tcp: adjust rcv zerocopy hints based on frag sizes

When SKBs are coalesced, we can have SKBs with different
frag sizes. Some with PAGE_SIZE and some not with PAGE_SIZE.
Since recv_skip_hint is always set to the full SKB size,
it can overestimate the amount that should be read using
normal read for coalesced packets.

Change the recv_skip_hint so that it only includes the first
frags that are not of PAGE_SIZE.

Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 78ac4d2e3827486eac1c37e5e4a5aa3bddf7c957..2827fa5643bde84633b174914bbb13a8273e9d32 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1805,8 +1805,17 @@ static int tcp_zerocopy_receive(struct sock *sk,
                                frags++;
                        }
                }
-               if (frags->size != PAGE_SIZE || frags->page_offset)
+               if (frags->size != PAGE_SIZE || frags->page_offset) {
+                       int remaining = zc->recv_skip_hint;
+
+                       while (remaining && (frags->size != PAGE_SIZE ||
+                                            frags->page_offset)) {
+                               remaining -= frags->size;
+                               frags++;
+                       }
+                       zc->recv_skip_hint -= remaining;
                        break;
+               }
                ret = vm_insert_page(vma, address + length,
                                     skb_frag_page(frags));
                if (ret)