[PATCH 3/4] perf record: Implement basic filtering for off-cpu

[Namhyung Kim]

It should honor cpu and task filtering with -a, -C or -p, -t options.

Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
---
 tools/perf/builtin-record.c            |  2 +-
 tools/perf/util/bpf_off_cpu.c          | 78 +++++++++++++++++++++++---
 tools/perf/util/bpf_skel/off_cpu.bpf.c | 52 +++++++++++++++--
 tools/perf/util/off_cpu.h              |  6 +-
 4 files changed, 123 insertions(+), 15 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4e0285ca9a2d..c9b78e2b74bb 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -907,7 +907,7 @@ static int record__config_text_poke(struct evlist *evlist)
 
 static int record__config_off_cpu(struct record *rec)
 {
-	return off_cpu_prepare(rec->evlist);
+	return off_cpu_prepare(rec->evlist, &rec->opts.target);
 }
 
 static bool record__kcore_readable(struct machine *machine)
diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index 1f87d2a9b86d..89f36229041d 100644
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -6,6 +6,9 @@
 #include "util/off_cpu.h"
 #include "util/perf-hooks.h"
 #include "util/session.h"
+#include "util/target.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
 #include <bpf/bpf.h>
 
 #include "bpf_skel/off_cpu.skel.h"
@@ -57,8 +60,23 @@ static int off_cpu_config(struct evlist *evlist)
 	return 0;
 }
 
-static void off_cpu_start(void *arg __maybe_unused)
+static void off_cpu_start(void *arg)
 {
+	struct evlist *evlist = arg;
+
+	/* update task filter for the given workload */
+	if (!skel->bss->has_cpu && !skel->bss->has_task &&
+	    perf_thread_map__pid(evlist->core.threads, 0) != -1) {
+		int fd;
+		u32 pid;
+		u8 val = 1;
+
+		skel->bss->has_task = 1;
+		fd = bpf_map__fd(skel->maps.task_filter);
+		pid = perf_thread_map__pid(evlist->core.threads, 0);
+		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
+	}
+
 	skel->bss->enabled = 1;
 }
 
@@ -68,31 +86,75 @@ static void off_cpu_finish(void *arg __maybe_unused)
 	off_cpu_bpf__destroy(skel);
 }
 
-int off_cpu_prepare(struct evlist *evlist)
+int off_cpu_prepare(struct evlist *evlist, struct target *target)
 {
-	int err;
+	int err, fd, i;
+	int ncpus = 1, ntasks = 1;
 
 	if (off_cpu_config(evlist) < 0) {
 		pr_err("Failed to config off-cpu BPF event\n");
 		return -1;
 	}
 
-	set_max_rlimit();
-
-	skel = off_cpu_bpf__open_and_load();
+	skel = off_cpu_bpf__open();
 	if (!skel) {
 		pr_err("Failed to open off-cpu skeleton\n");
 		return -1;
 	}
 
+	/* don't need to set cpu filter for system-wide mode */
+	if (target->cpu_list) {
+		ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
+		bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
+	}
+
+	if (target__has_task(target)) {
+		ncpus = perf_thread_map__nr(evlist->core.threads);
+		bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
+	}
+
+	set_max_rlimit();
+
+	err = off_cpu_bpf__load(skel);
+	if (err) {
+		pr_err("Failed to load off-cpu skeleton\n");
+		goto out;
+	}
+
+	if (target->cpu_list) {
+		u32 cpu;
+		u8 val = 1;
+
+		skel->bss->has_cpu = 1;
+		fd = bpf_map__fd(skel->maps.cpu_filter);
+
+		for (i = 0; i < ncpus; i++) {
+			cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, i).cpu;
+			bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
+		}
+	}
+
+	if (target__has_task(target)) {
+		u32 pid;
+		u8 val = 1;
+
+		skel->bss->has_task = 1;
+		fd = bpf_map__fd(skel->maps.task_filter);
+
+		for (i = 0; i < ntasks; i++) {
+			pid = perf_thread_map__pid(evlist->core.threads, i);
+			bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
+		}
+	}
+
 	err = off_cpu_bpf__attach(skel);
 	if (err) {
 		pr_err("Failed to attach off-cpu skeleton\n");
 		goto out;
 	}
 
-	if (perf_hooks__set_hook("record_start", off_cpu_start, NULL) ||
-	    perf_hooks__set_hook("record_end", off_cpu_finish, NULL)) {
+	if (perf_hooks__set_hook("record_start", off_cpu_start, evlist) ||
+	    perf_hooks__set_hook("record_end", off_cpu_finish, evlist)) {
 		pr_err("Failed to attach off-cpu skeleton\n");
 		goto out;
 	}
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index 5173ed882fdf..c35106b9e20b 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -49,12 +49,28 @@ struct {
 	__uint(max_entries, MAX_ENTRIES);
 } off_cpu SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} cpu_filter SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} task_filter SEC(".maps");
+
 /* old kernel task_struct definition */
 struct task_struct___old {
 	long state;
 } __attribute__((preserve_access_index));
 
 int enabled = 0;
+int has_cpu = 0;
+int has_task = 0;
 
 /*
  * Old kernel used to call it task_struct->state and now it's '__state'.
@@ -74,6 +90,37 @@ static inline int get_task_state(struct task_struct *t)
 	return BPF_CORE_READ(t_old, state);
 }
 
+static inline int can_record(struct task_struct *t, int state)
+{
+	if (has_cpu) {
+		__u32 cpu = bpf_get_smp_processor_id();
+		__u8 *ok;
+
+		ok = bpf_map_lookup_elem(&cpu_filter, &cpu);
+		if (!ok)
+			return 0;
+	}
+
+	if (has_task) {
+		__u8 *ok;
+		__u32 pid = t->pid;
+
+		ok = bpf_map_lookup_elem(&task_filter, &pid);
+		if (!ok)
+			return 0;
+	}
+
+	/* kernel threads don't have user stack */
+	if (t->flags & PF_KTHREAD)
+		return 0;
+
+	if (state != TASK_INTERRUPTIBLE &&
+	    state != TASK_UNINTERRUPTIBLE)
+		return 0;
+
+	return 1;
+}
+
 SEC("tp_btf/sched_switch")
 int on_switch(u64 *ctx)
 {
@@ -92,10 +139,7 @@ int on_switch(u64 *ctx)
 
 	ts = bpf_ktime_get_ns();
 
-	if (prev->flags & PF_KTHREAD)
-		goto next;
-	if (state != TASK_INTERRUPTIBLE &&
-	    state != TASK_UNINTERRUPTIBLE)
+	if (!can_record(prev, state))
 		goto next;
 
 	stack_id = bpf_get_stackid(ctx, &stacks,
diff --git a/tools/perf/util/off_cpu.h b/tools/perf/util/off_cpu.h
index 4113bd19a2e4..864d6148dfd3 100644
--- a/tools/perf/util/off_cpu.h
+++ b/tools/perf/util/off_cpu.h
@@ -2,13 +2,15 @@
 #define PERF_UTIL_OFF_CPU_H
 
 struct evlist;
+struct target;
 struct perf_session;
 
 #ifdef HAVE_BPF_SKEL
-int off_cpu_prepare(struct evlist *evlist);
+int off_cpu_prepare(struct evlist *evlist, struct target *target);
 int off_cpu_write(struct perf_session *session);
 #else
-static inline int off_cpu_prepare(struct evlist *evlist __maybe_unused)
+static inline int off_cpu_prepare(struct evlist *evlist __maybe_unused,
+				  struct target *target __maybe_unused)
 {
 	return -1;
 }
-- 
2.36.0.512.ge40c2bad7a-goog