diff options
author | David S. Miller <davem@davemloft.net> | 2018-05-07 23:35:08 -0400 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2018-05-07 23:35:08 -0400 |
commit | 01adc4851a8090b46c7a5ed9cfc4b97e65abfbf4 (patch) | |
tree | 2ae02593d7139962648dff203f3f9701e34ccbc3 /include | |
parent | 18b338f5f9539512e76fd9ebd4c6ca1a0e159e2b (diff) | |
parent | e94fa1d93117e7f1eb783dc9cae6c70650944449 (diff) | |
download | linux-01adc4851a8090b46c7a5ed9cfc4b97e65abfbf4.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Minor conflict, a CHECK was placed into an if() statement
in net-next, whilst a newline was added to that CHECK
call in 'net'. Thanks to Daniel for the merge resolution.
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/bpf.h | 35 | ||||
-rw-r--r-- | include/linux/bpf_trace.h | 1 | ||||
-rw-r--r-- | include/linux/bpf_types.h | 3 | ||||
-rw-r--r-- | include/linux/bpf_verifier.h | 9 | ||||
-rw-r--r-- | include/linux/filter.h | 9 | ||||
-rw-r--r-- | include/linux/netdevice.h | 1 | ||||
-rw-r--r-- | include/linux/socket.h | 5 | ||||
-rw-r--r-- | include/linux/tnum.h | 4 | ||||
-rw-r--r-- | include/net/xdp.h | 1 | ||||
-rw-r--r-- | include/net/xdp_sock.h | 66 | ||||
-rw-r--r-- | include/trace/events/bpf.h | 355 | ||||
-rw-r--r-- | include/uapi/linux/bpf.h | 94 | ||||
-rw-r--r-- | include/uapi/linux/if_xdp.h | 87 |
13 files changed, 292 insertions, 378 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 38ebbc61ed99..321969da67b7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -110,6 +110,11 @@ static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) return container_of(map, struct bpf_offloaded_map, map); } +static inline bool bpf_map_offload_neutral(const struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; +} + static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { return map->ops->map_seq_show_elem && map->ops->map_check_btf; @@ -235,6 +240,8 @@ struct bpf_verifier_ops { struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); + int (*gen_ld_abs)(const struct bpf_insn *orig, + struct bpf_insn *insn_buf); u32 (*convert_ctx_access)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, @@ -676,6 +683,31 @@ static inline int sock_map_prog(struct bpf_map *map, } #endif +#if defined(CONFIG_XDP_SOCKETS) +struct xdp_sock; +struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key); +int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs); +void __xsk_map_flush(struct bpf_map *map); +#else +struct xdp_sock; +static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} + +static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs) +{ + return -EOPNOTSUPP; +} + +static inline void __xsk_map_flush(struct bpf_map *map) +{ +} +#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; @@ -689,9 +721,8 @@ extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; 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_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; /* Shared helpers among cBPF and eBPF. */ diff --git a/include/linux/bpf_trace.h b/include/linux/bpf_trace.h index e6fe98ae3794..ddf896abcfb6 100644 --- a/include/linux/bpf_trace.h +++ b/include/linux/bpf_trace.h @@ -2,7 +2,6 @@ #ifndef __LINUX_BPF_TRACE_H__ #define __LINUX_BPF_TRACE_H__ -#include <trace/events/bpf.h> #include <trace/events/xdp.h> #endif /* __LINUX_BPF_TRACE_H__ */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 2b28fcf6f6ae..d7df1b323082 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -49,4 +49,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) +#if defined(CONFIG_XDP_SOCKETS) +BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) +#endif #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7e61c395fddf..8f70dc181e23 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -173,6 +173,11 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) #define BPF_MAX_SUBPROGS 256 +struct bpf_subprog_info { + u32 start; /* insn idx of function entry point */ + u16 stack_depth; /* max. stack depth used by this function */ +}; + /* single container for all structs * one verifier_env per bpf_check() call */ @@ -191,9 +196,7 @@ struct bpf_verifier_env { bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ struct bpf_verifier_log log; - u32 subprog_starts[BPF_MAX_SUBPROGS]; - /* computes the stack depth of each bpf function */ - u16 subprog_stack_depth[BPF_MAX_SUBPROGS + 1]; + struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; u32 subprog_cnt; }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 4da8b2308174..da7e16523128 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -47,7 +47,9 @@ struct xdp_buff; /* Additional register mappings for converted user programs. */ #define BPF_REG_A BPF_REG_0 #define BPF_REG_X BPF_REG_7 -#define BPF_REG_TMP BPF_REG_8 +#define BPF_REG_TMP BPF_REG_2 /* scratch reg */ +#define BPF_REG_D BPF_REG_8 /* data, callee-saved */ +#define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */ /* Kernel hidden auxiliary/helper register for hardening step. * Only used by eBPF JITs. It's nothing more than a temporary @@ -468,7 +470,8 @@ struct bpf_prog { dst_needed:1, /* Do we need dst entry? */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ - kprobe_override:1; /* Do we override a kprobe? */ + kprobe_override:1, /* Do we override a kprobe? */ + has_callchain_buf:1; /* callchain buffer allocated? */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ @@ -759,7 +762,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, * 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); + struct xdp_buff *xdp, struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 46dcb5f7522f..03ed492c4e14 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2510,6 +2510,7 @@ 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); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); +int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); diff --git a/include/linux/socket.h b/include/linux/socket.h index ea50f4a65816..7ed4713d5337 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -207,8 +207,9 @@ struct ucred { * PF_SMC protocol family that * reuses AF_INET address family */ +#define AF_XDP 44 /* XDP sockets */ -#define AF_MAX 44 /* For now.. */ +#define AF_MAX 45 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -257,6 +258,7 @@ struct ucred { #define PF_KCM AF_KCM #define PF_QIPCRTR AF_QIPCRTR #define PF_SMC AF_SMC +#define PF_XDP AF_XDP #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -338,6 +340,7 @@ struct ucred { #define SOL_NFC 280 #define SOL_KCM 281 #define SOL_TLS 282 +#define SOL_XDP 283 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/tnum.h b/include/linux/tnum.h index 0d2d3da46139..c7dc2b5902c0 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -23,8 +23,10 @@ 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) */ +/* Shift (rsh) a tnum right (by a fixed shift) */ struct tnum tnum_rshift(struct tnum a, u8 shift); +/* Shift (arsh) a tnum right (by a fixed min_shift) */ +struct tnum tnum_arshift(struct tnum a, u8 min_shift); /* Add two tnums, return @a + @b */ struct tnum tnum_add(struct tnum a, struct tnum b); /* Subtract two tnums, return @a - @b */ diff --git a/include/net/xdp.h b/include/net/xdp.h index 137ad5f9f40f..0b689cf561c7 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_buff(struct xdp_buff *xdp); int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index); diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h new file mode 100644 index 000000000000..185f4928fbda --- /dev/null +++ b/include/net/xdp_sock.h @@ -0,0 +1,66 @@ +/* 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 +#define _LINUX_XDP_SOCK_H + +#include <linux/mutex.h> +#include <net/sock.h> + +struct net_device; +struct xsk_queue; +struct xdp_umem; + +struct xdp_sock { + /* struct sock must be the first member of struct xdp_sock */ + struct sock sk; + struct xsk_queue *rx; + struct net_device *dev; + struct xdp_umem *umem; + struct list_head flush_node; + u16 queue_id; + struct xsk_queue *tx ____cacheline_aligned_in_smp; + /* Protects multiple processes in the control path */ + struct mutex mutex; + u64 rx_dropped; +}; + +struct xdp_buff; +#ifdef CONFIG_XDP_SOCKETS +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); +#else +static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +{ + return -ENOTSUPP; +} + +static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +{ + return -ENOTSUPP; +} + +static inline void xsk_flush(struct xdp_sock *xs) +{ +} + +static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) +{ + return false; +} +#endif /* CONFIG_XDP_SOCKETS */ + +#endif /* _LINUX_XDP_SOCK_H */ diff --git a/include/trace/events/bpf.h b/include/trace/events/bpf.h deleted file mode 100644 index 150185647e6b..000000000000 --- a/include/trace/events/bpf.h +++ /dev/null @@ -1,355 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM bpf - -#if !defined(_TRACE_BPF_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_BPF_H - -/* These are only used within the BPF_SYSCALL code */ -#ifdef CONFIG_BPF_SYSCALL - -#include <linux/filter.h> -#include <linux/bpf.h> -#include <linux/fs.h> -#include <linux/tracepoint.h> - -#define __PROG_TYPE_MAP(FN) \ - FN(SOCKET_FILTER) \ - FN(KPROBE) \ - FN(SCHED_CLS) \ - FN(SCHED_ACT) \ - FN(TRACEPOINT) \ - FN(XDP) \ - FN(PERF_EVENT) \ - FN(CGROUP_SKB) \ - FN(CGROUP_SOCK) \ - FN(LWT_IN) \ - FN(LWT_OUT) \ - FN(LWT_XMIT) - -#define __MAP_TYPE_MAP(FN) \ - FN(HASH) \ - FN(ARRAY) \ - FN(PROG_ARRAY) \ - FN(PERF_EVENT_ARRAY) \ - FN(PERCPU_HASH) \ - FN(PERCPU_ARRAY) \ - FN(STACK_TRACE) \ - FN(CGROUP_ARRAY) \ - FN(LRU_HASH) \ - FN(LRU_PERCPU_HASH) \ - FN(LPM_TRIE) - -#define __PROG_TYPE_TP_FN(x) \ - TRACE_DEFINE_ENUM(BPF_PROG_TYPE_##x); -#define __PROG_TYPE_SYM_FN(x) \ - { BPF_PROG_TYPE_##x, #x }, -#define __PROG_TYPE_SYM_TAB \ - __PROG_TYPE_MAP(__PROG_TYPE_SYM_FN) { -1, 0 } -__PROG_TYPE_MAP(__PROG_TYPE_TP_FN) - -#define __MAP_TYPE_TP_FN(x) \ - TRACE_DEFINE_ENUM(BPF_MAP_TYPE_##x); -#define __MAP_TYPE_SYM_FN(x) \ - { BPF_MAP_TYPE_##x, #x }, -#define __MAP_TYPE_SYM_TAB \ - __MAP_TYPE_MAP(__MAP_TYPE_SYM_FN) { -1, 0 } -__MAP_TYPE_MAP(__MAP_TYPE_TP_FN) - -DECLARE_EVENT_CLASS(bpf_prog_event, - - TP_PROTO(const struct bpf_prog *prg), - - TP_ARGS(prg), - - TP_STRUCT__entry( - __array(u8, prog_tag, 8) - __field(u32, type) - ), - - TP_fast_assign( - BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag)); - memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag)); - __entry->type = prg->type; - ), - - TP_printk("prog=%s type=%s", - __print_hex_str(__entry->prog_tag, 8), - __print_symbolic(__entry->type, __PROG_TYPE_SYM_TAB)) -); - -DEFINE_EVENT(bpf_prog_event, bpf_prog_get_type, - - TP_PROTO(const struct bpf_prog *prg), - - TP_ARGS(prg) -); - -DEFINE_EVENT(bpf_prog_event, bpf_prog_put_rcu, - - TP_PROTO(const struct bpf_prog *prg), - - TP_ARGS(prg) -); - -TRACE_EVENT(bpf_prog_load, - - TP_PROTO(const struct bpf_prog *prg, int ufd), - - TP_ARGS(prg, ufd), - - TP_STRUCT__entry( - __array(u8, prog_tag, 8) - __field(u32, type) - __field(int, ufd) - ), - - TP_fast_assign( - BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag)); - memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag)); - __entry->type = prg->type; - __entry->ufd = ufd; - ), - - TP_printk("prog=%s type=%s ufd=%d", - __print_hex_str(__entry->prog_tag, 8), - __print_symbolic(__entry->type, __PROG_TYPE_SYM_TAB), - __entry->ufd) -); - -TRACE_EVENT(bpf_map_create, - - TP_PROTO(const struct bpf_map *map, int ufd), - - TP_ARGS(map, ufd), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, size_key) - __field(u32, size_value) - __field(u32, max_entries) - __field(u32, flags) - __field(int, ufd) - ), - - TP_fast_assign( - __entry->type = map->map_type; - __entry->size_key = map->key_size; - __entry->size_value = map->value_size; - __entry->max_entries = map->max_entries; - __entry->flags = map->map_flags; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=%u val=%u max=%u flags=%x", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, __entry->size_key, __entry->size_value, - __entry->max_entries, __entry->flags) -); - -DECLARE_EVENT_CLASS(bpf_obj_prog, - - TP_PROTO(const struct bpf_prog *prg, int ufd, - const struct filename *pname), - - TP_ARGS(prg, ufd, pname), - - TP_STRUCT__entry( - __array(u8, prog_tag, 8) - __field(int, ufd) - __string(path, pname->name) - ), - - TP_fast_assign( - BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag)); - memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag)); - __assign_str(path, pname->name); - __entry->ufd = ufd; - ), - - TP_printk("prog=%s path=%s ufd=%d", - __print_hex_str(__entry->prog_tag, 8), - __get_str(path), __entry->ufd) -); - -DEFINE_EVENT(bpf_obj_prog, bpf_obj_pin_prog, - - TP_PROTO(const struct bpf_prog *prg, int ufd, - const struct filename *pname), - - TP_ARGS(prg, ufd, pname) -); - -DEFINE_EVENT(bpf_obj_prog, bpf_obj_get_prog, - - TP_PROTO(const struct bpf_prog *prg, int ufd, - const struct filename *pname), - - TP_ARGS(prg, ufd, pname) -); - -DECLARE_EVENT_CLASS(bpf_obj_map, - - TP_PROTO(const struct bpf_map *map, int ufd, - const struct filename *pname), - - TP_ARGS(map, ufd, pname), - - TP_STRUCT__entry( - __field(u32, type) - __field(int, ufd) - __string(path, pname->name) - ), - - TP_fast_assign( - __assign_str(path, pname->name); - __entry->type = map->map_type; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d path=%s", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, __get_str(path)) -); - -DEFINE_EVENT(bpf_obj_map, bpf_obj_pin_map, - - TP_PROTO(const struct bpf_map *map, int ufd, - const struct filename *pname), - - TP_ARGS(map, ufd, pname) -); - -DEFINE_EVENT(bpf_obj_map, bpf_obj_get_map, - - TP_PROTO(const struct bpf_map *map, int ufd, - const struct filename *pname), - - TP_ARGS(map, ufd, pname) -); - -DECLARE_EVENT_CLASS(bpf_map_keyval, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *val), - - TP_ARGS(map, ufd, key, val), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, key_len) - __dynamic_array(u8, key, map->key_size) - __field(bool, key_trunc) - __field(u32, val_len) - __dynamic_array(u8, val, map->value_size) - __field(bool, val_trunc) - __field(int, ufd) - ), - - TP_fast_assign( - memcpy(__get_dynamic_array(key), key, map->key_size); - memcpy(__get_dynamic_array(val), val, map->value_size); - __entry->type = map->map_type; - __entry->key_len = min(map->key_size, 16U); - __entry->key_trunc = map->key_size != __entry->key_len; - __entry->val_len = min(map->value_size, 16U); - __entry->val_trunc = map->value_size != __entry->val_len; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=[%s%s] val=[%s%s]", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, - __print_hex(__get_dynamic_array(key), __entry->key_len), - __entry->key_trunc ? " ..." : "", - __print_hex(__get_dynamic_array(val), __entry->val_len), - __entry->val_trunc ? " ..." : "") -); - -DEFINE_EVENT(bpf_map_keyval, bpf_map_lookup_elem, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *val), - - TP_ARGS(map, ufd, key, val) -); - -DEFINE_EVENT(bpf_map_keyval, bpf_map_update_elem, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *val), - - TP_ARGS(map, ufd, key, val) -); - -TRACE_EVENT(bpf_map_delete_elem, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key), - - TP_ARGS(map, ufd, key), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, key_len) - __dynamic_array(u8, key, map->key_size) - __field(bool, key_trunc) - __field(int, ufd) - ), - - TP_fast_assign( - memcpy(__get_dynamic_array(key), key, map->key_size); - __entry->type = map->map_type; - __entry->key_len = min(map->key_size, 16U); - __entry->key_trunc = map->key_size != __entry->key_len; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=[%s%s]", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, - __print_hex(__get_dynamic_array(key), __entry->key_len), - __entry->key_trunc ? " ..." : "") -); - -TRACE_EVENT(bpf_map_next_key, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *key_next), - - TP_ARGS(map, ufd, key, key_next), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, key_len) - __dynamic_array(u8, key, map->key_size) - __dynamic_array(u8, nxt, map->key_size) - __field(bool, key_trunc) - __field(bool, key_null) - __field(int, ufd) - ), - - TP_fast_assign( - if (key) - memcpy(__get_dynamic_array(key), key, map->key_size); - __entry->key_null = !key; - memcpy(__get_dynamic_array(nxt), key_next, map->key_size); - __entry->type = map->map_type; - __entry->key_len = min(map->key_size, 16U); - __entry->key_trunc = map->key_size != __entry->key_len; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=[%s%s] next=[%s%s]", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, - __entry->key_null ? "NULL" : __print_hex(__get_dynamic_array(key), - __entry->key_len), - __entry->key_trunc && !__entry->key_null ? " ..." : "", - __print_hex(__get_dynamic_array(nxt), __entry->key_len), - __entry->key_trunc ? " ..." : "") -); -#endif /* CONFIG_BPF_SYSCALL */ -#endif /* _TRACE_BPF_H */ - -#include <trace/define_trace.h> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index da77a9388947..93d5a4eeec2a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -116,6 +116,7 @@ enum bpf_map_type { BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, BPF_MAP_TYPE_CPUMAP, + BPF_MAP_TYPE_XSKMAP, }; enum bpf_prog_type { @@ -828,12 +829,12 @@ union bpf_attr { * * Also, be aware that the newer helper * **bpf_perf_event_read_value**\ () is recommended over - * **bpf_perf_event_read*\ () in general. The latter has some ABI + * **bpf_perf_event_read**\ () in general. The latter has some ABI * quirks where error and counter value are used as a return code * (which is wrong to do since ranges may overlap). This issue is - * fixed with bpf_perf_event_read_value(), which at the same time - * provides more features over the **bpf_perf_event_read**\ () - * interface. Please refer to the description of + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of * **bpf_perf_event_read_value**\ () for details. * Return * The value of the perf event counter read from the map, or a @@ -1361,7 +1362,7 @@ union bpf_attr { * Return * 0 * - * int bpf_setsockopt(struct bpf_sock_ops_kern *bpf_socket, int level, int optname, char *optval, int optlen) + * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) * Description * Emulate a call to **setsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1435,7 +1436,7 @@ union bpf_attr { * Return * **SK_PASS** on success, or **SK_DROP** on error. * - * int bpf_sock_map_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) + * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a *map* referencing sockets. The * *skops* is used as a new value for the entry associated to @@ -1533,7 +1534,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_perf_prog_read_value(struct bpf_perf_event_data_kern *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description * For en eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in @@ -1544,7 +1545,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_getsockopt(struct bpf_sock_ops_kern *bpf_socket, int level, int optname, char *optval, int optlen) + * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) * Description * Emulate a call to **getsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1588,7 +1589,7 @@ union bpf_attr { * Return * 0 * - * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops_kern *bpf_sock, int argval) + * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) * Description * Attempt to set the value of the **bpf_sock_ops_cb_flags** field * for the full TCP socket associated to *bpf_sock_ops* to @@ -1721,7 +1722,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_bind(struct bpf_sock_addr_kern *ctx, struct sockaddr *addr, int addr_len) + * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) * Description * Bind the socket associated to *ctx* to the address pointed by * *addr*, of length *addr_len*. This allows for making outgoing @@ -1767,6 +1768,64 @@ union bpf_attr { * **CONFIG_XFRM** configuration option. * Return * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # 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. + * + * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) + * Description + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * 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. + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -1835,7 +1894,9 @@ union bpf_attr { FN(msg_pull_data), \ FN(bind), \ FN(xdp_adjust_tail), \ - FN(skb_get_xfrm_state), + FN(skb_get_xfrm_state), \ + FN(get_stack), \ + FN(skb_load_bytes_relative), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -1869,11 +1930,14 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) -/* BPF_FUNC_get_stackid flags. */ +/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ #define BPF_F_SKIP_FIELD_MASK 0xffULL #define BPF_F_USER_STACK (1ULL << 8) +/* flags used by BPF_FUNC_get_stackid only. */ #define BPF_F_FAST_STACK_CMP (1ULL << 9) #define BPF_F_REUSE_STACKID (1ULL << 10) +/* flags used by BPF_FUNC_get_stack only. */ +#define BPF_F_USER_BUILD_ID (1ULL << 11) /* BPF_FUNC_skb_set_tunnel_key flags. */ #define BPF_F_ZERO_CSUM_TX (1ULL << 1) @@ -1893,6 +1957,12 @@ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, }; +/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ +enum bpf_hdr_start_off { + BPF_HDR_START_MAC, + BPF_HDR_START_NET, +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h new file mode 100644 index 000000000000..77b88c4efe98 --- /dev/null +++ b/include/uapi/linux/if_xdp.h @@ -0,0 +1,87 @@ +/* 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> + */ + +#ifndef _LINUX_IF_XDP_H +#define _LINUX_IF_XDP_H + +#include <linux/types.h> + +/* Options for the sxdp_flags field */ +#define XDP_SHARED_UMEM 1 + +struct sockaddr_xdp { + __u16 sxdp_family; + __u32 sxdp_ifindex; + __u32 sxdp_queue_id; + __u32 sxdp_shared_umem_fd; + __u16 sxdp_flags; +}; + +/* 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 + +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 */ +}; + +struct xdp_statistics { + __u64 rx_dropped; /* Dropped for reasons other than invalid desc */ + __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ +}; + +/* Pgoff for mmaping the rings */ +#define XDP_PGOFF_RX_RING 0 +#define XDP_PGOFF_TX_RING 0x80000000 +#define XDP_UMEM_PGOFF_FILL_RING 0x100000000 +#define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000 + +struct xdp_desc { + __u32 idx; + __u32 len; + __u16 offset; + __u8 flags; + __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_ring ptrs; + struct xdp_desc desc[0] __attribute__((aligned(64))); +}; + +/* Used for the fill and completion queues for buffers */ +struct xdp_umem_ring { + struct xdp_ring ptrs; + __u32 desc[0] __attribute__((aligned(64))); +}; + +#endif /* _LINUX_IF_XDP_H */ |