[PATCH v4 bpf-next 2/9] bpf: Run sleepable programs with migration disabled

[Alexei Starovoitov <alexei.starovoitov@xxxxxxxxx>]

From: Alexei Starovoitov <ast@xxxxxxxxxx>

In older non-RT kernels migrate_disable() was the same as preempt_disable().
Since commit 74d862b682f5 ("sched: Make migrate_disable/enable() independent of RT")
migrate_disable() is real and doesn't prevent sleeping.
Running sleepable programs with migration disabled allows to add support for
program stats and per-cpu maps later.

Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxx>
Acked-by: KP Singh <kpsingh@xxxxxxxxxx>
---
 kernel/bpf/trampoline.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 5be3beeedd74..89fc849ba271 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -425,11 +425,13 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
 void notrace __bpf_prog_enter_sleepable(void)
 {
 	rcu_read_lock_trace();
+	migrate_disable();
 	might_fault();
 }
 
 void notrace __bpf_prog_exit_sleepable(void)
 {
+	migrate_enable();
 	rcu_read_unlock_trace();
 }
 
-- 
2.24.1