* [patch net-next v2 14/21] mlxsw: spectrum_router: Make nexthops typed
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
In the router, some next hops may reference an encapsulating netdevice,
such as GRE or IPIP. To properly offload these next hops, mlxsw needs to
keep track of whether a given next hop is a regular Ethernet entry, or
an IP-in-IP tunneling entry.
To facilitate this book-keeping, add a type field to struct
mlxsw_sp_nexthop. There is, as of this patch, only one next hop type:
MLXSW_SP_NEXTHOP_TYPE_ETH. Follow-up patches will introduce the IP-in-IP
variant.
There are several places where next hops are initialized in the IPv4
path. Instead of replicating the logic at every one of them, factor it
out to a function mlxsw_sp_nexthop4_type_init(). The corresponding fini
is actually protocol-neutral, so put it to mlxsw_sp_nexthop_type_fini(),
but create a corresponding protocoled _fini function that dispatches to
the protocol-neutral one.
The IPv6 path is simpler, but for symmetry with IPv4, create the same
suite of functions with corresponding logic.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
.../net/ethernet/mellanox/mlxsw/spectrum_router.c | 138 ++++++++++++++-------
1 file changed, 95 insertions(+), 43 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 563e803..53bdd0f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1652,6 +1652,10 @@ static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
}
}
+enum mlxsw_sp_nexthop_type {
+ MLXSW_SP_NEXTHOP_TYPE_ETH,
+};
+
struct mlxsw_sp_nexthop_key {
struct fib_nh *fib_nh;
};
@@ -1676,7 +1680,10 @@ struct mlxsw_sp_nexthop {
update:1; /* set indicates that MAC of this neigh should be
* updated in HW
*/
- struct mlxsw_sp_neigh_entry *neigh_entry;
+ enum mlxsw_sp_nexthop_type type;
+ union {
+ struct mlxsw_sp_neigh_entry *neigh_entry;
+ };
};
struct mlxsw_sp_nexthop_group {
@@ -1964,9 +1971,9 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
}
static int
-mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop_group *nh_grp,
- bool reallocate)
+mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp,
+ bool reallocate)
{
u32 adj_index = nh_grp->adj_index; /* base */
struct mlxsw_sp_nexthop *nh;
@@ -1982,8 +1989,12 @@ mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp,
}
if (nh->update || reallocate) {
- err = mlxsw_sp_nexthop_mac_update(mlxsw_sp,
- adj_index, nh);
+ switch (nh->type) {
+ case MLXSW_SP_NEXTHOP_TYPE_ETH:
+ err = mlxsw_sp_nexthop_mac_update
+ (mlxsw_sp, adj_index, nh);
+ break;
+ }
if (err)
return err;
nh->update = 0;
@@ -2071,8 +2082,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
/* Nothing was added or removed, so no need to reallocate. Just
* update MAC on existing adjacency indexes.
*/
- err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp,
- false);
+ err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nh_grp, false);
if (err) {
dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
goto set_trap;
@@ -2099,7 +2109,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
nh_grp->adj_index_valid = 1;
nh_grp->adj_index = adj_index;
nh_grp->ecmp_size = ecmp_size;
- err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, true);
+ err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nh_grp, true);
if (err) {
dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
goto set_trap;
@@ -2287,6 +2297,48 @@ static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp,
return false;
}
+static void mlxsw_sp_nexthop_type_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh)
+{
+ switch (nh->type) {
+ case MLXSW_SP_NEXTHOP_TYPE_ETH:
+ mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
+ mlxsw_sp_nexthop_rif_fini(nh);
+ break;
+ }
+}
+
+static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh,
+ struct fib_nh *fib_nh)
+{
+ struct net_device *dev = fib_nh->nh_dev;
+ struct mlxsw_sp_rif *rif;
+ int err;
+
+ nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH;
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+ if (!rif)
+ return 0;
+
+ mlxsw_sp_nexthop_rif_init(nh, rif);
+ err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
+ if (err)
+ goto err_neigh_init;
+
+ return 0;
+
+err_neigh_init:
+ mlxsw_sp_nexthop_rif_fini(nh);
+ return err;
+}
+
+static void mlxsw_sp_nexthop4_type_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh)
+{
+ mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh);
+}
+
static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp,
struct mlxsw_sp_nexthop *nh,
@@ -2294,7 +2346,6 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
{
struct net_device *dev = fib_nh->nh_dev;
struct in_device *in_dev;
- struct mlxsw_sp_rif *rif;
int err;
nh->nh_grp = nh_grp;
@@ -2312,19 +2363,13 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
fib_nh->nh_flags & RTNH_F_LINKDOWN)
return 0;
- rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
- if (!rif)
- return 0;
- mlxsw_sp_nexthop_rif_init(nh, rif);
-
- err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
+ err = mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh);
if (err)
goto err_nexthop_neigh_init;
return 0;
err_nexthop_neigh_init:
- mlxsw_sp_nexthop_rif_fini(nh);
mlxsw_sp_nexthop_remove(mlxsw_sp, nh);
return err;
}
@@ -2332,8 +2377,7 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
static void mlxsw_sp_nexthop4_fini(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop *nh)
{
- mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
- mlxsw_sp_nexthop_rif_fini(nh);
+ mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh);
mlxsw_sp_nexthop_remove(mlxsw_sp, nh);
}
@@ -2342,7 +2386,6 @@ static void mlxsw_sp_nexthop4_event(struct mlxsw_sp *mlxsw_sp,
{
struct mlxsw_sp_nexthop_key key;
struct mlxsw_sp_nexthop *nh;
- struct mlxsw_sp_rif *rif;
if (mlxsw_sp->router->aborted)
return;
@@ -2352,18 +2395,12 @@ static void mlxsw_sp_nexthop4_event(struct mlxsw_sp *mlxsw_sp,
if (WARN_ON_ONCE(!nh))
return;
- rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev);
- if (!rif)
- return;
-
switch (event) {
case FIB_EVENT_NH_ADD:
- mlxsw_sp_nexthop_rif_init(nh, rif);
- mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
+ mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh);
break;
case FIB_EVENT_NH_DEL:
- mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
- mlxsw_sp_nexthop_rif_fini(nh);
+ mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh);
break;
}
@@ -2376,8 +2413,7 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop *nh, *tmp;
list_for_each_entry_safe(nh, tmp, &rif->nexthop_list, rif_list_node) {
- mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
- mlxsw_sp_nexthop_rif_fini(nh);
+ mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh);
mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
}
}
@@ -3487,22 +3523,16 @@ mlxsw_sp_fib6_entry_rt_find(const struct mlxsw_sp_fib6_entry *fib6_entry,
return NULL;
}
-static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_nexthop_group *nh_grp,
- struct mlxsw_sp_nexthop *nh,
- const struct rt6_info *rt)
+static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp,
+ struct mlxsw_sp_nexthop *nh,
+ const struct rt6_info *rt)
{
struct net_device *dev = rt->dst.dev;
struct mlxsw_sp_rif *rif;
int err;
- nh->nh_grp = nh_grp;
- memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr));
-
- if (!dev)
- return 0;
- nh->ifindex = dev->ifindex;
-
+ nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH;
rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
if (!rif)
return 0;
@@ -3519,11 +3549,33 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
return err;
}
+static void mlxsw_sp_nexthop6_type_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop *nh)
+{
+ mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh);
+}
+
+static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_nexthop_group *nh_grp,
+ struct mlxsw_sp_nexthop *nh,
+ const struct rt6_info *rt)
+{
+ struct net_device *dev = rt->dst.dev;
+
+ nh->nh_grp = nh_grp;
+ memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr));
+
+ if (!dev)
+ return 0;
+ nh->ifindex = dev->ifindex;
+
+ return mlxsw_sp_nexthop6_type_init(mlxsw_sp, nh_grp, nh, rt);
+}
+
static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop *nh)
{
- mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
- mlxsw_sp_nexthop_rif_fini(nh);
+ mlxsw_sp_nexthop6_type_fini(mlxsw_sp, nh);
}
static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp,
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 13/21] mlxsw: spectrum_router: Extract mlxsw_sp_rt6_is_gateway()
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
IPv6 counterpart of the previous patch: introduce a function to
determine whether a given route is a gateway route.
The new function takes a mlxsw_sp argument which follow-up patches will
use. Thus mlxsw_sp_fib6_entry_type_set() got that argument as well.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 15 +++++++++++----
1 file changed, 11 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 04e1887..563e803 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3526,6 +3526,12 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
mlxsw_sp_nexthop_rif_fini(nh);
}
+static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp,
+ const struct rt6_info *rt)
+{
+ return rt->rt6i_flags & RTF_GATEWAY;
+}
+
static struct mlxsw_sp_nexthop_group *
mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib6_entry *fib6_entry)
@@ -3548,7 +3554,7 @@ mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp,
#endif
mlxsw_sp_rt6 = list_first_entry(&fib6_entry->rt6_list,
struct mlxsw_sp_rt6, list);
- nh_grp->gateway = !!(mlxsw_sp_rt6->rt->rt6i_flags & RTF_GATEWAY);
+ nh_grp->gateway = mlxsw_sp_rt6_is_gateway(mlxsw_sp, mlxsw_sp_rt6->rt);
nh_grp->count = fib6_entry->nrt6;
for (i = 0; i < nh_grp->count; i++) {
struct rt6_info *rt = mlxsw_sp_rt6->rt;
@@ -3705,7 +3711,8 @@ mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp,
mlxsw_sp_rt6_destroy(mlxsw_sp_rt6);
}
-static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp_fib_entry *fib_entry,
+static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry,
const struct rt6_info *rt)
{
/* Packets hitting RTF_REJECT routes need to be discarded by the
@@ -3718,7 +3725,7 @@ static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp_fib_entry *fib_entry,
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
else if (rt->rt6i_flags & RTF_REJECT)
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
- else if (rt->rt6i_flags & RTF_GATEWAY)
+ else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt))
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
else
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
@@ -3758,7 +3765,7 @@ mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp,
goto err_rt6_create;
}
- mlxsw_sp_fib6_entry_type_set(fib_entry, mlxsw_sp_rt6->rt);
+ mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, mlxsw_sp_rt6->rt);
INIT_LIST_HEAD(&fib6_entry->rt6_list);
list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list);
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 12/21] mlxsw: spectrum_router: Extract mlxsw_sp_fi_is_gateway()
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
For IPv4 IP-in-IP offload, routes that direct traffic to IP-in-IP
devices need to be considered gateway routes as well. That involves a
bit more logic, so extract the current test to a separate function,
where the logic can be later added.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 72e386b..04e1887 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2382,6 +2382,12 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
}
}
+static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp,
+ const struct fib_info *fi)
+{
+ return fi->fib_nh->nh_scope == RT_SCOPE_LINK;
+}
+
static struct mlxsw_sp_nexthop_group *
mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
{
@@ -2401,7 +2407,7 @@ mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
INIT_LIST_HEAD(&nh_grp->fib_list);
nh_grp->neigh_tbl = &arp_tbl;
- nh_grp->gateway = fi->fib_nh->nh_scope == RT_SCOPE_LINK;
+ nh_grp->gateway = mlxsw_sp_fi_is_gateway(mlxsw_sp, fi);
nh_grp->count = fi->fib_nhs;
fib_info_hold(fi);
for (i = 0; i < nh_grp->count; i++) {
@@ -2801,10 +2807,10 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp,
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
return 0;
case RTN_UNICAST:
- if (fi->fib_nh->nh_scope != RT_SCOPE_LINK)
- fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
- else
+ if (mlxsw_sp_fi_is_gateway(mlxsw_sp, fi))
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
+ else
+ fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
return 0;
default:
return -EINVAL;
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 11/21] mlxsw: spectrum_router: Introduce loopback RIFs
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
When offloading L3 tunnels, an adjacency entry is created that loops the
packet back into the underlay router. Loopback interfaces then hold the
corresponding information and are created for IP-in-IP netdevices.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 1 +
.../net/ethernet/mellanox/mlxsw/spectrum_router.c | 152 ++++++++++++++++++++-
.../net/ethernet/mellanox/mlxsw/spectrum_router.h | 13 ++
3 files changed, 164 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index f8c7f7e..84ce83a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -77,6 +77,7 @@ enum mlxsw_sp_rif_type {
MLXSW_SP_RIF_TYPE_SUBPORT,
MLXSW_SP_RIF_TYPE_VLAN,
MLXSW_SP_RIF_TYPE_FID,
+ MLXSW_SP_RIF_TYPE_IPIP_LB, /* IP-in-IP loopback. */
MLXSW_SP_RIF_TYPE_MAX,
};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 38477c5..72e386b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1,9 +1,10 @@
/*
* drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016-2017 Mellanox Technologies. All rights reserved.
* Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
* Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com>
* Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com>
+ * Copyright (c) 2017 Petr Machata <petrm@mellanox.com>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
@@ -51,6 +52,7 @@
#include <net/ip_fib.h>
#include <net/ip6_fib.h>
#include <net/fib_rules.h>
+#include <net/ip_tunnels.h>
#include <net/l3mdev.h>
#include <net/addrconf.h>
#include <net/ndisc.h>
@@ -131,6 +133,17 @@ struct mlxsw_sp_rif_subport {
bool lag;
};
+struct mlxsw_sp_rif_ipip_lb {
+ struct mlxsw_sp_rif common;
+ struct mlxsw_sp_rif_ipip_lb_config lb_config;
+ u16 ul_vr_id; /* Reserved for Spectrum-2. */
+};
+
+struct mlxsw_sp_rif_params_ipip_lb {
+ struct mlxsw_sp_rif_params common;
+ struct mlxsw_sp_rif_ipip_lb_config lb_config;
+};
+
struct mlxsw_sp_rif_ops {
enum mlxsw_sp_rif_type type;
size_t rif_size;
@@ -883,6 +896,25 @@ static void mlxsw_sp_vrs_fini(struct mlxsw_sp *mlxsw_sp)
kfree(mlxsw_sp->router->vrs);
}
+static struct net_device *
+__mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev)
+{
+ struct ip_tunnel *tun = netdev_priv(ol_dev);
+ struct net *net = dev_net(ol_dev);
+
+ return __dev_get_by_index(net, tun->parms.link);
+}
+
+static u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev)
+{
+ struct net_device *d = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev);
+
+ if (d)
+ return l3mdev_fib_table(d) ? : RT_TABLE_MAIN;
+ else
+ return l3mdev_fib_table(ol_dev) ? : RT_TABLE_MAIN;
+}
+
struct mlxsw_sp_neigh_key {
struct neighbour *n;
};
@@ -2236,6 +2268,25 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp,
neigh_release(n);
}
+static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp,
+ const struct net_device *dev,
+ enum mlxsw_sp_ipip_type *p_type)
+{
+ struct mlxsw_sp_router *router = mlxsw_sp->router;
+ const struct mlxsw_sp_ipip_ops *ipip_ops;
+ enum mlxsw_sp_ipip_type ipipt;
+
+ for (ipipt = 0; ipipt < MLXSW_SP_IPIP_TYPE_MAX; ++ipipt) {
+ ipip_ops = router->ipip_ops_arr[ipipt];
+ if (dev->type == ipip_ops->dev_type) {
+ if (p_type)
+ *p_type = ipipt;
+ return true;
+ }
+ }
+ return false;
+}
+
static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp,
struct mlxsw_sp_nexthop *nh,
@@ -4374,7 +4425,10 @@ mlxsw_sp_dev_rif_type(const struct mlxsw_sp *mlxsw_sp,
{
enum mlxsw_sp_fid_type type;
- /* RIF type is derived from the type of the underlying FID */
+ if (mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, NULL))
+ return MLXSW_SP_RIF_TYPE_IPIP_LB;
+
+ /* Otherwise RIF type is derived from the type of the underlying FID. */
if (is_vlan_dev(dev) && netif_is_bridge_master(vlan_dev_real_dev(dev)))
type = MLXSW_SP_FID_TYPE_8021Q;
else if (netif_is_bridge_master(dev) && br_vlan_enabled(dev))
@@ -5164,10 +5218,104 @@ static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = {
.fid_get = mlxsw_sp_rif_fid_fid_get,
};
+static struct mlxsw_sp_rif_ipip_lb *
+mlxsw_sp_rif_ipip_lb_rif(struct mlxsw_sp_rif *rif)
+{
+ return container_of(rif, struct mlxsw_sp_rif_ipip_lb, common);
+}
+
+static void
+mlxsw_sp_rif_ipip_lb_setup(struct mlxsw_sp_rif *rif,
+ const struct mlxsw_sp_rif_params *params)
+{
+ struct mlxsw_sp_rif_params_ipip_lb *params_lb;
+ struct mlxsw_sp_rif_ipip_lb *rif_lb;
+
+ params_lb = container_of(params, struct mlxsw_sp_rif_params_ipip_lb,
+ common);
+ rif_lb = mlxsw_sp_rif_ipip_lb_rif(rif);
+ rif_lb->lb_config = params_lb->lb_config;
+}
+
+static int
+mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif,
+ struct mlxsw_sp_vr *ul_vr, bool enable)
+{
+ struct mlxsw_sp_rif_ipip_lb_config lb_cf = lb_rif->lb_config;
+ struct mlxsw_sp_rif *rif = &lb_rif->common;
+ struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
+ char ritr_pl[MLXSW_REG_RITR_LEN];
+ u32 saddr4;
+
+ switch (lb_cf.ul_protocol) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ saddr4 = be32_to_cpu(lb_cf.saddr.addr4);
+ mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF,
+ rif->rif_index, rif->vr_id, rif->dev->mtu);
+ mlxsw_reg_ritr_loopback_ipip4_pack(ritr_pl, lb_cf.lb_ipipt,
+ MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET,
+ ul_vr->id, saddr4, lb_cf.okey);
+ break;
+
+ case MLXSW_SP_L3_PROTO_IPV6:
+ return -EAFNOSUPPORT;
+ }
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static int
+mlxsw_sp_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
+{
+ struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif);
+ u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(rif->dev);
+ struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
+ struct mlxsw_sp_vr *ul_vr;
+ int err;
+
+ ul_vr = mlxsw_sp_vr_get(mlxsw_sp, ul_tb_id);
+ if (IS_ERR(ul_vr))
+ return PTR_ERR(ul_vr);
+
+ err = mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, true);
+ if (err)
+ goto err_loopback_op;
+
+ lb_rif->ul_vr_id = ul_vr->id;
+ ++ul_vr->rif_count;
+ return 0;
+
+err_loopback_op:
+ mlxsw_sp_vr_put(ul_vr);
+ return err;
+}
+
+static void mlxsw_sp_rif_ipip_lb_deconfigure(struct mlxsw_sp_rif *rif)
+{
+ struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif);
+ struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
+ struct mlxsw_sp_vr *ul_vr;
+
+ ul_vr = &mlxsw_sp->router->vrs[lb_rif->ul_vr_id];
+ mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, false);
+
+ --ul_vr->rif_count;
+ mlxsw_sp_vr_put(ul_vr);
+}
+
+static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_ipip_lb_ops = {
+ .type = MLXSW_SP_RIF_TYPE_IPIP_LB,
+ .rif_size = sizeof(struct mlxsw_sp_rif_ipip_lb),
+ .setup = mlxsw_sp_rif_ipip_lb_setup,
+ .configure = mlxsw_sp_rif_ipip_lb_configure,
+ .deconfigure = mlxsw_sp_rif_ipip_lb_deconfigure,
+};
+
static const struct mlxsw_sp_rif_ops *mlxsw_sp_rif_ops_arr[] = {
[MLXSW_SP_RIF_TYPE_SUBPORT] = &mlxsw_sp_rif_subport_ops,
[MLXSW_SP_RIF_TYPE_VLAN] = &mlxsw_sp_rif_vlan_ops,
[MLXSW_SP_RIF_TYPE_FID] = &mlxsw_sp_rif_fid_ops,
+ [MLXSW_SP_RIF_TYPE_IPIP_LB] = &mlxsw_sp_rif_ipip_lb_ops,
};
static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 67c6c1d..a5732aa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -36,12 +36,25 @@
#define _MLXSW_ROUTER_H_
#include "spectrum.h"
+#include "reg.h"
enum mlxsw_sp_l3proto {
MLXSW_SP_L3_PROTO_IPV4,
MLXSW_SP_L3_PROTO_IPV6,
};
+union mlxsw_sp_l3addr {
+ __be32 addr4;
+ struct in6_addr addr6;
+};
+
+struct mlxsw_sp_rif_ipip_lb_config {
+ enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt;
+ u32 okey;
+ enum mlxsw_sp_l3proto ul_protocol; /* Underlay. */
+ union mlxsw_sp_l3addr saddr;
+};
+
enum mlxsw_sp_rif_counter_dir {
MLXSW_SP_RIF_COUNTER_INGRESS,
MLXSW_SP_RIF_COUNTER_EGRESS,
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 10/21] mlxsw: spectrum_router: Support FID-less RIFs
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
Loopback RIFs, which will be introduced in a follow-up patch, differ
from other RIFs in that they do not have a FID associated with them.
To support this, demote FID allocation from mlxsw_sp_rif_create to
configure op of the existing RIF types, and likewise the FID release
from mlxsw_sp_rif_destroy to deconfigure op.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
.../net/ethernet/mellanox/mlxsw/spectrum_router.c | 85 ++++++++++++++++------
1 file changed, 63 insertions(+), 22 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index f85d249..38477c5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4444,9 +4444,9 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
{
u32 tb_id = l3mdev_fib_table(params->dev);
const struct mlxsw_sp_rif_ops *ops;
+ struct mlxsw_sp_fid *fid = NULL;
enum mlxsw_sp_rif_type type;
struct mlxsw_sp_rif *rif;
- struct mlxsw_sp_fid *fid;
struct mlxsw_sp_vr *vr;
u16 rif_index;
int err;
@@ -4470,12 +4470,14 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
rif->mlxsw_sp = mlxsw_sp;
rif->ops = ops;
- fid = ops->fid_get(rif);
- if (IS_ERR(fid)) {
- err = PTR_ERR(fid);
- goto err_fid_get;
+ if (ops->fid_get) {
+ fid = ops->fid_get(rif);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ goto err_fid_get;
+ }
+ rif->fid = fid;
}
- rif->fid = fid;
if (ops->setup)
ops->setup(rif, params);
@@ -4484,22 +4486,15 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
if (err)
goto err_configure;
- err = mlxsw_sp_rif_fdb_op(mlxsw_sp, params->dev->dev_addr,
- mlxsw_sp_fid_index(fid), true);
- if (err)
- goto err_rif_fdb_op;
-
mlxsw_sp_rif_counters_alloc(rif);
- mlxsw_sp_fid_rif_set(fid, rif);
mlxsw_sp->router->rifs[rif_index] = rif;
vr->rif_count++;
return rif;
-err_rif_fdb_op:
- ops->deconfigure(rif);
err_configure:
- mlxsw_sp_fid_put(fid);
+ if (fid)
+ mlxsw_sp_fid_put(fid);
err_fid_get:
kfree(rif);
err_rif_alloc:
@@ -4520,12 +4515,11 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
vr->rif_count--;
mlxsw_sp->router->rifs[rif->rif_index] = NULL;
- mlxsw_sp_fid_rif_set(fid, NULL);
mlxsw_sp_rif_counters_free(rif);
- mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->dev->dev_addr,
- mlxsw_sp_fid_index(fid), false);
ops->deconfigure(rif);
- mlxsw_sp_fid_put(fid);
+ if (fid)
+ /* Loopback RIFs are not associated with a FID. */
+ mlxsw_sp_fid_put(fid);
kfree(rif);
mlxsw_sp_vr_put(vr);
}
@@ -4965,11 +4959,32 @@ static int mlxsw_sp_rif_subport_op(struct mlxsw_sp_rif *rif, bool enable)
static int mlxsw_sp_rif_subport_configure(struct mlxsw_sp_rif *rif)
{
- return mlxsw_sp_rif_subport_op(rif, true);
+ int err;
+
+ err = mlxsw_sp_rif_subport_op(rif, true);
+ if (err)
+ return err;
+
+ err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
+ mlxsw_sp_fid_index(rif->fid), true);
+ if (err)
+ goto err_rif_fdb_op;
+
+ mlxsw_sp_fid_rif_set(rif->fid, rif);
+ return 0;
+
+err_rif_fdb_op:
+ mlxsw_sp_rif_subport_op(rif, false);
+ return err;
}
static void mlxsw_sp_rif_subport_deconfigure(struct mlxsw_sp_rif *rif)
{
+ struct mlxsw_sp_fid *fid = rif->fid;
+
+ mlxsw_sp_fid_rif_set(fid, NULL);
+ mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
+ mlxsw_sp_fid_index(fid), false);
mlxsw_sp_rif_subport_op(rif, false);
}
@@ -5028,8 +5043,17 @@ static int mlxsw_sp_rif_vlan_configure(struct mlxsw_sp_rif *rif)
if (err)
goto err_fid_bc_flood_set;
+ err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
+ mlxsw_sp_fid_index(rif->fid), true);
+ if (err)
+ goto err_rif_fdb_op;
+
+ mlxsw_sp_fid_rif_set(rif->fid, rif);
return 0;
+err_rif_fdb_op:
+ mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
+ mlxsw_sp_router_port(mlxsw_sp), false);
err_fid_bc_flood_set:
mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC,
mlxsw_sp_router_port(mlxsw_sp), false);
@@ -5040,9 +5064,13 @@ static int mlxsw_sp_rif_vlan_configure(struct mlxsw_sp_rif *rif)
static void mlxsw_sp_rif_vlan_deconfigure(struct mlxsw_sp_rif *rif)
{
- struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
u16 vid = mlxsw_sp_fid_8021q_vid(rif->fid);
+ struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
+ struct mlxsw_sp_fid *fid = rif->fid;
+ mlxsw_sp_fid_rif_set(fid, NULL);
+ mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
+ mlxsw_sp_fid_index(fid), false);
mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
mlxsw_sp_router_port(mlxsw_sp), false);
mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC,
@@ -5087,8 +5115,17 @@ static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif)
if (err)
goto err_fid_bc_flood_set;
+ err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
+ mlxsw_sp_fid_index(rif->fid), true);
+ if (err)
+ goto err_rif_fdb_op;
+
+ mlxsw_sp_fid_rif_set(rif->fid, rif);
return 0;
+err_rif_fdb_op:
+ mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
+ mlxsw_sp_router_port(mlxsw_sp), false);
err_fid_bc_flood_set:
mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC,
mlxsw_sp_router_port(mlxsw_sp), false);
@@ -5099,9 +5136,13 @@ static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif)
static void mlxsw_sp_rif_fid_deconfigure(struct mlxsw_sp_rif *rif)
{
- struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
u16 fid_index = mlxsw_sp_fid_index(rif->fid);
+ struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
+ struct mlxsw_sp_fid *fid = rif->fid;
+ mlxsw_sp_fid_rif_set(fid, NULL);
+ mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
+ mlxsw_sp_fid_index(fid), false);
mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
mlxsw_sp_router_port(mlxsw_sp), false);
mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC,
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 09/21] mlxsw: spectrum_router: Add mlxsw_sp_ipip_ops
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
Details of individual tunnel types are kept in an array of
mlxsw_sp_ipip_ops objects. Follow-up patches will use the list to
determine whether a constructed RIF should be a loopback, and to decide
whether a next hop references a tunnel.
The list is currently empty, follow-up patches will add support for GRE.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/Makefile | 4 +-
.../net/ethernet/mellanox/mlxsw/spectrum_ipip.c | 38 ++++++++++++++++
.../net/ethernet/mellanox/mlxsw/spectrum_ipip.h | 51 ++++++++++++++++++++++
.../net/ethernet/mellanox/mlxsw/spectrum_router.c | 19 ++++++++
4 files changed, 110 insertions(+), 2 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index f9956f3..891ff41 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -16,8 +16,8 @@ mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \
spectrum_switchdev.o spectrum_router.o \
spectrum_kvdl.o spectrum_acl_tcam.o \
spectrum_acl.o spectrum_flower.o \
- spectrum_cnt.o \
- spectrum_fid.o
+ spectrum_cnt.o spectrum_fid.o \
+ spectrum_ipip.o
mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o
mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o
obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
new file mode 100644
index 0000000..20b0b96
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -0,0 +1,38 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Petr Machata <petrm@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "spectrum_ipip.h"
+
+const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[] = {
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
new file mode 100644
index 0000000..65eb493
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
@@ -0,0 +1,51 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Petr Machata <petrm@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_IPIP_H_
+#define _MLXSW_IPIP_H_
+
+#include "spectrum_router.h"
+
+enum mlxsw_sp_ipip_type {
+ MLXSW_SP_IPIP_TYPE_MAX,
+};
+
+struct mlxsw_sp_ipip_ops {
+ int dev_type;
+ enum mlxsw_sp_l3proto ul_proto; /* Underlay. */
+};
+
+extern const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[];
+
+#endif /* _MLXSW_IPIP_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index f866ac5..f85d249 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -62,6 +62,7 @@
#include "reg.h"
#include "spectrum_cnt.h"
#include "spectrum_dpipe.h"
+#include "spectrum_ipip.h"
#include "spectrum_router.h"
struct mlxsw_sp_vr;
@@ -89,6 +90,7 @@ struct mlxsw_sp_router {
bool aborted;
struct notifier_block fib_nb;
const struct mlxsw_sp_rif_ops **rif_ops_arr;
+ const struct mlxsw_sp_ipip_ops **ipip_ops_arr;
};
struct mlxsw_sp_rif {
@@ -5152,6 +5154,16 @@ static void mlxsw_sp_rifs_fini(struct mlxsw_sp *mlxsw_sp)
kfree(mlxsw_sp->router->rifs);
}
+static int mlxsw_sp_ipips_init(struct mlxsw_sp *mlxsw_sp)
+{
+ mlxsw_sp->router->ipip_ops_arr = mlxsw_sp_ipip_ops_arr;
+ return 0;
+}
+
+static void mlxsw_sp_ipips_fini(struct mlxsw_sp *mlxsw_sp)
+{
+}
+
static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
{
struct mlxsw_sp_router *router;
@@ -5211,6 +5223,10 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
if (err)
goto err_rifs_init;
+ err = mlxsw_sp_ipips_init(mlxsw_sp);
+ if (err)
+ goto err_ipips_init;
+
err = rhashtable_init(&mlxsw_sp->router->nexthop_ht,
&mlxsw_sp_nexthop_ht_params);
if (err)
@@ -5252,6 +5268,8 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
err_nexthop_group_ht_init:
rhashtable_destroy(&mlxsw_sp->router->nexthop_ht);
err_nexthop_ht_init:
+ mlxsw_sp_ipips_fini(mlxsw_sp);
+err_ipips_init:
mlxsw_sp_rifs_fini(mlxsw_sp);
err_rifs_init:
__mlxsw_sp_router_fini(mlxsw_sp);
@@ -5268,6 +5286,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
mlxsw_sp_lpm_fini(mlxsw_sp);
rhashtable_destroy(&mlxsw_sp->router->nexthop_group_ht);
rhashtable_destroy(&mlxsw_sp->router->nexthop_ht);
+ mlxsw_sp_ipips_fini(mlxsw_sp);
mlxsw_sp_rifs_fini(mlxsw_sp);
__mlxsw_sp_router_fini(mlxsw_sp);
kfree(mlxsw_sp->router);
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 08/21] mlxsw: spectrum_router: Publish mlxsw_sp_l3proto
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
The spectrum_ipip module that will be introduced in the follow-up
patches needs to know the data type.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 5 -----
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h | 5 +++++
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 4e47d45..f866ac5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -405,11 +405,6 @@ struct mlxsw_sp_rt6 {
struct rt6_info *rt;
};
-enum mlxsw_sp_l3proto {
- MLXSW_SP_L3_PROTO_IPV4,
- MLXSW_SP_L3_PROTO_IPV6,
-};
-
struct mlxsw_sp_lpm_tree {
u8 id; /* tree ID */
unsigned int ref_count;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 87a04af..67c6c1d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -37,6 +37,11 @@
#include "spectrum.h"
+enum mlxsw_sp_l3proto {
+ MLXSW_SP_L3_PROTO_IPV4,
+ MLXSW_SP_L3_PROTO_IPV6,
+};
+
enum mlxsw_sp_rif_counter_dir {
MLXSW_SP_RIF_COUNTER_INGRESS,
MLXSW_SP_RIF_COUNTER_EGRESS,
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 07/21] mlxsw: reg: Give mlxsw_reg_ratr_pack a type parameter
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
To support IPIP, the driver needs to be able to construct an IPIP
adjacency. Change mlxsw_reg_ratr_pack to take an adjacency type as an
argument. Adjust the one existing caller.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 2 ++
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 ++-
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index d80cf9b..cc27c5d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -4483,11 +4483,13 @@ MLXSW_ITEM32(reg, ratr, ipip_ipv6_ptr, 0x1C, 0, 24);
static inline void
mlxsw_reg_ratr_pack(char *payload,
enum mlxsw_reg_ratr_op op, bool valid,
+ enum mlxsw_reg_ratr_type type,
u32 adjacency_index, u16 egress_rif)
{
MLXSW_REG_ZERO(ratr, payload);
mlxsw_reg_ratr_op_set(payload, op);
mlxsw_reg_ratr_v_set(payload, valid);
+ mlxsw_reg_ratr_type_set(payload, type);
mlxsw_reg_ratr_adjacency_index_low_set(payload, adjacency_index);
mlxsw_reg_ratr_adjacency_index_high_set(payload, adjacency_index >> 16);
mlxsw_reg_ratr_egress_router_interface_set(payload, egress_rif);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 3ddfbe3..4e47d45 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1928,7 +1928,8 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
char ratr_pl[MLXSW_REG_RATR_LEN];
mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY,
- true, adj_index, neigh_entry->rif);
+ true, MLXSW_REG_RATR_TYPE_ETHERNET,
+ adj_index, neigh_entry->rif);
mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl);
}
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 06/21] mlxsw: reg: Extract mlxsw_reg_ritr_mac_pack()
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
Unlike other interface types, loopback RIFs do not have MAC address. So
drop the corresponding argument from mlxsw_reg_ritr_pack() and move it
to a new function. Call that from callers of mlxsw_reg_ritr_pack.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 7 +++++--
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 7 ++++---
2 files changed, 9 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index a6eb96f..d80cf9b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -4263,8 +4263,7 @@ static inline void mlxsw_reg_ritr_sp_if_pack(char *payload, bool lag,
static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
enum mlxsw_reg_ritr_if_type type,
- u16 rif, u16 vr_id, u16 mtu,
- const char *mac)
+ u16 rif, u16 vr_id, u16 mtu)
{
bool op = enable ? MLXSW_REG_RITR_RIF_CREATE : MLXSW_REG_RITR_RIF_DEL;
@@ -4280,6 +4279,10 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
mlxsw_reg_ritr_lb_en_set(payload, 1);
mlxsw_reg_ritr_virtual_router_set(payload, vr_id);
mlxsw_reg_ritr_mtu_set(payload, mtu);
+}
+
+static inline void mlxsw_reg_ritr_mac_pack(char *payload, const char *mac)
+{
mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index de15eac..3ddfbe3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4955,8 +4955,8 @@ static int mlxsw_sp_rif_subport_op(struct mlxsw_sp_rif *rif, bool enable)
rif_subport = mlxsw_sp_rif_subport_rif(rif);
mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_SP_IF,
- rif->rif_index, rif->vr_id, rif->dev->mtu,
- rif->dev->dev_addr);
+ rif->rif_index, rif->vr_id, rif->dev->mtu);
+ mlxsw_reg_ritr_mac_pack(ritr_pl, rif->dev->dev_addr);
mlxsw_reg_ritr_sp_if_pack(ritr_pl, rif_subport->lag,
rif_subport->lag ? rif_subport->lag_id :
rif_subport->system_port,
@@ -4998,7 +4998,8 @@ static int mlxsw_sp_rif_vlan_fid_op(struct mlxsw_sp_rif *rif,
char ritr_pl[MLXSW_REG_RITR_LEN];
mlxsw_reg_ritr_pack(ritr_pl, enable, type, rif->rif_index, rif->vr_id,
- rif->dev->mtu, rif->dev->dev_addr);
+ rif->dev->mtu);
+ mlxsw_reg_ritr_mac_pack(ritr_pl, rif->dev->dev_addr);
mlxsw_reg_ritr_fid_set(ritr_pl, type, vid_fid);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 05/21] mlxsw: reg: Add Routing Tunnel Decap Properties Register
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
The RTDP register is used for configuring the tunnel decap properties of
NVE and IPinIP.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 129 ++++++++++++++++++++++++++++++
1 file changed, 129 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 24296cf..a6eb96f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5,6 +5,7 @@
* Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
* Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com>
* Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com>
+ * Copyright (c) 2017 Petr Machata <petrm@mellanox.com>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
@@ -5463,6 +5464,133 @@ static inline void mlxsw_reg_rauhtd_ent_ipv6_unpack(char *payload,
mlxsw_reg_rauhtd_ipv6_ent_dip_memcpy_from(payload, rec_index, p_dip);
}
+/* RTDP - Routing Tunnel Decap Properties Register
+ * -----------------------------------------------
+ * The RTDP register is used for configuring the tunnel decap properties of NVE
+ * and IPinIP.
+ */
+#define MLXSW_REG_RTDP_ID 0x8020
+#define MLXSW_REG_RTDP_LEN 0x44
+
+MLXSW_REG_DEFINE(rtdp, MLXSW_REG_RTDP_ID, MLXSW_REG_RTDP_LEN);
+
+enum mlxsw_reg_rtdp_type {
+ MLXSW_REG_RTDP_TYPE_NVE,
+ MLXSW_REG_RTDP_TYPE_IPIP,
+};
+
+/* reg_rtdp_type
+ * Type of the RTDP entry as per enum mlxsw_reg_rtdp_type.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rtdp, type, 0x00, 28, 4);
+
+/* reg_rtdp_tunnel_index
+ * Index to the Decap entry.
+ * For Spectrum, Index to KVD Linear.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, rtdp, tunnel_index, 0x00, 0, 24);
+
+/* IPinIP */
+
+/* reg_rtdp_ipip_irif
+ * Ingress Router Interface for the overlay router
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rtdp, ipip_irif, 0x04, 16, 16);
+
+enum mlxsw_reg_rtdp_ipip_sip_check {
+ /* No sip checks. */
+ MLXSW_REG_RTDP_IPIP_SIP_CHECK_NO,
+ /* Filter packet if underlay is not IPv4 or if underlay SIP does not
+ * equal ipv4_usip.
+ */
+ MLXSW_REG_RTDP_IPIP_SIP_CHECK_FILTER_IPV4,
+ /* Filter packet if underlay is not IPv6 or if underlay SIP does not
+ * equal ipv6_usip.
+ */
+ MLXSW_REG_RTDP_IPIP_SIP_CHECK_FILTER_IPV6 = 3,
+};
+
+/* reg_rtdp_ipip_sip_check
+ * SIP check to perform. If decapsulation failed due to these configurations
+ * then trap_id is IPIP_DECAP_ERROR.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rtdp, ipip_sip_check, 0x04, 0, 3);
+
+/* If set, allow decapsulation of IPinIP (without GRE). */
+#define MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_IPIP BIT(0)
+/* If set, allow decapsulation of IPinGREinIP without a key. */
+#define MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE BIT(1)
+/* If set, allow decapsulation of IPinGREinIP with a key. */
+#define MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE_KEY BIT(2)
+
+/* reg_rtdp_ipip_type_check
+ * Flags as per MLXSW_REG_RTDP_IPIP_TYPE_CHECK_*. If decapsulation failed due to
+ * these configurations then trap_id is IPIP_DECAP_ERROR.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rtdp, ipip_type_check, 0x08, 24, 3);
+
+/* reg_rtdp_ipip_gre_key_check
+ * Whether GRE key should be checked. When check is enabled:
+ * - A packet received as IPinIP (without GRE) will always pass.
+ * - A packet received as IPinGREinIP without a key will not pass the check.
+ * - A packet received as IPinGREinIP with a key will pass the check only if the
+ * key in the packet is equal to expected_gre_key.
+ * If decapsulation failed due to GRE key then trap_id is IPIP_DECAP_ERROR.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rtdp, ipip_gre_key_check, 0x08, 23, 1);
+
+/* reg_rtdp_ipip_ipv4_usip
+ * Underlay IPv4 address for ipv4 source address check.
+ * Reserved when sip_check is not '1'.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rtdp, ipip_ipv4_usip, 0x0C, 0, 32);
+
+/* reg_rtdp_ipip_ipv6_usip_ptr
+ * This field is valid when sip_check is "sipv6 check explicitly". This is a
+ * pointer to the IPv6 DIP which is configured by RIPS. For Spectrum, the index
+ * is to the KVD linear.
+ * Reserved when sip_check is not MLXSW_REG_RTDP_IPIP_SIP_CHECK_FILTER_IPV6.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rtdp, ipip_ipv6_usip_ptr, 0x10, 0, 24);
+
+/* reg_rtdp_ipip_expected_gre_key
+ * GRE key for checking.
+ * Reserved when gre_key_check is '0'.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rtdp, ipip_expected_gre_key, 0x14, 0, 32);
+
+static inline void mlxsw_reg_rtdp_pack(char *payload,
+ enum mlxsw_reg_rtdp_type type,
+ u32 tunnel_index)
+{
+ MLXSW_REG_ZERO(rtdp, payload);
+ mlxsw_reg_rtdp_type_set(payload, type);
+ mlxsw_reg_rtdp_tunnel_index_set(payload, tunnel_index);
+}
+
+static inline void
+mlxsw_reg_rtdp_ipip4_pack(char *payload, u16 irif,
+ enum mlxsw_reg_rtdp_ipip_sip_check sip_check,
+ unsigned int type_check, bool gre_key_check,
+ u32 ipv4_usip, u32 expected_gre_key)
+{
+ mlxsw_reg_rtdp_ipip_irif_set(payload, irif);
+ mlxsw_reg_rtdp_ipip_sip_check_set(payload, sip_check);
+ mlxsw_reg_rtdp_ipip_type_check_set(payload, type_check);
+ mlxsw_reg_rtdp_ipip_gre_key_check_set(payload, gre_key_check);
+ mlxsw_reg_rtdp_ipip_ipv4_usip_set(payload, ipv4_usip);
+ mlxsw_reg_rtdp_ipip_expected_gre_key_set(payload, expected_gre_key);
+}
+
/* MFCR - Management Fan Control Register
* --------------------------------------
* This register controls the settings of the Fan Speed PWM mechanism.
@@ -6724,6 +6852,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
MLXSW_REG(rgcr),
MLXSW_REG(ritr),
MLXSW_REG(ratr),
+ MLXSW_REG(rtdp),
MLXSW_REG(ricnt),
MLXSW_REG(ralta),
MLXSW_REG(ralst),
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 04/21] mlxsw: reg: Add mlxsw_reg_ralue_act_ip2me_tun_pack()
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
To implement IP-in-IP decapsulation, Spectrum uses LPM entries of type
IP2ME with tunnel validity bit and tunnel pointer set. The necessary
register fields are already available, so add a function to pack the
RALUE as appropriate.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index bf936b6..24296cf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5054,6 +5054,15 @@ mlxsw_reg_ralue_act_ip2me_pack(char *payload)
MLXSW_REG_RALUE_ACTION_TYPE_IP2ME);
}
+static inline void
+mlxsw_reg_ralue_act_ip2me_tun_pack(char *payload, u32 tunnel_ptr)
+{
+ mlxsw_reg_ralue_action_type_set(payload,
+ MLXSW_REG_RALUE_ACTION_TYPE_IP2ME);
+ mlxsw_reg_ralue_ip2me_v_set(payload, 1);
+ mlxsw_reg_ralue_ip2me_tunnel_ptr_set(payload, tunnel_ptr);
+}
+
/* RAUHT - Router Algorithmic LPM Unicast Host Table Register
* ----------------------------------------------------------
* The RAUHT register is used to configure and query the Unicast Host table in
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 03/21] mlxsw: reg: Move enum mlxsw_reg_ratr_trap_id
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
This enum is used with reg_ratr_trap_id, so move it next to the register
definition.
While at it, drop the enumerator initializers.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 6a7757f..bf936b6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -4423,17 +4423,17 @@ enum mlxsw_reg_ratr_trap_action {
*/
MLXSW_ITEM32(reg, ratr, trap_action, 0x0C, 28, 4);
-enum mlxsw_reg_ratr_trap_id {
- MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS0 = 0,
- MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS1 = 1,
-};
-
/* reg_ratr_adjacency_index_high
* Bits 23:16 of the adjacency_index.
* Access: Index
*/
MLXSW_ITEM32(reg, ratr, adjacency_index_high, 0x0C, 16, 8);
+enum mlxsw_reg_ratr_trap_id {
+ MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS0,
+ MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS1,
+};
+
/* reg_ratr_trap_id
* Trap ID to be reported to CPU.
* Trap-ID is RTR_EGRESS0 or RTR_EGRESS1.
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 02/21] mlxsw: reg: Update RATR to support IP-in-IP tunnels
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
So far, adjacencies have always been of type Ethernet (with value of 0),
and thus there was no need to explicitly support RATR type. However to
support IP-in-IP adjacencies, this type and a suite of IP-in-IP-specific
attributes need to be added.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 66 +++++++++++++++++++++++++++++++
1 file changed, 66 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 8736f8492..6a7757f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -4362,6 +4362,38 @@ MLXSW_ITEM32(reg, ratr, v, 0x00, 24, 1);
*/
MLXSW_ITEM32(reg, ratr, a, 0x00, 16, 1);
+enum mlxsw_reg_ratr_type {
+ /* Ethernet */
+ MLXSW_REG_RATR_TYPE_ETHERNET,
+ /* IPoIB Unicast without GRH.
+ * Reserved for Spectrum.
+ */
+ MLXSW_REG_RATR_TYPE_IPOIB_UC,
+ /* IPoIB Unicast with GRH. Supported only in table 0 (Ethernet unicast
+ * adjacency).
+ * Reserved for Spectrum.
+ */
+ MLXSW_REG_RATR_TYPE_IPOIB_UC_W_GRH,
+ /* IPoIB Multicast.
+ * Reserved for Spectrum.
+ */
+ MLXSW_REG_RATR_TYPE_IPOIB_MC,
+ /* MPLS.
+ * Reserved for SwitchX/-2.
+ */
+ MLXSW_REG_RATR_TYPE_MPLS,
+ /* IPinIP Encap.
+ * Reserved for SwitchX/-2.
+ */
+ MLXSW_REG_RATR_TYPE_IPIP,
+};
+
+/* reg_ratr_type
+ * Adjacency entry type.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, type, 0x04, 28, 4);
+
/* reg_ratr_adjacency_index_low
* Bits 15:0 of index into the adjacency table.
* For SwitchX and SwitchX-2, the adjacency table is linear and
@@ -4416,6 +4448,34 @@ MLXSW_ITEM32(reg, ratr, trap_id, 0x0C, 0, 8);
*/
MLXSW_ITEM_BUF(reg, ratr, eth_destination_mac, 0x12, 6);
+enum mlxsw_reg_ratr_ipip_type {
+ /* IPv4, address set by mlxsw_reg_ratr_ipip_ipv4_udip. */
+ MLXSW_REG_RATR_IPIP_TYPE_IPV4,
+ /* IPv6, address set by mlxsw_reg_ratr_ipip_ipv6_ptr. */
+ MLXSW_REG_RATR_IPIP_TYPE_IPV6,
+};
+
+/* reg_ratr_ipip_type
+ * Underlay destination ip type.
+ * Note: the type field must match the protocol of the router interface.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, ipip_type, 0x10, 16, 4);
+
+/* reg_ratr_ipip_ipv4_udip
+ * Underlay ipv4 dip.
+ * Reserved when ipip_type is IPv6.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, ipip_ipv4_udip, 0x18, 0, 32);
+
+/* reg_ratr_ipip_ipv6_ptr
+ * Pointer to IPv6 underlay destination ip address.
+ * For Spectrum: Pointer to KVD linear space.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ratr, ipip_ipv6_ptr, 0x1C, 0, 24);
+
static inline void
mlxsw_reg_ratr_pack(char *payload,
enum mlxsw_reg_ratr_op op, bool valid,
@@ -4435,6 +4495,12 @@ static inline void mlxsw_reg_ratr_eth_entry_pack(char *payload,
mlxsw_reg_ratr_eth_destination_mac_memcpy_to(payload, dest_mac);
}
+static inline void mlxsw_reg_ratr_ipip4_entry_pack(char *payload, u32 ipv4_udip)
+{
+ mlxsw_reg_ratr_ipip_type_set(payload, MLXSW_REG_RATR_IPIP_TYPE_IPV4);
+ mlxsw_reg_ratr_ipip_ipv4_udip_set(payload, ipv4_udip);
+}
+
/* RICNT - Router Interface Counter Register
* -----------------------------------------
* The RICNT register retrieves per port performance counters
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 01/21] mlxsw: reg: Update RITR to support loopback device
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
In-Reply-To: <20170902214929.2890-1-jiri@resnulli.us>
From: Petr Machata <petrm@mellanox.com>
Update the register so that loopback RIFs can be created and loopback
properties specified.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 88 +++++++++++++++++++++++++++++++
1 file changed, 88 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 11e290c..8736f8492 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3998,6 +3998,8 @@ enum mlxsw_reg_ritr_if_type {
MLXSW_REG_RITR_FID_IF,
/* Sub-port interface. */
MLXSW_REG_RITR_SP_IF,
+ /* Loopback Interface. */
+ MLXSW_REG_RITR_LOOPBACK_IF,
};
/* reg_ritr_type
@@ -4129,6 +4131,67 @@ MLXSW_ITEM32(reg, ritr, sp_if_system_port, 0x08, 0, 16);
*/
MLXSW_ITEM32(reg, ritr, sp_if_vid, 0x18, 0, 12);
+/* Loopback Interface */
+
+enum mlxsw_reg_ritr_loopback_protocol {
+ /* IPinIP IPv4 underlay Unicast */
+ MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV4,
+ /* IPinIP IPv6 underlay Unicast */
+ MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV6,
+};
+
+/* reg_ritr_loopback_protocol
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, loopback_protocol, 0x08, 28, 4);
+
+enum mlxsw_reg_ritr_loopback_ipip_type {
+ /* Tunnel is IPinIP. */
+ MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_IP,
+ /* Tunnel is GRE, no key. */
+ MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_IN_IP,
+ /* Tunnel is GRE, with a key. */
+ MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_KEY_IN_IP,
+};
+
+/* reg_ritr_loopback_ipip_type
+ * Encapsulation type.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, loopback_ipip_type, 0x10, 24, 4);
+
+enum mlxsw_reg_ritr_loopback_ipip_options {
+ /* The key is defined by gre_key. */
+ MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET,
+};
+
+/* reg_ritr_loopback_ipip_options
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, loopback_ipip_options, 0x10, 20, 4);
+
+/* reg_ritr_loopback_ipip_uvr
+ * Underlay Virtual Router ID.
+ * Range is 0..cap_max_virtual_routers-1.
+ * Reserved for Spectrum-2.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, loopback_ipip_uvr, 0x10, 0, 16);
+
+/* reg_ritr_loopback_ipip_usip*
+ * Encapsulation Underlay source IP.
+ * Access: RW
+ */
+MLXSW_ITEM_BUF(reg, ritr, loopback_ipip_usip6, 0x18, 16);
+MLXSW_ITEM32(reg, ritr, loopback_ipip_usip4, 0x24, 0, 32);
+
+/* reg_ritr_loopback_ipip_gre_key
+ * GRE Key.
+ * Reserved when ipip_type is not IP_IN_GRE_KEY_IN_IP.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, loopback_ipip_gre_key, 0x28, 0, 32);
+
/* Shared between ingress/egress */
enum mlxsw_reg_ritr_counter_set_type {
/* No Count. */
@@ -4219,6 +4282,31 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac);
}
+static inline void
+mlxsw_reg_ritr_loopback_ipip_common_pack(char *payload,
+ enum mlxsw_reg_ritr_loopback_ipip_type ipip_type,
+ enum mlxsw_reg_ritr_loopback_ipip_options options,
+ u16 uvr_id, u32 gre_key)
+{
+ mlxsw_reg_ritr_loopback_ipip_type_set(payload, ipip_type);
+ mlxsw_reg_ritr_loopback_ipip_options_set(payload, options);
+ mlxsw_reg_ritr_loopback_ipip_uvr_set(payload, uvr_id);
+ mlxsw_reg_ritr_loopback_ipip_gre_key_set(payload, gre_key);
+}
+
+static inline void
+mlxsw_reg_ritr_loopback_ipip4_pack(char *payload,
+ enum mlxsw_reg_ritr_loopback_ipip_type ipip_type,
+ enum mlxsw_reg_ritr_loopback_ipip_options options,
+ u16 uvr_id, u32 usip, u32 gre_key)
+{
+ mlxsw_reg_ritr_loopback_protocol_set(payload,
+ MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV4);
+ mlxsw_reg_ritr_loopback_ipip_common_pack(payload, ipip_type, options,
+ uvr_id, gre_key);
+ mlxsw_reg_ritr_loopback_ipip_usip4_set(payload, usip);
+}
+
/* RATR - Router Adjacency Table Register
* --------------------------------------
* The RATR register is used to configure the Router Adjacency (next-hop)
--
2.9.3
^ permalink raw reply related
* [patch net-next v2 00/21] mlxsw: Offloading GRE tunnels
From: Jiri Pirko @ 2017-09-02 21:49 UTC (permalink / raw)
To: netdev; +Cc: davem, petrm, idosch, mlxsw
From: Jiri Pirko <jiri@mellanox.com>
Petr says:
This patch series introduces to mlxsw driver support for offloading
IP-in-IP tunnels in general, and for (subset of) GRE in particular.
This patchset supports two ways of configuring GRE:
- So called "hierarchical configuration", where the GRE device has a bound
dummy device, which is in a different VRF. The VRF with host traffic is
called "overlay", the one with encapsulated traffic is called "underlay".
- So called "flat configuration", where the GRE device doesn't have a bound
device, and overlay and underlay are both in the same VRF (possibly the
default one).
Two routes are then interesting: a route that directs traffic to a GRE
device (which would typically be in overlay VRF, but could be in another
one), and a local route for the tunnel's local address (in underlay).
Handling of these two route types is then introduced as patches to support,
respectively, IPv4 and IPv6 encapsulation and IPv4 decapsulation.
The encap and decap routes then reference a loopback device, a new type of
RIF introduced by this patchset for the specific use of offloading tunnels.
The encap and decap code is abstract with respect to the particulars of
individual L3 tunnel types. This patchset introduces support for GRE
tunnels in particular.
Limitations:
- Each tunnel needs to have a different local address (within a given VRF).
When two tunnels are used that are in conflict, FIB abort is triggered
and the driver ceases offloading FIBs. Full handling of such
configurations needs special setup in the hardware, such that the tunnels
that share an address are dispatched correctly according to their key (or
lack thereof). That's currently not implemented, and to keep things
deterministic, the driver triggers FIB abort.
- A next hop that uses an incompletely-specified tunnel (e.g. such that are
used for LWT) is not offloaded, but doesn't trigger FIB abort like the
above. If such routes end up being in a de facto conflict with other
tunnels, then if there already is an offload for that address, the
traffic for the conflicting tunnel will end up mismatching the
configuration of the offloaded tunnel, and thus gets to slow path through
an error trap.
- GRE checksumming and sequence numbers are not supported and TTL and TOS
need to be set to inherit. Tunnels with a different configuration are not
offloaded and their traffic is trapping to slow path.
Note in particular that TOS of inherit is not the default configuration
and needs to be explicitly specified when the tunnel is created.
- The only feature that is not graciously handled is that if a change is
made to the tunnel, e.g. through "ip tunnel change", such changes are not
reflected in the driver. There is currently no notification mechanism for
these changes. Introduction of this mechanism and its leverage in the
driver will be subject of follow-up work. For now this limitation can be
worked around by removing and re-adding the encap route.
---
v1->v2:
-fix order of patch 5
Petr Machata (21):
mlxsw: reg: Update RITR to support loopback device
mlxsw: reg: Update RATR to support IP-in-IP tunnels
mlxsw: reg: Move enum mlxsw_reg_ratr_trap_id
mlxsw: reg: Add mlxsw_reg_ralue_act_ip2me_tun_pack()
mlxsw: reg: Add Routing Tunnel Decap Properties Register
mlxsw: reg: Extract mlxsw_reg_ritr_mac_pack()
mlxsw: reg: Give mlxsw_reg_ratr_pack a type parameter
mlxsw: spectrum_router: Publish mlxsw_sp_l3proto
mlxsw: spectrum_router: Add mlxsw_sp_ipip_ops
mlxsw: spectrum_router: Support FID-less RIFs
mlxsw: spectrum_router: Introduce loopback RIFs
mlxsw: spectrum_router: Extract mlxsw_sp_fi_is_gateway()
mlxsw: spectrum_router: Extract mlxsw_sp_rt6_is_gateway()
mlxsw: spectrum_router: Make nexthops typed
mlxsw: spectrum_router: Support IPv4 overlay encap
mlxsw: spectrum_router: Support IPv6 overlay encap
mlxsw: spectrum_router: Support IPv4 underlay decap
mlxsw: spectrum_router: Use existing decap route
mlxsw: spectrum: Register for IPIP_DECAP_ERROR trap
mlxsw: spectrum_router: Add loopback accessors
mlxsw: spectrum_router: Support GRE tunnels
drivers/net/ethernet/mellanox/mlxsw/Makefile | 4 +-
drivers/net/ethernet/mellanox/mlxsw/reg.h | 311 ++++++-
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 +
drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 1 +
.../net/ethernet/mellanox/mlxsw/spectrum_ipip.c | 214 +++++
.../net/ethernet/mellanox/mlxsw/spectrum_ipip.h | 79 ++
.../net/ethernet/mellanox/mlxsw/spectrum_router.c | 947 +++++++++++++++++++--
.../net/ethernet/mellanox/mlxsw/spectrum_router.h | 28 +
drivers/net/ethernet/mellanox/mlxsw/trap.h | 1 +
9 files changed, 1485 insertions(+), 101 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
--
2.9.3
^ permalink raw reply
* Re: [RFC PATCH v1 0/5] TCP Wave
From: Natale Patriciello @ 2017-09-02 20:33 UTC (permalink / raw)
To: Eric Dumazet; +Cc: netdev, Ahmed Said, Francesco Zampognaro, Cesare Roseti
In-Reply-To: <1501306413.1876.4.camel@edumazet-glaptop3.roam.corp.google.com>
Hello all,
first of all, we would like to thank everyone that commented our
patches; we are working to include all the suggestions (we are at a good
point).
However, we have two questions:
1) How to retrieve information about each connection? Right now we used
debug messages, but we understand it isn't the best option. TCP Wave
users have other values to track rather than congestion window and slow
start threshold. It seems we have two alternatives: (a) use get_info,
that returns strings to be read with ss, (b) open a file under /proc/net
and write data to it, in the same way as tcp_probe do. With option (a)
it is necessary a poll from userspace (for instance, using watch), but
is subjected to delays and maybe not suitable for fast connections
(watch minimum interval is 100 ms). Option (b), toggled with a module
parameter, seems the more viable. Is that correct?
The second one is inline:
On 28/07/17 at 10:33pm, Eric Dumazet wrote:
> On Fri, 2017-07-28 at 21:59 +0200, Natale Patriciello wrote:
> > Hi,
[cut]
> > TCP Wave (TCPW) replaces the window-based transmission paradigm of the standard
> > TCP with a burst-based transmission, the ACK-clock scheduling with a
> > self-managed timer and the RTT-based congestion control loop with an Ack-based
> > Capacity and Congestion Estimation (ACCE) module. In non-technical words, it
> > sends data down the stack when its internal timer expires, and the timing of
> > the received ACKs contribute to updating this timer regularly.
>
> This patch series seems to have missed recent efforts in TCP stack,
> namely TCP pacing.
>
> commit 218af599fa635b107cfe10acf3249c4dfe5e4123 ("tcp: internal
> implementation for pacing") added a timer already to get fine grained
> packet xmits.
Thank you, Eric, for this suggestion; in fact, we had problems with our
implementation of the timer, and we would like to switch to the new
pacing timer entirely. However, a pacing approach is exactly the
opposite we would like to achieve: we want to send a burst of data
(let's say, ten segments) and then wait some amount of time. Do you
think that adding a new congestion control callback that returns the
number of segments to send when the timer expires (default to 1) and another
callback for retrieving the pacing time can be a sound strategy?
Thank you again, have a nice day.
Natale
^ permalink raw reply
* [PATCH net-next v2 4/4] net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
From: Florian Fainelli @ 2017-09-02 18:06 UTC (permalink / raw)
To: netdev
Cc: davem, andrew, vivien.didelot, jiri, jhs, xiyou.wangcong,
Florian Fainelli
In-Reply-To: <20170902180609.23122-1-f.fainelli@gmail.com>
Even though TC2QOS mapping is for switch egress queues, we need to
configure it correclty in order for the Broadcom tag ingress (CPU ->
switch) queue selection to work correctly since there is a 1:1 mapping
between switch egress queues and ingress queues.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/dsa/bcm_sf2.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 6b184bafa235..d7b53d53c116 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -103,6 +103,7 @@ static void bcm_sf2_brcm_hdr_setup(struct bcm_sf2_priv *priv, int port)
static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
{
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+ unsigned int i;
u32 reg, offset;
if (priv->type == BCM7445_DEVICE_ID)
@@ -129,6 +130,14 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
reg |= MII_DUMB_FWDG_EN;
core_writel(priv, reg, CORE_SWITCH_CTRL);
+ /* Configure Traffic Class to QoS mapping, allow each priority to map
+ * to a different queue number
+ */
+ reg = core_readl(priv, CORE_PORT_TC2_QOS_MAP_PORT(port));
+ for (i = 0; i < SF2_NUM_EGRESS_QUEUES; i++)
+ reg |= i << (PRT_TO_QID_SHIFT * i);
+ core_writel(priv, reg, CORE_PORT_TC2_QOS_MAP_PORT(port));
+
bcm_sf2_brcm_hdr_setup(priv, port);
/* Force link status for IMP port */
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v2 3/4] net: dsa: bcm_sf2: Advertise number of egress queues
From: Florian Fainelli @ 2017-09-02 18:06 UTC (permalink / raw)
To: netdev
Cc: davem, andrew, vivien.didelot, jiri, jhs, xiyou.wangcong,
Florian Fainelli
In-Reply-To: <20170902180609.23122-1-f.fainelli@gmail.com>
The switch supports 8 egress queues per port, so indicate that such that
net/dsa/slave.c::dsa_slave_create can allocate the right number of TX queues.
While at it use SF2_NUM_EGRESS_QUEUE as a define for the number of queues we
support.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/dsa/bcm_sf2.c | 5 ++++-
drivers/net/dsa/bcm_sf2_regs.h | 3 +++
2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 554fe2df9365..6b184bafa235 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -244,7 +244,7 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
* to a different queue number
*/
reg = core_readl(priv, CORE_PORT_TC2_QOS_MAP_PORT(port));
- for (i = 0; i < 8; i++)
+ for (i = 0; i < SF2_NUM_EGRESS_QUEUES; i++)
reg |= i << (PRT_TO_QID_SHIFT * i);
core_writel(priv, reg, CORE_PORT_TC2_QOS_MAP_PORT(port));
@@ -1151,6 +1151,9 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
ds = dev->ds;
ds->ops = &bcm_sf2_ops;
+ /* Advertise the 8 egress queues */
+ ds->num_tx_queues = SF2_NUM_EGRESS_QUEUES;
+
dev_set_drvdata(&pdev->dev, priv);
spin_lock_init(&priv->indir_lock);
diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h
index 26052450091e..49695fcc2ea8 100644
--- a/drivers/net/dsa/bcm_sf2_regs.h
+++ b/drivers/net/dsa/bcm_sf2_regs.h
@@ -401,4 +401,7 @@ enum bcm_sf2_reg_offs {
#define CFP_NUM_RULES 256
+/* Number of egress queues per port */
+#define SF2_NUM_EGRESS_QUEUES 8
+
#endif /* __BCM_SF2_REGS_H */
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v2 2/4] net: dsa: tag_brcm: Set output queue from skb queue mapping
From: Florian Fainelli @ 2017-09-02 18:06 UTC (permalink / raw)
To: netdev
Cc: davem, andrew, vivien.didelot, jiri, jhs, xiyou.wangcong,
Florian Fainelli
In-Reply-To: <20170902180609.23122-1-f.fainelli@gmail.com>
We originally used skb->priority but that was not quite correct as this
bitfield needs to contain the egress switch queue we intend to send this
SKB to.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
net/dsa/tag_brcm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index de74c3f77818..dbb016434ace 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -62,6 +62,7 @@
static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
+ u16 queue = skb_get_queue_mapping(skb);
u8 *brcm_tag;
if (skb_cow_head(skb, BRCM_TAG_LEN) < 0)
@@ -78,7 +79,7 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev
* deprecated
*/
brcm_tag[0] = (1 << BRCM_OPCODE_SHIFT) |
- ((skb->priority << BRCM_IG_TC_SHIFT) & BRCM_IG_TC_MASK);
+ ((queue & BRCM_IG_TC_MASK) << BRCM_IG_TC_SHIFT);
brcm_tag[1] = 0;
brcm_tag[2] = 0;
if (p->dp->index == 8)
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v2 1/4] net: dsa: Allow switch drivers to indicate number of TX queues
From: Florian Fainelli @ 2017-09-02 18:06 UTC (permalink / raw)
To: netdev
Cc: davem, andrew, vivien.didelot, jiri, jhs, xiyou.wangcong,
Florian Fainelli
In-Reply-To: <20170902180609.23122-1-f.fainelli@gmail.com>
Let switch drivers indicate how many TX queues they support. Some
switches, such as Broadcom Starfighter 2 are designed with 8 egress
queues. Future changes will allow us to leverage the queue mapping and
direct the transmission towards a particular queue.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
include/net/dsa.h | 3 +++
net/dsa/slave.c | 8 ++++++--
2 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 398ca8d70ccd..dd44d6ce1097 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -243,6 +243,9 @@ struct dsa_switch {
/* devlink used to represent this switch device */
struct devlink *devlink;
+ /* Number of switch port queues */
+ unsigned int num_tx_queues;
+
/* Dynamically allocated ports, keep last */
size_t num_ports;
struct dsa_port ports[];
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 78e78a6e6833..2afa99506f8b 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1259,8 +1259,12 @@ int dsa_slave_create(struct dsa_port *port, const char *name)
cpu_dp = ds->dst->cpu_dp;
master = cpu_dp->netdev;
- slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), name,
- NET_NAME_UNKNOWN, ether_setup);
+ if (!ds->num_tx_queues)
+ ds->num_tx_queues = 1;
+
+ slave_dev = alloc_netdev_mqs(sizeof(struct dsa_slave_priv), name,
+ NET_NAME_UNKNOWN, ether_setup,
+ ds->num_tx_queues, 1);
if (slave_dev == NULL)
return -ENOMEM;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v2 0/4] net: dsa: Allow switch drivers to indicate number of TX queues
From: Florian Fainelli @ 2017-09-02 18:06 UTC (permalink / raw)
To: netdev
Cc: davem, andrew, vivien.didelot, jiri, jhs, xiyou.wangcong,
Florian Fainelli
Hi all,
This patch series extracts the parts of the patch set that are likely not to be
controversial and actually bringing multi-queue support to DSA-created network
devices.
With these patches, we can now use sch_multiq as documented under
Documentation/networking/multique.txt and let applications dedice the switch
port output queue they want to use. Currently only Broadcom tags utilize that
information.
Changes in v2:
- use a proper define for the number of TX queues in bcm_sf2.c (Andrew)
Changes from RFC:
- dropped the ability to configure RX queues since we don't do anything with
those just yet
- dropped the patches that dealt with binding the DSA slave network devices
queues with their master network devices queues this will be worked on
separately.
Florian Fainelli (4):
net: dsa: Allow switch drivers to indicate number of TX queues
net: dsa: tag_brcm: Set output queue from skb queue mapping
net: dsa: bcm_sf2: Advertise number of egress queues
net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
drivers/net/dsa/bcm_sf2.c | 14 +++++++++++++-
drivers/net/dsa/bcm_sf2_regs.h | 3 +++
include/net/dsa.h | 3 +++
net/dsa/slave.c | 8 ++++++--
net/dsa/tag_brcm.c | 3 ++-
5 files changed, 27 insertions(+), 4 deletions(-)
--
2.11.0
^ permalink raw reply
* Re: [PATCH net-next 4/4] net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
From: Florian Fainelli @ 2017-09-02 17:57 UTC (permalink / raw)
To: Andrew Lunn; +Cc: netdev, davem, vivien.didelot, jiri, jhs, xiyou.wangcong
In-Reply-To: <20170902174753.GA8981@lunn.ch>
On 09/02/2017 10:47 AM, Andrew Lunn wrote:
> On Sat, Sep 02, 2017 at 09:32:08AM -0700, Florian Fainelli wrote:
>>
>>
>> On 09/02/2017 09:30 AM, Andrew Lunn wrote:
>>>> @@ -129,6 +130,14 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
>>>> reg |= MII_DUMB_FWDG_EN;
>>>> core_writel(priv, reg, CORE_SWITCH_CTRL);
>>>>
>>>> + /* Configure Traffic Class to QoS mapping, allow each priority to map
>>>> + * to a different queue number
>>>> + */
>>>> + reg = core_readl(priv, CORE_PORT_TC2_QOS_MAP_PORT(port));
>>>> + for (i = 0; i < 8; i++)
>>>> + reg |= i << (PRT_TO_QID_SHIFT * i);
>>>
>>> Hi Florian
>>>
>>> Rather than 8, would ds->num_tx_queues be more descriptive?
>>
>> I actually have a patch on top of this which defines a constant for the
>> number of queues instead of open coding 8 here. Thanks!
>
> Hi Florian
>
> It sounds like it should be part of 3/4?
Right, let me re-submit with that change included. Thanks
--
Florian
^ permalink raw reply
* Re: [PATCH net-next 4/4] net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
From: Andrew Lunn @ 2017-09-02 17:47 UTC (permalink / raw)
To: Florian Fainelli; +Cc: netdev, davem, vivien.didelot, jiri, jhs, xiyou.wangcong
In-Reply-To: <e0d92f15-342d-2b5b-2f7d-aedba328116f@gmail.com>
On Sat, Sep 02, 2017 at 09:32:08AM -0700, Florian Fainelli wrote:
>
>
> On 09/02/2017 09:30 AM, Andrew Lunn wrote:
> >> @@ -129,6 +130,14 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
> >> reg |= MII_DUMB_FWDG_EN;
> >> core_writel(priv, reg, CORE_SWITCH_CTRL);
> >>
> >> + /* Configure Traffic Class to QoS mapping, allow each priority to map
> >> + * to a different queue number
> >> + */
> >> + reg = core_readl(priv, CORE_PORT_TC2_QOS_MAP_PORT(port));
> >> + for (i = 0; i < 8; i++)
> >> + reg |= i << (PRT_TO_QID_SHIFT * i);
> >
> > Hi Florian
> >
> > Rather than 8, would ds->num_tx_queues be more descriptive?
>
> I actually have a patch on top of this which defines a constant for the
> number of queues instead of open coding 8 here. Thanks!
Hi Florian
It sounds like it should be part of 3/4?
Andrew
^ permalink raw reply
* Re: [PATCH] Fix build on fedora-14 (and other older systems)
From: Michal Kubecek @ 2017-09-02 17:03 UTC (permalink / raw)
To: greearb; +Cc: netdev
In-Reply-To: <1504361702-30266-1-git-send-email-greearb@candelatech.com>
On Sat, Sep 02, 2017 at 07:15:02AM -0700, greearb@candelatech.com wrote:
> From: Ben Greear <greearb@candelatech.com>
>
> Seems Fedora-20 and below fail, hopefully this fixes
> them.
>
> Signed-off-by: Ben Greear <greearb@candelatech.com>
> ---
> include/linux/sysinfo.h | 8 ++++++++
> ip/ipxfrm.c | 1 +
> ip/xfrm_policy.c | 1 +
> ip/xfrm_state.c | 1 +
> 4 files changed, 11 insertions(+)
Works for me from openSUSE Tumbleweed to SLE11 SP4 (kernel 3.0). The
build on SLE11 SP2 (also 3.0 but older headers in /usr/include)
fails with unknown MS_PRIVATE and MS_REC in lib/bpf.c
Newer systems have these defined in <sys/mount.h>
Including <linux/fs.h> directly in lib/bpf.c fixes that but if we do
that, a copy of the file would have to be included.
> diff --git a/include/linux/sysinfo.h b/include/linux/sysinfo.h
> index 934335a..3596b02 100644
> --- a/include/linux/sysinfo.h
> +++ b/include/linux/sysinfo.h
> @@ -3,6 +3,14 @@
>
> #include <linux/types.h>
>
> +/* So we can compile on older OSs, hopefully this is correct. --Ben */
> +#ifndef __kernel_long_t
> +typedef long __kernel_long_t;
> +#endif
> +#ifndef __kernel_ulong_t
> +typedef unsigned long __kernel_ulong_t;
> +#endif
> +
> #define SI_LOAD_SHIFT 16
> struct sysinfo {
> __kernel_long_t uptime; /* Seconds since boot */
I'm not sure if it is acceptable to modify a file which is supposed to
be a direct copy of kernel uapi header.
Michal Kubecek
^ permalink raw reply
* Re: [PATCH net-next 0/4] net: dsa: add master interface
From: Florian Fainelli @ 2017-09-02 16:42 UTC (permalink / raw)
To: Vivien Didelot, netdev; +Cc: linux-kernel, kernel, David S. Miller, Andrew Lunn
In-Reply-To: <20170831183746.2109-1-vivien.didelot@savoirfairelinux.com>
Hi Vivien,
On 08/31/2017 11:37 AM, Vivien Didelot wrote:
> Currently the SoC network interface (called master) to which a switch
> fabric hangs, has its dsa_ptr pointing to a dsa_switch_tree instance.
>
> This is not quite correct, because this interface is physically wired to
> one of the switch ports (called CPU port), and because in a switch
> fabric with multiple CPU ports, several master interfaces will point to
> several CPU ports of the same dsa_switch_tree.
>
> This patchset adds a new dsa_master structure to represent the pipe
> between the SoC master interface and its switch CPU port. This structure
> will store specific data such as the master ethtool_ops copy and the
> tagging protocol used to pass frames with the associated slave ports.
> The dsa_ptr is changed to a dsa_master instance, and each DSA slave now
> has a pointer to a master port.
>
> This is a step forward better control over the CPU conduit and support
> for multiple CPU ports.
Looked briefly over this series and this looks good to me, Andrew has a
valid point about reducing the number of dereferences in hot paths
though. Thanks!
>
> Vivien Didelot (4):
> net: dsa: introduce dsa_master
> net: dsa: move master ethtool ops in dsa_master
> net: dsa: change dsa_ptr for a dsa_master
> net: dsa: assign a master to slave ports
>
> drivers/net/dsa/b53/b53_common.c | 4 +-
> drivers/net/dsa/bcm_sf2.c | 8 +--
> drivers/net/dsa/mt7530.c | 4 +-
> drivers/net/dsa/mv88e6060.c | 2 +-
> drivers/net/dsa/qca8k.c | 2 +-
> include/linux/netdevice.h | 4 +-
> include/net/dsa.h | 42 +++++------
> net/dsa/Makefile | 2 +-
> net/dsa/dsa.c | 34 +--------
> net/dsa/dsa2.c | 38 +++++-----
> net/dsa/dsa_priv.h | 24 +++----
> net/dsa/legacy.c | 34 +++++----
> net/dsa/master.c | 149 +++++++++++++++++++++++++++++++++++++++
> net/dsa/slave.c | 117 +++++-------------------------
> net/dsa/tag_brcm.c | 5 +-
> net/dsa/tag_dsa.c | 3 +-
> net/dsa/tag_edsa.c | 3 +-
> net/dsa/tag_ksz.c | 5 +-
> net/dsa/tag_lan9303.c | 6 +-
> net/dsa/tag_mtk.c | 12 +---
> net/dsa/tag_qca.c | 12 +---
> net/dsa/tag_trailer.c | 5 +-
> 22 files changed, 265 insertions(+), 250 deletions(-)
> create mode 100644 net/dsa/master.c
>
--
Florian
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox