diff options
Diffstat (limited to 'drivers/net/xen-netback')
| -rw-r--r-- | drivers/net/xen-netback/common.h | 47 | ||||
| -rw-r--r-- | drivers/net/xen-netback/interface.c | 78 | ||||
| -rw-r--r-- | drivers/net/xen-netback/netback.c | 480 | ||||
| -rw-r--r-- | drivers/net/xen-netback/xenbus.c | 3 |
4 files changed, 179 insertions, 429 deletions
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 08ae01b41c8..4c76bcb9a87 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -101,6 +101,13 @@ struct xenvif_rx_meta { #define MAX_PENDING_REQS 256 +/* It's possible for an skb to have a maximal number of frags + * but still be less than MAX_BUFFER_OFFSET in size. Thus the + * worst-case number of copy operations is MAX_SKB_FRAGS per + * ring slot. + */ +#define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE) + struct xenvif { /* Unique identifier for this interface. */ domid_t domid; @@ -136,20 +143,19 @@ struct xenvif { char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */ struct xen_netif_rx_back_ring rx; struct sk_buff_head rx_queue; - - /* Allow xenvif_start_xmit() to peek ahead in the rx request - * ring. This is a prediction of what rx_req_cons will be - * once all queued skbs are put on the ring. + bool rx_queue_stopped; + /* Set when the RX interrupt is triggered by the frontend. + * The worker thread may need to wake the queue. */ - RING_IDX rx_req_cons_peek; + bool rx_event; - /* Given MAX_BUFFER_OFFSET of 4096 the worst case is that each - * head/fragment page uses 2 copy operations because it - * straddles two buffers in the frontend. - */ - struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE]; - struct xenvif_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE]; + /* This array is allocated seperately as it is large */ + struct gnttab_copy *grant_copy_op; + /* We create one meta structure per ring request we consume, so + * the maximum number is the same as the ring size. + */ + struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE]; u8 fe_dev_addr[6]; @@ -198,8 +204,6 @@ void xenvif_xenbus_fini(void); int xenvif_schedulable(struct xenvif *vif); -int xenvif_rx_ring_full(struct xenvif *vif); - int xenvif_must_stop_queue(struct xenvif *vif); /* (Un)Map communication rings. */ @@ -211,21 +215,20 @@ int xenvif_map_frontend_rings(struct xenvif *vif, /* Check for SKBs from frontend and schedule backend processing */ void xenvif_check_rx_xenvif(struct xenvif *vif); -/* Queue an SKB for transmission to the frontend */ -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); - /* Prevent the device from generating any further traffic. */ void xenvif_carrier_off(struct xenvif *vif); -/* Returns number of ring slots required to send an skb to the frontend */ -unsigned int xenvif_count_skb_slots(struct xenvif *vif, struct sk_buff *skb); - int xenvif_tx_action(struct xenvif *vif, int budget); -void xenvif_rx_action(struct xenvif *vif); int xenvif_kthread(void *data); +void xenvif_kick_thread(struct xenvif *vif); + +/* Determine whether the needed number of slots (req) are available, + * and set req_event if not. + */ +bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed); + +void xenvif_stop_queue(struct xenvif *vif); extern bool separate_tx_rx_irq; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 2329cccf1fa..b9de31ea7fc 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -34,6 +34,7 @@ #include <linux/ethtool.h> #include <linux/rtnetlink.h> #include <linux/if_vlan.h> +#include <linux/vmalloc.h> #include <xen/events.h> #include <asm/xen/hypercall.h> @@ -46,11 +47,6 @@ int xenvif_schedulable(struct xenvif *vif) return netif_running(vif->dev) && netif_carrier_ok(vif->dev); } -static int xenvif_rx_schedulable(struct xenvif *vif) -{ - return xenvif_schedulable(vif) && !xenvif_rx_ring_full(vif); -} - static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id) { struct xenvif *vif = dev_id; @@ -104,8 +100,8 @@ static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id) { struct xenvif *vif = dev_id; - if (xenvif_rx_schedulable(vif)) - netif_wake_queue(vif->dev); + vif->rx_event = true; + xenvif_kick_thread(vif); return IRQ_HANDLED; } @@ -121,24 +117,35 @@ static irqreturn_t xenvif_interrupt(int irq, void *dev_id) static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); + int min_slots_needed; BUG_ON(skb->dev != dev); /* Drop the packet if vif is not ready */ - if (vif->task == NULL) + if (vif->task == NULL || !xenvif_schedulable(vif)) goto drop; - /* Drop the packet if the target domain has no receive buffers. */ - if (!xenvif_rx_schedulable(vif)) - goto drop; + /* At best we'll need one slot for the header and one for each + * frag. + */ + min_slots_needed = 1 + skb_shinfo(skb)->nr_frags; - /* Reserve ring slots for the worst-case number of fragments. */ - vif->rx_req_cons_peek += xenvif_count_skb_slots(vif, skb); + /* If the skb is GSO then we'll also need an extra slot for the + * metadata. + */ + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 || + skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + min_slots_needed++; - if (vif->can_queue && xenvif_must_stop_queue(vif)) - netif_stop_queue(dev); + /* If the skb can't possibly fit in the remaining slots + * then turn off the queue to give the ring a chance to + * drain. + */ + if (!xenvif_rx_ring_slots_available(vif, min_slots_needed)) + xenvif_stop_queue(vif); - xenvif_queue_tx_skb(vif, skb); + skb_queue_tail(&vif->rx_queue, skb); + xenvif_kick_thread(vif); return NETDEV_TX_OK; @@ -148,12 +155,6 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -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); @@ -307,6 +308,15 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, SET_NETDEV_DEV(dev, parent); vif = netdev_priv(dev); + + vif->grant_copy_op = vmalloc(sizeof(struct gnttab_copy) * + MAX_GRANT_COPY_OPS); + if (vif->grant_copy_op == NULL) { + pr_warn("Could not allocate grant copy space for %s\n", name); + free_netdev(dev); + return ERR_PTR(-ENOMEM); + } + vif->domid = domid; vif->handle = handle; vif->can_sg = 1; @@ -368,16 +378,18 @@ int xenvif_connect(struct xenvif *vif, 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; - /* Already connected through? */ - if (vif->tx_irq) - return 0; + BUG_ON(vif->tx_irq); + BUG_ON(vif->task); err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref); if (err < 0) goto err; + init_waitqueue_head(&vif->wq); + if (tx_evtchn == rx_evtchn) { /* feature-split-event-channels == 0 */ err = bind_interdomain_evtchn_to_irqhandler( @@ -410,15 +422,16 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, disable_irq(vif->rx_irq); } - init_waitqueue_head(&vif->wq); - vif->task = kthread_create(xenvif_kthread, - (void *)vif, "%s", vif->dev->name); - if (IS_ERR(vif->task)) { + task = kthread_create(xenvif_kthread, + (void *)vif, "%s", vif->dev->name); + if (IS_ERR(task)) { pr_warn("Could not allocate kthread for %s\n", vif->dev->name); - err = PTR_ERR(vif->task); + err = PTR_ERR(task); goto err_rx_unbind; } + vif->task = task; + rtnl_lock(); if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN) dev_set_mtu(vif->dev, ETH_DATA_LEN); @@ -461,8 +474,10 @@ void xenvif_disconnect(struct xenvif *vif) if (netif_carrier_ok(vif->dev)) xenvif_carrier_off(vif); - if (vif->task) + if (vif->task) { kthread_stop(vif->task); + vif->task = NULL; + } if (vif->tx_irq) { if (vif->tx_irq == vif->rx_irq) @@ -483,6 +498,7 @@ void xenvif_free(struct xenvif *vif) unregister_netdev(vif->dev); + vfree(vif->grant_copy_op); free_netdev(vif->dev); module_put(THIS_MODULE); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 919b6509455..6b62c3eb8e1 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -137,36 +137,26 @@ static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif) vif->pending_prod + vif->pending_cons; } -static int max_required_rx_slots(struct xenvif *vif) +bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed) { - int max = DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE); + RING_IDX prod, cons; - /* XXX FIXME: RX path dependent on MAX_SKB_FRAGS */ - if (vif->can_sg || vif->gso_mask || vif->gso_prefix_mask) - max += MAX_SKB_FRAGS + 1; /* extra_info + frags */ - - return max; -} - -int xenvif_rx_ring_full(struct xenvif *vif) -{ - RING_IDX peek = vif->rx_req_cons_peek; - RING_IDX needed = max_required_rx_slots(vif); + do { + prod = vif->rx.sring->req_prod; + cons = vif->rx.req_cons; - return ((vif->rx.sring->req_prod - peek) < needed) || - ((vif->rx.rsp_prod_pvt + XEN_NETIF_RX_RING_SIZE - peek) < needed); -} + if (prod - cons >= needed) + return true; -int xenvif_must_stop_queue(struct xenvif *vif) -{ - if (!xenvif_rx_ring_full(vif)) - return 0; + vif->rx.sring->req_event = prod + 1; - vif->rx.sring->req_event = vif->rx_req_cons_peek + - max_required_rx_slots(vif); - mb(); /* request notification /then/ check the queue */ + /* Make sure event is visible before we check prod + * again. + */ + mb(); + } while (vif->rx.sring->req_prod != prod); - return xenvif_rx_ring_full(vif); + return false; } /* @@ -209,93 +199,6 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head) return false; } -struct xenvif_count_slot_state { - unsigned long copy_off; - bool head; -}; - -unsigned int xenvif_count_frag_slots(struct xenvif *vif, - unsigned long offset, unsigned long size, - struct xenvif_count_slot_state *state) -{ - unsigned count = 0; - - offset &= ~PAGE_MASK; - - while (size > 0) { - unsigned long bytes; - - bytes = PAGE_SIZE - offset; - - if (bytes > size) - bytes = size; - - if (start_new_rx_buffer(state->copy_off, bytes, state->head)) { - count++; - state->copy_off = 0; - } - - if (state->copy_off + bytes > MAX_BUFFER_OFFSET) - bytes = MAX_BUFFER_OFFSET - state->copy_off; - - state->copy_off += bytes; - - offset += bytes; - size -= bytes; - - if (offset == PAGE_SIZE) - offset = 0; - - state->head = false; - } - - return count; -} - -/* - * 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 - * xenvif_gop_frag_copy. - */ -unsigned int xenvif_count_skb_slots(struct xenvif *vif, struct sk_buff *skb) -{ - struct xenvif_count_slot_state state; - unsigned int count; - unsigned char *data; - unsigned i; - - state.head = true; - state.copy_off = 0; - - /* Slot for the first (partial) page of data. */ - count = 1; - - /* Need a slot for the GSO prefix for GSO extra data? */ - if (skb_shinfo(skb)->gso_size) - count++; - - data = skb->data; - while (data < skb_tail_pointer(skb)) { - unsigned long offset = offset_in_page(data); - unsigned long size = PAGE_SIZE - offset; - - if (data + size > skb_tail_pointer(skb)) - size = skb_tail_pointer(skb) - data; - - count += xenvif_count_frag_slots(vif, offset, size, &state); - - data += size; - } - - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - unsigned long size = skb_frag_size(&skb_shinfo(skb)->frags[i]); - unsigned long offset = skb_shinfo(skb)->frags[i].page_offset; - - count += xenvif_count_frag_slots(vif, offset, size, &state); - } - return count; -} - struct netrx_pending_operations { unsigned copy_prod, copy_cons; unsigned meta_prod, meta_cons; @@ -451,7 +354,7 @@ static int xenvif_gop_skb(struct sk_buff *skb, } /* Set up a GSO prefix descriptor, if necessary */ - if ((1 << skb_shinfo(skb)->gso_type) & vif->gso_prefix_mask) { + if ((1 << gso_type) & vif->gso_prefix_mask) { req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); meta = npo->meta + npo->meta_prod++; meta->gso_type = gso_type; @@ -556,12 +459,12 @@ struct skb_cb_overlay { int meta_slots_used; }; -static void xenvif_kick_thread(struct xenvif *vif) +void xenvif_kick_thread(struct xenvif *vif) { wake_up(&vif->wq); } -void xenvif_rx_action(struct xenvif *vif) +static void xenvif_rx_action(struct xenvif *vif) { s8 status; u16 flags; @@ -570,11 +473,10 @@ void xenvif_rx_action(struct xenvif *vif) struct sk_buff *skb; LIST_HEAD(notify); int ret; - int nr_frags; - int count; unsigned long offset; struct skb_cb_overlay *sco; - int need_to_notify = 0; + bool need_to_notify = false; + bool ring_full = false; struct netrx_pending_operations npo = { .copy = vif->grant_copy_op, @@ -583,38 +485,54 @@ void xenvif_rx_action(struct xenvif *vif) skb_queue_head_init(&rxq); - count = 0; - while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) { - vif = netdev_priv(skb->dev); - nr_frags = skb_shinfo(skb)->nr_frags; + int max_slots_needed; + int i; + + /* We need a cheap worse case estimate for the number of + * slots we'll use. + */ + + max_slots_needed = DIV_ROUND_UP(offset_in_page(skb->data) + + skb_headlen(skb), + PAGE_SIZE); + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + unsigned int size; + size = skb_frag_size(&skb_shinfo(skb)->frags[i]); + max_slots_needed += DIV_ROUND_UP(size, PAGE_SIZE); + } + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 || + skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + max_slots_needed++; + + /* If the skb may not fit then bail out now */ + if (!xenvif_rx_ring_slots_available(vif, max_slots_needed)) { + skb_queue_head(&vif->rx_queue, skb); + need_to_notify = true; + ring_full = true; + break; + } sco = (struct skb_cb_overlay *)skb->cb; sco->meta_slots_used = xenvif_gop_skb(skb, &npo); - - count += nr_frags + 1; + BUG_ON(sco->meta_slots_used > max_slots_needed); __skb_queue_tail(&rxq, skb); - - /* Filled the batch queue? */ - /* XXX FIXME: RX path dependent on MAX_SKB_FRAGS */ - if (count + MAX_SKB_FRAGS >= XEN_NETIF_RX_RING_SIZE) - break; } BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta)); + vif->rx_queue_stopped = !npo.copy_prod && ring_full; + if (!npo.copy_prod) - return; + goto done; - BUG_ON(npo.copy_prod > ARRAY_SIZE(vif->grant_copy_op)); + BUG_ON(npo.copy_prod > MAX_GRANT_COPY_OPS); gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod); while ((skb = __skb_dequeue(&rxq)) != NULL) { sco = (struct skb_cb_overlay *)skb->cb; - vif = netdev_priv(skb->dev); - if ((1 << vif->meta[npo.meta_cons].gso_type) & vif->gso_prefix_mask) { resp = RING_GET_RESPONSE(&vif->rx, @@ -677,28 +595,15 @@ void xenvif_rx_action(struct xenvif *vif) RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret); - if (ret) - need_to_notify = 1; - - xenvif_notify_tx_completion(vif); + need_to_notify |= !!ret; npo.meta_cons += sco->meta_slots_used; dev_kfree_skb(skb); } +done: if (need_to_notify) notify_remote_via_irq(vif->rx_irq); - - /* More work to do? */ - if (!skb_queue_empty(&vif->rx_queue)) - xenvif_kick_thread(vif); -} - -void xenvif_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb) -{ - skb_queue_tail(&vif->rx_queue, skb); - - xenvif_kick_thread(vif); } void xenvif_check_rx_xenvif(struct xenvif *vif) @@ -1140,220 +1045,14 @@ static int xenvif_set_skb_gso(struct xenvif *vif, } skb_shinfo(skb)->gso_size = gso->u.gso.size; - - /* Header must be checked, and gso_segs computed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + /* gso_segs will be calculated later */ return 0; } -static inline void maybe_pull_tail(struct sk_buff *skb, unsigned int len) -{ - if (skb_is_nonlinear(skb) && skb_headlen(skb) < len) { - /* If we need to pullup then pullup to the max, so we - * won't need to do it again. - */ - int target = min_t(int, skb->len, MAX_TCP_HEADER); - __pskb_pull_tail(skb, target - skb_headlen(skb)); - } -} - -static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb, - int recalculate_partial_csum) -{ - struct iphdr *iph = (void *)skb->data; - unsigned int header_size; - unsigned int off; - int err = -EPROTO; - - off = sizeof(struct iphdr); - - header_size = skb->network_header + off + MAX_IPOPTLEN; - maybe_pull_tail(skb, header_size); - - off = iph->ihl * 4; - - switch (iph->protocol) { - case IPPROTO_TCP: - if (!skb_partial_csum_set(skb, off, - offsetof(struct tcphdr, check))) - goto out; - - if (recalculate_partial_csum) { - struct tcphdr *tcph = tcp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct tcphdr); - maybe_pull_tail(skb, header_size); - - tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - off, - IPPROTO_TCP, 0); - } - break; - case IPPROTO_UDP: - if (!skb_partial_csum_set(skb, off, - offsetof(struct udphdr, check))) - goto out; - - if (recalculate_partial_csum) { - struct udphdr *udph = udp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct udphdr); - maybe_pull_tail(skb, header_size); - - udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - off, - IPPROTO_UDP, 0); - } - break; - default: - if (net_ratelimit()) - netdev_err(vif->dev, - "Attempting to checksum a non-TCP/UDP packet, " - "dropping a protocol %d packet\n", - iph->protocol); - goto out; - } - - err = 0; - -out: - return err; -} - -static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb, - int recalculate_partial_csum) -{ - int err = -EPROTO; - struct ipv6hdr *ipv6h = (void *)skb->data; - u8 nexthdr; - unsigned int header_size; - unsigned int off; - bool fragment; - bool done; - - done = false; - - off = sizeof(struct ipv6hdr); - - header_size = skb->network_header + off; - maybe_pull_tail(skb, header_size); - - nexthdr = ipv6h->nexthdr; - - while ((off <= sizeof(struct ipv6hdr) + ntohs(ipv6h->payload_len)) && - !done) { - switch (nexthdr) { - case IPPROTO_DSTOPTS: - case IPPROTO_HOPOPTS: - case IPPROTO_ROUTING: { - struct ipv6_opt_hdr *hp = (void *)(skb->data + off); - - header_size = skb->network_header + - off + - sizeof(struct ipv6_opt_hdr); - maybe_pull_tail(skb, header_size); - - nexthdr = hp->nexthdr; - off += ipv6_optlen(hp); - break; - } - case IPPROTO_AH: { - struct ip_auth_hdr *hp = (void *)(skb->data + off); - - header_size = skb->network_header + - off + - sizeof(struct ip_auth_hdr); - maybe_pull_tail(skb, header_size); - - nexthdr = hp->nexthdr; - off += (hp->hdrlen+2)<<2; - break; - } - case IPPROTO_FRAGMENT: - fragment = true; - /* fall through */ - default: - done = true; - break; - } - } - - if (!done) { - if (net_ratelimit()) - netdev_err(vif->dev, "Failed to parse packet header\n"); - goto out; - } - - if (fragment) { - if (net_ratelimit()) - netdev_err(vif->dev, "Packet is a fragment!\n"); - goto out; - } - - switch (nexthdr) { - case IPPROTO_TCP: - if (!skb_partial_csum_set(skb, off, - offsetof(struct tcphdr, check))) - goto out; - - if (recalculate_partial_csum) { - struct tcphdr *tcph = tcp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct tcphdr); - maybe_pull_tail(skb, header_size); - - tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, - &ipv6h->daddr, - skb->len - off, - IPPROTO_TCP, 0); - } - break; - case IPPROTO_UDP: - if (!skb_partial_csum_set(skb, off, - offsetof(struct udphdr, check))) - goto out; - - if (recalculate_partial_csum) { - struct udphdr *udph = udp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct udphdr); - maybe_pull_tail(skb, header_size); - - udph->check = ~csum_ipv6_magic(&ipv6h->saddr, - &ipv6h->daddr, - skb->len - off, - IPPROTO_UDP, 0); - } - break; - default: - if (net_ratelimit()) - netdev_err(vif->dev, - "Attempting to checksum a non-TCP/UDP packet, " - "dropping a protocol %d packet\n", - nexthdr); - goto out; - } - - err = 0; - -out: - return err; -} - static int checksum_setup(struct xenvif *vif, struct sk_buff *skb) { - int err = -EPROTO; - int recalculate_partial_csum = 0; + bool recalculate_partial_csum = false; /* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy * peers can fail to set NETRXF_csum_blank when sending a GSO @@ -1363,19 +1062,14 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb) if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) { vif->rx_gso_checksum_fixup++; skb->ip_summed = CHECKSUM_PARTIAL; - recalculate_partial_csum = 1; + recalculate_partial_csum = true; } /* A non-CHECKSUM_PARTIAL SKB does not require setup. */ if (skb->ip_summed != CHECKSUM_PARTIAL) return 0; - if (skb->protocol == htons(ETH_P_IP)) - err = checksum_setup_ip(vif, skb, recalculate_partial_csum); - else if (skb->protocol == htons(ETH_P_IPV6)) - err = checksum_setup_ipv6(vif, skb, recalculate_partial_csum); - - return err; + return skb_checksum_setup(skb, recalculate_partial_csum); } static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) @@ -1410,14 +1104,15 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) return false; } -static unsigned xenvif_tx_build_gops(struct xenvif *vif) +static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) { struct gnttab_copy *gop = vif->tx_copy_ops, *request_gop; struct sk_buff *skb; int ret; while ((nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX - < MAX_PENDING_REQS)) { + < MAX_PENDING_REQS) && + (skb_queue_len(&vif->tx_queue) < budget)) { struct xen_netif_tx_request txreq; struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX]; struct page *page; @@ -1439,7 +1134,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif) continue; } - RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do); + work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx); if (!work_to_do) break; @@ -1579,14 +1274,13 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif) } -static int xenvif_tx_submit(struct xenvif *vif, int budget) +static int xenvif_tx_submit(struct xenvif *vif) { struct gnttab_copy *gop = vif->tx_copy_ops; struct sk_buff *skb; int work_done = 0; - while (work_done < budget && - (skb = __skb_dequeue(&vif->tx_queue)) != NULL) { + while ((skb = __skb_dequeue(&vif->tx_queue)) != NULL) { struct xen_netif_tx_request *txp; u16 pending_idx; unsigned data_len; @@ -1641,6 +1335,20 @@ static int xenvif_tx_submit(struct xenvif *vif, int budget) skb_probe_transport_header(skb, 0); + /* If the packet is GSO then we will have just set up the + * transport header offset in checksum_setup so it's now + * straightforward to calculate gso_segs. + */ + if (skb_is_gso(skb)) { + int mss = skb_shinfo(skb)->gso_size; + int hdrlen = skb_transport_header(skb) - + skb_mac_header(skb) + + tcp_hdrlen(skb); + + skb_shinfo(skb)->gso_segs = + DIV_ROUND_UP(skb->len - hdrlen, mss); + } + vif->dev->stats.rx_bytes += skb->len; vif->dev->stats.rx_packets++; @@ -1661,14 +1369,14 @@ int xenvif_tx_action(struct xenvif *vif, int budget) if (unlikely(!tx_work_todo(vif))) return 0; - nr_gops = xenvif_tx_build_gops(vif); + nr_gops = xenvif_tx_build_gops(vif, budget); if (nr_gops == 0) return 0; gnttab_batch_copy(vif->tx_copy_ops, nr_gops); - work_done = xenvif_tx_submit(vif, nr_gops); + work_done = xenvif_tx_submit(vif); return work_done; } @@ -1765,7 +1473,8 @@ static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif, static inline int rx_work_todo(struct xenvif *vif) { - return !skb_queue_empty(&vif->rx_queue); + return (!skb_queue_empty(&vif->rx_queue) && !vif->rx_queue_stopped) || + vif->rx_event; } static inline int tx_work_todo(struct xenvif *vif) @@ -1815,8 +1524,6 @@ int xenvif_map_frontend_rings(struct xenvif *vif, rxs = (struct xen_netif_rx_sring *)addr; BACK_RING_INIT(&vif->rx, rxs, PAGE_SIZE); - vif->rx_req_cons_peek = 0; - return 0; err: @@ -1824,9 +1531,24 @@ err: return err; } +void xenvif_stop_queue(struct xenvif *vif) +{ + if (!vif->can_queue) + return; + + netif_stop_queue(vif->dev); +} + +static void xenvif_start_queue(struct xenvif *vif) +{ + if (xenvif_schedulable(vif)) + netif_wake_queue(vif->dev); +} + int xenvif_kthread(void *data) { struct xenvif *vif = data; + struct sk_buff *skb; while (!kthread_should_stop()) { wait_event_interruptible(vif->wq, @@ -1835,12 +1557,22 @@ int xenvif_kthread(void *data) if (kthread_should_stop()) break; - if (rx_work_todo(vif)) + if (!skb_queue_empty(&vif->rx_queue)) xenvif_rx_action(vif); + vif->rx_event = false; + + if (skb_queue_empty(&vif->rx_queue) && + netif_queue_stopped(vif->dev)) + xenvif_start_queue(vif); + cond_resched(); } + /* Bin any remaining skbs */ + while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) + dev_kfree_skb(skb); + return 0; } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index f0358992b04..7a206cffb06 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -15,8 +15,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "common.h" |