From b3f980bd827e6e81a050c518d60ed7811a83061d Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Mon, 26 Aug 2013 12:59:38 +0100 Subject: xen-netback: switch to NAPI + kthread 1:1 model This patch implements 1:1 model netback. NAPI and kthread are utilized to do the weight-lifting job: - NAPI is used for guest side TX (host side RX) - kthread is used for guest side RX (host side TX) Xenvif and xen_netbk are made into one structure to reduce code size. This model provides better scheduling fairness among vifs. It is also prerequisite for implementing multiqueue for Xen netback. Signed-off-by: Wei Liu Acked-by: Ian Campbell Signed-off-by: David S. Miller --- drivers/net/xen-netback/interface.c | 119 ++++++++++++++++++++++++------------ 1 file changed, 80 insertions(+), 39 deletions(-) (limited to 'drivers/net/xen-netback/interface.c') diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 087d2db0389d..44d6b707c77e 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -30,6 +30,7 @@ #include "common.h" +#include #include #include #include @@ -38,17 +39,7 @@ #include #define XENVIF_QUEUE_LENGTH 32 - -void xenvif_get(struct xenvif *vif) -{ - atomic_inc(&vif->refcnt); -} - -void xenvif_put(struct xenvif *vif) -{ - if (atomic_dec_and_test(&vif->refcnt)) - wake_up(&vif->waiting_to_free); -} +#define XENVIF_NAPI_WEIGHT 64 int xenvif_schedulable(struct xenvif *vif) { @@ -64,21 +55,55 @@ static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id) { struct xenvif *vif = dev_id; - if (vif->netbk == NULL) - return IRQ_HANDLED; - - xen_netbk_schedule_xenvif(vif); + if (RING_HAS_UNCONSUMED_REQUESTS(&vif->tx)) + napi_schedule(&vif->napi); return IRQ_HANDLED; } +static int xenvif_poll(struct napi_struct *napi, int budget) +{ + struct xenvif *vif = container_of(napi, struct xenvif, napi); + int work_done; + + work_done = xen_netbk_tx_action(vif, budget); + + if (work_done < budget) { + int more_to_do = 0; + unsigned long flags; + + /* It is necessary to disable IRQ before calling + * RING_HAS_UNCONSUMED_REQUESTS. Otherwise we might + * lose event from the frontend. + * + * Consider: + * RING_HAS_UNCONSUMED_REQUESTS + * + * __napi_complete + * + * This handler is still in scheduled state so the + * event has no effect at all. After __napi_complete + * this handler is descheduled and cannot get + * scheduled again. We lose event in this case and the ring + * will be completely stalled. + */ + + local_irq_save(flags); + + RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do); + if (!more_to_do) + __napi_complete(napi); + + local_irq_restore(flags); + } + + return work_done; +} + static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id) { struct xenvif *vif = dev_id; - if (vif->netbk == NULL) - return IRQ_HANDLED; - if (xenvif_rx_schedulable(vif)) netif_wake_queue(vif->dev); @@ -99,7 +124,8 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) BUG_ON(skb->dev != dev); - if (vif->netbk == NULL) + /* Drop the packet if vif is not ready */ + if (vif->task == NULL) goto drop; /* Drop the packet if the target domain has no receive buffers. */ @@ -108,7 +134,6 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) /* 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); if (vif->can_queue && xen_netbk_must_stop_queue(vif)) netif_stop_queue(dev); @@ -123,11 +148,6 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) 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)) @@ -142,7 +162,7 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev) static void xenvif_up(struct xenvif *vif) { - xen_netbk_add_xenvif(vif); + napi_enable(&vif->napi); enable_irq(vif->tx_irq); if (vif->tx_irq != vif->rx_irq) enable_irq(vif->rx_irq); @@ -151,12 +171,11 @@ static void xenvif_up(struct xenvif *vif) static void xenvif_down(struct xenvif *vif) { + napi_disable(&vif->napi); disable_irq(vif->tx_irq); if (vif->tx_irq != vif->rx_irq) disable_irq(vif->rx_irq); del_timer_sync(&vif->credit_timeout); - xen_netbk_deschedule_xenvif(vif); - xen_netbk_remove_xenvif(vif); } static int xenvif_open(struct net_device *dev) @@ -272,11 +291,12 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, struct net_device *dev; struct xenvif *vif; char name[IFNAMSIZ] = {}; + int i; snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle); dev = alloc_netdev(sizeof(struct xenvif), name, ether_setup); if (dev == NULL) { - pr_warn("Could not allocate netdev\n"); + pr_warn("Could not allocate netdev for %s\n", name); return ERR_PTR(-ENOMEM); } @@ -285,14 +305,9 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, 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->dev = dev; - INIT_LIST_HEAD(&vif->schedule_list); - INIT_LIST_HEAD(&vif->notify_list); vif->credit_bytes = vif->remaining_credit = ~0UL; vif->credit_usec = 0UL; @@ -307,6 +322,16 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, dev->tx_queue_len = XENVIF_QUEUE_LENGTH; + skb_queue_head_init(&vif->rx_queue); + skb_queue_head_init(&vif->tx_queue); + + vif->pending_cons = 0; + vif->pending_prod = MAX_PENDING_REQS; + for (i = 0; i < MAX_PENDING_REQS; i++) + vif->pending_ring[i] = i; + for (i = 0; i < MAX_PENDING_REQS; i++) + vif->mmap_pages[i] = NULL; + /* * Initialise a dummy MAC address. We choose the numerically * largest non-broadcast address to prevent the address getting @@ -316,6 +341,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, memset(dev->dev_addr, 0xFF, ETH_ALEN); dev->dev_addr[0] &= ~0x01; + netif_napi_add(dev, &vif->napi, xenvif_poll, XENVIF_NAPI_WEIGHT); + netif_carrier_off(dev); err = register_netdev(dev); @@ -377,7 +404,14 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, disable_irq(vif->rx_irq); } - xenvif_get(vif); + init_waitqueue_head(&vif->wq); + vif->task = kthread_create(xen_netbk_kthread, + (void *)vif, vif->dev->name); + if (IS_ERR(vif->task)) { + pr_warn("Could not allocate kthread for %s\n", vif->dev->name); + err = PTR_ERR(vif->task); + goto err_rx_unbind; + } rtnl_lock(); if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN) @@ -388,7 +422,13 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, xenvif_up(vif); rtnl_unlock(); + wake_up_process(vif->task); + return 0; + +err_rx_unbind: + unbind_from_irqhandler(vif->rx_irq, vif); + vif->rx_irq = 0; err_tx_unbind: unbind_from_irqhandler(vif->tx_irq, vif); vif->tx_irq = 0; @@ -408,7 +448,6 @@ void xenvif_carrier_off(struct xenvif *vif) if (netif_running(dev)) xenvif_down(vif); rtnl_unlock(); - xenvif_put(vif); } void xenvif_disconnect(struct xenvif *vif) @@ -422,9 +461,6 @@ void xenvif_disconnect(struct xenvif *vif) if (netif_carrier_ok(vif->dev)) xenvif_carrier_off(vif); - atomic_dec(&vif->refcnt); - wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0); - if (vif->tx_irq) { if (vif->tx_irq == vif->rx_irq) unbind_from_irqhandler(vif->tx_irq, vif); @@ -438,6 +474,11 @@ void xenvif_disconnect(struct xenvif *vif) need_module_put = 1; } + if (vif->task) + kthread_stop(vif->task); + + netif_napi_del(&vif->napi); + unregister_netdev(vif->dev); xen_netbk_unmap_frontend_rings(vif); -- cgit v1.2.3 From 7376419a4697657b2e0ab904a592aacc2e485bf1 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Mon, 26 Aug 2013 12:59:39 +0100 Subject: xen-netback: rename functions As we move to 1:1 model and melt xen_netbk and xenvif together, it would be better to use single prefix for all functions in xen-netback. Signed-off-by: Wei Liu Acked-by: Ian Campbell Signed-off-by: David S. Miller --- drivers/net/xen-netback/interface.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'drivers/net/xen-netback/interface.c') diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 44d6b707c77e..625c6f49cfba 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -48,7 +48,7 @@ int xenvif_schedulable(struct xenvif *vif) static int xenvif_rx_schedulable(struct xenvif *vif) { - return xenvif_schedulable(vif) && !xen_netbk_rx_ring_full(vif); + return xenvif_schedulable(vif) && !xenvif_rx_ring_full(vif); } static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id) @@ -66,7 +66,7 @@ static int xenvif_poll(struct napi_struct *napi, int budget) struct xenvif *vif = container_of(napi, struct xenvif, napi); int work_done; - work_done = xen_netbk_tx_action(vif, budget); + work_done = xenvif_tx_action(vif, budget); if (work_done < budget) { int more_to_do = 0; @@ -133,12 +133,12 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) goto drop; /* Reserve ring slots for the worst-case number of fragments. */ - vif->rx_req_cons_peek += xen_netbk_count_skb_slots(vif, skb); + vif->rx_req_cons_peek += xenvif_count_skb_slots(vif, skb); - if (vif->can_queue && xen_netbk_must_stop_queue(vif)) + if (vif->can_queue && xenvif_must_stop_queue(vif)) netif_stop_queue(dev); - xen_netbk_queue_tx_skb(vif, skb); + xenvif_queue_tx_skb(vif, skb); return NETDEV_TX_OK; @@ -166,7 +166,7 @@ static void xenvif_up(struct xenvif *vif) enable_irq(vif->tx_irq); if (vif->tx_irq != vif->rx_irq) enable_irq(vif->rx_irq); - xen_netbk_check_rx_xenvif(vif); + xenvif_check_rx_xenvif(vif); } static void xenvif_down(struct xenvif *vif) @@ -368,7 +368,7 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, __module_get(THIS_MODULE); - err = xen_netbk_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref); + err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref); if (err < 0) goto err; @@ -405,7 +405,7 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, } init_waitqueue_head(&vif->wq); - vif->task = kthread_create(xen_netbk_kthread, + vif->task = kthread_create(xenvif_kthread, (void *)vif, vif->dev->name); if (IS_ERR(vif->task)) { pr_warn("Could not allocate kthread for %s\n", vif->dev->name); @@ -433,7 +433,7 @@ err_tx_unbind: unbind_from_irqhandler(vif->tx_irq, vif); vif->tx_irq = 0; err_unmap: - xen_netbk_unmap_frontend_rings(vif); + xenvif_unmap_frontend_rings(vif); err: module_put(THIS_MODULE); return err; @@ -481,7 +481,7 @@ void xenvif_disconnect(struct xenvif *vif) unregister_netdev(vif->dev); - xen_netbk_unmap_frontend_rings(vif); + xenvif_unmap_frontend_rings(vif); free_netdev(vif->dev); -- cgit v1.2.3 From a9677bc024dcaafcf36c1cc4b0706b87be26ee5f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 10 Sep 2013 21:39:11 -0700 Subject: xen-netback: fix possible format string flaw This makes sure a format string cannot accidentally leak into the kthread_run() call. Signed-off-by: Kees Cook Acked-by: Ian Campbell Signed-off-by: David S. Miller --- drivers/net/xen-netback/interface.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/xen-netback/interface.c') diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 625c6f49cfba..77fee1d51fb2 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -406,7 +406,7 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, init_waitqueue_head(&vif->wq); vif->task = kthread_create(xenvif_kthread, - (void *)vif, vif->dev->name); + (void *)vif, "%s", vif->dev->name); if (IS_ERR(vif->task)) { pr_warn("Could not allocate kthread for %s\n", vif->dev->name); err = PTR_ERR(vif->task); -- cgit v1.2.3 From 279f438e36c0a70b23b86d2090aeec50155034a9 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Tue, 17 Sep 2013 17:46:08 +0100 Subject: xen-netback: Don't destroy the netdev until the vif is shut down Without this patch, if a frontend cycles through states Closing and Closed (which Windows frontends need to do) then the netdev will be destroyed and requires re-invocation of hotplug scripts to restore state before the frontend can move to Connected. Thus when udev is not in use the backend gets stuck in InitWait. With this patch, the netdev is left alone whilst the backend is still online and is only de-registered and freed just prior to destroying the vif (which is also nicely symmetrical with the netdev allocation and registration being done during probe) so no re-invocation of hotplug scripts is required. Signed-off-by: Paul Durrant Cc: David Vrabel Cc: Wei Liu Cc: Ian Campbell Acked-by: Wei Liu Signed-off-by: David S. Miller --- drivers/net/xen-netback/interface.c | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) (limited to 'drivers/net/xen-netback/interface.c') diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 77fee1d51fb2..01bb854c7f62 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -353,6 +353,9 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, } netdev_dbg(dev, "Successfully created xenvif\n"); + + __module_get(THIS_MODULE); + return vif; } @@ -366,8 +369,6 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, if (vif->tx_irq) return 0; - __module_get(THIS_MODULE); - err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref); if (err < 0) goto err; @@ -452,12 +453,6 @@ void xenvif_carrier_off(struct xenvif *vif) void xenvif_disconnect(struct xenvif *vif) { - /* Disconnect funtion might get called by generic framework - * even before vif connects, so we need to check if we really - * need to do a module_put. - */ - int need_module_put = 0; - if (netif_carrier_ok(vif->dev)) xenvif_carrier_off(vif); @@ -468,23 +463,22 @@ void xenvif_disconnect(struct xenvif *vif) unbind_from_irqhandler(vif->tx_irq, vif); unbind_from_irqhandler(vif->rx_irq, vif); } - /* vif->irq is valid, we had a module_get in - * xenvif_connect. - */ - need_module_put = 1; + vif->tx_irq = 0; } if (vif->task) kthread_stop(vif->task); + xenvif_unmap_frontend_rings(vif); +} + +void xenvif_free(struct xenvif *vif) +{ netif_napi_del(&vif->napi); unregister_netdev(vif->dev); - xenvif_unmap_frontend_rings(vif); - free_netdev(vif->dev); - if (need_module_put) - module_put(THIS_MODULE); + module_put(THIS_MODULE); } -- cgit v1.2.3