Merge branch 'l3_hw_offload'

Scott Feldman says:

====================
switchdev: add IPv4 routing offload

v4:

  - Add NETIF_F_NETNS_LOCAL to rocker port feature list to keep rocker
    ports in the default netns.  Rocker hardware can't be partitioned
    to support multiple namespaces, currently.  It would be interesting
    to add netns support to rocker device by basically adding another
    match field to each table to match on some unique netns ID, with
    a port knowing it's netns ID.  Future work TDB.
  - Up-level the RTNH_F_EXTERNAL marking of routes installed to offload
    device from driver to switchdev common code.  Now driver can't skip
    routes.  Either it can install the route or it cannot.  Yes or No.
    If no on any route, all offloading is aborted by removing routes
    from offload device and setting ipv4.fib_offload_disabled so no more
    routes can be offloaded.  This is harsh, but it's our starting point.
    We can refine the policies in follow-up work.
  - Add new net.ipv4.fib_offload_disabled bool that is set if anything
    goes wrong with route offloading.  We can refine this later to make
    the setting per-device or per-device-port-netdev, but let's start
    here simple and refine in follow-up work.
  - Rebase against Alex's latest FIB changes.  I think I did everything
    correctly, and didn't run into any issues with testing, but I'd like
    Alex to look over the changes and maybe follow-up with any cleanups.

v3:

Changes based on v2 review comments:

  - Move check for custom rules up earlier in patch set, to keep git bisect
    safe.
  - Simplify the route add/modify failure handling to simple try until
    failure, and then on failure, undo everything.  The switchdev driver
    will return err when route can normally be installed to device, but
    the install fails for one reason or another (no space left on device,
    etc).  If a failure happens, uninstall all routes from the device,
    punting forwarding for all routes back to the kernel.
  - Scan route's full nexthop list, ensuring all nexthop devs belong
    to the same switchdev device, otherwise don't try to install route
    to device.

v2:

Changes based on v1 review comments and discussions at netconf:

  - Allow route modification, but use same ndo op used for adding route.
    Driver/device is expected to modify route in-place, if it can, to avoid
    interruption of service.
  - Add new RTNH_F_EXTERNAL flag to mark FIB entries offloaded externally.
  - Don't offload routes if using custom IP rules.  If routes are already
    offloaded, and custom IP rules are turned on, flush routes from offload
    device.  (Offloaded routes are marked with RTNH_F_EXTERNAL).
  - Use kernel's neigh resolution code to resolve route's nexthops' neigh
    MAC addrs.  (Thanks davem, works great!).
  - Use fib->fib_priority in rocker driver to give priorities to routes in
    OF-DPA unicast route table.

v1:

This patch set adds L3 routing offload support for IPv4 routes.  The idea is to
mirror routes installed in the kernel's FIB down to a hardware switch device to
offload the data forwarding path for L3.  Only the data forwarding path is
intercepted.  Control and management of the kernel's FIB remains with the
kernel.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/rocker/rocker.c

@@ -32,6 +32,9 @@
 #include <linux/bitops.h>
 #include <net/switchdev.h>
 #include <net/rtnetlink.h>
+#include <net/ip_fib.h>
+#include <net/netevent.h>
+#include <net/arp.h>
 #include <asm-generic/io-64-nonatomic-lo-hi.h>
 #include <generated/utsrelease.h>
 
@@ -111,9 +114,10 @@ struct rocker_flow_tbl_key {
 
 struct rocker_flow_tbl_entry {
 	struct hlist_node entry;
-	u32 ref_count;
+	u32 cmd;
 	u64 cookie;
 	struct rocker_flow_tbl_key key;
+	size_t key_len;
 	u32 key_crc32; /* key */
 };
 
@@ -161,6 +165,16 @@ struct rocker_internal_vlan_tbl_entry {
 	__be16 vlan_id;
 };
 
+struct rocker_neigh_tbl_entry {
+	struct hlist_node entry;
+	__be32 ip_addr; /* key */
+	struct net_device *dev;
+	u32 ref_count;
+	u32 index;
+	u8 eth_dst[ETH_ALEN];
+	bool ttl_check;
+};
+
 struct rocker_desc_info {
 	char *data; /* mapped */
 	size_t data_size;
@@ -234,6 +248,9 @@ struct rocker {
 	unsigned long internal_vlan_bitmap[ROCKER_INTERNAL_VLAN_BITMAP_LEN];
 	DECLARE_HASHTABLE(internal_vlan_tbl, 8);
 	spinlock_t internal_vlan_tbl_lock;
+	DECLARE_HASHTABLE(neigh_tbl, 16);
+	spinlock_t neigh_tbl_lock;
+	u32 neigh_tbl_next_index;
 };
 
 static const u8 zero_mac[ETH_ALEN]   = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
@@ -256,7 +273,6 @@ enum {
 	ROCKER_PRIORITY_VLAN = 1,
 	ROCKER_PRIORITY_TERM_MAC_UCAST = 0,
 	ROCKER_PRIORITY_TERM_MAC_MCAST = 1,
-	ROCKER_PRIORITY_UNICAST_ROUTING = 1,
 	ROCKER_PRIORITY_BRIDGING_VLAN_DFLT_EXACT = 1,
 	ROCKER_PRIORITY_BRIDGING_VLAN_DFLT_WILD = 2,
 	ROCKER_PRIORITY_BRIDGING_VLAN = 3,
@@ -1940,8 +1956,7 @@ static int rocker_cmd_flow_tbl_add(struct rocker *rocker,
 	struct rocker_tlv *cmd_info;
 	int err = 0;
 
-	if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE,
-			       ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_ADD))
+	if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE, entry->cmd))
 		return -EMSGSIZE;
 	cmd_info = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO);
 	if (!cmd_info)
@@ -1998,8 +2013,7 @@ static int rocker_cmd_flow_tbl_del(struct rocker *rocker,
 	const struct rocker_flow_tbl_entry *entry = priv;
 	struct rocker_tlv *cmd_info;
 
-	if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE,
-			       ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_DEL))
+	if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE, entry->cmd))
 		return -EMSGSIZE;
 	cmd_info = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO);
 	if (!cmd_info)
@@ -2168,9 +2182,9 @@ static int rocker_cmd_group_tbl_del(struct rocker *rocker,
 	return 0;
 }
 
-/*****************************************
- * Flow, group, FDB, internal VLAN tables
- *****************************************/
+/***************************************************
+ * Flow, group, FDB, internal VLAN and neigh tables
+ ***************************************************/
 
 static int rocker_init_tbls(struct rocker *rocker)
 {
@@ -2186,6 +2200,9 @@ static int rocker_init_tbls(struct rocker *rocker)
 	hash_init(rocker->internal_vlan_tbl);
 	spin_lock_init(&rocker->internal_vlan_tbl_lock);
 
+	hash_init(rocker->neigh_tbl);
+	spin_lock_init(&rocker->neigh_tbl_lock);
+
 	return 0;
 }
 
@@ -2196,6 +2213,7 @@ static void rocker_free_tbls(struct rocker *rocker)
 	struct rocker_group_tbl_entry *group_entry;
 	struct rocker_fdb_tbl_entry *fdb_entry;
 	struct rocker_internal_vlan_tbl_entry *internal_vlan_entry;
+	struct rocker_neigh_tbl_entry *neigh_entry;
 	struct hlist_node *tmp;
 	int bkt;
 
@@ -2219,16 +2237,22 @@ static void rocker_free_tbls(struct rocker *rocker)
 			   tmp, internal_vlan_entry, entry)
 		hash_del(&internal_vlan_entry->entry);
 	spin_unlock_irqrestore(&rocker->internal_vlan_tbl_lock, flags);
+
+	spin_lock_irqsave(&rocker->neigh_tbl_lock, flags);
+	hash_for_each_safe(rocker->neigh_tbl, bkt, tmp, neigh_entry, entry)
+		hash_del(&neigh_entry->entry);
+	spin_unlock_irqrestore(&rocker->neigh_tbl_lock, flags);
 }
 
 static struct rocker_flow_tbl_entry *
 rocker_flow_tbl_find(struct rocker *rocker, struct rocker_flow_tbl_entry *match)
 {
 	struct rocker_flow_tbl_entry *found;
+	size_t key_len = match->key_len ? match->key_len : sizeof(found->key);
 
 	hash_for_each_possible(rocker->flow_tbl, found,
 			       entry, match->key_crc32) {
-		if (memcmp(&found->key, &match->key, sizeof(found->key)) == 0)
+		if (memcmp(&found->key, &match->key, key_len) == 0)
 			return found;
 	}
 
@@ -2241,42 +2265,34 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port,
 {
 	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_flow_tbl_entry *found;
+	size_t key_len = match->key_len ? match->key_len : sizeof(found->key);
 	unsigned long flags;
-	bool add_to_hw = false;
-	int err = 0;
 
-	match->key_crc32 = crc32(~0, &match->key, sizeof(match->key));
+	match->key_crc32 = crc32(~0, &match->key, key_len);
 
 	spin_lock_irqsave(&rocker->flow_tbl_lock, flags);
 
 	found = rocker_flow_tbl_find(rocker, match);
 
 	if (found) {
-		kfree(match);
+		match->cookie = found->cookie;
+		hash_del(&found->entry);
+		kfree(found);
+		found = match;
+		found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_MOD;
 	} else {
 		found = match;
 		found->cookie = rocker->flow_tbl_next_cookie++;
-		hash_add(rocker->flow_tbl, &found->entry, found->key_crc32);
-		add_to_hw = true;
+		found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_ADD;
 	}
 
-	found->ref_count++;
+	hash_add(rocker->flow_tbl, &found->entry, found->key_crc32);
 
 	spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags);
 
-	if (add_to_hw) {
-		err = rocker_cmd_exec(rocker, rocker_port,
+	return rocker_cmd_exec(rocker, rocker_port,
 			       rocker_cmd_flow_tbl_add,
 			       found, NULL, NULL, nowait);
-		if (err) {
-			spin_lock_irqsave(&rocker->flow_tbl_lock, flags);
-			hash_del(&found->entry);
-			spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags);
-			kfree(found);
-		}
-	}
-
-	return err;
 }
 
 static int rocker_flow_tbl_del(struct rocker_port *rocker_port,
@@ -2285,29 +2301,26 @@ static int rocker_flow_tbl_del(struct rocker_port *rocker_port,
 {
 	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_flow_tbl_entry *found;
+	size_t key_len = match->key_len ? match->key_len : sizeof(found->key);
 	unsigned long flags;
-	bool del_from_hw = false;
 	int err = 0;
 
-	match->key_crc32 = crc32(~0, &match->key, sizeof(match->key));
+	match->key_crc32 = crc32(~0, &match->key, key_len);
 
 	spin_lock_irqsave(&rocker->flow_tbl_lock, flags);
 
 	found = rocker_flow_tbl_find(rocker, match);
 
 	if (found) {
-		found->ref_count--;
-		if (found->ref_count == 0) {
 		hash_del(&found->entry);
-			del_from_hw = true;
-		}
+		found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_DEL;
 	}
 
 	spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags);
 
 	kfree(match);
 
-	if (del_from_hw) {
+	if (found) {
 		err = rocker_cmd_exec(rocker, rocker_port,
 				      rocker_cmd_flow_tbl_del,
 				      found, NULL, NULL, nowait);
@@ -2467,6 +2480,31 @@ static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port,
 	return rocker_flow_tbl_do(rocker_port, flags, entry);
 }
 
+static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port,
+					  __be16 eth_type, __be32 dst,
+					  __be32 dst_mask, u32 priority,
+					  enum rocker_of_dpa_table_id goto_tbl,
+					  u32 group_id, int flags)
+{
+	struct rocker_flow_tbl_entry *entry;
+
+	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	if (!entry)
+		return -ENOMEM;
+
+	entry->key.tbl_id = ROCKER_OF_DPA_TABLE_ID_UNICAST_ROUTING;
+	entry->key.priority = priority;
+	entry->key.ucast_routing.eth_type = eth_type;
+	entry->key.ucast_routing.dst4 = dst;
+	entry->key.ucast_routing.dst4_mask = dst_mask;
+	entry->key.ucast_routing.goto_tbl = goto_tbl;
+	entry->key.ucast_routing.group_id = group_id;
+	entry->key_len = offsetof(struct rocker_flow_tbl_key,
+				  ucast_routing.group_id);
+
+	return rocker_flow_tbl_do(rocker_port, flags, entry);
+}
+
 static int rocker_flow_tbl_acl(struct rocker_port *rocker_port,
 			       int flags, u32 in_pport,
 			       u32 in_pport_mask,
@@ -2554,7 +2592,6 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port,
 	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_group_tbl_entry *found;
 	unsigned long flags;
-	int err = 0;
 
 	spin_lock_irqsave(&rocker->group_tbl_lock, flags);
 
@@ -2574,12 +2611,9 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port,
 
 	spin_unlock_irqrestore(&rocker->group_tbl_lock, flags);
 
-	if (found->cmd)
-		err = rocker_cmd_exec(rocker, rocker_port,
+	return rocker_cmd_exec(rocker, rocker_port,
 			       rocker_cmd_group_tbl_add,
 			       found, NULL, NULL, nowait);
-
-	return err;
 }
 
 static int rocker_group_tbl_del(struct rocker_port *rocker_port,
@@ -2675,6 +2709,244 @@ static int rocker_group_l2_flood(struct rocker_port *rocker_port,
 				       group_id);
 }
 
+static int rocker_group_l3_unicast(struct rocker_port *rocker_port,
+				   int flags, u32 index, u8 *src_mac,
+				   u8 *dst_mac, __be16 vlan_id,
+				   bool ttl_check, u32 pport)
+{
+	struct rocker_group_tbl_entry *entry;
+
+	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	if (!entry)
+		return -ENOMEM;
+
+	entry->group_id = ROCKER_GROUP_L3_UNICAST(index);
+	if (src_mac)
+		ether_addr_copy(entry->l3_unicast.eth_src, src_mac);
+	if (dst_mac)
+		ether_addr_copy(entry->l3_unicast.eth_dst, dst_mac);
+	entry->l3_unicast.vlan_id = vlan_id;
+	entry->l3_unicast.ttl_check = ttl_check;
+	entry->l3_unicast.group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, pport);
+
+	return rocker_group_tbl_do(rocker_port, flags, entry);
+}
+
+static struct rocker_neigh_tbl_entry *
+	rocker_neigh_tbl_find(struct rocker *rocker, __be32 ip_addr)
+{
+	struct rocker_neigh_tbl_entry *found;
+
+	hash_for_each_possible(rocker->neigh_tbl, found, entry, ip_addr)
+		if (found->ip_addr == ip_addr)
+			return found;
+
+	return NULL;
+}
+
+static void _rocker_neigh_add(struct rocker *rocker,
+			      struct rocker_neigh_tbl_entry *entry)
+{
+	entry->index = rocker->neigh_tbl_next_index++;
+	entry->ref_count++;
+	hash_add(rocker->neigh_tbl, &entry->entry, entry->ip_addr);
+}
+
+static void _rocker_neigh_del(struct rocker *rocker,
+			      struct rocker_neigh_tbl_entry *entry)
+{
+	if (--entry->ref_count == 0) {
+		hash_del(&entry->entry);
+		kfree(entry);
+	}
+}
+
+static void _rocker_neigh_update(struct rocker *rocker,
+				 struct rocker_neigh_tbl_entry *entry,
+				 u8 *eth_dst, bool ttl_check)
+{
+	if (eth_dst) {
+		ether_addr_copy(entry->eth_dst, eth_dst);
+		entry->ttl_check = ttl_check;
+	} else {
+		entry->ref_count++;
+	}
+}
+
+static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port,
+				  int flags, __be32 ip_addr, u8 *eth_dst)
+{
+	struct rocker *rocker = rocker_port->rocker;
+	struct rocker_neigh_tbl_entry *entry;
+	struct rocker_neigh_tbl_entry *found;
+	unsigned long lock_flags;
+	__be16 eth_type = htons(ETH_P_IP);
+	enum rocker_of_dpa_table_id goto_tbl =
+		ROCKER_OF_DPA_TABLE_ID_ACL_POLICY;
+	u32 group_id;
+	u32 priority = 0;
+	bool adding = !(flags & ROCKER_OP_FLAG_REMOVE);
+	bool updating;
+	bool removing;
+	int err = 0;
+
+	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	if (!entry)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&rocker->neigh_tbl_lock, lock_flags);
+
+	found = rocker_neigh_tbl_find(rocker, ip_addr);
+
+	updating = found && adding;
+	removing = found && !adding;
+	adding = !found && adding;
+
+	if (adding) {
+		entry->ip_addr = ip_addr;
+		entry->dev = rocker_port->dev;
+		ether_addr_copy(entry->eth_dst, eth_dst);
+		entry->ttl_check = true;
+		_rocker_neigh_add(rocker, entry);
+	} else if (removing) {
+		memcpy(entry, found, sizeof(*entry));
+		_rocker_neigh_del(rocker, found);
+	} else if (updating) {
+		_rocker_neigh_update(rocker, found, eth_dst, true);
+		memcpy(entry, found, sizeof(*entry));
+	} else {
+		err = -ENOENT;
+	}
+
+	spin_unlock_irqrestore(&rocker->neigh_tbl_lock, lock_flags);
+
+	if (err)
+		goto err_out;
+
+	/* For each active neighbor, we have an L3 unicast group and
+	 * a /32 route to the neighbor, which uses the L3 unicast
+	 * group.  The L3 unicast group can also be referred to by
+	 * other routes' nexthops.
+	 */
+
+	err = rocker_group_l3_unicast(rocker_port, flags,
+				      entry->index,
+				      rocker_port->dev->dev_addr,
+				      entry->eth_dst,
+				      rocker_port->internal_vlan_id,
+				      entry->ttl_check,
+				      rocker_port->pport);
+	if (err) {
+		netdev_err(rocker_port->dev,
+			   "Error (%d) L3 unicast group index %d\n",
+			   err, entry->index);
+		goto err_out;
+	}
+
+	if (adding || removing) {
+		group_id = ROCKER_GROUP_L3_UNICAST(entry->index);
+		err = rocker_flow_tbl_ucast4_routing(rocker_port,
+						     eth_type, ip_addr,
+						     inet_make_mask(32),
+						     priority, goto_tbl,
+						     group_id, flags);
+
+		if (err)
+			netdev_err(rocker_port->dev,
+				   "Error (%d) /32 unicast route %pI4 group 0x%08x\n",
+				   err, &entry->ip_addr, group_id);
+	}
+
+err_out:
+	if (!adding)
+		kfree(entry);
+
+	return err;
+}
+
+static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port,
+				    __be32 ip_addr)
+{
+	struct net_device *dev = rocker_port->dev;
+	struct neighbour *n = __ipv4_neigh_lookup(dev, ip_addr);
+	int err = 0;
+
+	if (!n)
+		n = neigh_create(&arp_tbl, &ip_addr, dev);
+	if (!n)
+		return -ENOMEM;
+
+	/* If the neigh is already resolved, then go ahead and
+	 * install the entry, otherwise start the ARP process to
+	 * resolve the neigh.
+	 */
+
+	if (n->nud_state & NUD_VALID)
+		err = rocker_port_ipv4_neigh(rocker_port, 0, ip_addr, n->ha);
+	else
+		neigh_event_send(n, NULL);
+
+	return err;
+}
+
+static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags,
+			       __be32 ip_addr, u32 *index)
+{
+	struct rocker *rocker = rocker_port->rocker;
+	struct rocker_neigh_tbl_entry *entry;
+	struct rocker_neigh_tbl_entry *found;
+	unsigned long lock_flags;
+	bool adding = !(flags & ROCKER_OP_FLAG_REMOVE);
+	bool updating;
+	bool removing;
+	bool resolved = true;
+	int err = 0;
+
+	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	if (!entry)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&rocker->neigh_tbl_lock, lock_flags);
+
+	found = rocker_neigh_tbl_find(rocker, ip_addr);
+	if (found)
+		*index = found->index;
+
+	updating = found && adding;
+	removing = found && !adding;
+	adding = !found && adding;
+
+	if (adding) {
+		entry->ip_addr = ip_addr;
+		entry->dev = rocker_port->dev;
+		_rocker_neigh_add(rocker, entry);
+		*index = entry->index;
+		resolved = false;
+	} else if (removing) {
+		_rocker_neigh_del(rocker, found);
+	} else if (updating) {
+		_rocker_neigh_update(rocker, found, NULL, false);
+		resolved = !is_zero_ether_addr(found->eth_dst);
+	} else {
+		err = -ENOENT;
+	}
+
+	spin_unlock_irqrestore(&rocker->neigh_tbl_lock, lock_flags);
+
+	if (!adding)
+		kfree(entry);
+
+	if (err)
+		return err;
+
+	/* Resolved means neigh ip_addr is resolved to neigh mac. */
+
+	if (!resolved)
+		err = rocker_port_ipv4_resolve(rocker_port, ip_addr);
+
+	return err;
+}
+
 static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port,
 					int flags, __be16 vlan_id)
 {
@@ -3429,6 +3701,51 @@ static void rocker_port_internal_vlan_id_put(struct rocker_port *rocker_port,
 	spin_unlock_irqrestore(&rocker->internal_vlan_tbl_lock, lock_flags);
 }
 
+static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, __be32 dst,
+				int dst_len, struct fib_info *fi, u32 tb_id,
+				int flags)
+{
+	struct fib_nh *nh;
+	__be16 eth_type = htons(ETH_P_IP);
+	__be32 dst_mask = inet_make_mask(dst_len);
+	__be16 internal_vlan_id = rocker_port->internal_vlan_id;
+	u32 priority = fi->fib_priority;
+	enum rocker_of_dpa_table_id goto_tbl =
+		ROCKER_OF_DPA_TABLE_ID_ACL_POLICY;
+	u32 group_id;
+	bool nh_on_port;
+	bool has_gw;
+	u32 index;
+	int err;
+
+	/* XXX support ECMP */
+
+	nh = fi->fib_nh;
+	nh_on_port = (fi->fib_dev == rocker_port->dev);
+	has_gw = !!nh->nh_gw;
+
+	if (has_gw && nh_on_port) {
+		err = rocker_port_ipv4_nh(rocker_port, flags,
+					  nh->nh_gw, &index);
+		if (err)
+			return err;
+
+		group_id = ROCKER_GROUP_L3_UNICAST(index);
+	} else {
+		/* Send to CPU for processing */
+		group_id = ROCKER_GROUP_L2_INTERFACE(internal_vlan_id, 0);
+	}
+
+	err = rocker_flow_tbl_ucast4_routing(rocker_port, eth_type, dst,
+					     dst_mask, priority, goto_tbl,
+					     group_id, flags);
+	if (err)
+		netdev_err(rocker_port->dev, "Error (%d) IPv4 route %pI4\n",
+			   err, &dst);
+
+	return err;
+}
+
 /*****************
  * Net device ops
  *****************/
@@ -3830,6 +4147,30 @@ static int rocker_port_switch_port_stp_update(struct net_device *dev, u8 state)
 	return rocker_port_stp_update(rocker_port, state);
 }
 
+static int rocker_port_switch_fib_ipv4_add(struct net_device *dev,
+					   __be32 dst, int dst_len,
+					   struct fib_info *fi,
+					   u8 tos, u8 type, u32 tb_id)
+{
+	struct rocker_port *rocker_port = netdev_priv(dev);
+	int flags = 0;
+
+	return rocker_port_fib_ipv4(rocker_port, dst, dst_len,
+				    fi, tb_id, flags);
+}
+
+static int rocker_port_switch_fib_ipv4_del(struct net_device *dev,
+					   __be32 dst, int dst_len,
+					   struct fib_info *fi,
+					   u8 tos, u8 type, u32 tb_id)
+{
+	struct rocker_port *rocker_port = netdev_priv(dev);
+	int flags = ROCKER_OP_FLAG_REMOVE;
+
+	return rocker_port_fib_ipv4(rocker_port, dst, dst_len,
+				    fi, tb_id, flags);
+}
+
 static const struct net_device_ops rocker_port_netdev_ops = {
 	.ndo_open			= rocker_port_open,
 	.ndo_stop			= rocker_port_stop,
@@ -3844,6 +4185,8 @@ static const struct net_device_ops rocker_port_netdev_ops = {
 	.ndo_bridge_getlink		= rocker_port_bridge_getlink,
 	.ndo_switch_parent_id_get	= rocker_port_switch_parent_id_get,
 	.ndo_switch_port_stp_update	= rocker_port_switch_port_stp_update,
+	.ndo_switch_fib_ipv4_add	= rocker_port_switch_fib_ipv4_add,
+	.ndo_switch_fib_ipv4_del	= rocker_port_switch_fib_ipv4_del,
 };
 
 /********************
@@ -4204,7 +4547,8 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
 		       NAPI_POLL_WEIGHT);
 	rocker_carrier_init(rocker_port);
 
-	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
+	dev->features |= NETIF_F_NETNS_LOCAL |
+			 NETIF_F_HW_VLAN_CTAG_FILTER |
 			 NETIF_F_HW_SWITCH_OFFLOAD;
 
 	err = register_netdev(dev);
@@ -4546,6 +4890,48 @@ static struct notifier_block rocker_netdevice_nb __read_mostly = {
 	.notifier_call = rocker_netdevice_event,
 };
 
+/************************************
+ * Net event notifier event handler
+ ************************************/
+
+static int rocker_neigh_update(struct net_device *dev, struct neighbour *n)
+{
+	struct rocker_port *rocker_port = netdev_priv(dev);
+	int flags = (n->nud_state & NUD_VALID) ? 0 : ROCKER_OP_FLAG_REMOVE;
+	__be32 ip_addr = *(__be32 *)n->primary_key;
+
+	return rocker_port_ipv4_neigh(rocker_port, flags, ip_addr, n->ha);
+}
+
+static int rocker_netevent_event(struct notifier_block *unused,
+				 unsigned long event, void *ptr)
+{
+	struct net_device *dev;
+	struct neighbour *n = ptr;
+	int err;
+
+	switch (event) {
+	case NETEVENT_NEIGH_UPDATE:
+		if (n->tbl != &arp_tbl)
+			return NOTIFY_DONE;
+		dev = n->dev;
+		if (!rocker_port_dev_check(dev))
+			return NOTIFY_DONE;
+		err = rocker_neigh_update(dev, n);
+		if (err)
+			netdev_warn(dev,
+				    "failed to handle neigh update (err %d)\n",
+				    err);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block rocker_netevent_nb __read_mostly = {
+	.notifier_call = rocker_netevent_event,
+};
+
 /***********************
  * Module init and exit
  ***********************/
@@ -4555,18 +4941,21 @@ static int __init rocker_module_init(void)
 	int err;
 
 	register_netdevice_notifier(&rocker_netdevice_nb);
+	register_netevent_notifier(&rocker_netevent_nb);
 	err = pci_register_driver(&rocker_pci_driver);
 	if (err)
 		goto err_pci_register_driver;
 	return 0;
 
 err_pci_register_driver:
+	unregister_netdevice_notifier(&rocker_netevent_nb);
 	unregister_netdevice_notifier(&rocker_netdevice_nb);
 	return err;
 }
 
 static void __exit rocker_module_exit(void)
 {
+	unregister_netevent_notifier(&rocker_netevent_nb);
 	unregister_netdevice_notifier(&rocker_netdevice_nb);
 	pci_unregister_driver(&rocker_pci_driver);
 }

include/linux/netdevice.h

@@ -768,6 +768,8 @@ struct netdev_phys_item_id {
 typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
 				       struct sk_buff *skb);
 
+struct fib_info;
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -1031,6 +1033,14 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  * int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state);
  *	Called to notify switch device port of bridge port STP
  *	state change.
+ * int (*ndo_sw_parent_fib_ipv4_add)(struct net_device *dev, __be32 dst,
+ *				     int dst_len, struct fib_info *fi,
+ *				     u8 tos, u8 type, u32 tb_id);
+ *	Called to add/modify IPv4 route to switch device.
+ * int (*ndo_sw_parent_fib_ipv4_del)(struct net_device *dev, __be32 dst,
+ *				     int dst_len, struct fib_info *fi,
+ *				     u8 tos, u8 type, u32 tb_id);
+ *	Called to delete IPv4 route from switch device.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1192,6 +1202,18 @@ struct net_device_ops {
 							    struct netdev_phys_item_id *psid);
 	int			(*ndo_switch_port_stp_update)(struct net_device *dev,
 							      u8 state);
+	int			(*ndo_switch_fib_ipv4_add)(struct net_device *dev,
+							   __be32 dst,
+							   int dst_len,
+							   struct fib_info *fi,
+							   u8 tos, u8 type,
+							   u32 tb_id);
+	int			(*ndo_switch_fib_ipv4_del)(struct net_device *dev,
+							   __be32 dst,
+							   int dst_len,
+							   struct fib_info *fi,
+							   u8 tos, u8 type,
+							   u32 tb_id);
 #endif
 };
 

include/net/ip_fib.h

@@ -196,6 +196,7 @@ int fib_table_delete(struct fib_table *, struct fib_config *);
 int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
 		   struct netlink_callback *cb);
 int fib_table_flush(struct fib_table *table);
+void fib_table_flush_external(struct fib_table *table);
 void fib_free_table(struct fib_table *tb);
 
 
@@ -308,6 +309,7 @@ static inline int fib_num_tclassid_users(struct net *net)
 	return 0;
 }
 #endif
+void fib_flush_external(struct net *net);
 
 /* Exported by fib_semantics.c */
 int ip_fib_check_default(__be32 gw, struct net_device *dev);

include/net/netns/ipv4.h

@@ -47,6 +47,7 @@ struct netns_ipv4 {
 	int			fib_num_tclassid_users;
 #endif
 	struct hlist_head	*fib_table_hash;
+	bool			fib_offload_disabled;
 	struct sock		*fibnl;
 
 	struct sock  * __percpu	*icmp_sk;

include/net/switchdev.h

@@ -51,6 +51,12 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
 					       struct nlmsghdr *nlh, u16 flags);
 int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev,
 					       struct nlmsghdr *nlh, u16 flags);
+int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
+			       u8 tos, u8 type, u32 tb_id);
+int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
+			       u8 tos, u8 type, u32 tb_id);
+void netdev_switch_fib_ipv4_abort(struct fib_info *fi);
+
 #else
 
 static inline int netdev_switch_parent_id_get(struct net_device *dev,
@@ -109,6 +115,24 @@ static inline int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *
 	return 0;
 }
 
+static inline int netdev_switch_fib_ipv4_add(u32 dst, int dst_len,
+					     struct fib_info *fi,
+					     u8 tos, u8 type, u32 tb_id)
+{
+	return 0;
+}
+
+static inline int netdev_switch_fib_ipv4_del(u32 dst, int dst_len,
+					     struct fib_info *fi,
+					     u8 tos, u8 type, u32 tb_id)
+{
+	return 0;
+}
+
+void netdev_switch_fib_ipv4_abort(struct fib_info *fi)
+{
+}
+
 #endif
 
 #endif /* _LINUX_SWITCHDEV_H_ */

include/uapi/linux/rtnetlink.h

@@ -334,6 +334,7 @@ struct rtnexthop {
 #define RTNH_F_DEAD		1	/* Nexthop is dead (used by multipath)	*/
 #define RTNH_F_PERVASIVE	2	/* Do recursive gateway lookup	*/
 #define RTNH_F_ONLINK		4	/* Gateway is forced on link	*/
+#define RTNH_F_EXTERNAL		8	/* Route installed externally	*/
 
 /* Macros to handle hexthops */
 

net/ipv4/fib_frontend.c

@@ -144,6 +144,19 @@ static void fib_flush(struct net *net)
 		rt_cache_flush(net);
 }
 
+void fib_flush_external(struct net *net)
+{
+	struct fib_table *tb;
+	struct hlist_head *head;
+	unsigned int h;
+
+	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
+		head = &net->ipv4.fib_table_hash[h];
+		hlist_for_each_entry(tb, head, tb_hlist)
+			fib_table_flush_external(tb);
+	}
+}
+
 /*
  * Find address type as if only "dev" was present in the system. If
  * on_dev is NULL then all interfaces are taken into consideration.

net/ipv4/fib_rules.c

@@ -209,6 +209,8 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	rule4->tos = frh->tos;
 
 	net->ipv4.fib_has_custom_rules = true;
+	fib_flush_external(rule->fr_net);
+
 	err = 0;
 errout:
 	return err;
@@ -224,6 +226,7 @@ static void fib4_rule_delete(struct fib_rule *rule)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	net->ipv4.fib_has_custom_rules = true;
+	fib_flush_external(rule->fr_net);
 }
 
 static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,

net/ipv4/fib_trie.c

@@ -79,6 +79,7 @@
 #include <net/tcp.h>
 #include <net/sock.h>
 #include <net/ip_fib.h>
+#include <net/switchdev.h>
 #include "fib_lookup.h"
 
 #define MAX_STAT_DEPTH 32
@@ -1135,7 +1136,18 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			new_fa->fa_state = state & ~FA_S_ACCESSED;
 			new_fa->fa_slen = fa->fa_slen;
 
+			err = netdev_switch_fib_ipv4_add(key, plen, fi,
+							 new_fa->fa_tos,
+							 cfg->fc_type,
+							 tb->tb_id);
+			if (err) {
+				netdev_switch_fib_ipv4_abort(fi);
+				kmem_cache_free(fn_alias_kmem, new_fa);
+				goto out;
+			}
+
 			hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list);
+
 			alias_free_mem_rcu(fa);
 
 			fib_release_info(fi_drop);
@@ -1171,10 +1183,18 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 	new_fa->fa_state = 0;
 	new_fa->fa_slen = slen;
 
+	/* (Optionally) offload fib entry to switch hardware. */
+	err = netdev_switch_fib_ipv4_add(key, plen, fi, tos,
+					 cfg->fc_type, tb->tb_id);
+	if (err) {
+		netdev_switch_fib_ipv4_abort(fi);
+		goto out_free_new_fa;
+	}
+
 	/* Insert new entry to the list. */
 	err = fib_insert_alias(t, tp, l, new_fa, fa, key);
 	if (err)
-		goto out_free_new_fa;
+		goto out_sw_fib_del;
 
 	if (!plen)
 		tb->tb_num_default++;
@@ -1185,6 +1205,8 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 succeeded:
 	return 0;
 
+out_sw_fib_del:
+	netdev_switch_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id);
 out_free_new_fa:
 	kmem_cache_free(fn_alias_kmem, new_fa);
 out:
@@ -1456,6 +1478,9 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
 	if (!fa_to_delete)
 		return -ESRCH;
 
+	netdev_switch_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos,
+				   cfg->fc_type, tb->tb_id);
+
 	rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
 		  &cfg->fc_nlinfo, 0);
 
@@ -1536,6 +1561,67 @@ static struct tnode *leaf_walk_rcu(struct tnode **tn, t_key key)
 	return n;
 }
 
+/* Caller must hold RTNL */
+void fib_table_flush_external(struct fib_table *tb)
+{
+	struct trie *t = (struct trie *)tb->tb_data;
+	struct fib_alias *fa;
+	struct tnode *n, *pn;
+	unsigned long cindex;
+	unsigned char slen;
+	int found = 0;
+
+	n = rcu_dereference(t->trie);
+	if (!n)
+		return;
+
+	pn = NULL;
+	cindex = 0;
+
+	while (IS_TNODE(n)) {
+		/* record pn and cindex for leaf walking */
+		pn = n;
+		cindex = 1ul << n->bits;
+backtrace:
+		/* walk trie in reverse order */
+		do {
+			while (!(cindex--)) {
+				t_key pkey = pn->key;
+
+				n = pn;
+				pn = node_parent(n);
+
+				/* resize completed node */
+				resize(t, n);
+
+				/* if we got the root we are done */
+				if (!pn)
+					return;
+
+				cindex = get_index(pkey, pn);
+			}
+
+			/* grab the next available node */
+			n = tnode_get_child(pn, cindex);
+		} while (!n);
+	}
+
+	hlist_for_each_entry(fa, &n->leaf, fa_list) {
+		struct fib_info *fi = fa->fa_info;
+
+		if (fi && (fi->fib_flags & RTNH_F_EXTERNAL)) {
+			netdev_switch_fib_ipv4_del(n->key,
+						   KEYLENGTH - fa->fa_slen,
+						   fi, fa->fa_tos,
+						   fa->fa_type, tb->tb_id);
+		}
+	}
+
+	/* if trie is leaf only loop is completed */
+	if (pn)
+		goto backtrace;
+}
+
 /* Caller must hold RTNL. */
 int fib_table_flush(struct fib_table *tb)
 {
@@ -1589,6 +1675,10 @@ int fib_table_flush(struct fib_table *tb)
 		struct fib_info *fi = fa->fa_info;
 
 		if (fi && (fi->fib_flags & RTNH_F_DEAD)) {
+			netdev_switch_fib_ipv4_del(n->key,
+						   KEYLENGTH - fa->fa_slen,
+						   fi, fa->fa_tos,
+						   fa->fa_type, tb->tb_id);
 			hlist_del_rcu(&fa->fa_list);
 			fib_release_info(fa->fa_info);
 			alias_free_mem_rcu(fa);

net/switchdev/switchdev.c

@@ -14,6 +14,7 @@
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 #include <linux/netdevice.h>
+#include <net/ip_fib.h>
 #include <net/switchdev.h>
 
 /**
@@ -225,3 +226,163 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
 	return ret;
 }
 EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink);
+
+static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	struct net_device *lower_dev;
+	struct net_device *port_dev;
+	struct list_head *iter;
+
+	/* Recusively search down until we find a sw port dev.
+	 * (A sw port dev supports ndo_switch_parent_id_get).
+	 */
+
+	if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD &&
+	    ops->ndo_switch_parent_id_get)
+		return dev;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		port_dev = netdev_switch_get_lowest_dev(lower_dev);
+		if (port_dev)
+			return port_dev;
+	}
+
+	return NULL;
+}
+
+static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi)
+{
+	struct netdev_phys_item_id psid;
+	struct netdev_phys_item_id prev_psid;
+	struct net_device *dev = NULL;
+	int nhsel;
+
+	/* For this route, all nexthop devs must be on the same switch. */
+
+	for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
+		const struct fib_nh *nh = &fi->fib_nh[nhsel];
+
+		if (!nh->nh_dev)
+			return NULL;
+
+		dev = netdev_switch_get_lowest_dev(nh->nh_dev);
+		if (!dev)
+			return NULL;
+
+		if (netdev_switch_parent_id_get(dev, &psid))
+			return NULL;
+
+		if (nhsel > 0) {
+			if (prev_psid.id_len != psid.id_len)
+				return NULL;
+			if (memcmp(prev_psid.id, psid.id, psid.id_len))
+				return NULL;
+		}
+
+		prev_psid = psid;
+	}
+
+	return dev;
+}
+
+/**
+ *	netdev_switch_fib_ipv4_add - Add IPv4 route entry to switch
+ *
+ *	@dst: route's IPv4 destination address
+ *	@dst_len: destination address length (prefix length)
+ *	@fi: route FIB info structure
+ *	@tos: route TOS
+ *	@type: route type
+ *	@tb_id: route table ID
+ *
+ *	Add IPv4 route entry to switch device.
+ */
+int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
+			       u8 tos, u8 type, u32 tb_id)
+{
+	struct net_device *dev;
+	const struct net_device_ops *ops;
+	int err = 0;
+
+	/* Don't offload route if using custom ip rules or if
+	 * IPv4 FIB offloading has been disabled completely.
+	 */
+
+	if (fi->fib_net->ipv4.fib_has_custom_rules |
+	    fi->fib_net->ipv4.fib_offload_disabled)
+		return 0;
+
+	dev = netdev_switch_get_dev_by_nhs(fi);
+	if (!dev)
+		return 0;
+	ops = dev->netdev_ops;
+
+	if (ops->ndo_switch_fib_ipv4_add) {
+		err = ops->ndo_switch_fib_ipv4_add(dev, htonl(dst), dst_len,
+						   fi, tos, type, tb_id);
+		if (!err)
+			fi->fib_flags |= RTNH_F_EXTERNAL;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(netdev_switch_fib_ipv4_add);
+
+/**
+ *	netdev_switch_fib_ipv4_del - Delete IPv4 route entry from switch
+ *
+ *	@dst: route's IPv4 destination address
+ *	@dst_len: destination address length (prefix length)
+ *	@fi: route FIB info structure
+ *	@tos: route TOS
+ *	@type: route type
+ *	@tb_id: route table ID
+ *
+ *	Delete IPv4 route entry from switch device.
+ */
+int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
+			       u8 tos, u8 type, u32 tb_id)
+{
+	struct net_device *dev;
+	const struct net_device_ops *ops;
+	int err = 0;
+
+	if (!(fi->fib_flags & RTNH_F_EXTERNAL))
+		return 0;
+
+	dev = netdev_switch_get_dev_by_nhs(fi);
+	if (!dev)
+		return 0;
+	ops = dev->netdev_ops;
+
+	if (ops->ndo_switch_fib_ipv4_del) {
+		err = ops->ndo_switch_fib_ipv4_del(dev, htonl(dst), dst_len,
+						   fi, tos, type, tb_id);
+		if (!err)
+			fi->fib_flags &= ~RTNH_F_EXTERNAL;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(netdev_switch_fib_ipv4_del);
+
+/**
+ *	netdev_switch_fib_ipv4_abort - Abort an IPv4 FIB operation
+ *
+ *	@fi: route FIB info structure
+ */
+void netdev_switch_fib_ipv4_abort(struct fib_info *fi)
+{
+	/* There was a problem installing this route to the offload
+	 * device.  For now, until we come up with more refined
+	 * policy handling, abruptly end IPv4 fib offloading for
+	 * for entire net by flushing offload device(s) of all
+	 * IPv4 routes, and mark IPv4 fib offloading broken from
+	 * this point forward.
+	 */
+
+	fib_flush_external(fi->fib_net);
+	fi->fib_net->ipv4.fib_offload_disabled = true;
+}
+EXPORT_SYMBOL(netdev_switch_fib_ipv4_abort);