mirror of
https://github.com/torvalds/linux.git
synced 2024-11-22 12:11:40 +00:00
56ac7bd2c5
786 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Arnaldo Carvalho de Melo
|
1de5b5dcb8 |
perf trace: Mark the 'head' arg in the set_robust_list syscall as coming from user space
With that it uses the generic BTF based pretty printer:
This one we need to think about, not being acquainted with this syscall,
should we _traverse_ that list somehow? Would that be useful?
root@number:~# perf trace -e set_robust_list sleep 1
0.000 ( 0.004 ms): sleep/1206493 set_robust_list(head: (struct robust_list_head){.list = (struct robust_list){.next = (struct robust_list *)0x7f48a9a02a20,},.futex_offset = (long int)-32,}, len: 24) =
root@number:~#
strace prints the default integer args:
root@number:~# strace -e set_robust_list sleep 1
set_robust_list(0x7efd99559a20, 24) = 0
+++ exited with 0 +++
root@number:~#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org
Link: https://lore.kernel.org/lkml/ZuH6MquMraBvODRp@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
0c1019e346 |
perf trace: Mark the 'rseq' arg in the rseq syscall as coming from user space
With that it uses the generic BTF based pretty printer:
root@number:~# grep -w rseq /sys/kernel/tracing/events/syscalls/sys_enter_rseq/format
field:struct rseq * rseq; offset:16; size:8; signed:0;
print fmt: "rseq: 0x%08lx, rseq_len: 0x%08lx, flags: 0x%08lx, sig: 0x%08lx", ((unsigned long)(REC->rseq)), ((unsigned long)(REC->rseq_len)), ((unsigned long)(REC->flags)), ((unsigned long)(REC->sig))
root@number:~#
Before:
root@number:~# perf trace -e rseq
0.000 ( 0.017 ms): Isolated Web C/1195452 rseq(rseq: 0x7ff0ecfe6fe0, rseq_len: 32, sig: 1392848979) = 0
74.018 ( 0.006 ms): :1195453/1195453 rseq(rseq: 0x7f2af20fffe0, rseq_len: 32, sig: 1392848979) = 0
1817.220 ( 0.009 ms): Isolated Web C/1195454 rseq(rseq: 0x7f5c9ec7dfe0, rseq_len: 32, sig: 1392848979) = 0
2515.526 ( 0.034 ms): :1195455/1195455 rseq(rseq: 0x7f61503fffe0, rseq_len: 32, sig: 1392848979) = 0
^Croot@number:~#
After:
root@number:~# perf trace -e rseq
0.000 ( 0.019 ms): Isolated Web C/1197258 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)4,.cpu_id = (__u32)4,.mm_cid = (__u32)5,}, rseq_len: 32, sig: 1392848979) = 0
1663.835 ( 0.019 ms): Isolated Web C/1197259 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)24,.cpu_id = (__u32)24,.mm_cid = (__u32)2,}, rseq_len: 32, sig: 1392848979) = 0
4750.444 ( 0.018 ms): Isolated Web C/1197260 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)8,.cpu_id = (__u32)8,.mm_cid = (__u32)4,}, rseq_len: 32, sig: 1392848979) = 0
4994.132 ( 0.018 ms): Isolated Web C/1197261 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)10,.cpu_id = (__u32)10,.mm_cid = (__u32)1,}, rseq_len: 32, sig: 1392848979) = 0
4997.578 ( 0.011 ms): Isolated Web C/1197263 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)16,.cpu_id = (__u32)16,.mm_cid = (__u32)4,}, rseq_len: 32, sig: 1392848979) = 0
4997.462 ( 0.014 ms): Isolated Web C/1197262 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)17,.cpu_id = (__u32)17,.mm_cid = (__u32)3,}, rseq_len: 32, sig: 1392848979) = 0
^Croot@number:~#
We'll probably need to come up with some way for using the BTF info to
synthesize a test that then gets used and captures the output of the
'perf trace' output to check if the arguments are the ones synthesized,
randomically, for now, lets make do manually:
root@number:~# cat ~acme/c/rseq.c
#include <sys/syscall.h> /* Definition of SYS_* constants */
#include <linux/rseq.h>
#include <errno.h>
#include <string.h>
#include <unistd.h>
#include <stdint.h>
#include <stdio.h>
/* Provide own rseq stub because glibc doesn't */
__attribute__((weak))
int sys_rseq(struct rseq *rseq, __u32 rseq_len, int flags, __u32 sig)
{
return syscall(SYS_rseq, rseq, rseq_len, flags, sig);
}
int main(int argc, char *argv[])
{
struct rseq rseq = {
.cpu_id_start = 12,
.cpu_id = 34,
.rseq_cs = 56,
.flags = 78,
.node_id = 90,
.mm_cid = 12,
};
int err = sys_rseq(&rseq, sizeof(rseq), 98765, 0xdeadbeaf);
printf("sys_rseq({ .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }, %d, 0) = %d (%s)\n", sizeof(rseq), err, strerror(errno));
return err;
}
root@number:~# perf trace -e rseq ~acme/c/rseq
sys_rseq({ .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }, 32, 0) = -1 (Invalid argument)
0.000 ( 0.003 ms): rseq/1200640 rseq(rseq: (struct rseq){}, rseq_len: 32, sig: 1392848979) =
0.064 ( 0.001 ms): rseq/1200640 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)12,.cpu_id = (__u32)34,.rseq_cs = (__u64)56,.flags = (__u32)78,.node_id = (__u32)90,.mm_cid = (__u32)12,}, rseq_len: 32, flags: 98765, sig: 3735928495) = -1 EINVAL (Invalid argument)
root@number:~#root@number:~# cat ~acme/c/rseq.c
#include <sys/syscall.h> /* Definition of SYS_* constants */
#include <linux/rseq.h>
#include <errno.h>
#include <string.h>
#include <unistd.h>
#include <stdint.h>
#include <stdio.h>
/* Provide own rseq stub because glibc doesn't */
__attribute__((weak))
int sys_rseq(struct rseq *rseq, __u32 rseq_len, int flags, __u32 sig)
{
return syscall(SYS_rseq, rseq, rseq_len, flags, sig);
}
int main(int argc, char *argv[])
{
struct rseq rseq = {
.cpu_id_start = 12,
.cpu_id = 34,
.rseq_cs = 56,
.flags = 78,
.node_id = 90,
.mm_cid = 12,
};
int err = sys_rseq(&rseq, sizeof(rseq), 98765, 0xdeadbeaf);
printf("sys_rseq({ .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }, %d, 0) = %d (%s)\n", sizeof(rseq), err, strerror(errno));
return err;
}
root@number:~# perf trace -e rseq ~acme/c/rseq
sys_rseq({ .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }, 32, 0) = -1 (Invalid argument)
0.000 ( 0.003 ms): rseq/1200640 rseq(rseq: (struct rseq){}, rseq_len: 32, sig: 1392848979) =
0.064 ( 0.001 ms): rseq/1200640 rseq(rseq: (struct rseq){.cpu_id_start = (__u32)12,.cpu_id = (__u32)34,.rseq_cs = (__u64)56,.flags = (__u32)78,.node_id = (__u32)90,.mm_cid = (__u32)12,}, rseq_len: 32, flags: 98765, sig: 3735928495) = -1 EINVAL (Invalid argument)
root@number:~#
Interesting, glibc seems to be using rseq here, as in addition to the
totally fake one this test case uses, we have this one, around these
other syscalls:
0.175 ( 0.001 ms): rseq/1201095 set_tid_address(tidptr: 0x7f6def759a10) = 1201095 (rseq)
0.177 ( 0.001 ms): rseq/1201095 set_robust_list(head: 0x7f6def759a20, len: 24) = 0
0.178 ( 0.001 ms): rseq/1201095 rseq(rseq: (struct rseq){}, rseq_len: 32, sig: 1392848979) =
0.231 ( 0.005 ms): rseq/1201095 mprotect(start: 0x7f6def93f000, len: 16384, prot: READ) = 0
0.238 ( 0.003 ms): rseq/1201095 mprotect(start: 0x403000, len: 4096, prot: READ) = 0
0.244 ( 0.004 ms): rseq/1201095 mprotect(start: 0x7f6def99c000, len: 8192, prot: READ)
Matches strace (well, not really as the strace in fedora:40 doesn't know
about rseq, printing just integer values in hex):
set_robust_list(0x7fbc6acc7a20, 24) = 0
rseq(0x7fbc6acc8060, 0x20, 0, 0x53053053) = 0
mprotect(0x7fbc6aead000, 16384, PROT_READ) = 0
mprotect(0x403000, 4096, PROT_READ) = 0
mprotect(0x7fbc6af0a000, 8192, PROT_READ) = 0
prlimit64(0, RLIMIT_STACK, NULL, {rlim_cur=8192*1024, rlim_max=RLIM64_INFINITY}) = 0
munmap(0x7fbc6aebd000, 81563) = 0
rseq(0x7fff15bb9920, 0x20, 0x181cd, 0xdeadbeaf) = -1 EINVAL (Invalid argument)
fstat(1, {st_mode=S_IFCHR|0620, st_rdev=makedev(0x88, 0x9), ...}) = 0
getrandom("\xd0\x34\x97\x17\x61\xc2\x2b\x10", 8, GRND_NONBLOCK) = 8
brk(NULL) = 0x18ff4000
brk(0x19015000) = 0x19015000
write(1, "sys_rseq({ .cpu_id_start = 12, ."..., 136sys_rseq({ .cpu_id_start = 12, .cpu_id = 34, .rseq_cs = 56, .flags = 78, .node_id = 90, .mm_cid = 12, }, 32, 0) = -1 (Invalid argument)
) = 136
exit_group(-1) = ?
+++ exited with 255 +++
root@number:~#
And also the focus for the v6.13 should be to have a better, strace
like BTF pretty printer as one of the outputs we can get from the libbpf
BTF dumper.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZuH2K1LLt1pIDkbd@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
4c1af9bf97 |
perf trace: If a syscall arg is marked as 'const', assume it is coming _from_ userspace
We need to decide where to copy syscall arg contents, if at the
syscalls:sys_entry hook, meaning is something that is coming from
user to kernel space, or if it is a response, i.e. if it is something
the _kernel_ is filling in and thus going to userspace.
Since we have 'const' used in those syscalls, and unsure about this
being consistent, doing:
root@number:~# echo $(grep const /sys/kernel/tracing/events/syscalls/sys_enter_*/format | grep struct | cut -c47- | cut -d'/' -f1)
clock_nanosleep clock_settime epoll_pwait2 futex io_pgetevents landlock_create_ruleset listmount mq_getsetattr mq_notify mq_timedreceive mq_timedsend preadv2 preadv prlimit64 process_madvise process_vm_readv process_vm_readv process_vm_writev process_vm_writev pwritev2 pwritev readv rt_sigaction rt_sigtimedwait semtimedop statmount timerfd_settime timer_settime vmsplice writev
root@number:~#
Seems to indicate that we can use that for the ones that have the
'const' to mark it as coming from user space, do it.
Most notable/frequent syscall that now gets BTF pretty printed in a
system wide 'perf trace' session is:
root@number:~# perf trace
21.160 ( ): MediaSu~isor #/1028597 futex(uaddr: 0x7f49e1dfe964, op: WAIT_BITSET|PRIVATE_FLAG, utime: (struct __kernel_timespec){.tv_sec = (__kernel_time64_t)50290,.tv_nsec = (long long int)810362837,}, val3: MATCH_ANY) ...
21.166 ( 0.000 ms): RemVidChild/6995 futex(uaddr: 0x7f49fcc7fa00, op: WAKE|PRIVATE_FLAG, val: 1) = 0
21.169 ( 0.001 ms): RemVidChild/6995 sendmsg(fd: 25<socket:[78915]>, msg: 0x7f49e9af9da0, flags: DONTWAIT) = 280
21.172 ( 0.289 ms): RemVidChild/6995 futex(uaddr: 0x7f49fcc7fa58, op: WAIT_BITSET|PRIVATE_FLAG|CLOCK_REALTIME, val3: MATCH_ANY) = 0
21.463 ( 0.000 ms): RemVidChild/6995 futex(uaddr: 0x7f49fcc7fa00, op: WAKE|PRIVATE_FLAG, val: 1) = 0
21.467 ( 0.001 ms): RemVidChild/6995 futex(uaddr: 0x7f49e28bb964, op: WAKE|PRIVATE_FLAG, val: 1) = 1
21.160 ( 0.314 ms): MediaSu~isor #/1028597 ... [continued]: futex()) = 0
21.469 ( ): RemVidChild/6995 futex(uaddr: 0x7f49fcc7fa5c, op: WAIT_BITSET|PRIVATE_FLAG|CLOCK_REALTIME, val3: MATCH_ANY) ...
21.475 ( 0.000 ms): MediaSu~isor #/1028597 futex(uaddr: 0x7f49d0223040, op: WAKE|PRIVATE_FLAG, val: 1) = 0
21.478 ( 0.001 ms): MediaSu~isor #/1028597 futex(uaddr: 0x7f49e26ac964, op: WAKE|PRIVATE_FLAG, val: 1) = 1
^Croot@number:~#
root@number:~# cat /sys/kernel/tracing/events/syscalls/sys_enter_futex/format
name: sys_enter_futex
ID: 454
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:int __syscall_nr; offset:8; size:4; signed:1;
field:u32 * uaddr; offset:16; size:8; signed:0;
field:int op; offset:24; size:8; signed:0;
field:u32 val; offset:32; size:8; signed:0;
field:const struct __kernel_timespec * utime; offset:40; size:8; signed:0;
field:u32 * uaddr2; offset:48; size:8; signed:0;
field:u32 val3; offset:56; size:8; signed:0;
print fmt: "uaddr: 0x%08lx, op: 0x%08lx, val: 0x%08lx, utime: 0x%08lx, uaddr2: 0x%08lx, val3: 0x%08lx", ((unsigned long)(REC->uaddr)), ((unsigned long)(REC->op)), ((unsigned long)(REC->val)), ((unsigned long)(REC->utime)), ((unsigned long)(REC->uaddr2)), ((unsigned long)(REC->val3))
root@number:~#
Suggested-by: Ian Rogers <irogers@google.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/CAP-5=fWnuQrrBoTn6Rrn6vM_xQ2fCoc9i-AitD7abTcNi-4o1Q@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
375f9262ac |
perf trace: Mark the rlim arg in the prlimit64 and setrlimit syscalls as coming from user space
With that it uses the generic BTF based pretty printer:
root@number:~# perf trace -e prlimit64
0.000 ( 0.004 ms): :3417020/3417020 prlimit64(resource: NOFILE, old_rlim: 0x7fb8842fe3b0) = 0
0.126 ( 0.003 ms): Chroot Helper/3417022 prlimit64(resource: NOFILE, old_rlim: 0x7fb8842fdfd0) = 0
12.557 ( 0.005 ms): firefox/3417020 prlimit64(resource: STACK, old_rlim: 0x7ffe9ade1b80) = 0
26.640 ( 0.006 ms): MainThread/3417020 prlimit64(resource: STACK, old_rlim: 0x7ffe9ade1780) = 0
27.553 ( 0.002 ms): Web Content/3417020 prlimit64(resource: AS, old_rlim: 0x7ffe9ade1660) = 0
29.405 ( 0.003 ms): Web Content/3417020 prlimit64(resource: NOFILE, old_rlim: 0x7ffe9ade0c80) = 0
30.471 ( 0.002 ms): Web Content/3417020 prlimit64(resource: RTTIME, old_rlim: 0x7ffe9ade1370) = 0
30.485 ( 0.001 ms): Web Content/3417020 prlimit64(resource: RTTIME, new_rlim: (struct rlimit64){.rlim_cur = (__u64)50000,.rlim_max = (__u64)200000,}) = 0
31.779 ( 0.001 ms): Web Content/3417020 prlimit64(resource: STACK, old_rlim: 0x7ffe9ade1670) = 0
^Croot@number:~#
Better than before, still needs improvements in the configurability of
the libbpf BTF dumper to get it to the strace output standard.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZuBQI-f8CGpuhIdH@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
f3f16112c6 |
perf trace: Support collecting 'union's with the BPF augmenter
And reuse the BTF based struct pretty printer, with that we can offer
initial support for the 'bpf' syscall's second argument, a 'union
bpf_attr' pointer.
But this is not that satisfactory as the libbpf btf dumper will pretty
print _all_ the union, we need to have a way to say that the first arg
selects the type for the union member to be pretty printed, something
like what pahole does translating the PERF_RECORD_ selector into a name,
and using that name to find a matching struct.
In the case of 'union bpf_attr' it would map PROG_LOAD to one of the
union members, but unfortunately there is no such mapping:
root@number:~# pahole bpf_attr
union bpf_attr {
struct {
__u32 map_type; /* 0 4 */
__u32 key_size; /* 4 4 */
__u32 value_size; /* 8 4 */
__u32 max_entries; /* 12 4 */
__u32 map_flags; /* 16 4 */
__u32 inner_map_fd; /* 20 4 */
__u32 numa_node; /* 24 4 */
char map_name[16]; /* 28 16 */
__u32 map_ifindex; /* 44 4 */
__u32 btf_fd; /* 48 4 */
__u32 btf_key_type_id; /* 52 4 */
__u32 btf_value_type_id; /* 56 4 */
__u32 btf_vmlinux_value_type_id; /* 60 4 */
/* --- cacheline 1 boundary (64 bytes) --- */
__u64 map_extra; /* 64 8 */
__s32 value_type_btf_obj_fd; /* 72 4 */
__s32 map_token_fd; /* 76 4 */
}; /* 0 80 */
struct {
__u32 map_fd; /* 0 4 */
/* XXX 4 bytes hole, try to pack */
__u64 key; /* 8 8 */
union {
__u64 value; /* 16 8 */
__u64 next_key; /* 16 8 */
}; /* 16 8 */
__u64 flags; /* 24 8 */
}; /* 0 32 */
struct {
__u64 in_batch; /* 0 8 */
__u64 out_batch; /* 8 8 */
__u64 keys; /* 16 8 */
__u64 values; /* 24 8 */
__u32 count; /* 32 4 */
__u32 map_fd; /* 36 4 */
__u64 elem_flags; /* 40 8 */
__u64 flags; /* 48 8 */
} batch; /* 0 56 */
struct {
__u32 prog_type; /* 0 4 */
__u32 insn_cnt; /* 4 4 */
__u64 insns; /* 8 8 */
__u64 license; /* 16 8 */
__u32 log_level; /* 24 4 */
__u32 log_size; /* 28 4 */
__u64 log_buf; /* 32 8 */
__u32 kern_version; /* 40 4 */
__u32 prog_flags; /* 44 4 */
char prog_name[16]; /* 48 16 */
/* --- cacheline 1 boundary (64 bytes) --- */
__u32 prog_ifindex; /* 64 4 */
__u32 expected_attach_type; /* 68 4 */
__u32 prog_btf_fd; /* 72 4 */
__u32 func_info_rec_size; /* 76 4 */
__u64 func_info; /* 80 8 */
__u32 func_info_cnt; /* 88 4 */
__u32 line_info_rec_size; /* 92 4 */
__u64 line_info; /* 96 8 */
__u32 line_info_cnt; /* 104 4 */
__u32 attach_btf_id; /* 108 4 */
union {
__u32 attach_prog_fd; /* 112 4 */
__u32 attach_btf_obj_fd; /* 112 4 */
}; /* 112 4 */
__u32 core_relo_cnt; /* 116 4 */
__u64 fd_array; /* 120 8 */
/* --- cacheline 2 boundary (128 bytes) --- */
__u64 core_relos; /* 128 8 */
__u32 core_relo_rec_size; /* 136 4 */
__u32 log_true_size; /* 140 4 */
__s32 prog_token_fd; /* 144 4 */
}; /* 0 152 */
struct {
__u64 pathname; /* 0 8 */
__u32 bpf_fd; /* 8 4 */
__u32 file_flags; /* 12 4 */
__s32 path_fd; /* 16 4 */
}; /* 0 24 */
struct {
union {
__u32 target_fd; /* 0 4 */
__u32 target_ifindex; /* 0 4 */
}; /* 0 4 */
__u32 attach_bpf_fd; /* 4 4 */
__u32 attach_type; /* 8 4 */
__u32 attach_flags; /* 12 4 */
__u32 replace_bpf_fd; /* 16 4 */
union {
__u32 relative_fd; /* 20 4 */
__u32 relative_id; /* 20 4 */
}; /* 20 4 */
__u64 expected_revision; /* 24 8 */
}; /* 0 32 */
struct {
__u32 prog_fd; /* 0 4 */
__u32 retval; /* 4 4 */
__u32 data_size_in; /* 8 4 */
__u32 data_size_out; /* 12 4 */
__u64 data_in; /* 16 8 */
__u64 data_out; /* 24 8 */
__u32 repeat; /* 32 4 */
__u32 duration; /* 36 4 */
__u32 ctx_size_in; /* 40 4 */
__u32 ctx_size_out; /* 44 4 */
__u64 ctx_in; /* 48 8 */
__u64 ctx_out; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
__u32 flags; /* 64 4 */
__u32 cpu; /* 68 4 */
__u32 batch_size; /* 72 4 */
} test; /* 0 80 */
struct {
union {
__u32 start_id; /* 0 4 */
__u32 prog_id; /* 0 4 */
__u32 map_id; /* 0 4 */
__u32 btf_id; /* 0 4 */
__u32 link_id; /* 0 4 */
}; /* 0 4 */
__u32 next_id; /* 4 4 */
__u32 open_flags; /* 8 4 */
}; /* 0 12 */
struct {
__u32 bpf_fd; /* 0 4 */
__u32 info_len; /* 4 4 */
__u64 info; /* 8 8 */
} info; /* 0 16 */
struct {
union {
__u32 target_fd; /* 0 4 */
__u32 target_ifindex; /* 0 4 */
}; /* 0 4 */
__u32 attach_type; /* 4 4 */
__u32 query_flags; /* 8 4 */
__u32 attach_flags; /* 12 4 */
__u64 prog_ids; /* 16 8 */
union {
__u32 prog_cnt; /* 24 4 */
__u32 count; /* 24 4 */
}; /* 24 4 */
/* XXX 4 bytes hole, try to pack */
__u64 prog_attach_flags; /* 32 8 */
__u64 link_ids; /* 40 8 */
__u64 link_attach_flags; /* 48 8 */
__u64 revision; /* 56 8 */
} query; /* 0 64 */
struct {
__u64 name; /* 0 8 */
__u32 prog_fd; /* 8 4 */
/* XXX 4 bytes hole, try to pack */
__u64 cookie; /* 16 8 */
} raw_tracepoint; /* 0 24 */
struct {
__u64 btf; /* 0 8 */
__u64 btf_log_buf; /* 8 8 */
__u32 btf_size; /* 16 4 */
__u32 btf_log_size; /* 20 4 */
__u32 btf_log_level; /* 24 4 */
__u32 btf_log_true_size; /* 28 4 */
__u32 btf_flags; /* 32 4 */
__s32 btf_token_fd; /* 36 4 */
}; /* 0 40 */
struct {
__u32 pid; /* 0 4 */
__u32 fd; /* 4 4 */
__u32 flags; /* 8 4 */
__u32 buf_len; /* 12 4 */
__u64 buf; /* 16 8 */
__u32 prog_id; /* 24 4 */
__u32 fd_type; /* 28 4 */
__u64 probe_offset; /* 32 8 */
__u64 probe_addr; /* 40 8 */
} task_fd_query; /* 0 48 */
struct {
union {
__u32 prog_fd; /* 0 4 */
__u32 map_fd; /* 0 4 */
}; /* 0 4 */
union {
__u32 target_fd; /* 4 4 */
__u32 target_ifindex; /* 4 4 */
}; /* 4 4 */
__u32 attach_type; /* 8 4 */
__u32 flags; /* 12 4 */
union {
__u32 target_btf_id; /* 16 4 */
struct {
__u64 iter_info; /* 16 8 */
__u32 iter_info_len; /* 24 4 */
}; /* 16 16 */
struct {
__u64 bpf_cookie; /* 16 8 */
} perf_event; /* 16 8 */
struct {
__u32 flags; /* 16 4 */
__u32 cnt; /* 20 4 */
__u64 syms; /* 24 8 */
__u64 addrs; /* 32 8 */
__u64 cookies; /* 40 8 */
} kprobe_multi; /* 16 32 */
struct {
__u32 target_btf_id; /* 16 4 */
/* XXX 4 bytes hole, try to pack */
__u64 cookie; /* 24 8 */
} tracing; /* 16 16 */
struct {
__u32 pf; /* 16 4 */
__u32 hooknum; /* 20 4 */
__s32 priority; /* 24 4 */
__u32 flags; /* 28 4 */
} netfilter; /* 16 16 */
struct {
union {
__u32 relative_fd; /* 16 4 */
__u32 relative_id; /* 16 4 */
}; /* 16 4 */
/* XXX 4 bytes hole, try to pack */
__u64 expected_revision; /* 24 8 */
} tcx; /* 16 16 */
struct {
__u64 path; /* 16 8 */
__u64 offsets; /* 24 8 */
__u64 ref_ctr_offsets; /* 32 8 */
__u64 cookies; /* 40 8 */
__u32 cnt; /* 48 4 */
__u32 flags; /* 52 4 */
__u32 pid; /* 56 4 */
} uprobe_multi; /* 16 48 */
struct {
union {
__u32 relative_fd; /* 16 4 */
__u32 relative_id; /* 16 4 */
}; /* 16 4 */
/* XXX 4 bytes hole, try to pack */
__u64 expected_revision; /* 24 8 */
} netkit; /* 16 16 */
}; /* 16 48 */
} link_create; /* 0 64 */
struct {
__u32 link_fd; /* 0 4 */
union {
__u32 new_prog_fd; /* 4 4 */
__u32 new_map_fd; /* 4 4 */
}; /* 4 4 */
__u32 flags; /* 8 4 */
union {
__u32 old_prog_fd; /* 12 4 */
__u32 old_map_fd; /* 12 4 */
}; /* 12 4 */
} link_update; /* 0 16 */
struct {
__u32 link_fd; /* 0 4 */
} link_detach; /* 0 4 */
struct {
__u32 type; /* 0 4 */
} enable_stats; /* 0 4 */
struct {
__u32 link_fd; /* 0 4 */
__u32 flags; /* 4 4 */
} iter_create; /* 0 8 */
struct {
__u32 prog_fd; /* 0 4 */
__u32 map_fd; /* 4 4 */
__u32 flags; /* 8 4 */
} prog_bind_map; /* 0 12 */
struct {
__u32 flags; /* 0 4 */
__u32 bpffs_fd; /* 4 4 */
} token_create; /* 0 8 */
};
root@number:~#
So this is one case where BTF gets us only that far, not getting all
the way to automate the pretty printing of unions designed like 'union
bpf_attr', we will need a custom pretty printer for this union, as using
the libbpf union BTF dumper is way too verbose:
root@number:~# perf trace --max-events 1 -e bpf bpftool map
0.000 ( 0.054 ms): bpftool/3409073 bpf(cmd: PROG_LOAD, uattr: (union bpf_attr){(struct){.map_type = (__u32)1,.key_size = (__u32)2,.value_size = (__u32)2755142048,.max_entries = (__u32)32764,.map_flags = (__u32)150263906,.inner_map_fd = (__u32)21920,},(struct){.map_fd = (__u32)1,.key = (__u64)140723063628192,(union){.value = (__u64)94145833392226,.next_key = (__u64)94145833392226,},},.batch = (struct){.in_batch = (__u64)8589934593,.out_batch = (__u64)140723063628192,.keys = (__u64)94145833392226,},(struct){.prog_type = (__u32)1,.insn_cnt = (__u32)2,.insns = (__u64)140723063628192,.license = (__u64)94145833392226,},(struct){.pathname = (__u64)8589934593,.bpf_fd = (__u32)2755142048,.file_flags = (__u32)32764,.path_fd = (__s32)150263906,},(struct){(union){.target_fd = (__u32)1,.target_ifindex = (__u32)1,},.attach_bpf_fd = (__u32)2,.attach_type = (__u32)2755142048,.attach_flags = (__u32)32764,.replace_bpf_fd = (__u32)150263906,(union){.relative_fd = (__u32)21920,.relative_id = (__u32)21920,},},.test = (struct){.prog_fd = (__u32)1,.retval = (__u32)2,.data_size_in = (__u32)2755142048,.data_size_out = (__u32)32764,.data_in = (__u64)94145833392226,},(struct){(union){.start_id = (__u32)1,.prog_id = (__u32)1,.map_id = (__u32)1,.btf_id = (__u32)1,.link_id = (__u32)1,},.next_id = (__u32)2,.open_flags = (__u32)2755142048,},.info = (struct){.bpf_fd = (__u32)1,.info_len = (__u32)2,.info = (__u64)140723063628192,},.query = (struct){(union){.target_fd = (__u32)1,.target_ifindex = (__u32)1,},.attach_type = (__u32)2,.query_flags = (__u32)2755142048,.attach_flags = (__u32)32764,.prog_ids = (__u64)94145833392226,},.raw_tracepoint = (struct){.name = (__u64)8589934593,.prog_fd = (__u32)2755142048,.cookie = (__u64)94145833392226,},(struct){.btf = (__u64)8589934593,.btf_log_buf = (__u64)140723063628192,.btf_size = (__u32)150263906,.btf_log_size = (__u32)21920,},.task_fd_query = (struct){.pid = (__u32)1,.fd = (__u32)2,.flags = (__u32)2755142048,.buf_len = (__u32)32764,.buf = (__u64)94145833392226,},.link_create = (struct){(union){.prog_fd = (__u32)1,.map_fd = (__u32)1,},(u) = 3
root@number:~# 2: prog_array name hid_jmp_table flags 0x0
key 4B value 4B max_entries 1024 memlock 8440B
owner_prog_type tracing owner jited
13: hash_of_maps name cgroup_hash flags 0x0
key 8B value 4B max_entries 2048 memlock 167584B
pids systemd(1)
960: array name libbpf_global flags 0x0
key 4B value 32B max_entries 1 memlock 280B
961: array name pid_iter.rodata flags 0x480
key 4B value 4B max_entries 1 memlock 8192B
btf_id 1846 frozen
pids bpftool(3409073)
962: array name libbpf_det_bind flags 0x0
key 4B value 32B max_entries 1 memlock 280B
root@number:~#
For simpler unions this may be better than not seeing any payload, so
keep it there.
Acked-by: Howard Chu <howardchu95@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZuBLat8cbadILNLA@x1
[ Removed needless parenteses in the if block leading to the trace__btf_scnprintf() call, as per Howard's review comments ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
Howard Chu
|
3278024540 |
perf trace: Add --force-btf for debugging
If --force-btf is enabled, prefer btf_dump general pretty printer to
perf trace's customized pretty printers.
Mostly for debug purposes.
Committer testing:
diff before/after shows we need several improvements to be able to
compare the changes, first we need to cut off/disable mutable data such
as pids and timestamps, then what is left are the buffer addresses
passed from userspace, returned from kernel space, maybe we can ask
'perf trace' to go on making those reproducible.
That would entail a Pointer Address Translation (PAT) like for
networking, that would, for simple, reproducible if not for these
details, workloads, that we would then use in our regression tests.
Enough digression, this is one such diff:
openat(dfd: CWD, filename: "/usr/share/locale/locale.alias", flags: RDONLY|CLOEXEC) = 3
-fstat(fd: 3, statbuf: 0x7fff01f212a0) = 0
-read(fd: 3, buf: 0x5596bab2d630, count: 4096) = 2998
-read(fd: 3, buf: 0x5596bab2d630, count: 4096) = 0
+fstat(fd: 3, statbuf: 0x7ffc163cf0e0) = 0
+read(fd: 3, buf: 0x55b4e0631630, count: 4096) = 2998
+read(fd: 3, buf: 0x55b4e0631630, count: 4096) = 0
close(fd: 3) = 0
openat(dfd: CWD, filename: "/usr/share/locale/en_US.UTF-8/LC_MESSAGES/coreutils.mo") = -1 ENOENT (No such file or directory)
openat(dfd: CWD, filename: "/usr/share/locale/en_US.utf8/LC_MESSAGES/coreutils.mo") = -1 ENOENT (No such file or directory)
@@ -45,7 +45,7 @@
openat(dfd: CWD, filename: "/usr/share/locale/en.UTF-8/LC_MESSAGES/coreutils.mo") = -1 ENOENT (No such file or directory)
openat(dfd: CWD, filename: "/usr/share/locale/en.utf8/LC_MESSAGES/coreutils.mo") = -1 ENOENT (No such file or directory)
openat(dfd: CWD, filename: "/usr/share/locale/en/LC_MESSAGES/coreutils.mo") = -1 ENOENT (No such file or directory)
-{ .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7fff01f21990) = 0
+(struct __kernel_timespec){.tv_sec = (__kernel_time64_t)1,}, rmtp: 0x7ffc163cf7d0) =
The problem more close to our hands is to make the libbpf BTF pretty
printer to have a mode that closely resembles what we're trying to
resemble: strace output.
Being able to run something with 'perf trace' and with 'strace' and get
the exact same output should be of interest of anybody wanting to have
strace and 'perf trace' regression tested against each other.
That last part is 'perf trace' shot at being something so useful as
strace... ;-)
Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240824163322.60796-8-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Howard Chu
|
b257fac12f |
perf trace: Pretty print buffer data
Define TRACE_AUG_MAX_BUF in trace_augment.h data, which is the maximum
buffer size we can augment. BPF will include this header too.
Print buffer in a way that's different than just printing a string, we
print all the control characters in \digits (such as \0 for null, and
\10 for newline, LF).
For character that has a bigger value than 127, we print the digits
instead of the character itself as well.
Committer notes:
Simplified the buffer scnprintf to avoid using multiple buffers as
discussed in the patch review thread.
We can't really all 'buf' args to SCA_BUF as we're collecting so far
just on the sys_enter path, so we would be printing the previous 'read'
arg buffer contents, not what the kernel puts there.
So instead of:
static int syscall_fmt__cmp(const void *name, const void *fmtp)
@@ -1987,8 +1989,6 @@ syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field
- else if (strstr(field->type, "char *") && strstr(field->name, "buf"))
- arg->scnprintf = SCA_BUF;
Do:
static const struct syscall_fmt syscall_fmts[] = {
+ { .name = "write", .errpid = true,
+ .arg = { [1] = { .scnprintf = SCA_BUF /* buf */, from_user = true, }, }, },
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240815013626.935097-8-howardchu95@gmail.com
Link: https://lore.kernel.org/r/20240824163322.60796-6-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Howard Chu
|
cb32035214 |
perf trace: Pretty print struct data
Change the arg->augmented.args to arg->augmented.args->value to skip the
header for customized pretty printers, since we collect data in BPF
using the general augment_sys_enter(), which always adds the header.
Use btf_dump API to pretty print augmented struct pointer.
Prefer existed pretty-printer than btf general pretty-printer.
set compact = true and skip_names = true, so that no newline character
and argument name are printed.
Committer notes:
Simplified the btf_dump_snprintf callback to avoid using multiple
buffers, as discussed in the thread accessible via the Link tag below.
Also made it do:
dump_data_opts.skip_names = !arg->trace->show_arg_names;
I.e. show the type and struct field names according to that tunable, we
probably need another tunable just for this, but for now if the user
wants to see syscall names in addition to its value, it makes sense to
see the struct field names according to that tunable.
Committer testing:
The following have explicitely set beautifiers (SCA_FILENAME,
SCA_SOCKADDR and SCA_PERF_ATTR), SCA_FILENAME is here just because we
have been wiring up the "renameat2" ("renameat" until recently), so it
doesn't use the introduced generic fallback (btf_struct_scnprintf(), see
the definition of SCA_PERF_ATTR, SCA_SOCKADDR to see the more feature
rich beautifiers, that are not using BTF):
root@number:~# rm -f 987654 ; touch 123456 ; perf trace -e rename* mv 123456 987654
0.000 ( 0.039 ms): mv/258478 renameat2(olddfd: CWD, oldname: "123456", newdfd: CWD, newname: "987654", flags: NOREPLACE) = 0
root@number:~# perf trace -e connect,sendto ping -c 1 www.google.com
0.000 ( 0.014 ms): ping/258481 connect(fd: 5, uservaddr: { .family: LOCAL, path: /run/systemd/resolve/io.systemd.Resolve }, addrlen: 42) = 0
0.040 ( 0.003 ms): ping/258481 sendto(fd: 5, buff: 0x55bc317a6980, len: 97, flags: DONTWAIT|NOSIGNAL) = 97
18.742 ( 0.020 ms): ping/258481 sendto(fd: 5, buff: 0x7ffc04768df0, len: 20, addr: { .family: NETLINK }, addr_len: 0xc) = 20
PING www.google.com (142.251.129.68) 56(84) bytes of data.
18.783 ( 0.012 ms): ping/258481 connect(fd: 5, uservaddr: { .family: INET6, port: 0, addr: 2800:3f0:4004:810::2004 }, addrlen: 28) = 0
18.797 ( 0.001 ms): ping/258481 connect(fd: 5, uservaddr: { .family: UNSPEC }, addrlen: 16) = 0
18.800 ( 0.004 ms): ping/258481 connect(fd: 5, uservaddr: { .family: INET, port: 0, addr: 142.251.129.68 }, addrlen: 16) = 0
18.815 ( 0.002 ms): ping/258481 connect(fd: 5, uservaddr: { .family: INET, port: 1025, addr: 142.251.129.68 }, addrlen: 16) = 0
18.862 ( 0.023 ms): ping/258481 sendto(fd: 3, buff: 0x55bc317a0ac0, len: 64, addr: { .family: INET, port: 0, addr: 142.251.129.68 }, addr_len: 0x10) = 64
63.330 ( 0.038 ms): ping/258481 connect(fd: 5, uservaddr: { .family: LOCAL, path: /run/systemd/resolve/io.systemd.Resolve }, addrlen: 42) = 0
63.435 ( 0.010 ms): ping/258481 sendto(fd: 5, buff: 0x55bc317a8340, len: 110, flags: DONTWAIT|NOSIGNAL) = 110
64 bytes from rio07s07-in-f4.1e100.net (142.251.129.68): icmp_seq=1 ttl=49 time=44.2 ms
--- www.google.com ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 44.158/44.158/44.158/0.000 ms
root@number:~# perf trace -e perf_event_open perf stat -e instructions,cache-misses,syscalls:sys_enter*sleep* sleep 1.23456789
0.000 ( 0.010 ms): :258487/258487 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), config: 0xa00000000, disabled: 1, { bp_len, config2 }: 0x900000000, branch_sample_type: USER|COUNTERS, sample_regs_user: 0x3f1b7ffffffff, sample_stack_user: 258487, clockid: -599052088, sample_regs_intr: 0x60a000003eb, sample_max_stack: 14, sig_data: 120259084288 }, cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
0.016 ( 0.002 ms): :258487/258487 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), config: 0x400000000, disabled: 1, { bp_len, config2 }: 0x900000000, branch_sample_type: USER|COUNTERS, sample_regs_user: 0x3f1b7ffffffff, sample_stack_user: 258487, clockid: -599044082, sample_regs_intr: 0x60a000003eb, sample_max_stack: 14, sig_data: 120259084288 }, cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 4
1.838 ( 0.006 ms): perf/258487 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0xa00000001, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258488 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 5
1.846 ( 0.002 ms): perf/258487 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x400000001, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258488 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 6
1.849 ( 0.002 ms): perf/258487 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0xa00000003, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258488 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 7
1.851 ( 0.002 ms): perf/258487 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x400000003, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258488 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 9
1.853 ( 0.600 ms): perf/258487 perf_event_open(attr_uptr: { type: 2 (tracepoint), size: 136, config: 0x190 (syscalls:sys_enter_nanosleep), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258488 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 10
2.456 ( 0.016 ms): perf/258487 perf_event_open(attr_uptr: { type: 2 (tracepoint), size: 136, config: 0x196 (syscalls:sys_enter_clock_nanosleep), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258488 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 11
Performance counter stats for 'sleep 1.23456789':
1,402,839 cpu_atom/instructions/
<not counted> cpu_core/instructions/ (0.00%)
11,066 cpu_atom/cache-misses/
<not counted> cpu_core/cache-misses/ (0.00%)
0 syscalls:sys_enter_nanosleep
1 syscalls:sys_enter_clock_nanosleep
1.236246714 seconds time elapsed
0.000000000 seconds user
0.001308000 seconds sys
root@number:~#
Now if we use it even for the ones we have a specific beautifier in
tools/perf/trace/beauty, i.e. use btf_struct_scnprintf() for all
structs, by adding the following patch:
@@ -2316,7 +2316,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
default_scnprintf = sc->arg_fmt[arg.idx].scnprintf;
- if (default_scnprintf == NULL || default_scnprintf == SCA_PTR) {
+ if (1 || (default_scnprintf == NULL || default_scnprintf == SCA_PTR)) {
btf_printed = trace__btf_scnprintf(trace, &arg, bf + printed,
size - printed, val, field->type);
if (btf_printed) {
We get:
root@number:~# perf trace -e connect,sendto ping -c 1 www.google.com
PING www.google.com (142.251.129.68) 56(84) bytes of data.
0.000 ( 0.015 ms): ping/283259 connect(fd: 5, uservaddr: (struct sockaddr){.sa_family = (sa_family_t)1,(union){.sa_data_min = (char[14])['/','r','u','n','/','s','y','s','t','e','m','d','/','r',],},}, addrlen: 42) = 0
0.046 ( 0.004 ms): ping/283259 sendto(fd: 5, buff: 0x559b008ae980, len: 97, flags: DONTWAIT|NOSIGNAL) = 97
0.353 ( 0.012 ms): ping/283259 sendto(fd: 5, buff: 0x7ffc01294960, len: 20, addr: (struct sockaddr){.sa_family = (sa_family_t)16,}, addr_len: 0xc) = 20
0.377 ( 0.006 ms): ping/283259 connect(fd: 5, uservaddr: (struct sockaddr){.sa_family = (sa_family_t)2,}, addrlen: 16) = 0
0.388 ( 0.010 ms): ping/283259 connect(fd: 5, uservaddr: (struct sockaddr){.sa_family = (sa_family_t)10,}, addrlen: 28) = 0
0.402 ( 0.001 ms): ping/283259 connect(fd: 5, uservaddr: (struct sockaddr){.sa_family = (sa_family_t)2,(union){.sa_data_min = (char[14])[4,1,142,251,129,'D',],},}, addrlen: 16) = 0
0.425 ( 0.045 ms): ping/283259 sendto(fd: 3, buff: 0x559b008a8ac0, len: 64, addr: (struct sockaddr){.sa_family = (sa_family_t)2,}, addr_len: 0x10) = 64
64 bytes from rio07s07-in-f4.1e100.net (142.251.129.68): icmp_seq=1 ttl=49 time=44.1 ms
--- www.google.com ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 44.113/44.113/44.113/0.000 ms
44.849 ( 0.038 ms): ping/283259 connect(fd: 5, uservaddr: (struct sockaddr){.sa_family = (sa_family_t)1,(union){.sa_data_min = (char[14])['/','r','u','n','/','s','y','s','t','e','m','d','/','r',],},}, addrlen: 42) = 0
44.927 ( 0.006 ms): ping/283259 sendto(fd: 5, buff: 0x559b008b03d0, len: 110, flags: DONTWAIT|NOSIGNAL) = 110
root@number:~#
Which looks sane, i.e.:
18.800 ( 0.004 ms): ping/258481 connect(fd: 5, uservaddr: { .family: INET, port: 0, addr: 142.251.129.68 }, addrlen: 16) = 0
Becomes:
0.402 ( 0.001 ms): ping/283259 connect(fd: 5, uservaddr: (struct sockaddr){.sa_family = (sa_family_t)2,(union){.sa_data_min = (char[14])[4,1,142,251,129,'D',],},}, addrlen: 16) = 0
And.
#define AF_UNIX 1 /* Unix domain sockets */
#define AF_LOCAL 1 /* POSIX name for AF_UNIX */
#define AF_INET 2 /* Internet IP Protocol */
<SNIP>
#define AF_INET6 10 /* IP version 6 */
And 'D' == 68, so the preexisting sockaddr BPF collector is working with
the new generic BTF pretty printer (btf_struct_scnprintf()), its just
that it doesn't know about 'struct sockaddr' besides what is in BTF,
i.e. its an array of bytes, not an IPv4 address that needs extra
massaging.
Ditto for the 'struct perf_event_attr' case:
1.851 ( 0.002 ms): perf/258487 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x400000003, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258488 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 9
Becomes:
2.081 ( 0.002 ms): :283304/283304 perf_event_open(attr_uptr: (struct perf_event_attr){.size = (__u32)136,.config = (__u64)17179869187,.sample_type = (__u64)65536,.read_format = (__u64)3,.disabled = (__u64)0x1,.inherit = (__u64)0x1,.enable_on_exec = (__u64)0x1,.exclude_guest = (__u64)0x1,}, pid: 283305 (sleep), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 9
hex(17179869187) = 0x400000003, etc.
read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING is
enum perf_event_read_format {
PERF_FORMAT_TOTAL_TIME_ENABLED = 1U << 0,
PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1,
and so on.
We need to work with the libbpf btf dump api to get one output that
matches the 'perf trace'/strace expectations/format, but having this in
this current form is already an improvement to 'perf trace', so lets
improve from what we have.
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240815013626.935097-7-howardchu95@gmail.com
Link: https://lore.kernel.org/r/20240824163322.60796-5-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Howard Chu
|
7f40306728 |
perf trace: Add trace__bpf_sys_enter_beauty_map() to prepare for fetching data in BPF
Set up beauty_map, load it to BPF, in such format: if argument No.3 is a
struct of size 32 bytes (of syscall number 114) beauty_map[114][2] = 32;
if argument No.3 is a string (of syscall number 114) beauty_map[114][2] =
1;
if argument No.3 is a buffer, its size is indicated by argument No.4 (of
syscall number 114) beauty_map[114][2] = -4; /* -1 ~ -6, we'll read this
buffer size in BPF */
Committer notes:
Moved syscall_arg_fmt__cache_btf_struct() from a ifdef
HAVE_LIBBPF_SUPPORT to closer to where it is used, that is ifdef'ed on
HAVE_BPF_SKEL and thus breaks the build when building with
BUILD_BPF_SKEL=0, as detected using 'make -C tools/perf build-test'.
Also add 'struct beauty_map_enter' to tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
as we're using it in this patch, otherwise we get this while trying to
build at this point in the original patch series:
builtin-trace.c: In function ‘trace__init_syscalls_bpf_prog_array_maps’:
builtin-trace.c:3725:58: error: ‘struct <anonymous>’ has no member named ‘beauty_map_enter’
3725 | int beauty_map_fd = bpf_map__fd(trace->skel->maps.beauty_map_enter);
|
We also have to take into account syscall_arg_fmt.from_user when telling
the kernel what to copy in the sys_enter generic collector, we don't
want to collect bogus data in buffers that will only be available to us
at sys_exit time, i.e. after the kernel has filled it, so leave this for
when we have such a sys_exit based collector.
Committer testing:
Not wired up yet, so all continues to work, using the existing BPF
collector and userspace beautifiers that are augmentation aware:
root@number:~# rm -f 987654 ; touch 123456 ; perf trace -e rename* mv 123456 987654
0.000 ( 0.031 ms): mv/20888 renameat2(olddfd: CWD, oldname: "123456", newdfd: CWD, newname: "987654", flags: NOREPLACE) = 0
root@number:~# perf trace -e connect,sendto ping -c 1 www.google.com
0.000 ( 0.014 ms): ping/20892 connect(fd: 5, uservaddr: { .family: LOCAL, path: /run/systemd/resolve/io.systemd.Resolve }, addrlen: 42) = 0
0.040 ( 0.003 ms): ping/20892 sendto(fd: 5, buff: 0x560b4ff17980, len: 97, flags: DONTWAIT|NOSIGNAL) = 97
0.480 ( 0.017 ms): ping/20892 sendto(fd: 5, buff: 0x7ffd82d07150, len: 20, addr: { .family: NETLINK }, addr_len: 0xc) = 20
0.526 ( 0.014 ms): ping/20892 connect(fd: 5, uservaddr: { .family: INET6, port: 0, addr: 2800:3f0:4004:810::2004 }, addrlen: 28) = 0
0.542 ( 0.002 ms): ping/20892 connect(fd: 5, uservaddr: { .family: UNSPEC }, addrlen: 16) = 0
0.544 ( 0.004 ms): ping/20892 connect(fd: 5, uservaddr: { .family: INET, port: 0, addr: 142.251.135.100 }, addrlen: 16) = 0
0.559 ( 0.002 ms): ping/20892 connect(fd: 5, uservaddr: { .family: INET, port: 1025, addr: 142.251.135.100 }, addrlen: 16PING www.google.com (142.251.135.100) 56(84) bytes of data.
) = 0
0.589 ( 0.058 ms): ping/20892 sendto(fd: 3, buff: 0x560b4ff11ac0, len: 64, addr: { .family: INET, port: 0, addr: 142.251.135.100 }, addr_len: 0x10) = 64
45.250 ( 0.029 ms): ping/20892 connect(fd: 5, uservaddr: { .family: LOCAL, path: /run/systemd/resolve/io.systemd.Resolve }, addrlen: 42) = 0
45.344 ( 0.012 ms): ping/20892 sendto(fd: 5, buff: 0x560b4ff19340, len: 111, flags: DONTWAIT|NOSIGNAL) = 111
64 bytes from rio09s08-in-f4.1e100.net (142.251.135.100): icmp_seq=1 ttl=49 time=44.4 ms
--- www.google.com ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 44.361/44.361/44.361/0.000 ms
root@number:~#
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240815013626.935097-4-howardchu95@gmail.com
Link: https://lore.kernel.org/r/20240824163322.60796-3-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
d92f490cba |
perf trace: Mark bpf's attr as from_user
This one has no specific pretty printer right now, so will be handled by the generic BTF based one later in this patch series. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
c790f2bafb |
perf trace: Introduce SCA_TIMESPEC_FROM_USER() to set .from_user = true
Paving the way for the generic BPF BTF based syscall arg augmenter. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
be14a71984 |
perf trace: Introduce SCA_SOCKADDR_FROM_USER() to set .from_user = true
Paving the way for the generic BPF BTF based syscall arg augmenter. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
690eda6508 |
perf trace: Introduce SCA_PERF_ATTR_FROM_USER() to set .from_user = true
Paving the way for the generic BPF BTF based syscall arg augmenter. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
2f2e439ba5 |
perf trace: Mark which syscall arguments go from user space to kernel space
We need to know where to collect it in the BPF augmenters, if in the sys_enter hook or in the sys_exit hook. Start with the SCA_FILENAME one, that is just from user to kernel space. The alternative, better, but takes a bit more time than I have now, is to use the __user information that is already in the syscall args and encoded in BTF via a tag, do it later. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
7bedcbaefd |
perf trace: Pass the richer 'struct syscall_arg' pointer to trace__btf_scnprintf()
Since we'll need it later in the current patch series and we can get the syscall_arg_fmt from syscall_arg->fmt. Based-on-a-patch-by: Howard Chu <howardchu95@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/Zsd8vqCrTh5h69rp@x1 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
Ian Rogers
|
30f29bae91 |
perf tool: Constify tool pointers
The tool pointer (to a struct largely of function pointers) is passed around but is unchanged except at initialization. Change parameter and variable types to be const to lower the possibilities of what could happen with a tool. Reviewed-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Leo Yan <leo.yan@arm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ilkka Koskinen <ilkka@os.amperecomputing.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Jonathan Cameron <jonathan.cameron@huawei.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Nick Terrell <terrelln@fb.com> Cc: Oliver Upton <oliver.upton@linux.dev> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <song@kernel.org> Cc: Sun Haiyong <sunhaiyong@loongson.cn> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Yanteng Si <siyanteng@loongson.cn> Cc: Yicong Yang <yangyicong@hisilicon.com> Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20240812204720.631678-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
Namhyung Kim
|
966854e72f |
perf bpf-filter: Pass 'target' to perf_bpf_filter__prepare()
This is needed to prepare target-specific actions in the later patch. We want to reuse the pinned BPF program and map for regular users to profile their own processes. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: KP Singh <kpsingh@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <song@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20240703223035.2024586-3-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
c3d747134c |
perf trace: Remove arg_fmt->is_enum, we can get that from the BTF type
This is to pave the way for other BTF types, i.e. we try to find BTF type then use things like btf_is_enum(btf_type) that we cached to find the right strtoul and scnprintf routines. For now only enum is supported, all the other types simple return zero for scnprintf which makes it have the same behaviour as when BTF isn't available, i.e. fallback to no pretty printing. Ditto for strtoul. root@x1:~# perf test -v enum 124: perf trace enum augmentation tests : Ok root@x1:~# perf test -v enum 124: perf trace enum augmentation tests : Ok root@x1:~# perf test -v enum 124: perf trace enum augmentation tests : Ok root@x1:~# perf test -v enum 124: perf trace enum augmentation tests : Ok root@x1:~# perf test -v enum 124: perf trace enum augmentation tests : Ok root@x1:~# Signed-off-by: Howard Chu <howardchu95@gmail.com> Tested-by: Howard Chu <howardchu95@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240624181345.124764-9-howardchu95@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
62284329b1 |
perf trace: Introduce trace__btf_scnprintf()
To have a central place that will look at the BTF type and call the right scnprintf routine or return zero, meaning BTF pretty printing isn't available or not implemented for a specific type. Signed-off-by: Howard Chu <howardchu95@gmail.com> Tested-by: Howard Chu <howardchu95@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240624181345.124764-8-howardchu95@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Howard Chu
|
9558658886 |
perf trace: Filter enum arguments with enum names
Before:
perf $ ./perf trace -e timer:hrtimer_start --filter='mode!=HRTIMER_MODE_ABS_PINNED_HARD' --max-events=1
No resolver (strtoul) for "mode" in "timer:hrtimer_start", can't set filter "(mode!=HRTIMER_MODE_ABS_PINNED_HARD) && (common_pid != 281988)"
After:
perf $ ./perf trace -e timer:hrtimer_start --filter='mode!=HRTIMER_MODE_ABS_PINNED_HARD' --max-events=1
0.000 :0/0 timer:hrtimer_start(hrtimer: 0xffff9498a6ca5f18, function: 0xffffffffa77a5be0, expires: 12351248764875, softexpires: 12351248764875, mode: HRTIMER_MODE_ABS)
&& and ||:
perf $ ./perf trace -e timer:hrtimer_start --filter='mode != HRTIMER_MODE_ABS_PINNED_HARD && mode != HRTIMER_MODE_ABS' --max-events=1
0.000 Hyprland/534 timer:hrtimer_start(hrtimer: 0xffff9497801a84d0, function: 0xffffffffc04cdbe0, expires: 12639434638458, softexpires: 12639433638458, mode: HRTIMER_MODE_REL)
perf $ ./perf trace -e timer:hrtimer_start --filter='mode == HRTIMER_MODE_REL || mode == HRTIMER_MODE_PINNED' --max-events=1
0.000 ldlck-test/60639 timer:hrtimer_start(hrtimer: 0xffffb16404ee7bf8, function: 0xffffffffa7790420, expires: 12772614418016, softexpires: 12772614368016, mode: HRTIMER_MODE_REL)
Switching it up, using both enum name and integer value(--filter='mode == HRTIMER_MODE_ABS_PINNED_HARD || mode == 0'):
perf $ ./perf trace -e timer:hrtimer_start --filter='mode == HRTIMER_MODE_ABS_PINNED_HARD || mode == 0' --max-events=3
0.000 :0/0 timer:hrtimer_start(hrtimer: 0xffff9498a6ca5f18, function: 0xffffffffa77a5be0, expires: 12601748739825, softexpires: 12601748739825, mode: HRTIMER_MODE_ABS_PINNED_HARD)
0.036 :0/0 timer:hrtimer_start(hrtimer: 0xffff9498a6ca5f18, function: 0xffffffffa77a5be0, expires: 12518758748124, softexpires: 12518758748124, mode: HRTIMER_MODE_ABS_PINNED_HARD)
0.172 tmux: server/41881 timer:hrtimer_start(hrtimer: 0xffffb164081e7838, function: 0xffffffffa7790420, expires: 12518768255836, softexpires: 12518768205836, mode: HRTIMER_MODE_ABS)
P.S.
perf $ pahole hrtimer_mode
enum hrtimer_mode {
HRTIMER_MODE_ABS = 0,
HRTIMER_MODE_REL = 1,
HRTIMER_MODE_PINNED = 2,
HRTIMER_MODE_SOFT = 4,
HRTIMER_MODE_HARD = 8,
HRTIMER_MODE_ABS_PINNED = 2,
HRTIMER_MODE_REL_PINNED = 3,
HRTIMER_MODE_ABS_SOFT = 4,
HRTIMER_MODE_REL_SOFT = 5,
HRTIMER_MODE_ABS_PINNED_SOFT = 6,
HRTIMER_MODE_REL_PINNED_SOFT = 7,
HRTIMER_MODE_ABS_HARD = 8,
HRTIMER_MODE_REL_HARD = 9,
HRTIMER_MODE_ABS_PINNED_HARD = 10,
HRTIMER_MODE_REL_PINNED_HARD = 11,
};
Committer testing:
root@x1:~# perf trace -e timer:hrtimer_start --filter='mode != HRTIMER_MODE_ABS' --max-events=2
0.000 :0/0 timer:hrtimer_start(hrtimer: 0xffff8d4eff2a5050, function: 0xffffffff9e22ddd0, expires: 241502326000000, softexpires: 241502326000000, mode: HRTIMER_MODE_ABS_PINNED_HARD)
18446744073709.488 :0/0 timer:hrtimer_start(hrtimer: 0xffff8d4eff425050, function: 0xffffffff9e22ddd0, expires: 241501814000000, softexpires: 241501814000000, mode: HRTIMER_MODE_ABS_PINNED_HARD)
root@x1:~# perf trace -e timer:hrtimer_start --filter='mode != HRTIMER_MODE_ABS && mode != HRTIMER_MODE_ABS_PINNED_HARD' --max-events=2
0.000 podman/510644 timer:hrtimer_start(hrtimer: 0xffffa2024f5f7dd0, function: 0xffffffff9e2170c0, expires: 241530497418194, softexpires: 241530497368194, mode: HRTIMER_MODE_REL)
40.251 gnome-shell/2484 timer:hrtimer_start(hrtimer: 0xffff8d48bda17650, function: 0xffffffffc0661550, expires: 241550528619247, softexpires: 241550527619247, mode: HRTIMER_MODE_REL)
root@x1:~# perf trace -v -e timer:hrtimer_start --filter='mode != HRTIMER_MODE_ABS && mode != HRTIMER_MODE_ABS_PINNED_HARD && mode != HRTIMER_MODE_REL' --max-events=2
Using CPUID GenuineIntel-6-BA-3
vmlinux BTF loaded
<SNIP>
0
0xa
0x1
New filter for timer:hrtimer_start: (mode != 0 && mode != 0xa && mode != 0x1) && (common_pid != 524049 && common_pid != 4041)
mmap size 528384B
^Croot@x1:~#
Suggested-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/ZnCcliuecJABD5FN@x1
Link: https://lore.kernel.org/r/20240624181345.124764-5-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Howard Chu
|
607bbdb49c |
perf trace: Augment non-syscall tracepoints with enum arguments with BTF
Before:
perf $ ./perf trace -e timer:hrtimer_start --max-events=1
0.000 :0/0 timer:hrtimer_start(hrtimer: 0xffff974466c25f18, function: 0xffffffff89da5be0, expires: 377432432256753, softexpires: 377432432256753, mode: 10)
After:
perf $ ./perf trace -e timer:hrtimer_start --max-events=1
0.000 :0/0 timer:hrtimer_start(hrtimer: 0xffff9498a6ca5f18, function: 0xffffffffa77a5be0, expires: 4382442895089, softexpires: 4382442895089, mode: HRTIMER_MODE_ABS_PINNED_HARD)
in which HRTIMER_MODE_ABS_PINNED_HARD is:
perf $ pahole hrtimer_mode
enum hrtimer_mode {
HRTIMER_MODE_ABS = 0,
HRTIMER_MODE_REL = 1,
HRTIMER_MODE_PINNED = 2,
HRTIMER_MODE_SOFT = 4,
HRTIMER_MODE_HARD = 8,
HRTIMER_MODE_ABS_PINNED = 2,
HRTIMER_MODE_REL_PINNED = 3,
HRTIMER_MODE_ABS_SOFT = 4,
HRTIMER_MODE_REL_SOFT = 5,
HRTIMER_MODE_ABS_PINNED_SOFT = 6,
HRTIMER_MODE_REL_PINNED_SOFT = 7,
HRTIMER_MODE_ABS_HARD = 8,
HRTIMER_MODE_REL_HARD = 9,
HRTIMER_MODE_ABS_PINNED_HARD = 10,
HRTIMER_MODE_REL_PINNED_HARD = 11,
};
Can also be tested by
./perf trace -e pagemap:mm_lru_insertion,timer:hrtimer_start,timer:hrtimer_init,skb:kfree_skb --max-events=10
(Chose these 4 events because they happen quite frequently.)
However some enum arguments may not be contained in vmlinux BTF. To see
what enum arguments are supported, use:
vmlinux_dir $ bpftool btf dump file /sys/kernel/btf/vmlinux > vmlinux
vmlinux_dir $ while read l; do grep "ENUM '$l'" vmlinux; done < <(grep field:enum /sys/kernel/tracing/events/*/*/format | awk '{print $3}' | sort | uniq) | awk '{print $3}' | sed "s/'\(.*\)'/\1/g"
dev_pm_qos_req_type
error_detector
hrtimer_mode
i2c_slave_event
ieee80211_bss_type
lru_list
migrate_mode
nl80211_auth_type
nl80211_band
nl80211_iftype
numa_vmaskip_reason
pm_qos_req_action
pwm_polarity
skb_drop_reason
thermal_trip_type
xen_lazy_mode
xen_mc_extend_args
xen_mc_flush_reason
zone_type
And what tracepoints have these enum types as their arguments:
vmlinux_dir $ while read l; do grep "ENUM '$l'" vmlinux; done < <(grep field:enum /sys/kernel/tracing/events/*/*/format | awk '{print $3}' | sort | uniq) | awk '{print $3}' | sed "s/'\(.*\)'/\1/g" > good_enums
vmlinux_dir $ cat good_enums
dev_pm_qos_req_type
error_detector
hrtimer_mode
i2c_slave_event
ieee80211_bss_type
lru_list
migrate_mode
nl80211_auth_type
nl80211_band
nl80211_iftype
numa_vmaskip_reason
pm_qos_req_action
pwm_polarity
skb_drop_reason
thermal_trip_type
xen_lazy_mode
xen_mc_extend_args
xen_mc_flush_reason
zone_type
vmlinux_dir $ grep -f good_enums -l /sys/kernel/tracing/events/*/*/format
/sys/kernel/tracing/events/cfg80211/cfg80211_chandef_dfs_required/format
/sys/kernel/tracing/events/cfg80211/cfg80211_ch_switch_notify/format
/sys/kernel/tracing/events/cfg80211/cfg80211_ch_switch_started_notify/format
/sys/kernel/tracing/events/cfg80211/cfg80211_get_bss/format
/sys/kernel/tracing/events/cfg80211/cfg80211_ibss_joined/format
/sys/kernel/tracing/events/cfg80211/cfg80211_inform_bss_frame/format
/sys/kernel/tracing/events/cfg80211/cfg80211_radar_event/format
/sys/kernel/tracing/events/cfg80211/cfg80211_ready_on_channel_expired/format
/sys/kernel/tracing/events/cfg80211/cfg80211_ready_on_channel/format
/sys/kernel/tracing/events/cfg80211/cfg80211_reg_can_beacon/format
/sys/kernel/tracing/events/cfg80211/cfg80211_return_bss/format
/sys/kernel/tracing/events/cfg80211/cfg80211_tx_mgmt_expired/format
/sys/kernel/tracing/events/cfg80211/rdev_add_virtual_intf/format
/sys/kernel/tracing/events/cfg80211/rdev_auth/format
/sys/kernel/tracing/events/cfg80211/rdev_change_virtual_intf/format
/sys/kernel/tracing/events/cfg80211/rdev_channel_switch/format
/sys/kernel/tracing/events/cfg80211/rdev_connect/format
/sys/kernel/tracing/events/cfg80211/rdev_inform_bss/format
/sys/kernel/tracing/events/cfg80211/rdev_libertas_set_mesh_channel/format
/sys/kernel/tracing/events/cfg80211/rdev_mgmt_tx/format
/sys/kernel/tracing/events/cfg80211/rdev_remain_on_channel/format
/sys/kernel/tracing/events/cfg80211/rdev_return_chandef/format
/sys/kernel/tracing/events/cfg80211/rdev_return_int_survey_info/format
/sys/kernel/tracing/events/cfg80211/rdev_set_ap_chanwidth/format
/sys/kernel/tracing/events/cfg80211/rdev_set_monitor_channel/format
/sys/kernel/tracing/events/cfg80211/rdev_set_radar_background/format
/sys/kernel/tracing/events/cfg80211/rdev_start_ap/format
/sys/kernel/tracing/events/cfg80211/rdev_start_radar_detection/format
/sys/kernel/tracing/events/cfg80211/rdev_tdls_channel_switch/format
/sys/kernel/tracing/events/compaction/mm_compaction_defer_compaction/format
/sys/kernel/tracing/events/compaction/mm_compaction_deferred/format
/sys/kernel/tracing/events/compaction/mm_compaction_defer_reset/format
/sys/kernel/tracing/events/compaction/mm_compaction_finished/format
/sys/kernel/tracing/events/compaction/mm_compaction_kcompactd_wake/format
/sys/kernel/tracing/events/compaction/mm_compaction_suitable/format
/sys/kernel/tracing/events/compaction/mm_compaction_wakeup_kcompactd/format
/sys/kernel/tracing/events/error_report/error_report_end/format
/sys/kernel/tracing/events/i2c_slave/i2c_slave/format
/sys/kernel/tracing/events/migrate/mm_migrate_pages/format
/sys/kernel/tracing/events/migrate/mm_migrate_pages_start/format
/sys/kernel/tracing/events/pagemap/mm_lru_insertion/format
/sys/kernel/tracing/events/power/dev_pm_qos_add_request/format
/sys/kernel/tracing/events/power/dev_pm_qos_remove_request/format
/sys/kernel/tracing/events/power/dev_pm_qos_update_request/format
/sys/kernel/tracing/events/power/pm_qos_update_flags/format
/sys/kernel/tracing/events/power/pm_qos_update_target/format
/sys/kernel/tracing/events/pwm/pwm_apply/format
/sys/kernel/tracing/events/pwm/pwm_get/format
/sys/kernel/tracing/events/sched/sched_skip_vma_numa/format
/sys/kernel/tracing/events/skb/kfree_skb/format
/sys/kernel/tracing/events/thermal/thermal_zone_trip/format
/sys/kernel/tracing/events/timer/hrtimer_init/format
/sys/kernel/tracing/events/timer/hrtimer_start/format
/sys/kernel/tracing/events/xen/xen_mc_batch/format
/sys/kernel/tracing/events/xen/xen_mc_extend_args/format
/sys/kernel/tracing/events/xen/xen_mc_flush_reason/format
/sys/kernel/tracing/events/xen/xen_mc_issue/format
Committer testing:
root@x1:~# perf trace -e timer:hrtimer_start --max-events=2
0.000 :0/0 timer:hrtimer_start(hrtimer: 0xffff8d4eff225050, function: 0xffffffff9e22ddd0, expires: 241152380000000, softexpires: 241152380000000, mode: HRTIMER_MODE_ABS)
0.028 :0/0 timer:hrtimer_start(hrtimer: 0xffff8d4eff225050, function: 0xffffffff9e22ddd0, expires: 241153654000000, softexpires: 241153654000000, mode: HRTIMER_MODE_ABS_PINNED_HARD)
root@x1:~#
Suggested-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Reviewed-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/20240615032743.112750-1-howardchu95@gmail.com
Link: https://lore.kernel.org/r/20240624181345.124764-4-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Howard Chu
|
45a0c928e7 |
perf trace: BTF-based enum pretty printing for syscall args
In this patch, BTF is used to turn enum value to the corresponding
name. There is only one system call that uses enum value as its
argument, that is `landlock_add_rule()`.
The vmlinux btf is loaded lazily, when user decided to trace the
`landlock_add_rule` syscall. But if one decide to run `perf trace`
without any arguments, the behaviour is to trace `landlock_add_rule`,
so vmlinux btf will be loaded by default.
The laziest behaviour is to load vmlinux btf when a
`landlock_add_rule` syscall hits. But I think you could lose some
samples when loading vmlinux btf at run time, for it can delay the
handling of other samples. I might need your precious opinions on
this...
before:
```
perf $ ./perf trace -e landlock_add_rule
0.000 ( 0.008 ms): ldlck-test/438194 landlock_add_rule(rule_type: 2) = -1 EBADFD (File descriptor in bad state)
0.010 ( 0.001 ms): ldlck-test/438194 landlock_add_rule(rule_type: 1) = -1 EBADFD (File descriptor in bad state)
```
after:
```
perf $ ./perf trace -e landlock_add_rule
0.000 ( 0.029 ms): ldlck-test/438194 landlock_add_rule(rule_type: LANDLOCK_RULE_NET_PORT) = -1 EBADFD (File descriptor in bad state)
0.036 ( 0.004 ms): ldlck-test/438194 landlock_add_rule(rule_type: LANDLOCK_RULE_PATH_BENEATH) = -1 EBADFD (File descriptor in bad state)
```
Committer notes:
Made it build with NO_LIBBPF=1, simplified btf_enum_fprintf(), see [1]
for the discussion.
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Günther Noack <gnoack@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mickaël Salaün <mic@digikod.net>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/20240613022757.3589783-1-howardchu95@gmail.com
Link: https://lore.kernel.org/lkml/ZnXAhFflUl_LV1QY@x1 # [1]
Link: https://lore.kernel.org/r/20240624181345.124764-3-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Howard Chu
|
7a2fb5619c |
perf trace: Fix iteration of syscall ids in syscalltbl->entries
This is a bug found when implementing pretty-printing for the
landlock_add_rule system call, I decided to send this patch separately
because this is a serious bug that should be fixed fast.
I wrote a test program to do landlock_add_rule syscall in a loop,
yet perf trace -e landlock_add_rule freezes, giving no output.
This bug is introduced by the false understanding of the variable "key"
below:
```
for (key = 0; key < trace->sctbl->syscalls.nr_entries; ++key) {
struct syscall *sc = trace__syscall_info(trace, NULL, key);
...
}
```
The code above seems right at the beginning, but when looking at
syscalltbl.c, I found these lines:
```
for (i = 0; i <= syscalltbl_native_max_id; ++i)
if (syscalltbl_native[i])
++nr_entries;
entries = tbl->syscalls.entries = malloc(sizeof(struct syscall) * nr_entries);
...
for (i = 0, j = 0; i <= syscalltbl_native_max_id; ++i) {
if (syscalltbl_native[i]) {
entries[j].name = syscalltbl_native[i];
entries[j].id = i;
++j;
}
}
```
meaning the key is merely an index to traverse the syscall table,
instead of the actual syscall id for this particular syscall.
So if one uses key to do trace__syscall_info(trace, NULL, key), because
key only goes up to trace->sctbl->syscalls.nr_entries, for example, on
my X86_64 machine, this number is 373, it will end up neglecting all
the rest of the syscall, in my case, everything after `rseq`, because
the traversal will stop at 373, and `rseq` is the last syscall whose id
is lower than 373
in tools/perf/arch/x86/include/generated/asm/syscalls_64.c:
```
...
[334] = "rseq",
[424] = "pidfd_send_signal",
...
```
The reason why the key is scrambled but perf trace works well is that
key is used in trace__syscall_info(trace, NULL, key) to do
trace->syscalls.table[id], this makes sure that the struct syscall returned
actually has an id the same value as key, making the later bpf_prog
matching all correct.
After fixing this bug, I can do perf trace on 38 more syscalls, and
because more syscalls are visible, we get 8 more syscalls that can be
augmented.
before:
perf $ perf trace -vv --max-events=1 |& grep Reusing
Reusing "open" BPF sys_enter augmenter for "stat"
Reusing "open" BPF sys_enter augmenter for "lstat"
Reusing "open" BPF sys_enter augmenter for "access"
Reusing "connect" BPF sys_enter augmenter for "accept"
Reusing "sendto" BPF sys_enter augmenter for "recvfrom"
Reusing "connect" BPF sys_enter augmenter for "bind"
Reusing "connect" BPF sys_enter augmenter for "getsockname"
Reusing "connect" BPF sys_enter augmenter for "getpeername"
Reusing "open" BPF sys_enter augmenter for "execve"
Reusing "open" BPF sys_enter augmenter for "truncate"
Reusing "open" BPF sys_enter augmenter for "chdir"
Reusing "open" BPF sys_enter augmenter for "mkdir"
Reusing "open" BPF sys_enter augmenter for "rmdir"
Reusing "open" BPF sys_enter augmenter for "creat"
Reusing "open" BPF sys_enter augmenter for "link"
Reusing "open" BPF sys_enter augmenter for "unlink"
Reusing "open" BPF sys_enter augmenter for "symlink"
Reusing "open" BPF sys_enter augmenter for "readlink"
Reusing "open" BPF sys_enter augmenter for "chmod"
Reusing "open" BPF sys_enter augmenter for "chown"
Reusing "open" BPF sys_enter augmenter for "lchown"
Reusing "open" BPF sys_enter augmenter for "mknod"
Reusing "open" BPF sys_enter augmenter for "statfs"
Reusing "open" BPF sys_enter augmenter for "pivot_root"
Reusing "open" BPF sys_enter augmenter for "chroot"
Reusing "open" BPF sys_enter augmenter for "acct"
Reusing "open" BPF sys_enter augmenter for "swapon"
Reusing "open" BPF sys_enter augmenter for "swapoff"
Reusing "open" BPF sys_enter augmenter for "delete_module"
Reusing "open" BPF sys_enter augmenter for "setxattr"
Reusing "open" BPF sys_enter augmenter for "lsetxattr"
Reusing "openat" BPF sys_enter augmenter for "fsetxattr"
Reusing "open" BPF sys_enter augmenter for "getxattr"
Reusing "open" BPF sys_enter augmenter for "lgetxattr"
Reusing "openat" BPF sys_enter augmenter for "fgetxattr"
Reusing "open" BPF sys_enter augmenter for "listxattr"
Reusing "open" BPF sys_enter augmenter for "llistxattr"
Reusing "open" BPF sys_enter augmenter for "removexattr"
Reusing "open" BPF sys_enter augmenter for "lremovexattr"
Reusing "fsetxattr" BPF sys_enter augmenter for "fremovexattr"
Reusing "open" BPF sys_enter augmenter for "mq_open"
Reusing "open" BPF sys_enter augmenter for "mq_unlink"
Reusing "fsetxattr" BPF sys_enter augmenter for "add_key"
Reusing "fremovexattr" BPF sys_enter augmenter for "request_key"
Reusing "fremovexattr" BPF sys_enter augmenter for "inotify_add_watch"
Reusing "fremovexattr" BPF sys_enter augmenter for "mkdirat"
Reusing "fremovexattr" BPF sys_enter augmenter for "mknodat"
Reusing "fremovexattr" BPF sys_enter augmenter for "fchownat"
Reusing "fremovexattr" BPF sys_enter augmenter for "futimesat"
Reusing "fremovexattr" BPF sys_enter augmenter for "newfstatat"
Reusing "fremovexattr" BPF sys_enter augmenter for "unlinkat"
Reusing "fremovexattr" BPF sys_enter augmenter for "linkat"
Reusing "open" BPF sys_enter augmenter for "symlinkat"
Reusing "fremovexattr" BPF sys_enter augmenter for "readlinkat"
Reusing "fremovexattr" BPF sys_enter augmenter for "fchmodat"
Reusing "fremovexattr" BPF sys_enter augmenter for "faccessat"
Reusing "fremovexattr" BPF sys_enter augmenter for "utimensat"
Reusing "connect" BPF sys_enter augmenter for "accept4"
Reusing "fremovexattr" BPF sys_enter augmenter for "name_to_handle_at"
Reusing "fremovexattr" BPF sys_enter augmenter for "renameat2"
Reusing "open" BPF sys_enter augmenter for "memfd_create"
Reusing "fremovexattr" BPF sys_enter augmenter for "execveat"
Reusing "fremovexattr" BPF sys_enter augmenter for "statx"
after
perf $ perf trace -vv --max-events=1 |& grep Reusing
Reusing "open" BPF sys_enter augmenter for "stat"
Reusing "open" BPF sys_enter augmenter for "lstat"
Reusing "open" BPF sys_enter augmenter for "access"
Reusing "connect" BPF sys_enter augmenter for "accept"
Reusing "sendto" BPF sys_enter augmenter for "recvfrom"
Reusing "connect" BPF sys_enter augmenter for "bind"
Reusing "connect" BPF sys_enter augmenter for "getsockname"
Reusing "connect" BPF sys_enter augmenter for "getpeername"
Reusing "open" BPF sys_enter augmenter for "execve"
Reusing "open" BPF sys_enter augmenter for "truncate"
Reusing "open" BPF sys_enter augmenter for "chdir"
Reusing "open" BPF sys_enter augmenter for "mkdir"
Reusing "open" BPF sys_enter augmenter for "rmdir"
Reusing "open" BPF sys_enter augmenter for "creat"
Reusing "open" BPF sys_enter augmenter for "link"
Reusing "open" BPF sys_enter augmenter for "unlink"
Reusing "open" BPF sys_enter augmenter for "symlink"
Reusing "open" BPF sys_enter augmenter for "readlink"
Reusing "open" BPF sys_enter augmenter for "chmod"
Reusing "open" BPF sys_enter augmenter for "chown"
Reusing "open" BPF sys_enter augmenter for "lchown"
Reusing "open" BPF sys_enter augmenter for "mknod"
Reusing "open" BPF sys_enter augmenter for "statfs"
Reusing "open" BPF sys_enter augmenter for "pivot_root"
Reusing "open" BPF sys_enter augmenter for "chroot"
Reusing "open" BPF sys_enter augmenter for "acct"
Reusing "open" BPF sys_enter augmenter for "swapon"
Reusing "open" BPF sys_enter augmenter for "swapoff"
Reusing "open" BPF sys_enter augmenter for "delete_module"
Reusing "open" BPF sys_enter augmenter for "setxattr"
Reusing "open" BPF sys_enter augmenter for "lsetxattr"
Reusing "openat" BPF sys_enter augmenter for "fsetxattr"
Reusing "open" BPF sys_enter augmenter for "getxattr"
Reusing "open" BPF sys_enter augmenter for "lgetxattr"
Reusing "openat" BPF sys_enter augmenter for "fgetxattr"
Reusing "open" BPF sys_enter augmenter for "listxattr"
Reusing "open" BPF sys_enter augmenter for "llistxattr"
Reusing "open" BPF sys_enter augmenter for "removexattr"
Reusing "open" BPF sys_enter augmenter for "lremovexattr"
Reusing "fsetxattr" BPF sys_enter augmenter for "fremovexattr"
Reusing "open" BPF sys_enter augmenter for "mq_open"
Reusing "open" BPF sys_enter augmenter for "mq_unlink"
Reusing "fsetxattr" BPF sys_enter augmenter for "add_key"
Reusing "fremovexattr" BPF sys_enter augmenter for "request_key"
Reusing "fremovexattr" BPF sys_enter augmenter for "inotify_add_watch"
Reusing "fremovexattr" BPF sys_enter augmenter for "mkdirat"
Reusing "fremovexattr" BPF sys_enter augmenter for "mknodat"
Reusing "fremovexattr" BPF sys_enter augmenter for "fchownat"
Reusing "fremovexattr" BPF sys_enter augmenter for "futimesat"
Reusing "fremovexattr" BPF sys_enter augmenter for "newfstatat"
Reusing "fremovexattr" BPF sys_enter augmenter for "unlinkat"
Reusing "fremovexattr" BPF sys_enter augmenter for "linkat"
Reusing "open" BPF sys_enter augmenter for "symlinkat"
Reusing "fremovexattr" BPF sys_enter augmenter for "readlinkat"
Reusing "fremovexattr" BPF sys_enter augmenter for "fchmodat"
Reusing "fremovexattr" BPF sys_enter augmenter for "faccessat"
Reusing "fremovexattr" BPF sys_enter augmenter for "utimensat"
Reusing "connect" BPF sys_enter augmenter for "accept4"
Reusing "fremovexattr" BPF sys_enter augmenter for "name_to_handle_at"
Reusing "fremovexattr" BPF sys_enter augmenter for "renameat2"
Reusing "open" BPF sys_enter augmenter for "memfd_create"
Reusing "fremovexattr" BPF sys_enter augmenter for "execveat"
Reusing "fremovexattr" BPF sys_enter augmenter for "statx"
TL;DR:
These are the new syscalls that can be augmented
Reusing "openat" BPF sys_enter augmenter for "open_tree"
Reusing "openat" BPF sys_enter augmenter for "openat2"
Reusing "openat" BPF sys_enter augmenter for "mount_setattr"
Reusing "openat" BPF sys_enter augmenter for "move_mount"
Reusing "open" BPF sys_enter augmenter for "fsopen"
Reusing "openat" BPF sys_enter augmenter for "fspick"
Reusing "openat" BPF sys_enter augmenter for "faccessat2"
Reusing "openat" BPF sys_enter augmenter for "fchmodat2"
as for the perf trace output:
before
perf $ perf trace -e faccessat2 --max-events=1
[no output]
after
perf $ ./perf trace -e faccessat2 --max-events=1
0.000 ( 0.037 ms): waybar/958 faccessat2(dfd: 40, filename: "uevent") = 0
P.S. The reason why this bug was not found in the past five years is
probably because it only happens to the newer syscalls whose id is
greater, for instance, faccessat2 of id 439, which not a lot of people
care about when using perf trace.
[Arnaldo]: notes
That and the fact that the BPF code was hidden before having to use -e,
that got changed kinda recently when we switched to using BPF skels for
augmenting syscalls in 'perf trace':
⬢[acme@toolbox perf-tools-next]$ git log --oneline tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
|
||
|
Namhyung Kim
|
74ad3cb08b |
Merge remote-tracking branch 'perf-tools' into perf-tools-next
Merge fixes and updates in v6.10 into perf-tools-next to resolve changes in synthesizing the LOST_SAMPLES records and build fixes. Signed-off-by: Namhyung Kim <namhyung@kernel.org> |
||
Changbin Du
|
f975c13d2a |
perf trace beauty: Always show mmap prot even though PROT_NONE
PROT_NONE is also useful information, so do not omit the mmap prot even
though it is 0. syscall_arg__scnprintf_mmap_prot() could print PROT_NONE
for prot 0.
Before: PROT_NONE is not shown.
$ sudo perf trace -e syscalls:sys_enter_mmap --filter prot==0 -- ls
0.000 ls/2979231 syscalls:sys_enter_mmap(len: 4220888, flags: PRIVATE|ANONYMOUS)
After: PROT_NONE is displayed.
$ sudo perf trace -e syscalls:sys_enter_mmap --filter prot==0 -- ls
0.000 ls/2975708 syscalls:sys_enter_mmap(len: 4220888, prot: NONE, flags: PRIVATE|ANONYMOUS)
Signed-off-by: Changbin Du <changbin.du@huawei.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240522033542.1359421-3-changbin.du@huawei.com
|
||
|
Changbin Du
|
92968dcc03 |
perf trace beauty: Always show param if show_zero is set
For some parameters, it is best to also display them when they are 0, e.g. flags. Here we only check the show_zero property and let arg printer handle special cases. Signed-off-by: Changbin Du <changbin.du@huawei.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240522033542.1359421-2-changbin.du@huawei.com |
||
|
Arnaldo Carvalho de Melo
|
1437a9f06f |
tools headers UAPI: Sync fcntl.h with the kernel sources to pick F_DUPFD_QUERY
There is no scrape script yet for those, but the warning pointed out we
need to update the array with the F_LINUX_SPECIFIC_BASE entries, do it.
Now 'perf trace' can decode that cmd and also use it in filter, as in:
root@number:~# perf trace -e syscalls:*enter_fcntl --filter 'cmd != SETFL && cmd != GETFL'
0.000 sssd_kcm/303828 syscalls:sys_enter_fcntl(fd: 13</var/lib/sss/secrets/secrets.ldb>, cmd: SETLK, arg: 0x7fffdc6a8a50)
0.013 sssd_kcm/303828 syscalls:sys_enter_fcntl(fd: 13</var/lib/sss/secrets/secrets.ldb>, cmd: SETLKW, arg: 0x7fffdc6a8aa0)
0.090 sssd_kcm/303828 syscalls:sys_enter_fcntl(fd: 13</var/lib/sss/secrets/secrets.ldb>, cmd: SETLKW, arg: 0x7fffdc6a88e0)
^Croot@number:~#
This picks up the changes in:
|
||
|
Ian Rogers
|
ee756ef749 |
perf dso: Add reference count checking and accessor functions
Add reference count checking to struct dso, this can help with
implementing correct reference counting discipline. To avoid
RC_CHK_ACCESS everywhere, add accessor functions for the variables in
struct dso.
The majority of the change is mechanical in nature and not easy to
split up.
Committer testing:
'perf test' up to this patch shows no regressions.
But:
util/symbol.c: In function ‘dso__load_bfd_symbols’:
util/symbol.c:1683:9: error: too few arguments to function ‘dso__set_adjust_symbols’
1683 | dso__set_adjust_symbols(dso);
| ^~~~~~~~~~~~~~~~~~~~~~~
In file included from util/symbol.c:21:
util/dso.h:268:20: note: declared here
268 | static inline void dso__set_adjust_symbols(struct dso *dso, bool val)
| ^~~~~~~~~~~~~~~~~~~~~~~
make[6]: *** [/home/acme/git/perf-tools-next/tools/build/Makefile.build:106: /tmp/tmp.ZWHbQftdN6/util/symbol.o] Error 1
MKDIR /tmp/tmp.ZWHbQftdN6/tests/workloads/
make[6]: *** Waiting for unfinished jobs....
This was updated:
- symbols__fixup_end(&dso->symbols, false);
- symbols__fixup_duplicate(&dso->symbols);
- dso->adjust_symbols = 1;
+ symbols__fixup_end(dso__symbols(dso), false);
+ symbols__fixup_duplicate(dso__symbols(dso));
+ dso__set_adjust_symbols(dso);
But not build tested with BUILD_NONDISTRO and libbfd devel files installed
(binutils-devel on fedora).
Add the missing argument:
symbols__fixup_end(dso__symbols(dso), false);
symbols__fixup_duplicate(dso__symbols(dso));
- dso__set_adjust_symbols(dso);
+ dso__set_adjust_symbols(dso, true);
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ahelenia Ziemiańska <nabijaczleweli@nabijaczleweli.xyz>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Chengen Du <chengen.du@canonical.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dima Kogan <dima@secretsauce.net>
Cc: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Li Dong <lidong@vivo.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paran Lee <p4ranlee@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Cc: Sun Haiyong <sunhaiyong@loongson.cn>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Yanteng Si <siyanteng@loongson.cn>
Cc: zhaimingbing <zhaimingbing@cmss.chinamobile.com>
Link: https://lore.kernel.org/r/20240504213803.218974-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Ian Rogers
|
8f283fb7b8 |
perf trace: Disable syscall augmentation with record
Syscall augmentation is causing samples not to be written to the perf.data file with "perf trace record". Disabling augmentation is sub-optimal, but it beats having a totally broken perf trace record. Closes: https://lore.kernel.org/lkml/CAP-5=fV9Gd1Teak+EOcUSxe13KqSyfZyPNagK97GbLiOQRgGaw@mail.gmail.com/ Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20240216172357.65037-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
Yang Jihong
|
09d2056efe |
perf evsel: Use evsel__name_is() helper
Code cleanup, replace strcmp(evsel__name(evsel, {NAME})) with
evsel__name_is() helper.
No functional change.
Committer notes:
Fix this build error:
trace.syscalls.events.bpf_output = evlist__last(trace.evlist);
- assert(evsel__name_is(trace.syscalls.events.bpf_output), "__augmented_syscalls__");
+ assert(evsel__name_is(trace.syscalls.events.bpf_output, "__augmented_syscalls__"));
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Yang Jihong <yangjihong@bytedance.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240401062724.1006010-3-yangjihong@bytedance.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
0831638e8c |
perf trace: Fix 'newfstatat'/'fstatat' argument pretty printing
There were needless two entries, one for 'newfstatat' and another for
'fstatat', keep just one and pretty print its 'flags' argument using the
fs_at_flags scnprintf that is also used by other FS syscalls such as
'stat', now:
root@number:~# perf trace -e newfstatat --max-events=5
0.000 ( 0.010 ms): abrt-dump-jour/1400 newfstatat(dfd: 7, filename: "", statbuf: 0x7fff0d127000, flag: EMPTY_PATH) = 0
0.020 ( 0.003 ms): abrt-dump-jour/1400 newfstatat(dfd: 9, filename: "", statbuf: 0x55752507b0e8, flag: EMPTY_PATH) = 0
0.039 ( 0.004 ms): abrt-dump-jour/1400 newfstatat(dfd: 19, filename: "", statbuf: 0x557525061378, flag: EMPTY_PATH) = 0
0.047 ( 0.003 ms): abrt-dump-jour/1400 newfstatat(dfd: 20, filename: "", statbuf: 0x5575250b8cc8, flag: EMPTY_PATH) = 0
0.053 ( 0.003 ms): abrt-dump-jour/1400 newfstatat(dfd: 22, filename: "", statbuf: 0x5575250535d8, flag: EMPTY_PATH) = 0
root@number:~#
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20240320193115.811899-6-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
4d92328290 |
perf trace: Beautify the 'flags' arg of unlinkat
Reusing the fs_at_flags array done for the 'stat' syscall. Reviewed-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/20240320193115.811899-5-acme@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
b8171a8406 |
perf beauty: Introduce faccessat2 flags scnprintf routine
The fsaccessat and fsaccessat2 now have beautifiers for its arguments. Reviewed-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/20240320193115.811899-4-acme@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
3d6cfbaf27 |
perf beauty: Introduce scrape script for various fs syscalls 'flags' arguments
It was using the first variation on producing a string representation
for a binary flag, one that used the system's fcntl.h and preprocessor
tricks that had to be updated everytime a new flag was introduced.
Use the more recent scrape script + strarray + strarray__scnprintf_flags() combo.
$ tools/perf/trace/beauty/fs_at_flags.sh
static const char *fs_at_flags[] = {
[ilog2(0x100) + 1] = "SYMLINK_NOFOLLOW",
[ilog2(0x200) + 1] = "REMOVEDIR",
[ilog2(0x400) + 1] = "SYMLINK_FOLLOW",
[ilog2(0x800) + 1] = "NO_AUTOMOUNT",
[ilog2(0x1000) + 1] = "EMPTY_PATH",
[ilog2(0x0000) + 1] = "STATX_SYNC_AS_STAT",
[ilog2(0x2000) + 1] = "STATX_FORCE_SYNC",
[ilog2(0x4000) + 1] = "STATX_DONT_SYNC",
[ilog2(0x8000) + 1] = "RECURSIVE",
[ilog2(0x80000000) + 1] = "GETATTR_NOSEC",
};
$
Now we need a copy of uapi/linux/fcntl.h from tools/include/ in the
scrape only directory tools/perf/trace/beauty/include and will use that
fs_at_flags array for other fs syscalls.
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20240320193115.811899-2-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Arnaldo Carvalho de Melo
|
a9f4c6c999 |
perf trace: Collect sys_nanosleep first argument
That is a 'struct timespec' passed from userspace to the kernel as we
can see with a system wide syscall tracing:
root@number:~# perf trace -e nanosleep
0.000 (10.102 ms): podman/9150 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
38.924 (10.077 ms): podman/2195174 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
100.177 (10.107 ms): podman/9150 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
139.171 (10.063 ms): podman/2195174 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
200.603 (10.105 ms): podman/9150 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
239.399 (10.064 ms): podman/2195174 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
300.994 (10.096 ms): podman/9150 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
339.584 (10.067 ms): podman/2195174 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
401.335 (10.057 ms): podman/9150 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
439.758 (10.166 ms): podman/2195174 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
501.814 (10.110 ms): podman/9150 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
539.983 (10.227 ms): podman/2195174 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
602.284 (10.199 ms): podman/9150 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
640.208 (10.105 ms): podman/2195174 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
702.662 (10.163 ms): podman/9150 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
740.440 (10.107 ms): podman/2195174 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
802.993 (10.159 ms): podman/9150 nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }) = 0
^Croot@number:~# strace -p 9150 -e nanosleep
If we then use the ptrace method to look at that podman process:
root@number:~# strace -p 9150 -e nanosleep
strace: Process 9150 attached
nanosleep({tv_sec=0, tv_nsec=10000000}, NULL) = 0
nanosleep({tv_sec=0, tv_nsec=10000000}, NULL) = 0
nanosleep({tv_sec=0, tv_nsec=10000000}, NULL) = 0
nanosleep({tv_sec=0, tv_nsec=10000000}, NULL) = 0
nanosleep({tv_sec=0, tv_nsec=10000000}, NULL) = 0
nanosleep({tv_sec=0, tv_nsec=10000000}, NULL) = 0
nanosleep({tv_sec=0, tv_nsec=10000000}, NULL) = 0
^Cstrace: Process 9150 detached
root@number:~#
With some changes we can get something closer to the strace output,
still in system wide mode:
root@number:~# perf config trace.show_arg_names=false
root@number:~# perf config trace.show_duration=false
root@number:~# perf config trace.show_timestamp=false
root@number:~# perf config trace.show_zeros=true
root@number:~# perf config trace.args_alignment=0
root@number:~# perf trace -e nanosleep --max-events=10
podman/2195174 nanosleep({ .tv_sec: 0, .tv_nsec: 10000000 }, NULL) = 0
podman/9150 nanosleep({ .tv_sec: 0, .tv_nsec: 10000000 }, NULL) = 0
podman/2195174 nanosleep({ .tv_sec: 0, .tv_nsec: 10000000 }, NULL) = 0
podman/9150 nanosleep({ .tv_sec: 0, .tv_nsec: 10000000 }, NULL) = 0
podman/2195174 nanosleep({ .tv_sec: 0, .tv_nsec: 10000000 }, NULL) = 0
podman/9150 nanosleep({ .tv_sec: 0, .tv_nsec: 10000000 }, NULL) = 0
podman/2195174 nanosleep({ .tv_sec: 0, .tv_nsec: 10000000 }, NULL) = 0
podman/9150 nanosleep({ .tv_sec: 0, .tv_nsec: 10000000 }, NULL) = 0
podman/2195174 nanosleep({ .tv_sec: 0, .tv_nsec: 10000000 }, NULL) = 0
podman/9150 nanosleep({ .tv_sec: 0, .tv_nsec: 10000000 }, NULL) = 0
root@number:~#
root@number:~# perf config
trace.show_arg_names=false
trace.show_duration=false
trace.show_timestamp=false
trace.show_zeros=true
trace.args_alignment=0
root@number:~# cat ~/.perfconfig
# this file is auto-generated.
[trace]
show_arg_names = false
show_duration = false
show_timestamp = false
show_zeros = true
args_alignment = 0
root@number:~#
This will not get reused by any other syscall as nanosleep is the only
one to have as its first argument a 'struct timespec" pointer argument
passed from userspace to the kernel:
root@number:~# grep timespec /sys/kernel/tracing/events/syscalls/sys_enter_*/format | grep offset:16
/sys/kernel/tracing/events/syscalls/sys_enter_nanosleep/format: field:struct __kernel_timespec * rqtp; offset:16; size:8; signed:0;
root@number:~#
BTF based pretty printing will simplify all this, but then lets just get
the low hanging fruits first.
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/Zbq72dJRpOlfRWnf@kernel.org/
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Ian Rogers
|
f178ffdf7e |
perf trace: Ignore thread hashing in summary
Commit
|
||
|
Arnaldo Carvalho de Melo
|
54373b5d53 |
perf env: Introduce perf_env__arch_strerrno()
That will cache the arch specific function translating error numbers to strings. Reviewed-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Laight <David.Laight@ACULAB.COM> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/20231201203046.486596-2-acme@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
64917f4df0 |
perf trace: Use heuristic when deciding if a syscall tracepoint "const char *" field is really a string
'perf trace' tries to find BPF progs associated with a syscall that have a signature that is similar to syscalls without one to try and reuse, so, for instance, the 'open' signature can be reused with many other syscalls that have as its first arg a string. It uses the tracefs events format file for finding a signature that can be reused, but then comes the "write" syscall with its second argument as a "const char *": # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_write/format name: sys_enter_write ID: 746 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int common_pid; offset:4; size:4; signed:1; field:int __syscall_nr; offset:8; size:4; signed:1; field:unsigned int fd; offset:16; size:8; signed:0; field:const char * buf; offset:24; size:8; signed:0; field:size_t count; offset:32; size:8; signed:0; print fmt: "fd: 0x%08lx, buf: 0x%08lx, count: 0x%08lx", ((unsigned long)(REC->fd)), ((unsigned long)(REC->buf)), ((unsigned long)(REC->count)) # Which isn't a string (the man page for glibc has buf as "void *"), so we have to use the name of the argument as an heuristic, to consider a string just args that are "const char *" and that have in its name the "path", "file", etc substrings. With that now it reuses: [root@quaco ~]# perf trace -v --max-events=1 |& grep Reus Reusing "open" BPF sys_enter augmenter for "stat" Reusing "open" BPF sys_enter augmenter for "lstat" Reusing "open" BPF sys_enter augmenter for "access" Reusing "connect" BPF sys_enter augmenter for "accept" Reusing "sendto" BPF sys_enter augmenter for "recvfrom" Reusing "connect" BPF sys_enter augmenter for "bind" Reusing "connect" BPF sys_enter augmenter for "getsockname" Reusing "connect" BPF sys_enter augmenter for "getpeername" Reusing "open" BPF sys_enter augmenter for "execve" Reusing "open" BPF sys_enter augmenter for "truncate" Reusing "open" BPF sys_enter augmenter for "chdir" Reusing "open" BPF sys_enter augmenter for "mkdir" Reusing "open" BPF sys_enter augmenter for "rmdir" Reusing "open" BPF sys_enter augmenter for "creat" Reusing "open" BPF sys_enter augmenter for "link" Reusing "open" BPF sys_enter augmenter for "unlink" Reusing "open" BPF sys_enter augmenter for "symlink" Reusing "open" BPF sys_enter augmenter for "readlink" Reusing "open" BPF sys_enter augmenter for "chmod" Reusing "open" BPF sys_enter augmenter for "chown" Reusing "open" BPF sys_enter augmenter for "lchown" Reusing "open" BPF sys_enter augmenter for "mknod" Reusing "open" BPF sys_enter augmenter for "statfs" Reusing "open" BPF sys_enter augmenter for "pivot_root" Reusing "open" BPF sys_enter augmenter for "chroot" Reusing "open" BPF sys_enter augmenter for "acct" Reusing "open" BPF sys_enter augmenter for "swapon" Reusing "open" BPF sys_enter augmenter for "swapoff" Reusing "open" BPF sys_enter augmenter for "delete_module" Reusing "open" BPF sys_enter augmenter for "setxattr" Reusing "open" BPF sys_enter augmenter for "lsetxattr" Reusing "openat" BPF sys_enter augmenter for "fsetxattr" Reusing "open" BPF sys_enter augmenter for "getxattr" Reusing "open" BPF sys_enter augmenter for "lgetxattr" Reusing "openat" BPF sys_enter augmenter for "fgetxattr" Reusing "open" BPF sys_enter augmenter for "listxattr" Reusing "open" BPF sys_enter augmenter for "llistxattr" Reusing "open" BPF sys_enter augmenter for "removexattr" Reusing "open" BPF sys_enter augmenter for "lremovexattr" Reusing "fsetxattr" BPF sys_enter augmenter for "fremovexattr" Reusing "open" BPF sys_enter augmenter for "mq_open" Reusing "open" BPF sys_enter augmenter for "mq_unlink" Reusing "fsetxattr" BPF sys_enter augmenter for "add_key" Reusing "fremovexattr" BPF sys_enter augmenter for "request_key" Reusing "fremovexattr" BPF sys_enter augmenter for "inotify_add_watch" Reusing "fremovexattr" BPF sys_enter augmenter for "mkdirat" Reusing "fremovexattr" BPF sys_enter augmenter for "mknodat" Reusing "fremovexattr" BPF sys_enter augmenter for "fchownat" Reusing "fremovexattr" BPF sys_enter augmenter for "futimesat" Reusing "fremovexattr" BPF sys_enter augmenter for "newfstatat" Reusing "fremovexattr" BPF sys_enter augmenter for "unlinkat" Reusing "fremovexattr" BPF sys_enter augmenter for "linkat" Reusing "open" BPF sys_enter augmenter for "symlinkat" Reusing "fremovexattr" BPF sys_enter augmenter for "readlinkat" Reusing "fremovexattr" BPF sys_enter augmenter for "fchmodat" Reusing "fremovexattr" BPF sys_enter augmenter for "faccessat" Reusing "fremovexattr" BPF sys_enter augmenter for "utimensat" Reusing "connect" BPF sys_enter augmenter for "accept4" Reusing "fremovexattr" BPF sys_enter augmenter for "name_to_handle_at" Reusing "fremovexattr" BPF sys_enter augmenter for "renameat2" Reusing "open" BPF sys_enter augmenter for "memfd_create" Reusing "fremovexattr" BPF sys_enter augmenter for "execveat" Reusing "fremovexattr" BPF sys_enter augmenter for "statx" [root@quaco ~]# Reviewed-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alan Maguire <alan.maguire@oracle.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/ZN5lrdeEdSMCn7hk@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
83a0943b18 |
perf trace: Use the augmented_raw_syscall BPF skel only for tracing syscalls
It is possible to use 'perf trace' with tracepoints and in that case we
can't initialize/use the augmented_raw_syscalls BPF skel.
For instance, this usecase:
# perf trace -e sched:*exec --max-events=5
? ( ): NetworkManager/1183 ... [continued]: poll()) = 1
0.043 ( 0.007 ms): NetworkManager/1183 epoll_wait(epfd: 17<anon_inode:[eventpoll]>, events: 0x55555f90e920, maxevents: 6) = 0
0.060 ( 0.007 ms): NetworkManager/1183 write(fd: 3<anon_inode:[eventfd]>, buf: 0x7ffc5a27cd30, count: 8) = 8
0.073 ( 0.005 ms): NetworkManager/1183 epoll_wait(epfd: 24<anon_inode:[eventpoll]>, events: 0x7ffc5a27cd20, maxevents: 2) = 1
0.082 ( 0.010 ms): NetworkManager/1183 recvmmsg(fd: 26<socket:[30298]>, mmsg: 0x7ffc5a27caa0, vlen: 8) = 1
#
Where we want to trace just some sched tracepoints ending in 'exec' ends
up tracing all syscalls.
Fix it by checking existing trace->trace_syscalls boolean to see if we
need the augmenter.
A followup patch will move those sections of code used only with the
augmenter to separate functions, to get it cleaner and remove the goto,
done just for reviewing purposes.
With this patch in place the previous behaviour is restored: no syscalls
when we have other events and no syscall names:
[root@quaco ~]# perf probe do_filp_open "filename=pathname->name:string"
Added new event:
probe:do_filp_open (on do_filp_open with filename=pathname->name:string)
You can now use it in all perf tools, such as:
perf record -e probe:do_filp_open -aR sleep 1
[root@quaco ~]# perf trace --max-events=10 -e probe:do_filp_open sleep 1
0.000 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/etc/ld.so.cache")
0.056 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/lib64/libc.so.6")
0.481 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/locale-archive")
0.501 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/share/locale/locale.alias")
0.572 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/en_US.UTF-8/LC_IDENTIFICATION")
0.581 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/en_US.utf8/LC_IDENTIFICATION")
0.616 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib64/gconv/gconv-modules.cache")
0.656 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/en_US.UTF-8/LC_MEASUREMENT")
0.664 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/en_US.utf8/LC_MEASUREMENT")
0.696 sleep/455122 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/en_US.UTF-8/LC_TELEPHONE")
[root@quaco ~]#
As well as mixing syscalls with tracepoints, getting the syscall
tracepoints used augmented using the BPF skel:
[root@quaco ~]# perf trace --max-events=10 -e open*,probe:do_filp_open sleep 1
0.000 ( ): sleep/455124 openat(dfd: CWD, filename: "/etc/ld.so.cache", flags: RDONLY|CLOEXEC) ...
0.005 ( ): sleep/455124 probe:do_filp_open(__probe_ip: -1186560412, filename: "/etc/ld.so.cache")
0.000 ( 0.011 ms): sleep/455124 ... [continued]: openat()) = 3
0.031 ( ): sleep/455124 openat(dfd: CWD, filename: "/lib64/libc.so.6", flags: RDONLY|CLOEXEC) ...
0.033 ( ): sleep/455124 probe:do_filp_open(__probe_ip: -1186560412, filename: "/lib64/libc.so.6")
0.031 ( 0.006 ms): sleep/455124 ... [continued]: openat()) = 3
0.258 ( ): sleep/455124 openat(dfd: CWD, filename: "/usr/lib/locale/locale-archive", flags: RDONLY|CLOEXEC) ...
0.261 ( ): sleep/455124 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/lib/locale/locale-archive")
0.258 ( 0.006 ms): sleep/455124 ... [continued]: openat()) = -1 ENOENT (No such file or directory)
0.272 ( ): sleep/455124 openat(dfd: CWD, filename: "/usr/share/locale/locale.alias", flags: RDONLY|CLOEXEC) ...
0.273 ( ): sleep/455124 probe:do_filp_open(__probe_ip: -1186560412, filename: "/usr/share/locale/locale.alias")
A final note: the probe:do_filp_open uses a kprobe (probably optimized
as its in the start of a function) that uses the kprobe_tracer mechanism
in the kernel to collect the pathname->name string and stash it into the
tracepoint created by 'perf probe' for that:
[root@quaco ~]# cat /sys/kernel/debug/tracing/kprobe_events
p:probe/do_filp_open _text+4621920 filename=+0(+0(%si)):string
[root@quaco ~]#
While the syscalls:sys_enter_openat tracepoint gets its string from a
BPF program attached to raw_syscalls:sys_enter that tail calls into
another BPF program that knows the types for the openat syscall args and
thus can bpf_probe_read it right after the normal
sys_enter/sys_enter_openat tracepoint payload that comes prefixed with
whatever perf_event_open asked for (CPU, timestamp, etc):
[root@quaco ~]# bpftool prog | grep -E "sys_enter |sys_enter_opena" -A3
3176: tracepoint name sys_enter tag 0bc3fc9d11754ba1 gpl
loaded_at 2023-08-17T12:32:20-0300 uid 0
xlated 272B jited 257B memlock 4096B map_ids 2462,2466,2463
btf_id 2976
--
3180: tracepoint name sys_enter_opena tag 19dd077f00ec2f58 gpl
loaded_at 2023-08-17T12:32:20-0300 uid 0
xlated 328B jited 206B memlock 4096B map_ids 2466,2465
btf_id 2976
[root@quaco ~]#
Fixes:
|
||
|
Ian Rogers
|
5e6da6be30 |
perf trace: Migrate BPF augmentation to use a skeleton
Previously a BPF event of augmented_raw_syscalls.c could be used to
enable augmentation of syscalls by perf trace. As BPF events are no
longer supported, switch to using a BPF skeleton which when attached
explicitly opens the sysenter and sysexit tracepoints.
The dump map is removed as debugging wasn't supported by the
augmentation and bpf_printk can be used when necessary.
Remove tools/perf/examples/bpf/augmented_raw_syscalls.c so that the
rename/migration to a BPF skeleton captures that this was the source.
Committer notes:
Some minor stylistic changes to help visualizing the diff.
Use libbpf_strerror when failing to load the augmented raw syscalls BPF.
Use bpf_object__for_each_program(prog, trace.skel->obj) to disable auto
attachment for all but the sys_enter, sys_exit tracepoints, to avoid
having to add extra lines as we go adding support for more pointer
receiving syscalls.
Committer testing:
# perf trace -e open* --max-events=10
0.000 ( 0.022 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 11
208.833 ( ): gnome-terminal/3223 openat(dfd: CWD, filename: "/proc/51250/cmdline") ...
249.993 ( 0.024 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 11
250.118 ( 0.030 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.pressure", flags: RDONLY|CLOEXEC) = 11
250.205 ( 0.016 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.current", flags: RDONLY|CLOEXEC) = 11
250.244 ( 0.014 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.min", flags: RDONLY|CLOEXEC) = 11
250.282 ( 0.014 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.low", flags: RDONLY|CLOEXEC) = 11
250.320 ( 0.014 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.swap.current", flags: RDONLY|CLOEXEC) = 11
250.355 ( 0.014 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1000.slice/user@1000.service/memory.stat", flags: RDONLY|CLOEXEC) = 11
250.717 ( 0.016 ms): systemd-oomd/1151 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1001.slice/user@1001.service/memory.pressure", flags: RDONLY|CLOEXEC) = 11
#
# perf trace -e *nanosleep* --max-events=10
? ( ): SCTP timer/28304 ... [continued]: clock_nanosleep()) = 0
0.007 (10.058 ms): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) = 0
10.069 ( ): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) ...
10.069 (10.056 ms): SCTP timer/28304 ... [continued]: clock_nanosleep()) = 0
17.059 ( ): podman/3572 nanosleep(rqtp: 0x7fc4f4d75be0) ...
17.059 (10.061 ms): podman/3572 ... [continued]: nanosleep()) = 0
20.131 (10.059 ms): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) = 0
30.195 (10.038 ms): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) = 0
40.238 (10.057 ms): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) = 0
50.301 ( ): SCTP timer/28304 clock_nanosleep(rqtp: { .tv_sec: 0, .tv_nsec: 10000000 }, rmtp: 0x7f0466b78de0) ...
#
# perf trace -e perf_event* -- perf stat -e instructions,cycles,cache-misses sleep 0.1
0.000 ( 0.011 ms): perf/51331 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x1 (PERF_COUNT_HW_INSTRUCTIONS), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 51332 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
0.013 ( 0.003 ms): perf/51331 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0 (PERF_COUNT_HW_CPU_CYCLES), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 51332 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 4
0.017 ( 0.002 ms): perf/51331 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x3 (PERF_COUNT_HW_CACHE_MISSES), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 51332 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 5
Performance counter stats for 'sleep 0.1':
1,495,051 instructions # 1.11 insn per cycle
1,347,641 cycles
35,424 cache-misses
0.100935279 seconds time elapsed
0.000924000 seconds user
0.000000000 seconds sys
#
# perf trace -e connect* ssh localhost
0.000 ( 0.012 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
0.118 ( 0.004 ms): ssh/51346 connect(fd: 6, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
0.399 ( 0.007 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
0.426 ( 0.003 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
0.754 ( 0.009 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: INET, port: 22, addr: 127.0.0.1 }, addrlen: 16) = 0
0.771 ( 0.010 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: INET6, port: 22, addr: ::1 }, addrlen: 28) = 0
0.798 ( 0.053 ms): ssh/51346 connect(fd: 4, uservaddr: { .family: INET6, port: 22, addr: ::1 }, addrlen: 28) = 0
0.870 ( 0.004 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
0.904 ( 0.003 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
0.930 ( 0.003 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
0.957 ( 0.003 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
0.981 ( 0.003 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
1.006 ( 0.004 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
1.036 ( 0.005 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/lib/sss/pipes/nss }, addrlen: 110) = -1 ECONNREFUSED (Connection refused)
65.077 ( 0.022 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/run/.heim_org.h5l.kcm-socket }, addrlen: 110) = 0
66.608 ( 0.014 ms): ssh/51346 connect(fd: 5, uservaddr: { .family: LOCAL, path: /var/run/.heim_org.h5l.kcm-socket }, addrlen: 110) = 0
root@localhost's password:
#
# perf trace -e sendto* ping -c 2 localhost
PING localhost(localhost (::1)) 56 data bytes
64 bytes from localhost (::1): icmp_seq=1 ttl=64 time=0.024 ms
0.000 ( 0.011 ms): ping/51357 sendto(fd: 5, buff: 0x7ffcca35e620, len: 20, addr: { .family: NETLINK }, addr_len: 0xc) = 20
0.135 ( 0.026 ms): ping/51357 sendto(fd: 4, buff: 0x5601398f7b20, len: 64, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 0x1c) = 64
1014.929 ( 0.050 ms): ping/51357 sendto(fd: 4, buff: 0x5601398f7b20, len: 64, flags: CONFIRM, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 0x1c) = 64
64 bytes from localhost (::1): icmp_seq=2 ttl=64 time=0.046 ms
--- localhost ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1015ms
rtt min/avg/max/mdev = 0.024/0.035/0.046/0.011 ms
#
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Carsten Haitzler <carsten.haitzler@arm.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Fangrui Song <maskray@google.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Tom Rix <trix@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Wang ShaoBo <bobo.shaobowang@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Cc: bpf@vger.kernel.org
Cc: llvm@lists.linux.dev
Link: https://lore.kernel.org/r/20230810184853.2860737-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Ian Rogers
|
3d6dfae889 |
perf parse-events: Remove BPF event support
New features like the BPF --filter support in perf record have made the
BPF event functionality somewhat redundant. As shown by commit
fcb027c1a4f6 ("perf tools: Revert enable indices setting syntax for BPF
map") and commit
|
||
|
Arnaldo Carvalho de Melo
|
fcca1faf11 |
perf trace: Free thread_trace->files table
The fd->pathname table that is kept in 'struct thread_trace' and thus in thread->priv must be freed when a thread is deleted. This was also detected using -fsanitize=address. Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/20230719202951.534582-6-acme@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Arnaldo Carvalho de Melo
|
7962ef1365 |
perf trace: Really free the evsel->priv area
In |
||
|
Arnaldo Carvalho de Melo
|
9de251cb50 |
perf trace: Register a thread priv destructor
To plug these leaks detected with:
$ make EXTRA_CFLAGS="-fsanitize=address" BUILD_BPF_SKEL=1 CORESIGHT=1 O=/tmp/build/perf-tools-next -C tools/perf install-bin
=================================================================
==473890==ERROR: LeakSanitizer: detected memory leaks
Direct leak of 112 byte(s) in 1 object(s) allocated from:
#0 0x7fdf19aba097 in calloc (/lib64/libasan.so.8+0xba097)
#1 0x987836 in zalloc (/home/acme/bin/perf+0x987836)
#2 0x5367ae in thread_trace__new /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:1289
#3 0x5367ae in thread__trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:1307
#4 0x5367ae in trace__sys_exit /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:2468
#5 0x52bf34 in trace__handle_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3177
#6 0x52bf34 in __trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3685
#7 0x542927 in trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3712
#8 0x542927 in trace__run /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:4055
#9 0x542927 in cmd_trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:5141
#10 0x5ef1a2 in run_builtin /home/acme/git/perf-tools-next/tools/perf/perf.c:323
#11 0x4196da in handle_internal_command /home/acme/git/perf-tools-next/tools/perf/perf.c:377
#12 0x4196da in run_argv /home/acme/git/perf-tools-next/tools/perf/perf.c:421
#13 0x4196da in main /home/acme/git/perf-tools-next/tools/perf/perf.c:537
#14 0x7fdf18a4a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f)
Direct leak of 2048 byte(s) in 1 object(s) allocated from:
#0 0x7f788fcba6af in __interceptor_malloc (/lib64/libasan.so.8+0xba6af)
#1 0x5337c0 in trace__sys_enter /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:2342
#2 0x52bfb4 in trace__handle_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3191
#3 0x52bfb4 in __trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3699
#4 0x542883 in trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3726
#5 0x542883 in trace__run /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:4069
#6 0x542883 in cmd_trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:5155
#7 0x5ef232 in run_builtin /home/acme/git/perf-tools-next/tools/perf/perf.c:323
#8 0x4196da in handle_internal_command /home/acme/git/perf-tools-next/tools/perf/perf.c:377
#9 0x4196da in run_argv /home/acme/git/perf-tools-next/tools/perf/perf.c:421
#10 0x4196da in main /home/acme/git/perf-tools-next/tools/perf/perf.c:537
#11 0x7f788ec4a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f)
Indirect leak of 48 byte(s) in 1 object(s) allocated from:
#0 0x7fdf19aba6af in __interceptor_malloc (/lib64/libasan.so.8+0xba6af)
#1 0x77b335 in intlist__new util/intlist.c:116
#2 0x5367fd in thread_trace__new /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:1293
#3 0x5367fd in thread__trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:1307
#4 0x5367fd in trace__sys_exit /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:2468
#5 0x52bf34 in trace__handle_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3177
#6 0x52bf34 in __trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3685
#7 0x542927 in trace__deliver_event /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3712
#8 0x542927 in trace__run /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:4055
#9 0x542927 in cmd_trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:5141
#10 0x5ef1a2 in run_builtin /home/acme/git/perf-tools-next/tools/perf/perf.c:323
#11 0x4196da in handle_internal_command /home/acme/git/perf-tools-next/tools/perf/perf.c:377
#12 0x4196da in run_argv /home/acme/git/perf-tools-next/tools/perf/perf.c:421
#13 0x4196da in main /home/acme/git/perf-tools-next/tools/perf/perf.c:537
#14 0x7fdf18a4a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f)
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20230719202951.534582-4-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|
Ian Rogers
|
8ab12a2038 |
perf callchain: Use pthread keys for tls callchain_cursor
Pthread keys are more portable than __thread and allow the association of a destructor with the key. Use the destructor to clean up TLS callchain cursors to aid understanding memory leaks. Committer notes: Had to fixup a series of unconverted places and also check for the return of get_tls_callchain_cursor() as it may fail and return NULL. In that unlikely case we now either print something to a file, if the caller was expecting to print a callchain, or return an error code to state that resolving the callchain isn't possible. In some cases this was made easier because thread__resolve_callchain() already can fail for other reasons, so this new one (cursor == NULL) can be added and the callers don't have to explicitely check for this new condition. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Brian Robbins <brianrob@linux.microsoft.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Fangrui Song <maskray@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Babrou <ivan@cloudflare.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: K Prateek Nayak <kprateek.nayak@amd.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Miguel Ojeda <ojeda@kernel.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Wenyu Liu <liuwenyu7@huawei.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Jihong <yangjihong1@huawei.com> Cc: Ye Xingchen <ye.xingchen@zte.com.cn> Cc: Yuan Can <yuancan@huawei.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230608232823.4027869-25-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Ian Rogers
|
0dd5041c9a |
perf addr_location: Add init/exit/copy functions
struct addr_location holds references to multiple reference counted objects. Add init/exit functions to make maintenance of those more consistent with the rest of the code and to try to avoid leaks. Modification of thread reference counts isn't included in this change. Committer notes: I needed to initialize result to sample->ip to make sure is set to something, fixing a compile time error, mostly keeping the previous logic as build_alloc_func_list() already does debugging/error prints about what went wrong if it takes the 'goto out'. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Brian Robbins <brianrob@linux.microsoft.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Fangrui Song <maskray@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Babrou <ivan@cloudflare.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: K Prateek Nayak <kprateek.nayak@amd.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Miguel Ojeda <ojeda@kernel.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Wenyu Liu <liuwenyu7@huawei.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Jihong <yangjihong1@huawei.com> Cc: Ye Xingchen <ye.xingchen@zte.com.cn> Cc: Yuan Can <yuancan@huawei.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230608232823.4027869-7-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Ian Rogers
|
ee84a3032b |
perf thread: Add accessor functions for thread
Using accessors will make it easier to add reference count checking in later patches. Committer notes: thread->nsinfo wasn't wrapped as it is used together with nsinfo__zput(), where does a trick to set the field with a refcount being dropped to NULL, and that doesn't work well with using thread__nsinfo(thread), that loses the &thread->nsinfo pointer. When refcount checking is added to 'struct thread', later in this series, nsinfo__zput(RC_CHK_ACCESS(thread)->nsinfo) will be used to check the thread pointer. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Brian Robbins <brianrob@linux.microsoft.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Fangrui Song <maskray@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Babrou <ivan@cloudflare.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: K Prateek Nayak <kprateek.nayak@amd.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Miguel Ojeda <ojeda@kernel.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Wenyu Liu <liuwenyu7@huawei.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Jihong <yangjihong1@huawei.com> Cc: Ye Xingchen <ye.xingchen@zte.com.cn> Cc: Yuan Can <yuancan@huawei.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230608232823.4027869-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Ian Rogers
|
7ee227f674 |
perf thread: Make threads rbtree non-invasive
Separate the rbtree out of thread and into a new struct thread_rb_node. The refcnt is in thread and the rbtree is responsible for a single count. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Brian Robbins <brianrob@linux.microsoft.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Fangrui Song <maskray@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Babrou <ivan@cloudflare.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: K Prateek Nayak <kprateek.nayak@amd.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Miguel Ojeda <ojeda@kernel.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Steinar H. Gunderson <sesse@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Wenyu Liu <liuwenyu7@huawei.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Jihong <yangjihong1@huawei.com> Cc: Ye Xingchen <ye.xingchen@zte.com.cn> Cc: Yuan Can <yuancan@huawei.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230608232823.4027869-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Ian Rogers
|
60995604d1 |
perf trace: Make some large static arrays const to move it to .data.rel.ro
Allows the movement of 33,128 bytes from .data to .data.rel.ro. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: K Prateek Nayak <kprateek.nayak@amd.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Ross Zwisler <zwisler@chromium.org> Cc: Sean Christopherson <seanjc@google.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tiezhu Yang <yangtiezhu@loongson.cn> Cc: Yang Jihong <yangjihong1@huawei.com> Link: https://lore.kernel.org/r/20230526183401.2326121-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |
||
|
Ian Rogers
|
411ad22ecf |
perf parse-events: Add pmu filter
To support the cputype argument added to "perf stat" for hybrid it is necessary to filter events during wildcard matching. Add a scanner argument for the filter and checking it when wildcard matching. Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Edward Baker <edward.baker@intel.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Samantha Alt <samantha.alt@intel.com> Cc: Stephane Eranian <eranian@google.com> Cc: Sumanth Korikkar <sumanthk@linux.ibm.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Tiezhu Yang <yangtiezhu@loongson.cn> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: Yang Jihong <yangjihong1@huawei.com> Link: https://lore.kernel.org/r/20230502223851.2234828-30-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> |