Pavel Begunkov wrote:
> Instead of accounting every page range against the socket separately, do
> it in batch based on the change in skb->truesize. It's also moved into
> __zerocopy_sg_from_iter(), so that zerocopy_fill_skb_from_iter() is
> simpler and responsible for setting frags but not the accounting.
>
> Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
Reviewed-by: Willem de Bruijn <willemb@xxxxxxxxxx>
> ---
> net/core/datagram.c | 31 ++++++++++++++++++-------------
> 1 file changed, 18 insertions(+), 13 deletions(-)
>
> diff --git a/net/core/datagram.c b/net/core/datagram.c
> index 7f7d5da2e406..2b24d69b1e94 100644
> --- a/net/core/datagram.c
> +++ b/net/core/datagram.c
> @@ -610,7 +610,7 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
> }
> EXPORT_SYMBOL(skb_copy_datagram_from_iter);
>
> -static int zerocopy_fill_skb_from_iter(struct sock *sk, struct sk_buff *skb,
> +static int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
> struct iov_iter *from, size_t length)
> {
> int frag = skb_shinfo(skb)->nr_frags;
> @@ -621,7 +621,6 @@ static int zerocopy_fill_skb_from_iter(struct sock *sk, struct sk_buff *skb,
> int refs, order, n = 0;
> size_t start;
> ssize_t copied;
> - unsigned long truesize;
>
> if (frag == MAX_SKB_FRAGS)
> return -EMSGSIZE;
Does the existing code then incorrectly not unwind sk_wmem_queued_add
and sk_mem_charge if returning with error from the second or later
loop..
> @@ -633,17 +632,9 @@ static int zerocopy_fill_skb_from_iter(struct sock *sk, struct sk_buff *skb,
>
> length -= copied;
>
> - truesize = PAGE_ALIGN(copied + start);
> skb->data_len += copied;
> skb->len += copied;
> - skb->truesize += truesize;
> - if (sk && sk->sk_type == SOCK_STREAM) {
> - sk_wmem_queued_add(sk, truesize);
> - if (!skb_zcopy_pure(skb))
> - sk_mem_charge(sk, truesize);
> - } else {
> - refcount_add(truesize, &skb->sk->sk_wmem_alloc);
> - }
> + skb->truesize += PAGE_ALIGN(copied + start);
>
> head = compound_head(pages[n]);
> order = compound_order(head);
> @@ -691,10 +682,24 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
> struct sk_buff *skb, struct iov_iter *from,
> size_t length)
> {
> + unsigned long orig_size = skb->truesize;
> + unsigned long truesize;
> + int ret;
> +
> if (msg && msg->msg_ubuf && msg->sg_from_iter)
> return msg->sg_from_iter(sk, skb, from, length);
> - else
> - return zerocopy_fill_skb_from_iter(sk, skb, from, length);
> +
> + ret = zerocopy_fill_skb_from_iter(skb, from, length);
> + truesize = skb->truesize - orig_size;
> +
> + if (sk && sk->sk_type == SOCK_STREAM) {
> + sk_wmem_queued_add(sk, truesize);
> + if (!skb_zcopy_pure(skb))
> + sk_mem_charge(sk, truesize);
> + } else {
> + refcount_add(truesize, &skb->sk->sk_wmem_alloc);
> + }
> + return ret;
> }
> EXPORT_SYMBOL(__zerocopy_sg_from_iter);
>
> --
> 2.44.0
>
