gve: pull network headers into skb linear part

Currently, in DQO mode with hw-gro enabled, entire received packet is
placed into skb fragments when header-split is disabled. This leaves
the skb linear part empty, forcing the networking stack to do multiple
small memory copies to access eth, IP and TCP headers.

This patch adds a single memcpy to put all headers into linear portion
before packet reaches the SW GRO stack; thus eliminating multiple
smaller memcpy calls.

Additionally, the criteria for calling napi_gro_frags() was updated.
Since skb->head is now populated, we instead check if the SKB is the
cached NAPI scratchpad to ensure we continue using the zero-allocation
path.

Signed-off-by: Ankit Garg <nktgrg@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Link: https://patch.msgid.link/20260303195549.2679070-4-joshwash@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 27885ccf52267ad5f4bc97546a4443055a5e1f3a..7924dce719e29bcf3c048d6c0df545e78e4867d1 100644 (file)
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -943,6 +943,8 @@ static int gve_rx_complete_rsc(struct sk_buff *skb,
 {
        struct skb_shared_info *shinfo = skb_shinfo(skb);
        int rsc_segments, rsc_seg_len, hdr_len;
+       skb_frag_t *frag;
+       void *va;
 
        /* HW-GRO only coalesces TCP. */
        if (ptype.l4_type != GVE_L4_TYPE_TCP)
@@ -970,10 +972,20 @@ static int gve_rx_complete_rsc(struct sk_buff *skb,
                /* HW-GRO packets are guaranteed to have complete TCP/IP
                 * headers in frag[0] when header-split is not enabled.
                 */
-               hdr_len = eth_get_headlen(skb->dev,
-                                         skb_frag_address(&shinfo->frags[0]),
-                                         skb_frag_size(&shinfo->frags[0]));
+               frag = &skb_shinfo(skb)->frags[0];
+               va = skb_frag_address(frag);
+               hdr_len =
+                       eth_get_headlen(skb->dev, va, skb_frag_size(frag));
                rsc_segments = DIV_ROUND_UP(skb->len - hdr_len, rsc_seg_len);
+               skb_copy_to_linear_data(skb, va, hdr_len);
+               skb_frag_size_sub(frag, hdr_len);
+               /* Verify we didn't empty the fragment completely as that could
+                * otherwise lead to page leaks.
+                */
+               DEBUG_NET_WARN_ON_ONCE(!skb_frag_size(frag));
+               skb_frag_off_add(frag, hdr_len);
+               skb->data_len -= hdr_len;
+               skb->tail += hdr_len;
        }
        shinfo->gso_size = rsc_seg_len;
        shinfo->gso_segs = rsc_segments;
@@ -1010,7 +1022,7 @@ static int gve_rx_complete_skb(struct gve_rx_ring *rx, struct napi_struct *napi,
                        return err;
        }
 
-       if (skb_headlen(rx->ctx.skb_head) == 0)
+       if (rx->ctx.skb_head == napi->skb)
                napi_gro_frags(napi);
        else
                napi_gro_receive(napi, rx->ctx.skb_head);