Merge branch 'mlxsw-Offload-IPv6-multicast-routes'

Ido Schimmel says:

====================
mlxsw: Offload IPv6 multicast routes

Yuval says:

The series is intended to allow offloading IPv6 multicast routes
and is split into two parts:

  - First half of the patches continue extending ip6mr [& refactor ipmr]
    with missing bits necessary for the offloading - fib-notifications,
    mfc refcounting and default rule identification.

  - Second half of the patches extend functionality inside mlxsw,
    beginning with extending lower-parts to support IPv6 mroutes
    to host and later extending the router/mr internal APIs within
    the driver to accommodate support in ipv6 configurations.
    Lastly it adds support in the RTNL_FAMILY_IP6MR notifications,
    allowing driver to react and offload related routes.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlxsw/reg.h

@@ -4225,6 +4225,12 @@ MLXSW_ITEM32(reg, ritr, ipv6, 0x00, 28, 1);
  */
 MLXSW_ITEM32(reg, ritr, ipv4_mc, 0x00, 27, 1);
 
+/* reg_ritr_ipv6_mc
+ * IPv6 multicast routing enable.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ipv6_mc, 0x00, 26, 1);
+
 enum mlxsw_reg_ritr_if_type {
 	/* VLAN interface. */
 	MLXSW_REG_RITR_VLAN_IF,
@@ -4290,6 +4296,14 @@ MLXSW_ITEM32(reg, ritr, ipv6_fe, 0x04, 28, 1);
  */
 MLXSW_ITEM32(reg, ritr, ipv4_mc_fe, 0x04, 27, 1);
 
+/* reg_ritr_ipv6_mc_fe
+ * IPv6 Multicast Forwarding Enable.
+ * When disabled, forwarding is blocked but local traffic (traps and IP to me)
+ * will be enabled.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ipv6_mc_fe, 0x04, 26, 1);
+
 /* reg_ritr_lb_en
  * Loop-back filter enable for unicast packets.
  * If the flag is set then loop-back filter for unicast packets is
@@ -4513,12 +4527,14 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
 	mlxsw_reg_ritr_ipv4_set(payload, 1);
 	mlxsw_reg_ritr_ipv6_set(payload, 1);
 	mlxsw_reg_ritr_ipv4_mc_set(payload, 1);
+	mlxsw_reg_ritr_ipv6_mc_set(payload, 1);
 	mlxsw_reg_ritr_type_set(payload, type);
 	mlxsw_reg_ritr_op_set(payload, op);
 	mlxsw_reg_ritr_rif_set(payload, rif);
 	mlxsw_reg_ritr_ipv4_fe_set(payload, 1);
 	mlxsw_reg_ritr_ipv6_fe_set(payload, 1);
 	mlxsw_reg_ritr_ipv4_mc_fe_set(payload, 1);
+	mlxsw_reg_ritr_ipv6_mc_fe_set(payload, 1);
 	mlxsw_reg_ritr_lb_en_set(payload, 1);
 	mlxsw_reg_ritr_virtual_router_set(payload, vr_id);
 	mlxsw_reg_ritr_mtu_set(payload, mtu);
@@ -6302,30 +6318,34 @@ MLXSW_ITEM32(reg, rmft2, irif_mask, 0x08, 24, 1);
  */
 MLXSW_ITEM32(reg, rmft2, irif, 0x08, 0, 16);
 
-/* reg_rmft2_dip4
- * Destination IPv4 address
+/* reg_rmft2_dip{4,6}
+ * Destination IPv4/6 address
  * Access: RW
  */
+MLXSW_ITEM_BUF(reg, rmft2, dip6, 0x10, 16);
 MLXSW_ITEM32(reg, rmft2, dip4, 0x1C, 0, 32);
 
-/* reg_rmft2_dip4_mask
+/* reg_rmft2_dip{4,6}_mask
  * A bit that is set directs the TCAM to compare the corresponding bit in key. A
  * bit that is clear directs the TCAM to ignore the corresponding bit in key.
  * Access: RW
  */
+MLXSW_ITEM_BUF(reg, rmft2, dip6_mask, 0x20, 16);
 MLXSW_ITEM32(reg, rmft2, dip4_mask, 0x2C, 0, 32);
 
-/* reg_rmft2_sip4
- * Source IPv4 address
+/* reg_rmft2_sip{4,6}
+ * Source IPv4/6 address
  * Access: RW
  */
+MLXSW_ITEM_BUF(reg, rmft2, sip6, 0x30, 16);
 MLXSW_ITEM32(reg, rmft2, sip4, 0x3C, 0, 32);
 
-/* reg_rmft2_sip4_mask
+/* reg_rmft2_sip{4,6}_mask
  * A bit that is set directs the TCAM to compare the corresponding bit in key. A
  * bit that is clear directs the TCAM to ignore the corresponding bit in key.
  * Access: RW
  */
+MLXSW_ITEM_BUF(reg, rmft2, sip6_mask, 0x40, 16);
 MLXSW_ITEM32(reg, rmft2, sip4_mask, 0x4C, 0, 32);
 
 /* reg_rmft2_flexible_action_set
@@ -6343,26 +6363,52 @@ MLXSW_ITEM_BUF(reg, rmft2, flexible_action_set, 0x80,
 	       MLXSW_REG_FLEX_ACTION_SET_LEN);
 
 static inline void
-mlxsw_reg_rmft2_ipv4_pack(char *payload, bool v, u16 offset, u16 virtual_router,
+mlxsw_reg_rmft2_common_pack(char *payload, bool v, u16 offset,
+			    u16 virtual_router,
 			    enum mlxsw_reg_rmft2_irif_mask irif_mask, u16 irif,
-			  u32 dip4, u32 dip4_mask, u32 sip4, u32 sip4_mask,
-			  const char *flexible_action_set)
+			    const char *flex_action_set)
 {
 	MLXSW_REG_ZERO(rmft2, payload);
 	mlxsw_reg_rmft2_v_set(payload, v);
-	mlxsw_reg_rmft2_type_set(payload, MLXSW_REG_RMFT2_TYPE_IPV4);
 	mlxsw_reg_rmft2_op_set(payload, MLXSW_REG_RMFT2_OP_READ_WRITE);
 	mlxsw_reg_rmft2_offset_set(payload, offset);
 	mlxsw_reg_rmft2_virtual_router_set(payload, virtual_router);
 	mlxsw_reg_rmft2_irif_mask_set(payload, irif_mask);
 	mlxsw_reg_rmft2_irif_set(payload, irif);
+	if (flex_action_set)
+		mlxsw_reg_rmft2_flexible_action_set_memcpy_to(payload,
+							      flex_action_set);
+}
+
+static inline void
+mlxsw_reg_rmft2_ipv4_pack(char *payload, bool v, u16 offset, u16 virtual_router,
+			  enum mlxsw_reg_rmft2_irif_mask irif_mask, u16 irif,
+			  u32 dip4, u32 dip4_mask, u32 sip4, u32 sip4_mask,
+			  const char *flexible_action_set)
+{
+	mlxsw_reg_rmft2_common_pack(payload, v, offset, virtual_router,
+				    irif_mask, irif, flexible_action_set);
+	mlxsw_reg_rmft2_type_set(payload, MLXSW_REG_RMFT2_TYPE_IPV4);
 	mlxsw_reg_rmft2_dip4_set(payload, dip4);
 	mlxsw_reg_rmft2_dip4_mask_set(payload, dip4_mask);
 	mlxsw_reg_rmft2_sip4_set(payload, sip4);
 	mlxsw_reg_rmft2_sip4_mask_set(payload, sip4_mask);
-	if (flexible_action_set)
-		mlxsw_reg_rmft2_flexible_action_set_memcpy_to(payload,
-							      flexible_action_set);
+}
+
+static inline void
+mlxsw_reg_rmft2_ipv6_pack(char *payload, bool v, u16 offset, u16 virtual_router,
+			  enum mlxsw_reg_rmft2_irif_mask irif_mask, u16 irif,
+			  struct in6_addr dip6, struct in6_addr dip6_mask,
+			  struct in6_addr sip6, struct in6_addr sip6_mask,
+			  const char *flexible_action_set)
+{
+	mlxsw_reg_rmft2_common_pack(payload, v, offset, virtual_router,
+				    irif_mask, irif, flexible_action_set);
+	mlxsw_reg_rmft2_type_set(payload, MLXSW_REG_RMFT2_TYPE_IPV6);
+	mlxsw_reg_rmft2_dip6_memcpy_to(payload, (void *)&dip6);
+	mlxsw_reg_rmft2_dip6_mask_memcpy_to(payload, (void *)&dip6_mask);
+	mlxsw_reg_rmft2_sip6_memcpy_to(payload, (void *)&sip6);
+	mlxsw_reg_rmft2_sip6_mask_memcpy_to(payload, (void *)&sip6_mask);
 }
 
 /* MFCR - Management Fan Control Register

drivers/net/ethernet/mellanox/mlxsw/spectrum.c

@@ -3380,6 +3380,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_NO_MARK(ACL0, TRAP_TO_CPU, IP2ME, false),
 	/* Multicast Router Traps */
 	MLXSW_SP_RXL_MARK(IPV4_PIM, TRAP_TO_CPU, PIM, false),
+	MLXSW_SP_RXL_MARK(IPV6_PIM, TRAP_TO_CPU, PIM, false),
 	MLXSW_SP_RXL_MARK(RPF, TRAP_TO_CPU, RPF, false),
 	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
 	MLXSW_SP_RXL_MR_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),

drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h

@@ -36,6 +36,7 @@
 #define _MLXSW_SPECTRUM_MCROUTER_H
 
 #include <linux/mroute.h>
+#include <linux/mroute6.h>
 #include "spectrum_router.h"
 #include "spectrum.h"
 
@@ -109,10 +110,10 @@ struct mlxsw_sp_mr_table;
 int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp,
 		     const struct mlxsw_sp_mr_ops *mr_ops);
 void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp);
-int mlxsw_sp_mr_route4_add(struct mlxsw_sp_mr_table *mr_table,
-			   struct mfc_cache *mfc, bool replace);
-void mlxsw_sp_mr_route4_del(struct mlxsw_sp_mr_table *mr_table,
-			    struct mfc_cache *mfc);
+int mlxsw_sp_mr_route_add(struct mlxsw_sp_mr_table *mr_table,
+			  struct mr_mfc *mfc, bool replace);
+void mlxsw_sp_mr_route_del(struct mlxsw_sp_mr_table *mr_table,
+			   struct mr_mfc *mfc);
 int mlxsw_sp_mr_vif_add(struct mlxsw_sp_mr_table *mr_table,
 			struct net_device *dev, vifi_t vif_index,
 			unsigned long vif_flags,

drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c

@@ -51,7 +51,7 @@ struct mlxsw_sp_mr_tcam_region {
 };
 
 struct mlxsw_sp_mr_tcam {
-	struct mlxsw_sp_mr_tcam_region ipv4_tcam_region;
+	struct mlxsw_sp_mr_tcam_region tcam_regions[MLXSW_SP_L3_PROTO_MAX];
 };
 
 /* This struct maps to one RIGR2 register entry */
@@ -316,20 +316,37 @@ static int mlxsw_sp_mr_tcam_route_replace(struct mlxsw_sp *mlxsw_sp,
 					  mlxsw_afa_block_first_set(afa_block));
 		break;
 	case MLXSW_SP_L3_PROTO_IPV6:
-	default:
-		WARN_ON_ONCE(1);
+		mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, true, parman_item->index,
+					  key->vrid,
+					  MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
+					  key->group.addr6,
+					  key->group_mask.addr6,
+					  key->source.addr6,
+					  key->source_mask.addr6,
+					  mlxsw_afa_block_first_set(afa_block));
 	}
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
 }
 
 static int mlxsw_sp_mr_tcam_route_remove(struct mlxsw_sp *mlxsw_sp, int vrid,
+					 struct mlxsw_sp_mr_route_key *key,
 					 struct parman_item *parman_item)
 {
+	struct in6_addr zero_addr = IN6ADDR_ANY_INIT;
 	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
 
-	mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index, vrid,
-				  0, 0, 0, 0, 0, 0, NULL);
+	switch (key->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index,
+					  vrid, 0, 0, 0, 0, 0, 0, NULL);
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, false, parman_item->index,
+					  vrid, 0, 0, zero_addr, zero_addr,
+					  zero_addr, zero_addr, NULL);
+		break;
+	}
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
 }
@@ -353,27 +370,30 @@ mlxsw_sp_mr_tcam_erif_populate(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
+static struct mlxsw_sp_mr_tcam_region *
+mlxsw_sp_mr_tcam_protocol_region(struct mlxsw_sp_mr_tcam *mr_tcam,
+				 enum mlxsw_sp_l3proto proto)
+{
+	return &mr_tcam->tcam_regions[proto];
+}
+
 static int
 mlxsw_sp_mr_tcam_route_parman_item_add(struct mlxsw_sp_mr_tcam *mr_tcam,
 				       struct mlxsw_sp_mr_tcam_route *route,
 				       enum mlxsw_sp_mr_route_prio prio)
 {
-	struct parman_prio *parman_prio = NULL;
+	struct mlxsw_sp_mr_tcam_region *tcam_region;
 	int err;
 
-	switch (route->key.proto) {
-	case MLXSW_SP_L3_PROTO_IPV4:
-		parman_prio = &mr_tcam->ipv4_tcam_region.parman_prios[prio];
-		err = parman_item_add(mr_tcam->ipv4_tcam_region.parman,
-				      parman_prio, &route->parman_item);
+	tcam_region = mlxsw_sp_mr_tcam_protocol_region(mr_tcam,
+						       route->key.proto);
+	err = parman_item_add(tcam_region->parman,
+			      &tcam_region->parman_prios[prio],
+			      &route->parman_item);
 	if (err)
 		return err;
-		break;
-	case MLXSW_SP_L3_PROTO_IPV6:
-	default:
-		WARN_ON_ONCE(1);
-	}
-	route->parman_prio = parman_prio;
+
+	route->parman_prio = &tcam_region->parman_prios[prio];
 	return 0;
 }
 
@@ -381,15 +401,13 @@ static void
 mlxsw_sp_mr_tcam_route_parman_item_remove(struct mlxsw_sp_mr_tcam *mr_tcam,
 					  struct mlxsw_sp_mr_tcam_route *route)
 {
-	switch (route->key.proto) {
-	case MLXSW_SP_L3_PROTO_IPV4:
-		parman_item_remove(mr_tcam->ipv4_tcam_region.parman,
+	struct mlxsw_sp_mr_tcam_region *tcam_region;
+
+	tcam_region = mlxsw_sp_mr_tcam_protocol_region(mr_tcam,
+						       route->key.proto);
+
+	parman_item_remove(tcam_region->parman,
 			   route->parman_prio, &route->parman_item);
-		break;
-	case MLXSW_SP_L3_PROTO_IPV6:
-	default:
-		WARN_ON_ONCE(1);
-	}
 }
 
 static int
@@ -462,7 +480,7 @@ static void mlxsw_sp_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
 
 	mlxsw_sp_mr_tcam_route_remove(mlxsw_sp, route->key.vrid,
-				      &route->parman_item);
+				      &route->key, &route->parman_item);
 	mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
 	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
 	mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
@@ -806,21 +824,42 @@ mlxsw_sp_mr_tcam_region_fini(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
 static int mlxsw_sp_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
 {
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
+	struct mlxsw_sp_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
+	u32 rtar_key;
+	int err;
 
 	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MC_ERIF_LIST_ENTRIES) ||
 	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_TCAM_RULES))
 		return -EIO;
 
-	return mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
-					    &mr_tcam->ipv4_tcam_region,
-					    MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST);
+	rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST;
+	err = mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
+					   &region[MLXSW_SP_L3_PROTO_IPV4],
+					   rtar_key);
+	if (err)
+		return err;
+
+	rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV6_MULTICAST;
+	err = mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
+					   &region[MLXSW_SP_L3_PROTO_IPV6],
+					   rtar_key);
+	if (err)
+		goto err_ipv6_region_init;
+
+	return 0;
+
+err_ipv6_region_init:
+	mlxsw_sp_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV4]);
+	return err;
 }
 
 static void mlxsw_sp_mr_tcam_fini(void *priv)
 {
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
+	struct mlxsw_sp_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
 
-	mlxsw_sp_mr_tcam_region_fini(&mr_tcam->ipv4_tcam_region);
+	mlxsw_sp_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV6]);
+	mlxsw_sp_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV4]);
 }
 
 const struct mlxsw_sp_mr_ops mlxsw_sp_mr_tcam_ops = {

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h

@@ -41,6 +41,7 @@
 enum mlxsw_sp_l3proto {
 	MLXSW_SP_L3_PROTO_IPV4,
 	MLXSW_SP_L3_PROTO_IPV6,
+#define MLXSW_SP_L3_PROTO_MAX	(MLXSW_SP_L3_PROTO_IPV6 + 1)
 };
 
 union mlxsw_sp_l3addr {

drivers/net/ethernet/mellanox/mlxsw/trap.h

@@ -77,6 +77,7 @@ enum {
 	MLXSW_TRAP_ID_IPV6_DHCP = 0x69,
 	MLXSW_TRAP_ID_IPV6_ALL_ROUTERS_LINK = 0x6F,
 	MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70,
+	MLXSW_TRAP_ID_IPV6_PIM = 0x79,
 	MLXSW_TRAP_ID_IPV4_BGP = 0x88,
 	MLXSW_TRAP_ID_IPV6_BGP = 0x89,
 	MLXSW_TRAP_ID_L3_IPV6_ROUTER_SOLICITATION = 0x8A,

include/linux/mroute.h

@@ -55,14 +55,6 @@ static inline bool ipmr_rule_default(const struct fib_rule *rule)
 }
 #endif
 
-struct vif_entry_notifier_info {
-	struct fib_notifier_info info;
-	struct net_device *dev;
-	vifi_t vif_index;
-	unsigned short vif_flags;
-	u32 tb_id;
-};
-
 #define VIFF_STATIC 0x8000
 
 struct mfc_cache_cmp_arg {
@@ -88,33 +80,8 @@ struct mfc_cache {
 	};
 };
 
-struct mfc_entry_notifier_info {
-	struct fib_notifier_info info;
-	struct mfc_cache *mfc;
-	u32 tb_id;
-};
-
 struct rtmsg;
 int ipmr_get_route(struct net *net, struct sk_buff *skb,
 		   __be32 saddr, __be32 daddr,
 		   struct rtmsg *rtm, u32 portid);
-
-#ifdef CONFIG_IP_MROUTE
-void ipmr_cache_free(struct mfc_cache *mfc_cache);
-#else
-static inline void ipmr_cache_free(struct mfc_cache *mfc_cache)
-{
-}
-#endif
-
-static inline void ipmr_cache_put(struct mfc_cache *c)
-{
-	if (refcount_dec_and_test(&c->_c.mfc_un.res.refcount))
-		ipmr_cache_free(c);
-}
-static inline void ipmr_cache_hold(struct mfc_cache *c)
-{
-	refcount_inc(&c->_c.mfc_un.res.refcount);
-}
-
 #endif

include/linux/mroute6.h

@@ -8,6 +8,7 @@
 #include <net/net_namespace.h>
 #include <uapi/linux/mroute6.h>
 #include <linux/mroute_base.h>
+#include <net/fib_rules.h>
 
 #ifdef CONFIG_IPV6_MROUTE
 static inline int ip6_mroute_opt(int opt)
@@ -63,6 +64,15 @@ static inline void ip6_mr_cleanup(void)
 }
 #endif
 
+#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
+bool ip6mr_rule_default(const struct fib_rule *rule);
+#else
+static inline bool ip6mr_rule_default(const struct fib_rule *rule)
+{
+	return true;
+}
+#endif
+
 #define VIFF_STATIC 0x8000
 
 struct mfc6_cache_cmp_arg {

include/linux/mroute_base.h

@@ -6,6 +6,7 @@
 #include <linux/spinlock.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
+#include <net/fib_notifier.h>
 
 /**
  * struct vif_device - interface representor for multicast routing
@@ -36,6 +37,58 @@ struct vif_device {
 	__be32 local, remote;
 };
 
+struct vif_entry_notifier_info {
+	struct fib_notifier_info info;
+	struct net_device *dev;
+	unsigned short vif_index;
+	unsigned short vif_flags;
+	u32 tb_id;
+};
+
+static inline int mr_call_vif_notifier(struct notifier_block *nb,
+				       struct net *net,
+				       unsigned short family,
+				       enum fib_event_type event_type,
+				       struct vif_device *vif,
+				       unsigned short vif_index, u32 tb_id)
+{
+	struct vif_entry_notifier_info info = {
+		.info = {
+			.family = family,
+			.net = net,
+		},
+		.dev = vif->dev,
+		.vif_index = vif_index,
+		.vif_flags = vif->flags,
+		.tb_id = tb_id,
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static inline int mr_call_vif_notifiers(struct net *net,
+					unsigned short family,
+					enum fib_event_type event_type,
+					struct vif_device *vif,
+					unsigned short vif_index, u32 tb_id,
+					unsigned int *ipmr_seq)
+{
+	struct vif_entry_notifier_info info = {
+		.info = {
+			.family = family,
+			.net = net,
+		},
+		.dev = vif->dev,
+		.vif_index = vif_index,
+		.vif_flags = vif->flags,
+		.tb_id = tb_id,
+	};
+
+	ASSERT_RTNL();
+	(*ipmr_seq)++;
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
 #ifndef MAXVIFS
 /* This one is nasty; value is defined in uapi using different symbols for
  * mroute and morute6 but both map into same 32.
@@ -72,6 +125,7 @@ enum {
  * @refcount: reference count for this entry
  * @list: global entry list
  * @rcu: used for entry destruction
+ * @free: Operation used for freeing an entry under RCU
  */
 struct mr_mfc {
 	struct rhlist_head mnode;
@@ -97,8 +151,64 @@ struct mr_mfc {
 	} mfc_un;
 	struct list_head list;
 	struct rcu_head	rcu;
+	void (*free)(struct rcu_head *head);
+};
+
+static inline void mr_cache_put(struct mr_mfc *c)
+{
+	if (refcount_dec_and_test(&c->mfc_un.res.refcount))
+		call_rcu(&c->rcu, c->free);
+}
+
+static inline void mr_cache_hold(struct mr_mfc *c)
+{
+	refcount_inc(&c->mfc_un.res.refcount);
+}
+
+struct mfc_entry_notifier_info {
+	struct fib_notifier_info info;
+	struct mr_mfc *mfc;
+	u32 tb_id;
 };
 
+static inline int mr_call_mfc_notifier(struct notifier_block *nb,
+				       struct net *net,
+				       unsigned short family,
+				       enum fib_event_type event_type,
+				       struct mr_mfc *mfc, u32 tb_id)
+{
+	struct mfc_entry_notifier_info info = {
+		.info = {
+			.family = family,
+			.net = net,
+		},
+		.mfc = mfc,
+		.tb_id = tb_id
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static inline int mr_call_mfc_notifiers(struct net *net,
+					unsigned short family,
+					enum fib_event_type event_type,
+					struct mr_mfc *mfc, u32 tb_id,
+					unsigned int *ipmr_seq)
+{
+	struct mfc_entry_notifier_info info = {
+		.info = {
+			.family = family,
+			.net = net,
+		},
+		.mfc = mfc,
+		.tb_id = tb_id
+	};
+
+	ASSERT_RTNL();
+	(*ipmr_seq)++;
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
 struct mr_table;
 
 /**
@@ -180,6 +290,13 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
 				 u32 portid, u32 seq, struct mr_mfc *c,
 				 int cmd, int flags),
 		     spinlock_t *lock);
+
+int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family,
+	    int (*rules_dump)(struct net *net,
+			      struct notifier_block *nb),
+	    struct mr_table *(*mr_iter)(struct net *net,
+					struct mr_table *mrt),
+	    rwlock_t *mrt_lock);
 #else
 static inline void vif_device_init(struct vif_device *v,
 				   struct net_device *dev,
@@ -236,6 +353,17 @@ mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
 {
 	return -EINVAL;
 }
+
+static inline int mr_dump(struct net *net, struct notifier_block *nb,
+			  unsigned short family,
+			  int (*rules_dump)(struct net *net,
+					    struct notifier_block *nb),
+			  struct mr_table *(*mr_iter)(struct net *net,
+						      struct mr_table *mrt),
+			  rwlock_t *mrt_lock)
+{
+	return -EINVAL;
+}
 #endif
 
 static inline void *mr_mfc_find(struct mr_table *mrt, void *hasharg)

include/net/netns/ipv6.h

@@ -96,6 +96,8 @@ struct netns_ipv6 {
 	atomic_t		fib6_sernum;
 	struct seg6_pernet_data *seg6_data;
 	struct fib_notifier_ops	*notifier_ops;
+	struct fib_notifier_ops	*ip6mr_notifier_ops;
+	unsigned int ipmr_seq; /* protected by rtnl_mutex */
 	struct {
 		struct hlist_head head;
 		spinlock_t	lock;

net/ipv4/ipmr.c

@@ -644,80 +644,22 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 }
 #endif
 
-static int call_ipmr_vif_entry_notifier(struct notifier_block *nb,
-					struct net *net,
-					enum fib_event_type event_type,
-					struct vif_device *vif,
-					vifi_t vif_index, u32 tb_id)
-{
-	struct vif_entry_notifier_info info = {
-		.info = {
-			.family = RTNL_FAMILY_IPMR,
-			.net = net,
-		},
-		.dev = vif->dev,
-		.vif_index = vif_index,
-		.vif_flags = vif->flags,
-		.tb_id = tb_id,
-	};
-
-	return call_fib_notifier(nb, net, event_type, &info.info);
-}
-
 static int call_ipmr_vif_entry_notifiers(struct net *net,
 					 enum fib_event_type event_type,
 					 struct vif_device *vif,
 					 vifi_t vif_index, u32 tb_id)
 {
-	struct vif_entry_notifier_info info = {
-		.info = {
-			.family = RTNL_FAMILY_IPMR,
-			.net = net,
-		},
-		.dev = vif->dev,
-		.vif_index = vif_index,
-		.vif_flags = vif->flags,
-		.tb_id = tb_id,
-	};
-
-	ASSERT_RTNL();
-	net->ipv4.ipmr_seq++;
-	return call_fib_notifiers(net, event_type, &info.info);
-}
-
-static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb,
-					struct net *net,
-					enum fib_event_type event_type,
-					struct mfc_cache *mfc, u32 tb_id)
-{
-	struct mfc_entry_notifier_info info = {
-		.info = {
-			.family = RTNL_FAMILY_IPMR,
-			.net = net,
-		},
-		.mfc = mfc,
-		.tb_id = tb_id
-	};
-
-	return call_fib_notifier(nb, net, event_type, &info.info);
+	return mr_call_vif_notifiers(net, RTNL_FAMILY_IPMR, event_type,
+				     vif, vif_index, tb_id,
+				     &net->ipv4.ipmr_seq);
 }
 
 static int call_ipmr_mfc_entry_notifiers(struct net *net,
 					 enum fib_event_type event_type,
 					 struct mfc_cache *mfc, u32 tb_id)
 {
-	struct mfc_entry_notifier_info info = {
-		.info = {
-			.family = RTNL_FAMILY_IPMR,
-			.net = net,
-		},
-		.mfc = mfc,
-		.tb_id = tb_id
-	};
-
-	ASSERT_RTNL();
-	net->ipv4.ipmr_seq++;
-	return call_fib_notifiers(net, event_type, &info.info);
+	return mr_call_mfc_notifiers(net, RTNL_FAMILY_IPMR, event_type,
+				     &mfc->_c, tb_id, &net->ipv4.ipmr_seq);
 }
 
 /**
@@ -790,11 +732,10 @@ static void ipmr_cache_free_rcu(struct rcu_head *head)
 	kmem_cache_free(mrt_cachep, (struct mfc_cache *)c);
 }
 
-void ipmr_cache_free(struct mfc_cache *c)
+static void ipmr_cache_free(struct mfc_cache *c)
 {
 	call_rcu(&c->_c.rcu, ipmr_cache_free_rcu);
 }
-EXPORT_SYMBOL(ipmr_cache_free);
 
 /* Destroy an unresolved cache entry, killing queued skbs
  * and reporting error to netlink readers.
@@ -1045,6 +986,7 @@ static struct mfc_cache *ipmr_cache_alloc(void)
 	if (c) {
 		c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 		c->_c.mfc_un.res.minvif = MAXVIFS;
+		c->_c.free = ipmr_cache_free_rcu;
 		refcount_set(&c->_c.mfc_un.res.refcount, 1);
 	}
 	return c;
@@ -1264,7 +1206,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
 	list_del_rcu(&c->_c.list);
 	call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id);
 	mroute_netlink_event(mrt, c, RTM_DELROUTE);
-	ipmr_cache_put(c);
+	mr_cache_put(&c->_c);
 
 	return 0;
 }
@@ -1376,7 +1318,7 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
 		call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, cache,
 					      mrt->id);
 		mroute_netlink_event(mrt, cache, RTM_DELROUTE);
-		ipmr_cache_put(cache);
+		mr_cache_put(c);
 	}
 
 	if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
@@ -2989,38 +2931,8 @@ static unsigned int ipmr_seq_read(struct net *net)
 
 static int ipmr_dump(struct net *net, struct notifier_block *nb)
 {
-	struct mr_table *mrt;
-	int err;
-
-	err = ipmr_rules_dump(net, nb);
-	if (err)
-		return err;
-
-	ipmr_for_each_table(mrt, net) {
-		struct vif_device *v = &mrt->vif_table[0];
-		struct mr_mfc *mfc;
-		int vifi;
-
-		/* Notifiy on table VIF entries */
-		read_lock(&mrt_lock);
-		for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
-			if (!v->dev)
-				continue;
-
-			call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD,
-						     v, vifi, mrt->id);
-		}
-		read_unlock(&mrt_lock);
-
-		/* Notify on table MFC entries */
-		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
-			call_ipmr_mfc_entry_notifier(nb, net,
-						     FIB_EVENT_ENTRY_ADD,
-						     (struct mfc_cache *)mfc,
-						     mrt->id);
-	}
-
-	return 0;
+	return mr_dump(net, nb, RTNL_FAMILY_IPMR, ipmr_rules_dump,
+		       ipmr_mr_table_iter, &mrt_lock);
 }
 
 static const struct fib_notifier_ops ipmr_notifier_ops_template = {

net/ipv4/ipmr_base.c

@@ -321,3 +321,45 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
 	return skb->len;
 }
 EXPORT_SYMBOL(mr_rtm_dumproute);
+
+int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family,
+	    int (*rules_dump)(struct net *net,
+			      struct notifier_block *nb),
+	    struct mr_table *(*mr_iter)(struct net *net,
+					struct mr_table *mrt),
+	    rwlock_t *mrt_lock)
+{
+	struct mr_table *mrt;
+	int err;
+
+	err = rules_dump(net, nb);
+	if (err)
+		return err;
+
+	for (mrt = mr_iter(net, NULL); mrt; mrt = mr_iter(net, mrt)) {
+		struct vif_device *v = &mrt->vif_table[0];
+		struct mr_mfc *mfc;
+		int vifi;
+
+		/* Notifiy on table VIF entries */
+		read_lock(mrt_lock);
+		for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
+			if (!v->dev)
+				continue;
+
+			mr_call_vif_notifier(nb, net, family,
+					     FIB_EVENT_VIF_ADD,
+					     v, vifi, mrt->id);
+		}
+		read_unlock(mrt_lock);
+
+		/* Notify on table MFC entries */
+		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
+			mr_call_mfc_notifier(nb, net, family,
+					     FIB_EVENT_ENTRY_ADD,
+					     mfc, mrt->id);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mr_dump);

net/ipv6/ip6mr.c

@@ -258,6 +258,23 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
 	fib_rules_unregister(net->ipv6.mr6_rules_ops);
 	rtnl_unlock();
 }
+
+static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR);
+}
+
+static unsigned int ip6mr_rules_seq_read(struct net *net)
+{
+	return fib_rules_seq_read(net, RTNL_FAMILY_IP6MR);
+}
+
+bool ip6mr_rule_default(const struct fib_rule *rule)
+{
+	return fib_rule_matchall(rule) && rule->action == FR_ACT_TO_TBL &&
+	       rule->table == RT6_TABLE_DFLT && !rule->l3mdev;
+}
+EXPORT_SYMBOL(ip6mr_rule_default);
 #else
 #define ip6mr_for_each_table(mrt, net) \
 	for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
@@ -295,6 +312,16 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
 	net->ipv6.mrt6 = NULL;
 	rtnl_unlock();
 }
+
+static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return 0;
+}
+
+static unsigned int ip6mr_rules_seq_read(struct net *net)
+{
+	return 0;
+}
 #endif
 
 static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -653,10 +680,25 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt)
 }
 #endif
 
-/*
- *	Delete a VIF entry
- */
+static int call_ip6mr_vif_entry_notifiers(struct net *net,
+					  enum fib_event_type event_type,
+					  struct vif_device *vif,
+					  mifi_t vif_index, u32 tb_id)
+{
+	return mr_call_vif_notifiers(net, RTNL_FAMILY_IP6MR, event_type,
+				     vif, vif_index, tb_id,
+				     &net->ipv6.ipmr_seq);
+}
 
+static int call_ip6mr_mfc_entry_notifiers(struct net *net,
+					  enum fib_event_type event_type,
+					  struct mfc6_cache *mfc, u32 tb_id)
+{
+	return mr_call_mfc_notifiers(net, RTNL_FAMILY_IP6MR, event_type,
+				     &mfc->_c, tb_id, &net->ipv6.ipmr_seq);
+}
+
+/* Delete a VIF entry */
 static int mif6_delete(struct mr_table *mrt, int vifi, int notify,
 		       struct list_head *head)
 {
@@ -669,6 +711,11 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify,
 
 	v = &mrt->vif_table[vifi];
 
+	if (VIF_EXISTS(mrt, vifi))
+		call_ip6mr_vif_entry_notifiers(read_pnet(&mrt->net),
+					       FIB_EVENT_VIF_DEL, v, vifi,
+					       mrt->id);
+
 	write_lock_bh(&mrt_lock);
 	dev = v->dev;
 	v->dev = NULL;
@@ -887,6 +934,8 @@ static int mif6_add(struct net *net, struct mr_table *mrt,
 	if (vifi + 1 > mrt->maxvif)
 		mrt->maxvif = vifi + 1;
 	write_unlock_bh(&mrt_lock);
+	call_ip6mr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD,
+				       v, vifi, mrt->id);
 	return 0;
 }
 
@@ -940,6 +989,8 @@ static struct mfc6_cache *ip6mr_cache_alloc(void)
 		return NULL;
 	c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 	c->_c.mfc_un.res.minvif = MAXMIFS;
+	c->_c.free = ip6mr_cache_free_rcu;
+	refcount_set(&c->_c.mfc_un.res.refcount, 1);
 	return c;
 }
 
@@ -1175,8 +1226,10 @@ static int ip6mr_mfc_delete(struct mr_table *mrt, struct mf6cctl *mfc,
 	rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ip6mr_rht_params);
 	list_del_rcu(&c->_c.list);
 
+	call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
+				       FIB_EVENT_ENTRY_DEL, c, mrt->id);
 	mr6_netlink_event(mrt, c, RTM_DELROUTE);
-	ip6mr_cache_free(c);
+	mr_cache_put(&c->_c);
 	return 0;
 }
 
@@ -1203,21 +1256,63 @@ static int ip6mr_device_event(struct notifier_block *this,
 	return NOTIFY_DONE;
 }
 
+static unsigned int ip6mr_seq_read(struct net *net)
+{
+	ASSERT_RTNL();
+
+	return net->ipv6.ipmr_seq + ip6mr_rules_seq_read(net);
+}
+
+static int ip6mr_dump(struct net *net, struct notifier_block *nb)
+{
+	return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump,
+		       ip6mr_mr_table_iter, &mrt_lock);
+}
+
 static struct notifier_block ip6_mr_notifier = {
 	.notifier_call = ip6mr_device_event
 };
 
-/*
- *	Setup for IP multicast routing
- */
+static const struct fib_notifier_ops ip6mr_notifier_ops_template = {
+	.family		= RTNL_FAMILY_IP6MR,
+	.fib_seq_read	= ip6mr_seq_read,
+	.fib_dump	= ip6mr_dump,
+	.owner		= THIS_MODULE,
+};
+
+static int __net_init ip6mr_notifier_init(struct net *net)
+{
+	struct fib_notifier_ops *ops;
+
+	net->ipv6.ipmr_seq = 0;
 
+	ops = fib_notifier_ops_register(&ip6mr_notifier_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+
+	net->ipv6.ip6mr_notifier_ops = ops;
+
+	return 0;
+}
+
+static void __net_exit ip6mr_notifier_exit(struct net *net)
+{
+	fib_notifier_ops_unregister(net->ipv6.ip6mr_notifier_ops);
+	net->ipv6.ip6mr_notifier_ops = NULL;
+}
+
+/* Setup for IP multicast routing */
 static int __net_init ip6mr_net_init(struct net *net)
 {
 	int err;
 
+	err = ip6mr_notifier_init(net);
+	if (err)
+		return err;
+
 	err = ip6mr_rules_init(net);
 	if (err < 0)
-		goto fail;
+		goto ip6mr_rules_fail;
 
 #ifdef CONFIG_PROC_FS
 	err = -ENOMEM;
@@ -1235,7 +1330,8 @@ static int __net_init ip6mr_net_init(struct net *net)
 proc_vif_fail:
 	ip6mr_rules_exit(net);
 #endif
-fail:
+ip6mr_rules_fail:
+	ip6mr_notifier_exit(net);
 	return err;
 }
 
@@ -1246,6 +1342,7 @@ static void __net_exit ip6mr_net_exit(struct net *net)
 	remove_proc_entry("ip6_mr_vif", net->proc_net);
 #endif
 	ip6mr_rules_exit(net);
+	ip6mr_notifier_exit(net);
 }
 
 static struct pernet_operations ip6mr_net_ops = {
@@ -1337,6 +1434,8 @@ static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt,
 		if (!mrtsock)
 			c->_c.mfc_flags |= MFC_STATIC;
 		write_unlock_bh(&mrt_lock);
+		call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE,
+					       c, mrt->id);
 		mr6_netlink_event(mrt, c, RTM_NEWROUTE);
 		return 0;
 	}
@@ -1388,6 +1487,8 @@ static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt,
 		ip6mr_cache_resolve(net, mrt, uc, c);
 		ip6mr_cache_free(uc);
 	}
+	call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD,
+				       c, mrt->id);
 	mr6_netlink_event(mrt, c, RTM_NEWROUTE);
 	return 0;
 }
@@ -1417,13 +1518,17 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
 		rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
 		list_del_rcu(&c->list);
 		mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
-		ip6mr_cache_free((struct mfc6_cache *)c);
+		mr_cache_put(c);
 	}
 
 	if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
 		spin_lock_bh(&mfc_unres_lock);
 		list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
 			list_del(&c->list);
+			call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
+						       FIB_EVENT_ENTRY_DEL,
+						       (struct mfc6_cache *)c,
+						       mrt->id);
 			mr6_netlink_event(mrt, (struct mfc6_cache *)c,
 					  RTM_DELROUTE);
 			ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);