Re: [PATCH bpf-next] bpf: Remove migrate_disable in kprobe_multi_link_prog_run

[Tao Chen]

在 2025/8/6 00:04, Jiri Olsa 写道:

On Tue, Aug 05, 2025 at 08:23:12PM +0800, Tao Chen wrote:

bpf program should run under migration disabled, kprobe_multi_link_prog_run
called the way from graph tracer, which disables preemption in
function_graph_enter_regs, as Jiri and Yonghong suggested, there is no
need to use migrate_disable. As a result, some overhead maybe will be
reduced.

Fixes: 0dcac2725406 ("bpf: Add multi kprobe link")
Signed-off-by: Tao Chen <chen.dyl...@linux.dev>

Acked-by: Jiri Olsa <jo...@kernel.org>

thanks,
jirka

---
  kernel/trace/bpf_trace.c | 9 +++++++--
  1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3ae52978cae..1993fc62539 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2734,14 +2734,19 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link 
*link,
                goto out;
        }

- migrate_disable();

+       /*
+        * bpf program should run under migration disabled, 
kprobe_multi_link_prog_run
+        * called the way from graph tracer, which disables preemption in

nit, s/called the way/called all the way/

will fix it, thanks.

+        * function_graph_enter_regs, so there is no need to use 
migrate_disable.
+        * Accessing the above percpu data bpf_prog_active is also safe for the 
same
+        * reason.
+        */
        rcu_read_lock();
        regs = ftrace_partial_regs(fregs, bpf_kprobe_multi_pt_regs_ptr());
        old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx);
        err = bpf_prog_run(link->link.prog, regs);
        bpf_reset_run_ctx(old_run_ctx);
        rcu_read_unlock();
-       migrate_enable();

out:

        __this_cpu_dec(bpf_prog_active);
--
2.48.1

--
Best Regards
Tao Chen