From: Haiyang Zhang haiyangz@microsoft.com
The existing code move the VF NIC to new namespace when NETDEV_REGISTER is received on netvsc NIC. During deletion of the namespace, default_device_exit_batch() >> default_device_exit_net() is called. When netvsc NIC is moved back and registered to the default namespace, it automatically brings VF NIC back to the default namespace. This will cause the default_device_exit_net() >> for_each_netdev_safe loop unable to detect the list end, and hit NULL ptr:
[ 231.449420] mana 7870:00:00.0 enP30832s1: Moved VF to namespace with: eth0 [ 231.449656] BUG: kernel NULL pointer dereference, address: 0000000000000010 [ 231.450246] #PF: supervisor read access in kernel mode [ 231.450579] #PF: error_code(0x0000) - not-present page [ 231.450916] PGD 17b8a8067 P4D 0 [ 231.451163] Oops: Oops: 0000 [#1] SMP NOPTI [ 231.451450] CPU: 82 UID: 0 PID: 1394 Comm: kworker/u768:1 Not tainted 6.16.0-rc4+ #3 VOLUNTARY [ 231.452042] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 11/21/2024 [ 231.452692] Workqueue: netns cleanup_net [ 231.452947] RIP: 0010:default_device_exit_batch+0x16c/0x3f0 [ 231.453326] Code: c0 0c f5 b3 e8 d5 db fe ff 48 85 c0 74 15 48 c7 c2 f8 fd ca b2 be 10 00 00 00 48 8d 7d c0 e8 7b 77 25 00 49 8b 86 28 01 00 00 <48> 8b 50 10 4c 8b 2a 4c 8d 62 f0 49 83 ed 10 4c 39 e0 0f 84 d6 00 [ 231.454294] RSP: 0018:ff75fc7c9bf9fd00 EFLAGS: 00010246 [ 231.454610] RAX: 0000000000000000 RBX: 0000000000000002 RCX: 61c8864680b583eb [ 231.455094] RDX: ff1fa9f71462d800 RSI: ff75fc7c9bf9fd38 RDI: 0000000030766564 [ 231.455686] RBP: ff75fc7c9bf9fd78 R08: 0000000000000000 R09: 0000000000000000 [ 231.456126] R10: 0000000000000001 R11: 0000000000000004 R12: ff1fa9f70088e340 [ 231.456621] R13: ff1fa9f70088e340 R14: ffffffffb3f50c20 R15: ff1fa9f7103e6340 [ 231.457161] FS: 0000000000000000(0000) GS:ff1faa6783a08000(0000) knlGS:0000000000000000 [ 231.457707] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 231.458031] CR2: 0000000000000010 CR3: 0000000179ab2006 CR4: 0000000000b73ef0 [ 231.458434] Call Trace: [ 231.458600] <TASK> [ 231.458777] ops_undo_list+0x100/0x220 [ 231.459015] cleanup_net+0x1b8/0x300 [ 231.459285] process_one_work+0x184/0x340
To fix it, move the ns change to a workqueue, and take rtnl_lock to avoid changing the netdev list when default_device_exit_net() is using it.
Cc: stable@vger.kernel.org Fixes: 4c262801ea60 ("hv_netvsc: Fix VF namespace also in synthetic NIC NETDEV_REGISTER event") Signed-off-by: Haiyang Zhang haiyangz@microsoft.com
--- v2: Moved the ns change to a workqueue as suggested by Jakub Kicinski.
--- drivers/net/hyperv/hyperv_net.h | 3 +++ drivers/net/hyperv/netvsc_drv.c | 29 ++++++++++++++++++++++++++++- 2 files changed, 31 insertions(+), 1 deletion(-)
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index cb6f5482d203..7397c693f984 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -1061,6 +1061,7 @@ struct net_device_context { struct net_device __rcu *vf_netdev; struct netvsc_vf_pcpu_stats __percpu *vf_stats; struct delayed_work vf_takeover; + struct delayed_work vfns_work;
/* 1: allocated, serial number is valid. 0: not allocated */ u32 vf_alloc; @@ -1075,6 +1076,8 @@ struct net_device_context { struct netvsc_device_info *saved_netvsc_dev_info; };
+void netvsc_vfns_work(struct work_struct *w); + /* Azure hosts don't support non-TCP port numbers in hashing for fragmented * packets. We can use ethtool to change UDP hash level when necessary. */ diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f44753756358..39c892e46cb0 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2522,6 +2522,7 @@ static int netvsc_probe(struct hv_device *dev, spin_lock_init(&net_device_ctx->lock); INIT_LIST_HEAD(&net_device_ctx->reconfig_events); INIT_DELAYED_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup); + INIT_DELAYED_WORK(&net_device_ctx->vfns_work, netvsc_vfns_work);
net_device_ctx->vf_stats = netdev_alloc_pcpu_stats(struct netvsc_vf_pcpu_stats); @@ -2666,6 +2667,8 @@ static void netvsc_remove(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork);
rtnl_lock(); + cancel_delayed_work_sync(&ndev_ctx->vfns_work); + nvdev = rtnl_dereference(ndev_ctx->nvdev); if (nvdev) { cancel_work_sync(&nvdev->subchan_work); @@ -2707,6 +2710,7 @@ static int netvsc_suspend(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork);
rtnl_lock(); + cancel_delayed_work_sync(&ndev_ctx->vfns_work);
nvdev = rtnl_dereference(ndev_ctx->nvdev); if (nvdev == NULL) { @@ -2800,6 +2804,27 @@ static void netvsc_event_set_vf_ns(struct net_device *ndev) } }
+void netvsc_vfns_work(struct work_struct *w) +{ + struct net_device_context *ndev_ctx = + container_of(w, struct net_device_context, vfns_work.work); + struct net_device *ndev; + + if (!rtnl_trylock()) { + schedule_delayed_work(&ndev_ctx->vfns_work, 1); + return; + } + + ndev = hv_get_drvdata(ndev_ctx->device_ctx); + if (!ndev) + goto out; + + netvsc_event_set_vf_ns(ndev); + +out: + rtnl_unlock(); +} + /* * On Hyper-V, every VF interface is matched with a corresponding * synthetic interface. The synthetic interface is presented first @@ -2810,10 +2835,12 @@ static int netvsc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + struct net_device_context *ndev_ctx; int ret = 0;
if (event_dev->netdev_ops == &device_ops && event == NETDEV_REGISTER) { - netvsc_event_set_vf_ns(event_dev); + ndev_ctx = netdev_priv(event_dev); + schedule_delayed_work(&ndev_ctx->vfns_work, 0); return NOTIFY_DONE; }