summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--drivers/net/Kconfig1
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c246
-rw-r--r--drivers/net/netdevsim/fib.c671
-rw-r--r--include/net/ip6_fib.h11
-rw-r--r--include/net/ip_fib.h13
-rw-r--r--include/uapi/linux/rtnetlink.h2
-rw-r--r--net/ipv4/fib_lookup.h8
-rw-r--r--net/ipv4/fib_semantics.c33
-rw-r--r--net/ipv4/fib_trie.c77
-rw-r--r--net/ipv4/route.c31
-rw-r--r--net/ipv6/route.c7
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/fib.sh180
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/fib.sh341
-rw-r--r--tools/testing/selftests/net/forwarding/fib_offload_lib.sh873
14 files changed, 2365 insertions, 129 deletions
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 01e2657e4c26..e65ed4d0a7ad 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -549,6 +549,7 @@ source "drivers/net/hyperv/Kconfig"
config NETDEVSIM
tristate "Simulated networking device"
depends on DEBUG_FS
+ depends on IPV6 || IPV6=n
select NET_DEVLINK
help
This driver is a developer testing tool and software model that can
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 7f70aa799064..a014bd8d504d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3235,20 +3235,6 @@ mlxsw_sp_nexthop_fib_entries_update(struct mlxsw_sp *mlxsw_sp,
return 0;
}
-static void
-mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op, int err);
-
-static void
-mlxsw_sp_nexthop_fib_entries_refresh(struct mlxsw_sp_nexthop_group *nh_grp)
-{
- enum mlxsw_reg_ralue_op op = MLXSW_REG_RALUE_OP_WRITE_WRITE;
- struct mlxsw_sp_fib_entry *fib_entry;
-
- list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node)
- mlxsw_sp_fib_entry_offload_refresh(fib_entry, op, 0);
-}
-
static void mlxsw_sp_adj_grp_size_round_up(u16 *p_adj_grp_size)
{
/* Valid sizes for an adjacency group are:
@@ -3352,6 +3338,73 @@ mlxsw_sp_nexthop_group_rebalance(struct mlxsw_sp_nexthop_group *nh_grp)
}
}
+static struct mlxsw_sp_nexthop *
+mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp,
+ const struct mlxsw_sp_rt6 *mlxsw_sp_rt6);
+
+static void
+mlxsw_sp_nexthop4_group_offload_refresh(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ int i;
+
+ for (i = 0; i < nh_grp->count; i++) {
+ struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+
+ if (nh->offloaded)
+ nh->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
+ else
+ nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
+ }
+}
+
+static void
+__mlxsw_sp_nexthop6_group_offload_refresh(struct mlxsw_sp_nexthop_group *nh_grp,
+ struct mlxsw_sp_fib6_entry *fib6_entry)
+{
+ struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
+
+ list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
+ struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh;
+ struct mlxsw_sp_nexthop *nh;
+
+ nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6);
+ if (nh && nh->offloaded)
+ fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
+ else
+ fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
+ }
+}
+
+static void
+mlxsw_sp_nexthop6_group_offload_refresh(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ struct mlxsw_sp_fib6_entry *fib6_entry;
+
+ /* Unfortunately, in IPv6 the route and the nexthop are described by
+ * the same struct, so we need to iterate over all the routes using the
+ * nexthop group and set / clear the offload indication for them.
+ */
+ list_for_each_entry(fib6_entry, &nh_grp->fib_list,
+ common.nexthop_group_node)
+ __mlxsw_sp_nexthop6_group_offload_refresh(nh_grp, fib6_entry);
+}
+
+static void
+mlxsw_sp_nexthop_group_offload_refresh(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp)
+{
+ switch (mlxsw_sp_nexthop_group_type(nh_grp)) {
+ case AF_INET:
+ mlxsw_sp_nexthop4_group_offload_refresh(mlxsw_sp, nh_grp);
+ break;
+ case AF_INET6:
+ mlxsw_sp_nexthop6_group_offload_refresh(mlxsw_sp, nh_grp);
+ break;
+ }
+}
+
static void
mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp)
@@ -3425,6 +3478,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
goto set_trap;
}
+ mlxsw_sp_nexthop_group_offload_refresh(mlxsw_sp, nh_grp);
+
if (!old_adj_index_valid) {
/* The trap was set for fib entries, so we have to call
* fib entry update to unset it and use adjacency index.
@@ -3446,9 +3501,6 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
goto set_trap;
}
- /* Offload state within the group changed, so update the flags. */
- mlxsw_sp_nexthop_fib_entries_refresh(nh_grp);
-
return;
set_trap:
@@ -3461,6 +3513,7 @@ set_trap:
err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
if (err)
dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n");
+ mlxsw_sp_nexthop_group_offload_refresh(mlxsw_sp, nh_grp);
if (old_adj_index_valid)
mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
nh_grp->ecmp_size, nh_grp->adj_index);
@@ -4043,131 +4096,128 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp,
}
static void
-mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
+mlxsw_sp_fib4_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
- struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
- int i;
-
- if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL ||
- fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE ||
- fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP ||
- fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP) {
- nh_grp->nexthops->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
- return;
- }
-
- for (i = 0; i < nh_grp->count; i++) {
- struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+ struct fib_info *fi = mlxsw_sp_nexthop4_group_fi(fib_entry->nh_group);
+ u32 *p_dst = (u32 *) fib_entry->fib_node->key.addr;
+ int dst_len = fib_entry->fib_node->key.prefix_len;
+ struct mlxsw_sp_fib4_entry *fib4_entry;
+ struct fib_rt_info fri;
+ bool should_offload;
- if (nh->offloaded)
- nh->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
- else
- nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
- }
+ should_offload = mlxsw_sp_fib_entry_should_offload(fib_entry);
+ fib4_entry = container_of(fib_entry, struct mlxsw_sp_fib4_entry,
+ common);
+ fri.fi = fi;
+ fri.tb_id = fib4_entry->tb_id;
+ fri.dst = cpu_to_be32(*p_dst);
+ fri.dst_len = dst_len;
+ fri.tos = fib4_entry->tos;
+ fri.type = fib4_entry->type;
+ fri.offload = should_offload;
+ fri.trap = !should_offload;
+ fib_alias_hw_flags_set(mlxsw_sp_net(mlxsw_sp), &fri);
}
static void
-mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
+mlxsw_sp_fib4_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
- struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
- int i;
-
- if (!list_is_singular(&nh_grp->fib_list))
- return;
-
- for (i = 0; i < nh_grp->count; i++) {
- struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
+ struct fib_info *fi = mlxsw_sp_nexthop4_group_fi(fib_entry->nh_group);
+ u32 *p_dst = (u32 *) fib_entry->fib_node->key.addr;
+ int dst_len = fib_entry->fib_node->key.prefix_len;
+ struct mlxsw_sp_fib4_entry *fib4_entry;
+ struct fib_rt_info fri;
- nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
- }
+ fib4_entry = container_of(fib_entry, struct mlxsw_sp_fib4_entry,
+ common);
+ fri.fi = fi;
+ fri.tb_id = fib4_entry->tb_id;
+ fri.dst = cpu_to_be32(*p_dst);
+ fri.dst_len = dst_len;
+ fri.tos = fib4_entry->tos;
+ fri.type = fib4_entry->type;
+ fri.offload = false;
+ fri.trap = false;
+ fib_alias_hw_flags_set(mlxsw_sp_net(mlxsw_sp), &fri);
}
static void
-mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
+mlxsw_sp_fib6_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
+ bool should_offload;
+
+ should_offload = mlxsw_sp_fib_entry_should_offload(fib_entry);
+ /* In IPv6 a multipath route is represented using multiple routes, so
+ * we need to set the flags on all of them.
+ */
fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry,
common);
-
- if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL ||
- fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE) {
- list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6,
- list)->rt->fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
- return;
- }
-
- list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
- struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
- struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh;
- struct mlxsw_sp_nexthop *nh;
-
- nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6);
- if (nh && nh->offloaded)
- fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
- else
- fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
- }
+ list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list)
+ fib6_info_hw_flags_set(mlxsw_sp_rt6->rt, should_offload,
+ !should_offload);
}
static void
-mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
+mlxsw_sp_fib6_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry,
common);
- list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
- struct fib6_info *rt = mlxsw_sp_rt6->rt;
-
- rt->fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
- }
+ list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list)
+ fib6_info_hw_flags_set(mlxsw_sp_rt6->rt, false, false);
}
-static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
+static void
+mlxsw_sp_fib_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
switch (fib_entry->fib_node->fib->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
- mlxsw_sp_fib4_entry_offload_set(fib_entry);
+ mlxsw_sp_fib4_entry_hw_flags_set(mlxsw_sp, fib_entry);
break;
case MLXSW_SP_L3_PROTO_IPV6:
- mlxsw_sp_fib6_entry_offload_set(fib_entry);
+ mlxsw_sp_fib6_entry_hw_flags_set(mlxsw_sp, fib_entry);
break;
}
}
static void
-mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
+mlxsw_sp_fib_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
{
switch (fib_entry->fib_node->fib->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
- mlxsw_sp_fib4_entry_offload_unset(fib_entry);
+ mlxsw_sp_fib4_entry_hw_flags_clear(mlxsw_sp, fib_entry);
break;
case MLXSW_SP_L3_PROTO_IPV6:
- mlxsw_sp_fib6_entry_offload_unset(fib_entry);
+ mlxsw_sp_fib6_entry_hw_flags_clear(mlxsw_sp, fib_entry);
break;
}
}
static void
-mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry,
- enum mlxsw_reg_ralue_op op, int err)
+mlxsw_sp_fib_entry_hw_flags_refresh(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry,
+ enum mlxsw_reg_ralue_op op)
{
switch (op) {
- case MLXSW_REG_RALUE_OP_WRITE_DELETE:
- return mlxsw_sp_fib_entry_offload_unset(fib_entry);
case MLXSW_REG_RALUE_OP_WRITE_WRITE:
- if (err)
- return;
- if (mlxsw_sp_fib_entry_should_offload(fib_entry))
- mlxsw_sp_fib_entry_offload_set(fib_entry);
- else
- mlxsw_sp_fib_entry_offload_unset(fib_entry);
- return;
+ mlxsw_sp_fib_entry_hw_flags_set(mlxsw_sp, fib_entry);
+ break;
+ case MLXSW_REG_RALUE_OP_WRITE_DELETE:
+ mlxsw_sp_fib_entry_hw_flags_clear(mlxsw_sp, fib_entry);
+ break;
default:
- return;
+ break;
}
}
@@ -4394,7 +4444,10 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
{
int err = __mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, op);
- mlxsw_sp_fib_entry_offload_refresh(fib_entry, op, err);
+ if (err)
+ return err;
+
+ mlxsw_sp_fib_entry_hw_flags_refresh(mlxsw_sp, fib_entry, op);
return err;
}
@@ -4830,7 +4883,7 @@ mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp,
if (!replaced)
return 0;
- mlxsw_sp_fib_entry_offload_unset(replaced);
+ mlxsw_sp_fib_entry_hw_flags_clear(mlxsw_sp, replaced);
fib4_replaced = container_of(replaced, struct mlxsw_sp_fib4_entry,
common);
mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib4_replaced);
@@ -5113,6 +5166,11 @@ static int mlxsw_sp_nexthop6_group_get(struct mlxsw_sp *mlxsw_sp,
&nh_grp->fib_list);
fib6_entry->common.nh_group = nh_grp;
+ /* The route and the nexthop are described by the same struct, so we
+ * need to the update the nexthop offload indication for the new route.
+ */
+ __mlxsw_sp_nexthop6_group_offload_refresh(nh_grp, fib6_entry);
+
return 0;
}
@@ -5393,7 +5451,7 @@ static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp,
if (!replaced)
return 0;
- mlxsw_sp_fib_entry_offload_unset(replaced);
+ mlxsw_sp_fib_entry_hw_flags_clear(mlxsw_sp, replaced);
fib6_replaced = container_of(replaced, struct mlxsw_sp_fib6_entry,
common);
mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_replaced);
diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c
index b5df308b4e33..8f56289fc2ec 100644
--- a/drivers/net/netdevsim/fib.c
+++ b/drivers/net/netdevsim/fib.c
@@ -14,6 +14,12 @@
* THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
*/
+#include <linux/in6.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/rhashtable.h>
+#include <linux/spinlock_types.h>
+#include <linux/types.h>
#include <net/fib_notifier.h>
#include <net/ip_fib.h>
#include <net/ip6_fib.h>
@@ -36,6 +42,48 @@ struct nsim_fib_data {
struct notifier_block fib_nb;
struct nsim_per_fib_data ipv4;
struct nsim_per_fib_data ipv6;
+ struct rhashtable fib_rt_ht;
+ struct list_head fib_rt_list;
+ spinlock_t fib_lock; /* Protects hashtable, list and accounting */
+ struct devlink *devlink;
+};
+
+struct nsim_fib_rt_key {
+ unsigned char addr[sizeof(struct in6_addr)];
+ unsigned char prefix_len;
+ int family;
+ u32 tb_id;
+};
+
+struct nsim_fib_rt {
+ struct nsim_fib_rt_key key;
+ struct rhash_head ht_node;
+ struct list_head list; /* Member of fib_rt_list */
+};
+
+struct nsim_fib4_rt {
+ struct nsim_fib_rt common;
+ struct fib_info *fi;
+ u8 tos;
+ u8 type;
+};
+
+struct nsim_fib6_rt {
+ struct nsim_fib_rt common;
+ struct list_head nh_list;
+ unsigned int nhs;
+};
+
+struct nsim_fib6_rt_nh {
+ struct list_head list; /* Member of nh_list */
+ struct fib6_info *rt;
+};
+
+static const struct rhashtable_params nsim_fib_rt_ht_params = {
+ .key_offset = offsetof(struct nsim_fib_rt, key),
+ .head_offset = offsetof(struct nsim_fib_rt, ht_node),
+ .key_len = sizeof(struct nsim_fib_rt_key),
+ .automatic_shrinking = true,
};
u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
@@ -144,18 +192,556 @@ static int nsim_fib_account(struct nsim_fib_entry *entry, bool add,
return err;
}
+static void nsim_fib_rt_init(struct nsim_fib_data *data,
+ struct nsim_fib_rt *fib_rt, const void *addr,
+ size_t addr_len, unsigned int prefix_len,
+ int family, u32 tb_id)
+{
+ memcpy(fib_rt->key.addr, addr, addr_len);
+ fib_rt->key.prefix_len = prefix_len;
+ fib_rt->key.family = family;
+ fib_rt->key.tb_id = tb_id;
+ list_add(&fib_rt->list, &data->fib_rt_list);
+}
+
+static void nsim_fib_rt_fini(struct nsim_fib_rt *fib_rt)
+{
+ list_del(&fib_rt->list);
+}
+
+static struct nsim_fib_rt *nsim_fib_rt_lookup(struct rhashtable *fib_rt_ht,
+ const void *addr, size_t addr_len,
+ unsigned int prefix_len,
+ int family, u32 tb_id)
+{
+ struct nsim_fib_rt_key key;
+
+ memset(&key, 0, sizeof(key));
+ memcpy(key.addr, addr, addr_len);
+ key.prefix_len = prefix_len;
+ key.family = family;
+ key.tb_id = tb_id;
+
+ return rhashtable_lookup_fast(fib_rt_ht, &key, nsim_fib_rt_ht_params);
+}
+
+static struct nsim_fib4_rt *
+nsim_fib4_rt_create(struct nsim_fib_data *data,
+ struct fib_entry_notifier_info *fen_info)
+{
+ struct nsim_fib4_rt *fib4_rt;
+
+ fib4_rt = kzalloc(sizeof(*fib4_rt), GFP_ATOMIC);
+ if (!fib4_rt)
+ return NULL;
+
+ nsim_fib_rt_init(data, &fib4_rt->common, &fen_info->dst, sizeof(u32),
+ fen_info->dst_len, AF_INET, fen_info->tb_id);
+
+ fib4_rt->fi = fen_info->fi;
+ fib_info_hold(fib4_rt->fi);
+ fib4_rt->tos = fen_info->tos;
+ fib4_rt->type = fen_info->type;
+
+ return fib4_rt;
+}
+
+static void nsim_fib4_rt_destroy(struct nsim_fib4_rt *fib4_rt)
+{
+ fib_info_put(fib4_rt->fi);
+ nsim_fib_rt_fini(&fib4_rt->common);
+ kfree(fib4_rt);
+}
+
+static struct nsim_fib4_rt *
+nsim_fib4_rt_lookup(struct rhashtable *fib_rt_ht,
+ const struct fib_entry_notifier_info *fen_info)
+{
+ struct nsim_fib_rt *fib_rt;
+
+ fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &fen_info->dst, sizeof(u32),
+ fen_info->dst_len, AF_INET,
+ fen_info->tb_id);
+ if (!fib_rt)
+ return NULL;
+
+ return container_of(fib_rt, struct nsim_fib4_rt, common);
+}
+
+static void nsim_fib4_rt_hw_flags_set(struct net *net,
+ const struct nsim_fib4_rt *fib4_rt,
+ bool trap)
+{
+ u32 *p_dst = (u32 *) fib4_rt->common.key.addr;
+ int dst_len = fib4_rt->common.key.prefix_len;
+ struct fib_rt_info fri;
+
+ fri.fi = fib4_rt->fi;
+ fri.tb_id = fib4_rt->common.key.tb_id;
+ fri.dst = cpu_to_be32(*p_dst);
+ fri.dst_len = dst_len;
+ fri.tos = fib4_rt->tos;
+ fri.type = fib4_rt->type;
+ fri.offload = false;
+ fri.trap = trap;
+ fib_alias_hw_flags_set(net, &fri);
+}
+
+static int nsim_fib4_rt_add(struct nsim_fib_data *data,
+ struct nsim_fib4_rt *fib4_rt,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = devlink_net(data->devlink);
+ int err;
+
+ err = nsim_fib_account(&data->ipv4.fib, true, extack);
+ if (err)
+ return err;
+
+ err = rhashtable_insert_fast(&data->fib_rt_ht,
+ &fib4_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to insert IPv4 route");
+ goto err_fib_dismiss;
+ }
+
+ nsim_fib4_rt_hw_flags_set(net, fib4_rt, true);
+
+ return 0;
+
+err_fib_dismiss:
+ nsim_fib_account(&data->ipv4.fib, false, extack);
+ return err;
+}
+
+static int nsim_fib4_rt_replace(struct nsim_fib_data *data,
+ struct nsim_fib4_rt *fib4_rt,
+ struct nsim_fib4_rt *fib4_rt_old,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = devlink_net(data->devlink);
+ int err;
+
+ /* We are replacing a route, so no need to change the accounting. */
+ err = rhashtable_replace_fast(&data->fib_rt_ht,
+ &fib4_rt_old->common.ht_node,
+ &fib4_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to replace IPv4 route");
+ return err;
+ }
+
+ nsim_fib4_rt_hw_flags_set(net, fib4_rt, true);
+
+ nsim_fib4_rt_hw_flags_set(net, fib4_rt_old, false);
+ nsim_fib4_rt_destroy(fib4_rt_old);
+
+ return 0;
+}
+
+static int nsim_fib4_rt_insert(struct nsim_fib_data *data,
+ struct fib_entry_notifier_info *fen_info)
+{
+ struct netlink_ext_ack *extack = fen_info->info.extack;
+ struct nsim_fib4_rt *fib4_rt, *fib4_rt_old;
+ int err;
+
+ fib4_rt = nsim_fib4_rt_create(data, fen_info);
+ if (!fib4_rt)
+ return -ENOMEM;
+
+ fib4_rt_old = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info);
+ if (!fib4_rt_old)
+ err = nsim_fib4_rt_add(data, fib4_rt, extack);
+ else
+ err = nsim_fib4_rt_replace(data, fib4_rt, fib4_rt_old, extack);
+
+ if (err)
+ nsim_fib4_rt_destroy(fib4_rt);
+
+ return err;
+}
+
+static void nsim_fib4_rt_remove(struct nsim_fib_data *data,
+ const struct fib_entry_notifier_info *fen_info)
+{
+ struct netlink_ext_ack *extack = fen_info->info.extack;
+ struct nsim_fib4_rt *fib4_rt;
+
+ fib4_rt = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info);
+ if (WARN_ON_ONCE(!fib4_rt))
+ return;
+
+ rhashtable_remove_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ nsim_fib_account(&data->ipv4.fib, false, extack);
+ nsim_fib4_rt_destroy(fib4_rt);
+}
+
+static int nsim_fib4_event(struct nsim_fib_data *data,
+ struct fib_notifier_info *info,
+ unsigned long event)
+{
+ struct fib_entry_notifier_info *fen_info;
+ int err = 0;
+
+ fen_info = container_of(info, struct fib_entry_notifier_info, info);
+
+ if (fen_info->fi->nh) {
+ NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported");
+ return 0;
+ }
+
+ switch (event) {
+ case FIB_EVENT_ENTRY_REPLACE:
+ err = nsim_fib4_rt_insert(data, fen_info);
+ break;
+ case FIB_EVENT_ENTRY_DEL:
+ nsim_fib4_rt_remove(data, fen_info);
+ break;
+ default:
+ break;
+ }
+
+ return err;
+}
+
+static struct nsim_fib6_rt_nh *
+nsim_fib6_rt_nh_find(const struct nsim_fib6_rt *fib6_rt,
+ const struct fib6_info *rt)
+{
+ struct nsim_fib6_rt_nh *fib6_rt_nh;
+
+ list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list) {
+ if (fib6_rt_nh->rt == rt)
+ return fib6_rt_nh;
+ }
+
+ return NULL;
+}
+
+static int nsim_fib6_rt_nh_add(struct nsim_fib6_rt *fib6_rt,
+ struct fib6_info *rt)
+{
+ struct nsim_fib6_rt_nh *fib6_rt_nh;
+
+ fib6_rt_nh = kzalloc(sizeof(*fib6_rt_nh), GFP_ATOMIC);
+ if (!fib6_rt_nh)
+ return -ENOMEM;
+
+ fib6_info_hold(rt);
+ fib6_rt_nh->rt = rt;
+ list_add_tail(&fib6_rt_nh->list, &fib6_rt->nh_list);
+ fib6_rt->nhs++;
+
+ return 0;
+}
+
+static void nsim_fib6_rt_nh_del(struct nsim_fib6_rt *fib6_rt,
+ const struct fib6_info *rt)
+{
+ struct nsim_fib6_rt_nh *fib6_rt_nh;
+
+ fib6_rt_nh = nsim_fib6_rt_nh_find(fib6_rt, rt);
+ if (WARN_ON_ONCE(!fib6_rt_nh))
+ return;
+
+ fib6_rt->nhs--;
+ list_del(&fib6_rt_nh->list);
+#if IS_ENABLED(CONFIG_IPV6)
+ fib6_info_release(fib6_rt_nh->rt);
+#endif
+ kfree(fib6_rt_nh);
+}
+
+static struct nsim_fib6_rt *
+nsim_fib6_rt_create(struct nsim_fib_data *data,
+ struct fib6_entry_notifier_info *fen6_info)
+{
+ struct fib6_info *iter, *rt = fen6_info->rt;
+ struct nsim_fib6_rt *fib6_rt;
+ int i = 0;
+ int err;
+
+ fib6_rt = kzalloc(sizeof(*fib6_rt), GFP_ATOMIC);
+ if (!fib6_rt)
+ return NULL;
+
+ nsim_fib_rt_init(data, &fib6_rt->common, &rt->fib6_dst.addr,
+ sizeof(rt->fib6_dst.addr), rt->fib6_dst.plen, AF_INET6,
+ rt->fib6_table->tb6_id);
+
+ /* We consider a multipath IPv6 route as one entry, but it can be made
+ * up from several fib6_info structs (one for each nexthop), so we
+ * add them all to the same list under the entry.
+ */
+ INIT_LIST_HEAD(&fib6_rt->nh_list);
+
+ err = nsim_fib6_rt_nh_add(fib6_rt, rt);
+ if (err)
+ goto err_fib_rt_fini;
+
+ if (!fen6_info->nsiblings)
+ return fib6_rt;
+
+ list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
+ if (i == fen6_info->nsiblings)
+ break;
+
+ err = nsim_fib6_rt_nh_add(fib6_rt, iter);
+ if (err)
+ goto err_fib6_rt_nh_del;
+ i++;
+ }
+ WARN_ON_ONCE(i != fen6_info->nsiblings);
+
+ return fib6_rt;
+
+err_fib6_rt_nh_del:
+ list_for_each_entry_continue_reverse(iter, &rt->fib6_siblings,
+ fib6_siblings)
+ nsim_fib6_rt_nh_del(fib6_rt, iter);
+ nsim_fib6_rt_nh_del(fib6_rt, rt);
+err_fib_rt_fini:
+ nsim_fib_rt_fini(&fib6_rt->common);
+ kfree(fib6_rt);
+ return ERR_PTR(err);
+}
+
+static void nsim_fib6_rt_destroy(struct nsim_fib6_rt *fib6_rt)
+{
+ struct nsim_fib6_rt_nh *iter, *tmp;
+
+ list_for_each_entry_safe(iter, tmp, &fib6_rt->nh_list, list)
+ nsim_fib6_rt_nh_del(fib6_rt, iter->rt);
+ WARN_ON_ONCE(!list_empty(&fib6_rt->nh_list));
+ nsim_fib_rt_fini(&fib6_rt->common);
+ kfree(fib6_rt);
+}
+
+static struct nsim_fib6_rt *
+nsim_fib6_rt_lookup(struct rhashtable *fib_rt_ht, const struct fib6_info *rt)
+{
+ struct nsim_fib_rt *fib_rt;
+
+ fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &rt->fib6_dst.addr,
+ sizeof(rt->fib6_dst.addr),
+ rt->fib6_dst.plen, AF_INET6,
+ rt->fib6_table->tb6_id);
+ if (!fib_rt)
+ return NULL;
+
+ return container_of(fib_rt, struct nsim_fib6_rt, common);
+}
+
+static int nsim_fib6_rt_append(struct nsim_fib_data *data,
+ struct fib6_entry_notifier_info *fen6_info)
+{
+ struct fib6_info *iter, *rt = fen6_info->rt;
+ struct nsim_fib6_rt *fib6_rt;
+ int i = 0;
+ int err;
+
+ fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt);
+ if (WARN_ON_ONCE(!fib6_rt))
+ return -EINVAL;
+
+ err = nsim_fib6_rt_nh_add(fib6_rt, rt);
+ if (err)
+ return err;
+ rt->trap = true;
+
+ if (!fen6_info->nsiblings)
+ return 0;
+
+ list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
+ if (i == fen6_info->nsiblings)
+ break;
+
+ err = nsim_fib6_rt_nh_add(fib6_rt, iter);
+ if (err)
+ goto err_fib6_rt_nh_del;
+ iter->trap = true;
+ i++;
+ }
+ WARN_ON_ONCE(i != fen6_info->nsiblings);
+
+ return 0;
+
+err_fib6_rt_nh_del:
+ list_for_each_entry_continue_reverse(iter, &rt->fib6_siblings,
+ fib6_siblings) {
+ iter->trap = false;
+ nsim_fib6_rt_nh_del(fib6_rt, iter);
+ }
+ rt->trap = false;
+ nsim_fib6_rt_nh_del(fib6_rt, rt);
+ return err;
+}
+
+static void nsim_fib6_rt_hw_flags_set(const struct nsim_fib6_rt *fib6_rt,
+ bool trap)
+{
+ struct nsim_fib6_rt_nh *fib6_rt_nh;
+
+ list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list)
+ fib6_info_hw_flags_set(fib6_rt_nh->rt, false, trap);
+}
+
+static int nsim_fib6_rt_add(struct nsim_fib_data *data,
+ struct nsim_fib6_rt *fib6_rt,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ err = nsim_fib_account(&data->ipv6.fib, true, extack);
+ if (err)
+ return err;
+
+ err = rhashtable_insert_fast(&data->fib_rt_ht,
+ &fib6_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to insert IPv6 route");
+ goto err_fib_dismiss;
+ }
+
+ nsim_fib6_rt_hw_flags_set(fib6_rt, true);
+
+ return 0;
+
+err_fib_dismiss:
+ nsim_fib_account(&data->ipv6.fib, false, extack);
+ return err;
+}
+
+static int nsim_fib6_rt_replace(struct nsim_fib_data *data,
+ struct nsim_fib6_rt *fib6_rt,
+ struct nsim_fib6_rt *fib6_rt_old,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ /* We are replacing a route, so no need to change the accounting. */
+ err = rhashtable_replace_fast(&data->fib_rt_ht,
+ &fib6_rt_old->common.ht_node,
+ &fib6_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to replace IPv6 route");
+ return err;
+ }
+
+ nsim_fib6_rt_hw_flags_set(fib6_rt, true);
+
+ nsim_fib6_rt_hw_flags_set(fib6_rt_old, false);
+ nsim_fib6_rt_destroy(fib6_rt_old);
+
+ return 0;
+}
+
+static int nsim_fib6_rt_insert(struct nsim_fib_data *data,
+ struct fib6_entry_notifier_info *fen6_info)
+{
+ struct netlink_ext_ack *extack = fen6_info->info.extack;
+ struct nsim_fib6_rt *fib6_rt, *fib6_rt_old;
+ int err;
+
+ fib6_rt = nsim_fib6_rt_create(data, fen6_info);
+ if (!fib6_rt)
+ return -ENOMEM;
+
+ fib6_rt_old = nsim_fib6_rt_lookup(&data->fib_rt_ht, fen6_info->rt);
+ if (!fib6_rt_old)
+ err = nsim_fib6_rt_add(data, fib6_rt, extack);
+ else
+ err = nsim_fib6_rt_replace(data, fib6_rt, fib6_rt_old, extack);
+
+ if (err)
+ nsim_fib6_rt_destroy(fib6_rt);
+
+ return err;
+}
+
+static void
+nsim_fib6_rt_remove(struct nsim_fib_data *data,
+ const struct fib6_entry_notifier_info *fen6_info)
+{
+ struct netlink_ext_ack *extack = fen6_info->info.extack;
+ struct nsim_fib6_rt *fib6_rt;
+
+ /* Multipath routes are first added to the FIB trie and only then
+ * notified. If we vetoed the addition, we will get a delete
+ * notification for a route we do not have. Therefore, do not warn if
+ * route was not found.
+ */
+ fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, fen6_info->rt);
+ if (!fib6_rt)
+ return;
+
+ /* If not all the nexthops are deleted, then only reduce the nexthop
+ * group.
+ */
+ if (fen6_info->nsiblings + 1 != fib6_rt->nhs) {
+ nsim_fib6_rt_nh_del(fib6_rt, fen6_info->rt);
+ return;
+ }
+
+ rhashtable_remove_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node,
+ nsim_fib_rt_ht_params);
+ nsim_fib_account(&data->ipv6.fib, false, extack);
+ nsim_fib6_rt_destroy(fib6_rt);
+}
+
+static int nsim_fib6_event(struct nsim_fib_data *data,
+ struct fib_notifier_info *info,
+ unsigned long event)
+{
+ struct fib6_entry_notifier_info *fen6_info;
+ int err = 0;
+
+ fen6_info = container_of(info, struct fib6_entry_notifier_info, info);
+
+ if (fen6_info->rt->nh) {
+ NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported");
+ return 0;
+ }
+
+ if (fen6_info->rt->fib6_src.plen) {
+ NL_SET_ERR_MSG_MOD(info->extack, "IPv6 source-specific route is not supported");
+ return 0;
+ }
+
+ switch (event) {
+ case FIB_EVENT_ENTRY_REPLACE:
+ err = nsim_fib6_rt_insert(data, fen6_info);
+ break;
+ case FIB_EVENT_ENTRY_APPEND:
+ err = nsim_fib6_rt_append(data, fen6_info);
+ break;
+ case FIB_EVENT_ENTRY_DEL:
+ nsim_fib6_rt_remove(data, fen6_info);
+ break;
+ default:
+ break;
+ }
+
+ return err;
+}
+
static int nsim_fib_event(struct nsim_fib_data *data,
- struct fib_notifier_info *info, bool add)
+ struct fib_notifier_info *info, unsigned long event)
{
- struct netlink_ext_ack *extack = info->extack;
int err = 0;
switch (info->family) {
case AF_INET:
- err = nsim_fib_account(&data->ipv4.fib, add, extack);
+ err = nsim_fib4_event(data, info, event);
break;
case AF_INET6:
- err = nsim_fib_account(&data->ipv6.fib, add, extack);
+ err = nsim_fib6_event(data, info, event);
break;
}
@@ -170,6 +756,9 @@ static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event,
struct fib_notifier_info *info = ptr;
int err = 0;
+ /* IPv6 routes can be added via RAs from softIRQ. */
+ spin_lock_bh(&data->fib_lock);
+
switch (event) {
case FIB_EVENT_RULE_ADD: /* fall through */
case FIB_EVENT_RULE_DEL:
@@ -178,23 +767,74 @@ static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event,
break;
case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+ case FIB_EVENT_ENTRY_APPEND: /* fall through */
case FIB_EVENT_ENTRY_DEL:
- err = nsim_fib_event(data, info, event != FIB_EVENT_ENTRY_DEL);
+ err = nsim_fib_event(data, info, event);
break;
}
+ spin_unlock_bh(&data->fib_lock);
+
return notifier_from_errno(err);
}
+static void nsim_fib4_rt_free(struct nsim_fib_rt *fib_rt,
+ struct nsim_fib_data *data)
+{
+ struct devlink *devlink = data->devlink;
+ struct nsim_fib4_rt *fib4_rt;
+
+ fib4_rt = container_of(fib_rt, struct nsim_fib4_rt, common);
+ nsim_fib4_rt_hw_flags_set(devlink_net(devlink), fib4_rt, false);
+ nsim_fib_account(&data->ipv4.fib, false, NULL);
+ nsim_fib4_rt_destroy(fib4_rt);
+}
+
+static void nsim_fib6_rt_free(struct nsim_fib_rt *fib_rt,
+ struct nsim_fib_data *data)
+{
+ struct nsim_fib6_rt *fib6_rt;
+
+ fib6_rt = container_of(fib_rt, struct nsim_fib6_rt, common);
+ nsim_fib6_rt_hw_flags_set(fib6_rt, false);
+ nsim_fib_account(&data->ipv6.fib, false, NULL);
+ nsim_fib6_rt_destroy(fib6_rt);
+}
+
+static void nsim_fib_rt_free(void *ptr, void *arg)
+{
+ struct nsim_fib_rt *fib_rt = ptr;
+ struct nsim_fib_data *data = arg;
+
+ switch (fib_rt->key.family) {
+ case AF_INET:
+ nsim_fib4_rt_free(fib_rt, data);
+ break;
+ case AF_INET6:
+ nsim_fib6_rt_free(fib_rt, data);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ }
+}
+
/* inconsistent dump, trying again */
static void nsim_fib_dump_inconsistent(struct notifier_block *nb)
{
struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data,
fib_nb);
+ struct nsim_fib_rt *fib_rt, *fib_rt_tmp;
+
+ /* The notifier block is still not registered, so we do not need to
+ * take any locks here.
+ */
+ list_for_each_entry_safe(fib_rt, fib_rt_tmp, &data->fib_rt_list, list) {
+ rhashtable_remove_fast(&data->fib_rt_ht, &fib_rt->ht_node,
+ nsim_fib_rt_ht_params);
+ nsim_fib_rt_free(fib_rt, data);
+ }
- data->ipv4.fib.num = 0ULL;
data->ipv4.rules.num = 0ULL;
- data->ipv6.fib.num = 0ULL;
data->ipv6.rules.num = 0ULL;
}
@@ -255,6 +895,13 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
return ERR_PTR(-ENOMEM);
+ data->devlink = devlink;
+
+ spin_lock_init(&data->fib_lock);
+ INIT_LIST_HEAD(&data->fib_rt_list);
+ err = rhashtable_init(&data->fib_rt_ht, &nsim_fib_rt_ht_params);
+ if (err)
+ goto err_data_free;
nsim_fib_set_max_all(data, devlink);
@@ -263,7 +910,7 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
nsim_fib_dump_inconsistent, extack);
if (err) {
pr_err("Failed to register fib notifier\n");
- goto err_out;
+ goto err_rhashtable_destroy;
}
devlink_resource_occ_get_register(devlink,
@@ -284,7 +931,10 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
data);
return data;
-err_out:
+err_rhashtable_destroy:
+ rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free,
+ data);
+err_data_free:
kfree(data);
return ERR_PTR(err);
}
@@ -300,5 +950,8 @@ void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data)
devlink_resource_occ_get_unregister(devlink,
NSIM_RESOURCE_IPV4_FIB);
unregister_fib_notifier(devlink_net(devlink), &data->fib_nb);
+ rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free,
+ data);
+ WARN_ON_ONCE(!list_empty(&data->fib_rt_list));
kfree(data);
}
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index b579faea41e9..fd60a8ac02ee 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -192,7 +192,9 @@ struct fib6_info {
dst_nopolicy:1,
dst_host:1,
fib6_destroying:1,
- unused:3;
+ offload:1,
+ trap:1,
+ unused:1;
struct rcu_head rcu;
struct nexthop *nh;
@@ -329,6 +331,13 @@ static inline void fib6_info_release(struct fib6_info *f6i)
call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
}
+static inline void fib6_info_hw_flags_set(struct fib6_info *f6i, bool offload,
+ bool trap)
+{
+ f6i->offload = offload;
+ f6i->trap = trap;
+}
+
enum fib6_walk_state {
#ifdef CONFIG_IPV6_SUBTREES
FWS_S,
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index b9cba41c6d4f..6a1ae49809de 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -204,6 +204,18 @@ __be32 fib_result_prefsrc(struct net *net, struct fib_result *res);
#define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev)
#define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif)
+struct fib_rt_info {
+ struct fib_info *fi;
+ u32 tb_id;
+ __be32 dst;
+ int dst_len;
+ u8 tos;
+ u8 type;
+ u8 offload:1,
+ trap:1,
+ unused:6;
+};
+
struct fib_entry_notifier_info {
struct fib_notifier_info info; /* must be first */
u32 dst;
@@ -464,6 +476,7 @@ int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *fc_encap,
void fib_nh_common_release(struct fib_nh_common *nhc);
/* Exported by fib_trie.c */
+void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri);
void fib_trie_init(void);
struct fib_table *fib_trie_table(u32 id, struct fib_table *alias);
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 1418a8362bb7..cd43321d20dd 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -309,6 +309,8 @@ enum rt_scope_t {
#define RTM_F_PREFIX 0x800 /* Prefix addresses */
#define RTM_F_LOOKUP_TABLE 0x1000 /* set rtm_table to FIB lookup result */
#define RTM_F_FIB_MATCH 0x2000 /* return full fib lookup match */
+#define RTM_F_OFFLOAD 0x4000 /* route is offloaded */
+#define RTM_F_TRAP 0x8000 /* route is trapping packets */
/* Reserved table identifiers */
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index a68b5e21ec51..c092e9a55790 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -16,6 +16,9 @@ struct fib_alias {
u8 fa_slen;
u32 tb_id;
s16 fa_default;
+ u8 offload:1,
+ trap:1,
+ unused:6;
struct rcu_head rcu;
};
@@ -35,9 +38,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
struct netlink_ext_ack *extack);
bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi);
-int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id,
- u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi,
- unsigned int);
+int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
+ struct fib_rt_info *fri, unsigned int flags);
void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len,
u32 tb_id, const struct nl_info *info, unsigned int nlm_flags);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f1888c683426..a803cdd9400a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -504,6 +504,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
int dst_len, u32 tb_id, const struct nl_info *info,
unsigned int nlm_flags)
{
+ struct fib_rt_info fri;
struct sk_buff *skb;
u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
int err = -ENOBUFS;
@@ -512,9 +513,15 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
if (!skb)
goto errout;
- err = fib_dump_info(skb, info->portid, seq, event, tb_id,
- fa->fa_type, key, dst_len,
- fa->fa_tos, fa->fa_info, nlm_flags);
+ fri.fi = fa->fa_info;
+ fri.tb_id = tb_id;
+ fri.dst = key;
+ fri.dst_len = dst_len;
+ fri.tos = fa->fa_tos;
+ fri.type = fa->fa_type;
+ fri.offload = fa->offload;
+ fri.trap = fa->trap;
+ err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -1725,10 +1732,11 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi)
#endif
int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
- u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
- struct fib_info *fi, unsigned int flags)
+ struct fib_rt_info *fri, unsigned int flags)
{
- unsigned int nhs = fib_info_num_path(fi);
+ unsigned int nhs = fib_info_num_path(fri->fi);
+ struct fib_info *fi = fri->fi;
+ u32 tb_id = fri->tb_id;
struct nlmsghdr *nlh;
struct rtmsg *rtm;
@@ -1738,22 +1746,22 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
rtm = nlmsg_data(nlh);
rtm->rtm_family = AF_INET;
- rtm->rtm_dst_len = dst_len;
+ rtm->rtm_dst_len = fri->dst_len;
rtm->rtm_src_len = 0;
- rtm->rtm_tos = tos;
+ rtm->rtm_tos = fri->tos;
if (tb_id < 256)
rtm->rtm_table = tb_id;
else
rtm->rtm_table = RT_TABLE_COMPAT;
if (nla_put_u32(skb, RTA_TABLE, tb_id))
goto nla_put_failure;
- rtm->rtm_type = type;
+ rtm->rtm_type = fri->type;
rtm->rtm_flags = fi->fib_flags;
rtm->rtm_scope = fi->fib_scope;
rtm->rtm_protocol = fi->fib_protocol;
if (rtm->rtm_dst_len &&
- nla_put_in_addr(skb, RTA_DST, dst))
+ nla_put_in_addr(skb, RTA_DST, fri->dst))
goto nla_put_failure;
if (fi->fib_priority &&
nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
@@ -1795,6 +1803,11 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
goto nla_put_failure;
}
+ if (fri->offload)
+ rtm->rtm_flags |= RTM_F_OFFLOAD;
+ if (fri->trap)
+ rtm->rtm_flags |= RTM_F_TRAP;
+
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index b92a42433a7d..6ce1f2bbffd0 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1012,6 +1012,52 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen,
return NULL;
}
+static struct fib_alias *
+fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)
+{
+ u8 slen = KEYLENGTH - fri->dst_len;
+ struct key_vector *l, *tp;
+ struct fib_table *tb;
+ struct fib_alias *fa;
+ struct trie *t;
+
+ tb = fib_get_table(net, fri->tb_id);
+ if (!tb)
+ return NULL;
+
+ t = (struct trie *)tb->tb_data;
+ l = fib_find_node(t, &tp, be32_to_cpu(fri->dst));
+ if (!l)
+ return NULL;
+
+ hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+ if (fa->fa_slen == slen && fa->tb_id == fri->tb_id &&
+ fa->fa_tos == fri->tos && fa->fa_info == fri->fi &&
+ fa->fa_type == fri->type)
+ return fa;
+ }
+
+ return NULL;
+}
+
+void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
+{
+ struct fib_alias *fa_match;
+
+ rcu_read_lock();
+
+ fa_match = fib_find_matching_alias(net, fri);
+ if (!fa_match)
+ goto out;
+
+ fa_match->offload = fri->offload;
+ fa_match->trap = fri->trap;
+
+out:
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set);
+
static void trie_rebalance(struct trie *t, struct key_vector *tn)
{
while (!IS_TRIE(tn))
@@ -1220,24 +1266,29 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
new_fa->fa_slen = fa->fa_slen;
new_fa->tb_id = tb->tb_id;
new_fa->fa_default = -1;
+ new_fa->offload = 0;
+ new_fa->trap = 0;
+
+ hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list);
if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0,
- tb->tb_id, true) == fa) {
+ tb->tb_id, true) == new_fa) {
enum fib_event_type fib_event;
fib_event = FIB_EVENT_ENTRY_REPLACE;
err = call_fib_entry_notifiers(net, fib_event,
key, plen,
new_fa, extack);
- if (err)
+ if (err) {
+ hlist_replace_rcu(&new_fa->fa_list,
+ &fa->fa_list);
goto out_free_new_fa;
+ }
}
rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
tb->tb_id, &cfg->fc_nlinfo, nlflags);
- hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list);
-
alias_free_mem_rcu(fa);
fib_release_info(fi_drop);
@@ -1275,6 +1326,8 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
new_fa->fa_slen = slen;
new_fa->tb_id = tb->tb_id;
new_fa->fa_default = -1;
+ new_fa->offload = 0;
+ new_fa->trap = 0;
/* Insert new entry to the list. */
err = fib_insert_alias(t, tp, l, new_fa, fa, key);
@@ -2191,14 +2244,20 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
if (filter->dump_routes) {
if (!s_fa) {
+ struct fib_rt_info fri;
+
+ fri.fi = fi;
+ fri.tb_id = tb->tb_id;
+ fri.dst = xkey;
+ fri.dst_len = KEYLENGTH - fa->fa_slen;
+ fri.tos = fa->fa_tos;
+ fri.type = fa->fa_type;
+ fri.offload = fa->offload;
+ fri.trap = fa->trap;
err = fib_dump_info(skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- RTM_NEWROUTE,
- tb->tb_id, fa->fa_type,
- xkey,
- KEYLENGTH - fa->fa_slen,
- fa->fa_tos, fi, flags);
+ RTM_NEWROUTE, &fri, flags);
if (err < 0)
goto stop;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 87e979f2b74a..2010888e68ca 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3223,16 +3223,41 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
skb_reset_mac_header(skb);
if (rtm->rtm_flags & RTM_F_FIB_MATCH) {
+ struct fib_rt_info fri;
+
if (!res.fi) {
err = fib_props[res.type].error;
if (!err)
err = -EHOSTUNREACH;
goto errout_rcu;
}
+ fri.fi = res.fi;
+ fri.tb_id = table_id;
+ fri.dst = res.prefix;
+ fri.dst_len = res.prefixlen;
+ fri.tos = fl4.flowi4_tos;
+ fri.type = rt->rt_type;
+ fri.offload = 0;
+ fri.trap = 0;
+ if (res.fa_head) {
+ struct fib_alias *fa;
+
+ hlist_for_each_entry_rcu(fa, res.fa_head, fa_list) {
+ u8 slen = 32 - fri.dst_len;
+
+ if (fa->fa_slen == slen &&
+ fa->tb_id == fri.tb_id &&
+ fa->fa_tos == fri.tos &&
+ fa->fa_info == res.fi &&
+ fa->fa_type == fri.type) {
+ fri.offload = fa->offload;
+ fri.trap = fa->trap;
+ break;
+ }
+ }
+ }
err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
- rt->rt_type, res.prefix, res.prefixlen,
- fl4.flowi4_tos, res.fi, 0);
+ nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0);
} else {
err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb,
NETLINK_CB(in_skb).portid,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0253b702afb7..4fbdc60b4e07 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5576,6 +5576,13 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
expires -= jiffies;
}
+ if (!dst) {
+ if (rt->offload)
+ rtm->rtm_flags |= RTM_F_OFFLOAD;
+ if (rt->trap)
+ rtm->rtm_flags |= RTM_F_TRAP;
+ }
+
if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0)
goto nla_put_failure;
diff --git a/tools/testing/selftests/drivers/net/mlxsw/fib.sh b/tools/testing/selftests/drivers/net/mlxsw/fib.sh
new file mode 100755
index 000000000000..45115f81c2b1
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/fib.sh
@@ -0,0 +1,180 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking the FIB offload API on top of mlxsw.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ ipv4_identical_routes
+ ipv4_tos
+ ipv4_metric
+ ipv4_replace
+ ipv4_delete
+ ipv4_plen
+ ipv4_replay
+ ipv4_flush
+ ipv6_add
+ ipv6_metric
+ ipv6_append_single
+ ipv6_replace_single
+ ipv6_metric_multipath
+ ipv6_append_multipath
+ ipv6_replace_multipath
+ ipv6_append_multipath_to_single
+ ipv6_delete_single
+ ipv6_delete_multipath
+ ipv6_replay_single
+ ipv6_replay_multipath
+"
+NUM_NETIFS=0
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+source $lib_dir/fib_offload_lib.sh
+
+ipv4_identical_routes()
+{
+ fib_ipv4_identical_routes_test "testns1"
+}
+
+ipv4_tos()
+{
+ fib_ipv4_tos_test "testns1"
+}
+
+ipv4_metric()
+{
+ fib_ipv4_metric_test "testns1"
+}
+
+ipv4_replace()
+{
+ fib_ipv4_replace_test "testns1"
+}
+
+ipv4_delete()
+{
+ fib_ipv4_delete_test "testns1"
+}
+
+ipv4_plen()
+{
+ fib_ipv4_plen_test "testns1"
+}
+
+ipv4_replay_metric()
+{
+ fib_ipv4_replay_metric_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay_tos()
+{
+ fib_ipv4_replay_tos_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay_plen()
+{
+ fib_ipv4_replay_plen_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay()
+{
+ ipv4_replay_metric
+ ipv4_replay_tos
+ ipv4_replay_plen
+}
+
+ipv4_flush()
+{
+ fib_ipv4_flush_test "testns1"
+}
+
+ipv6_add()
+{
+ fib_ipv6_add_test "testns1"
+}
+
+ipv6_metric()
+{
+ fib_ipv6_metric_test "testns1"
+}
+
+ipv6_append_single()
+{
+ fib_ipv6_append_single_test "testns1"
+}
+
+ipv6_replace_single()
+{
+ fib_ipv6_replace_single_test "testns1"
+}
+
+ipv6_metric_multipath()
+{
+ fib_ipv6_metric_multipath_test "testns1"
+}
+
+ipv6_append_multipath()
+{
+ fib_ipv6_append_multipath_test "testns1"
+}
+
+ipv6_replace_multipath()
+{
+ fib_ipv6_replace_multipath_test "testns1"
+}
+
+ipv6_append_multipath_to_single()
+{
+ fib_ipv6_append_multipath_to_single_test "testns1"
+}
+
+ipv6_delete_single()
+{
+ fib_ipv6_delete_single_test "testns1"
+}
+
+ipv6_delete_multipath()
+{
+ fib_ipv6_delete_multipath_test "testns1"
+}
+
+ipv6_replay_single()
+{
+ fib_ipv6_replay_single_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv6_replay_multipath()
+{
+ fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV"
+}
+
+setup_prepare()
+{
+ ip netns add testns1
+ if [ $? -ne 0 ]; then
+ echo "Failed to add netns \"testns1\""
+ exit 1
+ fi
+
+ devlink dev reload $DEVLINK_DEV netns testns1
+ if [ $? -ne 0 ]; then
+ echo "Failed to reload into netns \"testns1\""
+ exit 1
+ fi
+}
+
+cleanup()
+{
+ pre_cleanup
+ devlink -N testns1 dev reload $DEVLINK_DEV netns $$
+ ip netns del testns1
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib.sh b/tools/testing/selftests/drivers/net/netdevsim/fib.sh
new file mode 100755
index 000000000000..2f87c3be76a9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/fib.sh
@@ -0,0 +1,341 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking the FIB offload API. It makes use of netdevsim
+# which registers a listener to the FIB notification chain.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ ipv4_identical_routes
+ ipv4_tos
+ ipv4_metric
+ ipv4_replace
+ ipv4_delete
+ ipv4_plen
+ ipv4_replay
+ ipv4_flush
+ ipv4_error_path
+ ipv6_add
+ ipv6_metric
+ ipv6_append_single
+ ipv6_replace_single
+ ipv6_metric_multipath
+ ipv6_append_multipath
+ ipv6_replace_multipath
+ ipv6_append_multipath_to_single
+ ipv6_delete_single
+ ipv6_delete_multipath
+ ipv6_replay_single
+ ipv6_replay_multipath
+ ipv6_error_path
+"
+NETDEVSIM_PATH=/sys/bus/netdevsim/
+DEV_ADDR=1337
+DEV=netdevsim${DEV_ADDR}
+DEVLINK_DEV=netdevsim/${DEV}
+SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/
+NUM_NETIFS=0
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+source $lib_dir/fib_offload_lib.sh
+
+ipv4_identical_routes()
+{
+ fib_ipv4_identical_routes_test "testns1"
+}
+
+ipv4_tos()
+{
+ fib_ipv4_tos_test "testns1"
+}
+
+ipv4_metric()
+{
+ fib_ipv4_metric_test "testns1"
+}
+
+ipv4_replace()
+{
+ fib_ipv4_replace_test "testns1"
+}
+
+ipv4_delete()
+{
+ fib_ipv4_delete_test "testns1"
+}
+
+ipv4_plen()
+{
+ fib_ipv4_plen_test "testns1"
+}
+
+ipv4_replay_metric()
+{
+ fib_ipv4_replay_metric_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay_tos()
+{
+ fib_ipv4_replay_tos_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay_plen()
+{
+ fib_ipv4_replay_plen_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv4_replay()
+{
+ ipv4_replay_metric
+ ipv4_replay_tos
+ ipv4_replay_plen
+}
+
+ipv4_flush()
+{
+ fib_ipv4_flush_test "testns1"
+}
+
+ipv4_error_path_add()
+{
+ local lsb
+
+ RET=0
+
+ ip -n testns1 link add name dummy1 type dummy
+ ip -n testns1 link set dev dummy1 up
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 10
+ devlink -N testns1 dev reload $DEVLINK_DEV
+
+ for lsb in $(seq 1 20); do
+ ip -n testns1 route add 192.0.2.${lsb}/32 dev dummy1 \
+ &> /dev/null
+ done
+
+ log_test "IPv4 error path - add"
+
+ ip -n testns1 link del dev dummy1
+}
+
+ipv4_error_path_replay()
+{
+ local lsb
+
+ RET=0
+
+ ip -n testns1 link add name dummy1 type dummy
+ ip -n testns1 link set dev dummy1 up
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 100
+ devlink -N testns1 dev reload $DEVLINK_DEV
+
+ for lsb in $(seq 1 20); do
+ ip -n testns1 route add 192.0.2.${lsb}/32 dev dummy1
+ done
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 10
+ devlink -N testns1 dev reload $DEVLINK_DEV &> /dev/null
+
+ log_test "IPv4 error path - replay"
+
+ ip -n testns1 link del dev dummy1
+
+ # Successfully reload after deleting all the routes.
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 100
+ devlink -N testns1 dev reload $DEVLINK_DEV
+}
+
+ipv4_error_path()
+{
+ # Test the different error paths of the notifiers by limiting the size
+ # of the "IPv4/fib" resource.
+ ipv4_error_path_add
+ ipv4_error_path_replay
+}
+
+ipv6_add()
+{
+ fib_ipv6_add_test "testns1"
+}
+
+ipv6_metric()
+{
+ fib_ipv6_metric_test "testns1"
+}
+
+ipv6_append_single()
+{
+ fib_ipv6_append_single_test "testns1"
+}
+
+ipv6_replace_single()
+{
+ fib_ipv6_replace_single_test "testns1"
+}
+
+ipv6_metric_multipath()
+{
+ fib_ipv6_metric_multipath_test "testns1"
+}
+
+ipv6_append_multipath()
+{
+ fib_ipv6_append_multipath_test "testns1"
+}
+
+ipv6_replace_multipath()
+{
+ fib_ipv6_replace_multipath_test "testns1"
+}
+
+ipv6_append_multipath_to_single()
+{
+ fib_ipv6_append_multipath_to_single_test "testns1"
+}
+
+ipv6_delete_single()
+{
+ fib_ipv6_delete_single_test "testns1"
+}
+
+ipv6_delete_multipath()
+{
+ fib_ipv6_delete_multipath_test "testns1"
+}
+
+ipv6_replay_single()
+{
+ fib_ipv6_replay_single_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv6_replay_multipath()
+{
+ fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV"
+}
+
+ipv6_error_path_add_single()
+{
+ local lsb
+
+ RET=0
+
+ ip -n testns1 link add name dummy1 type dummy
+ ip -n testns1 link set dev dummy1 up
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10
+ devlink -N testns1 dev reload $DEVLINK_DEV
+
+ for lsb in $(seq 1 20); do
+ ip -n testns1 route add 2001:db8:1::${lsb}/128 dev dummy1 \
+ &> /dev/null
+ done
+
+ log_test "IPv6 error path - add single"
+
+ ip -n testns1 link del dev dummy1
+}
+
+ipv6_error_path_add_multipath()
+{
+ local lsb
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n testns1 link add name dummy$i type dummy
+ ip -n testns1 link set dev dummy$i up
+ ip -n testns1 address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10
+ devlink -N testns1 dev reload $DEVLINK_DEV
+
+ for lsb in $(seq 1 20); do
+ ip -n testns1 route add 2001:db8:10::${lsb}/128 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2 &> /dev/null
+ done
+
+ log_test "IPv6 error path - add multipath"
+
+ for i in $(seq 1 2); do
+ ip -n testns1 link del dev dummy$i
+ done
+}
+
+ipv6_error_path_replay()
+{
+ local lsb
+
+ RET=0
+
+ ip -n testns1 link add name dummy1 type dummy
+ ip -n testns1 link set dev dummy1 up
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 100
+ devlink -N testns1 dev reload $DEVLINK_DEV
+
+ for lsb in $(seq 1 20); do
+ ip -n testns1 route add 2001:db8:1::${lsb}/128 dev dummy1
+ done
+
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10
+ devlink -N testns1 dev reload $DEVLINK_DEV &> /dev/null
+
+ log_test "IPv6 error path - replay"
+
+ ip -n testns1 link del dev dummy1
+
+ # Successfully reload after deleting all the routes.
+ devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 100
+ devlink -N testns1 dev reload $DEVLINK_DEV
+}
+
+ipv6_error_path()
+{
+ # Test the different error paths of the notifiers by limiting the size
+ # of the "IPv6/fib" resource.
+ ipv6_error_path_add_single
+ ipv6_error_path_add_multipath
+ ipv6_error_path_replay
+}
+
+setup_prepare()
+{
+ local netdev
+
+ modprobe netdevsim &> /dev/null
+
+ echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device
+ while [ ! -d $SYSFS_NET_DIR ] ; do :; done
+
+ ip netns add testns1
+ if [ $? -ne 0 ]; then
+ echo "Failed to add netns \"testns1\""
+ exit 1
+ fi
+
+ devlink dev reload $DEVLINK_DEV netns testns1
+ if [ $? -ne 0 ]; then
+ echo "Failed to reload into netns \"testns1\""
+ exit 1
+ fi
+}
+
+cleanup()
+{
+ pre_cleanup
+ ip netns del testns1
+ echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device
+ modprobe -r netdevsim &> /dev/null
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh
new file mode 100644
index 000000000000..66496659bea7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh
@@ -0,0 +1,873 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Various helpers and tests to verify FIB offload.
+
+__fib_trap_check()
+{
+ local ns=$1; shift
+ local family=$1; shift
+ local route=$1; shift
+ local should_fail=$1; shift
+ local ret
+
+ ip -n $ns -j -p -$family route show $route \
+ | jq -e '.[]["flags"] | contains(["trap"])' &> /dev/null
+ ret=$?
+ if [[ $should_fail == "true" ]]; then
+ if [[ $ret -ne 0 ]]; then
+ return 0
+ else
+ return 1
+ fi
+ fi
+
+ return $ret
+}
+
+fib_trap_check()
+{
+ local ns=$1; shift
+ local family=$1; shift
+ local route=$1; shift
+ local should_fail=$1; shift
+
+ busywait 5000 __fib_trap_check $ns $family "$route" $should_fail
+}
+
+fib4_trap_check()
+{
+ local ns=$1; shift
+ local route=$1; shift
+ local should_fail=$1; shift
+
+ fib_trap_check $ns 4 "$route" $should_fail
+}
+
+fib6_trap_check()
+{
+ local ns=$1; shift
+ local route=$1; shift
+ local should_fail=$1; shift
+
+ fib_trap_check $ns 6 "$route" $should_fail
+}
+
+fib_ipv4_identical_routes_test()
+{
+ local ns=$1; shift
+ local i
+
+ RET=0
+
+ for i in $(seq 1 3); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ done
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route append 192.0.2.0/24 dev dummy2 tos 0 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy2 tos 0 metric 1024" true
+ check_err $? "Appended route in hardware when should not"
+
+ ip -n $ns route prepend 192.0.2.0/24 dev dummy3 tos 0 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy3 tos 0 metric 1024" false
+ check_err $? "Prepended route not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true
+ check_err $? "Route was not replaced in hardware by prepended one"
+
+ log_test "IPv4 identical routes"
+
+ for i in $(seq 1 3); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv4_tos_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 2 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 2 metric 1024" false
+ check_err $? "Highest TOS route not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true
+ check_err $? "Lowest TOS route still in hardware when should not"
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1 metric 1024" true
+ check_err $? "Middle TOS route in hardware when should not"
+
+ log_test "IPv4 routes with TOS"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_metric_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1022
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1022" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" true
+ check_err $? "Highest metric route still in hardware when should not"
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1023
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1023" true
+ check_err $? "Middle metric route in hardware when should not"
+
+ log_test "IPv4 routes with metric"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_replace_test()
+{
+ local ns=$1; shift
+ local i
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ done
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route replace 192.0.2.0/24 dev dummy2 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1024" false
+ check_err $? "Replacement route not in hardware when should"
+
+ # Add a route with an higher metric and make sure that replacing it
+ # does not affect the lower metric one.
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1025
+ ip -n $ns route replace 192.0.2.0/24 dev dummy2 metric 1025
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1025" true
+ check_err $? "Highest metric route in hardware when should not"
+
+ log_test "IPv4 route replace"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv4_delete_test()
+{
+ local ns=$1; shift
+ local metric
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ # Insert multiple routes with the same prefix and length and varying
+ # metrics. Make sure that throughout delete operations the lowest
+ # metric route is the one in hardware.
+ for metric in $(seq 1024 1026); do
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric $metric
+ done
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route del 192.0.2.0/24 dev dummy1 metric 1024
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ ip -n $ns route del 192.0.2.0/24 dev dummy1 metric 1026
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" false
+ check_err $? "Sole route not in hardware when should"
+
+ log_test "IPv4 route delete"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_plen_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ # Add two routes with the same key and different prefix length and
+ # make sure both are in hardware. It can be verfied that both are
+ # sharing the same leaf by checking the /proc/net/fib_trie
+ ip -n $ns route add 192.0.2.0/24 dev dummy1
+ ip -n $ns route add 192.0.2.0/25 dev dummy1
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1" false
+ check_err $? "/24 not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/25 dev dummy1" false
+ check_err $? "/25 not in hardware when should"
+
+ log_test "IPv4 routes with different prefix length"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_replay_metric_test()
+{
+ local ns=$1; shift
+ local devlink_dev=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1025
+
+ devlink -N $ns dev reload $devlink_dev
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" true
+ check_err $? "Highest metric route in hardware when should not"
+
+ log_test "IPv4 routes replay - metric"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_replay_tos_test()
+{
+ local ns=$1; shift
+ local devlink_dev=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1
+
+ devlink -N $ns dev reload $devlink_dev
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1" false
+ check_err $? "Highest TOS route not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0" true
+ check_err $? "Lowest TOS route in hardware when should not"
+
+ log_test "IPv4 routes replay - TOS"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_replay_plen_test()
+{
+ local ns=$1; shift
+ local devlink_dev=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 192.0.2.0/24 dev dummy1
+ ip -n $ns route add 192.0.2.0/25 dev dummy1
+
+ devlink -N $ns dev reload $devlink_dev
+
+ fib4_trap_check $ns "192.0.2.0/24 dev dummy1" false
+ check_err $? "/24 not in hardware when should"
+
+ fib4_trap_check $ns "192.0.2.0/25 dev dummy1" false
+ check_err $? "/25 not in hardware when should"
+
+ log_test "IPv4 routes replay - prefix length"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv4_flush_test()
+{
+ local ns=$1; shift
+ local metric
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ # Exercise the routes flushing code paths by inserting various
+ # prefix routes on a netdev and then deleting it.
+ for metric in $(seq 1 20); do
+ ip -n $ns route add 192.0.2.0/24 dev dummy1 metric $metric
+ done
+
+ ip -n $ns link del dev dummy1
+
+ log_test "IPv4 routes flushing"
+}
+
+fib_ipv6_add_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ done
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route append 2001:db8:1::/64 dev dummy2 metric 1024
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" true
+ check_err $? "Route in hardware when should not"
+
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware after appending route"
+
+ log_test "IPv6 single route add"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_metric_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ ip -n $ns link add name dummy1 type dummy
+ ip -n $ns link set dev dummy1 up
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1022
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1022" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" true
+ check_err $? "Highest metric route still in hardware when should not"
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1023
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1023" true
+ check_err $? "Middle metric route in hardware when should not"
+
+ log_test "IPv6 routes with metric"
+
+ ip -n $ns link del dev dummy1
+}
+
+fib_ipv6_append_single_test()
+{
+ local ns=$1; shift
+
+ # When an IPv6 multipath route is added without the 'nexthop' keyword,
+ # different code paths are taken compared to when the keyword is used.
+ # This test tries to verify the former.
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 via 2001:db8:1::2 metric 1024
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route append 2001:db8:10::/64 via 2001:db8:2::2 metric 1024
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware after appending"
+
+ ip -n $ns route add 2001:db8:10::/64 via 2001:db8:1::2 metric 1025
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Route in hardware when should not"
+
+ ip -n $ns route append 2001:db8:10::/64 via 2001:db8:2::2 metric 1025
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Route in hardware when should not after appending"
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ log_test "IPv6 append single route without 'nexthop' keyword"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_replace_single_test()
+{
+ local ns=$1; shift
+ local i
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ done
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route replace 2001:db8:1::/64 dev dummy2 metric 1024
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" false
+ check_err $? "Replacement route not in hardware when should"
+
+ # Add a route with an higher metric and make sure that replacing it
+ # does not affect the lower metric one.
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1025
+ ip -n $ns route replace 2001:db8:1::/64 dev dummy2 metric 1025
+
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1025" true
+ check_err $? "Highest metric route in hardware when should not"
+
+ log_test "IPv6 single route replace"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_metric_multipath_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1022 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1022" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1023 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" true
+ check_err $? "Highest metric route still in hardware when should not"
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1023" true
+ check_err $? "Middle metric route in hardware when should not"
+
+ log_test "IPv6 multipath routes with metric"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_append_multipath_test()
+{
+ local ns=$1; shift
+
+ RET=0
+
+ for i in $(seq 1 3); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route append 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:2::2 dev dummy2 \
+ nexthop via 2001:db8:3::2 dev dummy3
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware after appending"
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Route in hardware when should not"
+
+ ip -n $ns route append 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:2::2 dev dummy2 \
+ nexthop via 2001:db8:3::2 dev dummy3
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Route in hardware when should not after appending"
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+
+ log_test "IPv6 append multipath route with 'nexthop' keyword"
+
+ for i in $(seq 1 3); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_replace_multipath_test()
+{
+ local ns=$1; shift
+ local i
+
+ RET=0
+
+ for i in $(seq 1 3); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route replace 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:3::2 dev dummy3
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Replacement route not in hardware when should"
+
+ # Add a route with an higher metric and make sure that replacing it
+ # does not affect the lower metric one.
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route replace 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:3::2 dev dummy3
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Lowest metric route not in hardware when should"
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Highest metric route in hardware when should not"
+
+ log_test "IPv6 multipath route replace"
+
+ for i in $(seq 1 3); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_append_multipath_to_single_test()
+{
+ local ns=$1; shift
+
+ # Test that when the first route in the leaf is not a multipath route
+ # and we try to append a multipath route with the same metric to it, it
+ # is not notified.
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware when should"
+
+ ip -n $ns route append 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy2 metric 1024" true
+ check_err $? "Route in hardware when should not"
+
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware after append"
+
+ log_test "IPv6 append multipath route to non-multipath route"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_delete_single_test()
+{
+ local ns=$1; shift
+
+ # Test various deletion scenarios, where only a single route is
+ # deleted from the FIB node.
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ # Test deletion of a single route when it is the only route in the FIB
+ # node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024
+
+ log_test "IPv6 delete sole single route"
+
+ # Test that deletion of last route does not affect the first one.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025
+
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false
+ check_err $? "Route not in hardware after deleting higher metric route"
+
+ log_test "IPv6 delete single route not in hardware"
+
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024
+
+ # Test that first route is replaced by next single route in the FIB
+ # node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024
+
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1025" false
+ check_err $? "Route not in hardware after deleting lowest metric route"
+
+ log_test "IPv6 delete single route - replaced by single"
+
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025
+
+ # Test that first route is replaced by next multipath route in the FIB
+ # node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" false
+ check_err $? "Route not in hardware after deleting lowest metric route"
+
+ log_test "IPv6 delete single route - replaced by multipath"
+
+ ip -n $ns route del 2001:db8:10::/64 metric 1025
+
+ # Test deletion of a single nexthop from a multipath route.
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route del 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware after deleting a single nexthop"
+
+ log_test "IPv6 delete single nexthop"
+
+ ip -n $ns route del 2001:db8:10::/64 metric 1024
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_delete_multipath_test()
+{
+ local ns=$1; shift
+
+ # Test various deletion scenarios, where an entire multipath route is
+ # deleted from the FIB node.
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ # Test deletion of a multipath route when it is the only route in the
+ # FIB node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route del 2001:db8:10::/64 metric 1024
+
+ log_test "IPv6 delete sole multipath route"
+
+ # Test that deletion of last route does not affect the first one.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route del 2001:db8:10::/64 metric 1025
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "Route not in hardware after deleting higher metric route"
+
+ log_test "IPv6 delete multipath route not in hardware"
+
+ ip -n $ns route del 2001:db8:10::/64 metric 1024
+
+ # Test that first route is replaced by next single route in the FIB
+ # node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025
+ ip -n $ns route del 2001:db8:10::/64 metric 1024
+
+ fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1025" false
+ check_err $? "Route not in hardware after deleting lowest metric route"
+
+ log_test "IPv6 delete multipath route - replaced by single"
+
+ ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025
+
+ # Test that first route is replaced by next multipath route in the FIB
+ # node.
+ RET=0
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route del 2001:db8:10::/64 metric 1024
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" false
+ check_err $? "Route not in hardware after deleting lowest metric route"
+
+ log_test "IPv6 delete multipath route - replaced by multipath"
+
+ ip -n $ns route del 2001:db8:10::/64 metric 1025
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_replay_single_test()
+{
+ local ns=$1; shift
+ local devlink_dev=$1; shift
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ done
+
+ ip -n $ns route add 2001:db8:1::/64 dev dummy1
+ ip -n $ns route append 2001:db8:1::/64 dev dummy2
+
+ devlink -N $ns dev reload $devlink_dev
+
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy1" false
+ check_err $? "First route not in hardware when should"
+
+ fib6_trap_check $ns "2001:db8:1::/64 dev dummy2" true
+ check_err $? "Second route in hardware when should not"
+
+ log_test "IPv6 routes replay - single route"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
+
+fib_ipv6_replay_multipath_test()
+{
+ local ns=$1; shift
+ local devlink_dev=$1; shift
+
+ RET=0
+
+ for i in $(seq 1 2); do
+ ip -n $ns link add name dummy$i type dummy
+ ip -n $ns link set dev dummy$i up
+ ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i
+ done
+
+ ip -n $ns route add 2001:db8:10::/64 metric 1024 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+ ip -n $ns route add 2001:db8:10::/64 metric 1025 \
+ nexthop via 2001:db8:1::2 dev dummy1 \
+ nexthop via 2001:db8:2::2 dev dummy2
+
+ devlink -N $ns dev reload $devlink_dev
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false
+ check_err $? "First route not in hardware when should"
+
+ fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true
+ check_err $? "Second route in hardware when should not"
+
+ log_test "IPv6 routes replay - multipath route"
+
+ for i in $(seq 1 2); do
+ ip -n $ns link del dev dummy$i
+ done
+}
View Lorry Controller Status