linux_dsm_epyc7002/tools/bpf/bpftool/main.h
Martin KaFai Lau 65c9362859 bpftool: Add struct_ops support
This patch adds struct_ops support to the bpftool.

To recap a bit on the recent bpf_struct_ops feature on the kernel side:
It currently supports "struct tcp_congestion_ops" to be implemented
in bpf.  At a high level, bpf_struct_ops is struct_ops map populated
with a number of bpf progs.  bpf_struct_ops currently supports the
"struct tcp_congestion_ops".  However, the bpf_struct_ops design is
generic enough that other kernel struct ops can be supported in
the future.

Although struct_ops is map+progs at a high lever, there are differences
in details.  For example,
1) After registering a struct_ops, the struct_ops is held by the kernel
   subsystem (e.g. tcp-cc).  Thus, there is no need to pin a
   struct_ops map or its progs in order to keep them around.
2) To iterate all struct_ops in a system, it iterates all maps
   in type BPF_MAP_TYPE_STRUCT_OPS.  BPF_MAP_TYPE_STRUCT_OPS is
   the current usual filter.  In the future, it may need to
   filter by other struct_ops specific properties.  e.g. filter by
   tcp_congestion_ops or other kernel subsystem ops in the future.
3) struct_ops requires the running kernel having BTF info.  That allows
   more flexibility in handling other kernel structs.  e.g. it can
   always dump the latest bpf_map_info.
4) Also, "struct_ops" command is not intended to repeat all features
   already provided by "map" or "prog".  For example, if there really
   is a need to pin the struct_ops map, the user can use the "map" cmd
   to do that.

While the first attempt was to reuse parts from map/prog.c,  it ended up
not a lot to share.  The only obvious item is the map_parse_fds() but
that still requires modifications to accommodate struct_ops map specific
filtering (for the immediate and the future needs).  Together with the
earlier mentioned differences, it is better to part away from map/prog.c.

The initial set of subcmds are, register, unregister, show, and dump.

For register, it registers all struct_ops maps that can be found in an
obj file.  Option can be added in the future to specify a particular
struct_ops map.  Also, the common bpf_tcp_cc is stateless (e.g.
bpf_cubic.c and bpf_dctcp.c).  The "reuse map" feature is not
implemented in this patch and it can be considered later also.

For other subcmds, please see the man doc for details.

A sample output of dump:
[root@arch-fb-vm1 bpf]# bpftool struct_ops dump name cubic
[{
        "bpf_map_info": {
            "type": 26,
            "id": 64,
            "key_size": 4,
            "value_size": 256,
            "max_entries": 1,
            "map_flags": 0,
            "name": "cubic",
            "ifindex": 0,
            "btf_vmlinux_value_type_id": 18452,
            "netns_dev": 0,
            "netns_ino": 0,
            "btf_id": 52,
            "btf_key_type_id": 0,
            "btf_value_type_id": 0
        }
    },{
        "bpf_struct_ops_tcp_congestion_ops": {
            "refcnt": {
                "refs": {
                    "counter": 1
                }
            },
            "state": "BPF_STRUCT_OPS_STATE_INUSE",
            "data": {
                "list": {
                    "next": 0,
                    "prev": 0
                },
                "key": 0,
                "flags": 0,
                "init": "void (struct sock *) bictcp_init/prog_id:138",
                "release": "void (struct sock *) 0",
                "ssthresh": "u32 (struct sock *) bictcp_recalc_ssthresh/prog_id:141",
                "cong_avoid": "void (struct sock *, u32, u32) bictcp_cong_avoid/prog_id:140",
                "set_state": "void (struct sock *, u8) bictcp_state/prog_id:142",
                "cwnd_event": "void (struct sock *, enum tcp_ca_event) bictcp_cwnd_event/prog_id:139",
                "in_ack_event": "void (struct sock *, u32) 0",
                "undo_cwnd": "u32 (struct sock *) tcp_reno_undo_cwnd/prog_id:144",
                "pkts_acked": "void (struct sock *, const struct ack_sample *) bictcp_acked/prog_id:143",
                "min_tso_segs": "u32 (struct sock *) 0",
                "sndbuf_expand": "u32 (struct sock *) 0",
                "cong_control": "void (struct sock *, const struct rate_sample *) 0",
                "get_info": "size_t (struct sock *, u32, int *, union tcp_cc_info *) 0",
                "name": "bpf_cubic",
                "owner": 0
            }
        }
    }
]

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20200318171656.129650-1-kafai@fb.com
2020-03-20 15:51:35 +01:00

240 lines
7.4 KiB
C

/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
#ifndef __BPF_TOOL_H
#define __BPF_TOOL_H
/* BFD and kernel.h both define GCC_VERSION, differently */
#undef GCC_VERSION
#include <stdbool.h>
#include <stdio.h>
#include <linux/bpf.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/hashtable.h>
#include <tools/libc_compat.h>
#include <bpf/libbpf.h>
#include "json_writer.h"
#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr))
#define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); })
#define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
#define BAD_ARG() ({ p_err("what is '%s'?", *argv); -1; })
#define GET_ARG() ({ argc--; *argv++; })
#define REQ_ARGS(cnt) \
({ \
int _cnt = (cnt); \
bool _res; \
\
if (argc < _cnt) { \
p_err("'%s' needs at least %d arguments, %d found", \
argv[-1], _cnt, argc); \
_res = false; \
} else { \
_res = true; \
} \
_res; \
})
#define ERR_MAX_LEN 1024
#define BPF_TAG_FMT "%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx"
#define HELP_SPEC_PROGRAM \
"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }"
#define HELP_SPEC_OPTIONS \
"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} |\n" \
"\t {-m|--mapcompat} | {-n|--nomount} }"
#define HELP_SPEC_MAP \
"MAP := { id MAP_ID | pinned FILE | name MAP_NAME }"
static const char * const prog_type_name[] = {
[BPF_PROG_TYPE_UNSPEC] = "unspec",
[BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter",
[BPF_PROG_TYPE_KPROBE] = "kprobe",
[BPF_PROG_TYPE_SCHED_CLS] = "sched_cls",
[BPF_PROG_TYPE_SCHED_ACT] = "sched_act",
[BPF_PROG_TYPE_TRACEPOINT] = "tracepoint",
[BPF_PROG_TYPE_XDP] = "xdp",
[BPF_PROG_TYPE_PERF_EVENT] = "perf_event",
[BPF_PROG_TYPE_CGROUP_SKB] = "cgroup_skb",
[BPF_PROG_TYPE_CGROUP_SOCK] = "cgroup_sock",
[BPF_PROG_TYPE_LWT_IN] = "lwt_in",
[BPF_PROG_TYPE_LWT_OUT] = "lwt_out",
[BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit",
[BPF_PROG_TYPE_SOCK_OPS] = "sock_ops",
[BPF_PROG_TYPE_SK_SKB] = "sk_skb",
[BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device",
[BPF_PROG_TYPE_SK_MSG] = "sk_msg",
[BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint",
[BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr",
[BPF_PROG_TYPE_LWT_SEG6LOCAL] = "lwt_seg6local",
[BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2",
[BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport",
[BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector",
[BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl",
[BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable",
[BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt",
[BPF_PROG_TYPE_TRACING] = "tracing",
[BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops",
[BPF_PROG_TYPE_EXT] = "ext",
};
extern const char * const map_type_name[];
extern const size_t map_type_name_size;
enum bpf_obj_type {
BPF_OBJ_UNKNOWN,
BPF_OBJ_PROG,
BPF_OBJ_MAP,
};
extern const char *bin_name;
extern json_writer_t *json_wtr;
extern bool json_output;
extern bool show_pinned;
extern bool block_mount;
extern bool verifier_logs;
extern bool relaxed_maps;
extern struct pinned_obj_table prog_table;
extern struct pinned_obj_table map_table;
void __printf(1, 2) p_err(const char *fmt, ...);
void __printf(1, 2) p_info(const char *fmt, ...);
bool is_prefix(const char *pfx, const char *str);
int detect_common_prefix(const char *arg, ...);
void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
void usage(void) __noreturn;
void set_max_rlimit(void);
int mount_tracefs(const char *target);
struct pinned_obj_table {
DECLARE_HASHTABLE(table, 16);
};
struct pinned_obj {
__u32 id;
char *path;
struct hlist_node hash;
};
struct btf;
struct bpf_line_info;
int build_pinned_obj_table(struct pinned_obj_table *table,
enum bpf_obj_type type);
void delete_pinned_obj_table(struct pinned_obj_table *tab);
void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode);
void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode);
struct cmd {
const char *cmd;
int (*func)(int argc, char **argv);
};
int cmd_select(const struct cmd *cmds, int argc, char **argv,
int (*help)(int argc, char **argv));
int get_fd_type(int fd);
const char *get_fd_type_name(enum bpf_obj_type type);
char *get_fdinfo(int fd, const char *key);
int open_obj_pinned(char *path, bool quiet);
int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
int mount_bpffs_for_pin(const char *name);
int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***));
int do_pin_fd(int fd, const char *name);
int do_prog(int argc, char **arg);
int do_map(int argc, char **arg);
int do_event_pipe(int argc, char **argv);
int do_cgroup(int argc, char **arg);
int do_perf(int argc, char **arg);
int do_net(int argc, char **arg);
int do_tracelog(int argc, char **arg);
int do_feature(int argc, char **argv);
int do_btf(int argc, char **argv);
int do_gen(int argc, char **argv);
int do_struct_ops(int argc, char **argv);
int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what);
int prog_parse_fd(int *argc, char ***argv);
int map_parse_fd(int *argc, char ***argv);
int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
struct bpf_prog_linfo;
#ifdef HAVE_LIBBFD_SUPPORT
void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
const char *arch, const char *disassembler_options,
const struct btf *btf,
const struct bpf_prog_linfo *prog_linfo,
__u64 func_ksym, unsigned int func_idx,
bool linum);
int disasm_init(void);
#else
static inline
void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
const char *arch, const char *disassembler_options,
const struct btf *btf,
const struct bpf_prog_linfo *prog_linfo,
__u64 func_ksym, unsigned int func_idx,
bool linum)
{
}
static inline int disasm_init(void)
{
p_err("No libbfd support");
return -1;
}
#endif
void print_data_json(uint8_t *data, size_t len);
void print_hex_data_json(uint8_t *data, size_t len);
unsigned int get_page_size(void);
unsigned int get_possible_cpus(void);
const char *
ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino,
const char **opt);
struct btf_dumper {
const struct btf *btf;
json_writer_t *jw;
bool is_plain_text;
bool prog_id_as_func_ptr;
};
/* btf_dumper_type - print data along with type information
* @d: an instance containing context for dumping types
* @type_id: index in btf->types array. this points to the type to be dumped
* @data: pointer the actual data, i.e. the values to be printed
*
* Returns zero on success and negative error code otherwise
*/
int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
const void *data);
void btf_dumper_type_only(const struct btf *btf, __u32 func_type_id,
char *func_only, int size);
void btf_dump_linfo_plain(const struct btf *btf,
const struct bpf_line_info *linfo,
const char *prefix, bool linum);
void btf_dump_linfo_json(const struct btf *btf,
const struct bpf_line_info *linfo, bool linum);
struct nlattr;
struct ifinfomsg;
struct tcmsg;
int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb);
int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind,
const char *devname, int ifindex);
int print_all_levels(__maybe_unused enum libbpf_print_level level,
const char *format, va_list args);
#endif