linux/net/bridge/br_switchdev.c

134 lines
3.1 KiB
C
Raw Normal View History

bridge: switchdev: Add forward mark support for stacked devices switchdev_port_fwd_mark_set() is used to set the 'offload_fwd_mark' of port netdevs so that packets being flooded by the device won't be flooded twice. It works by assigning a unique identifier (the ifindex of the first bridge port) to bridge ports sharing the same parent ID. This prevents packets from being flooded twice by the same switch, but will flood packets through bridge ports belonging to a different switch. This method is problematic when stacked devices are taken into account, such as VLANs. In such cases, a physical port netdev can have upper devices being members in two different bridges, thus requiring two different 'offload_fwd_mark's to be configured on the port netdev, which is impossible. The main problem is that packet and netdev marking is performed at the physical netdev level, whereas flooding occurs between bridge ports, which are not necessarily port netdevs. Instead, packet and netdev marking should really be done in the bridge driver with the switch driver only telling it which packets it already forwarded. The bridge driver will mark such packets using the mark assigned to the ingress bridge port and will prevent the packet from being forwarded through any bridge port sharing the same mark (i.e. having the same parent ID). Remove the current switchdev 'offload_fwd_mark' implementation and instead implement the proposed method. In addition, make rocker - the sole user of the mark - use the proposed method. Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-26 00:42:37 +08:00
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/skbuff.h>
#include <net/switchdev.h>
#include "br_private.h"
static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev)
{
struct net_bridge_port *p;
/* dev is yet to be added to the port list. */
list_for_each_entry(p, &br->port_list, list) {
if (switchdev_port_same_parent_id(dev, p->dev))
return p->offload_fwd_mark;
}
return ++br->offload_fwd_mark;
}
int nbp_switchdev_mark_set(struct net_bridge_port *p)
{
struct switchdev_attr attr = {
.orig_dev = p->dev,
.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
};
int err;
ASSERT_RTNL();
err = switchdev_port_attr_get(p->dev, &attr);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
return err;
}
p->offload_fwd_mark = br_switchdev_mark_get(p->br, p->dev);
return 0;
}
void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
struct sk_buff *skb)
{
if (skb->offload_fwd_mark && !WARN_ON_ONCE(!p->offload_fwd_mark))
BR_INPUT_SKB_CB(skb)->offload_fwd_mark = p->offload_fwd_mark;
}
bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p,
const struct sk_buff *skb)
{
return !skb->offload_fwd_mark ||
BR_INPUT_SKB_CB(skb)->offload_fwd_mark != p->offload_fwd_mark;
}
/* Flags that can be offloaded to hardware */
#define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | \
BR_MCAST_FLOOD | BR_BCAST_FLOOD)
int br_switchdev_set_port_flag(struct net_bridge_port *p,
unsigned long flags,
unsigned long mask)
{
struct switchdev_attr attr = {
.orig_dev = p->dev,
.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT,
};
int err;
if (mask & ~BR_PORT_FLAGS_HW_OFFLOAD)
return 0;
err = switchdev_port_attr_get(p->dev, &attr);
if (err == -EOPNOTSUPP)
return 0;
if (err)
return err;
/* Check if specific bridge flag attribute offload is supported */
if (!(attr.u.brport_flags_support & mask)) {
br_warn(p->br, "bridge flag offload is not supported %u(%s)\n",
(unsigned int)p->port_no, p->dev->name);
return -EOPNOTSUPP;
}
attr.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS;
attr.flags = SWITCHDEV_F_DEFER;
attr.u.brport_flags = flags;
err = switchdev_port_attr_set(p->dev, &attr);
if (err) {
br_warn(p->br, "error setting offload flag on port %u(%s)\n",
(unsigned int)p->port_no, p->dev->name);
return err;
}
return 0;
}
static void
br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac,
u16 vid, struct net_device *dev)
{
struct switchdev_notifier_fdb_info info;
unsigned long notifier_type;
info.addr = mac;
info.vid = vid;
notifier_type = adding ? SWITCHDEV_FDB_ADD_TO_DEVICE : SWITCHDEV_FDB_DEL_TO_DEVICE;
call_switchdev_notifiers(notifier_type, dev, &info.info);
}
void
br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
{
bridge: check for null fdb->dst before notifying switchdev drivers current switchdev drivers dont seem to support offloading fdb entries pointing to the bridge device which have fdb->dst not set to any port. This patch adds a NULL fdb->dst check in the switchdev notifier code. This patch fixes the below NULL ptr dereference: $bridge fdb add 00:02:00:00:00:33 dev br0 self [ 69.953374] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 [ 69.954044] IP: br_switchdev_fdb_notify+0x29/0x80 [ 69.954044] PGD 66527067 [ 69.954044] P4D 66527067 [ 69.954044] PUD 7899c067 [ 69.954044] PMD 0 [ 69.954044] [ 69.954044] Oops: 0000 [#1] SMP [ 69.954044] Modules linked in: [ 69.954044] CPU: 1 PID: 3074 Comm: bridge Not tainted 4.13.0-rc6+ #1 [ 69.954044] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5.1-0-g8936dbb-20141113_115728-nilsson.home.kraxel.org 04/01/2014 [ 69.954044] task: ffff88007b827140 task.stack: ffffc90001564000 [ 69.954044] RIP: 0010:br_switchdev_fdb_notify+0x29/0x80 [ 69.954044] RSP: 0018:ffffc90001567918 EFLAGS: 00010246 [ 69.954044] RAX: 0000000000000000 RBX: ffff8800795e0880 RCX: 00000000000000c0 [ 69.954044] RDX: ffffc90001567920 RSI: 000000000000001c RDI: ffff8800795d0600 [ 69.954044] RBP: ffffc90001567938 R08: ffff8800795d0600 R09: 0000000000000000 [ 69.954044] R10: ffffc90001567a88 R11: ffff88007b849400 R12: ffff8800795e0880 [ 69.954044] R13: ffff8800795d0600 R14: ffffffff81ef8880 R15: 000000000000001c [ 69.954044] FS: 00007f93d3085700(0000) GS:ffff88007fd00000(0000) knlGS:0000000000000000 [ 69.954044] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 69.954044] CR2: 0000000000000008 CR3: 0000000066551000 CR4: 00000000000006e0 [ 69.954044] Call Trace: [ 69.954044] fdb_notify+0x3f/0xf0 [ 69.954044] __br_fdb_add.isra.12+0x1a7/0x370 [ 69.954044] br_fdb_add+0x178/0x280 [ 69.954044] rtnl_fdb_add+0x10a/0x200 [ 69.954044] rtnetlink_rcv_msg+0x1b4/0x240 [ 69.954044] ? skb_free_head+0x21/0x40 [ 69.954044] ? rtnl_calcit.isra.18+0xf0/0xf0 [ 69.954044] netlink_rcv_skb+0xed/0x120 [ 69.954044] rtnetlink_rcv+0x15/0x20 [ 69.954044] netlink_unicast+0x180/0x200 [ 69.954044] netlink_sendmsg+0x291/0x370 [ 69.954044] ___sys_sendmsg+0x180/0x2e0 [ 69.954044] ? filemap_map_pages+0x2db/0x370 [ 69.954044] ? do_wp_page+0x11d/0x420 [ 69.954044] ? __handle_mm_fault+0x794/0xd80 [ 69.954044] ? vma_link+0xcb/0xd0 [ 69.954044] __sys_sendmsg+0x4c/0x90 [ 69.954044] SyS_sendmsg+0x12/0x20 [ 69.954044] do_syscall_64+0x63/0xe0 [ 69.954044] entry_SYSCALL64_slow_path+0x25/0x25 [ 69.954044] RIP: 0033:0x7f93d2bad690 [ 69.954044] RSP: 002b:00007ffc7217a638 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 69.954044] RAX: ffffffffffffffda RBX: 00007ffc72182eac RCX: 00007f93d2bad690 [ 69.954044] RDX: 0000000000000000 RSI: 00007ffc7217a670 RDI: 0000000000000003 [ 69.954044] RBP: 0000000059a1f7f8 R08: 0000000000000006 R09: 000000000000000a [ 69.954044] R10: 00007ffc7217a400 R11: 0000000000000246 R12: 00007ffc7217a670 [ 69.954044] R13: 00007ffc72182a98 R14: 00000000006114c0 R15: 00007ffc72182aa0 [ 69.954044] Code: 1f 00 66 66 66 66 90 55 48 89 e5 48 83 ec 20 f6 47 20 04 74 0a 83 fe 1c 74 09 83 fe 1d 74 2c c9 66 90 c3 48 8b 47 10 48 8d 55 e8 <48> 8b 70 08 0f b7 47 1e 48 83 c7 18 48 89 7d f0 bf 03 00 00 00 [ 69.954044] RIP: br_switchdev_fdb_notify+0x29/0x80 RSP: ffffc90001567918 [ 69.954044] CR2: 0000000000000008 [ 69.954044] ---[ end trace 03e9eec4a82c238b ]--- Fixes: 6b26b51b1d13 ("net: bridge: Add support for notifying devices about FDB add/del") Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-27 12:13:48 +08:00
if (!fdb->added_by_user || !fdb->dst)
return;
switch (type) {
case RTM_DELNEIGH:
br_switchdev_fdb_call_notifiers(false, fdb->addr.addr,
fdb->vlan_id,
fdb->dst->dev);
break;
case RTM_NEWNEIGH:
br_switchdev_fdb_call_notifiers(true, fdb->addr.addr,
fdb->vlan_id,
fdb->dst->dev);
break;
}
}