On Sun, Mar 5, 2017 at 10:42 PM, Eric Dumazet <eric.duma...@gmail.com> wrote: > On Sun, 2017-03-05 at 21:38 -0800, Cong Wang wrote: > >> Do you really want to disable BH again here? >> >> dccp_check_req() should be always called on RX path where BH >> is already disabled and BH can't be disabled twice? > > What makes you think BH can't be disabled twice ? > > Look, I prefer being cautious here, no need to get another DCCP bug > report later.
Hmm, I thought BH should have a local_bh_save() to save its context but looking into its implementation it uses the preempt count to determine if BH is disabled or not, unlikely hardirq's. Sorry for the noise.