gro: decrease size of CB

The GRO control block (NAPI_GRO_CB) is currently at its maximum size.
This commit reduces its size by putting two groups of fields that are
used only at different times into a union.

Specifically, the fields frag0 and frag0_len are the fields that make up
the frag0 optimisation mechanism, which is used during the initial
parsing of the SKB.

The fields last and age are used after the initial parsing, while the
SKB is stored in the GRO list, waiting for other packets to arrive.

There was one location in dev_gro_receive that modified the frag0 fields
after setting last and age. I changed this accordingly without altering
the code behaviour.

Signed-off-by: Richard Gobert <[e-mail]>
Reviewed-by: Eric Dumazet <[e-mail]>
Link: https://lore.kernel.org/r/20230601161407.GA9253@debian
Signed-off-by: Paolo Abeni <[e-mail]>

include/net/gro.h

···
 #include <net/udp.h>
 
 struct napi_gro_cb {
-	/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
-	void	*frag0;
+	union {
+		struct {
+			/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
+			void	*frag0;
 
-	/* Length of frag0. */
-	unsigned int frag0_len;
+			/* Length of frag0. */
+			unsigned int frag0_len;
+		};
+
+		struct {
+			/* used in skb_gro_receive() slow path */
+			struct sk_buff *last;
+
+			/* jiffies when first packet was created/queued */
+			unsigned long age;
+		};
+	};
 
 	/* This indicates where we are processing relative to skb->data. */
 	int	data_offset;
···
 
 	/* Used in ipv6_gro_receive() and foo-over-udp */
 	u16	proto;
-
-	/* jiffies when first packet was created/queued */
-	unsigned long age;
 
 /* Used in napi_gro_cb::free */
 #define NAPI_GRO_FREE             1
···
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
-
-	/* used in skb_gro_receive() slow path */
-	struct sk_buff *last;
 };
 
 #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)

net/core/gro.c

···
 	}
 }
 
+static void gro_try_pull_from_frag0(struct sk_buff *skb)
+{
+	int grow = skb_gro_offset(skb) - skb_headlen(skb);
+
+	if (grow > 0)
+		gro_pull_from_frag0(skb, grow);
+}
+
 static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
 {
 	struct sk_buff *oldest;
···
 	struct sk_buff *pp = NULL;
 	enum gro_result ret;
 	int same_flow;
-	int grow;
 
 	if (netif_elide_gro(skb->dev))
 		goto normal;
···
 	else
 		gro_list->count++;
 
+	/* Must be called before setting NAPI_GRO_CB(skb)->{age|last} */
+	gro_try_pull_from_frag0(skb);
 	NAPI_GRO_CB(skb)->age = jiffies;
 	NAPI_GRO_CB(skb)->last = skb;
 	if (!skb_is_gso(skb))
 		skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	list_add(&skb->list, &gro_list->list);
 	ret = GRO_HELD;
-
-pull:
-	grow = skb_gro_offset(skb) - skb_headlen(skb);
-	if (grow > 0)
-		gro_pull_from_frag0(skb, grow);
 ok:
 	if (gro_list->count) {
 		if (!test_bit(bucket, &napi->gro_bitmask))
···
 
 normal:
 	ret = GRO_NORMAL;
-	goto pull;
+	gro_try_pull_from_frag0(skb);
+	goto ok;
 }
 
 struct packet_offload *gro_find_receive_by_type(__be16 type)