net: allow gro_max_size to exceed 65536

Allow the gro_max_size to exceed a value larger than 65536.

There weren't really any external limitations that prevented this other
than the fact that IPv4 only supports a 16 bit length field. Since we have
the option of adding a hop-by-hop header for IPv6 we can allow IPv6 to
exceed this value and for IPv4 and non-TCP flows we can cap things at 65536
via a constant rather than relying on gro_max_size.

[edumazet] limit GRO_MAX_SIZE to (8 * 65535) to avoid overflows.

Signed-off-by: Alexander Duyck <[email protected]>
Signed-off-by: Eric Dumazet <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: ahduyck

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -2038,7 +2038,7 @@ mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt)
 {
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 
-	return PAGE_SIZE * nr_frags + data_bcnt <= GRO_MAX_SIZE;
+	return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE;
 }
 
 static void

include/linux/netdevice.h

@@ -2161,7 +2161,11 @@ struct net_device {
 	struct bpf_prog __rcu	*xdp_prog;
 	unsigned long		gro_flush_timeout;
 	int			napi_defer_hard_irqs;
-#define GRO_MAX_SIZE		65536
+#define GRO_LEGACY_MAX_SIZE	65536u
+/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
+ * and shinfo->gso_segs is a 16bit field.
+ */
+#define GRO_MAX_SIZE		(8 * 65535u)
 	unsigned int		gro_max_size;
 	rx_handler_func_t __rcu	*rx_handler;
 	void __rcu		*rx_handler_data;

include/net/ipv6.h

@@ -477,7 +477,7 @@ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb)
 	const struct hop_jumbo_hdr *jhdr;
 	const struct ipv6hdr *nhdr;
 
-	if (likely(skb->len <= GRO_MAX_SIZE))
+	if (likely(skb->len <= GRO_LEGACY_MAX_SIZE))
 		return 0;
 
 	if (skb->protocol != htons(ETH_P_IPV6))

net/core/dev.c

@@ -10598,7 +10598,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
-	dev->gro_max_size = GRO_MAX_SIZE;
+	dev->gro_max_size = GRO_LEGACY_MAX_SIZE;
 	dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
 	dev->tso_max_segs = TSO_MAX_SEGS;
 	dev->upper_level = 1;

net/core/gro.c

@@ -167,6 +167,14 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush))
 		return -E2BIG;
 
+	if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) {
+		if (p->protocol != htons(ETH_P_IPV6) ||
+		    skb_headroom(p) < sizeof(struct hop_jumbo_hdr) ||
+		    ipv6_hdr(p)->nexthdr != IPPROTO_TCP ||
+		    p->encapsulation)
+			return -E2BIG;
+	}
+
 	lp = NAPI_GRO_CB(p)->last;
 	pinfo = skb_shinfo(lp);
 

net/core/rtnetlink.c

@@ -2360,14 +2360,6 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
 		}
 	}
 
-	if (tb[IFLA_GRO_MAX_SIZE]) {
-		u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]);
-
-		if (gro_max_size > GRO_MAX_SIZE) {
-			NL_SET_ERR_MSG(extack, "too big gro_max_size");
-			return -EINVAL;
-		}
-	}
 	return 0;
 }