Files
android_kernel_fxtec_sm6115/net/openvswitch/vport-netdev.c
Toke Høiland-Jørgensen afdeab486c net: openvswitch: Avoid releasing netdev before teardown completes
[ Upstream commit 7c770dadfda5cbbde6aa3c4363ed513f1d212bf8 ]

The patch cited in the Fixes tag below changed the teardown code for
OVS ports to no longer unconditionally take the RTNL. After this change,
the netdev_destroy() callback can proceed immediately to the call_rcu()
invocation if the IFF_OVS_DATAPATH flag is already cleared on the
netdev.

The ovs_netdev_detach_dev() function clears the flag before completing
the unregistration, and if it gets preempted after clearing the flag (as
can happen on an -rt kernel), netdev_destroy() can complete and the
device can be freed before the unregistration completes. This leads to a
splat like:

[  998.393867] Oops: general protection fault, probably for non-canonical address 0xff00000001000239: 0000 [#1] SMP PTI
[  998.393877] CPU: 42 UID: 0 PID: 55177 Comm: ip Kdump: loaded Not tainted 6.12.0-211.1.1.el10_2.x86_64+rt #1 PREEMPT_RT
[  998.393886] Hardware name: Dell Inc. PowerEdge R740/0JMK61, BIOS 2.24.0 03/27/2025
[  998.393889] RIP: 0010:dev_set_promiscuity+0x8d/0xa0
[  998.393901] Code: 00 00 75 d8 48 8b 53 08 48 83 ba b0 02 00 00 00 75 ca 48 83 c4 08 5b c3 cc cc cc cc 48 83 bf 48 09 00 00 00 75 91 48 8b 47 08 <48> 83 b8 b0 02 00 00 00 74 97 eb 81 0f 1f 80 00 00 00 00 90 90 90
[  998.393906] RSP: 0018:ffffce5864a5f6a0 EFLAGS: 00010246
[  998.393912] RAX: ff00000000ffff89 RBX: ffff894d0adf5a05 RCX: 0000000000000000
[  998.393917] RDX: 0000000000000000 RSI: 00000000ffffffff RDI: ffff894d0adf5a05
[  998.393921] RBP: ffff894d19252000 R08: ffff894d19252000 R09: 0000000000000000
[  998.393924] R10: ffff894d19252000 R11: ffff894d192521b8 R12: 0000000000000006
[  998.393927] R13: ffffce5864a5f738 R14: 00000000ffffffe2 R15: 0000000000000000
[  998.393931] FS:  00007fad61971800(0000) GS:ffff894cc0140000(0000) knlGS:0000000000000000
[  998.393936] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  998.393940] CR2: 000055df0a2a6e40 CR3: 000000011c7fe003 CR4: 00000000007726f0
[  998.393944] PKRU: 55555554
[  998.393946] Call Trace:
[  998.393949]  <TASK>
[  998.393952]  ? show_trace_log_lvl+0x1b0/0x2f0
[  998.393961]  ? show_trace_log_lvl+0x1b0/0x2f0
[  998.393975]  ? dp_device_event+0x41/0x80 [openvswitch]
[  998.394009]  ? __die_body.cold+0x8/0x12
[  998.394016]  ? die_addr+0x3c/0x60
[  998.394027]  ? exc_general_protection+0x16d/0x390
[  998.394042]  ? asm_exc_general_protection+0x26/0x30
[  998.394058]  ? dev_set_promiscuity+0x8d/0xa0
[  998.394066]  ? ovs_netdev_detach_dev+0x3a/0x80 [openvswitch]
[  998.394092]  dp_device_event+0x41/0x80 [openvswitch]
[  998.394102]  notifier_call_chain+0x5a/0xd0
[  998.394106]  unregister_netdevice_many_notify+0x51b/0xa60
[  998.394110]  rtnl_dellink+0x169/0x3e0
[  998.394121]  ? rt_mutex_slowlock.constprop.0+0x95/0xd0
[  998.394125]  rtnetlink_rcv_msg+0x142/0x3f0
[  998.394128]  ? avc_has_perm_noaudit+0x69/0xf0
[  998.394130]  ? __pfx_rtnetlink_rcv_msg+0x10/0x10
[  998.394132]  netlink_rcv_skb+0x50/0x100
[  998.394138]  netlink_unicast+0x292/0x3f0
[  998.394141]  netlink_sendmsg+0x21b/0x470
[  998.394145]  ____sys_sendmsg+0x39d/0x3d0
[  998.394149]  ___sys_sendmsg+0x9a/0xe0
[  998.394156]  __sys_sendmsg+0x7a/0xd0
[  998.394160]  do_syscall_64+0x7f/0x170
[  998.394162]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  998.394165] RIP: 0033:0x7fad61bf4724
[  998.394188] Code: 89 02 b8 ff ff ff ff eb bb 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 80 3d c5 e9 0c 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 89 54 24 1c 48 89
[  998.394189] RSP: 002b:00007ffd7e2f7cb8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
[  998.394191] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007fad61bf4724
[  998.394193] RDX: 0000000000000000 RSI: 00007ffd7e2f7d20 RDI: 0000000000000003
[  998.394194] RBP: 00007ffd7e2f7d90 R08: 0000000000000010 R09: 000000000000003f
[  998.394195] R10: 000055df11558010 R11: 0000000000000202 R12: 00007ffd7e2f8380
[  998.394196] R13: 0000000069b233d7 R14: 000055df0a256040 R15: 0000000000000000
[  998.394200]  </TASK>

To fix this, reorder the operations in ovs_netdev_detach_dev() to only
clear the flag after completing the other operations, and introduce an
smp_wmb() to make the ordering requirement explicit. The smp_wmb() is
paired with a full smp_mb() in netdev_destroy() to make sure the
call_rcu() invocation does not happen before the unregister operations
are visible.

Reported-by: Minxi Hou <mhou@redhat.com>
Tested-by: Minxi Hou <mhou@redhat.com>
Fixes: 549822767630 ("net: openvswitch: Avoid needlessly taking the RTNL on vport destroy")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://patch.msgid.link/20260318155554.1133405-1-toke@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Ulrich Hecht <uli@kernel.org>
2026-05-07 10:55:20 +02:00

233 lines
5.5 KiB
C

/*
* Copyright (c) 2007-2012 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/if_arp.h>
#include <linux/if_bridge.h>
#include <linux/if_vlan.h>
#include <linux/kernel.h>
#include <linux/llc.h>
#include <linux/rtnetlink.h>
#include <linux/skbuff.h>
#include <linux/openvswitch.h>
#include <linux/export.h>
#include <net/ip_tunnels.h>
#include <net/rtnetlink.h>
#include "datapath.h"
#include "vport.h"
#include "vport-internal_dev.h"
#include "vport-netdev.h"
static struct vport_ops ovs_netdev_vport_ops;
/* Must be called with rcu_read_lock. */
static void netdev_port_receive(struct sk_buff *skb)
{
struct vport *vport;
vport = ovs_netdev_get_vport(skb->dev);
if (unlikely(!vport))
goto error;
if (unlikely(skb_warn_if_lro(skb)))
goto error;
/* Make our own copy of the packet. Otherwise we will mangle the
* packet for anyone who came before us (e.g. tcpdump via AF_PACKET).
*/
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(!skb))
return;
if (skb->dev->type == ARPHRD_ETHER) {
skb_push(skb, ETH_HLEN);
skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
}
ovs_vport_receive(vport, skb, skb_tunnel_info(skb));
return;
error:
kfree_skb(skb);
}
/* Called with rcu_read_lock and bottom-halves disabled. */
static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb)
{
struct sk_buff *skb = *pskb;
if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
return RX_HANDLER_PASS;
netdev_port_receive(skb);
return RX_HANDLER_CONSUMED;
}
static struct net_device *get_dpdev(const struct datapath *dp)
{
struct vport *local;
local = ovs_vport_ovsl(dp, OVSP_LOCAL);
BUG_ON(!local);
return local->dev;
}
struct vport *ovs_netdev_link(struct vport *vport, const char *name)
{
int err;
vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), name);
if (!vport->dev) {
err = -ENODEV;
goto error_free_vport;
}
if (vport->dev->flags & IFF_LOOPBACK ||
(vport->dev->type != ARPHRD_ETHER &&
vport->dev->type != ARPHRD_NONE) ||
ovs_is_internal_dev(vport->dev)) {
err = -EINVAL;
goto error_put;
}
rtnl_lock();
err = netdev_master_upper_dev_link(vport->dev,
get_dpdev(vport->dp),
NULL, NULL, NULL);
if (err)
goto error_unlock;
err = netdev_rx_handler_register(vport->dev, netdev_frame_hook,
vport);
if (err)
goto error_master_upper_dev_unlink;
dev_disable_lro(vport->dev);
dev_set_promiscuity(vport->dev, 1);
vport->dev->priv_flags |= IFF_OVS_DATAPATH;
rtnl_unlock();
return vport;
error_master_upper_dev_unlink:
netdev_upper_dev_unlink(vport->dev, get_dpdev(vport->dp));
error_unlock:
rtnl_unlock();
error_put:
dev_put(vport->dev);
error_free_vport:
ovs_vport_free(vport);
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(ovs_netdev_link);
static struct vport *netdev_create(const struct vport_parms *parms)
{
struct vport *vport;
vport = ovs_vport_alloc(0, &ovs_netdev_vport_ops, parms);
if (IS_ERR(vport))
return vport;
return ovs_netdev_link(vport, parms->name);
}
static void vport_netdev_free(struct rcu_head *rcu)
{
struct vport *vport = container_of(rcu, struct vport, rcu);
if (vport->dev)
dev_put(vport->dev);
ovs_vport_free(vport);
}
void ovs_netdev_detach_dev(struct vport *vport)
{
ASSERT_RTNL();
netdev_rx_handler_unregister(vport->dev);
netdev_upper_dev_unlink(vport->dev,
netdev_master_upper_dev_get(vport->dev));
dev_set_promiscuity(vport->dev, -1);
/* paired with smp_mb() in netdev_destroy() */
smp_wmb();
vport->dev->priv_flags &= ~IFF_OVS_DATAPATH;
}
static void netdev_destroy(struct vport *vport)
{
rtnl_lock();
if (vport->dev->priv_flags & IFF_OVS_DATAPATH)
ovs_netdev_detach_dev(vport);
rtnl_unlock();
/* paired with smp_wmb() in ovs_netdev_detach_dev() */
smp_mb();
call_rcu(&vport->rcu, vport_netdev_free);
}
void ovs_netdev_tunnel_destroy(struct vport *vport)
{
rtnl_lock();
if (vport->dev->priv_flags & IFF_OVS_DATAPATH)
ovs_netdev_detach_dev(vport);
/* We can be invoked by both explicit vport deletion and
* underlying netdev deregistration; delete the link only
* if it's not already shutting down.
*/
if (vport->dev->reg_state == NETREG_REGISTERED)
rtnl_delete_link(vport->dev);
dev_put(vport->dev);
vport->dev = NULL;
rtnl_unlock();
call_rcu(&vport->rcu, vport_netdev_free);
}
EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy);
/* Returns null if this device is not attached to a datapath. */
struct vport *ovs_netdev_get_vport(struct net_device *dev)
{
if (likely(dev->priv_flags & IFF_OVS_DATAPATH))
return (struct vport *)
rcu_dereference_rtnl(dev->rx_handler_data);
else
return NULL;
}
static struct vport_ops ovs_netdev_vport_ops = {
.type = OVS_VPORT_TYPE_NETDEV,
.create = netdev_create,
.destroy = netdev_destroy,
.send = dev_queue_xmit,
};
int __init ovs_netdev_init(void)
{
return ovs_vport_ops_register(&ovs_netdev_vport_ops);
}
void ovs_netdev_exit(void)
{
ovs_vport_ops_unregister(&ovs_netdev_vport_ops);
}