From e0526ec5360a48ad3ab2e26e802b0532302a7e11 Mon Sep 17 00:00:00 2001 From: Souradeep Chakrabarti Date: Tue, 30 Jan 2024 23:35:51 -0800 Subject: hv_netvsc: Fix race condition between netvsc_probe and netvsc_remove In commit ac5047671758 ("hv_netvsc: Disable NAPI before closing the VMBus channel"), napi_disable was getting called for all channels, including all subchannels without confirming if they are enabled or not. This caused hv_netvsc getting hung at napi_disable, when netvsc_probe() has finished running but nvdev->subchan_work has not started yet. netvsc_subchan_work() -> rndis_set_subchannel() has not created the sub-channels and because of that netvsc_sc_open() is not running. netvsc_remove() calls cancel_work_sync(&nvdev->subchan_work), for which netvsc_subchan_work did not run. netif_napi_add() sets the bit NAPI_STATE_SCHED because it ensures NAPI cannot be scheduled. Then netvsc_sc_open() -> napi_enable will clear the NAPIF_STATE_SCHED bit, so it can be scheduled. napi_disable() does the opposite. Now during netvsc_device_remove(), when napi_disable is called for those subchannels, napi_disable gets stuck on infinite msleep. This fix addresses this problem by ensuring that napi_disable() is not getting called for non-enabled NAPI struct. But netif_napi_del() is still necessary for these non-enabled NAPI struct for cleanup purpose. Call trace: [ 654.559417] task:modprobe state:D stack: 0 pid: 2321 ppid: 1091 flags:0x00004002 [ 654.568030] Call Trace: [ 654.571221] [ 654.573790] __schedule+0x2d6/0x960 [ 654.577733] schedule+0x69/0xf0 [ 654.581214] schedule_timeout+0x87/0x140 [ 654.585463] ? __bpf_trace_tick_stop+0x20/0x20 [ 654.590291] msleep+0x2d/0x40 [ 654.593625] napi_disable+0x2b/0x80 [ 654.597437] netvsc_device_remove+0x8a/0x1f0 [hv_netvsc] [ 654.603935] rndis_filter_device_remove+0x194/0x1c0 [hv_netvsc] [ 654.611101] ? do_wait_intr+0xb0/0xb0 [ 654.615753] netvsc_remove+0x7c/0x120 [hv_netvsc] [ 654.621675] vmbus_remove+0x27/0x40 [hv_vmbus] Cc: stable@vger.kernel.org Fixes: ac5047671758 ("hv_netvsc: Disable NAPI before closing the VMBus channel") Signed-off-by: Souradeep Chakrabarti Reviewed-by: Dexuan Cui Reviewed-by: Haiyang Zhang Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/1706686551-28510-1-git-send-email-schakrabarti@linux.microsoft.com Signed-off-by: Jakub Kicinski --- drivers/net/hyperv/netvsc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/net/hyperv') diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 1dafa44155d0..a6fcbda64ecc 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -708,7 +708,10 @@ void netvsc_device_remove(struct hv_device *device) /* Disable NAPI and disassociate its context from the device. */ for (i = 0; i < net_device->num_chn; i++) { /* See also vmbus_reset_channel_cb(). */ - napi_disable(&net_device->chan_table[i].napi); + /* only disable enabled NAPI channel */ + if (i < ndev->real_num_rx_queues) + napi_disable(&net_device->chan_table[i].napi); + netif_napi_del(&net_device->chan_table[i].napi); } -- cgit v1.2.3-70-g09d2 From 9cae43da9867412f8bd09aee5c8a8dc5e8dc3dc2 Mon Sep 17 00:00:00 2001 From: Shradha Gupta Date: Thu, 1 Feb 2024 20:40:38 -0800 Subject: hv_netvsc: Register VF in netvsc_probe if NET_DEVICE_REGISTER missed If hv_netvsc driver is unloaded and reloaded, the NET_DEVICE_REGISTER handler cannot perform VF register successfully as the register call is received before netvsc_probe is finished. This is because we register register_netdevice_notifier() very early( even before vmbus_driver_register()). To fix this, we try to register each such matching VF( if it is visible as a netdevice) at the end of netvsc_probe. Cc: stable@vger.kernel.org Fixes: 85520856466e ("hv_netvsc: Fix race of register_netdevice_notifier and VF register") Suggested-by: Dexuan Cui Signed-off-by: Shradha Gupta Reviewed-by: Haiyang Zhang Reviewed-by: Dexuan Cui Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc_drv.c | 82 +++++++++++++++++++++++++++++++---------- 1 file changed, 62 insertions(+), 20 deletions(-) (limited to 'drivers/net/hyperv') diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 273bd8a20122..11831a1c9762 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -42,6 +42,10 @@ #define LINKCHANGE_INT (2 * HZ) #define VF_TAKEOVER_INT (HZ / 10) +/* Macros to define the context of vf registration */ +#define VF_REG_IN_PROBE 1 +#define VF_REG_IN_NOTIFIER 2 + static unsigned int ring_size __ro_after_init = 128; module_param(ring_size, uint, 0444); MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)"); @@ -2185,7 +2189,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb) } static int netvsc_vf_join(struct net_device *vf_netdev, - struct net_device *ndev) + struct net_device *ndev, int context) { struct net_device_context *ndev_ctx = netdev_priv(ndev); int ret; @@ -2208,7 +2212,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto upper_link_failed; } - schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); + /* If this registration is called from probe context vf_takeover + * is taken care of later in probe itself. + */ + if (context == VF_REG_IN_NOTIFIER) + schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); call_netdevice_notifiers(NETDEV_JOIN, vf_netdev); @@ -2346,7 +2354,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev) return NOTIFY_DONE; } -static int netvsc_register_vf(struct net_device *vf_netdev) +static int netvsc_register_vf(struct net_device *vf_netdev, int context) { struct net_device_context *net_device_ctx; struct netvsc_device *netvsc_dev; @@ -2386,7 +2394,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev) netdev_info(ndev, "VF registering: %s\n", vf_netdev->name); - if (netvsc_vf_join(vf_netdev, ndev) != 0) + if (netvsc_vf_join(vf_netdev, ndev, context) != 0) return NOTIFY_DONE; dev_hold(vf_netdev); @@ -2484,10 +2492,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) return NOTIFY_OK; } +static int check_dev_is_matching_vf(struct net_device *event_ndev) +{ + /* Skip NetVSC interfaces */ + if (event_ndev->netdev_ops == &device_ops) + return -ENODEV; + + /* Avoid non-Ethernet type devices */ + if (event_ndev->type != ARPHRD_ETHER) + return -ENODEV; + + /* Avoid Vlan dev with same MAC registering as VF */ + if (is_vlan_dev(event_ndev)) + return -ENODEV; + + /* Avoid Bonding master dev with same MAC registering as VF */ + if (netif_is_bond_master(event_ndev)) + return -ENODEV; + + return 0; +} + static int netvsc_probe(struct hv_device *dev, const struct hv_vmbus_device_id *dev_id) { - struct net_device *net = NULL; + struct net_device *net = NULL, *vf_netdev; struct net_device_context *net_device_ctx; struct netvsc_device_info *device_info = NULL; struct netvsc_device *nvdev; @@ -2599,6 +2628,30 @@ static int netvsc_probe(struct hv_device *dev, } list_add(&net_device_ctx->list, &netvsc_dev_list); + + /* When the hv_netvsc driver is unloaded and reloaded, the + * NET_DEVICE_REGISTER for the vf device is replayed before probe + * is complete. This is because register_netdevice_notifier() gets + * registered before vmbus_driver_register() so that callback func + * is set before probe and we don't miss events like NETDEV_POST_INIT + * So, in this section we try to register the matching vf device that + * is present as a netdevice, knowing that its register call is not + * processed in the netvsc_netdev_notifier(as probing is progress and + * get_netvsc_byslot fails). + */ + for_each_netdev(dev_net(net), vf_netdev) { + ret = check_dev_is_matching_vf(vf_netdev); + if (ret != 0) + continue; + + if (net != get_netvsc_byslot(vf_netdev)) + continue; + + netvsc_prepare_bonding(vf_netdev); + netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE); + __netvsc_vf_setup(net, vf_netdev); + break; + } rtnl_unlock(); netvsc_devinfo_put(device_info); @@ -2754,28 +2807,17 @@ 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); + int ret = 0; - /* Skip our own events */ - if (event_dev->netdev_ops == &device_ops) - return NOTIFY_DONE; - - /* Avoid non-Ethernet type devices */ - if (event_dev->type != ARPHRD_ETHER) - return NOTIFY_DONE; - - /* Avoid Vlan dev with same MAC registering as VF */ - if (is_vlan_dev(event_dev)) - return NOTIFY_DONE; - - /* Avoid Bonding master dev with same MAC registering as VF */ - if (netif_is_bond_master(event_dev)) + ret = check_dev_is_matching_vf(event_dev); + if (ret != 0) return NOTIFY_DONE; switch (event) { case NETDEV_POST_INIT: return netvsc_prepare_bonding(event_dev); case NETDEV_REGISTER: - return netvsc_register_vf(event_dev); + return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER); case NETDEV_UNREGISTER: return netvsc_unregister_vf(event_dev); case NETDEV_UP: -- cgit v1.2.3-70-g09d2