On 2021/3/23 8:37, Cong Wang wrote:
> From: Cong Wang <cong.wang@xxxxxxxxxxxxx>
>
> Currently we rely on lock_sock to protect ingress_msg,
> it is too big for this, we can actually just use a spinlock
> to protect this list like protecting other skb queues.
>
> __tcp_bpf_recvmsg() is still special because of peeking,
> it still has to use lock_sock.
>
> Cc: John Fastabend <john.fastabend@xxxxxxxxx>
> Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
> Cc: Lorenz Bauer <lmb@xxxxxxxxxxxxxx>
> Acked-by: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>
> Signed-off-by: Cong Wang <cong.wang@xxxxxxxxxxxxx>
> ---
> include/linux/skmsg.h | 46 +++++++++++++++++++++++++++++++++++++++++++
> net/core/skmsg.c | 3 +++
> net/ipv4/tcp_bpf.c | 18 ++++++-----------
> 3 files changed, 55 insertions(+), 12 deletions(-)
>
> diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
> index 6c09d94be2e9..f2d45a73b2b2 100644
> --- a/include/linux/skmsg.h
> +++ b/include/linux/skmsg.h
> @@ -89,6 +89,7 @@ struct sk_psock {
> #endif
> struct sk_buff_head ingress_skb;
> struct list_head ingress_msg;
> + spinlock_t ingress_lock;
> unsigned long state;
> struct list_head link;
> spinlock_t link_lock;
> @@ -284,7 +285,45 @@ static inline struct sk_psock *sk_psock(const struct sock *sk)
> static inline void sk_psock_queue_msg(struct sk_psock *psock,
> struct sk_msg *msg)
> {
> + spin_lock_bh(&psock->ingress_lock);
> list_add_tail(&msg->list, &psock->ingress_msg);
> + spin_unlock_bh(&psock->ingress_lock);
> +}
> +
> +static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock)
> +{
> + struct sk_msg *msg;
> +
> + spin_lock_bh(&psock->ingress_lock);
> + msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);
> + if (msg)
> + list_del(&msg->list);
> + spin_unlock_bh(&psock->ingress_lock);
> + return msg;
> +}
> +
> +static inline struct sk_msg *sk_psock_peek_msg(struct sk_psock *psock)
> +{
> + struct sk_msg *msg;
> +
> + spin_lock_bh(&psock->ingress_lock);
> + msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);
> + spin_unlock_bh(&psock->ingress_lock);
> + return msg;
> +}
> +
> +static inline struct sk_msg *sk_psock_next_msg(struct sk_psock *psock,
> + struct sk_msg *msg)
> +{
> + struct sk_msg *ret;
Nit:
Use msg instead of ret to be consistently with sk_psock_dequeue_msg()
and sk_psock_next_msg().
> +
> + spin_lock_bh(&psock->ingress_lock);
> + if (list_is_last(&msg->list, &psock->ingress_msg))
> + ret = NULL;
> + else
> + ret = list_next_entry(msg, list);
> + spin_unlock_bh(&psock->ingress_lock);
> + return ret;
> }
