; /* offset of function section */ __u32 type_off; /* offset of type section */ + __u32 type_len; /* length of type section */ __u32 str_off; /* offset of string section */ __u32 str_len; /* length of string section */ }; /* Max # of type identifier */ -#define BTF_MAX_TYPE 0x7fffffff +#define BTF_MAX_TYPE 0x0000ffff /* Max offset into the string section */ -#define BTF_MAX_NAME_OFFSET 0x7fffffff +#define BTF_MAX_NAME_OFFSET 0x0000ffff /* Max # of struct/union/enum members or func args */ #define BTF_MAX_VLEN 0xffff -/* The type id is referring to a parent BTF */ -#define BTF_TYPE_PARENT(id) (((id) >> 31) & 0x1) -#define BTF_TYPE_ID(id) ((id) & BTF_MAX_TYPE) - -/* String is in the ELF string section */ -#define BTF_STR_TBL_ELF_ID(ref) (((ref) >> 31) & 0x1) -#define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET) - struct btf_type { __u32 name_off; /* "info" bits arrangement * bits 0-15: vlen (e.g. # of struct's members) * bits 16-23: unused - * bits 24-28: kind (e.g. int, ptr, array...etc) - * bits 29-30: unused - * bits 31: root + * bits 24-27: kind (e.g. int, ptr, array...etc) + * bits 28-31: unused */ __u32 info; /* "size" is used by INT, ENUM, STRUCT and UNION. @@ -62,8 +49,7 @@ struct btf_type { }; }; -#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f) -#define BTF_INFO_ISROOT(info) (!!(((info) >> 24) & 0x80)) +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f) #define BTF_INFO_VLEN(info) ((info) & 0xffff) #define BTF_KIND_UNKN 0 /* Unknown */ @@ -88,15 +74,14 @@ struct btf_type { /* BTF_KIND_INT is followed by a u32 and the following * is the 32 bits arrangement: */ -#define BTF_INT_ENCODING(VAL) (((VAL) & 0xff000000) >> 24) +#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) #define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) #define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) /* Attributes stored in the BTF_INT_ENCODING */ -#define BTF_INT_SIGNED 0x1 -#define BTF_INT_CHAR 0x2 -#define BTF_INT_BOOL 0x4 -#define BTF_INT_VARARGS 0x8 +#define BTF_INT_SIGNED (1 << 0) +#define BTF_INT_CHAR (1 << 1) +#define BTF_INT_BOOL (1 << 2) /* BTF_KIND_ENUM is followed by multiple "struct btf_enum". * The exact number of btf_enum is stored in the vlen (of the diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index 77b88c4efe98..4737cfe222f5 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -1,17 +1,8 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note - * +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* * if_xdp: XDP socket user-space interface * Copyright(c) 2018 Intel Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * * Author(s): Björn Töpel <bjorn.topel@intel.com> * Magnus Karlsson <magnus.karlsson@intel.com> */ @@ -26,19 +17,33 @@ struct sockaddr_xdp { __u16 sxdp_family; + __u16 sxdp_flags; __u32 sxdp_ifindex; __u32 sxdp_queue_id; __u32 sxdp_shared_umem_fd; - __u16 sxdp_flags; +}; + +struct xdp_ring_offset { + __u64 producer; + __u64 consumer; + __u64 desc; +}; + +struct xdp_mmap_offsets { + struct xdp_ring_offset rx; + struct xdp_ring_offset tx; + struct xdp_ring_offset fr; /* Fill */ + struct xdp_ring_offset cr; /* Completion */ }; /* XDP socket options */ -#define XDP_RX_RING 1 -#define XDP_TX_RING 2 -#define XDP_UMEM_REG 3 -#define XDP_UMEM_FILL_RING 4 -#define XDP_UMEM_COMPLETION_RING 5 -#define XDP_STATISTICS 6 +#define XDP_MMAP_OFFSETS 1 +#define XDP_RX_RING 2 +#define XDP_TX_RING 3 +#define XDP_UMEM_REG 4 +#define XDP_UMEM_FILL_RING 5 +#define XDP_UMEM_COMPLETION_RING 6 +#define XDP_STATISTICS 7 struct xdp_umem_reg { __u64 addr; /* Start of packet data area */ @@ -59,6 +64,7 @@ struct xdp_statistics { #define XDP_UMEM_PGOFF_FILL_RING 0x100000000 #define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000 +/* Rx/Tx descriptor */ struct xdp_desc { __u32 idx; __u32 len; @@ -67,21 +73,6 @@ struct xdp_desc { __u8 padding[5]; }; -struct xdp_ring { - __u32 producer __attribute__((aligned(64))); - __u32 consumer __attribute__((aligned(64))); -}; - -/* Used for the RX and TX queues for packets */ -struct xdp_rxtx_ring { - struct xdp_ |