This makes sense, thanks!
Acked-by: Petar Penkov <ppenkov@xxxxxxxxxx>
On Wed, Aug 21, 2019 at 5:19 AM Jakub Sitnicki <jakub@xxxxxxxxxxxxxx> wrote:
>
> Call to bpf_prog_put(), with help of call_rcu(), queues an RCU-callback to
> free the program once a grace period has elapsed. The callback can run
> together with new RCU readers that started after the last grace period.
> New RCU readers can potentially see the "old" to-be-freed or already-freed
> pointer to the program object before the RCU update-side NULLs it.
>
> Reorder the operations so that the RCU update-side resets the protected
> pointer before the end of the grace period after which the program will be
> freed.
>
> Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook")
> Reported-by: Lorenz Bauer <lmb@xxxxxxxxxxxxxx>
> Signed-off-by: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>
> ---
> net/core/flow_dissector.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
> index 3e6fedb57bc1..2470b4b404e6 100644
> --- a/net/core/flow_dissector.c
> +++ b/net/core/flow_dissector.c
> @@ -142,8 +142,8 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
> mutex_unlock(&flow_dissector_mutex);
> return -ENOENT;
> }
> - bpf_prog_put(attached);
> RCU_INIT_POINTER(net->flow_dissector_prog, NULL);
> + bpf_prog_put(attached);
> mutex_unlock(&flow_dissector_mutex);
> return 0;
> }
> --
> 2.20.1
>
