perf lock contention: Constify control data for BPF

The control knobs set before loading BPF programs should be declared as
'const volatile' so that it can be optimized by the BPF core.

Committer testing:

root@x1:~# perf lock contention --use-bpf
contended total wait max wait avg wait type caller

5 31.57 us 14.93 us 6.31 us mutex btrfs_delayed_update_inode+0x43
1 16.91 us 16.91 us 16.91 us rwsem:R btrfs_tree_read_lock_nested+0x1b
1 15.13 us 15.13 us 15.13 us spinlock btrfs_getattr+0xd1
1 6.65 us 6.65 us 6.65 us rwsem:R btrfs_tree_read_lock_nested+0x1b
1 4.34 us 4.34 us 4.34 us spinlock process_one_work+0x1a9
root@x1:~#
root@x1:~# perf trace -e bpf --max-events 10 perf lock contention --use-bpf
0.000 ( 0.013 ms): :2948281/2948281 bpf(cmd: 36, uattr: 0x7ffd5f12d730, size: 8) = -1 EOPNOTSUPP (Operation not supported)
0.024 ( 0.120 ms): :2948281/2948281 bpf(cmd: PROG_LOAD, uattr: 0x7ffd5f12d460, size: 148) = 16
0.158 ( 0.034 ms): :2948281/2948281 bpf(cmd: PROG_LOAD, uattr: 0x7ffd5f12d520, size: 148) = 16
26.653 ( 0.154 ms): perf/2948281 bpf(cmd: PROG_LOAD, uattr: 0x7ffd5f12d3d0, size: 148) = 16
26.825 ( 0.014 ms): perf/2948281 bpf(uattr: 0x7ffd5f12d580, size: 80) = 16
87.924 ( 0.038 ms): perf/2948281 bpf(cmd: BTF_LOAD, uattr: 0x7ffd5f12d400, size: 40) = 16
87.988 ( 0.006 ms): perf/2948281 bpf(cmd: BTF_LOAD, uattr: 0x7ffd5f12d470, size: 40) = 16
88.019 ( 0.006 ms): perf/2948281 bpf(cmd: BTF_LOAD, uattr: 0x7ffd5f12d250, size: 40) = 16
88.029 ( 0.172 ms): perf/2948281 bpf(cmd: PROG_LOAD, uattr: 0x7ffd5f12d320, size: 148) = 17
88.217 ( 0.005 ms): perf/2948281 bpf(cmd: BTF_LOAD, uattr: 0x7ffd5f12d4d0, size: 40) = 16
root@x1:~#

Signed-off-by: Namhyung Kim <[e-mail]>
Tested-by: Arnaldo Carvalho de Melo <[e-mail]>
Cc: Adrian Hunter <[e-mail]>
Cc: Ian Rogers <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Kan Liang <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Song Liu <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/util/bpf_lock_contention.c

···
 	else
 		bpf_map__set_max_entries(skel->maps.stacks, 1);
 
-	if (target__has_cpu(target))
+	if (target__has_cpu(target)) {
+		skel->rodata->has_cpu = 1;
 		ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
-	if (target__has_task(target))
+	}
+	if (target__has_task(target)) {
+		skel->rodata->has_task = 1;
 		ntasks = perf_thread_map__nr(evlist->core.threads);
-	if (con->filters->nr_types)
+	}
+	if (con->filters->nr_types) {
+		skel->rodata->has_type = 1;
 		ntypes = con->filters->nr_types;
-	if (con->filters->nr_cgrps)
+	}
+	if (con->filters->nr_cgrps) {
+		skel->rodata->has_cgroup = 1;
 		ncgrps = con->filters->nr_cgrps;
+	}
 
 	/* resolve lock name filters to addr */
 	if (con->filters->nr_syms) {
···
 			con->filters->addrs = addrs;
 		}
 		naddrs = con->filters->nr_addrs;
+		skel->rodata->has_addr = 1;
 	}
 
 	bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
···
 	bpf_map__set_max_entries(skel->maps.type_filter, ntypes);
 	bpf_map__set_max_entries(skel->maps.addr_filter, naddrs);
 	bpf_map__set_max_entries(skel->maps.cgroup_filter, ncgrps);
+
+	skel->rodata->stack_skip = con->stack_skip;
+	skel->rodata->aggr_mode = con->aggr_mode;
+	skel->rodata->needs_callstack = con->save_callstack;
+	skel->rodata->lock_owner = con->owner;
+
+	if (con->aggr_mode == LOCK_AGGR_CGROUP || con->filters->nr_cgrps) {
+		if (cgroup_is_v2("perf_event"))
+			skel->rodata->use_cgroup_v2 = 1;
+	}
 
 	if (lock_contention_bpf__load(skel) < 0) {
 		pr_err("Failed to load lock-contention BPF skeleton\n");
···
 		u32 cpu;
 		u8 val = 1;
 
-		skel->bss->has_cpu = 1;
 		fd = bpf_map__fd(skel->maps.cpu_filter);
 
 		for (i = 0; i < ncpus; i++) {
···
 		u32 pid;
 		u8 val = 1;
 
-		skel->bss->has_task = 1;
 		fd = bpf_map__fd(skel->maps.task_filter);
 
 		for (i = 0; i < ntasks; i++) {
···
 		u32 pid = evlist->workload.pid;
 		u8 val = 1;
 
-		skel->bss->has_task = 1;
 		fd = bpf_map__fd(skel->maps.task_filter);
 		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
 	}
···
 	if (con->filters->nr_types) {
 		u8 val = 1;
 
-		skel->bss->has_type = 1;
 		fd = bpf_map__fd(skel->maps.type_filter);
 
 		for (i = 0; i < con->filters->nr_types; i++)
···
 	if (con->filters->nr_addrs) {
 		u8 val = 1;
 
-		skel->bss->has_addr = 1;
 		fd = bpf_map__fd(skel->maps.addr_filter);
 
 		for (i = 0; i < con->filters->nr_addrs; i++)
···
 	if (con->filters->nr_cgrps) {
 		u8 val = 1;
 
-		skel->bss->has_cgroup = 1;
 		fd = bpf_map__fd(skel->maps.cgroup_filter);
 
 		for (i = 0; i < con->filters->nr_cgrps; i++)
 			bpf_map_update_elem(fd, &con->filters->cgrps[i], &val, BPF_ANY);
 	}
 
-	/* these don't work well if in the rodata section */
-	skel->bss->stack_skip = con->stack_skip;
-	skel->bss->aggr_mode = con->aggr_mode;
-	skel->bss->needs_callstack = con->save_callstack;
-	skel->bss->lock_owner = con->owner;
-
-	if (con->aggr_mode == LOCK_AGGR_CGROUP) {
-		if (cgroup_is_v2("perf_event"))
-			skel->bss->use_cgroup_v2 = 1;
-
+	if (con->aggr_mode == LOCK_AGGR_CGROUP)
 		read_all_cgroups(&con->cgroups);
-	}
 
 	bpf_program__set_autoload(skel->progs.collect_lock_syms, false);
 

tools/perf/util/bpf_skel/lock_contention.bpf.c

···
 } __attribute__((preserve_access_index));
 
 /* control flags */
-int enabled;
-int has_cpu;
-int has_task;
-int has_type;
-int has_addr;
-int has_cgroup;
-int needs_callstack;
-int stack_skip;
-int lock_owner;
-
-int use_cgroup_v2;
-int perf_subsys_id = -1;
+const volatile int has_cpu;
+const volatile int has_task;
+const volatile int has_type;
+const volatile int has_addr;
+const volatile int has_cgroup;
+const volatile int needs_callstack;
+const volatile int stack_skip;
+const volatile int lock_owner;
+const volatile int use_cgroup_v2;
 
 /* determine the key of lock stat */
-int aggr_mode;
+const volatile int aggr_mode;
+
+int enabled;
+
+int perf_subsys_id = -1;
 
 __u64 end_ts;