From d30fb712e52964f2cf9a9c14cf67078394044837 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Sun, 19 Nov 2023 08:23:41 -0800 Subject: [PATCH] hv_netvsc: fix race of netvsc and VF register_netdevice The rtnl lock also needs to be held before rndis_filter_device_add() which advertises nvsp_2_vsc_capability / sriov bit, and triggers VF NIC offering and registering. If VF NIC finished register_netdev() earlier it may cause name based config failure. To fix this issue, move the call to rtnl_lock() before rndis_filter_device_add(), so VF will be registered later than netvsc / synthetic NIC, and gets a name numbered (ethX) after netvsc. Cc: stable@vger.kernel.org Fixes: e04e7a7bbd4b ("hv_netvsc: Fix a deadlock by getting rtnl lock earlier in netvsc_probe()") Reported-by: Dexuan Cui Signed-off-by: Haiyang Zhang Reviewed-by: Wojciech Drewek Reviewed-by: Simon Horman Reviewed-by: Dexuan Cui Signed-off-by: Paolo Abeni --- drivers/net/hyperv/netvsc_drv.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 3ba3c8fb28a5..5e528a76f5f5 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2531,6 +2531,21 @@ static int netvsc_probe(struct hv_device *dev, goto devinfo_failed; } + /* We must get rtnl lock before scheduling nvdev->subchan_work, + * otherwise netvsc_subchan_work() can get rtnl lock first and wait + * all subchannels to show up, but that may not happen because + * netvsc_probe() can't get rtnl lock and as a result vmbus_onoffer() + * -> ... -> device_add() -> ... -> __device_attach() can't get + * the device lock, so all the subchannels can't be processed -- + * finally netvsc_subchan_work() hangs forever. + * + * The rtnl lock also needs to be held before rndis_filter_device_add() + * which advertises nvsp_2_vsc_capability / sriov bit, and triggers + * VF NIC offering and registering. If VF NIC finished register_netdev() + * earlier it may cause name based config failure. + */ + rtnl_lock(); + nvdev = rndis_filter_device_add(dev, device_info); if (IS_ERR(nvdev)) { ret = PTR_ERR(nvdev); @@ -2540,16 +2555,6 @@ static int netvsc_probe(struct hv_device *dev, eth_hw_addr_set(net, device_info->mac_adr); - /* We must get rtnl lock before scheduling nvdev->subchan_work, - * otherwise netvsc_subchan_work() can get rtnl lock first and wait - * all subchannels to show up, but that may not happen because - * netvsc_probe() can't get rtnl lock and as a result vmbus_onoffer() - * -> ... -> device_add() -> ... -> __device_attach() can't get - * the device lock, so all the subchannels can't be processed -- - * finally netvsc_subchan_work() hangs forever. - */ - rtnl_lock(); - if (nvdev->num_chn > 1) schedule_work(&nvdev->subchan_work); @@ -2586,9 +2591,9 @@ static int netvsc_probe(struct hv_device *dev, return 0; register_failed: - rtnl_unlock(); rndis_filter_device_remove(dev, nvdev); rndis_failed: + rtnl_unlock(); netvsc_devinfo_put(device_info); devinfo_failed: free_percpu(net_device_ctx->vf_stats);