tcp: optimise skb_zerocopy_iter_stream()

It's expensive to make a copy of 40B struct iov_iter to the point it
was taking 0.2-0.5% of all cycles in my tests. iov_iter_revert() should
be fine as it's a simple case without nested reverts/truncates.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/a7e1690c00c5dfe700c30eb9a8a81ec59f6545dd.1650884401.git.asml.silence@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b92e93dcaa91cffe9125f0bd8d5be1fe74b75895..475183f378914937f38d17410bc03570990c1f8f 100644 (file)
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1344,7 +1344,6 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
                             struct ubuf_info *uarg)
 {
        struct ubuf_info *orig_uarg = skb_zcopy(skb);
-       struct iov_iter orig_iter = msg->msg_iter;
        int err, orig_len = skb->len;
 
        /* An skb can only point to one uarg. This edge case happens when
@@ -1358,7 +1357,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
                struct sock *save_sk = skb->sk;
 
                /* Streams do not free skb on error. Reset to prev state. */
-               msg->msg_iter = orig_iter;
+               iov_iter_revert(&msg->msg_iter, skb->len - orig_len);
                skb->sk = sk;
                ___pskb_trim(skb, orig_len);
                skb->sk = save_sk;