gro: add ability to control gro max packet size

Eric Dumazet suggested to allow users to modify max GRO packet size.

We have seen GRO being disabled by users of appliances (such as
wifi access points) because of claimed bufferbloat issues,
or some work arounds in sch_cake, to split GRO/GSO packets.

Instead of disabling GRO completely, one can chose to limit
the maximum packet size of GRO packets, depending on their
latency constraints.

This patch adds a per device gro_max_size attribute
that can be changed with ip link command.

ip link set dev eth0 gro_max_size 16000

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Coco Li <lixiaoyan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 28 insertions, 1 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 6c8b226b5f2f..83a4089990a0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10180,6 +10180,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
+	dev->gro_max_size = GRO_MAX_SIZE;
 	dev->upper_level = 1;
 	dev->lower_level = 1;
 #ifdef CONFIG_LOCKDEP
diff --git a/net/core/gro.c b/net/core/gro.c
index 8ec8b44596da..a11b286d1495 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -132,10 +132,14 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	unsigned int headlen = skb_headlen(skb);
 	unsigned int len = skb_gro_len(skb);
 	unsigned int delta_truesize;
+	unsigned int gro_max_size;
 	unsigned int new_truesize;
 	struct sk_buff *lp;
 
-	if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush))
+	/* pairs with WRITE_ONCE() in netif_set_gro_max_size() */
+	gro_max_size = READ_ONCE(p->dev->gro_max_size);
+
+	if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush))
 		return -E2BIG;
 
 	lp = NAPI_GRO_CB(p)->last;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d6eba554b137..e476403231f0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1026,6 +1026,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */
 	       + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */
 	       + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */
+	       + nla_total_size(4) /* IFLA_GRO_MAX_SIZE */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
@@ -1728,6 +1729,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	    nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) ||
 	    nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) ||
 	    nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) ||
+	    nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) ||
 #ifdef CONFIG_RPS
 	    nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
 #endif
@@ -1880,6 +1882,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED },
 	[IFLA_NEW_IFINDEX]	= NLA_POLICY_MIN(NLA_S32, 1),
 	[IFLA_PARENT_DEV_NAME]	= { .type = NLA_NUL_STRING },
+	[IFLA_GRO_MAX_SIZE]	= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2299,6 +2302,14 @@ 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;
 }
 
@@ -2772,6 +2783,15 @@ static int do_setlink(const struct sk_buff *skb,
 		}
 	}
 
+	if (tb[IFLA_GRO_MAX_SIZE]) {
+		u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]);
+
+		if (dev->gro_max_size ^ gro_max_size) {
+			netif_set_gro_max_size(dev, gro_max_size);
+			status |= DO_SETLINK_MODIFIED;
+		}
+	}
+
 	if (tb[IFLA_OPERSTATE])
 		set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
 
@@ -3222,6 +3242,8 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 		netif_set_gso_max_size(dev, nla_get_u32(tb[IFLA_GSO_MAX_SIZE]));
 	if (tb[IFLA_GSO_MAX_SEGS])
 		netif_set_gso_max_segs(dev, nla_get_u32(tb[IFLA_GSO_MAX_SEGS]));
+	if (tb[IFLA_GRO_MAX_SIZE])
+		netif_set_gro_max_size(dev, nla_get_u32(tb[IFLA_GRO_MAX_SIZE]));
 
 	return dev;
 }