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 087d2db0389..44d6b707c77 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 v1.2.3-70-g09d2 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/common.h | 24 ++-- drivers/net/xen-netback/interface.c | 20 ++-- drivers/net/xen-netback/netback.c | 223 ++++++++++++++++++------------------ 3 files changed, 134 insertions(+), 133 deletions(-) (limited to 'drivers/net/xen-netback/interface.c') diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 9c1f15872e1..a1977430ddf 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -190,21 +190,21 @@ void xenvif_xenbus_fini(void); int xenvif_schedulable(struct xenvif *vif); -int xen_netbk_rx_ring_full(struct xenvif *vif); +int xenvif_rx_ring_full(struct xenvif *vif); -int xen_netbk_must_stop_queue(struct xenvif *vif); +int xenvif_must_stop_queue(struct xenvif *vif); /* (Un)Map communication rings. */ -void xen_netbk_unmap_frontend_rings(struct xenvif *vif); -int xen_netbk_map_frontend_rings(struct xenvif *vif, - grant_ref_t tx_ring_ref, - grant_ref_t rx_ring_ref); +void xenvif_unmap_frontend_rings(struct xenvif *vif); +int xenvif_map_frontend_rings(struct xenvif *vif, + grant_ref_t tx_ring_ref, + grant_ref_t rx_ring_ref); /* Check for SKBs from frontend and schedule backend processing */ -void xen_netbk_check_rx_xenvif(struct xenvif *vif); +void xenvif_check_rx_xenvif(struct xenvif *vif); /* Queue an SKB for transmission to the frontend */ -void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb); +void xenvif_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb); /* Notify xenvif that ring now has space to send an skb to the frontend */ void xenvif_notify_tx_completion(struct xenvif *vif); @@ -212,12 +212,12 @@ void xenvif_notify_tx_completion(struct xenvif *vif); void xenvif_carrier_off(struct xenvif *vif); /* Returns number of ring slots required to send an skb to the frontend */ -unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb); +unsigned int xenvif_count_skb_slots(struct xenvif *vif, struct sk_buff *skb); -int xen_netbk_tx_action(struct xenvif *vif, int budget); -void xen_netbk_rx_action(struct xenvif *vif); +int xenvif_tx_action(struct xenvif *vif, int budget); +void xenvif_rx_action(struct xenvif *vif); -int xen_netbk_kthread(void *data); +int xenvif_kthread(void *data); extern bool separate_tx_rx_irq; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 44d6b707c77..625c6f49cfb 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); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 44ccc674c02..956130c7003 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -80,8 +80,9 @@ static inline int pending_tx_is_head(struct xenvif *vif, RING_IDX idx) return vif->pending_tx_info[idx].head != INVALID_PENDING_RING_IDX; } -static void xen_netbk_idx_release(struct xenvif *vif, u16 pending_idx, - u8 status); +static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx, + u8 status); + static void make_tx_response(struct xenvif *vif, struct xen_netif_tx_request *txp, s8 st); @@ -150,7 +151,7 @@ static int max_required_rx_slots(struct xenvif *vif) return max; } -int xen_netbk_rx_ring_full(struct xenvif *vif) +int xenvif_rx_ring_full(struct xenvif *vif) { RING_IDX peek = vif->rx_req_cons_peek; RING_IDX needed = max_required_rx_slots(vif); @@ -159,16 +160,16 @@ int xen_netbk_rx_ring_full(struct xenvif *vif) ((vif->rx.rsp_prod_pvt + XEN_NETIF_RX_RING_SIZE - peek) < needed); } -int xen_netbk_must_stop_queue(struct xenvif *vif) +int xenvif_must_stop_queue(struct xenvif *vif) { - if (!xen_netbk_rx_ring_full(vif)) + if (!xenvif_rx_ring_full(vif)) return 0; vif->rx.sring->req_event = vif->rx_req_cons_peek + max_required_rx_slots(vif); mb(); /* request notification /then/ check the queue */ - return xen_netbk_rx_ring_full(vif); + return xenvif_rx_ring_full(vif); } /* @@ -214,9 +215,9 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head) /* * Figure out how many ring slots we're going to need to send @skb to * the guest. This function is essentially a dry run of - * netbk_gop_frag_copy. + * xenvif_gop_frag_copy. */ -unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb) +unsigned int xenvif_count_skb_slots(struct xenvif *vif, struct sk_buff *skb) { unsigned int count; int i, copy_off; @@ -296,10 +297,10 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif, * Set up the grant operations for this fragment. If it's a flipping * interface, we also set up the unmap request from here. */ -static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, - struct netrx_pending_operations *npo, - struct page *page, unsigned long size, - unsigned long offset, int *head) +static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, + struct netrx_pending_operations *npo, + struct page *page, unsigned long size, + unsigned long offset, int *head) { struct gnttab_copy *copy_gop; struct xenvif_rx_meta *meta; @@ -382,8 +383,8 @@ static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, * zero GSO descriptors (for non-GSO packets) or one descriptor (for * frontend-side LRO). */ -static int netbk_gop_skb(struct sk_buff *skb, - struct netrx_pending_operations *npo) +static int xenvif_gop_skb(struct sk_buff *skb, + struct netrx_pending_operations *npo) { struct xenvif *vif = netdev_priv(skb->dev); int nr_frags = skb_shinfo(skb)->nr_frags; @@ -426,30 +427,30 @@ static int netbk_gop_skb(struct sk_buff *skb, if (data + len > skb_tail_pointer(skb)) len = skb_tail_pointer(skb) - data; - netbk_gop_frag_copy(vif, skb, npo, - virt_to_page(data), len, offset, &head); + xenvif_gop_frag_copy(vif, skb, npo, + virt_to_page(data), len, offset, &head); data += len; } for (i = 0; i < nr_frags; i++) { - netbk_gop_frag_copy(vif, skb, npo, - skb_frag_page(&skb_shinfo(skb)->frags[i]), - skb_frag_size(&skb_shinfo(skb)->frags[i]), - skb_shinfo(skb)->frags[i].page_offset, - &head); + xenvif_gop_frag_copy(vif, skb, npo, + skb_frag_page(&skb_shinfo(skb)->frags[i]), + skb_frag_size(&skb_shinfo(skb)->frags[i]), + skb_shinfo(skb)->frags[i].page_offset, + &head); } return npo->meta_prod - old_meta_prod; } /* - * This is a twin to netbk_gop_skb. Assume that netbk_gop_skb was + * This is a twin to xenvif_gop_skb. Assume that xenvif_gop_skb was * used to set up the operations on the top of * netrx_pending_operations, which have since been done. Check that * they didn't give any errors and advance over them. */ -static int netbk_check_gop(struct xenvif *vif, int nr_meta_slots, - struct netrx_pending_operations *npo) +static int xenvif_check_gop(struct xenvif *vif, int nr_meta_slots, + struct netrx_pending_operations *npo) { struct gnttab_copy *copy_op; int status = XEN_NETIF_RSP_OKAY; @@ -468,9 +469,9 @@ static int netbk_check_gop(struct xenvif *vif, int nr_meta_slots, return status; } -static void netbk_add_frag_responses(struct xenvif *vif, int status, - struct xenvif_rx_meta *meta, - int nr_meta_slots) +static void xenvif_add_frag_responses(struct xenvif *vif, int status, + struct xenvif_rx_meta *meta, + int nr_meta_slots) { int i; unsigned long offset; @@ -498,12 +499,12 @@ struct skb_cb_overlay { int meta_slots_used; }; -static void xen_netbk_kick_thread(struct xenvif *vif) +static void xenvif_kick_thread(struct xenvif *vif) { wake_up(&vif->wq); } -void xen_netbk_rx_action(struct xenvif *vif) +void xenvif_rx_action(struct xenvif *vif) { s8 status; u16 flags; @@ -532,7 +533,7 @@ void xen_netbk_rx_action(struct xenvif *vif) nr_frags = skb_shinfo(skb)->nr_frags; sco = (struct skb_cb_overlay *)skb->cb; - sco->meta_slots_used = netbk_gop_skb(skb, &npo); + sco->meta_slots_used = xenvif_gop_skb(skb, &npo); count += nr_frags + 1; @@ -575,7 +576,7 @@ void xen_netbk_rx_action(struct xenvif *vif) vif->dev->stats.tx_bytes += skb->len; vif->dev->stats.tx_packets++; - status = netbk_check_gop(vif, sco->meta_slots_used, &npo); + status = xenvif_check_gop(vif, sco->meta_slots_used, &npo); if (sco->meta_slots_used == 1) flags = 0; @@ -611,9 +612,9 @@ void xen_netbk_rx_action(struct xenvif *vif) gso->flags = 0; } - netbk_add_frag_responses(vif, status, - vif->meta + npo.meta_cons + 1, - sco->meta_slots_used); + xenvif_add_frag_responses(vif, status, + vif->meta + npo.meta_cons + 1, + sco->meta_slots_used); RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret); @@ -631,17 +632,17 @@ void xen_netbk_rx_action(struct xenvif *vif) /* More work to do? */ if (!skb_queue_empty(&vif->rx_queue)) - xen_netbk_kick_thread(vif); + xenvif_kick_thread(vif); } -void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb) +void xenvif_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb) { skb_queue_tail(&vif->rx_queue, skb); - xen_netbk_kick_thread(vif); + xenvif_kick_thread(vif); } -void xen_netbk_check_rx_xenvif(struct xenvif *vif) +void xenvif_check_rx_xenvif(struct xenvif *vif) { int more_to_do; @@ -675,11 +676,11 @@ static void tx_credit_callback(unsigned long data) { struct xenvif *vif = (struct xenvif *)data; tx_add_credit(vif); - xen_netbk_check_rx_xenvif(vif); + xenvif_check_rx_xenvif(vif); } -static void netbk_tx_err(struct xenvif *vif, - struct xen_netif_tx_request *txp, RING_IDX end) +static void xenvif_tx_err(struct xenvif *vif, + struct xen_netif_tx_request *txp, RING_IDX end) { RING_IDX cons = vif->tx.req_cons; @@ -692,16 +693,16 @@ static void netbk_tx_err(struct xenvif *vif, vif->tx.req_cons = cons; } -static void netbk_fatal_tx_err(struct xenvif *vif) +static void xenvif_fatal_tx_err(struct xenvif *vif) { netdev_err(vif->dev, "fatal error; disabling device\n"); xenvif_carrier_off(vif); } -static int netbk_count_requests(struct xenvif *vif, - struct xen_netif_tx_request *first, - struct xen_netif_tx_request *txp, - int work_to_do) +static int xenvif_count_requests(struct xenvif *vif, + struct xen_netif_tx_request *first, + struct xen_netif_tx_request *txp, + int work_to_do) { RING_IDX cons = vif->tx.req_cons; int slots = 0; @@ -718,7 +719,7 @@ static int netbk_count_requests(struct xenvif *vif, netdev_err(vif->dev, "Asked for %d slots but exceeds this limit\n", work_to_do); - netbk_fatal_tx_err(vif); + xenvif_fatal_tx_err(vif); return -ENODATA; } @@ -729,7 +730,7 @@ static int netbk_count_requests(struct xenvif *vif, netdev_err(vif->dev, "Malicious frontend using %d slots, threshold %u\n", slots, fatal_skb_slots); - netbk_fatal_tx_err(vif); + xenvif_fatal_tx_err(vif); return -E2BIG; } @@ -777,7 +778,7 @@ static int netbk_count_requests(struct xenvif *vif, if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) { netdev_err(vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n", txp->offset, txp->size); - netbk_fatal_tx_err(vif); + xenvif_fatal_tx_err(vif); return -EINVAL; } @@ -789,15 +790,15 @@ static int netbk_count_requests(struct xenvif *vif, } while (more_data); if (drop_err) { - netbk_tx_err(vif, first, cons + slots); + xenvif_tx_err(vif, first, cons + slots); return drop_err; } return slots; } -static struct page *xen_netbk_alloc_page(struct xenvif *vif, - u16 pending_idx) +static struct page *xenvif_alloc_page(struct xenvif *vif, + u16 pending_idx) { struct page *page; @@ -809,10 +810,10 @@ static struct page *xen_netbk_alloc_page(struct xenvif *vif, return page; } -static struct gnttab_copy *xen_netbk_get_requests(struct xenvif *vif, - struct sk_buff *skb, - struct xen_netif_tx_request *txp, - struct gnttab_copy *gop) +static struct gnttab_copy *xenvif_get_requests(struct xenvif *vif, + struct sk_buff *skb, + struct xen_netif_tx_request *txp, + struct gnttab_copy *gop) { struct skb_shared_info *shinfo = skb_shinfo(skb); skb_frag_t *frags = shinfo->frags; @@ -835,7 +836,7 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xenvif *vif, /* Coalesce tx requests, at this point the packet passed in * should be <= 64K. Any packets larger than 64K have been - * handled in netbk_count_requests(). + * handled in xenvif_count_requests(). */ for (shinfo->nr_frags = slot = start; slot < nr_slots; shinfo->nr_frags++) { @@ -918,20 +919,20 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xenvif *vif, err: /* Unwind, freeing all pages and sending error responses. */ while (shinfo->nr_frags-- > start) { - xen_netbk_idx_release(vif, + xenvif_idx_release(vif, frag_get_pending_idx(&frags[shinfo->nr_frags]), XEN_NETIF_RSP_ERROR); } /* The head too, if necessary. */ if (start) - xen_netbk_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); + xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); return NULL; } -static int xen_netbk_tx_check_gop(struct xenvif *vif, - struct sk_buff *skb, - struct gnttab_copy **gopp) +static int xenvif_tx_check_gop(struct xenvif *vif, + struct sk_buff *skb, + struct gnttab_copy **gopp) { struct gnttab_copy *gop = *gopp; u16 pending_idx = *((u16 *)skb->data); @@ -944,7 +945,7 @@ static int xen_netbk_tx_check_gop(struct xenvif *vif, /* Check status of header. */ err = gop->status; if (unlikely(err)) - xen_netbk_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); + xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); /* Skip first skb fragment if it is on same page as header fragment. */ start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); @@ -968,13 +969,13 @@ static int xen_netbk_tx_check_gop(struct xenvif *vif, if (likely(!newerr)) { /* Had a previous error? Invalidate this fragment. */ if (unlikely(err)) - xen_netbk_idx_release(vif, pending_idx, - XEN_NETIF_RSP_OKAY); + xenvif_idx_release(vif, pending_idx, + XEN_NETIF_RSP_OKAY); continue; } /* Error on this fragment: respond to client with an error. */ - xen_netbk_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); + xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); /* Not the first error? Preceding frags already invalidated. */ if (err) @@ -982,11 +983,11 @@ static int xen_netbk_tx_check_gop(struct xenvif *vif, /* First error: invalidate header and preceding fragments. */ pending_idx = *((u16 *)skb->data); - xen_netbk_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); + xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); for (j = start; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); - xen_netbk_idx_release(vif, pending_idx, - XEN_NETIF_RSP_OKAY); + xenvif_idx_release(vif, pending_idx, + XEN_NETIF_RSP_OKAY); } /* Remember the error: invalidate all subsequent fragments. */ @@ -997,7 +998,7 @@ static int xen_netbk_tx_check_gop(struct xenvif *vif, return err; } -static void xen_netbk_fill_frags(struct xenvif *vif, struct sk_buff *skb) +static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); int nr_frags = shinfo->nr_frags; @@ -1018,13 +1019,13 @@ static void xen_netbk_fill_frags(struct xenvif *vif, struct sk_buff *skb) skb->data_len += txp->size; skb->truesize += txp->size; - /* Take an extra reference to offset xen_netbk_idx_release */ + /* Take an extra reference to offset xenvif_idx_release */ get_page(vif->mmap_pages[pending_idx]); - xen_netbk_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); + xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); } } -static int xen_netbk_get_extras(struct xenvif *vif, +static int xenvif_get_extras(struct xenvif *vif, struct xen_netif_extra_info *extras, int work_to_do) { @@ -1034,7 +1035,7 @@ static int xen_netbk_get_extras(struct xenvif *vif, do { if (unlikely(work_to_do-- <= 0)) { netdev_err(vif->dev, "Missing extra info\n"); - netbk_fatal_tx_err(vif); + xenvif_fatal_tx_err(vif); return -EBADR; } @@ -1045,7 +1046,7 @@ static int xen_netbk_get_extras(struct xenvif *vif, vif->tx.req_cons = ++cons; netdev_err(vif->dev, "Invalid extra type: %d\n", extra.type); - netbk_fatal_tx_err(vif); + xenvif_fatal_tx_err(vif); return -EINVAL; } @@ -1056,20 +1057,20 @@ static int xen_netbk_get_extras(struct xenvif *vif, return work_to_do; } -static int netbk_set_skb_gso(struct xenvif *vif, - struct sk_buff *skb, - struct xen_netif_extra_info *gso) +static int xenvif_set_skb_gso(struct xenvif *vif, + struct sk_buff *skb, + struct xen_netif_extra_info *gso) { if (!gso->u.gso.size) { netdev_err(vif->dev, "GSO size must not be zero.\n"); - netbk_fatal_tx_err(vif); + xenvif_fatal_tx_err(vif); return -EINVAL; } /* Currently only TCPv4 S.O. is supported. */ if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) { netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type); - netbk_fatal_tx_err(vif); + xenvif_fatal_tx_err(vif); return -EINVAL; } @@ -1180,7 +1181,7 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) return false; } -static unsigned xen_netbk_tx_build_gops(struct xenvif *vif) +static unsigned xenvif_tx_build_gops(struct xenvif *vif) { struct gnttab_copy *gop = vif->tx_copy_ops, *request_gop; struct sk_buff *skb; @@ -1205,7 +1206,7 @@ static unsigned xen_netbk_tx_build_gops(struct xenvif *vif) "req_prod %d, req_cons %d, size %ld\n", vif->tx.sring->req_prod, vif->tx.req_cons, XEN_NETIF_TX_RING_SIZE); - netbk_fatal_tx_err(vif); + xenvif_fatal_tx_err(vif); continue; } @@ -1229,14 +1230,14 @@ static unsigned xen_netbk_tx_build_gops(struct xenvif *vif) memset(extras, 0, sizeof(extras)); if (txreq.flags & XEN_NETTXF_extra_info) { - work_to_do = xen_netbk_get_extras(vif, extras, - work_to_do); + work_to_do = xenvif_get_extras(vif, extras, + work_to_do); idx = vif->tx.req_cons; if (unlikely(work_to_do < 0)) break; } - ret = netbk_count_requests(vif, &txreq, txfrags, work_to_do); + ret = xenvif_count_requests(vif, &txreq, txfrags, work_to_do); if (unlikely(ret < 0)) break; @@ -1245,7 +1246,7 @@ static unsigned xen_netbk_tx_build_gops(struct xenvif *vif) if (unlikely(txreq.size < ETH_HLEN)) { netdev_dbg(vif->dev, "Bad packet size: %d\n", txreq.size); - netbk_tx_err(vif, &txreq, idx); + xenvif_tx_err(vif, &txreq, idx); break; } @@ -1255,7 +1256,7 @@ static unsigned xen_netbk_tx_build_gops(struct xenvif *vif) "txreq.offset: %x, size: %u, end: %lu\n", txreq.offset, txreq.size, (txreq.offset&~PAGE_MASK) + txreq.size); - netbk_fatal_tx_err(vif); + xenvif_fatal_tx_err(vif); break; } @@ -1271,7 +1272,7 @@ static unsigned xen_netbk_tx_build_gops(struct xenvif *vif) if (unlikely(skb == NULL)) { netdev_dbg(vif->dev, "Can't allocate a skb in start_xmit.\n"); - netbk_tx_err(vif, &txreq, idx); + xenvif_tx_err(vif, &txreq, idx); break; } @@ -1282,18 +1283,18 @@ static unsigned xen_netbk_tx_build_gops(struct xenvif *vif) struct xen_netif_extra_info *gso; gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; - if (netbk_set_skb_gso(vif, skb, gso)) { - /* Failure in netbk_set_skb_gso is fatal. */ + if (xenvif_set_skb_gso(vif, skb, gso)) { + /* Failure in xenvif_set_skb_gso is fatal. */ kfree_skb(skb); break; } } /* XXX could copy straight to head */ - page = xen_netbk_alloc_page(vif, pending_idx); + page = xenvif_alloc_page(vif, pending_idx); if (!page) { kfree_skb(skb); - netbk_tx_err(vif, &txreq, idx); + xenvif_tx_err(vif, &txreq, idx); break; } @@ -1329,10 +1330,10 @@ static unsigned xen_netbk_tx_build_gops(struct xenvif *vif) vif->pending_cons++; - request_gop = xen_netbk_get_requests(vif, skb, txfrags, gop); + request_gop = xenvif_get_requests(vif, skb, txfrags, gop); if (request_gop == NULL) { kfree_skb(skb); - netbk_tx_err(vif, &txreq, idx); + xenvif_tx_err(vif, &txreq, idx); break; } gop = request_gop; @@ -1349,7 +1350,7 @@ static unsigned xen_netbk_tx_build_gops(struct xenvif *vif) } -static int xen_netbk_tx_submit(struct xenvif *vif, int budget) +static int xenvif_tx_submit(struct xenvif *vif, int budget) { struct gnttab_copy *gop = vif->tx_copy_ops; struct sk_buff *skb; @@ -1365,7 +1366,7 @@ static int xen_netbk_tx_submit(struct xenvif *vif, int budget) txp = &vif->pending_tx_info[pending_idx].req; /* Check the remap error code. */ - if (unlikely(xen_netbk_tx_check_gop(vif, skb, &gop))) { + if (unlikely(xenvif_tx_check_gop(vif, skb, &gop))) { netdev_dbg(vif->dev, "netback grant failed.\n"); skb_shinfo(skb)->nr_frags = 0; kfree_skb(skb); @@ -1382,8 +1383,8 @@ static int xen_netbk_tx_submit(struct xenvif *vif, int budget) txp->size -= data_len; } else { /* Schedule a response immediately. */ - xen_netbk_idx_release(vif, pending_idx, - XEN_NETIF_RSP_OKAY); + xenvif_idx_release(vif, pending_idx, + XEN_NETIF_RSP_OKAY); } if (txp->flags & XEN_NETTXF_csum_blank) @@ -1391,7 +1392,7 @@ static int xen_netbk_tx_submit(struct xenvif *vif, int budget) else if (txp->flags & XEN_NETTXF_data_validated) skb->ip_summed = CHECKSUM_UNNECESSARY; - xen_netbk_fill_frags(vif, skb); + xenvif_fill_frags(vif, skb); /* * If the initial fragment was < PKT_PROT_LEN then @@ -1428,7 +1429,7 @@ static int xen_netbk_tx_submit(struct xenvif *vif, int budget) } /* Called after netfront has transmitted */ -int xen_netbk_tx_action(struct xenvif *vif, int budget) +int xenvif_tx_action(struct xenvif *vif, int budget) { unsigned nr_gops; int work_done; @@ -1436,20 +1437,20 @@ int xen_netbk_tx_action(struct xenvif *vif, int budget) if (unlikely(!tx_work_todo(vif))) return 0; - nr_gops = xen_netbk_tx_build_gops(vif); + nr_gops = xenvif_tx_build_gops(vif); if (nr_gops == 0) return 0; gnttab_batch_copy(vif->tx_copy_ops, nr_gops); - work_done = xen_netbk_tx_submit(vif, nr_gops); + work_done = xenvif_tx_submit(vif, nr_gops); return work_done; } -static void xen_netbk_idx_release(struct xenvif *vif, u16 pending_idx, - u8 status) +static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx, + u8 status) { struct pending_tx_info *pending_tx_info; pending_ring_idx_t head; @@ -1554,7 +1555,7 @@ static inline int tx_work_todo(struct xenvif *vif) return 0; } -void xen_netbk_unmap_frontend_rings(struct xenvif *vif) +void xenvif_unmap_frontend_rings(struct xenvif *vif) { if (vif->tx.sring) xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif), @@ -1564,9 +1565,9 @@ void xen_netbk_unmap_frontend_rings(struct xenvif *vif) vif->rx.sring); } -int xen_netbk_map_frontend_rings(struct xenvif *vif, - grant_ref_t tx_ring_ref, - grant_ref_t rx_ring_ref) +int xenvif_map_frontend_rings(struct xenvif *vif, + grant_ref_t tx_ring_ref, + grant_ref_t rx_ring_ref) { void *addr; struct xen_netif_tx_sring *txs; @@ -1595,11 +1596,11 @@ int xen_netbk_map_frontend_rings(struct xenvif *vif, return 0; err: - xen_netbk_unmap_frontend_rings(vif); + xenvif_unmap_frontend_rings(vif); return err; } -int xen_netbk_kthread(void *data) +int xenvif_kthread(void *data) { struct xenvif *vif = data; @@ -1611,7 +1612,7 @@ int xen_netbk_kthread(void *data) break; if (rx_work_todo(vif)) - xen_netbk_rx_action(vif); + xenvif_rx_action(vif); cond_resched(); } -- cgit v1.2.3-70-g09d2 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 625c6f49cfb..77fee1d51fb 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 v1.2.3-70-g09d2 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/common.h | 1 + drivers/net/xen-netback/interface.c | 26 ++++++++++---------------- drivers/net/xen-netback/xenbus.c | 17 ++++++++++++----- 3 files changed, 23 insertions(+), 21 deletions(-) (limited to 'drivers/net/xen-netback/interface.c') diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index a1977430ddf..5715318d6ba 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -184,6 +184,7 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, unsigned long rx_ring_ref, unsigned int tx_evtchn, unsigned int rx_evtchn); void xenvif_disconnect(struct xenvif *vif); +void xenvif_free(struct xenvif *vif); int xenvif_xenbus_init(void); void xenvif_xenbus_fini(void); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 77fee1d51fb..01bb854c7f6 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); } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 1fe48fe364e..a53782ef154 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -42,7 +42,7 @@ static int netback_remove(struct xenbus_device *dev) if (be->vif) { kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status"); - xenvif_disconnect(be->vif); + xenvif_free(be->vif); be->vif = NULL; } kfree(be); @@ -213,9 +213,18 @@ static void disconnect_backend(struct xenbus_device *dev) { struct backend_info *be = dev_get_drvdata(&dev->dev); + if (be->vif) + xenvif_disconnect(be->vif); +} + +static void destroy_backend(struct xenbus_device *dev) +{ + struct backend_info *be = dev_get_drvdata(&dev->dev); + if (be->vif) { + kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status"); - xenvif_disconnect(be->vif); + xenvif_free(be->vif); be->vif = NULL; } } @@ -246,14 +255,11 @@ static void frontend_changed(struct xenbus_device *dev, case XenbusStateConnected: if (dev->state == XenbusStateConnected) break; - backend_create_xenvif(be); if (be->vif) connect(be); break; case XenbusStateClosing: - if (be->vif) - kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); disconnect_backend(dev); xenbus_switch_state(dev, XenbusStateClosing); break; @@ -262,6 +268,7 @@ static void frontend_changed(struct xenbus_device *dev, xenbus_switch_state(dev, XenbusStateClosed); if (xenbus_dev_is_online(dev)) break; + destroy_backend(dev); /* fall through if not online */ case XenbusStateUnknown: device_unregister(&dev->dev); -- cgit v1.2.3-70-g09d2