net: gro: decouple GRO from the NAPI layer

In fact, these two are not tied closely to each other. The only
requirements to GRO are to use it in the BH context and have some
sane limits on the packet batches, e.g. NAPI has a limit of its
budget (64/8/etc.).
Move purely GRO fields into a new structure, &gro_node. Embed it
into &napi_struct and adjust all the references.
gro_node::cached_napi_id is effectively the same as
napi_struct::napi_id, but to be used on GRO hotpath to mark skbs.
napi_struct::napi_id is now a fully control path field.

Three Ethernet drivers use napi_gro_flush() not really meant to be
exported, so move it to <net/gro.h> and add that include there.
napi_gro_receive() is used in more than 100 drivers, keep it
in <linux/netdevice.h>.
This does not make GRO ready to use outside of the NAPI context
yet.

Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

2 files changed, 34 insertions, 13 deletions

diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index cab6146a510a..6e172d0f6ef5 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -127,18 +127,24 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 }
 
 /* used in the NIC receive handler to mark the skb */
-static inline void skb_mark_napi_id(struct sk_buff *skb,
-				    struct napi_struct *napi)
+static inline void __skb_mark_napi_id(struct sk_buff *skb,
+				      const struct gro_node *gro)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	/* If the skb was already marked with a valid NAPI ID, avoid overwriting
 	 * it.
 	 */
 	if (!napi_id_valid(skb->napi_id))
-		skb->napi_id = napi->napi_id;
+		skb->napi_id = gro->cached_napi_id;
 #endif
 }
 
+static inline void skb_mark_napi_id(struct sk_buff *skb,
+				    const struct napi_struct *napi)
+{
+	__skb_mark_napi_id(skb, &napi->gro);
+}
+
 /* used in the protocol handler to propagate the napi_id to the socket */
 static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 {
diff --git a/include/net/gro.h b/include/net/gro.h
index 7b548f91754b..38d70c69ff80 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -509,26 +509,41 @@ static inline int gro_receive_network_flush(const void *th, const void *th2,
 
 int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
 int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb);
+void __gro_flush(struct gro_node *gro, bool flush_old);
+
+static inline void gro_flush(struct gro_node *gro, bool flush_old)
+{
+	if (!gro->bitmask)
+		return;
+
+	__gro_flush(gro, flush_old);
+}
+
+static inline void napi_gro_flush(struct napi_struct *napi, bool flush_old)
+{
+	gro_flush(&napi->gro, flush_old);
+}
 
 /* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
-static inline void gro_normal_list(struct napi_struct *napi)
+static inline void gro_normal_list(struct gro_node *gro)
 {
-	if (!napi->rx_count)
+	if (!gro->rx_count)
 		return;
-	netif_receive_skb_list_internal(&napi->rx_list);
-	INIT_LIST_HEAD(&napi->rx_list);
-	napi->rx_count = 0;
+	netif_receive_skb_list_internal(&gro->rx_list);
+	INIT_LIST_HEAD(&gro->rx_list);
+	gro->rx_count = 0;
 }
 
 /* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
  * pass the whole batch up to the stack.
  */
-static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs)
+static inline void gro_normal_one(struct gro_node *gro, struct sk_buff *skb,
+				  int segs)
 {
-	list_add_tail(&skb->list, &napi->rx_list);
-	napi->rx_count += segs;
-	if (napi->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch))
-		gro_normal_list(napi);
+	list_add_tail(&skb->list, &gro->rx_list);
+	gro->rx_count += segs;
+	if (gro->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch))
+		gro_normal_list(gro);
 }
 
 /* This function is the alternative of 'inet_iif' and 'inet_sdif'