2018-05-04 23:23:29 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
|
#ifndef _PERF_BPF_H
|
|
|
|
|
#define _PERF_BPF_H
|
perf bpf: Include uapi/linux/bpf.h from the 'perf trace' script's bpf.h
The next example scripts need the definition for the BPF functions, i.e.
things like BPF_FUNC_probe_read, and in time will require lots of other
definitions found in uapi/linux/bpf.h, so include it from the bpf.h file
included from the eBPF scripts build with clang via '-e bpf_script.c'
like in this example:
$ tail -8 tools/perf/examples/bpf/5sec.c
#include <bpf.h>
int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
{
return sec == 5;
}
license(GPL);
$
That 'bpf.h' include in the 5sec.c eBPF example will come from a set of
header files crafted for building eBPF objects, that in a end-user
system will come from:
/usr/lib/perf/include/bpf/bpf.h
And will include <uapi/linux/bpf.h> either from the place where the
kernel was built, or from a kernel-devel rpm package like:
-working-directory /lib/modules/4.17.9-100.fc27.x86_64/build
That is set up by tools/perf/util/llvm-utils.c, and can be overriden
by setting the 'kbuild-dir' variable in the "llvm" ~/.perfconfig file,
like:
# cat ~/.perfconfig
[llvm]
kbuild-dir = /home/foo/git/build/linux
This usually doesn't need any change, just documenting here my findings
while working with this code.
In the future we may want to instead just use what is in
/usr/include/linux/bpf.h, that comes from the UAPI provided from the
kernel sources, for now, to avoid getting the kernel's non-UAPI
"linux/bpf.h" file, that will cause clang to fail and is not what we
want anyway (no BPF function definitions, etc), do it explicitely by
asking for "uapi/linux/bpf.h".
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zd8zeyhr2sappevojdem9xxt@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-01 21:50:51 +08:00
|
|
|
|
|
|
|
|
#include <uapi/linux/bpf.h>
|
|
|
|
|
|
perf bpf: Add struct bpf_map struct
A helper structure used by eBPF C program to describe map attributes to
elf_bpf loader, to be used initially by the special __bpf_stdout__ map
used to print strings into the perf ring buffer in BPF scripts, e.g.:
Using the upcoming stdio.h and puts() macros to use the __bpf_stdout__
map to add strings to the ring buffer:
# cat tools/perf/examples/bpf/hello.c
#include <stdio.h>
int syscall_enter(openat)(void *args)
{
puts("Hello, world\n");
return 0;
}
license(GPL);
#
# cat ~/.perfconfig
[llvm]
dump-obj = true
# perf trace -e openat,tools/perf/examples/bpf/hello.c/call-graph=dwarf/ cat /etc/passwd > /dev/null
LLVM: dumping tools/perf/examples/bpf/hello.o
0.016 ( ): __bpf_stdout__:Hello, world
0.018 ( 0.010 ms): cat/9079 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
0.057 ( ): __bpf_stdout__:Hello, world
0.059 ( 0.011 ms): cat/9079 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
0.417 ( ): __bpf_stdout__:Hello, world
0.419 ( 0.009 ms): cat/9079 openat(dfd: CWD, filename: /etc/passwd ) = 3
#
# file tools/perf/examples/bpf/hello.o
tools/perf/examples/bpf/hello.o: ELF 64-bit LSB relocatable, *unknown arch 0xf7* version 1 (SYSV), not stripped
# readelf -SW tools/perf/examples/bpf/hello.o
There are 10 section headers, starting at offset 0x208:
Section Headers:
[Nr] Name Type Address Off Size ES Flg Lk Inf Al
[ 0] NULL 0000000000000000 000000 000000 00 0 0 0
[ 1] .strtab STRTAB 0000000000000000 000188 00007f 00 0 0 1
[ 2] .text PROGBITS 0000000000000000 000040 000000 00 AX 0 0 4
[ 3] syscalls:sys_enter_openat PROGBITS 0000000000000000 000040 000088 00 AX 0 0 8
[ 4] .relsyscalls:sys_enter_openat REL 0000000000000000 000178 000010 10 9 3 8
[ 5] maps PROGBITS 0000000000000000 0000c8 00001c 00 WA 0 0 4
[ 6] .rodata.str1.1 PROGBITS 0000000000000000 0000e4 00000e 01 AMS 0 0 1
[ 7] license PROGBITS 0000000000000000 0000f2 000004 00 WA 0 0 1
[ 8] version PROGBITS 0000000000000000 0000f8 000004 00 WA 0 0 4
[ 9] .symtab SYMTAB 0000000000000000 000100 000078 18 1 1 8
Key to Flags:
W (write), A (alloc), X (execute), M (merge), S (strings), I (info),
L (link order), O (extra OS processing required), G (group), T (TLS),
C (compressed), x (unknown), o (OS specific), E (exclude),
p (processor specific)
# readelf -s tools/perf/examples/bpf/hello.o
Symbol table '.symtab' contains 5 entries:
Num: Value Size Type Bind Vis Ndx Name
0: 0000000000000000 0 NOTYPE LOCAL DEFAULT UND
1: 0000000000000000 0 NOTYPE GLOBAL DEFAULT 5 __bpf_stdout__
2: 0000000000000000 0 NOTYPE GLOBAL DEFAULT 7 _license
3: 0000000000000000 0 NOTYPE GLOBAL DEFAULT 8 _version
4: 0000000000000000 0 NOTYPE GLOBAL DEFAULT 3 syscall_enter_openat
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-81fg60om2ifnatsybzwmiga3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-06 20:02:26 +08:00
|
|
|
/*
|
|
|
|
|
* A helper structure used by eBPF C program to describe map attributes to
|
|
|
|
|
* elf_bpf loader, taken from tools/testing/selftests/bpf/bpf_helpers.h:
|
|
|
|
|
*/
|
|
|
|
|
struct bpf_map {
|
|
|
|
|
unsigned int type;
|
|
|
|
|
unsigned int key_size;
|
|
|
|
|
unsigned int value_size;
|
|
|
|
|
unsigned int max_entries;
|
|
|
|
|
unsigned int map_flags;
|
|
|
|
|
unsigned int inner_map_idx;
|
|
|
|
|
unsigned int numa_node;
|
|
|
|
|
};
|
|
|
|
|
|
2019-01-24 22:01:46 +08:00
|
|
|
#define bpf_map(name, _type, type_key, type_val, _max_entries) \
|
|
|
|
|
struct bpf_map SEC("maps") name = { \
|
|
|
|
|
.type = BPF_MAP_TYPE_##_type, \
|
|
|
|
|
.key_size = sizeof(type_key), \
|
|
|
|
|
.value_size = sizeof(type_val), \
|
|
|
|
|
.max_entries = _max_entries, \
|
|
|
|
|
}
|
|
|
|
|
|
perf bpf: Reduce the hardcoded .max_entries for pid_maps
While working on augmented syscalls I got into this error:
# trace -vv --filter-pids 2469,1663 -e tools/perf/examples/bpf/augmented_raw_syscalls.c sleep 1
<SNIP>
libbpf: map 0 is "__augmented_syscalls__"
libbpf: map 1 is "__bpf_stdout__"
libbpf: map 2 is "pids_filtered"
libbpf: map 3 is "syscalls"
libbpf: collecting relocating info for: '.text'
libbpf: relo for 13 value 84 name 133
libbpf: relocation: insn_idx=3
libbpf: relocation: find map 3 (pids_filtered) for insn 3
libbpf: collecting relocating info for: 'raw_syscalls:sys_enter'
libbpf: relo for 8 value 0 name 0
libbpf: relocation: insn_idx=1
libbpf: relo for 8 value 0 name 0
libbpf: relocation: insn_idx=3
libbpf: relo for 9 value 28 name 178
libbpf: relocation: insn_idx=36
libbpf: relocation: find map 1 (__augmented_syscalls__) for insn 36
libbpf: collecting relocating info for: 'raw_syscalls:sys_exit'
libbpf: relo for 8 value 0 name 0
libbpf: relocation: insn_idx=0
libbpf: relo for 8 value 0 name 0
libbpf: relocation: insn_idx=2
bpf: config program 'raw_syscalls:sys_enter'
bpf: config program 'raw_syscalls:sys_exit'
libbpf: create map __bpf_stdout__: fd=3
libbpf: create map __augmented_syscalls__: fd=4
libbpf: create map syscalls: fd=5
libbpf: create map pids_filtered: fd=6
libbpf: added 13 insn from .text to prog raw_syscalls:sys_enter
libbpf: added 13 insn from .text to prog raw_syscalls:sys_exit
libbpf: load bpf program failed: Operation not permitted
libbpf: failed to load program 'raw_syscalls:sys_exit'
libbpf: failed to load object 'tools/perf/examples/bpf/augmented_raw_syscalls.c'
bpf: load objects failed: err=-4009: (Incorrect kernel version)
event syntax error: 'tools/perf/examples/bpf/augmented_raw_syscalls.c'
\___ Failed to load program for unknown reason
(add -v to see detail)
Run 'perf list' for a list of valid events
Usage: perf trace [<options>] [<command>]
or: perf trace [<options>] -- <command> [<options>]
or: perf trace record [<options>] [<command>]
or: perf trace record [<options>] -- <command> [<options>]
-e, --event <event> event/syscall selector. use 'perf list' to list available events
If I then try to use strace (perf trace'ing 'perf trace' needs some more work
before its possible) to get a bit more info I get:
# strace -e bpf trace --filter-pids 2469,1663 -e tools/perf/examples/bpf/augmented_raw_syscalls.c sleep 1
bpf(BPF_MAP_CREATE, {map_type=BPF_MAP_TYPE_PERF_EVENT_ARRAY, key_size=4, value_size=4, max_entries=4, map_flags=0, inner_map_fd=0, map_name="__bpf_stdout__", map_ifindex=0}, 72) = 3
bpf(BPF_MAP_CREATE, {map_type=BPF_MAP_TYPE_PERF_EVENT_ARRAY, key_size=4, value_size=4, max_entries=4, map_flags=0, inner_map_fd=0, map_name="__augmented_sys", map_ifindex=0}, 72) = 4
bpf(BPF_MAP_CREATE, {map_type=BPF_MAP_TYPE_ARRAY, key_size=4, value_size=1, max_entries=500, map_flags=0, inner_map_fd=0, map_name="syscalls", map_ifindex=0}, 72) = 5
bpf(BPF_MAP_CREATE, {map_type=BPF_MAP_TYPE_HASH, key_size=4, value_size=1, max_entries=512, map_flags=0, inner_map_fd=0, map_name="pids_filtered", map_ifindex=0}, 72) = 6
bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_TRACEPOINT, insn_cnt=57, insns=0x1223f50, license="GPL", log_level=0, log_size=0, log_buf=NULL, kern_version=KERNEL_VERSION(4, 18, 10), prog_flags=0, prog_name="sys_enter", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS}, 72) = 7
bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_TRACEPOINT, insn_cnt=18, insns=0x1224120, license="GPL", log_level=0, log_size=0, log_buf=NULL, kern_version=KERNEL_VERSION(4, 18, 10), prog_flags=0, prog_name="sys_exit", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS}, 72) = -1 EPERM (Operation not permitted)
bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_TRACEPOINT, insn_cnt=18, insns=0x1224120, license="GPL", log_level=1, log_size=262144, log_buf="", kern_version=KERNEL_VERSION(4, 18, 10), prog_flags=0, prog_name="sys_exit", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS}, 72) = -1 EPERM (Operation not permitted)
bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_KPROBE, insn_cnt=18, insns=0x1224120, license="GPL", log_level=0, log_size=0, log_buf=NULL, kern_version=KERNEL_VERSION(4, 18, 10), prog_flags=0, prog_name="sys_exit", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS}, 72) = -1 EPERM (Operation not permitted)
event syntax error: 'tools/perf/examples/bpf/augmented_raw_syscalls.c'
\___ Failed to load program for unknown reason
<SNIP similar output as without 'strace'>
#
I managed to create the maps, etc, but then installing the "sys_exit" hook into
the "raw_syscalls:sys_exit" tracepoint somehow gets -EPERMed...
I then go and try reducing the size of this new table:
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -47,6 +47,17 @@ struct augmented_filename {
#define SYS_OPEN 2
#define SYS_OPENAT 257
+struct syscall {
+ bool filtered;
+};
+
+struct bpf_map SEC("maps") syscalls = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(struct syscall),
+ .max_entries = 500,
+};
And after reducing that .max_entries a tad, it works. So yeah, the "unknown
reason" should be related to the number of bytes all this is taking, reduce the
default for pid_map()s so that we can have a "syscalls" map with enough slots
for all syscalls in most arches. And take notes about this error message,
improve it :-)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Edward Cree <ecree@solarflare.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-yjzhak8asumz9e9hts2dgplp@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-08 01:49:27 +08:00
|
|
|
/*
|
|
|
|
|
* FIXME: this should receive .max_entries as a parameter, as careful
|
|
|
|
|
* tuning of these limits is needed to avoid hitting limits that
|
|
|
|
|
* prevents other BPF constructs, such as tracepoint handlers,
|
|
|
|
|
* to get installed, with cryptic messages from libbpf, etc.
|
|
|
|
|
* For the current need, 'perf trace --filter-pids', 64 should
|
|
|
|
|
* be good enough, but this surely needs to be revisited.
|
|
|
|
|
*/
|
2019-01-24 22:11:28 +08:00
|
|
|
#define pid_map(name, value_type) bpf_map(name, HASH, pid_t, value_type, 64)
|
2018-11-07 02:46:27 +08:00
|
|
|
|
|
|
|
|
static int (*bpf_map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags) = (void *)BPF_FUNC_map_update_elem;
|
|
|
|
|
static void *(*bpf_map_lookup_elem)(struct bpf_map *map, void *key) = (void *)BPF_FUNC_map_lookup_elem;
|
|
|
|
|
|
2018-05-04 23:23:29 +08:00
|
|
|
#define SEC(NAME) __attribute__((section(NAME), used))
|
2018-05-05 02:18:31 +08:00
|
|
|
|
perf bpf: Add probe() helper to reduce kprobes boilerplate
So that kprobe definitions become:
int probe(function, variables)(void *ctx, int err, var1, var2, ...)
The existing 5sec.c, got converted and goes from:
SEC("func=hrtimer_nanosleep rqtp->tv_sec")
int func(void *ctx, int err, long sec)
{
}
To:
int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
{
}
If we decide to add tv_nsec as well, then it becomes:
$ cat tools/perf/examples/bpf/5sec.c
#include <bpf.h>
int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec)
{
return sec == 5;
}
license(GPL);
$
And if we run it, system wide as before and run some 'sleep' with values
for the tv_nsec field, we get:
# perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c
0.000 perf_bpf_probe:hrtimer_nanosleep:(ffffffff9811b5f0) tv_sec=5 tv_nsec=100000000
9641.650 perf_bpf_probe:hrtimer_nanosleep:(ffffffff9811b5f0) tv_sec=5 tv_nsec=123450001
^C#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-1v9r8f6ds5av0w9pcwpeknyl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-05-05 02:59:16 +08:00
|
|
|
#define probe(function, vars) \
|
|
|
|
|
SEC(#function "=" #function " " #vars) function
|
|
|
|
|
|
2018-08-04 03:28:35 +08:00
|
|
|
#define syscall_enter(name) \
|
|
|
|
|
SEC("syscalls:sys_enter_" #name) syscall_enter_ ## name
|
|
|
|
|
|
2018-08-30 19:48:44 +08:00
|
|
|
#define syscall_exit(name) \
|
|
|
|
|
SEC("syscalls:sys_exit_" #name) syscall_exit_ ## name
|
|
|
|
|
|
2018-05-05 02:18:31 +08:00
|
|
|
#define license(name) \
|
|
|
|
|
char _license[] SEC("license") = #name; \
|
|
|
|
|
int _version SEC("version") = LINUX_VERSION_CODE;
|
|
|
|
|
|
2018-08-08 02:10:19 +08:00
|
|
|
static int (*probe_read)(void *dst, int size, const void *unsafe_addr) = (void *)BPF_FUNC_probe_read;
|
|
|
|
|
static int (*probe_read_str)(void *dst, int size, const void *unsafe_addr) = (void *)BPF_FUNC_probe_read_str;
|
|
|
|
|
|
2018-12-13 02:31:28 +08:00
|
|
|
static int (*perf_event_output)(void *, struct bpf_map *, int, void *, unsigned long) = (void *)BPF_FUNC_perf_event_output;
|
|
|
|
|
|
2018-05-04 23:23:29 +08:00
|
|
|
#endif /* _PERF_BPF_H */
|