--- zzzz-none-000/linux-3.10.107/drivers/net/xen-netback/interface.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/net/xen-netback/interface.c 2021-02-04 17:41:59.000000000 +0000 @@ -30,84 +30,159 @@ #include "common.h" +#include #include #include #include +#include #include #include +#include #define XENVIF_QUEUE_LENGTH 32 +#define XENVIF_NAPI_WEIGHT 64 -void xenvif_get(struct xenvif *vif) -{ - atomic_inc(&vif->refcnt); -} +/* Number of bytes allowed on the internal guest Rx queue. */ +#define XENVIF_RX_QUEUE_BYTES (XEN_NETIF_RX_RING_SIZE/2 * PAGE_SIZE) -void xenvif_get_rings(struct xenvif *vif) +/* This function is used to set SKBTX_DEV_ZEROCOPY as well as + * increasing the inflight counter. We need to increase the inflight + * counter because core driver calls into xenvif_zerocopy_callback + * which calls xenvif_skb_zerocopy_complete. + */ +void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue, + struct sk_buff *skb) { - atomic_inc(&vif->ring_refcnt); + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + atomic_inc(&queue->inflight_packets); } -void xenvif_put(struct xenvif *vif) +void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue) { - if (atomic_dec_and_test(&vif->refcnt)) - wake_up(&vif->waiting_to_free); + atomic_dec(&queue->inflight_packets); + + /* Wake the dealloc thread _after_ decrementing inflight_packets so + * that if kthread_stop() has already been called, the dealloc thread + * does not wait forever with nothing to wake it. + */ + wake_up(&queue->dealloc_wq); } -void xenvif_put_rings(struct xenvif *vif) +int xenvif_schedulable(struct xenvif *vif) { - if (atomic_dec_and_test(&vif->ring_refcnt)) - wake_up(&vif->waiting_to_unmap); + return netif_running(vif->dev) && + test_bit(VIF_STATUS_CONNECTED, &vif->status) && + !vif->disabled; } -int xenvif_schedulable(struct xenvif *vif) +static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id) { - return netif_running(vif->dev) && netif_carrier_ok(vif->dev); + struct xenvif_queue *queue = dev_id; + + if (RING_HAS_UNCONSUMED_REQUESTS(&queue->tx)) + napi_schedule(&queue->napi); + + return IRQ_HANDLED; } -static int xenvif_rx_schedulable(struct xenvif *vif) +static int xenvif_poll(struct napi_struct *napi, int budget) { - return xenvif_schedulable(vif) && !xen_netbk_rx_ring_full(vif); + struct xenvif_queue *queue = + container_of(napi, struct xenvif_queue, napi); + int work_done; + + /* This vif is rogue, we pretend we've there is nothing to do + * for this vif to deschedule it from NAPI. But this interface + * will be turned off in thread context later. + */ + if (unlikely(queue->vif->disabled)) { + napi_complete(napi); + return 0; + } + + work_done = xenvif_tx_action(queue, budget); + + if (work_done < budget) { + napi_complete(napi); + xenvif_napi_schedule_or_enable_events(queue); + } + + return work_done; } -static irqreturn_t xenvif_interrupt(int irq, void *dev_id) +static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id) { - struct xenvif *vif = dev_id; + struct xenvif_queue *queue = dev_id; - if (vif->netbk == NULL) - return IRQ_NONE; + xenvif_kick_thread(queue); - xen_netbk_schedule_xenvif(vif); + return IRQ_HANDLED; +} - if (xenvif_rx_schedulable(vif)) - netif_wake_queue(vif->dev); +irqreturn_t xenvif_interrupt(int irq, void *dev_id) +{ + xenvif_tx_interrupt(irq, dev_id); + xenvif_rx_interrupt(irq, dev_id); return IRQ_HANDLED; } +int xenvif_queue_stopped(struct xenvif_queue *queue) +{ + struct net_device *dev = queue->vif->dev; + unsigned int id = queue->id; + return netif_tx_queue_stopped(netdev_get_tx_queue(dev, id)); +} + +void xenvif_wake_queue(struct xenvif_queue *queue) +{ + struct net_device *dev = queue->vif->dev; + unsigned int id = queue->id; + netif_tx_wake_queue(netdev_get_tx_queue(dev, id)); +} + static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + u16 index; + struct xenvif_rx_cb *cb; BUG_ON(skb->dev != dev); - if (vif->netbk == NULL) + /* Drop the packet if queues are not set up */ + if (num_queues < 1) goto drop; - /* Drop the packet if the target domain has no receive buffers. */ - if (!xenvif_rx_schedulable(vif)) + /* Obtain the queue to be used to transmit this packet */ + index = skb_get_queue_mapping(skb); + if (index >= num_queues) { + pr_warn_ratelimited("Invalid queue %hu for packet on interface %s\n.", + index, vif->dev->name); + index %= num_queues; + } + queue = &vif->queues[index]; + + /* Drop the packet if queue is not ready */ + if (queue->task == NULL || + queue->dealloc_task == NULL || + !xenvif_schedulable(vif)) goto drop; - /* Reserve ring slots for the worst-case number of fragments. */ - vif->rx_req_cons_peek += xen_netbk_count_skb_slots(vif, skb); - xenvif_get(vif); - xenvif_get_rings(vif); + if (vif->multicast_control && skb->pkt_type == PACKET_MULTICAST) { + struct ethhdr *eth = (struct ethhdr *)skb->data; + + if (!xenvif_mcast_match(vif, eth->h_dest)) + goto drop; + } - if (vif->can_queue && xen_netbk_must_stop_queue(vif)) - netif_stop_queue(dev); + cb = XENVIF_RX_CB(skb); + cb->expires = jiffies + vif->drain_timeout; - xen_netbk_queue_tx_skb(vif, skb); + xenvif_rx_queue_tail(queue, skb); + xenvif_kick_thread(queue); return NETDEV_TX_OK; @@ -117,53 +192,85 @@ return NETDEV_TX_OK; } -void xenvif_receive_skb(struct xenvif *vif, struct sk_buff *skb) -{ - netif_rx_ni(skb); -} - -void xenvif_notify_tx_completion(struct xenvif *vif) -{ - if (netif_queue_stopped(vif->dev) && xenvif_rx_schedulable(vif)) - netif_wake_queue(vif->dev); -} - static struct net_device_stats *xenvif_get_stats(struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + unsigned long rx_bytes = 0; + unsigned long rx_packets = 0; + unsigned long tx_bytes = 0; + unsigned long tx_packets = 0; + unsigned int index; + + if (vif->queues == NULL) + goto out; + + /* Aggregate tx and rx stats from each queue */ + for (index = 0; index < num_queues; ++index) { + queue = &vif->queues[index]; + rx_bytes += queue->stats.rx_bytes; + rx_packets += queue->stats.rx_packets; + tx_bytes += queue->stats.tx_bytes; + tx_packets += queue->stats.tx_packets; + } + +out: + vif->dev->stats.rx_bytes = rx_bytes; + vif->dev->stats.rx_packets = rx_packets; + vif->dev->stats.tx_bytes = tx_bytes; + vif->dev->stats.tx_packets = tx_packets; + return &vif->dev->stats; } static void xenvif_up(struct xenvif *vif) { - xen_netbk_add_xenvif(vif); - enable_irq(vif->irq); - xen_netbk_check_rx_xenvif(vif); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + unsigned int queue_index; + + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + napi_enable(&queue->napi); + enable_irq(queue->tx_irq); + if (queue->tx_irq != queue->rx_irq) + enable_irq(queue->rx_irq); + xenvif_napi_schedule_or_enable_events(queue); + } } static void xenvif_down(struct xenvif *vif) { - disable_irq(vif->irq); - del_timer_sync(&vif->credit_timeout); - xen_netbk_deschedule_xenvif(vif); - xen_netbk_remove_xenvif(vif); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + unsigned int queue_index; + + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + disable_irq(queue->tx_irq); + if (queue->tx_irq != queue->rx_irq) + disable_irq(queue->rx_irq); + napi_disable(&queue->napi); + del_timer_sync(&queue->credit_timeout); + } } static int xenvif_open(struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); - if (netif_carrier_ok(dev)) + if (test_bit(VIF_STATUS_CONNECTED, &vif->status)) xenvif_up(vif); - netif_start_queue(dev); + netif_tx_start_all_queues(dev); return 0; } static int xenvif_close(struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); - if (netif_carrier_ok(dev)) + if (test_bit(VIF_STATUS_CONNECTED, &vif->status)) xenvif_down(vif); - netif_stop_queue(dev); + netif_tx_stop_all_queues(dev); return 0; } @@ -185,10 +292,14 @@ if (!vif->can_sg) features &= ~NETIF_F_SG; - if (!vif->gso && !vif->gso_prefix) + if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV4)) features &= ~NETIF_F_TSO; - if (!vif->csum) + if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV6)) + features &= ~NETIF_F_TSO6; + if (!vif->ip_csum) features &= ~NETIF_F_IP_CSUM; + if (!vif->ipv6_csum) + features &= ~NETIF_F_IPV6_CSUM; return features; } @@ -199,7 +310,29 @@ } xenvif_stats[] = { { "rx_gso_checksum_fixup", - offsetof(struct xenvif, rx_gso_checksum_fixup) + offsetof(struct xenvif_stats, rx_gso_checksum_fixup) + }, + /* If (sent != success + fail), there are probably packets never + * freed up properly! + */ + { + "tx_zerocopy_sent", + offsetof(struct xenvif_stats, tx_zerocopy_sent), + }, + { + "tx_zerocopy_success", + offsetof(struct xenvif_stats, tx_zerocopy_success), + }, + { + "tx_zerocopy_fail", + offsetof(struct xenvif_stats, tx_zerocopy_fail) + }, + /* Number of packets exceeding MAX_SKB_FRAG slots. You should use + * a guest with the same MAX_SKB_FRAG + */ + { + "tx_frag_overflow", + offsetof(struct xenvif_stats, tx_frag_overflow) }, }; @@ -216,11 +349,19 @@ static void xenvif_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 * data) { - void *vif = netdev_priv(dev); + struct xenvif *vif = netdev_priv(dev); + unsigned int num_queues = vif->num_queues; int i; + unsigned int queue_index; - for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) - data[i] = *(unsigned long *)(vif + xenvif_stats[i].offset); + for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) { + unsigned long accum = 0; + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + void *vif_stats = &vif->queues[queue_index].stats; + accum += *(unsigned long *)(vif_stats + xenvif_stats[i].offset); + } + data[i] = accum; + } } static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data) @@ -264,36 +405,43 @@ char name[IFNAMSIZ] = {}; snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle); - dev = alloc_netdev(sizeof(struct xenvif), name, ether_setup); + /* Allocate a netdev with the max. supported number of queues. + * When the guest selects the desired number, it will be updated + * via netif_set_real_num_*_queues(). + */ + dev = alloc_netdev_mq(sizeof(struct xenvif), name, NET_NAME_UNKNOWN, + ether_setup, xenvif_max_queues); if (dev == NULL) { - pr_warn("Could not allocate netdev\n"); + pr_warn("Could not allocate netdev for %s\n", name); return ERR_PTR(-ENOMEM); } SET_NETDEV_DEV(dev, parent); vif = netdev_priv(dev); + vif->domid = domid; vif->handle = handle; - vif->netbk = NULL; vif->can_sg = 1; - vif->csum = 1; - atomic_set(&vif->refcnt, 1); - init_waitqueue_head(&vif->waiting_to_free); + vif->ip_csum = 1; vif->dev = dev; - INIT_LIST_HEAD(&vif->schedule_list); - INIT_LIST_HEAD(&vif->notify_list); - init_waitqueue_head(&vif->waiting_to_unmap); - - vif->credit_bytes = vif->remaining_credit = ~0UL; - vif->credit_usec = 0UL; - init_timer(&vif->credit_timeout); - vif->credit_window_start = get_jiffies_64(); + vif->disabled = false; + vif->drain_timeout = msecs_to_jiffies(rx_drain_timeout_msecs); + vif->stall_timeout = msecs_to_jiffies(rx_stall_timeout_msecs); + + /* Start out with no queues. */ + vif->queues = NULL; + vif->num_queues = 0; + + spin_lock_init(&vif->lock); + INIT_LIST_HEAD(&vif->fe_mcast_addr); dev->netdev_ops = &xenvif_netdev_ops; - dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; - dev->features = dev->hw_features; - SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops); + dev->hw_features = NETIF_F_SG | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_TSO | NETIF_F_TSO6; + dev->features = dev->hw_features | NETIF_F_RXCSUM; + dev->ethtool_ops = &xenvif_ethtool_ops; dev->tx_queue_len = XENVIF_QUEUE_LENGTH; @@ -303,7 +451,7 @@ * stolen by an Ethernet bridge for STP purposes. * (FE:FF:FF:FF:FF:FF) */ - memset(dev->dev_addr, 0xFF, ETH_ALEN); + eth_broadcast_addr(dev->dev_addr); dev->dev_addr[0] &= ~0x01; netif_carrier_off(dev); @@ -322,42 +470,153 @@ return vif; } -int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, - unsigned long rx_ring_ref, unsigned int evtchn) +int xenvif_init_queue(struct xenvif_queue *queue) { - int err = -ENOMEM; + int err, i; - /* Already connected through? */ - if (vif->irq) - return 0; + queue->credit_bytes = queue->remaining_credit = ~0UL; + queue->credit_usec = 0UL; + init_timer(&queue->credit_timeout); + queue->credit_timeout.function = xenvif_tx_credit_callback; + queue->credit_window_start = get_jiffies_64(); - err = xen_netbk_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref); - if (err < 0) - goto err; + queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES; - err = bind_interdomain_evtchn_to_irqhandler( - vif->domid, evtchn, xenvif_interrupt, 0, - vif->dev->name, vif); - if (err < 0) - goto err_unmap; - vif->irq = err; - disable_irq(vif->irq); + skb_queue_head_init(&queue->rx_queue); + skb_queue_head_init(&queue->tx_queue); + + queue->pending_cons = 0; + queue->pending_prod = MAX_PENDING_REQS; + for (i = 0; i < MAX_PENDING_REQS; ++i) + queue->pending_ring[i] = i; - xenvif_get(vif); + spin_lock_init(&queue->callback_lock); + spin_lock_init(&queue->response_lock); + /* If ballooning is disabled, this will consume real memory, so you + * better enable it. The long term solution would be to use just a + * bunch of valid page descriptors, without dependency on ballooning + */ + err = gnttab_alloc_pages(MAX_PENDING_REQS, + queue->mmap_pages); + if (err) { + netdev_err(queue->vif->dev, "Could not reserve mmap_pages\n"); + return -ENOMEM; + } + + for (i = 0; i < MAX_PENDING_REQS; i++) { + queue->pending_tx_info[i].callback_struct = (struct ubuf_info) + { .callback = xenvif_zerocopy_callback, + .ctx = NULL, + .desc = i }; + queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE; + } + + return 0; +} + +void xenvif_carrier_on(struct xenvif *vif) +{ rtnl_lock(); if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN) dev_set_mtu(vif->dev, ETH_DATA_LEN); netdev_update_features(vif->dev); - netif_carrier_on(vif->dev); + set_bit(VIF_STATUS_CONNECTED, &vif->status); if (netif_running(vif->dev)) xenvif_up(vif); rtnl_unlock(); +} + +int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref, + unsigned long rx_ring_ref, unsigned int tx_evtchn, + unsigned int rx_evtchn) +{ + struct task_struct *task; + int err = -ENOMEM; + + BUG_ON(queue->tx_irq); + BUG_ON(queue->task); + BUG_ON(queue->dealloc_task); + + err = xenvif_map_frontend_rings(queue, tx_ring_ref, rx_ring_ref); + if (err < 0) + goto err; + + init_waitqueue_head(&queue->wq); + init_waitqueue_head(&queue->dealloc_wq); + atomic_set(&queue->inflight_packets, 0); + + netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll, + XENVIF_NAPI_WEIGHT); + + if (tx_evtchn == rx_evtchn) { + /* feature-split-event-channels == 0 */ + err = bind_interdomain_evtchn_to_irqhandler( + queue->vif->domid, tx_evtchn, xenvif_interrupt, 0, + queue->name, queue); + if (err < 0) + goto err_unmap; + queue->tx_irq = queue->rx_irq = err; + disable_irq(queue->tx_irq); + } else { + /* feature-split-event-channels == 1 */ + snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name), + "%s-tx", queue->name); + err = bind_interdomain_evtchn_to_irqhandler( + queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0, + queue->tx_irq_name, queue); + if (err < 0) + goto err_unmap; + queue->tx_irq = err; + disable_irq(queue->tx_irq); + + snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name), + "%s-rx", queue->name); + err = bind_interdomain_evtchn_to_irqhandler( + queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0, + queue->rx_irq_name, queue); + if (err < 0) + goto err_tx_unbind; + queue->rx_irq = err; + disable_irq(queue->rx_irq); + } + + queue->stalled = true; + + task = kthread_create(xenvif_kthread_guest_rx, + (void *)queue, "%s-guest-rx", queue->name); + if (IS_ERR(task)) { + pr_warn("Could not allocate kthread for %s\n", queue->name); + err = PTR_ERR(task); + goto err_rx_unbind; + } + queue->task = task; + get_task_struct(task); + + task = kthread_create(xenvif_dealloc_kthread, + (void *)queue, "%s-dealloc", queue->name); + if (IS_ERR(task)) { + pr_warn("Could not allocate kthread for %s\n", queue->name); + err = PTR_ERR(task); + goto err_rx_unbind; + } + queue->dealloc_task = task; + + wake_up_process(queue->task); + wake_up_process(queue->dealloc_task); return 0; + +err_rx_unbind: + unbind_from_irqhandler(queue->rx_irq, queue); + queue->rx_irq = 0; +err_tx_unbind: + unbind_from_irqhandler(queue->tx_irq, queue); + queue->tx_irq = 0; err_unmap: - xen_netbk_unmap_frontend_rings(vif); + xenvif_unmap_frontend_rings(queue); err: + module_put(THIS_MODULE); return err; } @@ -366,33 +625,80 @@ struct net_device *dev = vif->dev; rtnl_lock(); - netif_carrier_off(dev); /* discard queued packets */ - if (netif_running(dev)) - xenvif_down(vif); + if (test_and_clear_bit(VIF_STATUS_CONNECTED, &vif->status)) { + netif_carrier_off(dev); /* discard queued packets */ + if (netif_running(dev)) + xenvif_down(vif); + } rtnl_unlock(); - xenvif_put(vif); } void xenvif_disconnect(struct xenvif *vif) { - if (netif_carrier_ok(vif->dev)) - xenvif_carrier_off(vif); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + unsigned int queue_index; + + xenvif_carrier_off(vif); + + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + + netif_napi_del(&queue->napi); + + if (queue->task) { + kthread_stop(queue->task); + put_task_struct(queue->task); + queue->task = NULL; + } + + if (queue->dealloc_task) { + kthread_stop(queue->dealloc_task); + queue->dealloc_task = NULL; + } + + if (queue->tx_irq) { + if (queue->tx_irq == queue->rx_irq) + unbind_from_irqhandler(queue->tx_irq, queue); + else { + unbind_from_irqhandler(queue->tx_irq, queue); + unbind_from_irqhandler(queue->rx_irq, queue); + } + queue->tx_irq = 0; + } - disable_irq(vif->irq); - xen_netbk_unmap_frontend_rings(vif); - if (vif->irq) { - unbind_from_irqhandler(vif->irq, vif); - vif->irq = 0; + xenvif_unmap_frontend_rings(queue); } + + xenvif_mcast_addr_list_free(vif); +} + +/* Reverse the relevant parts of xenvif_init_queue(). + * Used for queue teardown from xenvif_free(), and on the + * error handling paths in xenbus.c:connect(). + */ +void xenvif_deinit_queue(struct xenvif_queue *queue) +{ + gnttab_free_pages(MAX_PENDING_REQS, queue->mmap_pages); } void xenvif_free(struct xenvif *vif) { - atomic_dec(&vif->refcnt); - wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0); + struct xenvif_queue *queue = NULL; + unsigned int num_queues = vif->num_queues; + unsigned int queue_index; unregister_netdev(vif->dev); + for (queue_index = 0; queue_index < num_queues; ++queue_index) { + queue = &vif->queues[queue_index]; + xenvif_deinit_queue(queue); + } + + vfree(vif->queues); + vif->queues = NULL; + vif->num_queues = 0; + free_netdev(vif->dev); module_put(THIS_MODULE);