net: add gso_ipv4_max_size and gro_ipv4_max_size per device

This patch introduces gso_ipv4_max_size and gro_ipv4_max_size
per device and adds netlink attributes for them, so that IPV4
BIG TCP can be guarded by a separate tunable in the next patch.

To not break the old application using "gso/gro_max_size" for
IPv4 GSO packets, this patch updates "gso/gro_ipv4_max_size"
in netif_set_gso/gro_max_size() if the new size isn't greater
than GSO_LEGACY_MAX_SIZE, so that nothing will change even if
userspace doesn't realize the new netlink attributes.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/netdevice.h

@@ -1964,6 +1964,8 @@ enum netdev_ml_priv_type {
  *	@gso_max_segs:	Maximum number of segments that can be passed to the
  *			NIC for GSO
  *	@tso_max_segs:	Device (as in HW) limit on the max TSO segment count
+ * 	@gso_ipv4_max_size:	Maximum size of generic segmentation offload,
+ * 				for IPv4.
  *
  *	@dcbnl_ops:	Data Center Bridging netlink ops
  *	@num_tc:	Number of traffic classes in the net device
@@ -2004,6 +2006,8 @@ enum netdev_ml_priv_type {
  *			keep a list of interfaces to be deleted.
  *	@gro_max_size:	Maximum size of aggregated packet in generic
  *			receive offload (GRO)
+ * 	@gro_ipv4_max_size:	Maximum size of aggregated packet in generic
+ * 				receive offload (GRO), for IPv4.
  *
  *	@dev_addr_shadow:	Copy of @dev_addr to catch direct writes.
  *	@linkwatch_dev_tracker:	refcount tracker used by linkwatch.
@@ -2207,6 +2211,7 @@ struct net_device {
  */
 #define GRO_MAX_SIZE		(8 * 65535u)
 	unsigned int		gro_max_size;
+	unsigned int		gro_ipv4_max_size;
 	rx_handler_func_t __rcu	*rx_handler;
 	void __rcu		*rx_handler_data;
 
@@ -2330,6 +2335,7 @@ struct net_device {
 	u16			gso_max_segs;
 #define TSO_MAX_SEGS		U16_MAX
 	u16			tso_max_segs;
+	unsigned int		gso_ipv4_max_size;
 
 #ifdef CONFIG_DCB
 	const struct dcbnl_rtnl_ops *dcbnl_ops;

include/uapi/linux/if_link.h

@@ -374,6 +374,9 @@ enum {
 
 	IFLA_DEVLINK_PORT,
 
+	IFLA_GSO_IPV4_MAX_SIZE,
+	IFLA_GRO_IPV4_MAX_SIZE,
+
 	__IFLA_MAX
 };
 

net/core/dev.c

@@ -3001,6 +3001,8 @@ void netif_set_tso_max_size(struct net_device *dev, unsigned int size)
 	dev->tso_max_size = min(GSO_MAX_SIZE, size);
 	if (size < READ_ONCE(dev->gso_max_size))
 		netif_set_gso_max_size(dev, size);
+	if (size < READ_ONCE(dev->gso_ipv4_max_size))
+		netif_set_gso_ipv4_max_size(dev, size);
 }
 EXPORT_SYMBOL(netif_set_tso_max_size);
 
@@ -10614,6 +10616,8 @@ 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_LEGACY_MAX_SIZE;
+	dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE;
+	dev->gro_ipv4_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/dev.h

@@ -100,6 +100,8 @@ static inline void netif_set_gso_max_size(struct net_device *dev,
 {
 	/* dev->gso_max_size is read locklessly from sk_setup_caps() */
 	WRITE_ONCE(dev->gso_max_size, size);
+	if (size <= GSO_LEGACY_MAX_SIZE)
+		WRITE_ONCE(dev->gso_ipv4_max_size, size);
 }
 
 static inline void netif_set_gso_max_segs(struct net_device *dev,
@@ -114,6 +116,22 @@ static inline void netif_set_gro_max_size(struct net_device *dev,
 {
 	/* This pairs with the READ_ONCE() in skb_gro_receive() */
 	WRITE_ONCE(dev->gro_max_size, size);
+	if (size <= GRO_LEGACY_MAX_SIZE)
+		WRITE_ONCE(dev->gro_ipv4_max_size, size);
+}
+
+static inline void netif_set_gso_ipv4_max_size(struct net_device *dev,
+					       unsigned int size)
+{
+	/* dev->gso_ipv4_max_size is read locklessly from sk_setup_caps() */
+	WRITE_ONCE(dev->gso_ipv4_max_size, size);
+}
+
+static inline void netif_set_gro_ipv4_max_size(struct net_device *dev,
+					       unsigned int size)
+{
+	/* This pairs with the READ_ONCE() in skb_gro_receive() */
+	WRITE_ONCE(dev->gro_ipv4_max_size, size);
 }
 
 #endif

net/core/rtnetlink.c

@@ -1074,6 +1074,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + 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(4) /* IFLA_GSO_IPV4_MAX_SIZE */
+	       + nla_total_size(4) /* IFLA_GRO_IPV4_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_TSO_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_TSO_MAX_SEGS */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
@@ -1807,6 +1809,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	    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) ||
+	    nla_put_u32(skb, IFLA_GSO_IPV4_MAX_SIZE, dev->gso_ipv4_max_size) ||
+	    nla_put_u32(skb, IFLA_GRO_IPV4_MAX_SIZE, dev->gro_ipv4_max_size) ||
 	    nla_put_u32(skb, IFLA_TSO_MAX_SIZE, dev->tso_max_size) ||
 	    nla_put_u32(skb, IFLA_TSO_MAX_SEGS, dev->tso_max_segs) ||
 #ifdef CONFIG_RPS
@@ -1968,6 +1972,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_TSO_MAX_SIZE]	= { .type = NLA_REJECT },
 	[IFLA_TSO_MAX_SEGS]	= { .type = NLA_REJECT },
 	[IFLA_ALLMULTI]		= { .type = NLA_REJECT },
+	[IFLA_GSO_IPV4_MAX_SIZE]	= { .type = NLA_U32 },
+	[IFLA_GRO_IPV4_MAX_SIZE]	= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2883,6 +2889,29 @@ static int do_setlink(const struct sk_buff *skb,
 		}
 	}
 
+	if (tb[IFLA_GSO_IPV4_MAX_SIZE]) {
+		u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]);
+
+		if (max_size > dev->tso_max_size) {
+			err = -EINVAL;
+			goto errout;
+		}
+
+		if (dev->gso_ipv4_max_size ^ max_size) {
+			netif_set_gso_ipv4_max_size(dev, max_size);
+			status |= DO_SETLINK_MODIFIED;
+		}
+	}
+
+	if (tb[IFLA_GRO_IPV4_MAX_SIZE]) {
+		u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]);
+
+		if (dev->gro_ipv4_max_size ^ gro_max_size) {
+			netif_set_gro_ipv4_max_size(dev, gro_max_size);
+			status |= DO_SETLINK_MODIFIED;
+		}
+	}
+
 	if (tb[IFLA_OPERSTATE])
 		set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
 
@@ -3325,6 +3354,10 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 		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]));
+	if (tb[IFLA_GSO_IPV4_MAX_SIZE])
+		netif_set_gso_ipv4_max_size(dev, nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]));
+	if (tb[IFLA_GRO_IPV4_MAX_SIZE])
+		netif_set_gro_ipv4_max_size(dev, nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]));
 
 	return dev;
 }