Skip to content

Commit a887466

Browse files
acmelacmel
committed
perf bpf skels: Stop using vmlinux.h generated from BTF, use subset of used structs + CO-RE
Linus reported a build break due to using a vmlinux without a BTF elf section to generate the vmlinux.h header with bpftool for use in the BPF tools in tools/perf/util/bpf_skel/*.bpf.c. Instead add a vmlinux.h file with the structs needed with the fields the tools need, marking the structs with __attribute__((preserve_access_index)), so that libbpf's CO-RE code can fixup the struct field offsets. In some cases the vmlinux.h file that was being generated by bpftool from the kernel BTF information was not needed at all, just including linux/bpf.h, sometimes linux/perf_event.h was enough as non-UAPI types were not being used. To keep te patch small, include those UAPI headers from the trimmed down vmlinux.h file, that then provides the tools with just the structs and the subset of its fields needed for them. Testing it: # perf lock contention -b find / > /dev/null ^C contended total wait max wait avg wait type caller 7 53.59 us 10.86 us 7.66 us rwlock:R start_this_handle+0xa0 2 30.35 us 21.99 us 15.17 us rwsem:R iterate_dir+0x52 1 9.04 us 9.04 us 9.04 us rwlock:W start_this_handle+0x291 1 8.73 us 8.73 us 8.73 us spinlock raw_spin_rq_lock_nested+0x1e # # perf lock contention -abl find / > /dev/null ^C contended total wait max wait avg wait address symbol 1 262.96 ms 262.96 ms 262.96 ms ffff8e67502d0170 (mutex) 12 244.24 us 39.91 us 20.35 us ffff8e6af56f8070 mmap_lock (rwsem) 7 30.28 us 6.85 us 4.33 us ffff8e6c865f1d40 rq_lock (spinlock) 3 7.42 us 4.03 us 2.47 us ffff8e6c864b1d40 rq_lock (spinlock) 2 3.72 us 2.19 us 1.86 us ffff8e6c86571d40 rq_lock (spinlock) 1 2.42 us 2.42 us 2.42 us ffff8e6c86471d40 rq_lock (spinlock) 4 2.11 us 559 ns 527 ns ffffffff9a146c80 rcu_state (spinlock) 3 1.45 us 818 ns 482 ns ffff8e674ae8384c (rwlock) 1 870 ns 870 ns 870 ns ffff8e68456ee060 (rwlock) 1 663 ns 663 ns 663 ns ffff8e6c864f1d40 rq_lock (spinlock) 1 573 ns 573 ns 573 ns ffff8e6c86531d40 rq_lock (spinlock) 1 472 ns 472 ns 472 ns ffff8e6c86431740 (spinlock) 1 397 ns 397 ns 397 ns ffff8e67413a4f04 (spinlock) # # perf test offcpu 95: perf record offcpu profiling tests : Ok # # perf kwork latency --use-bpf Starting trace, Hit <Ctrl+C> to stop and report ^C Kwork Name | Cpu | Avg delay | Count | Max delay | Max delay start | Max delay end | -------------------------------------------------------------------------------------------------------------------------------- (w)flush_memcg_stats_dwork | 0000 | 1056.212 ms | 2 | 2112.345 ms | 550113.229573 s | 550115.341919 s | (w)toggle_allocation_gate | 0000 | 10.144 ms | 62 | 416.389 ms | 550113.453518 s | 550113.869907 s | (w)0xffff8e6748e28080 | 0002 | 0.623 ms | 1 | 0.623 ms | 550110.989841 s | 550110.990464 s | (w)vmstat_shepherd | 0000 | 0.586 ms | 10 | 2.828 ms | 550111.971536 s | 550111.974364 s | (w)vmstat_update | 0007 | 0.363 ms | 5 | 1.634 ms | 550113.222520 s | 550113.224154 s | (w)vmstat_update | 0000 | 0.324 ms | 10 | 2.827 ms | 550111.971526 s | 550111.974354 s | (w)0xffff8e674c5f4a58 | 0002 | 0.102 ms | 5 | 0.134 ms | 550110.989839 s | 550110.989972 s | (w)psi_avgs_work | 0001 | 0.086 ms | 3 | 0.107 ms | 550114.957852 s | 550114.957959 s | (w)psi_avgs_work | 0000 | 0.079 ms | 5 | 0.100 ms | 550118.605668 s | 550118.605768 s | (w)kfree_rcu_monitor | 0006 | 0.079 ms | 1 | 0.079 ms | 550110.925821 s | 550110.925900 s | (w)psi_avgs_work | 0004 | 0.079 ms | 1 | 0.079 ms | 550109.581835 s | 550109.581914 s | (w)psi_avgs_work | 0001 | 0.078 ms | 1 | 0.078 ms | 550109.197809 s | 550109.197887 s | (w)psi_avgs_work | 0002 | 0.077 ms | 5 | 0.086 ms | 550110.669819 s | 550110.669905 s | <SNIP> # strace -e bpf -o perf-stat-bpf-counters.output perf stat -e cycles --bpf-counters sleep 1 Performance counter stats for 'sleep 1': 6,197,983 cycles 1.003922848 seconds time elapsed 0.000000000 seconds user 0.002032000 seconds sys # head -7 perf-stat-bpf-counters.output bpf(BPF_OBJ_GET, {pathname="/sys/fs/bpf/perf_attr_map", bpf_fd=0, file_flags=0}, 16) = 3 bpf(BPF_OBJ_GET_INFO_BY_FD, {info={bpf_fd=3, info_len=88, info=0x7ffcead64990}}, 16) = 0 bpf(BPF_MAP_LOOKUP_ELEM, {map_fd=3, key=0x24129e0, value=0x7ffcead65a48, flags=BPF_ANY}, 32) = 0 bpf(BPF_LINK_GET_FD_BY_ID, {link_id=1252}, 12) = -1 ENOENT (No such file or directory) bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_SOCKET_FILTER, insn_cnt=2, insns=0x7ffcead65780, license="GPL", log_level=0, log_size=0, log_buf=NULL, kern_version=KERNEL_VERSION(0, 0, 0), prog_flags=0, prog_name="", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS, prog_btf_fd=0, func_info_rec_size=0, +func_info=NULL, func_info_cnt=0, line_info_rec_size=0, line_info=NULL, line_info_cnt=0, attach_btf_id=0, attach_prog_fd=0}, 116) = 4 bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_SOCKET_FILTER, insn_cnt=2, insns=0x7ffcead65920, license="GPL", log_level=0, log_size=0, log_buf=NULL, kern_version=KERNEL_VERSION(0, 0, 0), prog_flags=0, prog_name="", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS, prog_btf_fd=0, func_info_rec_size=0, +func_info=NULL, func_info_cnt=0, line_info_rec_size=0, line_info=NULL, line_info_cnt=0, attach_btf_id=0, attach_prog_fd=0, fd_array=NULL}, 128) = 4 bpf(BPF_BTF_LOAD, {btf="\237\353\1\0\30\0\0\0\0\0\0\0\20\0\0\0\20\0\0\0\5\0\0\0\1\0\0\0\0\0\0\1"..., btf_log_buf=NULL, btf_size=45, btf_log_size=0, btf_log_level=0}, 28) = 4 # Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Suggested-by: Andrii Nakryiko <andrii@kernel.org> Tested-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Song Liu <song@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Co-developed-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/lkml/ZFU1PJrn8YtHIqno@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
1 parent ecc68ee commit a887466

File tree

3 files changed

+174
-20
lines changed

3 files changed

+174
-20
lines changed

‎tools/perf/Makefile.perf

Lines changed: 1 addition & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -1063,25 +1063,7 @@ $(BPFTOOL): | $(SKEL_TMP_OUT)
10631063
$(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \
10641064
OUTPUT=$(SKEL_TMP_OUT)/ bootstrap
10651065

1066-
VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \
1067-
$(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
1068-
../../vmlinux \
1069-
/sys/kernel/btf/vmlinux \
1070-
/boot/vmlinux-$(shell uname -r)
1071-
VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
1072-
1073-
$(SKEL_OUT)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL)
1074-
ifeq ($(VMLINUX_H),)
1075-
$(QUIET_GEN)$(BPFTOOL) btf dump file $< format c > $@ || \
1076-
(echo "Failure to generate vmlinux.h needed for the recommended BPF skeleton support." && \
1077-
echo "To disable this use the build option NO_BPF_SKEL=1." && \
1078-
echo "Alternatively point at a pre-generated vmlinux.h with VMLINUX_H=<path>." && \
1079-
false)
1080-
else
1081-
$(Q)cp "$(VMLINUX_H)" $@
1082-
endif
1083-
1084-
$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) $(SKEL_OUT)/vmlinux.h | $(SKEL_TMP_OUT)
1066+
$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT)
10851067
$(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \
10861068
-c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@
10871069

‎tools/perf/util/bpf_skel/.gitignore

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
11
# SPDX-License-Identifier: GPL-2.0-only
22
.tmp
33
*.skel.h
4-
vmlinux.h

‎tools/perf/util/bpf_skel/vmlinux.h

Lines changed: 173 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,173 @@
1+
#ifndef __VMLINUX_H
2+
#define __VMLINUX_H
3+
4+
#include <linux/bpf.h>
5+
#include <linux/types.h>
6+
#include <linux/perf_event.h>
7+
#include <stdbool.h>
8+
9+
// non-UAPI kernel data structures, used in the .bpf.c BPF tool component.
10+
11+
// Just the fields used in these tools preserving the access index so that
12+
// libbpf can fixup offsets with the ones used in the kernel when loading the
13+
// BPF bytecode, if they differ from what is used here.
14+
15+
typedef __u8 u8;
16+
typedef __u32 u32;
17+
typedef __u64 u64;
18+
typedef __s64 s64;
19+
20+
typedef int pid_t;
21+
22+
enum cgroup_subsys_id {
23+
perf_event_cgrp_id = 8,
24+
};
25+
26+
enum {
27+
HI_SOFTIRQ = 0,
28+
TIMER_SOFTIRQ,
29+
NET_TX_SOFTIRQ,
30+
NET_RX_SOFTIRQ,
31+
BLOCK_SOFTIRQ,
32+
IRQ_POLL_SOFTIRQ,
33+
TASKLET_SOFTIRQ,
34+
SCHED_SOFTIRQ,
35+
HRTIMER_SOFTIRQ,
36+
RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */
37+
38+
NR_SOFTIRQS
39+
};
40+
41+
typedef struct {
42+
s64 counter;
43+
} __attribute__((preserve_access_index)) atomic64_t;
44+
45+
typedef atomic64_t atomic_long_t;
46+
47+
struct raw_spinlock {
48+
int rawlock;
49+
} __attribute__((preserve_access_index));
50+
51+
typedef struct raw_spinlock raw_spinlock_t;
52+
53+
typedef struct {
54+
struct raw_spinlock rlock;
55+
} __attribute__((preserve_access_index)) spinlock_t;
56+
57+
struct sighand_struct {
58+
spinlock_t siglock;
59+
} __attribute__((preserve_access_index));
60+
61+
struct rw_semaphore {
62+
atomic_long_t owner;
63+
} __attribute__((preserve_access_index));
64+
65+
struct mutex {
66+
atomic_long_t owner;
67+
} __attribute__((preserve_access_index));
68+
69+
struct kernfs_node {
70+
u64 id;
71+
} __attribute__((preserve_access_index));
72+
73+
struct cgroup {
74+
struct kernfs_node *kn;
75+
int level;
76+
} __attribute__((preserve_access_index));
77+
78+
struct cgroup_subsys_state {
79+
struct cgroup *cgroup;
80+
} __attribute__((preserve_access_index));
81+
82+
struct css_set {
83+
struct cgroup_subsys_state *subsys[13];
84+
struct cgroup *dfl_cgrp;
85+
} __attribute__((preserve_access_index));
86+
87+
struct mm_struct {
88+
struct rw_semaphore mmap_lock;
89+
} __attribute__((preserve_access_index));
90+
91+
struct task_struct {
92+
unsigned int flags;
93+
struct mm_struct *mm;
94+
pid_t pid;
95+
pid_t tgid;
96+
char comm[16];
97+
struct sighand_struct *sighand;
98+
struct css_set *cgroups;
99+
} __attribute__((preserve_access_index));
100+
101+
struct trace_entry {
102+
short unsigned int type;
103+
unsigned char flags;
104+
unsigned char preempt_count;
105+
int pid;
106+
} __attribute__((preserve_access_index));
107+
108+
struct trace_event_raw_irq_handler_entry {
109+
struct trace_entry ent;
110+
int irq;
111+
u32 __data_loc_name;
112+
char __data[];
113+
} __attribute__((preserve_access_index));
114+
115+
struct trace_event_raw_irq_handler_exit {
116+
struct trace_entry ent;
117+
int irq;
118+
int ret;
119+
char __data[];
120+
} __attribute__((preserve_access_index));
121+
122+
struct trace_event_raw_softirq {
123+
struct trace_entry ent;
124+
unsigned int vec;
125+
char __data[];
126+
} __attribute__((preserve_access_index));
127+
128+
struct trace_event_raw_workqueue_execute_start {
129+
struct trace_entry ent;
130+
void *work;
131+
void *function;
132+
char __data[];
133+
} __attribute__((preserve_access_index));
134+
135+
struct trace_event_raw_workqueue_execute_end {
136+
struct trace_entry ent;
137+
void *work;
138+
void *function;
139+
char __data[];
140+
} __attribute__((preserve_access_index));
141+
142+
struct trace_event_raw_workqueue_activate_work {
143+
struct trace_entry ent;
144+
void *work;
145+
char __data[];
146+
} __attribute__((preserve_access_index));
147+
148+
struct perf_sample_data {
149+
u64 addr;
150+
u64 period;
151+
union perf_sample_weight weight;
152+
u64 txn;
153+
union perf_mem_data_src data_src;
154+
u64 ip;
155+
struct {
156+
u32 pid;
157+
u32 tid;
158+
} tid_entry;
159+
u64 time;
160+
u64 id;
161+
struct {
162+
u32 cpu;
163+
} cpu_entry;
164+
u64 phys_addr;
165+
u64 data_page_size;
166+
u64 code_page_size;
167+
} __attribute__((__aligned__(64))) __attribute__((preserve_access_index));
168+
169+
struct bpf_perf_event_data_kern {
170+
struct perf_sample_data *data;
171+
struct perf_event *event;
172+
} __attribute__((preserve_access_index));
173+
#endif // __VMLINUX_H

0 commit comments

Comments
 (0)