mirror of
https://github.com/torvalds/linux.git
synced 2024-11-25 05:32:00 +00:00
5832c4a77d
Historically, tunnel flags like TUNNEL_CSUM or TUNNEL_ERSPAN_OPT have been defined as __be16. Now all of those 16 bits are occupied and there's no more free space for new flags. It can't be simply switched to a bigger container with no adjustments to the values, since it's an explicit Endian storage, and on LE systems (__be16)0x0001 equals to (__be64)0x0001000000000000. We could probably define new 64-bit flags depending on the Endianness, i.e. (__be64)0x0001 on BE and (__be64)0x00010000... on LE, but that would introduce an Endianness dependency and spawn a ton of Sparse warnings. To mitigate them, all of those places which were adjusted with this change would be touched anyway, so why not define stuff properly if there's no choice. Define IP_TUNNEL_*_BIT counterparts as a bit number instead of the value already coded and a fistful of <16 <-> bitmap> converters and helpers. The two flags which have a different bit position are SIT_ISATAP_BIT and VTI_ISVTI_BIT, as they were defined not as __cpu_to_be16(), but as (__force __be16), i.e. had different positions on LE and BE. Now they both have strongly defined places. Change all __be16 fields which were used to store those flags, to IP_TUNNEL_DECLARE_FLAGS() -> DECLARE_BITMAP(__IP_TUNNEL_FLAG_NUM) -> unsigned long[1] for now, and replace all TUNNEL_* occurrences to their bitmap counterparts. Use the converters in the places which talk to the userspace, hardware (NFP) or other hosts (GRE header). The rest must explicitly use the new flags only. This must be done at once, otherwise there will be too many conversions throughout the code in the intermediate commits. Finally, disable the old __be16 flags for use in the kernel code (except for the two 'irregular' flags mentioned above), to prevent any accidental (mis)use of them. For the userspace, nothing is changed, only additions were made. Most noticeable bloat-o-meter difference (.text): vmlinux: 307/-1 (306) gre.ko: 62/0 (62) ip_gre.ko: 941/-217 (724) [*] ip_tunnel.ko: 390/-900 (-510) [**] ip_vti.ko: 138/0 (138) ip6_gre.ko: 534/-18 (516) [*] ip6_tunnel.ko: 118/-10 (108) [*] gre_flags_to_tnl_flags() grew, but still is inlined [**] ip_tunnel_find() got uninlined, hence such decrease The average code size increase in non-extreme case is 100-200 bytes per module, mostly due to sizeof(long) > sizeof(__be16), as %__IP_TUNNEL_FLAG_NUM is less than %BITS_PER_LONG and the compilers are able to expand the majority of bitmap_*() calls here into direct operations on scalars. Reviewed-by: Simon Horman <horms@kernel.org> Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
228 lines
5.3 KiB
C
228 lines
5.3 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* Bridge per vlan tunnel port dst_metadata handling code
|
|
*
|
|
* Authors:
|
|
* Roopa Prabhu <roopa@cumulusnetworks.com>
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/slab.h>
|
|
#include <net/switchdev.h>
|
|
#include <net/dst_metadata.h>
|
|
|
|
#include "br_private.h"
|
|
#include "br_private_tunnel.h"
|
|
|
|
static inline int br_vlan_tunid_cmp(struct rhashtable_compare_arg *arg,
|
|
const void *ptr)
|
|
{
|
|
const struct net_bridge_vlan *vle = ptr;
|
|
__be64 tunid = *(__be64 *)arg->key;
|
|
|
|
return vle->tinfo.tunnel_id != tunid;
|
|
}
|
|
|
|
static const struct rhashtable_params br_vlan_tunnel_rht_params = {
|
|
.head_offset = offsetof(struct net_bridge_vlan, tnode),
|
|
.key_offset = offsetof(struct net_bridge_vlan, tinfo.tunnel_id),
|
|
.key_len = sizeof(__be64),
|
|
.nelem_hint = 3,
|
|
.obj_cmpfn = br_vlan_tunid_cmp,
|
|
.automatic_shrinking = true,
|
|
};
|
|
|
|
static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl,
|
|
__be64 tunnel_id)
|
|
{
|
|
return rhashtable_lookup_fast(tbl, &tunnel_id,
|
|
br_vlan_tunnel_rht_params);
|
|
}
|
|
|
|
static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan)
|
|
{
|
|
struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst);
|
|
|
|
WRITE_ONCE(vlan->tinfo.tunnel_id, 0);
|
|
RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL);
|
|
dst_release(&tdst->dst);
|
|
}
|
|
|
|
void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg,
|
|
struct net_bridge_vlan *vlan)
|
|
{
|
|
if (!rcu_access_pointer(vlan->tinfo.tunnel_dst))
|
|
return;
|
|
rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode,
|
|
br_vlan_tunnel_rht_params);
|
|
vlan_tunnel_info_release(vlan);
|
|
}
|
|
|
|
static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg,
|
|
struct net_bridge_vlan *vlan, u32 tun_id)
|
|
{
|
|
struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst);
|
|
__be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id));
|
|
IP_TUNNEL_DECLARE_FLAGS(flags) = { };
|
|
int err;
|
|
|
|
if (metadata)
|
|
return -EEXIST;
|
|
|
|
__set_bit(IP_TUNNEL_KEY_BIT, flags);
|
|
metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, flags, key, 0);
|
|
if (!metadata)
|
|
return -EINVAL;
|
|
|
|
metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE;
|
|
rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata);
|
|
WRITE_ONCE(vlan->tinfo.tunnel_id, key);
|
|
|
|
err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode,
|
|
br_vlan_tunnel_rht_params);
|
|
if (err)
|
|
goto out;
|
|
|
|
return 0;
|
|
out:
|
|
vlan_tunnel_info_release(vlan);
|
|
|
|
return err;
|
|
}
|
|
|
|
/* Must be protected by RTNL.
|
|
* Must be called with vid in range from 1 to 4094 inclusive.
|
|
*/
|
|
int nbp_vlan_tunnel_info_add(const struct net_bridge_port *port, u16 vid,
|
|
u32 tun_id)
|
|
{
|
|
struct net_bridge_vlan_group *vg;
|
|
struct net_bridge_vlan *vlan;
|
|
|
|
ASSERT_RTNL();
|
|
|
|
vg = nbp_vlan_group(port);
|
|
vlan = br_vlan_find(vg, vid);
|
|
if (!vlan)
|
|
return -EINVAL;
|
|
|
|
return __vlan_tunnel_info_add(vg, vlan, tun_id);
|
|
}
|
|
|
|
/* Must be protected by RTNL.
|
|
* Must be called with vid in range from 1 to 4094 inclusive.
|
|
*/
|
|
int nbp_vlan_tunnel_info_delete(const struct net_bridge_port *port, u16 vid)
|
|
{
|
|
struct net_bridge_vlan_group *vg;
|
|
struct net_bridge_vlan *v;
|
|
|
|
ASSERT_RTNL();
|
|
|
|
vg = nbp_vlan_group(port);
|
|
v = br_vlan_find(vg, vid);
|
|
if (!v)
|
|
return -ENOENT;
|
|
|
|
vlan_tunnel_info_del(vg, v);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void __vlan_tunnel_info_flush(struct net_bridge_vlan_group *vg)
|
|
{
|
|
struct net_bridge_vlan *vlan, *tmp;
|
|
|
|
list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist)
|
|
vlan_tunnel_info_del(vg, vlan);
|
|
}
|
|
|
|
void nbp_vlan_tunnel_info_flush(struct net_bridge_port *port)
|
|
{
|
|
struct net_bridge_vlan_group *vg;
|
|
|
|
ASSERT_RTNL();
|
|
|
|
vg = nbp_vlan_group(port);
|
|
__vlan_tunnel_info_flush(vg);
|
|
}
|
|
|
|
int vlan_tunnel_init(struct net_bridge_vlan_group *vg)
|
|
{
|
|
return rhashtable_init(&vg->tunnel_hash, &br_vlan_tunnel_rht_params);
|
|
}
|
|
|
|
void vlan_tunnel_deinit(struct net_bridge_vlan_group *vg)
|
|
{
|
|
rhashtable_destroy(&vg->tunnel_hash);
|
|
}
|
|
|
|
void br_handle_ingress_vlan_tunnel(struct sk_buff *skb,
|
|
struct net_bridge_port *p,
|
|
struct net_bridge_vlan_group *vg)
|
|
{
|
|
struct ip_tunnel_info *tinfo = skb_tunnel_info(skb);
|
|
struct net_bridge_vlan *vlan;
|
|
|
|
if (!vg || !tinfo)
|
|
return;
|
|
|
|
/* if already tagged, ignore */
|
|
if (skb_vlan_tagged(skb))
|
|
return;
|
|
|
|
/* lookup vid, given tunnel id */
|
|
vlan = br_vlan_tunnel_lookup(&vg->tunnel_hash, tinfo->key.tun_id);
|
|
if (!vlan)
|
|
return;
|
|
|
|
skb_dst_drop(skb);
|
|
|
|
__vlan_hwaccel_put_tag(skb, p->br->vlan_proto, vlan->vid);
|
|
}
|
|
|
|
int br_handle_egress_vlan_tunnel(struct sk_buff *skb,
|
|
struct net_bridge_vlan *vlan)
|
|
{
|
|
IP_TUNNEL_DECLARE_FLAGS(flags) = { };
|
|
struct metadata_dst *tunnel_dst;
|
|
__be64 tunnel_id;
|
|
int err;
|
|
|
|
if (!vlan)
|
|
return 0;
|
|
|
|
tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id);
|
|
if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb)))
|
|
return 0;
|
|
|
|
skb_dst_drop(skb);
|
|
err = skb_vlan_pop(skb);
|
|
if (err)
|
|
return err;
|
|
|
|
if (BR_INPUT_SKB_CB(skb)->backup_nhid) {
|
|
__set_bit(IP_TUNNEL_KEY_BIT, flags);
|
|
tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, flags,
|
|
tunnel_id, 0);
|
|
if (!tunnel_dst)
|
|
return -ENOMEM;
|
|
|
|
tunnel_dst->u.tun_info.mode |= IP_TUNNEL_INFO_TX |
|
|
IP_TUNNEL_INFO_BRIDGE;
|
|
tunnel_dst->u.tun_info.key.nhid =
|
|
BR_INPUT_SKB_CB(skb)->backup_nhid;
|
|
skb_dst_set(skb, &tunnel_dst->dst);
|
|
|
|
return 0;
|
|
}
|
|
|
|
tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst);
|
|
if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst))
|
|
skb_dst_set(skb, &tunnel_dst->dst);
|
|
|
|
return 0;
|
|
}
|