4.14-stable review patch. If anyone has any objections, please let me know. ------------------ From: Stephen Hemminger <stephen@xxxxxxxxxxxxxxxxxx> [ Commit 7b2ee50c0cd513a176a26a71f2989facdd75bfea upstream. ] Make common function for detaching internals of device during changes to MTU and RSS. Make sure no more packets are transmitted and all packets have been received before doing device teardown. Change the wait logic to be common and use usleep_range(). Changes transmit enabling logic so that transmit queues are disabled during the period when lower device is being changed. And enabled only after sub channels are setup. This avoids issue where it could be that a packet was being sent while subchannel was not initialized. Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug") Signed-off-by: Stephen Hemminger <sthemmin@xxxxxxxxxxxxx> Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/net/hyperv/hyperv_net.h | 1 drivers/net/hyperv/netvsc.c | 21 +- drivers/net/hyperv/netvsc_drv.c | 280 +++++++++++++++++++++----------------- drivers/net/hyperv/rndis_filter.c | 15 -- 4 files changed, 175 insertions(+), 142 deletions(-) --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -208,7 +208,6 @@ void netvsc_channel_cb(void *context); int netvsc_poll(struct napi_struct *napi, int budget); void rndis_set_subchannel(struct work_struct *w); -bool rndis_filter_opened(const struct netvsc_device *nvdev); int rndis_filter_open(struct netvsc_device *nvdev); int rndis_filter_close(struct netvsc_device *nvdev); struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -554,8 +554,6 @@ void netvsc_device_remove(struct hv_devi = rtnl_dereference(net_device_ctx->nvdev); int i; - cancel_work_sync(&net_device->subchan_work); - netvsc_revoke_buf(device, net_device); RCU_INIT_POINTER(net_device_ctx->nvdev, NULL); @@ -644,13 +642,18 @@ static void netvsc_send_tx_complete(stru queue_sends = atomic_dec_return(&net_device->chan_table[q_idx].queue_sends); - if (net_device->destroy && queue_sends == 0) - wake_up(&net_device->wait_drain); - - if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) && - (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER || - queue_sends < 1)) - netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx)); + if (unlikely(net_device->destroy)) { + if (queue_sends == 0) + wake_up(&net_device->wait_drain); + } else { + struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx); + + if (netif_tx_queue_stopped(txq) && + (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER || + queue_sends < 1)) { + netif_tx_wake_queue(txq); + } + } } static void netvsc_send_completion(struct netvsc_device *net_device, --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -45,7 +45,10 @@ #include "hyperv_net.h" -#define RING_SIZE_MIN 64 +#define RING_SIZE_MIN 64 +#define RETRY_US_LO 5000 +#define RETRY_US_HI 10000 +#define RETRY_MAX 2000 /* >10 sec */ #define LINKCHANGE_INT (2 * HZ) #define VF_TAKEOVER_INT (HZ / 10) @@ -89,10 +92,8 @@ static int netvsc_open(struct net_device } rdev = nvdev->extension; - if (!rdev->link_state) { + if (!rdev->link_state) netif_carrier_on(net); - netif_tx_wake_all_queues(net); - } if (vf_netdev) { /* Setting synthetic device up transparently sets @@ -108,36 +109,25 @@ static int netvsc_open(struct net_device return 0; } -static int netvsc_close(struct net_device *net) +static int netvsc_wait_until_empty(struct netvsc_device *nvdev) { - struct net_device_context *net_device_ctx = netdev_priv(net); - struct net_device *vf_netdev - = rtnl_dereference(net_device_ctx->vf_netdev); - struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); - int ret = 0; - u32 aread, i, msec = 10, retry = 0, retry_max = 20; - struct vmbus_channel *chn; - - netif_tx_disable(net); - - /* No need to close rndis filter if it is removed already */ - if (!nvdev) - goto out; - - ret = rndis_filter_close(nvdev); - if (ret != 0) { - netdev_err(net, "unable to close device (ret %d).\n", ret); - return ret; - } + unsigned int retry = 0; + int i; /* Ensure pending bytes in ring are read */ - while (true) { - aread = 0; + for (;;) { + u32 aread = 0; + for (i = 0; i < nvdev->num_chn; i++) { - chn = nvdev->chan_table[i].channel; + struct vmbus_channel *chn + = nvdev->chan_table[i].channel; + if (!chn) continue; + /* make sure receive not running now */ + napi_synchronize(&nvdev->chan_table[i].napi); + aread = hv_get_bytes_to_read(&chn->inbound); if (aread) break; @@ -147,22 +137,40 @@ static int netvsc_close(struct net_devic break; } - retry++; - if (retry > retry_max || aread == 0) - break; + if (aread == 0) + return 0; - msleep(msec); + if (++retry > RETRY_MAX) + return -ETIMEDOUT; - if (msec < 1000) - msec *= 2; + usleep_range(RETRY_US_LO, RETRY_US_HI); } +} - if (aread) { - netdev_err(net, "Ring buffer not empty after closing rndis\n"); - ret = -ETIMEDOUT; +static int netvsc_close(struct net_device *net) +{ + struct net_device_context *net_device_ctx = netdev_priv(net); + struct net_device *vf_netdev + = rtnl_dereference(net_device_ctx->vf_netdev); + struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); + int ret; + + netif_tx_disable(net); + + /* No need to close rndis filter if it is removed already */ + if (!nvdev) + return 0; + + ret = rndis_filter_close(nvdev); + if (ret != 0) { + netdev_err(net, "unable to close device (ret %d).\n", ret); + return ret; } -out: + ret = netvsc_wait_until_empty(nvdev); + if (ret) + netdev_err(net, "Ring buffer not empty after closing rndis\n"); + if (vf_netdev) dev_close(vf_netdev); @@ -820,16 +828,81 @@ static void netvsc_get_channels(struct n } } +static int netvsc_detach(struct net_device *ndev, + struct netvsc_device *nvdev) +{ + struct net_device_context *ndev_ctx = netdev_priv(ndev); + struct hv_device *hdev = ndev_ctx->device_ctx; + int ret; + + /* Don't try continuing to try and setup sub channels */ + if (cancel_work_sync(&nvdev->subchan_work)) + nvdev->num_chn = 1; + + /* If device was up (receiving) then shutdown */ + if (netif_running(ndev)) { + netif_tx_disable(ndev); + + ret = rndis_filter_close(nvdev); + if (ret) { + netdev_err(ndev, + "unable to close device (ret %d).\n", ret); + return ret; + } + + ret = netvsc_wait_until_empty(nvdev); + if (ret) { + netdev_err(ndev, + "Ring buffer not empty after closing rndis\n"); + return ret; + } + } + + netif_device_detach(ndev); + + rndis_filter_device_remove(hdev, nvdev); + + return 0; +} + +static int netvsc_attach(struct net_device *ndev, + struct netvsc_device_info *dev_info) +{ + struct net_device_context *ndev_ctx = netdev_priv(ndev); + struct hv_device *hdev = ndev_ctx->device_ctx; + struct netvsc_device *nvdev; + struct rndis_device *rdev; + int ret; + + nvdev = rndis_filter_device_add(hdev, dev_info); + if (IS_ERR(nvdev)) + return PTR_ERR(nvdev); + + /* Note: enable and attach happen when sub-channels setup */ + + netif_carrier_off(ndev); + + if (netif_running(ndev)) { + ret = rndis_filter_open(nvdev); + if (ret) + return ret; + + rdev = nvdev->extension; + if (!rdev->link_state) + netif_carrier_on(ndev); + } + + return 0; +} + static int netvsc_set_channels(struct net_device *net, struct ethtool_channels *channels) { struct net_device_context *net_device_ctx = netdev_priv(net); - struct hv_device *dev = net_device_ctx->device_ctx; struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); unsigned int orig, count = channels->combined_count; struct netvsc_device_info device_info; - bool was_opened; - int ret = 0; + int ret; /* We do not support separate count for rx, tx, or other */ if (count == 0 || @@ -846,9 +919,6 @@ static int netvsc_set_channels(struct ne return -EINVAL; orig = nvdev->num_chn; - was_opened = rndis_filter_opened(nvdev); - if (was_opened) - rndis_filter_close(nvdev); memset(&device_info, 0, sizeof(device_info)); device_info.num_chn = count; @@ -858,28 +928,17 @@ static int netvsc_set_channels(struct ne device_info.recv_sections = nvdev->recv_section_cnt; device_info.recv_section_size = nvdev->recv_section_size; - rndis_filter_device_remove(dev, nvdev); + ret = netvsc_detach(net, nvdev); + if (ret) + return ret; - nvdev = rndis_filter_device_add(dev, &device_info); - if (IS_ERR(nvdev)) { - ret = PTR_ERR(nvdev); + ret = netvsc_attach(net, &device_info); + if (ret) { device_info.num_chn = orig; - nvdev = rndis_filter_device_add(dev, &device_info); - - if (IS_ERR(nvdev)) { - netdev_err(net, "restoring channel setting failed: %ld\n", - PTR_ERR(nvdev)); - return ret; - } + if (netvsc_attach(net, &device_info)) + netdev_err(net, "restoring channel setting failed\n"); } - if (was_opened) - rndis_filter_open(nvdev); - - /* We may have missed link change notifications */ - net_device_ctx->last_reconfig = 0; - schedule_delayed_work(&net_device_ctx->dwork, 0); - return ret; } @@ -946,10 +1005,8 @@ static int netvsc_change_mtu(struct net_ struct net_device_context *ndevctx = netdev_priv(ndev); struct net_device *vf_netdev = rtnl_dereference(ndevctx->vf_netdev); struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev); - struct hv_device *hdev = ndevctx->device_ctx; int orig_mtu = ndev->mtu; struct netvsc_device_info device_info; - bool was_opened; int ret = 0; if (!nvdev || nvdev->destroy) @@ -962,11 +1019,6 @@ static int netvsc_change_mtu(struct net_ return ret; } - netif_device_detach(ndev); - was_opened = rndis_filter_opened(nvdev); - if (was_opened) - rndis_filter_close(nvdev); - memset(&device_info, 0, sizeof(device_info)); device_info.ring_size = ring_size; device_info.num_chn = nvdev->num_chn; @@ -975,35 +1027,27 @@ static int netvsc_change_mtu(struct net_ device_info.recv_sections = nvdev->recv_section_cnt; device_info.recv_section_size = nvdev->recv_section_size; - rndis_filter_device_remove(hdev, nvdev); + ret = netvsc_detach(ndev, nvdev); + if (ret) + goto rollback_vf; ndev->mtu = mtu; - nvdev = rndis_filter_device_add(hdev, &device_info); - if (IS_ERR(nvdev)) { - ret = PTR_ERR(nvdev); - - /* Attempt rollback to original MTU */ - ndev->mtu = orig_mtu; - nvdev = rndis_filter_device_add(hdev, &device_info); - - if (vf_netdev) - dev_set_mtu(vf_netdev, orig_mtu); - - if (IS_ERR(nvdev)) { - netdev_err(ndev, "restoring mtu failed: %ld\n", - PTR_ERR(nvdev)); - return ret; - } - } - - if (was_opened) - rndis_filter_open(nvdev); + ret = netvsc_attach(ndev, &device_info); + if (ret) + goto rollback; - netif_device_attach(ndev); + return 0; - /* We may have missed link change notifications */ - schedule_delayed_work(&ndevctx->dwork, 0); +rollback: + /* Attempt rollback to original MTU */ + ndev->mtu = orig_mtu; + + if (netvsc_attach(ndev, &device_info)) + netdev_err(ndev, "restoring mtu failed\n"); +rollback_vf: + if (vf_netdev) + dev_set_mtu(vf_netdev, orig_mtu); return ret; } @@ -1469,11 +1513,9 @@ static int netvsc_set_ringparam(struct n { struct net_device_context *ndevctx = netdev_priv(ndev); struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev); - struct hv_device *hdev = ndevctx->device_ctx; struct netvsc_device_info device_info; struct ethtool_ringparam orig; u32 new_tx, new_rx; - bool was_opened; int ret = 0; if (!nvdev || nvdev->destroy) @@ -1499,34 +1541,18 @@ static int netvsc_set_ringparam(struct n device_info.recv_sections = new_rx; device_info.recv_section_size = nvdev->recv_section_size; - netif_device_detach(ndev); - was_opened = rndis_filter_opened(nvdev); - if (was_opened) - rndis_filter_close(nvdev); - - rndis_filter_device_remove(hdev, nvdev); - - nvdev = rndis_filter_device_add(hdev, &device_info); - if (IS_ERR(nvdev)) { - ret = PTR_ERR(nvdev); + ret = netvsc_detach(ndev, nvdev); + if (ret) + return ret; + ret = netvsc_attach(ndev, &device_info); + if (ret) { device_info.send_sections = orig.tx_pending; device_info.recv_sections = orig.rx_pending; - nvdev = rndis_filter_device_add(hdev, &device_info); - if (IS_ERR(nvdev)) { - netdev_err(ndev, "restoring ringparam failed: %ld\n", - PTR_ERR(nvdev)); - return ret; - } - } - if (was_opened) - rndis_filter_open(nvdev); - netif_device_attach(ndev); - - /* We may have missed link change notifications */ - ndevctx->last_reconfig = 0; - schedule_delayed_work(&ndevctx->dwork, 0); + if (netvsc_attach(ndev, &device_info)) + netdev_err(ndev, "restoring ringparam failed"); + } return ret; } @@ -2003,8 +2029,8 @@ no_net: static int netvsc_remove(struct hv_device *dev) { struct net_device_context *ndev_ctx; - struct net_device *vf_netdev; - struct net_device *net; + struct net_device *vf_netdev, *net; + struct netvsc_device *nvdev; net = hv_get_drvdata(dev); if (net == NULL) { @@ -2014,10 +2040,14 @@ static int netvsc_remove(struct hv_devic ndev_ctx = netdev_priv(net); - netif_device_detach(net); - cancel_delayed_work_sync(&ndev_ctx->dwork); + rcu_read_lock(); + nvdev = rcu_dereference(ndev_ctx->nvdev); + + if (nvdev) + cancel_work_sync(&nvdev->subchan_work); + /* * Call to the vsc driver to let it know that the device is being * removed. Also blocks mtu and channel changes. @@ -2027,11 +2057,13 @@ static int netvsc_remove(struct hv_devic if (vf_netdev) netvsc_unregister_vf(vf_netdev); + if (nvdev) + rndis_filter_device_remove(dev, nvdev); + unregister_netdevice(net); - rndis_filter_device_remove(dev, - rtnl_dereference(ndev_ctx->nvdev)); rtnl_unlock(); + rcu_read_unlock(); hv_set_drvdata(dev, NULL); --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1112,6 +1112,7 @@ void rndis_set_subchannel(struct work_st for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) ndev_ctx->tx_table[i] = i % nvdev->num_chn; + netif_device_attach(ndev); rtnl_unlock(); return; @@ -1122,6 +1123,8 @@ failed: nvdev->max_chn = 1; nvdev->num_chn = 1; + + netif_device_attach(ndev); unlock: rtnl_unlock(); } @@ -1324,6 +1327,10 @@ out: net_device->num_chn = 1; } + /* No sub channels, device is ready */ + if (net_device->num_chn == 1) + netif_device_attach(net); + return net_device; err_dev_remv: @@ -1336,9 +1343,6 @@ void rndis_filter_device_remove(struct h { struct rndis_device *rndis_dev = net_dev->extension; - /* Don't try and setup sub channels if about to halt */ - cancel_work_sync(&net_dev->subchan_work); - /* Halt and release the rndis device */ rndis_filter_halt_device(rndis_dev); @@ -1368,8 +1372,3 @@ int rndis_filter_close(struct netvsc_dev return rndis_filter_close_device(nvdev->extension); } - -bool rndis_filter_opened(const struct netvsc_device *nvdev) -{ - return atomic_read(&nvdev->open_cnt) > 0; -}